* [PATCH 0/2] powerpc: Remove support for ppc405/440 Xilinx platforms
From: Michal Simek @ 2020-03-27 12:12 UTC (permalink / raw)
To: linux-kernel, monstr, michal.simek, git, sfr, marc.zyngier
Cc: Kate Stewart, Mark Rutland, Desnes A. Nunes do Rosario,
Geert Uytterhoeven, linux-doc, alsa-devel, dri-devel,
Jaroslav Kysela, Richard Fontana, Paul Mackerras, Miquel Raynal,
Mauro Carvalho Chehab, Fabio Estevam, Sasha Levin,
Jonathan Corbet, Masahiro Yamada, YueHaibing, Krzysztof Kozlowski,
linux-arm-kernel, Leonardo Bras, devicetree, Andrew Donnellan,
Arnd Bergmann, Bartlomiej Zolnierkiewicz, Alistair Popple,
linuxppc-dev, Nicholas Piggin, Alexios Zavras, Mark Brown,
linux-fbdev, Jonathan Cameron, Thomas Gleixner, Andy Shevchenko,
Allison Randal, Wei Hu, Greg Kroah-Hartman, Nick Desaulniers,
Takashi Iwai, Armijn Hemel, Rob Herring, Enrico Weigelt,
David S. Miller, Thiago Jung Bauermann
Hi,
recently we wanted to update xilinx intc driver and we found that function
which we wanted to remove is still wired by ancient Xilinx PowerPC
platforms. Here is the thread about it.
https://lore.kernel.org/linux-next/48d3232d-0f1d-42ea-3109-f44bbabfa2e8@xilinx.com/
I have been talking about it internally and there is no interest in these
platforms and it is also orphan for quite a long time. None is really
running/testing these platforms regularly that's why I think it makes sense
to remove them also with drivers which are specific to this platform.
U-Boot support was removed in 2017 without anybody complain about it
https://github.com/Xilinx/u-boot-xlnx/commit/98f705c9cefdfdba62c069821bbba10273a0a8ed
Based on current ppc/next.
If anyone has any objection about it, please let me know.
Thanks,
Michal
Michal Simek (2):
sound: ac97: Remove sound driver for ancient platform
powerpc: Remove Xilinx PPC405/PPC440 support
Documentation/devicetree/bindings/xilinx.txt | 143 --
Documentation/powerpc/bootwrapper.rst | 28 +-
MAINTAINERS | 6 -
arch/powerpc/Kconfig.debug | 2 +-
arch/powerpc/boot/Makefile | 7 +-
arch/powerpc/boot/dts/Makefile | 1 -
arch/powerpc/boot/dts/virtex440-ml507.dts | 406 ------
arch/powerpc/boot/dts/virtex440-ml510.dts | 466 -------
arch/powerpc/boot/ops.h | 1 -
arch/powerpc/boot/serial.c | 5 -
arch/powerpc/boot/uartlite.c | 79 --
arch/powerpc/boot/virtex.c | 97 --
arch/powerpc/boot/virtex405-head.S | 31 -
arch/powerpc/boot/wrapper | 8 -
arch/powerpc/configs/40x/virtex_defconfig | 75 -
arch/powerpc/configs/44x/virtex5_defconfig | 74 -
arch/powerpc/configs/ppc40x_defconfig | 8 -
arch/powerpc/configs/ppc44x_defconfig | 8 -
arch/powerpc/include/asm/xilinx_intc.h | 16 -
arch/powerpc/include/asm/xilinx_pci.h | 21 -
arch/powerpc/kernel/cputable.c | 39 -
arch/powerpc/platforms/40x/Kconfig | 31 -
arch/powerpc/platforms/40x/Makefile | 1 -
arch/powerpc/platforms/40x/virtex.c | 54 -
arch/powerpc/platforms/44x/Kconfig | 37 -
arch/powerpc/platforms/44x/Makefile | 2 -
arch/powerpc/platforms/44x/virtex.c | 60 -
arch/powerpc/platforms/44x/virtex_ml510.c | 30 -
arch/powerpc/platforms/Kconfig | 4 -
arch/powerpc/sysdev/Makefile | 2 -
arch/powerpc/sysdev/xilinx_intc.c | 88 --
arch/powerpc/sysdev/xilinx_pci.c | 132 --
arch/powerpc/xmon/ppc-dis.c | 6 -
arch/powerpc/xmon/ppc-opc.c | 23 -
arch/powerpc/xmon/ppc.h | 5 -
drivers/char/Kconfig | 2 +-
drivers/video/fbdev/Kconfig | 2 +-
sound/drivers/Kconfig | 12 -
sound/drivers/Makefile | 2 -
sound/drivers/ml403-ac97cr.c | 1298 ------------------
40 files changed, 7 insertions(+), 3305 deletions(-)
delete mode 100644 arch/powerpc/boot/dts/virtex440-ml507.dts
delete mode 100644 arch/powerpc/boot/dts/virtex440-ml510.dts
delete mode 100644 arch/powerpc/boot/uartlite.c
delete mode 100644 arch/powerpc/boot/virtex.c
delete mode 100644 arch/powerpc/boot/virtex405-head.S
delete mode 100644 arch/powerpc/configs/40x/virtex_defconfig
delete mode 100644 arch/powerpc/configs/44x/virtex5_defconfig
delete mode 100644 arch/powerpc/include/asm/xilinx_intc.h
delete mode 100644 arch/powerpc/include/asm/xilinx_pci.h
delete mode 100644 arch/powerpc/platforms/40x/virtex.c
delete mode 100644 arch/powerpc/platforms/44x/virtex.c
delete mode 100644 arch/powerpc/platforms/44x/virtex_ml510.c
delete mode 100644 arch/powerpc/sysdev/xilinx_intc.c
delete mode 100644 arch/powerpc/sysdev/xilinx_pci.c
delete mode 100644 sound/drivers/ml403-ac97cr.c
--
2.26.0
^ permalink raw reply
* Re: [PATCH v3] powerpc/perf: Use SIER_USER_MASK while updating SPRN_SIER for EBB events
From: Athira Rajeev @ 2020-03-27 11:53 UTC (permalink / raw)
To: Michael Ellerman; +Cc: maddy, linuxppc-dev
In-Reply-To: <87r1xod3c3.fsf@mpe.ellerman.id.au>
> On 19-Mar-2020, at 4:22 PM, Michael Ellerman <mpe@ellerman.id.au> wrote:
>
> Hi Athira,
>
> Athira Rajeev <atrajeev@linux.vnet.ibm.com> writes:
>> Sampled Instruction Event Register (SIER), is a PMU register,
> ^
> that
>> captures architecture state for a given sample. And sier_user_mask
> ^ ^
> don't think we need "architecture" SIER_USER_MASK
>
>> defined in commit 330a1eb7775b ("powerpc/perf: Core EBB support for 64-bit
>> book3s") defines the architected bits that needs to be saved from the SPR.
>
> Not quite, it defines the bits that are visible to userspace.
>
> And I think it's true that for EBB events the bits we need/want to save
> are only the user visible bits.
>
>> Currently all of the bits from SIER are saved for EBB events. Patch fixes
>> this by ANDing the "sier_user_mask" to data from SIER in ebb_switch_out().
>> This will force save only architected bits from the SIER.
>
> s/architected/user visible/
>
>
> But, why does it matter? The kernel saves the user visible bits, as well
> as the kernel-only bits into the thread struct. And then later the
> kernel restores that value into the hardware before returning to
> userspace.
>
> But the hardware enforces the visibility of the bits, so userspace can't
> observe any bits that it shouldn't.
>
> Or is there some other mechanism whereby userspace can see those bits? ;)
>
> If there was, what would the security implications of that be?
Hi Michael,
Thanks for your comments.
In ebb_switch_in, we set PMCC bit [MMCR0 44:45 ] to 10 which means SIER ( Group B ) register is readable in problem state. Hence the intention of the patch was to make sure we are not exposing the bits which the userspace shouldn't be reading.
But following your comment about "hardware enforcing the visibility of bits", I did try an "ebb" experiment which showed that reading SPRN_SIER didn't expose any bits other than the user visible bits. Sorry for the confusion here.
In that case, Can we drop the existing definition of SIER_USER_MASK if it is no more needed ?
Thanks
Athira
>
> cheers
>
>> Fixes: 330a1eb7775b ("powerpc/perf: Core EBB support for 64-bit book3s")
>> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
>> ---
>> Changelog:
>> v2 -> v3:
>> - Corrected name of SIER register in commit message
>> as pointed by Segher Boessenkool
>> v1 -> v2:
>> - Make the commit message more clearer.
>>
>> arch/powerpc/perf/core-book3s.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
>> index 3086055..48b61cc 100644
>> --- a/arch/powerpc/perf/core-book3s.c
>> +++ b/arch/powerpc/perf/core-book3s.c
>> @@ -579,7 +579,7 @@ static void ebb_switch_out(unsigned long mmcr0)
>> return;
>>
>> current->thread.siar = mfspr(SPRN_SIAR);
>> - current->thread.sier = mfspr(SPRN_SIER);
>> + current->thread.sier = mfspr(SPRN_SIER) & SIER_USER_MASK;
>> current->thread.sdar = mfspr(SPRN_SDAR);
>> current->thread.mmcr0 = mmcr0 & MMCR0_USER_MASK;
>> current->thread.mmcr2 = mfspr(SPRN_MMCR2) & MMCR2_USER_MASK;
>> --
>> 1.8.3.1
^ permalink raw reply
* [PATCH v4 4/6] powerpc/sysfs: Show idle_purr and idle_spurr for every CPU
From: Gautham R. Shenoy @ 2020-03-27 11:32 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
In-Reply-To: <1585308760-28792-1-git-send-email-ego@linux.vnet.ibm.com>
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
On Pseries LPARs, to calculate utilization, we need to know the
[S]PURR ticks when the CPUs were busy or idle.
The total PURR and SPURR ticks are already exposed via the per-cpu
sysfs files "purr" and "spurr". This patch adds support for exposing
the idle PURR and SPURR ticks via new per-cpu sysfs files named
"idle_purr" and "idle_spurr".
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/kernel/sysfs.c | 82 +++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 79 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 479c706..571b325 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -19,6 +19,7 @@
#include <asm/smp.h>
#include <asm/pmc.h>
#include <asm/firmware.h>
+#include <asm/idle.h>
#include <asm/svm.h>
#include "cacheinfo.h"
@@ -760,6 +761,74 @@ static void create_svm_file(void)
}
#endif /* CONFIG_PPC_SVM */
+#ifdef CONFIG_PPC_PSERIES
+static void read_idle_purr(void *val)
+{
+ u64 *ret = val;
+
+ *ret = read_this_idle_purr();
+}
+
+static ssize_t idle_purr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ u64 val;
+
+ smp_call_function_single(cpu->dev.id, read_idle_purr, &val, 1);
+ return sprintf(buf, "%llx\n", val);
+}
+static DEVICE_ATTR(idle_purr, 0400, idle_purr_show, NULL);
+
+static void create_idle_purr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_create_file(s, &dev_attr_idle_purr);
+}
+
+static void remove_idle_purr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_remove_file(s, &dev_attr_idle_purr);
+}
+
+static void read_idle_spurr(void *val)
+{
+ u64 *ret = val;
+
+ *ret = read_this_idle_spurr();
+}
+
+static ssize_t idle_spurr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ u64 val;
+
+ smp_call_function_single(cpu->dev.id, read_idle_spurr, &val, 1);
+ return sprintf(buf, "%llx\n", val);
+}
+static DEVICE_ATTR(idle_spurr, 0400, idle_spurr_show, NULL);
+
+static void create_idle_spurr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_create_file(s, &dev_attr_idle_spurr);
+}
+
+static void remove_idle_spurr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_remove_file(s, &dev_attr_idle_spurr);
+}
+
+#else /* CONFIG_PPC_PSERIES */
+#define create_idle_purr_file(s)
+#define remove_idle_purr_file(s)
+#define create_idle_spurr_file(s)
+#define remove_idle_spurr_file(s)
+#endif /* CONFIG_PPC_PSERIES */
+
static int register_cpu_online(unsigned int cpu)
{
struct cpu *c = &per_cpu(cpu_devices, cpu);
@@ -823,10 +892,13 @@ static int register_cpu_online(unsigned int cpu)
if (!firmware_has_feature(FW_FEATURE_LPAR))
add_write_permission_dev_attr(&dev_attr_purr);
device_create_file(s, &dev_attr_purr);
+ create_idle_purr_file(s);
}
- if (cpu_has_feature(CPU_FTR_SPURR))
+ if (cpu_has_feature(CPU_FTR_SPURR)) {
device_create_file(s, &dev_attr_spurr);
+ create_idle_spurr_file(s);
+ }
if (cpu_has_feature(CPU_FTR_DSCR))
device_create_file(s, &dev_attr_dscr);
@@ -910,11 +982,15 @@ static int unregister_cpu_online(unsigned int cpu)
device_remove_file(s, &dev_attr_mmcra);
#endif /* CONFIG_PMU_SYSFS */
- if (cpu_has_feature(CPU_FTR_PURR))
+ if (cpu_has_feature(CPU_FTR_PURR)) {
device_remove_file(s, &dev_attr_purr);
+ remove_idle_purr_file(s);
+ }
- if (cpu_has_feature(CPU_FTR_SPURR))
+ if (cpu_has_feature(CPU_FTR_SPURR)) {
device_remove_file(s, &dev_attr_spurr);
+ remove_idle_spurr_file(s);
+ }
if (cpu_has_feature(CPU_FTR_DSCR))
device_remove_file(s, &dev_attr_dscr);
--
1.9.4
^ permalink raw reply related
* [PATCH v4 6/6] pseries/sysfs: Minimise IPI noise while reading [idle_][s]purr
From: Gautham R. Shenoy @ 2020-03-27 11:32 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
In-Reply-To: <1585308760-28792-1-git-send-email-ego@linux.vnet.ibm.com>
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Currently purr, spurr, idle_purr, idle_spurr are exposed for every CPU
via the sysfs interface
/sys/devices/system/cpu/cpuX/[idle_][s]purr. Each sysfs read currently
generates an IPI to obtain the desired value from the target CPU X.
Since these aforementioned sysfs are typically read one after another,
we end up generating 4 IPIs per CPU in a short duration.
In order to minimize the IPI noise, this patch caches the values of
all the four entities whenever one of them is read. If subsequently
any of these are read within the next 10ms, the cached value is
returned. With this, we will generate at most one IPI every 10ms for
every CPU.
Test-results: While reading the four sysfs files back-to-back for a
given CPU every second for 100 seconds.
Without the patch:
16 [XICS 2 Edge IPI] = 422 times
DBL [Doorbell interrupts] = 13 times
Total : 435 IPIs.
With the patch:
16 [XICS 2 Edge IPI] = 111 times
DBL [Doorbell interrupts] = 17 times
Total : 128 IPIs.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/kernel/sysfs.c | 117 ++++++++++++++++++++++++++++++++++++--------
1 file changed, 97 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 571b325..bd92023 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -586,8 +586,6 @@ void ppc_enable_pmcs(void)
* SPRs which are not related to PMU.
*/
#ifdef CONFIG_PPC64
-SYSFS_SPRSETUP(purr, SPRN_PURR);
-SYSFS_SPRSETUP(spurr, SPRN_SPURR);
SYSFS_SPRSETUP(pir, SPRN_PIR);
SYSFS_SPRSETUP(tscr, SPRN_TSCR);
@@ -596,8 +594,6 @@ void ppc_enable_pmcs(void)
enable write when needed with a separate function.
Lets be conservative and default to pseries.
*/
-static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
-static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
static DEVICE_ATTR(pir, 0400, show_pir, NULL);
static DEVICE_ATTR(tscr, 0600, show_tscr, store_tscr);
#endif /* CONFIG_PPC64 */
@@ -761,22 +757,110 @@ static void create_svm_file(void)
}
#endif /* CONFIG_PPC_SVM */
+#ifdef CONFIG_PPC64
+/*
+ * The duration (in ms) from the last IPI to the target CPU until
+ * which a cached value of purr, spurr, idle_purr, idle_spurr can be
+ * reported to the user on a corresponding sysfs file read. Beyond
+ * this duration, fresh values need to be obtained by sending IPIs to
+ * the target CPU when the sysfs files are read.
+ */
+static unsigned long util_stats_staleness_tolerance_ms = 10;
+struct util_acct_stats {
+ u64 latest_purr;
+ u64 latest_spurr;
+#ifdef CONFIG_PPC_PSERIES
+ u64 latest_idle_purr;
+ u64 latest_idle_spurr;
+#endif
+ unsigned long last_update_jiffies;
+};
+
+DEFINE_PER_CPU(struct util_acct_stats, util_acct_stats);
+
+static void update_util_acct_stats(void *ptr)
+{
+ struct util_acct_stats *stats = ptr;
+
+ stats->latest_purr = mfspr(SPRN_PURR);
+ stats->latest_spurr = mfspr(SPRN_SPURR);
#ifdef CONFIG_PPC_PSERIES
-static void read_idle_purr(void *val)
+ stats->latest_idle_purr = read_this_idle_purr();
+ stats->latest_idle_spurr = read_this_idle_spurr();
+#endif
+ stats->last_update_jiffies = jiffies;
+}
+
+struct util_acct_stats *get_util_stats_ptr(int cpu)
+{
+ struct util_acct_stats *stats = per_cpu_ptr(&util_acct_stats, cpu);
+ unsigned long delta_jiffies;
+
+ delta_jiffies = jiffies - stats->last_update_jiffies;
+
+ /*
+ * If we have a recent enough data, reuse that instead of
+ * sending an IPI.
+ */
+ if (jiffies_to_msecs(delta_jiffies) < util_stats_staleness_tolerance_ms)
+ return stats;
+
+ smp_call_function_single(cpu, update_util_acct_stats, stats, 1);
+ return stats;
+}
+
+static ssize_t show_purr(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
- u64 *ret = val;
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ struct util_acct_stats *stats;
- *ret = read_this_idle_purr();
+ stats = get_util_stats_ptr(cpu->dev.id);
+ return sprintf(buf, "%llx\n", stats->latest_purr);
}
+static void write_purr(void *val)
+{
+ mtspr(SPRN_PURR, *(unsigned long *)val);
+}
+
+static ssize_t __used store_purr(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ unsigned long val;
+ int ret = kstrtoul(buf, 16, &val);
+
+ if (ret != 0)
+ return -EINVAL;
+
+ smp_call_function_single(cpu->dev.id, write_purr, &val, 1);
+ return count;
+}
+static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
+
+static ssize_t show_spurr(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ struct util_acct_stats *stats;
+
+ stats = get_util_stats_ptr(cpu->dev.id);
+ return sprintf(buf, "%llx\n", stats->latest_spurr);
+}
+static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
+#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_PPC_PSERIES
static ssize_t idle_purr_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct cpu *cpu = container_of(dev, struct cpu, dev);
- u64 val;
+ struct util_acct_stats *stats;
- smp_call_function_single(cpu->dev.id, read_idle_purr, &val, 1);
- return sprintf(buf, "%llx\n", val);
+ stats = get_util_stats_ptr(cpu->dev.id);
+ return sprintf(buf, "%llx\n", stats->latest_idle_purr);
}
static DEVICE_ATTR(idle_purr, 0400, idle_purr_show, NULL);
@@ -792,21 +876,14 @@ static void remove_idle_purr_file(struct device *s)
device_remove_file(s, &dev_attr_idle_purr);
}
-static void read_idle_spurr(void *val)
-{
- u64 *ret = val;
-
- *ret = read_this_idle_spurr();
-}
-
static ssize_t idle_spurr_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct cpu *cpu = container_of(dev, struct cpu, dev);
- u64 val;
+ struct util_acct_stats *stats;
- smp_call_function_single(cpu->dev.id, read_idle_spurr, &val, 1);
- return sprintf(buf, "%llx\n", val);
+ stats = get_util_stats_ptr(cpu->dev.id);
+ return sprintf(buf, "%llx\n", stats->latest_idle_spurr);
}
static DEVICE_ATTR(idle_spurr, 0400, idle_spurr_show, NULL);
--
1.9.4
^ permalink raw reply related
* [PATCH v4 5/6] Documentation: Document sysfs interfaces purr, spurr, idle_purr, idle_spurr
From: Gautham R. Shenoy @ 2020-03-27 11:32 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
In-Reply-To: <1585308760-28792-1-git-send-email-ego@linux.vnet.ibm.com>
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Add documentation for the following sysfs interfaces:
/sys/devices/system/cpu/cpuX/purr
/sys/devices/system/cpu/cpuX/spurr
/sys/devices/system/cpu/cpuX/idle_purr
/sys/devices/system/cpu/cpuX/idle_spurr
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
Documentation/ABI/testing/sysfs-devices-system-cpu | 39 ++++++++++++++++++++++
1 file changed, 39 insertions(+)
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 2e0e3b4..bc07677 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -580,3 +580,42 @@ Description: Secure Virtual Machine
If 1, it means the system is using the Protected Execution
Facility in POWER9 and newer processors. i.e., it is a Secure
Virtual Machine.
+
+What: /sys/devices/system/cpu/cpuX/purr
+Date: Apr 2005
+Contact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
+Description: PURR ticks for this CPU since the system boot.
+
+ The Processor Utilization Resources Register (PURR) is
+ a 64-bit counter which provides an estimate of the
+ resources used by the CPU thread. The contents of this
+ register increases monotonically. This sysfs interface
+ exposes the number of PURR ticks for cpuX.
+
+What: /sys/devices/system/cpu/cpuX/spurr
+Date: Dec 2006
+Contact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
+Description: SPURR ticks for this CPU since the system boot.
+
+ The Scaled Processor Utilization Resources Register
+ (SPURR) is a 64-bit counter that provides a frequency
+ invariant estimate of the resources used by the CPU
+ thread. The contents of this register increases
+ monotonically. This sysfs interface exposes the number
+ of SPURR ticks for cpuX.
+
+What: /sys/devices/system/cpu/cpuX/idle_purr
+Date: Mar 2020
+Contact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
+Description: PURR ticks for cpuX when it was idle.
+
+ This sysfs interface exposes the number of PURR ticks
+ for cpuX when it was idle.
+
+What: /sys/devices/system/cpu/cpuX/idle_spurr
+Date: Mar 2020
+Contact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
+Description: SPURR ticks for cpuX when it was idle.
+
+ This sysfs interface exposes the number of SPURR ticks
+ for cpuX when it was idle.
--
1.9.4
^ permalink raw reply related
* [PATCH v4 1/6] powerpc: Move idle_loop_prolog()/epilog() functions to header file
From: Gautham R. Shenoy @ 2020-03-27 11:32 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
In-Reply-To: <1585308760-28792-1-git-send-email-ego@linux.vnet.ibm.com>
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Currently prior to entering an idle state on a Linux Guest, the
pseries cpuidle driver implement an idle_loop_prolog() and
idle_loop_epilog() functions which ensure that idle_purr is correctly
computed, and the hypervisor is informed that the CPU cycles have been
donated.
These prolog and epilog functions are also required in the default
idle call, i.e pseries_lpar_idle(). Hence move these accessor
functions to a common header file and call them from
pseries_lpar_idle(). Since the existing header files such as
asm/processor.h have enough clutter, create a new header file
asm/idle.h. Finally rename idle_loop_prolog() and idle_loop_epilog()
to pseries_idle_prolog() and pseries_idle_epilog() as they are only
relavent for on pseries guests.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/idle.h | 31 +++++++++++++++++++++++++++++
arch/powerpc/platforms/pseries/setup.c | 7 +++++--
drivers/cpuidle/cpuidle-pseries.c | 36 +++++++---------------------------
3 files changed, 43 insertions(+), 31 deletions(-)
create mode 100644 arch/powerpc/include/asm/idle.h
diff --git a/arch/powerpc/include/asm/idle.h b/arch/powerpc/include/asm/idle.h
new file mode 100644
index 0000000..32064a4c
--- /dev/null
+++ b/arch/powerpc/include/asm/idle.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_IDLE_H
+#define _ASM_POWERPC_IDLE_H
+#include <asm/runlatch.h>
+#include <asm/paca.h>
+
+#ifdef CONFIG_PPC_PSERIES
+static inline void pseries_idle_prolog(unsigned long *in_purr)
+{
+ ppc64_runlatch_off();
+ *in_purr = mfspr(SPRN_PURR);
+ /*
+ * Indicate to the HV that we are idle. Now would be
+ * a good time to find other work to dispatch.
+ */
+ get_lppaca()->idle = 1;
+}
+
+static inline void pseries_idle_epilog(unsigned long in_purr)
+{
+ u64 wait_cycles;
+
+ wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
+ wait_cycles += mfspr(SPRN_PURR) - in_purr;
+ get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
+ get_lppaca()->idle = 0;
+
+ ppc64_runlatch_on();
+}
+#endif /* CONFIG_PPC_PSERIES */
+#endif
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 0c8421d..2f53e6b 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -68,6 +68,7 @@
#include <asm/isa-bridge.h>
#include <asm/security_features.h>
#include <asm/asm-const.h>
+#include <asm/idle.h>
#include <asm/swiotlb.h>
#include <asm/svm.h>
@@ -319,6 +320,8 @@ static int alloc_dispatch_log_kmem_cache(void)
static void pseries_lpar_idle(void)
{
+ unsigned long in_purr;
+
/*
* Default handler to go into low thread priority and possibly
* low power mode by ceding processor to hypervisor
@@ -328,7 +331,7 @@ static void pseries_lpar_idle(void)
return;
/* Indicate to hypervisor that we are idle. */
- get_lppaca()->idle = 1;
+ pseries_idle_prolog(&in_purr);
/*
* Yield the processor to the hypervisor. We return if
@@ -339,7 +342,7 @@ static void pseries_lpar_idle(void)
*/
cede_processor();
- get_lppaca()->idle = 0;
+ pseries_idle_epilog(in_purr);
}
/*
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 74c2479..46d5e05 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -19,6 +19,7 @@
#include <asm/machdep.h>
#include <asm/firmware.h>
#include <asm/runlatch.h>
+#include <asm/idle.h>
#include <asm/plpar_wrappers.h>
struct cpuidle_driver pseries_idle_driver = {
@@ -31,29 +32,6 @@ struct cpuidle_driver pseries_idle_driver = {
static u64 snooze_timeout __read_mostly;
static bool snooze_timeout_en __read_mostly;
-static inline void idle_loop_prolog(unsigned long *in_purr)
-{
- ppc64_runlatch_off();
- *in_purr = mfspr(SPRN_PURR);
- /*
- * Indicate to the HV that we are idle. Now would be
- * a good time to find other work to dispatch.
- */
- get_lppaca()->idle = 1;
-}
-
-static inline void idle_loop_epilog(unsigned long in_purr)
-{
- u64 wait_cycles;
-
- wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
- wait_cycles += mfspr(SPRN_PURR) - in_purr;
- get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
- get_lppaca()->idle = 0;
-
- ppc64_runlatch_on();
-}
-
static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
@@ -63,7 +41,7 @@ static int snooze_loop(struct cpuidle_device *dev,
set_thread_flag(TIF_POLLING_NRFLAG);
- idle_loop_prolog(&in_purr);
+ pseries_idle_prolog(&in_purr);
local_irq_enable();
snooze_exit_time = get_tb() + snooze_timeout;
@@ -87,7 +65,7 @@ static int snooze_loop(struct cpuidle_device *dev,
local_irq_disable();
- idle_loop_epilog(in_purr);
+ pseries_idle_epilog(in_purr);
return index;
}
@@ -115,7 +93,7 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
{
unsigned long in_purr;
- idle_loop_prolog(&in_purr);
+ pseries_idle_prolog(&in_purr);
get_lppaca()->donate_dedicated_cpu = 1;
HMT_medium();
@@ -124,7 +102,7 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
local_irq_disable();
get_lppaca()->donate_dedicated_cpu = 0;
- idle_loop_epilog(in_purr);
+ pseries_idle_epilog(in_purr);
return index;
}
@@ -135,7 +113,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
{
unsigned long in_purr;
- idle_loop_prolog(&in_purr);
+ pseries_idle_prolog(&in_purr);
/*
* Yield the processor to the hypervisor. We return if
@@ -147,7 +125,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
check_and_cede_processor();
local_irq_disable();
- idle_loop_epilog(in_purr);
+ pseries_idle_epilog(in_purr);
return index;
}
--
1.9.4
^ permalink raw reply related
* [PATCH v4 3/6] powerpc/pseries: Account for SPURR ticks on idle CPUs
From: Gautham R. Shenoy @ 2020-03-27 11:32 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
In-Reply-To: <1585308760-28792-1-git-send-email-ego@linux.vnet.ibm.com>
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
On Pseries LPARs, to calculate utilization, we need to know the
[S]PURR ticks when the CPUs were busy or idle.
Via pseries_idle_prolog(), pseries_idle_epilog(), we track the idle
PURR ticks in the VPA variable "wait_state_cycles". This patch extends
the support to account for the idle SPURR ticks. It also provides an
accessor function to accurately reads idle SPURR ticks.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/idle.h | 33 +++++++++++++++++++++++++++++++++
arch/powerpc/platforms/pseries/setup.c | 2 ++
2 files changed, 35 insertions(+)
diff --git a/arch/powerpc/include/asm/idle.h b/arch/powerpc/include/asm/idle.h
index d4bfb6a..accd1f5 100644
--- a/arch/powerpc/include/asm/idle.h
+++ b/arch/powerpc/include/asm/idle.h
@@ -5,13 +5,20 @@
#include <asm/paca.h>
#ifdef CONFIG_PPC_PSERIES
+DECLARE_PER_CPU(u64, idle_spurr_cycles);
DECLARE_PER_CPU(u64, idle_entry_purr_snap);
+DECLARE_PER_CPU(u64, idle_entry_spurr_snap);
static inline void snapshot_purr_idle_entry(void)
{
*this_cpu_ptr(&idle_entry_purr_snap) = mfspr(SPRN_PURR);
}
+static inline void snapshot_spurr_idle_entry(void)
+{
+ *this_cpu_ptr(&idle_entry_spurr_snap) = mfspr(SPRN_SPURR);
+}
+
static inline void update_idle_purr_accounting(void)
{
u64 wait_cycles;
@@ -22,10 +29,19 @@ static inline void update_idle_purr_accounting(void)
get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
}
+static inline void update_idle_spurr_accounting(void)
+{
+ u64 *idle_spurr_cycles_ptr = this_cpu_ptr(&idle_spurr_cycles);
+ u64 in_spurr = *this_cpu_ptr(&idle_entry_spurr_snap);
+
+ *idle_spurr_cycles_ptr += mfspr(SPRN_SPURR) - in_spurr;
+}
+
static inline void pseries_idle_prolog(void)
{
ppc64_runlatch_off();
snapshot_purr_idle_entry();
+ snapshot_spurr_idle_entry();
/*
* Indicate to the HV that we are idle. Now would be
* a good time to find other work to dispatch.
@@ -36,6 +52,7 @@ static inline void pseries_idle_prolog(void)
static inline void pseries_idle_epilog(void)
{
update_idle_purr_accounting();
+ update_idle_spurr_accounting();
get_lppaca()->idle = 0;
ppc64_runlatch_on();
}
@@ -56,5 +73,21 @@ static inline u64 read_this_idle_purr(void)
return be64_to_cpu(get_lppaca()->wait_state_cycles);
}
+static inline u64 read_this_idle_spurr(void)
+{
+ /*
+ * If we are reading from an idle context, update the
+ * idle-spurr cycles corresponding to the last idle period.
+ * Since the idle context is not yet over, take a fresh
+ * snapshot of the idle-spurr.
+ */
+ if (get_lppaca()->idle == 1) {
+ update_idle_spurr_accounting();
+ snapshot_spurr_idle_entry();
+ }
+
+ return *this_cpu_ptr(&idle_spurr_cycles);
+}
+
#endif /* CONFIG_PPC_PSERIES */
#endif
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 4905c96..1b55e80 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -318,7 +318,9 @@ static int alloc_dispatch_log_kmem_cache(void)
}
machine_early_initcall(pseries, alloc_dispatch_log_kmem_cache);
+DEFINE_PER_CPU(u64, idle_spurr_cycles);
DEFINE_PER_CPU(u64, idle_entry_purr_snap);
+DEFINE_PER_CPU(u64, idle_entry_spurr_snap);
static void pseries_lpar_idle(void)
{
/*
--
1.9.4
^ permalink raw reply related
* [PATCH v4 2/6] powerpc/idle: Add accessor function to always read latest idle PURR
From: Gautham R. Shenoy @ 2020-03-27 11:32 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
In-Reply-To: <1585308760-28792-1-git-send-email-ego@linux.vnet.ibm.com>
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Currently when CPU goes idle, we take a snapshot of PURR via
pseries_idle_prolog() which is used at the CPU idle exit to compute
the idle PURR cycles via the function pseries_idle_epilog(). Thus,
the value of idle PURR cycle thus read before pseries_idle_prolog() and
after pseries_idle_epilog() is always correct.
However, if we were to read the idle PURR cycles from an interrupt
context between pseries_idle_prolog() and pseries_idle_epilog() (this will
be done in a future patch), then, the value of the idle PURR thus read
will not include the cycles spent in the most recent idle period.
This patch addresses the issue by providing accessor function to read
the idle PURR such such that it includes the cycles spent in the most
recent idle period, if we read it between pseries_idle_prolog() and
pseries_idle_epilog(). In order to achieve it, the patch saves the
snapshot of PURR in pseries_idle_prolog() in a per-cpu variable,
instead of on the stack, so that it can be accessed from an interrupt
context.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/idle.h | 47 +++++++++++++++++++++++++++-------
arch/powerpc/platforms/pseries/setup.c | 7 +++--
drivers/cpuidle/cpuidle-pseries.c | 15 +++++------
3 files changed, 47 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/include/asm/idle.h b/arch/powerpc/include/asm/idle.h
index 32064a4c..d4bfb6a 100644
--- a/arch/powerpc/include/asm/idle.h
+++ b/arch/powerpc/include/asm/idle.h
@@ -5,10 +5,27 @@
#include <asm/paca.h>
#ifdef CONFIG_PPC_PSERIES
-static inline void pseries_idle_prolog(unsigned long *in_purr)
+DECLARE_PER_CPU(u64, idle_entry_purr_snap);
+
+static inline void snapshot_purr_idle_entry(void)
+{
+ *this_cpu_ptr(&idle_entry_purr_snap) = mfspr(SPRN_PURR);
+}
+
+static inline void update_idle_purr_accounting(void)
+{
+ u64 wait_cycles;
+ u64 in_purr = *this_cpu_ptr(&idle_entry_purr_snap);
+
+ wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
+ wait_cycles += mfspr(SPRN_PURR) - in_purr;
+ get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
+}
+
+static inline void pseries_idle_prolog(void)
{
ppc64_runlatch_off();
- *in_purr = mfspr(SPRN_PURR);
+ snapshot_purr_idle_entry();
/*
* Indicate to the HV that we are idle. Now would be
* a good time to find other work to dispatch.
@@ -16,16 +33,28 @@ static inline void pseries_idle_prolog(unsigned long *in_purr)
get_lppaca()->idle = 1;
}
-static inline void pseries_idle_epilog(unsigned long in_purr)
+static inline void pseries_idle_epilog(void)
{
- u64 wait_cycles;
-
- wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
- wait_cycles += mfspr(SPRN_PURR) - in_purr;
- get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
+ update_idle_purr_accounting();
get_lppaca()->idle = 0;
-
ppc64_runlatch_on();
}
+
+static inline u64 read_this_idle_purr(void)
+{
+ /*
+ * If we are reading from an idle context, update the
+ * idle-purr cycles corresponding to the last idle period.
+ * Since the idle context is not yet over, take a fresh
+ * snapshot of the idle-purr.
+ */
+ if (unlikely(get_lppaca()->idle == 1)) {
+ update_idle_purr_accounting();
+ snapshot_purr_idle_entry();
+ }
+
+ return be64_to_cpu(get_lppaca()->wait_state_cycles);
+}
+
#endif /* CONFIG_PPC_PSERIES */
#endif
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 2f53e6b..4905c96 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -318,10 +318,9 @@ static int alloc_dispatch_log_kmem_cache(void)
}
machine_early_initcall(pseries, alloc_dispatch_log_kmem_cache);
+DEFINE_PER_CPU(u64, idle_entry_purr_snap);
static void pseries_lpar_idle(void)
{
- unsigned long in_purr;
-
/*
* Default handler to go into low thread priority and possibly
* low power mode by ceding processor to hypervisor
@@ -331,7 +330,7 @@ static void pseries_lpar_idle(void)
return;
/* Indicate to hypervisor that we are idle. */
- pseries_idle_prolog(&in_purr);
+ pseries_idle_prolog();
/*
* Yield the processor to the hypervisor. We return if
@@ -342,7 +341,7 @@ static void pseries_lpar_idle(void)
*/
cede_processor();
- pseries_idle_epilog(in_purr);
+ pseries_idle_epilog();
}
/*
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 46d5e05..6513ef2 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -36,12 +36,11 @@ static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
- unsigned long in_purr;
u64 snooze_exit_time;
set_thread_flag(TIF_POLLING_NRFLAG);
- pseries_idle_prolog(&in_purr);
+ pseries_idle_prolog();
local_irq_enable();
snooze_exit_time = get_tb() + snooze_timeout;
@@ -65,7 +64,7 @@ static int snooze_loop(struct cpuidle_device *dev,
local_irq_disable();
- pseries_idle_epilog(in_purr);
+ pseries_idle_epilog();
return index;
}
@@ -91,9 +90,8 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
- unsigned long in_purr;
- pseries_idle_prolog(&in_purr);
+ pseries_idle_prolog();
get_lppaca()->donate_dedicated_cpu = 1;
HMT_medium();
@@ -102,7 +100,7 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
local_irq_disable();
get_lppaca()->donate_dedicated_cpu = 0;
- pseries_idle_epilog(in_purr);
+ pseries_idle_epilog();
return index;
}
@@ -111,9 +109,8 @@ static int shared_cede_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
- unsigned long in_purr;
- pseries_idle_prolog(&in_purr);
+ pseries_idle_prolog();
/*
* Yield the processor to the hypervisor. We return if
@@ -125,7 +122,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
check_and_cede_processor();
local_irq_disable();
- pseries_idle_epilog(in_purr);
+ pseries_idle_epilog();
return index;
}
--
1.9.4
^ permalink raw reply related
* [PATCH v4 0/6] [PATCH v4 0/6] Track and expose idle PURR and SPURR ticks
From: Gautham R. Shenoy @ 2020-03-27 11:32 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Hi,
This is the fourth version of the patches to track and expose idle PURR
and SPURR ticks. These patches are required by tools such as lparstat
to compute system utilization for capacity planning purposes.
The previous versions can be found here:
v3: https://lkml.org/lkml/2020/3/11/331
v2: https://lkml.org/lkml/2020/2/21/21
v1: https://lore.kernel.org/patchwork/cover/1159341/
They key changes from v3 are:
- Fixed the build errors on !CONFIG_PPC64 and !CONFIG_PPC_PSERIES
configurations notified by the kbuild bot.
Motivation:
===========
On PSeries LPARs, the data centers planners desire a more accurate
view of system utilization per resource such as CPU to plan the system
capacity requirements better. Such accuracy can be obtained by reading
PURR/SPURR registers for CPU resource utilization.
Tools such as lparstat which are used to compute the utilization need
to know [S]PURR ticks when the cpu was busy or idle. The [S]PURR
counters are already exposed through sysfs. We already account for
PURR ticks when we go to idle so that we can update the VPA area. This
patchset extends support to account for SPURR ticks when idle, and
expose both via per-cpu sysfs files.
This patch series also introduces a patch (Patch 6/6) to send an IPI
in order to read and cache the values of purr, spurr, idle_purr and
idle_spurr of the target CPU when any one of them is read via
sysfs. These cached values will be presented if any of these sysfs are
read within the next 10ms. If these sysfs files are read after 10ms
from the earlier IPI, a fresh IPI is issued to read and cache the
values again. This minimizes the number of IPIs required to be sent
when these values are read back-to-back via the sysfs interface.
Without patch 6/6 (Without caching):
16 [XICS 2 Edge IPI] = 422 times
DBL [Doorbell interrupts] = 13 times
Total : 435 IPIs.
With patch 6/6 (With caching):
16 [XICS 2 Edge IPI] = 111 times
DBL [Doorbell interrupts] = 17 times
Total : 128 IPIs.
These patches are required for enhancement to the lparstat utility
that compute the CPU utilization based on PURR and SPURR which can be
found here :
https://groups.google.com/forum/#!topic/powerpc-utils-devel/fYRo69xO9r4
With the patches, when lparstat is run on a LPAR running CPU-Hogs,
=========================================================================
sudo ./src/lparstat -E 1 3
System Configuration
type=Dedicated mode=Capped smt=8 lcpu=2 mem=4834176 kB cpus=0 ent=2.00
---Actual--- -Normalized-
%busy %idle Frequency %busy %idle
------ ------ ------------- ------ ------
99.99 0.00 3.35GHz[111%] 110.99 0.00
100.00 0.00 3.35GHz[111%] 111.00 0.00
100.00 0.00 3.35GHz[111%] 111.00 0.00
With patches, when lparstat is run on and idle LPAR
=========================================================================
---Actual--- -Normalized-
%busy %idle Frequency %busy %idle
------ ------ ------------- ------ ------
0.20 99.81 2.17GHz[ 72%] 0.19 71.82
0.42 99.58 2.11GHz[ 70%] 0.31 69.69
0.41 99.59 2.11GHz[ 70%] 0.31 69.69
Gautham R. Shenoy (6):
powerpc: Move idle_loop_prolog()/epilog() functions to header file
powerpc/idle: Add accessor function to always read latest idle PURR
powerpc/pseries: Account for SPURR ticks on idle CPUs
powerpc/sysfs: Show idle_purr and idle_spurr for every CPU
Documentation: Document sysfs interfaces purr, spurr, idle_purr,
idle_spurr
pseries/sysfs: Minimise IPI noise while reading [idle_][s]purr
Documentation/ABI/testing/sysfs-devices-system-cpu | 39 +++++
arch/powerpc/include/asm/idle.h | 93 ++++++++++++
arch/powerpc/kernel/sysfs.c | 167 ++++++++++++++++++++-
arch/powerpc/platforms/pseries/setup.c | 8 +-
drivers/cpuidle/cpuidle-pseries.c | 39 +----
5 files changed, 305 insertions(+), 41 deletions(-)
create mode 100644 arch/powerpc/include/asm/idle.h
--
1.9.4
^ permalink raw reply
* [PATCH v7 6/6] perf/tools/pmu-events/powerpc: Add hv_24x7 socket/chip level metric events
From: Kajol Jain @ 2020-03-27 10:25 UTC (permalink / raw)
To: acme, linuxppc-dev, mpe, sukadev
Cc: mark.rutland, maddy, peterz, yao.jin, mingo, kan.liang, ak,
alexander.shishkin, anju, mamatha4, ravi.bangoria, kjain, jmario,
namhyung, tglx, mpetlan, gregkh, linux-kernel, linux-perf-users,
jolsa
In-Reply-To: <20200327102528.4267-1-kjain@linux.ibm.com>
The hv_24×7 feature in IBM® POWER9™ processor-based servers provide the
facility to continuously collect large numbers of hardware performance
metrics efficiently and accurately.
This patch adds hv_24x7 metric file for different Socket/chip
resources.
Result:
power9 platform:
command:# ./perf stat --metric-only -M Memory_RD_BW_Chip -C 0 -I 1000
1.000096188 0.9 0.3
2.000285720 0.5 0.1
3.000424990 0.4 0.1
command:# ./perf stat --metric-only -M PowerBUS_Frequency -C 0 -I 1000
1.000097981 2.3 2.3
2.000291713 2.3 2.3
3.000421719 2.3 2.3
4.000550912 2.3 2.3
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
---
.../arch/powerpc/power9/nest_metrics.json | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
create mode 100644 tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json b/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
new file mode 100644
index 000000000000..c121e526442a
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
@@ -0,0 +1,19 @@
+[
+ {
+ "MetricExpr": "(hv_24x7@PM_MCS01_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_RD_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT23\\,chip\\=?@)",
+ "MetricName": "Memory_RD_BW_Chip",
+ "MetricGroup": "Memory_BW",
+ "ScaleUnit": "1.6e-2MB"
+ },
+ {
+ "MetricExpr": "(hv_24x7@PM_MCS01_128B_WR_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_WR_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_WR_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_WR_DISP_PORT23\\,chip\\=?@ )",
+ "MetricName": "Memory_WR_BW_Chip",
+ "MetricGroup": "Memory_BW",
+ "ScaleUnit": "1.6e-2MB"
+ },
+ {
+ "MetricExpr": "(hv_24x7@PM_PB_CYC\\,chip\\=?@ )",
+ "MetricName": "PowerBUS_Frequency",
+ "ScaleUnit": "2.5e-7GHz"
+ }
+]
--
2.18.1
^ permalink raw reply related
* [PATCH v7 5/6] tools/perf: Enable Hz/hz prinitg for --metric-only option
From: Kajol Jain @ 2020-03-27 10:25 UTC (permalink / raw)
To: acme, linuxppc-dev, mpe, sukadev
Cc: mark.rutland, maddy, peterz, yao.jin, mingo, kan.liang, ak,
alexander.shishkin, anju, mamatha4, ravi.bangoria, kjain, jmario,
namhyung, tglx, mpetlan, gregkh, linux-kernel, linux-perf-users,
jolsa
In-Reply-To: <20200327102528.4267-1-kjain@linux.ibm.com>
Commit 54b5091606c18 ("perf stat: Implement --metric-only mode")
added function 'valid_only_metric()' which drops "Hz" or "hz",
if it is part of "ScaleUnit". This patch enable it since hv_24x7
supports couple of frequency events.
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
---
tools/perf/util/stat-display.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 16efdba1973a..ecdebfcdd379 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -237,8 +237,6 @@ static bool valid_only_metric(const char *unit)
if (!unit)
return false;
if (strstr(unit, "/sec") ||
- strstr(unit, "hz") ||
- strstr(unit, "Hz") ||
strstr(unit, "CPUs utilized"))
return false;
return true;
--
2.18.1
^ permalink raw reply related
* [PATCH v7 4/6] perf/tools: Enhance JSON/metric infrastructure to handle "?"
From: Kajol Jain @ 2020-03-27 10:25 UTC (permalink / raw)
To: acme, linuxppc-dev, mpe, sukadev
Cc: mark.rutland, maddy, peterz, yao.jin, mingo, kan.liang, ak,
alexander.shishkin, anju, mamatha4, ravi.bangoria, kjain, jmario,
namhyung, tglx, mpetlan, gregkh, linux-kernel, linux-perf-users,
jolsa
In-Reply-To: <20200327102528.4267-1-kjain@linux.ibm.com>
Patch enhances current metric infrastructure to handle "?" in the metric
expression. The "?" can be use for parameters whose value not known while
creating metric events and which can be replace later at runtime to
the proper value. It also add flexibility to create multiple events out
of single metric event added in json file.
Patch adds function 'arch_get_runtimeparam' which is a arch specific
function, returns the count of metric events need to be created.
By default it return 1.
This infrastructure needed for hv_24x7 socket/chip level events.
"hv_24x7" chip level events needs specific chip-id to which the
data is requested. Function 'arch_get_runtimeparam' implemented
in header.c which extract number of sockets from sysfs file
"sockets" under "/sys/devices/hv_24x7/interface/".
With this patch basically we are trying to create as many metric events
as define by runtime_param.
For that one loop is added in function 'metricgroup__add_metric',
which create multiple events at run time depend on return value of
'arch_get_runtimeparam' and merge that event in 'group_list'.
To achieve that we are actually passing this parameter value as part of
`expr__find_other` function and changing "?" present in metric expression
with this value.
As in our json file, there gonna be single metric event, and out of
which we are creating multiple events.
To understand which data count belongs to which parameter value,
we also printing param value in generic_metric function.
For example,
command:# ./perf stat -M PowerBUS_Frequency -C 0 -I 1000
1.000101867 9,356,933 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0
1.000101867 9,366,134 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1
2.000314878 9,365,868 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0
2.000314878 9,366,092 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1
So, here _0 and _1 after PowerBUS_Frequency specify parameter value.
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
---
| 8 ++++++++
tools/perf/tests/expr.c | 8 ++++----
tools/perf/util/expr.c | 11 ++++++-----
tools/perf/util/expr.h | 5 +++--
tools/perf/util/expr.l | 27 +++++++++++++++++++-------
tools/perf/util/metricgroup.c | 28 ++++++++++++++++++++++++---
tools/perf/util/metricgroup.h | 2 ++
tools/perf/util/stat-shadow.c | 17 ++++++++++------
8 files changed, 79 insertions(+), 27 deletions(-)
--git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 3b4cdfc5efd6..d4870074f14c 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -7,6 +7,8 @@
#include <string.h>
#include <linux/stringify.h>
#include "header.h"
+#include "metricgroup.h"
+#include <api/fs/fs.h>
#define mfspr(rn) ({unsigned long rval; \
asm volatile("mfspr %0," __stringify(rn) \
@@ -44,3 +46,9 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
return bufp;
}
+
+int arch_get_runtimeparam(void)
+{
+ int count;
+ return sysfs__read_int("/devices/hv_24x7/interface/sockets", &count) < 0 ? 1 : count;
+}
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index ea10fc4412c4..516504cf0ea5 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -10,7 +10,7 @@ static int test(struct expr_parse_ctx *ctx, const char *e, double val2)
{
double val;
- if (expr__parse(&val, ctx, e))
+ if (expr__parse(&val, ctx, e, 1))
TEST_ASSERT_VAL("parse test failed", 0);
TEST_ASSERT_VAL("unexpected value", val == val2);
return 0;
@@ -44,15 +44,15 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
return ret;
p = "FOO/0";
- ret = expr__parse(&val, &ctx, p);
+ ret = expr__parse(&val, &ctx, p, 1);
TEST_ASSERT_VAL("division by zero", ret == -1);
p = "BAR/";
- ret = expr__parse(&val, &ctx, p);
+ ret = expr__parse(&val, &ctx, p, 1);
TEST_ASSERT_VAL("missing operand", ret == -1);
TEST_ASSERT_VAL("find other",
- expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other) == 0);
+ expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other, 1) == 0);
TEST_ASSERT_VAL("find other", num_other == 3);
TEST_ASSERT_VAL("find other", !strcmp(other[0], "BAR"));
TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ"));
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index c3382d58cf40..9d56e5fb3873 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -27,10 +27,11 @@ void expr__ctx_init(struct expr_parse_ctx *ctx)
static int
__expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr,
- int start)
+ int start, int param)
{
struct expr_scanner_ctx scanner_ctx = {
.start_token = start,
+ .runtime_param = param,
};
YY_BUFFER_STATE buffer;
void *scanner;
@@ -54,9 +55,9 @@ __expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr,
return ret;
}
-int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr)
+int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr, int param)
{
- return __expr__parse(final_val, ctx, expr, EXPR_PARSE) ? -1 : 0;
+ return __expr__parse(final_val, ctx, expr, EXPR_PARSE, param) ? -1 : 0;
}
static bool
@@ -74,13 +75,13 @@ already_seen(const char *val, const char *one, const char **other,
}
int expr__find_other(const char *expr, const char *one, const char ***other,
- int *num_other)
+ int *num_other, int param)
{
int err, i = 0, j = 0;
struct expr_parse_ctx ctx;
expr__ctx_init(&ctx);
- err = __expr__parse(NULL, &ctx, expr, EXPR_OTHER);
+ err = __expr__parse(NULL, &ctx, expr, EXPR_OTHER, param);
if (err)
return -1;
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 0938ad166ece..0b91597d6512 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -17,12 +17,13 @@ struct expr_parse_ctx {
struct expr_scanner_ctx {
int start_token;
+ int runtime_param;
};
void expr__ctx_init(struct expr_parse_ctx *ctx);
void expr__add_id(struct expr_parse_ctx *ctx, const char *id, double val);
-int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr);
+int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr, int param);
int expr__find_other(const char *expr, const char *one, const char ***other,
- int *num_other);
+ int *num_other, int param);
#endif
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index 2582c2464938..86eb822c51cc 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -35,7 +35,7 @@ static int value(yyscan_t scanner, int base)
* Allow @ instead of / to be able to specify pmu/event/ without
* conflicts with normal division.
*/
-static char *normalize(char *str)
+static char *normalize(char *str, int runtime_param)
{
char *ret = str;
char *dst = str;
@@ -45,6 +45,19 @@ static char *normalize(char *str)
*dst++ = '/';
else if (*str == '\\')
*dst++ = *++str;
+ else if (*str == '?') {
+ char *paramval;
+ int i = 0;
+ int size = asprintf(¶mval, "%d", runtime_param);
+
+ if (size < 0)
+ *dst++ = '0';
+ else {
+ while (i < size)
+ *dst++ = paramval[i++];
+ free(paramval);
+ }
+ }
else
*dst++ = *str;
str++;
@@ -54,16 +67,16 @@ static char *normalize(char *str)
return ret;
}
-static int str(yyscan_t scanner, int token)
+static int str(yyscan_t scanner, int token, int runtime_param)
{
YYSTYPE *yylval = expr_get_lval(scanner);
char *text = expr_get_text(scanner);
- yylval->str = normalize(strdup(text));
+ yylval->str = normalize(strdup(text), runtime_param);
if (!yylval->str)
return EXPR_ERROR;
- yylval->str = normalize(yylval->str);
+ yylval->str = normalize(yylval->str, runtime_param);
return token;
}
%}
@@ -72,8 +85,8 @@ number [0-9]+
sch [-,=]
spec \\{sch}
-sym [0-9a-zA-Z_\.:@]+
-symbol {spec}*{sym}*{spec}*{sym}*
+sym [0-9a-zA-Z_\.:@?]+
+symbol {spec}*{sym}*{spec}*{sym}*{spec}*{sym}
%%
struct expr_scanner_ctx *sctx = expr_get_extra(yyscanner);
@@ -93,7 +106,7 @@ if { return IF; }
else { return ELSE; }
#smt_on { return SMT_ON; }
{number} { return value(yyscanner, 10); }
-{symbol} { return str(yyscanner, ID); }
+{symbol} { return str(yyscanner, ID, sctx->runtime_param); }
"|" { return '|'; }
"^" { return '^'; }
"&" { return '&'; }
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index b905eaa907a7..66695b4a358d 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -90,6 +90,7 @@ struct egroup {
const char *metric_name;
const char *metric_expr;
const char *metric_unit;
+ int param;
};
static struct evsel *find_evsel_group(struct evlist *perf_evlist,
@@ -202,6 +203,7 @@ static int metricgroup__setup_events(struct list_head *groups,
expr->metric_name = eg->metric_name;
expr->metric_unit = eg->metric_unit;
expr->metric_events = metric_events;
+ expr->param = eg->param;
list_add(&expr->nd, &me->head);
}
@@ -485,8 +487,13 @@ static bool metricgroup__has_constraint(struct pmu_event *pe)
return false;
}
+int __weak arch_get_runtimeparam(void)
+{
+ return 1;
+}
+
static int __metricgroup__add_metric(struct strbuf *events,
- struct list_head *group_list, struct pmu_event *pe)
+ struct list_head *group_list, struct pmu_event *pe, int param)
{
const char **ids;
@@ -494,7 +501,7 @@ static int __metricgroup__add_metric(struct strbuf *events,
struct egroup *eg;
int ret = -EINVAL;
- if (expr__find_other(pe->metric_expr, NULL, &ids, &idnum) < 0)
+ if (expr__find_other(pe->metric_expr, NULL, &ids, &idnum, param) < 0)
return ret;
if (events->len > 0)
@@ -514,6 +521,7 @@ static int __metricgroup__add_metric(struct strbuf *events,
eg->metric_name = pe->metric_name;
eg->metric_expr = pe->metric_expr;
eg->metric_unit = pe->unit;
+ eg->param = param;
list_add_tail(&eg->nd, group_list);
return 0;
@@ -541,7 +549,21 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
- ret = __metricgroup__add_metric(events, group_list, pe);
+ if (!strstr(pe->metric_expr, "?")) {
+ ret = __metricgroup__add_metric(events, group_list, pe, 1);
+ } else {
+ int j, count;
+
+ count = arch_get_runtimeparam();
+
+ /* This loop is added to create multiple
+ * events depend on count value and add
+ * those events to group_list.
+ */
+
+ for (j = 0; j < count; j++)
+ ret = __metricgroup__add_metric(events, group_list, pe, j);
+ }
if (ret == -EINVAL || !ret)
continue;
}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 475c7f912864..01393bb33acd 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -22,6 +22,7 @@ struct metric_expr {
const char *metric_name;
const char *metric_unit;
struct evsel **metric_events;
+ int param;
};
struct metric_event *metricgroup__lookup(struct rblist *metric_events,
@@ -34,4 +35,5 @@ int metricgroup__parse_groups(const struct option *opt,
void metricgroup__print(bool metrics, bool groups, char *filter,
bool raw, bool details);
bool metricgroup__has_metric(const char *metric);
+int arch_get_runtimeparam(void);
#endif
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 402af3e8d287..c8c582355e32 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -336,7 +336,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
metric_events = counter->metric_events;
if (!metric_events) {
if (expr__find_other(counter->metric_expr, counter->name,
- &metric_names, &num_metric_names) < 0)
+ &metric_names, &num_metric_names, 1) < 0)
continue;
metric_events = calloc(sizeof(struct evsel *),
@@ -723,6 +723,7 @@ static void generic_metric(struct perf_stat_config *config,
char *name,
const char *metric_name,
const char *metric_unit,
+ int param,
double avg,
int cpu,
struct perf_stat_output_ctx *out,
@@ -777,7 +778,7 @@ static void generic_metric(struct perf_stat_config *config,
}
if (!metric_events[i]) {
- if (expr__parse(&ratio, &pctx, metric_expr) == 0) {
+ if (expr__parse(&ratio, &pctx, metric_expr, param) == 0) {
char *unit;
char metric_bf[64];
@@ -786,9 +787,13 @@ static void generic_metric(struct perf_stat_config *config,
&unit, &scale) >= 0) {
ratio *= scale;
}
-
- scnprintf(metric_bf, sizeof(metric_bf),
+ if (strstr(metric_expr, "?"))
+ scnprintf(metric_bf, sizeof(metric_bf),
+ "%s %s_%d", unit, metric_name, param);
+ else
+ scnprintf(metric_bf, sizeof(metric_bf),
"%s %s", unit, metric_name);
+
print_metric(config, ctxp, NULL, "%8.1f",
metric_bf, ratio);
} else {
@@ -1019,7 +1024,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, name, 0);
} else if (evsel->metric_expr) {
generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
- evsel->metric_name, NULL, avg, cpu, out, st);
+ evsel->metric_name, NULL, 1, avg, cpu, out, st);
} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
char unit = 'M';
char unit_buf[10];
@@ -1048,7 +1053,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
out->new_line(config, ctxp);
generic_metric(config, mexp->metric_expr, mexp->metric_events,
evsel->name, mexp->metric_name,
- mexp->metric_unit, avg, cpu, out, st);
+ mexp->metric_unit, mexp->param, avg, cpu, out, st);
}
}
if (num == 0)
--
2.18.1
^ permalink raw reply related
* [PATCH v7 3/6] perf/tools: Refactoring metricgroup__add_metric function
From: Kajol Jain @ 2020-03-27 10:25 UTC (permalink / raw)
To: acme, linuxppc-dev, mpe, sukadev
Cc: mark.rutland, maddy, peterz, yao.jin, mingo, kan.liang, ak,
alexander.shishkin, anju, mamatha4, ravi.bangoria, kjain, jmario,
namhyung, tglx, mpetlan, gregkh, linux-kernel, linux-perf-users,
jolsa
In-Reply-To: <20200327102528.4267-1-kjain@linux.ibm.com>
This patch refactor metricgroup__add_metric function where
some part of it move to function metricgroup__add_metric_param.
No logic change.
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
---
tools/perf/util/metricgroup.c | 61 +++++++++++++++++++++--------------
1 file changed, 36 insertions(+), 25 deletions(-)
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 926449a7cdbf..b905eaa907a7 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -485,6 +485,40 @@ static bool metricgroup__has_constraint(struct pmu_event *pe)
return false;
}
+static int __metricgroup__add_metric(struct strbuf *events,
+ struct list_head *group_list, struct pmu_event *pe)
+{
+
+ const char **ids;
+ int idnum;
+ struct egroup *eg;
+ int ret = -EINVAL;
+
+ if (expr__find_other(pe->metric_expr, NULL, &ids, &idnum) < 0)
+ return ret;
+
+ if (events->len > 0)
+ strbuf_addf(events, ",");
+
+ if (metricgroup__has_constraint(pe))
+ metricgroup__add_metric_non_group(events, ids, idnum);
+ else
+ metricgroup__add_metric_weak_group(events, ids, idnum);
+
+ eg = malloc(sizeof(*eg));
+ if (!eg)
+ return -ENOMEM;
+
+ eg->ids = ids;
+ eg->idnum = idnum;
+ eg->metric_name = pe->metric_name;
+ eg->metric_expr = pe->metric_expr;
+ eg->metric_unit = pe->unit;
+ list_add_tail(&eg->nd, group_list);
+
+ return 0;
+}
+
static int metricgroup__add_metric(const char *metric, struct strbuf *events,
struct list_head *group_list)
{
@@ -504,35 +538,12 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
continue;
if (match_metric(pe->metric_group, metric) ||
match_metric(pe->metric_name, metric)) {
- const char **ids;
- int idnum;
- struct egroup *eg;
pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
- if (expr__find_other(pe->metric_expr,
- NULL, &ids, &idnum) < 0)
+ ret = __metricgroup__add_metric(events, group_list, pe);
+ if (ret == -EINVAL || !ret)
continue;
- if (events->len > 0)
- strbuf_addf(events, ",");
-
- if (metricgroup__has_constraint(pe))
- metricgroup__add_metric_non_group(events, ids, idnum);
- else
- metricgroup__add_metric_weak_group(events, ids, idnum);
-
- eg = malloc(sizeof(struct egroup));
- if (!eg) {
- ret = -ENOMEM;
- break;
- }
- eg->ids = ids;
- eg->idnum = idnum;
- eg->metric_name = pe->metric_name;
- eg->metric_expr = pe->metric_expr;
- eg->metric_unit = pe->unit;
- list_add_tail(&eg->nd, group_list);
- ret = 0;
}
}
return ret;
--
2.18.1
^ permalink raw reply related
* [PATCH v7 2/6] perf expr: Add expr_scanner_ctx object
From: Kajol Jain @ 2020-03-27 10:25 UTC (permalink / raw)
To: acme, linuxppc-dev, mpe, sukadev
Cc: mark.rutland, maddy, peterz, yao.jin, mingo, kan.liang, ak,
alexander.shishkin, anju, mamatha4, ravi.bangoria, kjain, jmario,
namhyung, tglx, mpetlan, gregkh, linux-kernel, linux-perf-users,
jolsa
In-Reply-To: <20200327102528.4267-1-kjain@linux.ibm.com>
From: Jiri Olsa <jolsa@kernel.org>
Adding expr_scanner_ctx object to hold user data
for the expr scanner. Currently it holds only
start_token, Kajol Jain will use it to hold 24x7
runtime param.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/util/expr.c | 6 ++++--
tools/perf/util/expr.h | 4 ++++
tools/perf/util/expr.l | 10 +++++-----
3 files changed, 13 insertions(+), 7 deletions(-)
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index c8ccc548a585..c3382d58cf40 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -3,7 +3,6 @@
#include <assert.h>
#include "expr.h"
#include "expr-bison.h"
-#define YY_EXTRA_TYPE int
#include "expr-flex.h"
#ifdef PARSER_DEBUG
@@ -30,11 +29,14 @@ static int
__expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr,
int start)
{
+ struct expr_scanner_ctx scanner_ctx = {
+ .start_token = start,
+ };
YY_BUFFER_STATE buffer;
void *scanner;
int ret;
- ret = expr_lex_init_extra(start, &scanner);
+ ret = expr_lex_init_extra(&scanner_ctx, &scanner);
if (ret)
return ret;
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index b9e53f2b5844..0938ad166ece 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -15,6 +15,10 @@ struct expr_parse_ctx {
struct expr_parse_id ids[MAX_PARSE_ID];
};
+struct expr_scanner_ctx {
+ int start_token;
+};
+
void expr__ctx_init(struct expr_parse_ctx *ctx);
void expr__add_id(struct expr_parse_ctx *ctx, const char *id, double val);
int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr);
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index eaad29243c23..2582c2464938 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -76,13 +76,13 @@ sym [0-9a-zA-Z_\.:@]+
symbol {spec}*{sym}*{spec}*{sym}*
%%
- {
- int start_token;
+ struct expr_scanner_ctx *sctx = expr_get_extra(yyscanner);
- start_token = expr_get_extra(yyscanner);
+ {
+ int start_token = sctx->start_token;
- if (start_token) {
- expr_set_extra(NULL, yyscanner);
+ if (sctx->start_token) {
+ sctx->start_token = 0;
return start_token;
}
}
--
2.18.1
^ permalink raw reply related
* [PATCH v7 1/6] perf expr: Add expr_ prefix for parse_ctx and parse_id
From: Kajol Jain @ 2020-03-27 10:25 UTC (permalink / raw)
To: acme, linuxppc-dev, mpe, sukadev
Cc: mark.rutland, maddy, peterz, yao.jin, mingo, kan.liang, ak,
alexander.shishkin, anju, mamatha4, ravi.bangoria, kjain, jmario,
namhyung, tglx, mpetlan, gregkh, linux-kernel, linux-perf-users,
jolsa
In-Reply-To: <20200327102528.4267-1-kjain@linux.ibm.com>
From: Jiri Olsa <jolsa@kernel.org>
Adding expr_ prefix for parse_ctx and parse_id,
to straighten out the expr* namespace.
There's no functional change.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/tests/expr.c | 4 ++--
tools/perf/util/expr.c | 10 +++++-----
tools/perf/util/expr.h | 12 ++++++------
tools/perf/util/expr.y | 6 +++---
tools/perf/util/stat-shadow.c | 2 +-
5 files changed, 17 insertions(+), 17 deletions(-)
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 28313e59d6f6..ea10fc4412c4 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -6,7 +6,7 @@
#include <string.h>
#include <linux/zalloc.h>
-static int test(struct parse_ctx *ctx, const char *e, double val2)
+static int test(struct expr_parse_ctx *ctx, const char *e, double val2)
{
double val;
@@ -22,7 +22,7 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
const char **other;
double val;
int i, ret;
- struct parse_ctx ctx;
+ struct expr_parse_ctx ctx;
int num_other;
expr__ctx_init(&ctx);
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index fd192ddf93c1..c8ccc548a585 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -11,7 +11,7 @@ extern int expr_debug;
#endif
/* Caller must make sure id is allocated */
-void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
+void expr__add_id(struct expr_parse_ctx *ctx, const char *name, double val)
{
int idx;
@@ -21,13 +21,13 @@ void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
ctx->ids[idx].val = val;
}
-void expr__ctx_init(struct parse_ctx *ctx)
+void expr__ctx_init(struct expr_parse_ctx *ctx)
{
ctx->num_ids = 0;
}
static int
-__expr__parse(double *val, struct parse_ctx *ctx, const char *expr,
+__expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr,
int start)
{
YY_BUFFER_STATE buffer;
@@ -52,7 +52,7 @@ __expr__parse(double *val, struct parse_ctx *ctx, const char *expr,
return ret;
}
-int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr)
+int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr)
{
return __expr__parse(final_val, ctx, expr, EXPR_PARSE) ? -1 : 0;
}
@@ -75,7 +75,7 @@ int expr__find_other(const char *expr, const char *one, const char ***other,
int *num_other)
{
int err, i = 0, j = 0;
- struct parse_ctx ctx;
+ struct expr_parse_ctx ctx;
expr__ctx_init(&ctx);
err = __expr__parse(NULL, &ctx, expr, EXPR_OTHER);
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 9377538f4097..b9e53f2b5844 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -5,19 +5,19 @@
#define EXPR_MAX_OTHER 20
#define MAX_PARSE_ID EXPR_MAX_OTHER
-struct parse_id {
+struct expr_parse_id {
const char *name;
double val;
};
-struct parse_ctx {
+struct expr_parse_ctx {
int num_ids;
- struct parse_id ids[MAX_PARSE_ID];
+ struct expr_parse_id ids[MAX_PARSE_ID];
};
-void expr__ctx_init(struct parse_ctx *ctx);
-void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
-int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr);
+void expr__ctx_init(struct expr_parse_ctx *ctx);
+void expr__add_id(struct expr_parse_ctx *ctx, const char *id, double val);
+int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr);
int expr__find_other(const char *expr, const char *one, const char ***other,
int *num_other);
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 4720cbe79357..cd17486c1c5d 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -15,7 +15,7 @@
%define api.pure full
%parse-param { double *final_val }
-%parse-param { struct parse_ctx *ctx }
+%parse-param { struct expr_parse_ctx *ctx }
%parse-param {void *scanner}
%lex-param {void* scanner}
@@ -39,14 +39,14 @@
%{
static void expr_error(double *final_val __maybe_unused,
- struct parse_ctx *ctx __maybe_unused,
+ struct expr_parse_ctx *ctx __maybe_unused,
void *scanner,
const char *s)
{
pr_debug("%s\n", s);
}
-static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
+static int lookup_id(struct expr_parse_ctx *ctx, char *id, double *val)
{
int i;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 0fd713d3674f..402af3e8d287 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -729,7 +729,7 @@ static void generic_metric(struct perf_stat_config *config,
struct runtime_stat *st)
{
print_metric_t print_metric = out->print_metric;
- struct parse_ctx pctx;
+ struct expr_parse_ctx pctx;
double ratio, scale;
int i;
void *ctxp = out->ctx;
--
2.18.1
^ permalink raw reply related
* [PATCH v7 0/6] powerpc/perf: Add json file metric support for the hv_24x7 socket/chip level events
From: Kajol Jain @ 2020-03-27 10:25 UTC (permalink / raw)
To: acme, linuxppc-dev, mpe, sukadev
Cc: mark.rutland, maddy, peterz, yao.jin, mingo, kan.liang, ak,
alexander.shishkin, anju, mamatha4, ravi.bangoria, kjain, jmario,
namhyung, tglx, mpetlan, gregkh, linux-kernel, linux-perf-users,
jolsa
Patchset adds json file metric support for the hv_24x7 socket/chip level
events. "hv_24x7" pmu interface events needs system dependent parameter
like socket/chip/core. For example, hv_24x7 chip level events needs
specific chip-id to which the data is requested should be added as part
of pmu events.
So to enable JSON file support to "hv_24x7" interface, patchset reads
total number of sockets details in sysfs under
"/sys/devices/hv_24x7/interface/".
Second patch of the patchset adds expr_scanner_ctx object to hold user
data for the expr scanner, which can be used to hold runtime parameter.
Patch 4 & 6 of the patchset handles perf tool plumbing needed to replace
the "?" character in the metric expression to proper value and hv_24x7
json metric file for different Socket/chip resources.
Patch set also enable Hz/hz prinitg for --metric-only option to print
metric data for bus frequency.
Applied and tested all these patches cleanly on top of jiri's flex changes
with the changes done by Kan Liang for "Support metric group constraint"
patchset and made required changes.
Also apply this patch on top of the fix patch send earlier
for printing metric name incase overlapping events.
https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/commit/?h=perf/core&id=37cd7f65bf71a48f25eeb6d9be5dacb20d008ea6
Changelog:
v6 -> v7
- Spit patchset into two patch series one for kernel changes and other
for tool side changes.
- Made changes Suggested by Jiri, including rather then reading runtime
parameter from metric name, actually add it in structure egroup and
metric_expr.
- As we don't need to read runtime parameter from metric name,
now I am not appending it and rather just printing it in
generic_metric function.
Kernel Side changes patch series: https://lkml.org/lkml/2020/3/27/58
v5 -> v6
- resolve compilation issue due to rearranging patch series.
- Rather then adding new function to take careof case for runtime param
in metricgroup__add_metric, using metricgroup__add_metric_param itself
for that work.
- Address some optimization suggested like using directly file path
rather then adding new macro in header.c
- Change commit message on patch where we are adding "?" support
by adding simple example.
v4 -> v5
- Using sysfs__read_int instead of sysfs__read_ull while reading
parameter value in powerpc/util/header.c file.
- Using asprintf rather then malloc and sprintf
Suggested by Arnaldo Carvalho de Melo
- Break patch 6 from previous version to two patch,
- One to add refactor current "metricgroup__add_metric" function
and another where actually "?" handling infra added.
- Add expr__runtimeparam as part of 'expr_scanner_ctx' struct
rather then making it global variable. Thanks Jiri for
adding this structure to hold user data for the expr scanner.
- Add runtime param as agrugement to function 'expr__find_other'
and 'expr__parse' and made changes on references accordingly.
v3 -> v4
- Apply these patch on top of Kan liang changes.
As suggested by Jiri.
v2 -> v3
- Remove setting event_count to 0 part in function 'h_24x7_event_read'
with comment rather then adding 0 to event_count value.
Suggested by: Sukadev Bhattiprolu
- Apply tool side changes require to replace "?" on Jiri's flex patch
series and made all require changes to make it compatible with added
flex change.
v1 -> v2
- Rename hv-24x7 metric json file as nest_metrics.json
Jiri Olsa (2):
perf expr: Add expr_ prefix for parse_ctx and parse_id
perf expr: Add expr_scanner_ctx object
Kajol Jain (4):
perf/tools: Refactoring metricgroup__add_metric function
perf/tools: Enhance JSON/metric infrastructure to handle "?"
tools/perf: Enable Hz/hz prinitg for --metric-only option
perf/tools/pmu-events/powerpc: Add hv_24x7 socket/chip level metric
events
tools/perf/arch/powerpc/util/header.c | 8 ++
.../arch/powerpc/power9/nest_metrics.json | 19 +++++
tools/perf/tests/expr.c | 12 +--
tools/perf/util/expr.c | 25 +++---
tools/perf/util/expr.h | 19 +++--
tools/perf/util/expr.l | 37 ++++++---
tools/perf/util/expr.y | 6 +-
tools/perf/util/metricgroup.c | 79 +++++++++++++------
tools/perf/util/metricgroup.h | 2 +
tools/perf/util/stat-display.c | 2 -
tools/perf/util/stat-shadow.c | 19 +++--
11 files changed, 157 insertions(+), 71 deletions(-)
create mode 100644 tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
--
2.18.1
^ permalink raw reply
* Re: hardcoded SIGSEGV in __die() ?
From: Joakim Tjernlund @ 2020-03-27 10:10 UTC (permalink / raw)
To: christophe.leroy@c-s.fr, mpe@ellerman.id.au,
linuxppc-dev@ozlabs.org
In-Reply-To: <87lfnovu11.fsf@mpe.ellerman.id.au>
On Thu, 2020-03-26 at 11:28 +1100, Michael Ellerman wrote:
> CAUTION: This email originated from outside of the organization. Do not click links or open attachments unless you recognize the sender and know the content is safe.
>
>
> Joakim Tjernlund <Joakim.Tjernlund@infinera.com> writes:
> > On Mon, 2020-03-23 at 15:45 +0100, Christophe Leroy wrote:
> > > Le 23/03/2020 à 15:43, Christophe Leroy a écrit :
> > > > Le 23/03/2020 à 15:17, Joakim Tjernlund a écrit :
> > > > > In __die(), see below, there is this call to notify_send() with
> > > > > SIGSEGV hardcoded, this seems odd
> > > > > to me as the variable "err" holds the true signal(in my case SIGBUS)
> > > > > Should not SIGSEGV be replaced with the true signal no.?
> > > >
> > > > As far as I can see, comes from
> > > > https://nam03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgit.kernel.org%2Fpub%2Fscm%2Flinux%2Fkernel%2Fgit%2Ftorvalds%2Flinux.git%2Fcommit%2F%3Fid%3D66fcb1059&data=02%7C01%7CJoakim.Tjernlund%40infinera.com%7Caa316058f9e34dd758c808d7d11ca391%7C285643de5f5b4b03a1530ae2dc8aaf77%7C1%7C0%7C637207793252449714&sdata=LBzRMxHWJzNEztnnG0UzJb7PHvaDGVswQD%2B8WpY9YX8%3D&reserved=0
> > > >
> > >
> > > And
> > > https://nam03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgit.kernel.org%2Fpub%2Fscm%2Flinux%2Fkernel%2Fgit%2Ftorvalds%2Flinux.git%2Fcommit%2F%3Fid%3Dae87221d3ce49d9de1e43756da834fd0bf05a2ad&data=02%7C01%7CJoakim.Tjernlund%40infinera.com%7Caa316058f9e34dd758c808d7d11ca391%7C285643de5f5b4b03a1530ae2dc8aaf77%7C1%7C0%7C637207793252449714&sdata=Dh%2BUTRgG85oVSgC3SCR1B7izQH4HofT4ppOMiy9xvDA%3D&reserved=0
> > > shows it is (was?) similar on x86.
> > >
> >
> > I tried to follow that chain thinking it would end up sending a signal to user space but I cannot see
> > that happens. Seems to be related to debugging.
> >
> > In short, I cannot see any signal being delivered to user space. If so that would explain why
> > our user space process never dies.
> > Is there a signal hidden in machine_check handler for SIGBUS I cannot see?
>
> It's platform specific. What platform are you on?
I am on e500, e5500(e500mc) and 83xx :)
>
> See the ppc_md & cur_cpu_spec calls here:
>
> void machine_check_exception(struct pt_regs *regs)
> {
> int recover = 0;
> bool nested = in_nmi();
> if (!nested)
> nmi_enter();
>
> __this_cpu_inc(irq_stat.mce_exceptions);
>
> add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
>
> /* See if any machine dependent calls. In theory, we would want
> * to call the CPU first, and call the ppc_md. one if the CPU
> * one returns a positive number. However there is existing code
> * that assumes the board gets a first chance, so let's keep it
> * that way for now and fix things later. --BenH.
> */
> if (ppc_md.machine_check_exception)
> recover = ppc_md.machine_check_exception(regs);
> else if (cur_cpu_spec->machine_check)
> recover = cur_cpu_spec->machine_check(regs);
>
> if (recover > 0)
> goto bail;
>
>
> Either the ppc_md or cpu_spec handlers can send a signal, but after a
> bit of grepping I think only the pseries and powernv ones do.
Seems so
>
> If you get into die() then it's an oops, which is not the same as a
> normal signal.
Exactly, and the die/OOPS does not seem work as intended either. The system tries to limp along
and generates more similar OOPses and may even hang.
>
> cheers
^ permalink raw reply
* [PATCH v1] powerpc: Make setjmp/longjump signature standard
From: Clement Courbet @ 2020-03-27 10:07 UTC (permalink / raw)
Cc: Greg Kroah-Hartman, Nick Desaulniers, linux-kernel,
clang-built-linux, Paul Mackerras, Clement Courbet,
Nathan Chancellor, linuxppc-dev, Thomas Gleixner
Declaring setjmp()/longjmp() as taking longs makes the signature
non-standard, and makes clang complain. In the past, this has been
worked around by adding -ffreestanding to the compile flags.
The implementation looks like it only ever propagates the value
(in longjmp) or sets it to 1 (in setjmp), and we only call longjmp
with integer parameters.
This allows removing -ffreestanding from the compilation flags.
Context:
https://lore.kernel.org/patchwork/patch/1214060
https://lore.kernel.org/patchwork/patch/1216174
Signed-off-by: Clement Courbet <courbet@google.com>
---
arch/powerpc/include/asm/setjmp.h | 6 ++++--
arch/powerpc/kexec/Makefile | 3 ---
2 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/setjmp.h b/arch/powerpc/include/asm/setjmp.h
index e9f81bb3f83b..84bb0d140d59 100644
--- a/arch/powerpc/include/asm/setjmp.h
+++ b/arch/powerpc/include/asm/setjmp.h
@@ -7,7 +7,9 @@
#define JMP_BUF_LEN 23
-extern long setjmp(long *) __attribute__((returns_twice));
-extern void longjmp(long *, long) __attribute__((noreturn));
+typedef long *jmp_buf;
+
+extern int setjmp(jmp_buf env) __attribute__((returns_twice));
+extern void longjmp(jmp_buf env, int val) __attribute__((noreturn));
#endif /* _ASM_POWERPC_SETJMP_H */
diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile
index 378f6108a414..86380c69f5ce 100644
--- a/arch/powerpc/kexec/Makefile
+++ b/arch/powerpc/kexec/Makefile
@@ -3,9 +3,6 @@
# Makefile for the linux kernel.
#
-# Avoid clang warnings around longjmp/setjmp declarations
-CFLAGS_crash.o += -ffreestanding
-
obj-y += core.o crash.o core_$(BITS).o
obj-$(CONFIG_PPC32) += relocate_32.o
--
2.25.1.696.g5e7596f4ac-goog
^ permalink raw reply related
* Re: [PATCH v6 09/11] perf/tools: Enhance JSON/metric infrastructure to handle "?"
From: kajoljain @ 2020-03-27 10:00 UTC (permalink / raw)
To: Jiri Olsa
Cc: mark.rutland, maddy, peterz, yao.jin, mingo, kan.liang, ak,
alexander.shishkin, anju, mamatha4, sukadev, ravi.bangoria, acme,
jmario, namhyung, tglx, mpetlan, gregkh, linux-kernel,
linux-perf-users, jolsa, linuxppc-dev
In-Reply-To: <20200324131141.GV1534489@krava>
On 3/24/20 6:41 PM, Jiri Olsa wrote:
> On Fri, Mar 20, 2020 at 06:24:04PM +0530, Kajol Jain wrote:
>> Patch enhances current metric infrastructure to handle "?" in the metric
>> expression. The "?" can be use for parameters whose value not known while
>> creating metric events and which can be replace later at runtime to
>> the proper value. It also add flexibility to create multiple events out
>> of single metric event added in json file.
>>
>> Patch adds function 'arch_get_runtimeparam' which is a arch specific
>> function, returns the count of metric events need to be created.
>> By default it return 1.
>>
>> This infrastructure needed for hv_24x7 socket/chip level events.
>> "hv_24x7" chip level events needs specific chip-id to which the
>> data is requested. Function 'arch_get_runtimeparam' implemented
>> in header.c which extract number of sockets from sysfs file
>> "sockets" under "/sys/devices/hv_24x7/interface/".
>>
>>
>> With this patch basically we are trying to create as many metric events
>> as define by runtime_param.
>>
>> For that one loop is added in function 'metricgroup__add_metric',
>> which create multiple events at run time depend on return value of
>> 'arch_get_runtimeparam' and merge that event in 'group_list'.
>>
>> To achieve that we are actually passing this parameter value as part of
>> `expr__find_other` function and changing "?" present in metric expression
>> with this value.
>>
>> As in our json file, there gonna be single metric event, and out of
>> which we are creating multiple events, I am also merging this value
>> to the original metric name to specify parameter value.
>>
>> For example,
>> command:# ./perf stat -M PowerBUS_Frequency -C 0 -I 1000
>> # time counts unit events
>> 1.000101867 9,356,933 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0
>> 1.000101867 9,366,134 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1
>> 2.000314878 9,365,868 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0
>> 2.000314878 9,366,092 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1
>>
>> So, here _0 and _1 after PowerBUS_Frequency specify parameter value.
>>
>> As after adding this to group_list, again we call expr__parse
>> in 'generic_metric' function present in util/stat-display.c.
>> By this time again we need to pass this parameter value. So, now to get this value
>> actually I am trying to extract it from metric name itself. Because
>> otherwise it gonna point to last updated value present in runtime_param.
>> And gonna match for that value only.
>
> so why can't we pass that param as integer value through the metric objects?
>
> it get's created in metricgroup__add_metric_param:
> - as struct egroup *eg
> - we can add egroup::param and store the param value there
>
> then in metricgroup__setup_events it moves to:
> - struct metric_expr *expr
> - we can add metric_expr::param to keep the param
>
> then in perf_stat__print_shadow_stats there's:
> - struct metric_expr *mexp loop
> - calling generic_metric metric - we could call it with mexp::param
> - and pass the param to expr__parse
>
Hi jiri,
Thanks for the suggestion, Yes it make more sense to use like that.
Will update.
Thanks,
Kajol
> jirka
>
^ permalink raw reply
* [PATCH] selftests/powerpc: Fix try-run when source tree is not writable
From: Michael Ellerman @ 2020-03-27 9:53 UTC (permalink / raw)
To: linuxppc-dev; +Cc: harish
We added a usage of try-run to pmu/ebb/Makefile to detect if the
toolchain supported the -no-pie option.
This fails if we build out-of-tree and the source tree is not
writable, as try-run tries to write its temporary files to the current
directory. That leads to the -no-pie option being silently dropped,
which leads to broken executables with some toolchains.
If we remove the redirect to /dev/null in try-run, we see the error:
make[3]: Entering directory '/linux/tools/testing/selftests/powerpc/pmu/ebb'
/usr/bin/ld: cannot open output file .54.tmp: Read-only file system
collect2: error: ld returned 1 exit status
make[3]: Nothing to be done for 'all'.
And looking with strace we see it's trying to use a file that's in the
source tree:
lstat("/linux/tools/testing/selftests/powerpc/pmu/ebb/.54.tmp", 0x7ffffc0f83c8)
We can fix it by setting TMPOUT to point to the $(OUTPUT) directory,
and we can verify with strace it's now trying to write to the output
directory:
lstat("/output/kselftest/powerpc/pmu/ebb/.54.tmp", 0x7fffd1bf6bf8)
And also see that the -no-pie option is now correctly detected.
Fixes: 0695f8bca93e ("selftests/powerpc: Handle Makefile for unrecognized option")
Cc: stable@vger.kernel.org # v5.5+
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
tools/testing/selftests/powerpc/pmu/ebb/Makefile | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index 417306353e07..ca35dd8848b0 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -7,6 +7,7 @@ include ../../../../../../scripts/Kbuild.include
# The EBB handler is 64-bit code and everything links against it
CFLAGS += -m64
+TMPOUT = $(OUTPUT)/
# Toolchains may build PIE by default which breaks the assembly
no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
$(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
base-commit: 11a48a5a18c63fd7621bb050228cebf13566e4d8
prerequisite-patch-id: e460261e180666bfb63bcd0cc554874d73c3b71f
prerequisite-patch-id: 67db368cfdf8d3aefd78f140420281f9b4b53e07
prerequisite-patch-id: cf5d957a366998b4a3ce70a79b6e969eb98fca7d
prerequisite-patch-id: 3ace935c6ae425ad635eb38f906e790c3c9bf41f
--
2.25.1
^ permalink raw reply related
* Re: [PATCH v2] mm/sparse: Fix kernel crash with pfn_section_valid check
From: David Hildenbrand @ 2020-03-27 9:42 UTC (permalink / raw)
To: Aneesh Kumar K.V, linux-mm, akpm
Cc: Sachin Sant, Pankaj Gupta, Michal Hocko, Baoquan He, linux-kernel,
stable, Mike Rapoport, Wei Yang, Dan Williams, linuxppc-dev,
Oscar Salvador
In-Reply-To: <20200326133235.343616-1-aneesh.kumar@linux.ibm.com>
On 26.03.20 14:32, Aneesh Kumar K.V wrote:
> Fixes the below crash
>
> BUG: Kernel NULL pointer dereference on read at 0x00000000
> Faulting instruction address: 0xc000000000c3447c
> Oops: Kernel access of bad area, sig: 11 [#1]
> LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
> CPU: 11 PID: 7519 Comm: lt-ndctl Not tainted 5.6.0-rc7-autotest #1
> ...
> NIP [c000000000c3447c] vmemmap_populated+0x98/0xc0
> LR [c000000000088354] vmemmap_free+0x144/0x320
> Call Trace:
> section_deactivate+0x220/0x240
> __remove_pages+0x118/0x170
> arch_remove_memory+0x3c/0x150
> memunmap_pages+0x1cc/0x2f0
> devm_action_release+0x30/0x50
> release_nodes+0x2f8/0x3e0
> device_release_driver_internal+0x168/0x270
> unbind_store+0x130/0x170
> drv_attr_store+0x44/0x60
> sysfs_kf_write+0x68/0x80
> kernfs_fop_write+0x100/0x290
> __vfs_write+0x3c/0x70
> vfs_write+0xcc/0x240
> ksys_write+0x7c/0x140
> system_call+0x5c/0x68
>
> The crash is due to NULL dereference at
>
> test_bit(idx, ms->usage->subsection_map); due to ms->usage = NULL; in pfn_section_valid()
>
> With commit: d41e2f3bd546 ("mm/hotplug: fix hot remove failure in SPARSEMEM|!VMEMMAP case")
> section_mem_map is set to NULL after depopulate_section_mem(). This
> was done so that pfn_page() can work correctly with kernel config that disables
> SPARSEMEM_VMEMMAP. With that config pfn_to_page does
>
> __section_mem_map_addr(__sec) + __pfn;
> where
>
> static inline struct page *__section_mem_map_addr(struct mem_section *section)
> {
> unsigned long map = section->section_mem_map;
> map &= SECTION_MAP_MASK;
> return (struct page *)map;
> }
>
> Now with SPASEMEM_VMEMAP enabled, mem_section->usage->subsection_map is used to
> check the pfn validity (pfn_valid()). Since section_deactivate release
> mem_section->usage if a section is fully deactivated, pfn_valid() check after
> a subsection_deactivate cause a kernel crash.
>
> static inline int pfn_valid(unsigned long pfn)
> {
> ...
> return early_section(ms) || pfn_section_valid(ms, pfn);
> }
>
> where
>
> static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
> {
> int idx = subsection_map_index(pfn);
>
> return test_bit(idx, ms->usage->subsection_map);
> }
>
> Avoid this by clearing SECTION_HAS_MEM_MAP when mem_section->usage is freed.
> For architectures like ppc64 where large pages are used for vmmemap mapping (16MB),
> a specific vmemmap mapping can cover multiple sections. Hence before a vmemmap
> mapping page can be freed, the kernel needs to make sure there are no valid sections
> within that mapping. Clearing the section valid bit before
> depopulate_section_memap enables this.
>
> Fixes: d41e2f3bd546 ("mm/hotplug: fix hot remove failure in SPARSEMEM|!VMEMMAP case")
> Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
> Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
> Cc: Baoquan He <bhe@redhat.com>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: Dan Williams <dan.j.williams@intel.com>
> Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Michal Hocko <mhocko@suse.com>
> Cc: Wei Yang <richardw.yang@linux.intel.com>
> Cc: Oscar Salvador <osalvador@suse.de>
> Cc: Mike Rapoport <rppt@linux.ibm.com>
> Cc: <stable@vger.kernel.org>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> ---
> mm/sparse.c | 6 ++++++
> 1 file changed, 6 insertions(+)
>
> diff --git a/mm/sparse.c b/mm/sparse.c
> index aadb7298dcef..65599e8bd636 100644
> --- a/mm/sparse.c
> +++ b/mm/sparse.c
> @@ -781,6 +781,12 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
> ms->usage = NULL;
> }
> memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
> + /*
> + * Mark the section invalid so that valid_section()
> + * return false. This prevents code from dereferencing
s/return/returns/
> + * ms->usage array.
maybe "(see pfn_section_valid())"
> + */
> + ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
--
Thanks,
David / dhildenb
^ permalink raw reply
* Re: [PATCH 1/2] powerpc/vmlinux.lds: Explicitly retain .gnu.hash
From: Michael Ellerman @ 2020-03-27 9:29 UTC (permalink / raw)
To: Alan Modra; +Cc: linuxppc-dev, joel
In-Reply-To: <20200227062147.GC32593@bubble.grove.modra.org>
Alan Modra <amodra@gmail.com> writes:
> On Thu, Feb 27, 2020 at 03:59:32PM +1100, Michael Ellerman wrote:
>> Relocatable kernel builds produce a warning about .gnu.hash being an
>> orphan section:
>>
>> ld: warning: orphan section `.gnu.hash' from `linker stubs' being placed in section `.gnu.hash'
>>
>> If we try to discard it the build fails:
>>
>> ld -EL -m elf64lppc -pie --orphan-handling=warn --build-id -o
>> .tmp_vmlinux1 -T ./arch/powerpc/kernel/vmlinux.lds --whole-archive
>> arch/powerpc/kernel/head_64.o arch/powerpc/kernel/entry_64.o
>> ...
>> sound/built-in.a net/built-in.a virt/built-in.a --no-whole-archive
>> --start-group lib/lib.a --end-group
>> ld: could not find section .gnu.hash
>>
>> So add an entry to explicitly retain it, as we do for .hash.
>
> Looks fine to me. You can also pass --hash-style=sysv to ld (since
> binutils-2.18) to disable generation of .gnu.hash.
Our current minimum is 2.21, so that's probably 5-10 years away :)
cheers
^ permalink raw reply
* Re: [PATCH 2/2] powerpc/vmlinux.lds: Discard .interp section
From: Michael Ellerman @ 2020-03-27 9:27 UTC (permalink / raw)
To: Alan Modra; +Cc: linuxppc-dev, joel
In-Reply-To: <20200227062750.GD32593@bubble.grove.modra.org>
Alan Modra <amodra@gmail.com> writes:
> On Thu, Feb 27, 2020 at 03:59:33PM +1100, Michael Ellerman wrote:
>> The .interp section specifies which "interpreter", ie. dynamic loader,
>> the kernel requests. But that doesn't make any sense, the kernel is
>> not a regular binary that is run with an interpreter.
>>
>> The content seems to be some default value, this file doesn't even
>> exist on my system:
>> 00000000 2f 75 73 72 2f 6c 69 62 2f 6c 64 2e 73 6f 2e 31 |/usr/lib/ld.so.1|
>>
>> So the section serves no useful purpose and consumes a small amount of
>> space.
>>
>> Also Alan Modra says we "likely could discard" it, so do so.
>
> Yes, but you ought to check with the mimimum required binutils. It is
> quite possible that an older linker will blow up.
OK, I guess I'll have to test.
> If the minimum required binutils is at least binutils-2.26 then
> passing --no-dynamic-linker to ld is a more elegant solution.
The current minimum is 2.21, though there's talk of increasing it to
2.23.
cheers
^ permalink raw reply
* Re: [PATCH v2] powerpc/kprobes: Blacklist functions running with MMU disabled on PPC32
From: Naveen N. Rao @ 2020-03-27 9:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Christophe Leroy, Michael Ellerman,
Paul Mackerras
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <3ada1af1b479c5a88bf9f3b8955bf5ba3f32f1ba.1582565849.git.christophe.leroy@c-s.fr>
Christophe Leroy wrote:
> kprobe does not handle events happening in real mode, all
> functions running with MMU disabled have to be blacklisted.
>
> As already done for PPC64, do it for PPC32.
>
> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
> ---
> v2:
> - Don't rename nonrecoverable as local, mark it noprobe instead.
> - Add missing linux/kprobes.h include in pq2.c
> ---
> arch/powerpc/include/asm/ppc_asm.h | 10 +++
> arch/powerpc/kernel/cpu_setup_6xx.S | 4 +-
> arch/powerpc/kernel/entry_32.S | 65 ++++++++------------
> arch/powerpc/kernel/fpu.S | 1 +
> arch/powerpc/kernel/idle_6xx.S | 2 +-
> arch/powerpc/kernel/idle_e500.S | 2 +-
> arch/powerpc/kernel/l2cr_6xx.S | 2 +-
> arch/powerpc/kernel/misc.S | 2 +
> arch/powerpc/kernel/misc_32.S | 4 +-
> arch/powerpc/kernel/swsusp_32.S | 6 +-
> arch/powerpc/kernel/vector.S | 1 +
> arch/powerpc/mm/book3s32/hash_low.S | 38 ++++++------
> arch/powerpc/mm/mem.c | 2 +
> arch/powerpc/platforms/52xx/lite5200_sleep.S | 2 +
> arch/powerpc/platforms/82xx/pq2.c | 3 +
> arch/powerpc/platforms/83xx/suspend-asm.S | 1 +
> arch/powerpc/platforms/powermac/cache.S | 2 +
> arch/powerpc/platforms/powermac/sleep.S | 13 ++--
> 18 files changed, 86 insertions(+), 74 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
> index 6b03dff61a05..e8f34ba89497 100644
> --- a/arch/powerpc/include/asm/ppc_asm.h
> +++ b/arch/powerpc/include/asm/ppc_asm.h
> @@ -267,8 +267,18 @@ GLUE(.,name):
> .pushsection "_kprobe_blacklist","aw"; \
> PPC_LONG (entry) ; \
> .popsection
> +#define _NOKPROBE_ENTRY(entry) \
> + _ASM_NOKPROBE_SYMBOL(entry) \
> + _ENTRY(entry)
> +#define _NOKPROBE_GLOBAL(entry) \
> + _ASM_NOKPROBE_SYMBOL(entry) \
> + _GLOBAL(entry)
> #else
> #define _ASM_NOKPROBE_SYMBOL(entry)
> +#define _NOKPROBE_ENTRY(entry) \
> + _ENTRY(entry)
> +#define _NOKPROBE_GLOBAL(entry) \
> + _GLOBAL(entry)
> #endif
Michael hasn't preferred including NOKPROBE variants of those macros
previously, since he would like to see some cleanups there:
https://patchwork.ozlabs.org/patch/696138/
>
> #define FUNC_START(name) _GLOBAL(name)
> diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
> index f6517f67265a..1cb947268546 100644
> --- a/arch/powerpc/kernel/cpu_setup_6xx.S
> +++ b/arch/powerpc/kernel/cpu_setup_6xx.S
> @@ -276,7 +276,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NO_DPM)
> * in some 750 cpus where using a not yet initialized FPU register after
> * power on reset may hang the CPU
> */
> -_GLOBAL(__init_fpu_registers)
> +_NOKPROBE_GLOBAL(__init_fpu_registers)
> mfmsr r10
> ori r11,r10,MSR_FP
> mtmsr r11
> @@ -381,7 +381,7 @@ _GLOBAL(__save_cpu_setup)
> * restore CPU state as backed up by the previous
> * function. This does not include cache setting
> */
> -_GLOBAL(__restore_cpu_setup)
> +_NOKPROBE_GLOBAL(__restore_cpu_setup)
> /* Some CR fields are volatile, we back it up all */
> mfcr r7
>
> diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
> index 16af0d8d90a8..f788d586254d 100644
> --- a/arch/powerpc/kernel/entry_32.S
> +++ b/arch/powerpc/kernel/entry_32.S
> @@ -44,24 +44,21 @@
> .align 12
>
> #ifdef CONFIG_BOOKE
> - .globl mcheck_transfer_to_handler
> -mcheck_transfer_to_handler:
> +_NOKPROBE_ENTRY(mcheck_transfer_to_handler)
> mfspr r0,SPRN_DSRR0
> stw r0,_DSRR0(r11)
> mfspr r0,SPRN_DSRR1
> stw r0,_DSRR1(r11)
> /* fall through */
>
> - .globl debug_transfer_to_handler
> -debug_transfer_to_handler:
> +_NOKPROBE_ENTRY(debug_transfer_to_handler)
> mfspr r0,SPRN_CSRR0
> stw r0,_CSRR0(r11)
> mfspr r0,SPRN_CSRR1
> stw r0,_CSRR1(r11)
> /* fall through */
>
> - .globl crit_transfer_to_handler
> -crit_transfer_to_handler:
> +_NOKPROBE_ENTRY(crit_transfer_to_handler)
> #ifdef CONFIG_PPC_BOOK3E_MMU
> mfspr r0,SPRN_MAS0
> stw r0,MAS0(r11)
> @@ -97,8 +94,7 @@ crit_transfer_to_handler:
> #endif
>
> #ifdef CONFIG_40x
> - .globl crit_transfer_to_handler
> -crit_transfer_to_handler:
> +_NOKPROBE_ENTRY(crit_transfer_to_handler)
> lwz r0,crit_r10@l(0)
> stw r0,GPR10(r11)
> lwz r0,crit_r11@l(0)
> @@ -124,13 +120,11 @@ crit_transfer_to_handler:
> * Note that we rely on the caller having set cr0.eq iff the exception
> * occurred in kernel mode (i.e. MSR:PR = 0).
> */
> - .globl transfer_to_handler_full
> -transfer_to_handler_full:
> +_NOKPROBE_ENTRY(transfer_to_handler_full)
> SAVE_NVGPRS(r11)
> /* fall through */
>
> - .globl transfer_to_handler
> -transfer_to_handler:
> +_NOKPROBE_ENTRY(transfer_to_handler)
> stw r2,GPR2(r11)
> stw r12,_NIP(r11)
> stw r9,_MSR(r11)
> @@ -194,8 +188,7 @@ transfer_to_handler:
> bt- 31-TLF_NAPPING,4f
> bt- 31-TLF_SLEEPING,7f
> #endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_E500 */
> - .globl transfer_to_handler_cont
> -transfer_to_handler_cont:
> +_NOKPROBE_ENTRY(transfer_to_handler_cont)
> 3:
> mflr r9
> tovirt_novmstack r2, r2 /* set r2 to current */
> @@ -297,6 +290,7 @@ reenable_mmu:
> * On kernel stack overflow, load up an initial stack pointer
> * and call StackOverflow(regs), which should not return.
> */
> +_ASM_NOKPROBE_SYMBOL(stack_ovf)
> stack_ovf:
The current convention is to add the NOKPROBE annotation at the _end_ of
the associated function/symbol...
> /* sometimes we use a statically-allocated stack, which is OK. */
> lis r12,_end@h
> @@ -460,6 +454,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
> lwz r7,_NIP(r1)
> lwz r2,GPR2(r1)
> lwz r1,GPR1(r1)
> +syscall_exit_finish:
> #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
> mtspr SPRN_NRI, r0
> #endif
> @@ -467,6 +462,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
> mtspr SPRN_SRR1,r8
> SYNC
> RFI
> +_ASM_NOKPROBE_SYMBOL(syscall_exit_finish)
... like so.
> #ifdef CONFIG_44x
> 2: li r7,0
> iccci r0,r0
> @@ -750,8 +746,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPE)
> addi r1,r1,INT_FRAME_SIZE
> blr
>
> - .globl fast_exception_return
> -fast_exception_return:
> +_NOKPROBE_ENTRY(fast_exception_return)
> #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
> andi. r10,r9,MSR_RI /* check for recoverable interrupt */
> beq 1f /* if not, we've got problems */
> @@ -780,8 +775,8 @@ fast_exception_return:
>
> #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
> /* check if the exception happened in a restartable section */
> -1: lis r3,exc_exit_restart_end@ha
> - addi r3,r3,exc_exit_restart_end@l
> +1: lis r3,.Lexc_exit_restart_end@ha
> + addi r3,r3,.Lexc_exit_restart_end@l
> cmplw r12,r3
> #ifdef CONFIG_PPC_BOOK3S_601
> bge 2b
> @@ -1005,15 +1000,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
> LOAD_REG_IMMEDIATE(r10,MSR_KERNEL & ~MSR_RI)
> SYNC
> mtmsr r10 /* clear the RI bit */
> - .globl exc_exit_restart
> -exc_exit_restart:
> +_NOKPROBE_ENTRY(exc_exit_restart)
> lwz r12,_NIP(r1)
> mtspr SPRN_SRR0,r12
> mtspr SPRN_SRR1,r9
> REST_4GPRS(9, r1)
> lwz r1,GPR1(r1)
> - .globl exc_exit_restart_end
> -exc_exit_restart_end:
> +.Lexc_exit_restart_end:
> SYNC
> RFI
>
> @@ -1033,17 +1026,15 @@ exc_exit_restart_end:
> li r10, 0
> stw r10, 8(r1)
> REST_2GPRS(9, r1)
> - .globl exc_exit_restart
> +_NOKPROBE_ENTRY(exc_exit_restart)
> exc_exit_restart:
> lwz r11,_NIP(r1)
> lwz r12,_MSR(r1)
> -exc_exit_start:
> mtspr SPRN_SRR0,r11
> mtspr SPRN_SRR1,r12
> REST_2GPRS(11, r1)
> lwz r1,GPR1(r1)
> - .globl exc_exit_restart_end
> -exc_exit_restart_end:
> +.Lexc_exit_restart_end:
I think it would be good to break this into smaller patches to handle
specific code paths, if possible. At the very least, it would be good to
move changes to symbol visibility to a separate patch since this also
changes the names printed in a backtrace.
- Naveen
^ permalink raw reply
* Re: [PATCH v2] powerpc xmon: use `dcbf` inplace of `dcbi` instruction for 64bit Book3S
From: Balamuruhan S @ 2020-03-27 9:03 UTC (permalink / raw)
To: Christophe Leroy, mpe
Cc: ravi.bangoria, jniethe5, paulus, sandipan, naveen.n.rao,
linuxppc-dev
In-Reply-To: <caf285b1-172e-7116-b2ed-3645f36264ed@c-s.fr>
On Fri, 2020-03-27 at 07:48 +0100, Christophe Leroy wrote:
>
> Le 26/03/2020 à 07:15, Balamuruhan S a écrit :
> > Data Cache Block Invalidate (dcbi) instruction was implemented back in
> > PowerPC
> > architecture version 2.03. It is obsolete and attempt to use of this
> > illegal
> > instruction results in a hypervisor emulation assistance interrupt. So,
> > ifdef
> > it out the option `i` in xmon for 64bit Book3S.
>
> I don't understand. You say two contradictory things:
> 1/ You say it _was_ added back.
> 2/ You say it _is_ obsolete.
>
> How can it be obsolete if it was added back ?
I actually learnt it from P8 and P9 User Manual,
The POWER8/POWER9 core does not provide support for the following optional or
obsolete instructions (attempted use of these results in a hypervisor emulation
assistance interrupt):
• tlbia - TLB invalidate all
• tlbiex - TLB invalidate entry by index (obsolete)
• slbiex - SLB invalidate entry by index (obsolete)
• dcba - Data cache block allocate (Book II; obsolete)
• dcbi - Data cache block invalidate (obsolete)
• rfi - Return from interrupt (32-bit; obsolete)
>
> [...]
>
> > diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
> > index 0ec9640335bb..bfd5a97689cd 100644
> > --- a/arch/powerpc/xmon/xmon.c
> > +++ b/arch/powerpc/xmon/xmon.c
> > @@ -335,10 +335,12 @@ static inline void cflush(void *p)
> > asm volatile ("dcbf 0,%0; icbi 0,%0" : : "r" (p));
> > }
> >
> > +#ifndef CONFIG_PPC_BOOK3S_64
>
> You don't need that #ifndef. Keeping it should be harmless.
okay.
>
> > static inline void cinval(void *p)
> > {
> > asm volatile ("dcbi 0,%0; icbi 0,%0" : : "r" (p));
> > }
> > +#endif
> >
> > /**
> > * write_ciabr() - write the CIABR SPR
> > @@ -1791,8 +1793,9 @@ static void prregs(struct pt_regs *fp)
> >
> > static void cacheflush(void)
> > {
> > - int cmd;
> > unsigned long nflush;
> > +#ifndef CONFIG_PPC_BOOK3S_64
>
> Don't make it so complex, see below
>
> > + int cmd;
> >
> > cmd = inchar();
> > if (cmd != 'i')
> > @@ -1800,13 +1803,14 @@ static void cacheflush(void)
> > scanhex((void *)&adrs);
> > if (termch != '\n')
> > termch = 0;
> > +#endif
> > nflush = 1;
> > scanhex(&nflush);
> > nflush = (nflush + L1_CACHE_BYTES - 1) / L1_CACHE_BYTES;
> > if (setjmp(bus_error_jmp) == 0) {
> > catch_memory_errors = 1;
> > sync();
> > -
> > +#ifndef CONFIG_PPC_BOOK3S_64
>
> You don't need that ifndef, just ensure below that regardless of cmd,
> book3s/64 calls cflush and not cinval.
>
> > if (cmd != 'i') {
>
> The only thing you have to do is to replace the above test by:
>
> if (cmd != 'i' || IS_ENABLED(CONFIG_PPC_BOOK3S_64)) {
yes, this is the better way.
>
> > for (; nflush > 0; --nflush, adrs += L1_CACHE_BYTES)
> > cflush((void *) adrs);
> > @@ -1814,6 +1818,10 @@ static void cacheflush(void)
> > for (; nflush > 0; --nflush, adrs += L1_CACHE_BYTES)
> > cinval((void *) adrs);
> > }
> > +#else
>
> Don't need that at all, it's a duplication of the above.
sure :+1:
Thanks for reviewing.
-- Bala
>
> > + for (; nflush > 0; --nflush, adrs += L1_CACHE_BYTES)
> > + cflush((void *)adrs);
> > +#endif
> > sync();
> > /* wait a little while to see if we get a machine check */
> > __delay(200);
> >
> > base-commit: a87b93bdf800a4d7a42d95683624a4516e516b4f
> >
>
> Christophe
^ permalink raw reply
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