* [PATCH 1/2] ALSA: ppc: drop if block with always false condition
From: Uwe Kleine-König @ 2020-11-26 16:59 UTC (permalink / raw)
To: Geoff Levand, Jaroslav Kysela, Takashi Iwai, Michael Ellerman,
Jens Axboe, Jim Paris, Arnd Bergmann, Greg Kroah-Hartman,
David S. Miller, Jakub Kicinski, James E.J. Bottomley,
Martin K. Petersen, Alan Stern, Bartlomiej Zolnierkiewicz
Cc: alsa-devel, linux-scsi, linux-usb, linux-fbdev, dri-devel,
linux-block, Paul Mackerras, netdev, linuxppc-dev
The remove callback is only called for devices that were probed
successfully before. As the matching probe function cannot complete
without error if dev->match_id != PS3_MATCH_ID_SOUND, we don't have to
check this here.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
---
sound/ppc/snd_ps3.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/sound/ppc/snd_ps3.c b/sound/ppc/snd_ps3.c
index 58bb49fff184..6ab796a5d936 100644
--- a/sound/ppc/snd_ps3.c
+++ b/sound/ppc/snd_ps3.c
@@ -1053,8 +1053,6 @@ static int snd_ps3_driver_remove(struct ps3_system_bus_device *dev)
{
int ret;
pr_info("%s:start id=%d\n", __func__, dev->match_id);
- if (dev->match_id != PS3_MATCH_ID_SOUND)
- return -ENXIO;
/*
* ctl and preallocate buffer will be freed in
--
2.29.2
^ permalink raw reply related
* [PATCH 2/2] powerpc/ps3: make system bus's remove and shutdown callbacks return void
From: Uwe Kleine-König @ 2020-11-26 16:59 UTC (permalink / raw)
To: Geoff Levand, Jaroslav Kysela, Takashi Iwai, Michael Ellerman,
Jens Axboe, Jim Paris, Arnd Bergmann, Greg Kroah-Hartman,
David S. Miller, Jakub Kicinski, James E.J. Bottomley,
Martin K. Petersen, Alan Stern, Bartlomiej Zolnierkiewicz
Cc: alsa-devel, linux-scsi, linux-usb, linux-fbdev, dri-devel,
linux-block, Paul Mackerras, netdev, linuxppc-dev
In-Reply-To: <20201126165950.2554997-1-u.kleine-koenig@pengutronix.de>
The driver core ignores the return value of struct device_driver::remove
because there is only little that can be done. For the shutdown callback
it's ps3_system_bus_shutdown() which ignores the return value.
To simplify the quest to make struct device_driver::remove return void,
let struct ps3_system_bus_driver::remove return void, too. All users
already unconditionally return 0, this commit makes it obvious that
returning an error code is a bad idea and ensures future users behave
accordingly.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
---
arch/powerpc/include/asm/ps3.h | 4 ++--
arch/powerpc/platforms/ps3/system-bus.c | 5 ++---
drivers/block/ps3disk.c | 3 +--
drivers/block/ps3vram.c | 3 +--
drivers/char/ps3flash.c | 3 +--
drivers/net/ethernet/toshiba/ps3_gelic_net.c | 3 +--
drivers/ps3/ps3-lpm.c | 3 +--
drivers/ps3/ps3-vuart.c | 10 ++++------
drivers/scsi/ps3rom.c | 3 +--
drivers/usb/host/ehci-ps3.c | 4 +---
drivers/usb/host/ohci-ps3.c | 4 +---
drivers/video/fbdev/ps3fb.c | 4 +---
sound/ppc/snd_ps3.c | 3 +--
13 files changed, 18 insertions(+), 34 deletions(-)
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index cb89e4bf55ce..e646c7f218bc 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -378,8 +378,8 @@ struct ps3_system_bus_driver {
enum ps3_match_sub_id match_sub_id;
struct device_driver core;
int (*probe)(struct ps3_system_bus_device *);
- int (*remove)(struct ps3_system_bus_device *);
- int (*shutdown)(struct ps3_system_bus_device *);
+ void (*remove)(struct ps3_system_bus_device *);
+ void (*shutdown)(struct ps3_system_bus_device *);
/* int (*suspend)(struct ps3_system_bus_device *, pm_message_t); */
/* int (*resume)(struct ps3_system_bus_device *); */
};
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index c62aaa29a9d5..b431f41c6cb5 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -382,7 +382,6 @@ static int ps3_system_bus_probe(struct device *_dev)
static int ps3_system_bus_remove(struct device *_dev)
{
- int result = 0;
struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
struct ps3_system_bus_driver *drv;
@@ -393,13 +392,13 @@ static int ps3_system_bus_remove(struct device *_dev)
BUG_ON(!drv);
if (drv->remove)
- result = drv->remove(dev);
+ drv->remove(dev);
else
dev_dbg(&dev->core, "%s:%d %s: no remove method\n",
__func__, __LINE__, drv->core.name);
pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev_name(&dev->core));
- return result;
+ return 0;
}
static void ps3_system_bus_shutdown(struct device *_dev)
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 7b55811c2a81..ba3ece56cbb3 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -507,7 +507,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
return error;
}
-static int ps3disk_remove(struct ps3_system_bus_device *_dev)
+static void ps3disk_remove(struct ps3_system_bus_device *_dev)
{
struct ps3_storage_device *dev = to_ps3_storage_device(&_dev->core);
struct ps3disk_private *priv = ps3_system_bus_get_drvdata(&dev->sbd);
@@ -526,7 +526,6 @@ static int ps3disk_remove(struct ps3_system_bus_device *_dev)
kfree(dev->bounce_buf);
kfree(priv);
ps3_system_bus_set_drvdata(_dev, NULL);
- return 0;
}
static struct ps3_system_bus_driver ps3disk = {
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 1088798c8dd0..b71d28372ef3 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -797,7 +797,7 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev)
return error;
}
-static int ps3vram_remove(struct ps3_system_bus_device *dev)
+static void ps3vram_remove(struct ps3_system_bus_device *dev)
{
struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
@@ -817,7 +817,6 @@ static int ps3vram_remove(struct ps3_system_bus_device *dev)
free_pages((unsigned long) priv->xdr_buf, get_order(XDR_BUF_SIZE));
kfree(priv);
ps3_system_bus_set_drvdata(dev, NULL);
- return 0;
}
static struct ps3_system_bus_driver ps3vram = {
diff --git a/drivers/char/ps3flash.c b/drivers/char/ps3flash.c
index 1a07fee33f66..23871cde41fb 100644
--- a/drivers/char/ps3flash.c
+++ b/drivers/char/ps3flash.c
@@ -403,7 +403,7 @@ static int ps3flash_probe(struct ps3_system_bus_device *_dev)
return error;
}
-static int ps3flash_remove(struct ps3_system_bus_device *_dev)
+static void ps3flash_remove(struct ps3_system_bus_device *_dev)
{
struct ps3_storage_device *dev = to_ps3_storage_device(&_dev->core);
@@ -413,7 +413,6 @@ static int ps3flash_remove(struct ps3_system_bus_device *_dev)
kfree(ps3_system_bus_get_drvdata(&dev->sbd));
ps3_system_bus_set_drvdata(&dev->sbd, NULL);
ps3flash_dev = NULL;
- return 0;
}
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index d9a5722f561b..3d1fc8d2ca66 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -1791,7 +1791,7 @@ static int ps3_gelic_driver_probe(struct ps3_system_bus_device *dev)
* ps3_gelic_driver_remove - remove a device from the control of this driver
*/
-static int ps3_gelic_driver_remove(struct ps3_system_bus_device *dev)
+static void ps3_gelic_driver_remove(struct ps3_system_bus_device *dev)
{
struct gelic_card *card = ps3_system_bus_get_drvdata(dev);
struct net_device *netdev0;
@@ -1840,7 +1840,6 @@ static int ps3_gelic_driver_remove(struct ps3_system_bus_device *dev)
ps3_close_hv_device(dev);
pr_debug("%s: done\n", __func__);
- return 0;
}
static struct ps3_system_bus_driver ps3_gelic_driver = {
diff --git a/drivers/ps3/ps3-lpm.c b/drivers/ps3/ps3-lpm.c
index e54aa2d82f50..65512b6cc6fd 100644
--- a/drivers/ps3/ps3-lpm.c
+++ b/drivers/ps3/ps3-lpm.c
@@ -1196,7 +1196,7 @@ static int ps3_lpm_probe(struct ps3_system_bus_device *dev)
return 0;
}
-static int ps3_lpm_remove(struct ps3_system_bus_device *dev)
+static void ps3_lpm_remove(struct ps3_system_bus_device *dev)
{
dev_dbg(&dev->core, " -> %s:%u:\n", __func__, __LINE__);
@@ -1206,7 +1206,6 @@ static int ps3_lpm_remove(struct ps3_system_bus_device *dev)
lpm_priv = NULL;
dev_info(&dev->core, " <- %s:%u:\n", __func__, __LINE__);
- return 0;
}
static struct ps3_system_bus_driver ps3_lpm_driver = {
diff --git a/drivers/ps3/ps3-vuart.c b/drivers/ps3/ps3-vuart.c
index 4ed131eaff51..e34ae6a442c7 100644
--- a/drivers/ps3/ps3-vuart.c
+++ b/drivers/ps3/ps3-vuart.c
@@ -1102,7 +1102,7 @@ static int ps3_vuart_cleanup(struct ps3_system_bus_device *dev)
* device can no longer be used.
*/
-static int ps3_vuart_remove(struct ps3_system_bus_device *dev)
+static void ps3_vuart_remove(struct ps3_system_bus_device *dev)
{
struct ps3_vuart_port_priv *priv = to_port_priv(dev);
struct ps3_vuart_port_driver *drv;
@@ -1118,7 +1118,7 @@ static int ps3_vuart_remove(struct ps3_system_bus_device *dev)
dev_dbg(&dev->core, "%s:%d: no driver bound\n", __func__,
__LINE__);
mutex_unlock(&vuart_bus_priv.probe_mutex);
- return 0;
+ return;
}
drv = ps3_system_bus_dev_to_vuart_drv(dev);
@@ -1141,7 +1141,6 @@ static int ps3_vuart_remove(struct ps3_system_bus_device *dev)
dev_dbg(&dev->core, " <- %s:%d\n", __func__, __LINE__);
mutex_unlock(&vuart_bus_priv.probe_mutex);
- return 0;
}
/**
@@ -1154,7 +1153,7 @@ static int ps3_vuart_remove(struct ps3_system_bus_device *dev)
* sequence.
*/
-static int ps3_vuart_shutdown(struct ps3_system_bus_device *dev)
+static void ps3_vuart_shutdown(struct ps3_system_bus_device *dev)
{
struct ps3_vuart_port_driver *drv;
@@ -1169,7 +1168,7 @@ static int ps3_vuart_shutdown(struct ps3_system_bus_device *dev)
dev_dbg(&dev->core, "%s:%d: no driver bound\n", __func__,
__LINE__);
mutex_unlock(&vuart_bus_priv.probe_mutex);
- return 0;
+ return;
}
drv = ps3_system_bus_dev_to_vuart_drv(dev);
@@ -1193,7 +1192,6 @@ static int ps3_vuart_shutdown(struct ps3_system_bus_device *dev)
dev_dbg(&dev->core, " <- %s:%d\n", __func__, __LINE__);
mutex_unlock(&vuart_bus_priv.probe_mutex);
- return 0;
}
static int __init ps3_vuart_bus_init(void)
diff --git a/drivers/scsi/ps3rom.c b/drivers/scsi/ps3rom.c
index f75c0b5cd587..ccb5771f1cb7 100644
--- a/drivers/scsi/ps3rom.c
+++ b/drivers/scsi/ps3rom.c
@@ -402,7 +402,7 @@ static int ps3rom_probe(struct ps3_system_bus_device *_dev)
return error;
}
-static int ps3rom_remove(struct ps3_system_bus_device *_dev)
+static void ps3rom_remove(struct ps3_system_bus_device *_dev)
{
struct ps3_storage_device *dev = to_ps3_storage_device(&_dev->core);
struct Scsi_Host *host = ps3_system_bus_get_drvdata(&dev->sbd);
@@ -412,7 +412,6 @@ static int ps3rom_remove(struct ps3_system_bus_device *_dev)
scsi_host_put(host);
ps3_system_bus_set_drvdata(&dev->sbd, NULL);
kfree(dev->bounce_buf);
- return 0;
}
static struct ps3_system_bus_driver ps3rom = {
diff --git a/drivers/usb/host/ehci-ps3.c b/drivers/usb/host/ehci-ps3.c
index fb52133c3557..98568b046a1a 100644
--- a/drivers/usb/host/ehci-ps3.c
+++ b/drivers/usb/host/ehci-ps3.c
@@ -200,7 +200,7 @@ static int ps3_ehci_probe(struct ps3_system_bus_device *dev)
return result;
}
-static int ps3_ehci_remove(struct ps3_system_bus_device *dev)
+static void ps3_ehci_remove(struct ps3_system_bus_device *dev)
{
unsigned int tmp;
struct usb_hcd *hcd = ps3_system_bus_get_drvdata(dev);
@@ -227,8 +227,6 @@ static int ps3_ehci_remove(struct ps3_system_bus_device *dev)
ps3_dma_region_free(dev->d_region);
ps3_close_hv_device(dev);
-
- return 0;
}
static int __init ps3_ehci_driver_register(struct ps3_system_bus_driver *drv)
diff --git a/drivers/usb/host/ohci-ps3.c b/drivers/usb/host/ohci-ps3.c
index f77cd6af0ccf..4f5af929c3e4 100644
--- a/drivers/usb/host/ohci-ps3.c
+++ b/drivers/usb/host/ohci-ps3.c
@@ -184,7 +184,7 @@ static int ps3_ohci_probe(struct ps3_system_bus_device *dev)
return result;
}
-static int ps3_ohci_remove(struct ps3_system_bus_device *dev)
+static void ps3_ohci_remove(struct ps3_system_bus_device *dev)
{
unsigned int tmp;
struct usb_hcd *hcd = ps3_system_bus_get_drvdata(dev);
@@ -212,8 +212,6 @@ static int ps3_ohci_remove(struct ps3_system_bus_device *dev)
ps3_dma_region_free(dev->d_region);
ps3_close_hv_device(dev);
-
- return 0;
}
static int __init ps3_ohci_driver_register(struct ps3_system_bus_driver *drv)
diff --git a/drivers/video/fbdev/ps3fb.c b/drivers/video/fbdev/ps3fb.c
index 203c254f8f6c..2fe08b67eda7 100644
--- a/drivers/video/fbdev/ps3fb.c
+++ b/drivers/video/fbdev/ps3fb.c
@@ -1208,7 +1208,7 @@ static int ps3fb_probe(struct ps3_system_bus_device *dev)
return retval;
}
-static int ps3fb_shutdown(struct ps3_system_bus_device *dev)
+static void ps3fb_shutdown(struct ps3_system_bus_device *dev)
{
struct fb_info *info = ps3_system_bus_get_drvdata(dev);
u64 xdr_lpar = ps3_mm_phys_to_lpar(__pa(ps3fb_videomemory.address));
@@ -1241,8 +1241,6 @@ static int ps3fb_shutdown(struct ps3_system_bus_device *dev)
lv1_gpu_memory_free(ps3fb.memory_handle);
ps3_close_hv_device(dev);
dev_dbg(&dev->core, " <- %s:%d\n", __func__, __LINE__);
-
- return 0;
}
static struct ps3_system_bus_driver ps3fb_driver = {
diff --git a/sound/ppc/snd_ps3.c b/sound/ppc/snd_ps3.c
index 6ab796a5d936..8e44fa5d4dc7 100644
--- a/sound/ppc/snd_ps3.c
+++ b/sound/ppc/snd_ps3.c
@@ -1049,7 +1049,7 @@ static int snd_ps3_driver_probe(struct ps3_system_bus_device *dev)
}; /* snd_ps3_probe */
/* called when module removal */
-static int snd_ps3_driver_remove(struct ps3_system_bus_device *dev)
+static void snd_ps3_driver_remove(struct ps3_system_bus_device *dev)
{
int ret;
pr_info("%s:start id=%d\n", __func__, dev->match_id);
@@ -1075,7 +1075,6 @@ static int snd_ps3_driver_remove(struct ps3_system_bus_device *dev)
lv1_gpu_device_unmap(2);
ps3_close_hv_device(dev);
pr_info("%s:end id=%d\n", __func__, dev->match_id);
- return 0;
} /* snd_ps3_remove */
static struct ps3_system_bus_driver snd_ps3_bus_driver_info = {
--
2.29.2
^ permalink raw reply related
* [PATCH V2 4/7] powerpc/perf: Add generic and cache event list for power10 DD1
From: Athira Rajeev @ 2020-11-26 16:54 UTC (permalink / raw)
To: mpe; +Cc: maddy, linuxppc-dev
In-Reply-To: <1606409684-1589-1-git-send-email-atrajeev@linux.vnet.ibm.com>
There are event code updates for some of the generic events
and cache events for power10. Inorder to maintain the current
event codes work with DD1 also, create a new array of generic_events,
cache_events and pmu_attr_groups with suffix _dd1, example,
power10_events_attr_dd1. So that further updates to event codes
can be made in the original list, ie, power10_events_attr. Update the
power10 pmu init code to pick the dd1 list while registering
the power PMU, based on the pvr (Processor Version Register) value.
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/perf/power10-pmu.c | 152 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 152 insertions(+)
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index 88c5430..bc3d4dd 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -129,6 +129,31 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS);
CACHE_EVENT_ATTR(iTLB-load-misses, PM_ITLB_MISS);
+static struct attribute *power10_events_attr_dd1[] = {
+ GENERIC_EVENT_PTR(PM_RUN_CYC),
+ GENERIC_EVENT_PTR(PM_RUN_INST_CMPL),
+ GENERIC_EVENT_PTR(PM_BR_CMPL),
+ GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL),
+ GENERIC_EVENT_PTR(PM_LD_REF_L1),
+ GENERIC_EVENT_PTR(PM_LD_MISS_L1),
+ GENERIC_EVENT_PTR(MEM_LOADS),
+ GENERIC_EVENT_PTR(MEM_STORES),
+ CACHE_EVENT_PTR(PM_LD_MISS_L1),
+ CACHE_EVENT_PTR(PM_LD_REF_L1),
+ CACHE_EVENT_PTR(PM_LD_PREFETCH_CACHE_LINE_MISS),
+ CACHE_EVENT_PTR(PM_ST_MISS_L1),
+ CACHE_EVENT_PTR(PM_L1_ICACHE_MISS),
+ CACHE_EVENT_PTR(PM_INST_FROM_L1),
+ CACHE_EVENT_PTR(PM_IC_PREF_REQ),
+ CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS),
+ CACHE_EVENT_PTR(PM_DATA_FROM_L3),
+ CACHE_EVENT_PTR(PM_BR_MPRED_CMPL),
+ CACHE_EVENT_PTR(PM_BR_CMPL),
+ CACHE_EVENT_PTR(PM_DTLB_MISS),
+ CACHE_EVENT_PTR(PM_ITLB_MISS),
+ NULL
+};
+
static struct attribute *power10_events_attr[] = {
GENERIC_EVENT_PTR(PM_RUN_CYC),
GENERIC_EVENT_PTR(PM_RUN_INST_CMPL),
@@ -154,6 +179,11 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
NULL
};
+static struct attribute_group power10_pmu_events_group_dd1 = {
+ .name = "events",
+ .attrs = power10_events_attr_dd1,
+};
+
static struct attribute_group power10_pmu_events_group = {
.name = "events",
.attrs = power10_events_attr,
@@ -205,12 +235,27 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
.attrs = power10_pmu_format_attr,
};
+static const struct attribute_group *power10_pmu_attr_groups_dd1[] = {
+ &power10_pmu_format_group,
+ &power10_pmu_events_group_dd1,
+ NULL,
+};
+
static const struct attribute_group *power10_pmu_attr_groups[] = {
&power10_pmu_format_group,
&power10_pmu_events_group,
NULL,
};
+static int power10_generic_events_dd1[] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = PM_RUN_CYC,
+ [PERF_COUNT_HW_INSTRUCTIONS] = PM_RUN_INST_CMPL,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_CMPL,
+ [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1,
+ [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1,
+};
+
static int power10_generic_events[] = {
[PERF_COUNT_HW_CPU_CYCLES] = PM_RUN_CYC,
[PERF_COUNT_HW_INSTRUCTIONS] = PM_RUN_INST_CMPL,
@@ -276,6 +321,107 @@ static void power10_config_bhrb(u64 pmu_bhrb_filter)
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
+static u64 power10_cache_events_dd1[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+ [C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_LD_REF_L1,
+ [C(RESULT_MISS)] = PM_LD_MISS_L1,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_ST_MISS_L1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = PM_LD_PREFETCH_CACHE_LINE_MISS,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_INST_FROM_L1,
+ [C(RESULT_MISS)] = PM_L1_ICACHE_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = PM_INST_FROM_L1MISS,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = PM_IC_PREF_REQ,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_DATA_FROM_L3,
+ [C(RESULT_MISS)] = PM_DATA_FROM_L3MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_DTLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_ITLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_BR_CMPL,
+ [C(RESULT_MISS)] = PM_BR_MPRED_CMPL,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+};
+
static u64 power10_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = {
[C(OP_READ)] = {
@@ -422,6 +568,12 @@ int init_power10_pmu(void)
/* Set the PERF_REG_EXTENDED_MASK here */
PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31;
+ if ((PVR_CFG(pvr) == 1)) {
+ power10_pmu.generic_events = power10_generic_events_dd1;
+ power10_pmu.attr_groups = power10_pmu_attr_groups_dd1;
+ power10_pmu.cache_events = &power10_cache_events_dd1;
+ }
+
rc = register_power_pmu(&power10_pmu);
if (rc)
return rc;
--
1.8.3.1
^ permalink raw reply related
* [PATCH V2 7/7] powerpc/perf: MMCR0 control for PMU registers under PMCC=00
From: Athira Rajeev @ 2020-11-26 16:54 UTC (permalink / raw)
To: mpe; +Cc: maddy, linuxppc-dev
In-Reply-To: <1606409684-1589-1-git-send-email-atrajeev@linux.vnet.ibm.com>
PowerISA v3.1 introduces new control bit (PMCCEXT) for restricting
access to group B PMU registers in problem state when
MMCR0 PMCC=0b00. In problem state and when MMCR0 PMCC=0b00,
setting the Monitor Mode Control Register bit 54 (MMCR0 PMCCEXT),
will restrict read permission on Group B Performance Monitor
Registers (SIER, SIAR, SDAR and MMCR1). When this bit is set to zero,
group B registers will be readable. In other platforms (like power9),
the older behaviour is retained where group B PMU SPRs are readable.
Patch adds support for MMCR0 PMCCEXT bit in power10 by enabling
this bit during boot and during the PMU event enable/disable callback
functions.
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/reg.h | 1 +
arch/powerpc/kernel/cpu_setup_power.c | 1 +
arch/powerpc/kernel/dt_cpu_ftrs.c | 1 +
arch/powerpc/perf/core-book3s.c | 4 ++++
arch/powerpc/perf/isa207-common.c | 8 ++++++++
5 files changed, 15 insertions(+)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f877a57..cba9965 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -864,6 +864,7 @@
#define MMCR0_BHRBA 0x00200000UL /* BHRB Access allowed in userspace */
#define MMCR0_EBE 0x00100000UL /* Event based branch enable */
#define MMCR0_PMCC 0x000c0000UL /* PMC control */
+#define MMCR0_PMCCEXT ASM_CONST(0x00000200) /* PMCCEXT control */
#define MMCR0_PMCC_U6 0x00080000UL /* PMC1-6 are R/W by user (PR) */
#define MMCR0_PMC1CE 0x00008000UL /* PMC1 count enable*/
#define MMCR0_PMCjCE ASM_CONST(0x00004000) /* PMCj count enable*/
diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c
index 0c2191e..3cca88e 100644
--- a/arch/powerpc/kernel/cpu_setup_power.c
+++ b/arch/powerpc/kernel/cpu_setup_power.c
@@ -123,6 +123,7 @@ static void init_PMU_ISA31(void)
{
mtspr(SPRN_MMCR3, 0);
mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
+ mtspr(SPRN_MMCR0, MMCR0_PMCCEXT);
}
/*
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 1098863..9d07965 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -454,6 +454,7 @@ static void init_pmu_power10(void)
mtspr(SPRN_MMCR3, 0);
mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
+ mtspr(SPRN_MMCR0, MMCR0_PMCCEXT);
}
static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 3c8c6ce..35cf93c 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -95,6 +95,7 @@ struct cpu_hw_events {
#define SPRN_SIER3 0
#define MMCRA_SAMPLE_ENABLE 0
#define MMCRA_BHRB_DISABLE 0
+#define MMCR0_PMCCEXT 0
static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
{
@@ -1270,6 +1271,9 @@ static void power_pmu_disable(struct pmu *pmu)
val |= MMCR0_FC;
val &= ~(MMCR0_EBE | MMCR0_BHRBA | MMCR0_PMCC | MMCR0_PMAO |
MMCR0_FC56);
+ /* Set mmcr0 PMCCEXT for p10 */
+ if (ppmu->flags & PPMU_ARCH_31)
+ val |= MMCR0_PMCCEXT;
/*
* The barrier is to make sure the mtspr has been
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 0f4983e..24f0a90 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -558,6 +558,14 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
if (!(pmc_inuse & 0x60))
mmcr->mmcr0 |= MMCR0_FC56;
+ /*
+ * Set mmcr0 (PMCCEXT) for p10 which
+ * will restrict access to group B registers
+ * when MMCR0 PMCC=0b00.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ mmcr->mmcr0 |= MMCR0_PMCCEXT;
+
mmcr->mmcr1 = mmcr1;
mmcr->mmcra = mmcra;
mmcr->mmcr2 = mmcr2;
--
1.8.3.1
^ permalink raw reply related
* [PATCH V2 6/7] powerpc/perf: Fix to update cache events with l2l3 events in power10
From: Athira Rajeev @ 2020-11-26 16:54 UTC (permalink / raw)
To: mpe; +Cc: maddy, linuxppc-dev
In-Reply-To: <1606409684-1589-1-git-send-email-atrajeev@linux.vnet.ibm.com>
Export l2l3 events (PM_L2_ST_MISS and PM_L2_ST) and LLC-prefetches
(PM_L3_PF_MISS_L3) via sysfs, and also add these to list of
cache_events.
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/perf/power10-events-list.h | 6 ++++++
arch/powerpc/perf/power10-pmu.c | 12 +++++++++---
2 files changed, 15 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/perf/power10-events-list.h b/arch/powerpc/perf/power10-events-list.h
index abd778f..e45dafe 100644
--- a/arch/powerpc/perf/power10-events-list.h
+++ b/arch/powerpc/perf/power10-events-list.h
@@ -39,6 +39,12 @@
EVENT(PM_DATA_FROM_L3, 0x01340000001c040);
/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */
EVENT(PM_DATA_FROM_L3MISS, 0x300fe);
+/* All successful D-side store dispatches for this thread */
+EVENT(PM_L2_ST, 0x010000046080);
+/* All successful D-side store dispatches for this thread that were L2 Miss */
+EVENT(PM_L2_ST_MISS, 0x26880);
+/* Total HW L3 prefetches(Load+store) */
+EVENT(PM_L3_PF_MISS_L3, 0x100000016080);
/* Data PTEG reload */
EVENT(PM_DTLB_MISS, 0x300fc);
/* ITLB Reloaded */
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index a02da69..79e0206 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -127,6 +127,9 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
CACHE_EVENT_ATTR(L1-icache-prefetches, PM_IC_PREF_REQ);
CACHE_EVENT_ATTR(LLC-load-misses, PM_DATA_FROM_L3MISS);
CACHE_EVENT_ATTR(LLC-loads, PM_DATA_FROM_L3);
+CACHE_EVENT_ATTR(LLC-prefetches, PM_L3_PF_MISS_L3);
+CACHE_EVENT_ATTR(LLC-store-misses, PM_L2_ST_MISS);
+CACHE_EVENT_ATTR(LLC-stores, PM_L2_ST);
CACHE_EVENT_ATTR(branch-load-misses, PM_BR_MPRED_CMPL);
CACHE_EVENT_ATTR(branch-loads, PM_BR_CMPL);
CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS);
@@ -175,6 +178,9 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
CACHE_EVENT_PTR(PM_IC_PREF_REQ),
CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS),
CACHE_EVENT_PTR(PM_DATA_FROM_L3),
+ CACHE_EVENT_PTR(PM_L3_PF_MISS_L3),
+ CACHE_EVENT_PTR(PM_L2_ST_MISS),
+ CACHE_EVENT_PTR(PM_L2_ST),
CACHE_EVENT_PTR(PM_BR_MPRED_CMPL),
CACHE_EVENT_PTR(PM_BR_CMPL),
CACHE_EVENT_PTR(PM_DTLB_MISS),
@@ -460,11 +466,11 @@ static void power10_config_bhrb(u64 pmu_bhrb_filter)
[C(RESULT_MISS)] = PM_DATA_FROM_L3MISS,
},
[C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = -1,
- [C(RESULT_MISS)] = -1,
+ [C(RESULT_ACCESS)] = PM_L2_ST,
+ [C(RESULT_MISS)] = PM_L2_ST_MISS,
},
[C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_ACCESS)] = PM_L3_PF_MISS_L3,
[C(RESULT_MISS)] = 0,
},
},
--
1.8.3.1
^ permalink raw reply related
* [PATCH V2 5/7] powerpc/perf: Fix to update generic event codes for power10
From: Athira Rajeev @ 2020-11-26 16:54 UTC (permalink / raw)
To: mpe; +Cc: maddy, linuxppc-dev
In-Reply-To: <1606409684-1589-1-git-send-email-atrajeev@linux.vnet.ibm.com>
Fix the event code for events: branch-instructions (to PM_BR_FIN),
branch-misses (to PM_MPRED_BR_FIN) and cache-misses (to
PM_LD_DEMAND_MISS_L1_FIN) for power10 PMU. Update the
list of generic events with this modified event code.
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/perf/power10-events-list.h | 3 +++
arch/powerpc/perf/power10-pmu.c | 15 +++++++++------
2 files changed, 12 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/perf/power10-events-list.h b/arch/powerpc/perf/power10-events-list.h
index 60c1b81..abd778f 100644
--- a/arch/powerpc/perf/power10-events-list.h
+++ b/arch/powerpc/perf/power10-events-list.h
@@ -15,6 +15,9 @@
EVENT(PM_RUN_INST_CMPL, 0x500fa);
EVENT(PM_BR_CMPL, 0x4d05e);
EVENT(PM_BR_MPRED_CMPL, 0x400f6);
+EVENT(PM_BR_FIN, 0x2f04a);
+EVENT(PM_MPRED_BR_FIN, 0x3e098);
+EVENT(PM_LD_DEMAND_MISS_L1_FIN, 0x400f0);
/* All L1 D cache load references counted at finish, gated by reject */
EVENT(PM_LD_REF_L1, 0x100fc);
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index bc3d4dd..a02da69 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -114,6 +114,9 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1);
GENERIC_EVENT_ATTR(mem-loads, MEM_LOADS);
GENERIC_EVENT_ATTR(mem-stores, MEM_STORES);
+GENERIC_EVENT_ATTR(branch-instructions, PM_BR_FIN);
+GENERIC_EVENT_ATTR(branch-misses, PM_MPRED_BR_FIN);
+GENERIC_EVENT_ATTR(cache-misses, PM_LD_DEMAND_MISS_L1_FIN);
CACHE_EVENT_ATTR(L1-dcache-load-misses, PM_LD_MISS_L1);
CACHE_EVENT_ATTR(L1-dcache-loads, PM_LD_REF_L1);
@@ -157,10 +160,10 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
static struct attribute *power10_events_attr[] = {
GENERIC_EVENT_PTR(PM_RUN_CYC),
GENERIC_EVENT_PTR(PM_RUN_INST_CMPL),
- GENERIC_EVENT_PTR(PM_BR_CMPL),
- GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL),
+ GENERIC_EVENT_PTR(PM_BR_FIN),
+ GENERIC_EVENT_PTR(PM_MPRED_BR_FIN),
GENERIC_EVENT_PTR(PM_LD_REF_L1),
- GENERIC_EVENT_PTR(PM_LD_MISS_L1),
+ GENERIC_EVENT_PTR(PM_LD_DEMAND_MISS_L1_FIN),
GENERIC_EVENT_PTR(MEM_LOADS),
GENERIC_EVENT_PTR(MEM_STORES),
CACHE_EVENT_PTR(PM_LD_MISS_L1),
@@ -259,10 +262,10 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
static int power10_generic_events[] = {
[PERF_COUNT_HW_CPU_CYCLES] = PM_RUN_CYC,
[PERF_COUNT_HW_INSTRUCTIONS] = PM_RUN_INST_CMPL,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_CMPL,
- [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_FIN,
+ [PERF_COUNT_HW_BRANCH_MISSES] = PM_MPRED_BR_FIN,
[PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1,
- [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1,
+ [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_DEMAND_MISS_L1_FIN,
};
static u64 power10_bhrb_filter_map(u64 branch_sample_type)
--
1.8.3.1
^ permalink raw reply related
* [PATCH V2 3/7] powerpc/perf: Fix the PMU group constraints for threshold events in power10
From: Athira Rajeev @ 2020-11-26 16:54 UTC (permalink / raw)
To: mpe; +Cc: maddy, linuxppc-dev
In-Reply-To: <1606409684-1589-1-git-send-email-atrajeev@linux.vnet.ibm.com>
The PMU group constraints mask for threshold events covers
all thresholding bits which includes threshold control value
(start/stop), select value as well as thresh_cmp value (MMCRA[9:18].
In power9, thresh_cmp bits were part of the event code. But in case
of power10, thresh_cmp bits are not part of event code due to
inclusion of MMCR3 bits. Hence thresh_cmp is not valid for
group constraints for power10.
Fix the PMU group constraints checking for threshold events in
power10 by using constraint mask and value for only threshold control
and select bits.
Fixes: a64e697cef23 ("powerpc/perf: power10 Performance Monitoring support")
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/perf/isa207-common.c | 7 ++++++-
arch/powerpc/perf/isa207-common.h | 3 +++
2 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 38ed450c..0f4983e 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -351,7 +351,12 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
}
- if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ if (event_is_threshold(event)) {
+ mask |= CNST_THRESH_CTL_SEL_MASK;
+ value |= CNST_THRESH_CTL_SEL_VAL(event >> EVENT_THRESH_SHIFT);
+ }
+ } else if (cpu_has_feature(CPU_FTR_ARCH_300)) {
if (event_is_threshold(event) && is_thresh_cmp_valid(event)) {
mask |= CNST_THRESH_MASK;
value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT);
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index dc9c3d2..4208764 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -149,6 +149,9 @@
#define CNST_THRESH_VAL(v) (((v) & EVENT_THRESH_MASK) << 32)
#define CNST_THRESH_MASK CNST_THRESH_VAL(EVENT_THRESH_MASK)
+#define CNST_THRESH_CTL_SEL_VAL(v) (((v) & 0x7ffull) << 32)
+#define CNST_THRESH_CTL_SEL_MASK CNST_THRESH_CTL_SEL_VAL(0x7ff)
+
#define CNST_EBB_VAL(v) (((v) & EVENT_EBB_MASK) << 24)
#define CNST_EBB_MASK CNST_EBB_VAL(EVENT_EBB_MASK)
--
1.8.3.1
^ permalink raw reply related
* [PATCH V2 0/7] powerpc/perf: Fixes for power10 PMU
From: Athira Rajeev @ 2020-11-26 16:54 UTC (permalink / raw)
To: mpe; +Cc: maddy, linuxppc-dev
Patchset contains PMU fixes for power10.
This patchset contains 7 patches.
Patch1 includes fix to update event code with radix_scope_qual
bit in power10.
Patch2 and Patch3 updates the event group constraints for L2/L3
and threshold events in power10.
Patch4, patch5 and patch6 includes the event code changes for
l2/l3 events and some of the generic events.
Patch7 adds fixes for PMCCEXT bit in power10.
Changelog:
Changes from v1 -> v2
- Addressed Michael Ellerman's comments in the patchset.
Split patch 2 to address l2l3 and threshold events
group constraints fixes separately.
Split Patch 3 also to address event code updates
separately for generic and cache events.
Fixed commit messages and also PMCCEXT bit setting
during event enable.
Athira Rajeev (7):
powerpc/perf: Fix to update radix_scope_qual in power10
powerpc/perf: Update the PMU group constraints for l2l3 events in
power10
powerpc/perf: Fix the PMU group constraints for threshold events in
power10
powerpc/perf: Add generic and cache event list for power10 DD1
powerpc/perf: Fix to update generic event codes for power10
powerpc/perf: Fix to update cache events with l2l3 events in power10
powerpc/perf: MMCR0 control for PMU registers under PMCC=00
arch/powerpc/include/asm/reg.h | 1 +
arch/powerpc/kernel/cpu_setup_power.c | 1 +
arch/powerpc/kernel/dt_cpu_ftrs.c | 1 +
arch/powerpc/perf/core-book3s.c | 4 +
arch/powerpc/perf/isa207-common.c | 35 ++++++-
arch/powerpc/perf/isa207-common.h | 16 ++-
arch/powerpc/perf/power10-events-list.h | 9 ++
arch/powerpc/perf/power10-pmu.c | 178 ++++++++++++++++++++++++++++++--
8 files changed, 231 insertions(+), 14 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH V2 2/7] powerpc/perf: Update the PMU group constraints for l2l3 events in power10
From: Athira Rajeev @ 2020-11-26 16:54 UTC (permalink / raw)
To: mpe; +Cc: maddy, linuxppc-dev
In-Reply-To: <1606409684-1589-1-git-send-email-atrajeev@linux.vnet.ibm.com>
In Power9, L2/L3 bus events are always available as a
"bank" of 4 events. To obtain the counts for any of the
l2/l3 bus events in a given bank, the user will have to
program PMC4 with corresponding l2/l3 bus event for that
bank.
Commit 59029136d750 ("powerpc/perf: Add constraints for power9 l2/l3 bus events")
enforced this rule in Power9. But this is not valid for
Power10, since in Power10 Monitor Mode Control Register2
(MMCR2) has bits to configure l2/l3 event bits. Hence remove
this PMC4 constraint check from power10.
Since the l2/l3 bits in MMCR2 are not per-pmc, patch handles
group constrints checks for l2/l3 bits in MMCR2.
Fixes: a64e697cef23 ("powerpc/perf: power10 Performance Monitoring support")
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/perf/isa207-common.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index f57f54f..38ed450c 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -311,9 +311,11 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
}
if (unit >= 6 && unit <= 9) {
- if (cpu_has_feature(CPU_FTR_ARCH_31) && (unit == 6)) {
- mask |= CNST_L2L3_GROUP_MASK;
- value |= CNST_L2L3_GROUP_VAL(event >> p10_L2L3_EVENT_SHIFT);
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ if (unit == 6) {
+ mask |= CNST_L2L3_GROUP_MASK;
+ value |= CNST_L2L3_GROUP_VAL(event >> p10_L2L3_EVENT_SHIFT);
+ }
} else if (cpu_has_feature(CPU_FTR_ARCH_300)) {
mask |= CNST_CACHE_GROUP_MASK;
value |= CNST_CACHE_GROUP_VAL(event & 0xff);
--
1.8.3.1
^ permalink raw reply related
* [PATCH V2 1/7] powerpc/perf: Fix to update radix_scope_qual in power10
From: Athira Rajeev @ 2020-11-26 16:54 UTC (permalink / raw)
To: mpe; +Cc: maddy, linuxppc-dev
In-Reply-To: <1606409684-1589-1-git-send-email-atrajeev@linux.vnet.ibm.com>
power10 uses bit 9 of the raw event code as RADIX_SCOPE_QUAL.
This bit is used for enabling the radix process events.
Patch fixes the PMU counter support functions to program bit
18 of MMCR1 ( Monitor Mode Control Register1 ) with the
RADIX_SCOPE_QUAL bit value. Since this field is not per-pmc,
add this to PMU group constraints to make sure events in a
group will have same bit value for this field. Use bit 21 as
constraint bit field for radix_scope_qual. Patch also updates
the power10 raw event encoding layout information, format field
and constraints bit layout to include the radix_scope_qual bit.
Fixes: a64e697cef23 ("powerpc/perf: power10 Performance Monitoring support")
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/perf/isa207-common.c | 12 ++++++++++++
arch/powerpc/perf/isa207-common.h | 13 ++++++++++---
arch/powerpc/perf/power10-pmu.c | 11 +++++++----
3 files changed, 29 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 2848904..f57f54f 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -339,6 +339,11 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
value |= CNST_L1_QUAL_VAL(cache);
}
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ mask |= CNST_RADIX_SCOPE_GROUP_MASK;
+ value |= CNST_RADIX_SCOPE_GROUP_VAL(event >> p10_EVENT_RADIX_SCOPE_QUAL_SHIFT);
+ }
+
if (is_event_marked(event)) {
mask |= CNST_SAMPLE_MASK;
value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
@@ -456,6 +461,13 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
}
}
+ /* Set RADIX_SCOPE_QUAL bit */
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ val = (event[i] >> p10_EVENT_RADIX_SCOPE_QUAL_SHIFT) &
+ p10_EVENT_RADIX_SCOPE_QUAL_MASK;
+ mmcr1 |= val << p10_MMCR1_RADIX_SCOPE_QUAL_SHIFT;
+ }
+
if (is_event_marked(event[i])) {
mmcra |= MMCRA_SAMPLE_ENABLE;
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 7025de5..dc9c3d2 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -101,6 +101,9 @@
#define p10_EVENT_CACHE_SEL_MASK 0x3ull
#define p10_EVENT_MMCR3_MASK 0x7fffull
#define p10_EVENT_MMCR3_SHIFT 45
+#define p10_EVENT_RADIX_SCOPE_QUAL_SHIFT 9
+#define p10_EVENT_RADIX_SCOPE_QUAL_MASK 0x1
+#define p10_MMCR1_RADIX_SCOPE_QUAL_SHIFT 45
#define p10_EVENT_VALID_MASK \
((p10_SDAR_MODE_MASK << p10_SDAR_MODE_SHIFT | \
@@ -112,6 +115,7 @@
(p9_EVENT_COMBINE_MASK << p9_EVENT_COMBINE_SHIFT) | \
(p10_EVENT_MMCR3_MASK << p10_EVENT_MMCR3_SHIFT) | \
(EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) | \
+ (p10_EVENT_RADIX_SCOPE_QUAL_MASK << p10_EVENT_RADIX_SCOPE_QUAL_SHIFT) | \
EVENT_LINUX_MASK | \
EVENT_PSEL_MASK))
/*
@@ -125,9 +129,9 @@
*
* 28 24 20 16 12 8 4 0
* | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- * [ ] | [ ] [ sample ] [ ] [6] [5] [4] [3] [2] [1]
- * | | | |
- * BHRB IFM -* | | | Count of events for each PMC.
+ * [ ] | [ ] | [ sample ] [ ] [6] [5] [4] [3] [2] [1]
+ * | | | | |
+ * BHRB IFM -* | | |*radix_scope | Count of events for each PMC.
* EBB -* | | p1, p2, p3, p4, p5, p6.
* L1 I/D qualifier -* |
* nc - number of counters -*
@@ -165,6 +169,9 @@
#define CNST_L2L3_GROUP_VAL(v) (((v) & 0x1full) << 55)
#define CNST_L2L3_GROUP_MASK CNST_L2L3_GROUP_VAL(0x1f)
+#define CNST_RADIX_SCOPE_GROUP_VAL(v) (((v) & 0x1ull) << 21)
+#define CNST_RADIX_SCOPE_GROUP_MASK CNST_RADIX_SCOPE_GROUP_VAL(1)
+
/*
* For NC we are counting up to 4 events. This requires three bits, and we need
* the fifth event to overflow and set the 4th bit. To achieve that we bias the
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index a01e87f..88c5430 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -23,10 +23,10 @@
*
* 28 24 20 16 12 8 4 0
* | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- * [ ] [ sample ] [ ] [ ] [ pmc ] [unit ] [ ] m [ pmcxsel ]
- * | | | | | |
- * | | | | | *- mark
- * | | | *- L1/L2/L3 cache_sel |
+ * [ ] [ sample ] [ ] [ ] [ pmc ] [unit ] [ ] | m [ pmcxsel ]
+ * | | | | | | |
+ * | | | | | | *- mark
+ * | | | *- L1/L2/L3 cache_sel | |*-radix_scope_qual
* | | sdar_mode |
* | *- sampling mode for marked events *- combine
* |
@@ -59,6 +59,7 @@
*
* MMCR1[16] = cache_sel[0]
* MMCR1[17] = cache_sel[1]
+ * MMCR1[18] = radix_scope_qual
*
* if mark:
* MMCRA[63] = 1 (SAMPLE_ENABLE)
@@ -175,6 +176,7 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
PMU_FORMAT_ATTR(invert_bit, "config:47");
PMU_FORMAT_ATTR(src_mask, "config:48-53");
PMU_FORMAT_ATTR(src_match, "config:54-59");
+PMU_FORMAT_ATTR(radix_scope, "config:9");
static struct attribute *power10_pmu_format_attr[] = {
&format_attr_event.attr,
@@ -194,6 +196,7 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
&format_attr_invert_bit.attr,
&format_attr_src_mask.attr,
&format_attr_src_match.attr,
+ &format_attr_radix_scope.attr,
NULL,
};
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH v2 4/6] arm64/mm: Implement pXX_leaf_size() support
From: Will Deacon @ 2020-11-26 14:32 UTC (permalink / raw)
To: Peter Zijlstra
Cc: mark.rutland, aneesh.kumar, willy, catalin.marinas,
alexander.shishkin, linuxppc-dev, npiggin, linux-kernel, acme,
davem, dave.hansen, ak, eranian, linux-arch, sparclinux, jolsa,
mingo, kirill.shutemov, kan.liang
In-Reply-To: <20201126125747.GG2414@hirez.programming.kicks-ass.net>
On Thu, Nov 26, 2020 at 01:57:47PM +0100, Peter Zijlstra wrote:
>
> Now with pmd_cont() defined...
>
> ---
> Subject: arm64/mm: Implement pXX_leaf_size() support
> From: Peter Zijlstra <peterz@infradead.org>
> Date: Fri Nov 13 11:46:06 CET 2020
>
> ARM64 has non-pagetable aligned large page support with PTE_CONT, when
> this bit is set the page is part of a super-page. Match the hugetlb
> code and support these super pages for PTE and PMD levels.
>
> This enables PERF_SAMPLE_{DATA,CODE}_PAGE_SIZE to report accurate
> pagetable leaf sizes.
>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
> arch/arm64/include/asm/pgtable.h | 4 ++++
> 1 file changed, 4 insertions(+)
>
> --- a/arch/arm64/include/asm/pgtable.h
> +++ b/arch/arm64/include/asm/pgtable.h
> @@ -407,6 +407,7 @@ static inline int pmd_trans_huge(pmd_t p
> #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd))
> #define pmd_young(pmd) pte_young(pmd_pte(pmd))
> #define pmd_valid(pmd) pte_valid(pmd_pte(pmd))
> +#define pmd_cont(pmd) pte_cont(pmd_pte(pmd))
> #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd)))
> #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd)))
> #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd)))
> @@ -503,6 +504,9 @@ extern pgprot_t phys_mem_access_prot(str
> PMD_TYPE_SECT)
> #define pmd_leaf(pmd) pmd_sect(pmd)
>
> +#define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE)
> +#define pte_leaf_size(pte) (pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE)
> +
> #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3
> static inline bool pud_sect(pud_t pud) { return false; }
> static inline bool pud_table(pud_t pud) { return true; }
Acked-by: Will Deacon <will@kernel.org>
I'm still highly dubious about the utility of this feature in perf, since
the TLB entry size is pretty much independent of the page-table
configuration, but that's a problem for all architectures I suspect.
Will
^ permalink raw reply
* [PATCH 8/8] net: ethernet: ibm: ibmvnic: Fix some kernel-doc issues
From: Lee Jones @ 2020-11-26 13:38 UTC (permalink / raw)
To: lee.jones
Cc: Thomas Falcon, John Allen, linux-kernel, Santiago Leon,
Jakub Kicinski, netdev, Lijun Pan, Dany Madden, Paul Mackerras,
Sukadev Bhattiprolu, linuxppc-dev, David S. Miller
In-Reply-To: <20201126133853.3213268-1-lee.jones@linaro.org>
Fixes the following W=1 kernel build warning(s):
from drivers/net/ethernet/ibm/ibmvnic.c:35:
inlined from ‘handle_vpd_rsp’ at drivers/net/ethernet/ibm/ibmvnic.c:4124:3:
drivers/net/ethernet/ibm/ibmvnic.c:1362: warning: Function parameter or member 'hdr_data' not described in 'build_hdr_data'
drivers/net/ethernet/ibm/ibmvnic.c:1362: warning: Excess function parameter 'tot_len' description in 'build_hdr_data'
drivers/net/ethernet/ibm/ibmvnic.c:1423: warning: Function parameter or member 'hdr_data' not described in 'create_hdr_descs'
drivers/net/ethernet/ibm/ibmvnic.c:1423: warning: Excess function parameter 'data' description in 'create_hdr_descs'
drivers/net/ethernet/ibm/ibmvnic.c:1474: warning: Function parameter or member 'txbuff' not described in 'build_hdr_descs_arr'
drivers/net/ethernet/ibm/ibmvnic.c:1474: warning: Excess function parameter 'skb' description in 'build_hdr_descs_arr'
drivers/net/ethernet/ibm/ibmvnic.c:1474: warning: Excess function parameter 'subcrq' description in 'build_hdr_descs_arr'
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Dany Madden <drt@linux.ibm.com>
Cc: Lijun Pan <ljp@linux.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Santiago Leon <santi_leon@yahoo.com>
Cc: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Cc: John Allen <jallen@linux.vnet.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: netdev@vger.kernel.org
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
drivers/net/ethernet/ibm/ibmvnic.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 36ea37721e3c8..0687f6cb0c7a2 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1379,7 +1379,7 @@ static int ibmvnic_close(struct net_device *netdev)
* @hdr_field: bitfield determining needed headers
* @skb: socket buffer
* @hdr_len: array of header lengths
- * @tot_len: total length of data
+ * @hdr_data: buffer to write the header to
*
* Reads hdr_field to determine which headers are needed by firmware.
* Builds a buffer containing these headers. Saves individual header
@@ -1437,7 +1437,7 @@ static int build_hdr_data(u8 hdr_field, struct sk_buff *skb,
/**
* create_hdr_descs - create header and header extension descriptors
* @hdr_field: bitfield determining needed headers
- * @data: buffer containing header data
+ * @hdr_data: buffer containing header data
* @len: length of data buffer
* @hdr_len: array of individual header lengths
* @scrq_arr: descriptor array
@@ -1488,9 +1488,8 @@ static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len,
/**
* build_hdr_descs_arr - build a header descriptor array
- * @skb: socket buffer
+ * @txbuff: tx buffer
* @num_entries: number of descriptors to be sent
- * @subcrq: first TX descriptor
* @hdr_field: bit field determining which headers will be sent
*
* This function will build a TX descriptor array with applicable
--
2.25.1
^ permalink raw reply related
* [PATCH 6/8] net: ethernet: toshiba: ps3_gelic_net: Fix some kernel-doc misdemeanours
From: Lee Jones @ 2020-11-26 13:38 UTC (permalink / raw)
To: lee.jones
Cc: Geoff Levand, linux-kernel, Jens Osterkamp, netdev,
Paul Mackerras, Utz Bacher, Jakub Kicinski, linuxppc-dev,
David S. Miller
In-Reply-To: <20201126133853.3213268-1-lee.jones@linaro.org>
Fixes the following W=1 kernel build warning(s):
drivers/net/ethernet/toshiba/ps3_gelic_net.c:1107: warning: Function parameter or member 'irq' not described in 'gelic_card_interrupt'
drivers/net/ethernet/toshiba/ps3_gelic_net.c:1107: warning: Function parameter or member 'ptr' not described in 'gelic_card_interrupt'
drivers/net/ethernet/toshiba/ps3_gelic_net.c:1407: warning: Function parameter or member 'txqueue' not described in 'gelic_net_tx_timeout'
drivers/net/ethernet/toshiba/ps3_gelic_net.c:1439: warning: Function parameter or member 'napi' not described in 'gelic_ether_setup_netdev_ops'
drivers/net/ethernet/toshiba/ps3_gelic_net.c:1639: warning: Function parameter or member 'dev' not described in 'ps3_gelic_driver_probe'
drivers/net/ethernet/toshiba/ps3_gelic_net.c:1795: warning: Function parameter or member 'dev' not described in 'ps3_gelic_driver_remove'
Cc: Geoff Levand <geoff@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Utz Bacher <utz.bacher@de.ibm.com>
Cc: Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
Cc: netdev@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
drivers/net/ethernet/toshiba/ps3_gelic_net.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index d9a5722f561b5..f886e23f8ed0a 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -1100,7 +1100,7 @@ static int gelic_net_poll(struct napi_struct *napi, int budget)
return packets_done;
}
-/**
+/*
* gelic_card_interrupt - event handler for gelic_net
*/
static irqreturn_t gelic_card_interrupt(int irq, void *ptr)
@@ -1400,6 +1400,7 @@ static void gelic_net_tx_timeout_task(struct work_struct *work)
/**
* gelic_net_tx_timeout - called when the tx timeout watchdog kicks in.
* @netdev: interface device structure
+ * @txqueue: unused
*
* called, if tx hangs. Schedules a task that resets the interface
*/
@@ -1431,6 +1432,7 @@ static const struct net_device_ops gelic_netdevice_ops = {
/**
* gelic_ether_setup_netdev_ops - initialization of net_device operations
* @netdev: net_device structure
+ * @napi: napi structure
*
* fills out function pointers in the net_device structure
*/
@@ -1632,7 +1634,7 @@ static void gelic_card_get_vlan_info(struct gelic_card *card)
dev_info(ctodev(card), "internal vlan %s\n",
card->vlan_required? "enabled" : "disabled");
}
-/**
+/*
* ps3_gelic_driver_probe - add a device to the control of this driver
*/
static int ps3_gelic_driver_probe(struct ps3_system_bus_device *dev)
@@ -1787,10 +1789,9 @@ static int ps3_gelic_driver_probe(struct ps3_system_bus_device *dev)
return result;
}
-/**
+/*
* ps3_gelic_driver_remove - remove a device from the control of this driver
*/
-
static int ps3_gelic_driver_remove(struct ps3_system_bus_device *dev)
{
struct gelic_card *card = ps3_system_bus_get_drvdata(dev);
--
2.25.1
^ permalink raw reply related
* [PATCH 5/8] net: ethernet: ibm: ibmvnic: Fix some kernel-doc misdemeanours
From: Lee Jones @ 2020-11-26 13:38 UTC (permalink / raw)
To: lee.jones
Cc: Thomas Falcon, John Allen, linux-kernel, Santiago Leon,
Jakub Kicinski, netdev, Lijun Pan, Dany Madden, Paul Mackerras,
Sukadev Bhattiprolu, linuxppc-dev, David S. Miller
In-Reply-To: <20201126133853.3213268-1-lee.jones@linaro.org>
Fixes the following W=1 kernel build warning(s):
from drivers/net/ethernet/ibm/ibmvnic.c:35:
inlined from ‘handle_vpd_rsp’ at drivers/net/ethernet/ibm/ibmvnic.c:4124:3:
drivers/net/ethernet/ibm/ibmvnic.c:1362: warning: Function parameter or member 'hdr_field' not described in 'build_hdr_data'
drivers/net/ethernet/ibm/ibmvnic.c:1362: warning: Function parameter or member 'skb' not described in 'build_hdr_data'
drivers/net/ethernet/ibm/ibmvnic.c:1362: warning: Function parameter or member 'hdr_len' not described in 'build_hdr_data'
drivers/net/ethernet/ibm/ibmvnic.c:1362: warning: Function parameter or member 'hdr_data' not described in 'build_hdr_data'
drivers/net/ethernet/ibm/ibmvnic.c:1423: warning: Function parameter or member 'hdr_field' not described in 'create_hdr_descs'
drivers/net/ethernet/ibm/ibmvnic.c:1423: warning: Function parameter or member 'hdr_data' not described in 'create_hdr_descs'
drivers/net/ethernet/ibm/ibmvnic.c:1423: warning: Function parameter or member 'len' not described in 'create_hdr_descs'
drivers/net/ethernet/ibm/ibmvnic.c:1423: warning: Function parameter or member 'hdr_len' not described in 'create_hdr_descs'
drivers/net/ethernet/ibm/ibmvnic.c:1423: warning: Function parameter or member 'scrq_arr' not described in 'create_hdr_descs'
drivers/net/ethernet/ibm/ibmvnic.c:1474: warning: Function parameter or member 'txbuff' not described in 'build_hdr_descs_arr'
drivers/net/ethernet/ibm/ibmvnic.c:1474: warning: Function parameter or member 'num_entries' not described in 'build_hdr_descs_arr'
drivers/net/ethernet/ibm/ibmvnic.c:1474: warning: Function parameter or member 'hdr_field' not described in 'build_hdr_descs_arr'
drivers/net/ethernet/ibm/ibmvnic.c:1832: warning: Function parameter or member 'adapter' not described in 'do_change_param_reset'
drivers/net/ethernet/ibm/ibmvnic.c:1832: warning: Function parameter or member 'rwi' not described in 'do_change_param_reset'
drivers/net/ethernet/ibm/ibmvnic.c:1832: warning: Function parameter or member 'reset_state' not described in 'do_change_param_reset'
drivers/net/ethernet/ibm/ibmvnic.c:1911: warning: Function parameter or member 'adapter' not described in 'do_reset'
drivers/net/ethernet/ibm/ibmvnic.c:1911: warning: Function parameter or member 'rwi' not described in 'do_reset'
drivers/net/ethernet/ibm/ibmvnic.c:1911: warning: Function parameter or member 'reset_state' not described in 'do_reset'
Cc: Dany Madden <drt@linux.ibm.com>
Cc: Lijun Pan <ljp@linux.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Santiago Leon <santi_leon@yahoo.com>
Cc: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Cc: John Allen <jallen@linux.vnet.ibm.com>
Cc: netdev@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
drivers/net/ethernet/ibm/ibmvnic.c | 28 ++++++++++++++--------------
drivers/net/xen-netfront.c | 6 +++---
2 files changed, 17 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index b0884eba568d7..36ea37721e3c8 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1376,10 +1376,10 @@ static int ibmvnic_close(struct net_device *netdev)
/**
* build_hdr_data - creates L2/L3/L4 header data buffer
- * @hdr_field - bitfield determining needed headers
- * @skb - socket buffer
- * @hdr_len - array of header lengths
- * @tot_len - total length of data
+ * @hdr_field: bitfield determining needed headers
+ * @skb: socket buffer
+ * @hdr_len: array of header lengths
+ * @tot_len: total length of data
*
* Reads hdr_field to determine which headers are needed by firmware.
* Builds a buffer containing these headers. Saves individual header
@@ -1436,11 +1436,11 @@ static int build_hdr_data(u8 hdr_field, struct sk_buff *skb,
/**
* create_hdr_descs - create header and header extension descriptors
- * @hdr_field - bitfield determining needed headers
- * @data - buffer containing header data
- * @len - length of data buffer
- * @hdr_len - array of individual header lengths
- * @scrq_arr - descriptor array
+ * @hdr_field: bitfield determining needed headers
+ * @data: buffer containing header data
+ * @len: length of data buffer
+ * @hdr_len: array of individual header lengths
+ * @scrq_arr: descriptor array
*
* Creates header and, if needed, header extension descriptors and
* places them in a descriptor array, scrq_arr
@@ -1488,10 +1488,10 @@ static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len,
/**
* build_hdr_descs_arr - build a header descriptor array
- * @skb - socket buffer
- * @num_entries - number of descriptors to be sent
- * @subcrq - first TX descriptor
- * @hdr_field - bit field determining which headers will be sent
+ * @skb: socket buffer
+ * @num_entries: number of descriptors to be sent
+ * @subcrq: first TX descriptor
+ * @hdr_field: bit field determining which headers will be sent
*
* This function will build a TX descriptor array with applicable
* L2/L3/L4 packet header descriptors to be sent by send_subcrq_indirect.
@@ -1997,7 +1997,7 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter,
return 0;
}
-/**
+/*
* do_reset returns zero if we are able to keep processing reset events, or
* non-zero if we hit a fatal error and must halt.
*/
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 920cac4385bf7..93740ef4cf1b4 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1582,7 +1582,7 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
return ERR_PTR(err);
}
-/**
+/*
* Entry point to this code when a new device is created. Allocate the basic
* structures and the ring buffers for communication with the backend, and
* inform the backend of the appropriate details for those.
@@ -1659,7 +1659,7 @@ static void xennet_disconnect_backend(struct netfront_info *info)
}
}
-/**
+/*
* We are reconnecting to the backend, due to a suspend/resume, or a backend
* driver restart. We tear down our netif structure and recreate it, but
* leave the device-layer structures intact so that this is transparent to the
@@ -2305,7 +2305,7 @@ static int xennet_connect(struct net_device *dev)
return 0;
}
-/**
+/*
* Callback received when the backend's state changes.
*/
static void netback_changed(struct xenbus_device *dev,
--
2.25.1
^ permalink raw reply related
* [PATCH 0/8] Rid W=1 warnings in Net
From: Lee Jones @ 2020-11-26 13:38 UTC (permalink / raw)
To: lee.jones
Cc: Paul Durrant, Kurt Kanzenbach, Alexei Starovoitov,
Gustavo A. R. Silva, Peter Cammaert, Paul Mackerras,
Sukadev Bhattiprolu, Wei Liu, Daniel Borkmann, John Fastabend,
Santiago Leon, Jakub Kicinski, Grygorii Strashko, Thomas Falcon,
Jesper Dangaard Brouer, Jens Osterkamp, Rusty Russell,
Daris A Nevil, Lijun Pan, xen-devel, Ivan Khoronzhuk,
Nicolas Pitre, Geoff Levand, netdev, linux-kernel, Erik Stahlman,
John Allen, Utz Bacher, Dany Madden, bpf, linuxppc-dev,
David S. Miller, Russell King
Resending the stragglers.
This set is part of a larger effort attempting to clean-up W=1
kernel builds, which are currently overwhelmingly riddled with
niggly little warnings.
Lee Jones (8):
net: ethernet: smsc: smc91x: Demote non-conformant kernel function
header
net: xen-netback: xenbus: Demote nonconformant kernel-doc headers
net: ethernet: ti: am65-cpsw-qos: Demote non-conformant function
header
net: ethernet: ti: am65-cpts: Document am65_cpts_rx_enable()'s 'en'
parameter
net: ethernet: ibm: ibmvnic: Fix some kernel-doc misdemeanours
net: ethernet: toshiba: ps3_gelic_net: Fix some kernel-doc
misdemeanours
net: ethernet: toshiba: spider_net: Document a whole bunch of function
parameters
net: ethernet: ibm: ibmvnic: Fix some kernel-doc issues
drivers/net/ethernet/ibm/ibmvnic.c | 27 ++++++++++----------
drivers/net/ethernet/smsc/smc91x.c | 2 +-
drivers/net/ethernet/ti/am65-cpsw-qos.c | 2 +-
drivers/net/ethernet/ti/am65-cpts.c | 2 +-
drivers/net/ethernet/toshiba/ps3_gelic_net.c | 9 ++++---
drivers/net/ethernet/toshiba/spider_net.c | 18 ++++++++-----
drivers/net/xen-netback/xenbus.c | 4 +--
drivers/net/xen-netfront.c | 6 ++---
8 files changed, 37 insertions(+), 33 deletions(-)
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: bpf@vger.kernel.org
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dany Madden <drt@linux.ibm.com>
Cc: Daris A Nevil <dnevil@snmc.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Erik Stahlman <erik@vt.edu>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Grygorii Strashko <grygorii.strashko@ti.com>
Cc: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Cc: Ishizaki Kou <kou.ishizaki@toshiba.co.jp>
Cc: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
Cc: Jesper Dangaard Brouer <hawk@kernel.org>
Cc: John Allen <jallen@linux.vnet.ibm.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Kurt Kanzenbach <kurt@linutronix.de>
Cc: Lijun Pan <ljp@linux.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: netdev@vger.kernel.org
Cc: Nicolas Pitre <nico@fluxnic.net>
Cc: Paul Durrant <paul@xen.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Cammaert <pc@denkart.be>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Santiago Leon <santi_leon@yahoo.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.ibm.com>
Cc: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Cc: Utz Bacher <utz.bacher@de.ibm.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: xen-devel@lists.xenproject.org
--
2.25.1
^ permalink raw reply
* Re: [PATCH v2 3/6] perf/core: Fix arch_perf_get_page_size()
From: Matthew Wilcox @ 2020-11-26 13:27 UTC (permalink / raw)
To: Peter Zijlstra
Cc: mark.rutland, aneesh.kumar, linux-arch, catalin.marinas, will,
alexander.shishkin, linuxppc-dev, npiggin, linux-kernel, acme,
davem, dave.hansen, ak, eranian, sparclinux, jolsa, mingo,
kirill.shutemov, kan.liang
In-Reply-To: <20201126130619.GI2414@hirez.programming.kicks-ass.net>
On Thu, Nov 26, 2020 at 02:06:19PM +0100, Peter Zijlstra wrote:
> On Thu, Nov 26, 2020 at 12:56:06PM +0000, Matthew Wilcox wrote:
> > On Thu, Nov 26, 2020 at 01:42:07PM +0100, Peter Zijlstra wrote:
> > > + pgdp = pgd_offset(mm, addr);
> > > + pgd = READ_ONCE(*pgdp);
> >
> > I forget how x86-32-PAE maps to Linux's PGD/P4D/PUD/PMD scheme, but
> > according to volume 3, section 4.4.2, PAE paging uses a 64-bit PDE, so
> > whether a PDE is a PGD or a PMD, we're only reading it with READ_ONCE
> > rather than the lockless-retry method used by ptep_get_lockless().
> > So it's potentially racy? Do we need a pmdp_get_lockless() or
> > pgdp_get_lockless()?
>
> Oh gawd... this isn't new here though, right? Current gup_fast also gets
> that wrong, if it is in deed wrong.
>
> I suppose it's a race far more likely today, with THP and all, than it
> ever was back then.
Right, it's not new. I wouldn't block this patchset for that fix.
Just want to get the problem on your radar ;-) I just never reviewed
the gup fast codepath before, and this jumped out at me.
^ permalink raw reply
* Re: [PATCH v4 2/2] lkdtm/powerpc: Add SLB multihit test
From: Ganesh @ 2020-11-26 13:27 UTC (permalink / raw)
To: Michael Ellerman
Cc: Michal Suchánek, linuxppc-dev, keescook, npiggin, mahesh
In-Reply-To: <20201019131541.GL29778@kitsune.suse.cz>
On 10/19/20 6:45 PM, Michal Suchánek wrote:
> On Mon, Oct 19, 2020 at 09:59:57PM +1100, Michael Ellerman wrote:
>> Hi Ganesh,
>>
>> Some comments below ...
>>
>> Ganesh Goudar <ganeshgr@linux.ibm.com> writes:
>>> To check machine check handling, add support to inject slb
>>> multihit errors.
>>>
>>> Cc: Kees Cook <keescook@chromium.org>
>>> Reviewed-by: Michal Suchánek <msuchanek@suse.de>
>>> Co-developed-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>
>>> Signed-off-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>
>>> Signed-off-by: Ganesh Goudar <ganeshgr@linux.ibm.com>
>>> ---
>>> drivers/misc/lkdtm/Makefile | 1 +
>>> drivers/misc/lkdtm/core.c | 3 +
>>> drivers/misc/lkdtm/lkdtm.h | 3 +
>>> drivers/misc/lkdtm/powerpc.c | 156 ++++++++++++++++++++++++
>>> tools/testing/selftests/lkdtm/tests.txt | 1 +
>>> 5 files changed, 164 insertions(+)
>>> create mode 100644 drivers/misc/lkdtm/powerpc.c
>>>
>> ..
>>> diff --git a/drivers/misc/lkdtm/powerpc.c b/drivers/misc/lkdtm/powerpc.c
>>> new file mode 100644
>>> index 000000000000..f388b53dccba
>>> --- /dev/null
>>> +++ b/drivers/misc/lkdtm/powerpc.c
>>> @@ -0,0 +1,156 @@
>>> +// SPDX-License-Identifier: GPL-2.0
>>> +
>>> +#include "lkdtm.h"
>>> +#include <linux/slab.h>
>>> +#include <linux/vmalloc.h>
>> Usual style is to include the linux headers first and then the local header.
ok
>>> +
>>> +/* Gets index for new slb entry */
>>> +static inline unsigned long get_slb_index(void)
>>> +{
>>> + unsigned long index;
>>> +
>>> + index = get_paca()->stab_rr;
>>> +
>>> + /*
>>> + * simple round-robin replacement of slb starting at SLB_NUM_BOLTED.
>>> + */
>>> + if (index < (mmu_slb_size - 1))
>>> + index++;
>>> + else
>>> + index = SLB_NUM_BOLTED;
>>> + get_paca()->stab_rr = index;
>>> + return index;
>>> +}
>> I'm not sure we need that really?
>>
>> We can just always insert at SLB_MUM_BOLTED and SLB_NUM_BOLTED + 1.
>>
>> Or we could allocate from the top down using mmu_slb_size - 1, and
>> mmu_slb_size - 2.
Ok, We can do that.
>>> +#define slb_esid_mask(ssize) \
>>> + (((ssize) == MMU_SEGSIZE_256M) ? ESID_MASK : ESID_MASK_1T)
>>> +
>>> +/* Form the operand for slbmte */
>>> +static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
>>> + unsigned long slot)
>>> +{
>>> + return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | slot;
>>> +}
>>> +
>>> +#define slb_vsid_shift(ssize) \
>>> + ((ssize) == MMU_SEGSIZE_256M ? SLB_VSID_SHIFT : SLB_VSID_SHIFT_1T)
>>> +
>>> +/* Form the operand for slbmte */
>>> +static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
>>> + unsigned long flags)
>>> +{
>>> + return (get_kernel_vsid(ea, ssize) << slb_vsid_shift(ssize)) | flags |
>>> + ((unsigned long)ssize << SLB_VSID_SSIZE_SHIFT);
>>> +}
>> I realise it's not much code, but I'd rather those were in a header,
>> rather than copied from slb.c. That way they can never skew vs the
>> versions in slb.c
>>
>> Best place I think would be arch/powerpc/include/asm/book3s/64/mmu-hash.h
Ok, ill move them.
>>> +
>>> +/* Inserts new slb entry */
>> It inserts two.
Right.
>>> +static void insert_slb_entry(char *p, int ssize)
>>> +{
>>> + unsigned long flags, entry;
>>> +
>>> + flags = SLB_VSID_KERNEL | mmu_psize_defs[MMU_PAGE_64K].sllp;
>> That won't work if the kernel is built for 4K pages. Or at least it
>> won't work the way we want it to.
>>
>> You should use mmu_linear_psize.
>>
>> But for vmalloc you should use mmu_vmalloc_psize, so it will need to be
>> a parameter.
Sure, Thanks
>>> + preempt_disable();
>>> +
>>> + entry = get_slb_index();
>>> + asm volatile("slbmte %0,%1" :
>>> + : "r" (mk_vsid_data((unsigned long)p, ssize, flags)),
>>> + "r" (mk_esid_data((unsigned long)p, ssize, entry))
>>> + : "memory");
>>> +
>>> + entry = get_slb_index();
>>> + asm volatile("slbmte %0,%1" :
>>> + : "r" (mk_vsid_data((unsigned long)p, ssize, flags)),
>>> + "r" (mk_esid_data((unsigned long)p, ssize, entry))
>>> + : "memory");
>>> + preempt_enable();
>>> + /*
>>> + * This triggers exception, If handled correctly we must recover
>>> + * from this error.
>>> + */
>>> + p[0] = '!';
>> That doesn't belong in here, it should be done by the caller.
>>
>> That would also mean p could be unsigned long in here, so you wouldn't
>> have to cast it four times.
Sure, ill change it.
>>> +}
>>> +
>>> +/* Inject slb multihit on vmalloc-ed address i.e 0xD00... */
>>> +static void inject_vmalloc_slb_multihit(void)
>>> +{
>>> + char *p;
>>> +
>>> + p = vmalloc(2048);
>> vmalloc() allocates whole pages, so it may as well be vmalloc(PAGE_SIZE).
ok
>>> + if (!p)
>>> + return;
>> That's unlikely, but it should be an error that's propagated up to the caller.
ok
>>> +
>>> + insert_slb_entry(p, MMU_SEGSIZE_1T);
>>> + vfree(p);
>>> +}
>>> +
>>> +/* Inject slb multihit on kmalloc-ed address i.e 0xC00... */
>>> +static void inject_kmalloc_slb_multihit(void)
>>> +{
>>> + char *p;
>>> +
>>> + p = kmalloc(2048, GFP_KERNEL);
>>> + if (!p)
>>> + return;
>>> +
>>> + insert_slb_entry(p, MMU_SEGSIZE_1T);
>>> + kfree(p);
>>> +}
>>> +
>>> +/*
>>> + * Few initial SLB entries are bolted. Add a test to inject
>>> + * multihit in bolted entry 0.
>>> + */
>>> +static void insert_dup_slb_entry_0(void)
>>> +{
>>> + unsigned long test_address = 0xC000000000000000;
>> Should use PAGE_OFFSET;
ok
>>> + volatile unsigned long *test_ptr;
>> Does it need to be a volatile?
>> The slbmte should act as a compiler barrier (it has a memory clobber)
>> and a CPU barrier as well?
Yes, volatile is not required, ill remove it.
>>> + unsigned long entry, i = 0;
>>> + unsigned long esid, vsid;
>> Please group your variables:
>>
>> unsigned long esid, vsid, entry, test_address, i;
>> volatile unsigned long *test_ptr;
>>
>> And then initialise them as appropriate.
ok
>>> + test_ptr = (unsigned long *)test_address;
>>> + preempt_disable();
>>> +
>>> + asm volatile("slbmfee %0,%1" : "=r" (esid) : "r" (i));
>>> + asm volatile("slbmfev %0,%1" : "=r" (vsid) : "r" (i));
>> Why do we need to read them out of the SLB rather than just computing
>> the values?
> It ensures that the entry is perfect duplicate without copying even more
> code from other parts of the kernel, doesn't it?
>
> Especially when inserting only one duplicate as suggested later it
> ensures that the test really does what it should.
>>> + entry = get_slb_index();
>>> +
>>> + /* for i !=0 we would need to mask out the old entry number */
>> Or you could just compute esid and then it wouldn't be an issue.
>>
>>> + asm volatile("slbmte %0,%1" :
>>> + : "r" (vsid),
>>> + "r" (esid | entry)
>>> + : "memory");
>> At this point we've just inserted a duplicate of entry 0. So you don't
>> need to insert a third entry do you?
> This code was obviously adapted from the previous one which needed two
> entries in case there was none for the memory region to start with.
>
> Addin only one duplicate should suffice and it can be easily tested that
> it still generates a MCE.
>
>>> + asm volatile("slbmfee %0,%1" : "=r" (esid) : "r" (i));
>>> + asm volatile("slbmfev %0,%1" : "=r" (vsid) : "r" (i));
>>> + entry = get_slb_index();
>>> +
>>> + /* for i !=0 we would need to mask out the old entry number */
>>> + asm volatile("slbmte %0,%1" :
>>> + : "r" (vsid),
>>> + "r" (esid | entry)
>>> + : "memory");
>>> +
>>> + pr_info("%s accessing test address 0x%lx: 0x%lx\n",
>>> + __func__, test_address, *test_ptr);
>> This prints the first two instructions of the kernel. I happen to know
>> what values they should have, but most people won't understand what
>> they're seeing. A better test would be to read the value at the top of
>> the function and then load it again here and check we got the right
>> thing.
> It does not really matter what we read back so long as the compiler does
> not optimize out the read. The point here is to access an address in the
> range covered by the SLB entry 0. The failure case is that the system
> crashes and the test never finishes.
>
> Thanks
>
> Michal
^ permalink raw reply
* Re: [PATCH v14 8/9] powerpc/vdso: Switch VDSO to generic C implementation.
From: Christophe Leroy @ 2020-11-26 13:20 UTC (permalink / raw)
To: Michael Ellerman, linuxppc-dev
In-Reply-To: <20201126131006.2431205-8-mpe@ellerman.id.au>
Le 26/11/2020 à 14:10, Michael Ellerman a écrit :
> From: Christophe Leroy <christophe.leroy@csgroup.eu>
>
> For VDSO32 on PPC64, we create a fake 32 bits config, on the same
> principle as MIPS architecture, in order to get the correct parts of
> the different asm header files.
The above is not done anymore since v13.
Christophe
>
> With the C VDSO, the performance is slightly lower, but it is worth
> it as it will ease maintenance and evolution, and also brings clocks
> that are not supported with the ASM VDSO.
>
> On an 8xx at 132 MHz, vdsotest with the ASM VDSO:
> gettimeofday: vdso: 828 nsec/call
> clock-getres-realtime-coarse: vdso: 391 nsec/call
> clock-gettime-realtime-coarse: vdso: 614 nsec/call
> clock-getres-realtime: vdso: 460 nsec/call
> clock-gettime-realtime: vdso: 876 nsec/call
> clock-getres-monotonic-coarse: vdso: 399 nsec/call
> clock-gettime-monotonic-coarse: vdso: 691 nsec/call
> clock-getres-monotonic: vdso: 460 nsec/call
> clock-gettime-monotonic: vdso: 1026 nsec/call
>
> On an 8xx at 132 MHz, vdsotest with the C VDSO:
> gettimeofday: vdso: 955 nsec/call
> clock-getres-realtime-coarse: vdso: 545 nsec/call
> clock-gettime-realtime-coarse: vdso: 592 nsec/call
> clock-getres-realtime: vdso: 545 nsec/call
> clock-gettime-realtime: vdso: 941 nsec/call
> clock-getres-monotonic-coarse: vdso: 545 nsec/call
> clock-gettime-monotonic-coarse: vdso: 591 nsec/call
> clock-getres-monotonic: vdso: 545 nsec/call
> clock-gettime-monotonic: vdso: 940 nsec/call
>
> It is even better for gettime with monotonic clocks.
>
> Unsupported clocks with ASM VDSO:
> clock-gettime-boottime: vdso: 3851 nsec/call
> clock-gettime-tai: vdso: 3852 nsec/call
> clock-gettime-monotonic-raw: vdso: 3396 nsec/call
>
> Same clocks with C VDSO:
> clock-gettime-tai: vdso: 941 nsec/call
> clock-gettime-monotonic-raw: vdso: 1001 nsec/call
> clock-gettime-monotonic-coarse: vdso: 591 nsec/call
>
> On an 8321E at 333 MHz, vdsotest with the ASM VDSO:
> gettimeofday: vdso: 220 nsec/call
> clock-getres-realtime-coarse: vdso: 102 nsec/call
> clock-gettime-realtime-coarse: vdso: 178 nsec/call
> clock-getres-realtime: vdso: 129 nsec/call
> clock-gettime-realtime: vdso: 235 nsec/call
> clock-getres-monotonic-coarse: vdso: 105 nsec/call
> clock-gettime-monotonic-coarse: vdso: 208 nsec/call
> clock-getres-monotonic: vdso: 129 nsec/call
> clock-gettime-monotonic: vdso: 274 nsec/call
>
> On an 8321E at 333 MHz, vdsotest with the C VDSO:
> gettimeofday: vdso: 272 nsec/call
> clock-getres-realtime-coarse: vdso: 160 nsec/call
> clock-gettime-realtime-coarse: vdso: 184 nsec/call
> clock-getres-realtime: vdso: 166 nsec/call
> clock-gettime-realtime: vdso: 281 nsec/call
> clock-getres-monotonic-coarse: vdso: 160 nsec/call
> clock-gettime-monotonic-coarse: vdso: 184 nsec/call
> clock-getres-monotonic: vdso: 169 nsec/call
> clock-gettime-monotonic: vdso: 275 nsec/call
>
> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
> [mpe: Tweak include guards]
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
> Link: https://lore.kernel.org/r/ef30ff8270a96c5c3b981523cd9b4e3d89049d3d.1604426550.git.christophe.leroy@csgroup.eu
> ---
> arch/powerpc/Kconfig | 2 +
> arch/powerpc/include/asm/vdso/vsyscall.h | 25 ++
> arch/powerpc/include/asm/vdso_datapage.h | 40 +--
> arch/powerpc/kernel/asm-offsets.c | 49 +---
> arch/powerpc/kernel/time.c | 91 +------
> arch/powerpc/kernel/vdso.c | 5 +-
> arch/powerpc/kernel/vdso32/Makefile | 26 +-
> arch/powerpc/kernel/vdso32/gettimeofday.S | 291 +---------------------
> arch/powerpc/kernel/vdso32/vdso32.lds.S | 1 +
> arch/powerpc/kernel/vdso64/Makefile | 23 +-
> arch/powerpc/kernel/vdso64/gettimeofday.S | 242 +-----------------
> arch/powerpc/kernel/vdso64/vdso64.lds.S | 2 +-
> 12 files changed, 106 insertions(+), 691 deletions(-)
> create mode 100644 arch/powerpc/include/asm/vdso/vsyscall.h
>
> v14: unchanged
>
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index 7f4995b245a3..aad8532a718e 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -176,6 +176,7 @@ config PPC
> select GENERIC_STRNCPY_FROM_USER
> select GENERIC_STRNLEN_USER
> select GENERIC_TIME_VSYSCALL
> + select GENERIC_GETTIMEOFDAY
> select HAVE_ARCH_AUDITSYSCALL
> select HAVE_ARCH_HUGE_VMAP if PPC_BOOK3S_64 && PPC_RADIX_MMU
> select HAVE_ARCH_JUMP_LABEL
> @@ -206,6 +207,7 @@ config PPC
> select HAVE_FUNCTION_GRAPH_TRACER
> select HAVE_FUNCTION_TRACER
> select HAVE_GCC_PLUGINS if GCC_VERSION >= 50200 # plugin support on gcc <= 5.1 is buggy on PPC
> + select HAVE_GENERIC_VDSO
> select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
> select HAVE_IDE
> select HAVE_IOREMAP_PROT
> diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h
> new file mode 100644
> index 000000000000..48cf23f1e273
> --- /dev/null
> +++ b/arch/powerpc/include/asm/vdso/vsyscall.h
> @@ -0,0 +1,25 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _ASM_POWERPC_VDSO_VSYSCALL_H
> +#define _ASM_POWERPC_VDSO_VSYSCALL_H
> +
> +#ifndef __ASSEMBLY__
> +
> +#include <linux/timekeeper_internal.h>
> +#include <asm/vdso_datapage.h>
> +
> +/*
> + * Update the vDSO data page to keep in sync with kernel timekeeping.
> + */
> +static __always_inline
> +struct vdso_data *__arch_get_k_vdso_data(void)
> +{
> + return vdso_data->data;
> +}
> +#define __arch_get_k_vdso_data __arch_get_k_vdso_data
> +
> +/* The asm-generic header needs to be included after the definitions above */
> +#include <asm-generic/vdso/vsyscall.h>
> +
> +#endif /* !__ASSEMBLY__ */
> +
> +#endif /* _ASM_POWERPC_VDSO_VSYSCALL_H */
> diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
> index b9ef6cf50ea5..c4d320504d26 100644
> --- a/arch/powerpc/include/asm/vdso_datapage.h
> +++ b/arch/powerpc/include/asm/vdso_datapage.h
> @@ -36,6 +36,7 @@
>
> #include <linux/unistd.h>
> #include <linux/time.h>
> +#include <vdso/datapage.h>
>
> #define SYSCALL_MAP_SIZE ((NR_syscalls + 31) / 32)
>
> @@ -45,7 +46,7 @@
>
> #ifdef CONFIG_PPC64
>
> -struct vdso_data {
> +struct vdso_arch_data {
> __u8 eye_catcher[16]; /* Eyecatcher: SYSTEMCFG:PPC64 0x00 */
> struct { /* Systemcfg version numbers */
> __u32 major; /* Major number 0x10 */
> @@ -59,13 +60,13 @@ struct vdso_data {
> __u32 processor; /* Processor type 0x1C */
> __u64 processorCount; /* # of physical processors 0x20 */
> __u64 physicalMemorySize; /* Size of real memory(B) 0x28 */
> - __u64 tb_orig_stamp; /* Timebase at boot 0x30 */
> + __u64 tb_orig_stamp; /* (NU) Timebase at boot 0x30 */
> __u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */
> - __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */
> - __u64 stamp_xsec; /* 0x48 */
> - __u64 tb_update_count; /* Timebase atomicity ctr 0x50 */
> - __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */
> - __u32 tz_dsttime; /* Type of dst correction 0x5C */
> + __u64 tb_to_xs; /* (NU) Inverse of TB to 2^20 0x40 */
> + __u64 stamp_xsec; /* (NU) 0x48 */
> + __u64 tb_update_count; /* (NU) Timebase atomicity ctr 0x50 */
> + __u32 tz_minuteswest; /* (NU) Min. west of Greenwich 0x58 */
> + __u32 tz_dsttime; /* (NU) Type of dst correction 0x5C */
> __u32 dcache_size; /* L1 d-cache size 0x60 */
> __u32 dcache_line_size; /* L1 d-cache line size 0x64 */
> __u32 icache_size; /* L1 i-cache size 0x68 */
> @@ -78,14 +79,10 @@ struct vdso_data {
> __u32 icache_block_size; /* L1 i-cache block size */
> __u32 dcache_log_block_size; /* L1 d-cache log block size */
> __u32 icache_log_block_size; /* L1 i-cache log block size */
> - __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */
> - __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */
> - __s64 wtom_clock_sec; /* Wall to monotonic clock sec */
> - __s64 stamp_xtime_sec; /* xtime secs as at tb_orig_stamp */
> - __s64 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */
> - __u32 hrtimer_res; /* hrtimer resolution */
> __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */
> __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
> +
> + struct vdso_data data[CS_BASES];
> };
>
> #else /* CONFIG_PPC64 */
> @@ -93,26 +90,15 @@ struct vdso_data {
> /*
> * And here is the simpler 32 bits version
> */
> -struct vdso_data {
> - __u64 tb_orig_stamp; /* Timebase at boot 0x30 */
> +struct vdso_arch_data {
> __u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */
> - __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */
> - __u64 stamp_xsec; /* 0x48 */
> - __u32 tb_update_count; /* Timebase atomicity ctr 0x50 */
> - __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */
> - __u32 tz_dsttime; /* Type of dst correction 0x5C */
> - __s32 wtom_clock_sec; /* Wall to monotonic clock */
> - __s32 wtom_clock_nsec;
> - __s32 stamp_xtime_sec; /* xtime seconds as at tb_orig_stamp */
> - __s32 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */
> - __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */
> - __u32 hrtimer_res; /* hrtimer resolution */
> __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
> + struct vdso_data data[CS_BASES];
> };
>
> #endif /* CONFIG_PPC64 */
>
> -extern struct vdso_data *vdso_data;
> +extern struct vdso_arch_data *vdso_data;
>
> #else /* __ASSEMBLY__ */
>
> diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
> index c2722ff36e98..a2dcb8ed79b9 100644
> --- a/arch/powerpc/kernel/asm-offsets.c
> +++ b/arch/powerpc/kernel/asm-offsets.c
> @@ -398,47 +398,16 @@ int main(void)
> #endif /* ! CONFIG_PPC64 */
>
> /* datapage offsets for use by vdso */
> - OFFSET(CFG_TB_ORIG_STAMP, vdso_data, tb_orig_stamp);
> - OFFSET(CFG_TB_TICKS_PER_SEC, vdso_data, tb_ticks_per_sec);
> - OFFSET(CFG_TB_TO_XS, vdso_data, tb_to_xs);
> - OFFSET(CFG_TB_UPDATE_COUNT, vdso_data, tb_update_count);
> - OFFSET(CFG_TZ_MINUTEWEST, vdso_data, tz_minuteswest);
> - OFFSET(CFG_TZ_DSTTIME, vdso_data, tz_dsttime);
> - OFFSET(CFG_SYSCALL_MAP32, vdso_data, syscall_map_32);
> - OFFSET(WTOM_CLOCK_SEC, vdso_data, wtom_clock_sec);
> - OFFSET(WTOM_CLOCK_NSEC, vdso_data, wtom_clock_nsec);
> - OFFSET(STAMP_XTIME_SEC, vdso_data, stamp_xtime_sec);
> - OFFSET(STAMP_XTIME_NSEC, vdso_data, stamp_xtime_nsec);
> - OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction);
> - OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res);
> + OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data);
> + OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec);
> + OFFSET(CFG_SYSCALL_MAP32, vdso_arch_data, syscall_map_32);
> #ifdef CONFIG_PPC64
> - OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size);
> - OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size);
> - OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size);
> - OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_data, dcache_log_block_size);
> - OFFSET(CFG_SYSCALL_MAP64, vdso_data, syscall_map_64);
> - OFFSET(TVAL64_TV_SEC, __kernel_old_timeval, tv_sec);
> - OFFSET(TVAL64_TV_USEC, __kernel_old_timeval, tv_usec);
> -#endif
> - OFFSET(TSPC64_TV_SEC, __kernel_timespec, tv_sec);
> - OFFSET(TSPC64_TV_NSEC, __kernel_timespec, tv_nsec);
> - OFFSET(TVAL32_TV_SEC, old_timeval32, tv_sec);
> - OFFSET(TVAL32_TV_USEC, old_timeval32, tv_usec);
> - OFFSET(TSPC32_TV_SEC, old_timespec32, tv_sec);
> - OFFSET(TSPC32_TV_NSEC, old_timespec32, tv_nsec);
> - /* timeval/timezone offsets for use by vdso */
> - OFFSET(TZONE_TZ_MINWEST, timezone, tz_minuteswest);
> - OFFSET(TZONE_TZ_DSTTIME, timezone, tz_dsttime);
> -
> - /* Other bits used by the vdso */
> - DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
> - DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
> - DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
> - DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
> - DEFINE(CLOCK_MAX, CLOCK_TAI);
> - DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
> - DEFINE(EINVAL, EINVAL);
> - DEFINE(KTIME_LOW_RES, KTIME_LOW_RES);
> + OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size);
> + OFFSET(CFG_DCACHE_BLOCKSZ, vdso_arch_data, dcache_block_size);
> + OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_arch_data, icache_log_block_size);
> + OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_arch_data, dcache_log_block_size);
> + OFFSET(CFG_SYSCALL_MAP64, vdso_arch_data, syscall_map_64);
> +#endif
>
> #ifdef CONFIG_BUG
> DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
> diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
> index 74efe46f5532..92481463f9dc 100644
> --- a/arch/powerpc/kernel/time.c
> +++ b/arch/powerpc/kernel/time.c
> @@ -82,6 +82,7 @@ static struct clocksource clocksource_timebase = {
> .flags = CLOCK_SOURCE_IS_CONTINUOUS,
> .mask = CLOCKSOURCE_MASK(64),
> .read = timebase_read,
> + .vdso_clock_mode = VDSO_CLOCKMODE_ARCHTIMER,
> };
>
> #define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
> @@ -831,95 +832,6 @@ static notrace u64 timebase_read(struct clocksource *cs)
> return (u64)get_tb();
> }
>
> -
> -void update_vsyscall(struct timekeeper *tk)
> -{
> - struct timespec64 xt;
> - struct clocksource *clock = tk->tkr_mono.clock;
> - u32 mult = tk->tkr_mono.mult;
> - u32 shift = tk->tkr_mono.shift;
> - u64 cycle_last = tk->tkr_mono.cycle_last;
> - u64 new_tb_to_xs, new_stamp_xsec;
> - u64 frac_sec;
> -
> - if (clock != &clocksource_timebase)
> - return;
> -
> - xt.tv_sec = tk->xtime_sec;
> - xt.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
> -
> - /* Make userspace gettimeofday spin until we're done. */
> - ++vdso_data->tb_update_count;
> - smp_mb();
> -
> - /*
> - * This computes ((2^20 / 1e9) * mult) >> shift as a
> - * 0.64 fixed-point fraction.
> - * The computation in the else clause below won't overflow
> - * (as long as the timebase frequency is >= 1.049 MHz)
> - * but loses precision because we lose the low bits of the constant
> - * in the shift. Note that 19342813113834067 ~= 2^(20+64) / 1e9.
> - * For a shift of 24 the error is about 0.5e-9, or about 0.5ns
> - * over a second. (Shift values are usually 22, 23 or 24.)
> - * For high frequency clocks such as the 512MHz timebase clock
> - * on POWER[6789], the mult value is small (e.g. 32768000)
> - * and so we can shift the constant by 16 initially
> - * (295147905179 ~= 2^(20+64-16) / 1e9) and then do the
> - * remaining shifts after the multiplication, which gives a
> - * more accurate result (e.g. with mult = 32768000, shift = 24,
> - * the error is only about 1.2e-12, or 0.7ns over 10 minutes).
> - */
> - if (mult <= 62500000 && clock->shift >= 16)
> - new_tb_to_xs = ((u64) mult * 295147905179ULL) >> (clock->shift - 16);
> - else
> - new_tb_to_xs = (u64) mult * (19342813113834067ULL >> clock->shift);
> -
> - /*
> - * Compute the fractional second in units of 2^-32 seconds.
> - * The fractional second is tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift
> - * in nanoseconds, so multiplying that by 2^32 / 1e9 gives
> - * it in units of 2^-32 seconds.
> - * We assume shift <= 32 because clocks_calc_mult_shift()
> - * generates shift values in the range 0 - 32.
> - */
> - frac_sec = tk->tkr_mono.xtime_nsec << (32 - shift);
> - do_div(frac_sec, NSEC_PER_SEC);
> -
> - /*
> - * Work out new stamp_xsec value for any legacy users of systemcfg.
> - * stamp_xsec is in units of 2^-20 seconds.
> - */
> - new_stamp_xsec = frac_sec >> 12;
> - new_stamp_xsec += tk->xtime_sec * XSEC_PER_SEC;
> -
> - /*
> - * tb_update_count is used to allow the userspace gettimeofday code
> - * to assure itself that it sees a consistent view of the tb_to_xs and
> - * stamp_xsec variables. It reads the tb_update_count, then reads
> - * tb_to_xs and stamp_xsec and then reads tb_update_count again. If
> - * the two values of tb_update_count match and are even then the
> - * tb_to_xs and stamp_xsec values are consistent. If not, then it
> - * loops back and reads them again until this criteria is met.
> - */
> - vdso_data->tb_orig_stamp = cycle_last;
> - vdso_data->stamp_xsec = new_stamp_xsec;
> - vdso_data->tb_to_xs = new_tb_to_xs;
> - vdso_data->wtom_clock_sec = tk->wall_to_monotonic.tv_sec;
> - vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec;
> - vdso_data->stamp_xtime_sec = xt.tv_sec;
> - vdso_data->stamp_xtime_nsec = xt.tv_nsec;
> - vdso_data->stamp_sec_fraction = frac_sec;
> - vdso_data->hrtimer_res = hrtimer_resolution;
> - smp_wmb();
> - ++(vdso_data->tb_update_count);
> -}
> -
> -void update_vsyscall_tz(void)
> -{
> - vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
> - vdso_data->tz_dsttime = sys_tz.tz_dsttime;
> -}
> -
> static void __init clocksource_init(void)
> {
> struct clocksource *clock = &clocksource_timebase;
> @@ -1079,7 +991,6 @@ void __init time_init(void)
> sys_tz.tz_dsttime = 0;
> }
>
> - vdso_data->tb_update_count = 0;
> vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
>
> /* initialise and enable the large decrementer (if we have one) */
> diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
> index 8dad44262e75..23208a051af5 100644
> --- a/arch/powerpc/kernel/vdso.c
> +++ b/arch/powerpc/kernel/vdso.c
> @@ -17,6 +17,7 @@
> #include <linux/elf.h>
> #include <linux/security.h>
> #include <linux/memblock.h>
> +#include <vdso/datapage.h>
>
> #include <asm/processor.h>
> #include <asm/mmu.h>
> @@ -70,10 +71,10 @@ static int vdso_ready;
> * with it, it will become dynamically allocated
> */
> static union {
> - struct vdso_data data;
> + struct vdso_arch_data data;
> u8 page[PAGE_SIZE];
> } vdso_data_store __page_aligned_data;
> -struct vdso_data *vdso_data = &vdso_data_store.data;
> +struct vdso_arch_data *vdso_data = &vdso_data_store.data;
>
> /* Format of the patch table */
> struct vdso_patch_def
> diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
> index 73eada6bc8cd..853545a19a1e 100644
> --- a/arch/powerpc/kernel/vdso32/Makefile
> +++ b/arch/powerpc/kernel/vdso32/Makefile
> @@ -2,8 +2,20 @@
>
> # List of files in the vdso, has to be asm only for now
>
> +ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN
> +include $(srctree)/lib/vdso/Makefile
> +
> obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
>
> +ifneq ($(c-gettimeofday-y),)
> + CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
> + CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
> + CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector)
> + CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING
> + CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables
> + CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
> +endif
> +
> # Build rules
>
> ifdef CROSS32_COMPILE
> @@ -15,6 +27,7 @@ endif
> CC32FLAGS :=
> ifdef CONFIG_PPC64
> CC32FLAGS += -m32
> +KBUILD_CFLAGS := $(filter-out -mcmodel=medium,$(KBUILD_CFLAGS))
> endif
>
> targets := $(obj-vdso32) vdso32.so vdso32.so.dbg
> @@ -23,6 +36,7 @@ obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
> GCOV_PROFILE := n
> KCOV_INSTRUMENT := n
> UBSAN_SANITIZE := n
> +KASAN_SANITIZE := n
>
> ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
> -Wl,-soname=linux-vdso32.so.1 -Wl,--hash-style=both
> @@ -36,8 +50,8 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc
> $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
>
> # link rule for the .so file, .lds has to be first
> -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE
> - $(call if_changed,vdso32ld)
> +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday.o FORCE
> + $(call if_changed,vdso32ld_and_check)
>
> # strip rule for the .so file
> $(obj)/%.so: OBJCOPYFLAGS := -S
> @@ -47,12 +61,16 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
> # assembly rules for the .S files
> $(obj-vdso32): %.o: %.S FORCE
> $(call if_changed_dep,vdso32as)
> +$(obj)/vgettimeofday.o: %.o: %.c FORCE
> + $(call if_changed_dep,vdso32cc)
>
> # actual build commands
> -quiet_cmd_vdso32ld = VDSO32L $@
> - cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
> +quiet_cmd_vdso32ld_and_check = VDSO32L $@
> + cmd_vdso32ld_and_check = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check)
> quiet_cmd_vdso32as = VDSO32A $@
> cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $<
> +quiet_cmd_vdso32cc = VDSO32C $@
> + cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $<
>
> # install commands for the unstripped file
> quiet_cmd_vdso_install = INSTALL $@
> diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
> index e7f8f9f1b3f4..fd7b01c51281 100644
> --- a/arch/powerpc/kernel/vdso32/gettimeofday.S
> +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
> @@ -12,13 +12,7 @@
> #include <asm/vdso_datapage.h>
> #include <asm/asm-offsets.h>
> #include <asm/unistd.h>
> -
> -/* Offset for the low 32-bit part of a field of long type */
> -#ifdef CONFIG_PPC64
> -#define LOPART 4
> -#else
> -#define LOPART 0
> -#endif
> +#include <asm/vdso/gettimeofday.h>
>
> .text
> /*
> @@ -28,32 +22,7 @@
> *
> */
> V_FUNCTION_BEGIN(__kernel_gettimeofday)
> - .cfi_startproc
> - mflr r12
> - .cfi_register lr,r12
> -
> - mr. r10,r3 /* r10 saves tv */
> - mr r11,r4 /* r11 saves tz */
> - get_datapage r9, r0
> - beq 3f
> - LOAD_REG_IMMEDIATE(r7, 1000000) /* load up USEC_PER_SEC */
> - bl __do_get_tspec@local /* get sec/usec from tb & kernel */
> - stw r3,TVAL32_TV_SEC(r10)
> - stw r4,TVAL32_TV_USEC(r10)
> -
> -3: cmplwi r11,0 /* check if tz is NULL */
> - mtlr r12
> - crclr cr0*4+so
> - li r3,0
> - beqlr
> -
> - lwz r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */
> - lwz r5,CFG_TZ_DSTTIME(r9)
> - stw r4,TZONE_TZ_MINWEST(r11)
> - stw r5,TZONE_TZ_DSTTIME(r11)
> -
> - blr
> - .cfi_endproc
> + cvdso_call __c_kernel_gettimeofday
> V_FUNCTION_END(__kernel_gettimeofday)
>
> /*
> @@ -63,127 +32,7 @@ V_FUNCTION_END(__kernel_gettimeofday)
> *
> */
> V_FUNCTION_BEGIN(__kernel_clock_gettime)
> - .cfi_startproc
> - /* Check for supported clock IDs */
> - cmpli cr0,r3,CLOCK_REALTIME
> - cmpli cr1,r3,CLOCK_MONOTONIC
> - cror cr0*4+eq,cr0*4+eq,cr1*4+eq
> -
> - cmpli cr5,r3,CLOCK_REALTIME_COARSE
> - cmpli cr6,r3,CLOCK_MONOTONIC_COARSE
> - cror cr5*4+eq,cr5*4+eq,cr6*4+eq
> -
> - cror cr0*4+eq,cr0*4+eq,cr5*4+eq
> - bne cr0, .Lgettime_fallback
> -
> - mflr r12 /* r12 saves lr */
> - .cfi_register lr,r12
> - mr r11,r4 /* r11 saves tp */
> - get_datapage r9, r0
> - LOAD_REG_IMMEDIATE(r7, NSEC_PER_SEC) /* load up NSEC_PER_SEC */
> - beq cr5, .Lcoarse_clocks
> -.Lprecise_clocks:
> - bl __do_get_tspec@local /* get sec/nsec from tb & kernel */
> - bne cr1, .Lfinish /* not monotonic -> all done */
> -
> - /*
> - * CLOCK_MONOTONIC
> - */
> -
> - /* now we must fixup using wall to monotonic. We need to snapshot
> - * that value and do the counter trick again. Fortunately, we still
> - * have the counter value in r8 that was returned by __do_get_xsec.
> - * At this point, r3,r4 contain our sec/nsec values, r5 and r6
> - * can be used, r7 contains NSEC_PER_SEC.
> - */
> -
> - lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9)
> - lwz r6,WTOM_CLOCK_NSEC(r9)
> -
> - /* We now have our offset in r5,r6. We create a fake dependency
> - * on that value and re-check the counter
> - */
> - or r0,r6,r5
> - xor r0,r0,r0
> - add r9,r9,r0
> - lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
> - cmpl cr0,r8,r0 /* check if updated */
> - bne- .Lprecise_clocks
> - b .Lfinish_monotonic
> -
> - /*
> - * For coarse clocks we get data directly from the vdso data page, so
> - * we don't need to call __do_get_tspec, but we still need to do the
> - * counter trick.
> - */
> -.Lcoarse_clocks:
> - lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
> - andi. r0,r8,1 /* pending update ? loop */
> - bne- .Lcoarse_clocks
> - add r9,r9,r0 /* r0 is already 0 */
> -
> - /*
> - * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
> - * too
> - */
> - lwz r3,STAMP_XTIME_SEC+LOPART(r9)
> - lwz r4,STAMP_XTIME_NSEC+LOPART(r9)
> - bne cr6,1f
> -
> - /* CLOCK_MONOTONIC_COARSE */
> - lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9)
> - lwz r6,WTOM_CLOCK_NSEC(r9)
> -
> - /* check if counter has updated */
> - or r0,r6,r5
> -1: or r0,r0,r3
> - or r0,r0,r4
> - xor r0,r0,r0
> - add r3,r3,r0
> - lwz r0,CFG_TB_UPDATE_COUNT+LOPART(r9)
> - cmpl cr0,r0,r8 /* check if updated */
> - bne- .Lcoarse_clocks
> -
> - /* Counter has not updated, so continue calculating proper values for
> - * sec and nsec if monotonic coarse, or just return with the proper
> - * values for realtime.
> - */
> - bne cr6, .Lfinish
> -
> - /* Calculate and store result. Note that this mimics the C code,
> - * which may cause funny results if nsec goes negative... is that
> - * possible at all ?
> - */
> -.Lfinish_monotonic:
> - add r3,r3,r5
> - add r4,r4,r6
> - cmpw cr0,r4,r7
> - cmpwi cr1,r4,0
> - blt 1f
> - subf r4,r7,r4
> - addi r3,r3,1
> -1: bge cr1, .Lfinish
> - addi r3,r3,-1
> - add r4,r4,r7
> -
> -.Lfinish:
> - stw r3,TSPC32_TV_SEC(r11)
> - stw r4,TSPC32_TV_NSEC(r11)
> -
> - mtlr r12
> - crclr cr0*4+so
> - li r3,0
> - blr
> -
> - /*
> - * syscall fallback
> - */
> -.Lgettime_fallback:
> - li r0,__NR_clock_gettime
> - .cfi_restore lr
> - sc
> - blr
> - .cfi_endproc
> + cvdso_call __c_kernel_clock_gettime
> V_FUNCTION_END(__kernel_clock_gettime)
>
>
> @@ -194,37 +43,7 @@ V_FUNCTION_END(__kernel_clock_gettime)
> *
> */
> V_FUNCTION_BEGIN(__kernel_clock_getres)
> - .cfi_startproc
> - /* Check for supported clock IDs */
> - cmplwi cr0, r3, CLOCK_MAX
> - cmpwi cr1, r3, CLOCK_REALTIME_COARSE
> - cmpwi cr7, r3, CLOCK_MONOTONIC_COARSE
> - bgt cr0, 99f
> - LOAD_REG_IMMEDIATE(r5, KTIME_LOW_RES)
> - beq cr1, 1f
> - beq cr7, 1f
> -
> - mflr r12
> - .cfi_register lr,r12
> - get_datapage r3, r0
> - lwz r5, CLOCK_HRTIMER_RES(r3)
> - mtlr r12
> -1: li r3,0
> - cmpli cr0,r4,0
> - crclr cr0*4+so
> - beqlr
> - stw r3,TSPC32_TV_SEC(r4)
> - stw r5,TSPC32_TV_NSEC(r4)
> - blr
> -
> - /*
> - * syscall fallback
> - */
> -99:
> - li r0,__NR_clock_getres
> - sc
> - blr
> - .cfi_endproc
> + cvdso_call __c_kernel_clock_getres
> V_FUNCTION_END(__kernel_clock_getres)
>
>
> @@ -235,105 +54,5 @@ V_FUNCTION_END(__kernel_clock_getres)
> *
> */
> V_FUNCTION_BEGIN(__kernel_time)
> - .cfi_startproc
> - mflr r12
> - .cfi_register lr,r12
> -
> - mr r11,r3 /* r11 holds t */
> - get_datapage r9, r0
> -
> - lwz r3,STAMP_XTIME_SEC+LOPART(r9)
> -
> - cmplwi r11,0 /* check if t is NULL */
> - mtlr r12
> - crclr cr0*4+so
> - beqlr
> - stw r3,0(r11) /* store result at *t */
> - blr
> - .cfi_endproc
> + cvdso_call_time __c_kernel_time
> V_FUNCTION_END(__kernel_time)
> -
> -/*
> - * This is the core of clock_gettime() and gettimeofday(),
> - * it returns the current time in r3 (seconds) and r4.
> - * On entry, r7 gives the resolution of r4, either USEC_PER_SEC
> - * or NSEC_PER_SEC, giving r4 in microseconds or nanoseconds.
> - * It expects the datapage ptr in r9 and doesn't clobber it.
> - * It clobbers r0, r5 and r6.
> - * On return, r8 contains the counter value that can be reused.
> - * This clobbers cr0 but not any other cr field.
> - */
> -__do_get_tspec:
> - .cfi_startproc
> - /* Check for update count & load values. We use the low
> - * order 32 bits of the update count
> - */
> -1: lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
> - andi. r0,r8,1 /* pending update ? loop */
> - bne- 1b
> - xor r0,r8,r8 /* create dependency */
> - add r9,r9,r0
> -
> - /* Load orig stamp (offset to TB) */
> - lwz r5,CFG_TB_ORIG_STAMP(r9)
> - lwz r6,(CFG_TB_ORIG_STAMP+4)(r9)
> -
> - /* Get a stable TB value */
> -2: MFTBU(r3)
> - MFTBL(r4)
> - MFTBU(r0)
> - cmplw cr0,r3,r0
> - bne- 2b
> -
> - /* Subtract tb orig stamp and shift left 12 bits.
> - */
> - subfc r4,r6,r4
> - subfe r0,r5,r3
> - slwi r0,r0,12
> - rlwimi. r0,r4,12,20,31
> - slwi r4,r4,12
> -
> - /*
> - * Load scale factor & do multiplication.
> - * We only use the high 32 bits of the tb_to_xs value.
> - * Even with a 1GHz timebase clock, the high 32 bits of
> - * tb_to_xs will be at least 4 million, so the error from
> - * ignoring the low 32 bits will be no more than 0.25ppm.
> - * The error will just make the clock run very very slightly
> - * slow until the next time the kernel updates the VDSO data,
> - * at which point the clock will catch up to the kernel's value,
> - * so there is no long-term error accumulation.
> - */
> - lwz r5,CFG_TB_TO_XS(r9) /* load values */
> - mulhwu r4,r4,r5
> - li r3,0
> -
> - beq+ 4f /* skip high part computation if 0 */
> - mulhwu r3,r0,r5
> - mullw r5,r0,r5
> - addc r4,r4,r5
> - addze r3,r3
> -4:
> - /* At this point, we have seconds since the xtime stamp
> - * as a 32.32 fixed-point number in r3 and r4.
> - * Load & add the xtime stamp.
> - */
> - lwz r5,STAMP_XTIME_SEC+LOPART(r9)
> - lwz r6,STAMP_SEC_FRAC(r9)
> - addc r4,r4,r6
> - adde r3,r3,r5
> -
> - /* We create a fake dependency on the result in r3/r4
> - * and re-check the counter
> - */
> - or r6,r4,r3
> - xor r0,r6,r6
> - add r9,r9,r0
> - lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
> - cmplw cr0,r8,r0 /* check if updated */
> - bne- 1b
> -
> - mulhwu r4,r4,r7 /* convert to micro or nanoseconds */
> -
> - blr
> - .cfi_endproc
> diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
> index 7eadac74c7f9..51e9b3f3f88a 100644
> --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
> +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
> @@ -111,6 +111,7 @@ SECTIONS
> *(.note.GNU-stack)
> *(.data .data.* .gnu.linkonce.d.* .sdata*)
> *(.bss .sbss .dynbss .dynsbss)
> + *(.got1)
> }
> }
>
> diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
> index dfd34f68bfa1..4a8c5e4d25c0 100644
> --- a/arch/powerpc/kernel/vdso64/Makefile
> +++ b/arch/powerpc/kernel/vdso64/Makefile
> @@ -1,8 +1,20 @@
> # SPDX-License-Identifier: GPL-2.0
> # List of files in the vdso, has to be asm only for now
>
> +ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN
> +include $(srctree)/lib/vdso/Makefile
> +
> obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
>
> +ifneq ($(c-gettimeofday-y),)
> + CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
> + CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
> + CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector)
> + CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING
> + CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables
> + CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
> +endif
> +
> # Build rules
>
> targets := $(obj-vdso64) vdso64.so vdso64.so.dbg
> @@ -11,6 +23,7 @@ obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
> GCOV_PROFILE := n
> KCOV_INSTRUMENT := n
> UBSAN_SANITIZE := n
> +KASAN_SANITIZE := n
>
> ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
> -Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both
> @@ -20,12 +33,14 @@ obj-y += vdso64_wrapper.o
> targets += vdso64.lds
> CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
>
> +$(obj)/vgettimeofday.o: %.o: %.c FORCE
> +
> # Force dependency (incbin is bad)
> $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
>
> # link rule for the .so file, .lds has to be first
> -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
> - $(call if_changed,vdso64ld)
> +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday.o FORCE
> + $(call if_changed,vdso64ld_and_check)
>
> # strip rule for the .so file
> $(obj)/%.so: OBJCOPYFLAGS := -S
> @@ -33,8 +48,8 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
> $(call if_changed,objcopy)
>
> # actual build commands
> -quiet_cmd_vdso64ld = VDSO64L $@
> - cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
> +quiet_cmd_vdso64ld_and_check = VDSO64L $@
> + cmd_vdso64ld_and_check = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check)
>
> # install commands for the unstripped file
> quiet_cmd_vdso_install = INSTALL $@
> diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
> index 20f8be40c653..d7a7bfb51081 100644
> --- a/arch/powerpc/kernel/vdso64/gettimeofday.S
> +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
> @@ -12,6 +12,7 @@
> #include <asm/vdso_datapage.h>
> #include <asm/asm-offsets.h>
> #include <asm/unistd.h>
> +#include <asm/vdso/gettimeofday.h>
>
> .text
> /*
> @@ -21,31 +22,7 @@
> *
> */
> V_FUNCTION_BEGIN(__kernel_gettimeofday)
> - .cfi_startproc
> - mflr r12
> - .cfi_register lr,r12
> -
> - mr r11,r3 /* r11 holds tv */
> - mr r10,r4 /* r10 holds tz */
> - get_datapage r3, r0
> - cmpldi r11,0 /* check if tv is NULL */
> - beq 2f
> - lis r7,1000000@ha /* load up USEC_PER_SEC */
> - addi r7,r7,1000000@l
> - bl V_LOCAL_FUNC(__do_get_tspec) /* get sec/us from tb & kernel */
> - std r4,TVAL64_TV_SEC(r11) /* store sec in tv */
> - std r5,TVAL64_TV_USEC(r11) /* store usec in tv */
> -2: cmpldi r10,0 /* check if tz is NULL */
> - beq 1f
> - lwz r4,CFG_TZ_MINUTEWEST(r3)/* fill tz */
> - lwz r5,CFG_TZ_DSTTIME(r3)
> - stw r4,TZONE_TZ_MINWEST(r10)
> - stw r5,TZONE_TZ_DSTTIME(r10)
> -1: mtlr r12
> - crclr cr0*4+so
> - li r3,0 /* always success */
> - blr
> - .cfi_endproc
> + cvdso_call __c_kernel_gettimeofday
> V_FUNCTION_END(__kernel_gettimeofday)
>
>
> @@ -56,120 +33,7 @@ V_FUNCTION_END(__kernel_gettimeofday)
> *
> */
> V_FUNCTION_BEGIN(__kernel_clock_gettime)
> - .cfi_startproc
> - /* Check for supported clock IDs */
> - cmpwi cr0,r3,CLOCK_REALTIME
> - cmpwi cr1,r3,CLOCK_MONOTONIC
> - cror cr0*4+eq,cr0*4+eq,cr1*4+eq
> -
> - cmpwi cr5,r3,CLOCK_REALTIME_COARSE
> - cmpwi cr6,r3,CLOCK_MONOTONIC_COARSE
> - cror cr5*4+eq,cr5*4+eq,cr6*4+eq
> -
> - cror cr0*4+eq,cr0*4+eq,cr5*4+eq
> - bne cr0,99f
> -
> - mflr r12 /* r12 saves lr */
> - .cfi_register lr,r12
> - mr r11,r4 /* r11 saves tp */
> - get_datapage r3, r0
> - lis r7,NSEC_PER_SEC@h /* want nanoseconds */
> - ori r7,r7,NSEC_PER_SEC@l
> - beq cr5,70f
> -50: bl V_LOCAL_FUNC(__do_get_tspec) /* get time from tb & kernel */
> - bne cr1,80f /* if not monotonic, all done */
> -
> - /*
> - * CLOCK_MONOTONIC
> - */
> -
> - /* now we must fixup using wall to monotonic. We need to snapshot
> - * that value and do the counter trick again. Fortunately, we still
> - * have the counter value in r8 that was returned by __do_get_tspec.
> - * At this point, r4,r5 contain our sec/nsec values.
> - */
> -
> - ld r6,WTOM_CLOCK_SEC(r3)
> - lwa r9,WTOM_CLOCK_NSEC(r3)
> -
> - /* We now have our result in r6,r9. We create a fake dependency
> - * on that result and re-check the counter
> - */
> - or r0,r6,r9
> - xor r0,r0,r0
> - add r3,r3,r0
> - ld r0,CFG_TB_UPDATE_COUNT(r3)
> - cmpld cr0,r0,r8 /* check if updated */
> - bne- 50b
> - b 78f
> -
> - /*
> - * For coarse clocks we get data directly from the vdso data page, so
> - * we don't need to call __do_get_tspec, but we still need to do the
> - * counter trick.
> - */
> -70: ld r8,CFG_TB_UPDATE_COUNT(r3)
> - andi. r0,r8,1 /* pending update ? loop */
> - bne- 70b
> - add r3,r3,r0 /* r0 is already 0 */
> -
> - /*
> - * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
> - * too
> - */
> - ld r4,STAMP_XTIME_SEC(r3)
> - ld r5,STAMP_XTIME_NSEC(r3)
> - bne cr6,75f
> -
> - /* CLOCK_MONOTONIC_COARSE */
> - ld r6,WTOM_CLOCK_SEC(r3)
> - lwa r9,WTOM_CLOCK_NSEC(r3)
> -
> - /* check if counter has updated */
> - or r0,r6,r9
> -75: or r0,r0,r4
> - or r0,r0,r5
> - xor r0,r0,r0
> - add r3,r3,r0
> - ld r0,CFG_TB_UPDATE_COUNT(r3)
> - cmpld cr0,r0,r8 /* check if updated */
> - bne- 70b
> -
> - /* Counter has not updated, so continue calculating proper values for
> - * sec and nsec if monotonic coarse, or just return with the proper
> - * values for realtime.
> - */
> - bne cr6,80f
> -
> - /* Add wall->monotonic offset and check for overflow or underflow */
> -78: add r4,r4,r6
> - add r5,r5,r9
> - cmpd cr0,r5,r7
> - cmpdi cr1,r5,0
> - blt 79f
> - subf r5,r7,r5
> - addi r4,r4,1
> -79: bge cr1,80f
> - addi r4,r4,-1
> - add r5,r5,r7
> -
> -80: std r4,TSPC64_TV_SEC(r11)
> - std r5,TSPC64_TV_NSEC(r11)
> -
> - mtlr r12
> - crclr cr0*4+so
> - li r3,0
> - blr
> -
> - /*
> - * syscall fallback
> - */
> -99:
> - li r0,__NR_clock_gettime
> - .cfi_restore lr
> - sc
> - blr
> - .cfi_endproc
> + cvdso_call __c_kernel_clock_gettime
> V_FUNCTION_END(__kernel_clock_gettime)
>
>
> @@ -180,34 +44,7 @@ V_FUNCTION_END(__kernel_clock_gettime)
> *
> */
> V_FUNCTION_BEGIN(__kernel_clock_getres)
> - .cfi_startproc
> - /* Check for supported clock IDs */
> - cmpwi cr0,r3,CLOCK_REALTIME
> - cmpwi cr1,r3,CLOCK_MONOTONIC
> - cror cr0*4+eq,cr0*4+eq,cr1*4+eq
> - bne cr0,99f
> -
> - mflr r12
> - .cfi_register lr,r12
> - get_datapage r3, r0
> - lwz r5, CLOCK_HRTIMER_RES(r3)
> - mtlr r12
> - li r3,0
> - cmpldi cr0,r4,0
> - crclr cr0*4+so
> - beqlr
> - std r3,TSPC64_TV_SEC(r4)
> - std r5,TSPC64_TV_NSEC(r4)
> - blr
> -
> - /*
> - * syscall fallback
> - */
> -99:
> - li r0,__NR_clock_getres
> - sc
> - blr
> - .cfi_endproc
> + cvdso_call __c_kernel_clock_getres
> V_FUNCTION_END(__kernel_clock_getres)
>
> /*
> @@ -217,74 +54,5 @@ V_FUNCTION_END(__kernel_clock_getres)
> *
> */
> V_FUNCTION_BEGIN(__kernel_time)
> - .cfi_startproc
> - mflr r12
> - .cfi_register lr,r12
> -
> - mr r11,r3 /* r11 holds t */
> - get_datapage r3, r0
> -
> - ld r4,STAMP_XTIME_SEC(r3)
> -
> - cmpldi r11,0 /* check if t is NULL */
> - beq 2f
> - std r4,0(r11) /* store result at *t */
> -2: mtlr r12
> - crclr cr0*4+so
> - mr r3,r4
> - blr
> - .cfi_endproc
> + cvdso_call_time __c_kernel_time
> V_FUNCTION_END(__kernel_time)
> -
> -
> -/*
> - * This is the core of clock_gettime() and gettimeofday(),
> - * it returns the current time in r4 (seconds) and r5.
> - * On entry, r7 gives the resolution of r5, either USEC_PER_SEC
> - * or NSEC_PER_SEC, giving r5 in microseconds or nanoseconds.
> - * It expects the datapage ptr in r3 and doesn't clobber it.
> - * It clobbers r0, r6 and r9.
> - * On return, r8 contains the counter value that can be reused.
> - * This clobbers cr0 but not any other cr field.
> - */
> -V_FUNCTION_BEGIN(__do_get_tspec)
> - .cfi_startproc
> - /* check for update count & load values */
> -1: ld r8,CFG_TB_UPDATE_COUNT(r3)
> - andi. r0,r8,1 /* pending update ? loop */
> - bne- 1b
> - xor r0,r8,r8 /* create dependency */
> - add r3,r3,r0
> -
> - /* Get TB & offset it. We use the MFTB macro which will generate
> - * workaround code for Cell.
> - */
> - MFTB(r6)
> - ld r9,CFG_TB_ORIG_STAMP(r3)
> - subf r6,r9,r6
> -
> - /* Scale result */
> - ld r5,CFG_TB_TO_XS(r3)
> - sldi r6,r6,12 /* compute time since stamp_xtime */
> - mulhdu r6,r6,r5 /* in units of 2^-32 seconds */
> -
> - /* Add stamp since epoch */
> - ld r4,STAMP_XTIME_SEC(r3)
> - lwz r5,STAMP_SEC_FRAC(r3)
> - or r0,r4,r5
> - or r0,r0,r6
> - xor r0,r0,r0
> - add r3,r3,r0
> - ld r0,CFG_TB_UPDATE_COUNT(r3)
> - cmpld r0,r8 /* check if updated */
> - bne- 1b /* reload if so */
> -
> - /* convert to seconds & nanoseconds and add to stamp */
> - add r6,r6,r5 /* add on fractional seconds of xtime */
> - mulhwu r5,r6,r7 /* compute micro or nanoseconds and */
> - srdi r6,r6,32 /* seconds since stamp_xtime */
> - clrldi r5,r5,32
> - add r4,r4,r6
> - blr
> - .cfi_endproc
> -V_FUNCTION_END(__do_get_tspec)
> diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S
> index 256fb9720298..71be083b24ed 100644
> --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S
> +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S
> @@ -61,7 +61,6 @@ SECTIONS
> .gcc_except_table : { *(.gcc_except_table) }
> .rela.dyn ALIGN(8) : { *(.rela.dyn) }
>
> - .opd ALIGN(8) : { KEEP (*(.opd)) }
> .got ALIGN(8) : { *(.got .toc) }
>
> _end = .;
> @@ -111,6 +110,7 @@ SECTIONS
> *(.branch_lt)
> *(.data .data.* .gnu.linkonce.d.* .sdata*)
> *(.bss .sbss .dynbss .dynsbss)
> + *(.opd)
> }
> }
>
>
^ permalink raw reply
* [PATCH v14 9/9] powerpc/vdso: Provide __kernel_clock_gettime64() on vdso32
From: Michael Ellerman @ 2020-11-26 13:10 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <20201126131006.2431205-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Provides __kernel_clock_gettime64() on vdso32. This is the
64 bits version of __kernel_clock_gettime() which is
y2038 compliant.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/44a5541c0355b9eedbac712eabe682118b3a508c.1604426550.git.christophe.leroy@csgroup.eu
---
arch/powerpc/include/asm/vdso/gettimeofday.h | 2 ++
arch/powerpc/kernel/vdso32/gettimeofday.S | 9 +++++++++
arch/powerpc/kernel/vdso32/vdso32.lds.S | 1 +
arch/powerpc/kernel/vdso32/vgettimeofday.c | 6 ++++++
4 files changed, 18 insertions(+)
v14: unchanged
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index 6f56a6bce615..0f95569e8fc3 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -187,6 +187,8 @@ int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
#else
int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
const struct vdso_data *vd);
+int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
+ const struct vdso_data *vd);
int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
const struct vdso_data *vd);
#endif
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index fd7b01c51281..a6e29f880e0e 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -35,6 +35,15 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
cvdso_call __c_kernel_clock_gettime
V_FUNCTION_END(__kernel_clock_gettime)
+/*
+ * Exact prototype of clock_gettime64()
+ *
+ * int __kernel_clock_gettime64(clockid_t clock_id, struct __timespec64 *ts);
+ *
+ */
+V_FUNCTION_BEGIN(__kernel_clock_gettime64)
+ cvdso_call __c_kernel_clock_gettime64
+V_FUNCTION_END(__kernel_clock_gettime64)
/*
* Exact prototype of clock_getres()
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 51e9b3f3f88a..27a2d03c72d5 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -147,6 +147,7 @@ VERSION
__kernel_get_syscall_map;
__kernel_gettimeofday;
__kernel_clock_gettime;
+ __kernel_clock_gettime64;
__kernel_clock_getres;
__kernel_time;
__kernel_get_tbfreq;
diff --git a/arch/powerpc/kernel/vdso32/vgettimeofday.c b/arch/powerpc/kernel/vdso32/vgettimeofday.c
index 0d4bc217529e..65fb03fb1731 100644
--- a/arch/powerpc/kernel/vdso32/vgettimeofday.c
+++ b/arch/powerpc/kernel/vdso32/vgettimeofday.c
@@ -10,6 +10,12 @@ int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
return __cvdso_clock_gettime32_data(vd, clock, ts);
}
+int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_gettime_data(vd, clock, ts);
+}
+
int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
const struct vdso_data *vd)
{
--
2.25.1
^ permalink raw reply related
* [PATCH v14 8/9] powerpc/vdso: Switch VDSO to generic C implementation.
From: Michael Ellerman @ 2020-11-26 13:10 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <20201126131006.2431205-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@csgroup.eu>
For VDSO32 on PPC64, we create a fake 32 bits config, on the same
principle as MIPS architecture, in order to get the correct parts of
the different asm header files.
With the C VDSO, the performance is slightly lower, but it is worth
it as it will ease maintenance and evolution, and also brings clocks
that are not supported with the ASM VDSO.
On an 8xx at 132 MHz, vdsotest with the ASM VDSO:
gettimeofday: vdso: 828 nsec/call
clock-getres-realtime-coarse: vdso: 391 nsec/call
clock-gettime-realtime-coarse: vdso: 614 nsec/call
clock-getres-realtime: vdso: 460 nsec/call
clock-gettime-realtime: vdso: 876 nsec/call
clock-getres-monotonic-coarse: vdso: 399 nsec/call
clock-gettime-monotonic-coarse: vdso: 691 nsec/call
clock-getres-monotonic: vdso: 460 nsec/call
clock-gettime-monotonic: vdso: 1026 nsec/call
On an 8xx at 132 MHz, vdsotest with the C VDSO:
gettimeofday: vdso: 955 nsec/call
clock-getres-realtime-coarse: vdso: 545 nsec/call
clock-gettime-realtime-coarse: vdso: 592 nsec/call
clock-getres-realtime: vdso: 545 nsec/call
clock-gettime-realtime: vdso: 941 nsec/call
clock-getres-monotonic-coarse: vdso: 545 nsec/call
clock-gettime-monotonic-coarse: vdso: 591 nsec/call
clock-getres-monotonic: vdso: 545 nsec/call
clock-gettime-monotonic: vdso: 940 nsec/call
It is even better for gettime with monotonic clocks.
Unsupported clocks with ASM VDSO:
clock-gettime-boottime: vdso: 3851 nsec/call
clock-gettime-tai: vdso: 3852 nsec/call
clock-gettime-monotonic-raw: vdso: 3396 nsec/call
Same clocks with C VDSO:
clock-gettime-tai: vdso: 941 nsec/call
clock-gettime-monotonic-raw: vdso: 1001 nsec/call
clock-gettime-monotonic-coarse: vdso: 591 nsec/call
On an 8321E at 333 MHz, vdsotest with the ASM VDSO:
gettimeofday: vdso: 220 nsec/call
clock-getres-realtime-coarse: vdso: 102 nsec/call
clock-gettime-realtime-coarse: vdso: 178 nsec/call
clock-getres-realtime: vdso: 129 nsec/call
clock-gettime-realtime: vdso: 235 nsec/call
clock-getres-monotonic-coarse: vdso: 105 nsec/call
clock-gettime-monotonic-coarse: vdso: 208 nsec/call
clock-getres-monotonic: vdso: 129 nsec/call
clock-gettime-monotonic: vdso: 274 nsec/call
On an 8321E at 333 MHz, vdsotest with the C VDSO:
gettimeofday: vdso: 272 nsec/call
clock-getres-realtime-coarse: vdso: 160 nsec/call
clock-gettime-realtime-coarse: vdso: 184 nsec/call
clock-getres-realtime: vdso: 166 nsec/call
clock-gettime-realtime: vdso: 281 nsec/call
clock-getres-monotonic-coarse: vdso: 160 nsec/call
clock-gettime-monotonic-coarse: vdso: 184 nsec/call
clock-getres-monotonic: vdso: 169 nsec/call
clock-gettime-monotonic: vdso: 275 nsec/call
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
[mpe: Tweak include guards]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/ef30ff8270a96c5c3b981523cd9b4e3d89049d3d.1604426550.git.christophe.leroy@csgroup.eu
---
arch/powerpc/Kconfig | 2 +
arch/powerpc/include/asm/vdso/vsyscall.h | 25 ++
arch/powerpc/include/asm/vdso_datapage.h | 40 +--
arch/powerpc/kernel/asm-offsets.c | 49 +---
arch/powerpc/kernel/time.c | 91 +------
arch/powerpc/kernel/vdso.c | 5 +-
arch/powerpc/kernel/vdso32/Makefile | 26 +-
arch/powerpc/kernel/vdso32/gettimeofday.S | 291 +---------------------
arch/powerpc/kernel/vdso32/vdso32.lds.S | 1 +
arch/powerpc/kernel/vdso64/Makefile | 23 +-
arch/powerpc/kernel/vdso64/gettimeofday.S | 242 +-----------------
arch/powerpc/kernel/vdso64/vdso64.lds.S | 2 +-
12 files changed, 106 insertions(+), 691 deletions(-)
create mode 100644 arch/powerpc/include/asm/vdso/vsyscall.h
v14: unchanged
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 7f4995b245a3..aad8532a718e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -176,6 +176,7 @@ config PPC
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL
+ select GENERIC_GETTIMEOFDAY
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_HUGE_VMAP if PPC_BOOK3S_64 && PPC_RADIX_MMU
select HAVE_ARCH_JUMP_LABEL
@@ -206,6 +207,7 @@ config PPC
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS if GCC_VERSION >= 50200 # plugin support on gcc <= 5.1 is buggy on PPC
+ select HAVE_GENERIC_VDSO
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
select HAVE_IDE
select HAVE_IOREMAP_PROT
diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h
new file mode 100644
index 000000000000..48cf23f1e273
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/vsyscall.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_VDSO_VSYSCALL_H
+#define _ASM_POWERPC_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/timekeeper_internal.h>
+#include <asm/vdso_datapage.h>
+
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline
+struct vdso_data *__arch_get_k_vdso_data(void)
+{
+ return vdso_data->data;
+}
+#define __arch_get_k_vdso_data __arch_get_k_vdso_data
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_VDSO_VSYSCALL_H */
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index b9ef6cf50ea5..c4d320504d26 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -36,6 +36,7 @@
#include <linux/unistd.h>
#include <linux/time.h>
+#include <vdso/datapage.h>
#define SYSCALL_MAP_SIZE ((NR_syscalls + 31) / 32)
@@ -45,7 +46,7 @@
#ifdef CONFIG_PPC64
-struct vdso_data {
+struct vdso_arch_data {
__u8 eye_catcher[16]; /* Eyecatcher: SYSTEMCFG:PPC64 0x00 */
struct { /* Systemcfg version numbers */
__u32 major; /* Major number 0x10 */
@@ -59,13 +60,13 @@ struct vdso_data {
__u32 processor; /* Processor type 0x1C */
__u64 processorCount; /* # of physical processors 0x20 */
__u64 physicalMemorySize; /* Size of real memory(B) 0x28 */
- __u64 tb_orig_stamp; /* Timebase at boot 0x30 */
+ __u64 tb_orig_stamp; /* (NU) Timebase at boot 0x30 */
__u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */
- __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */
- __u64 stamp_xsec; /* 0x48 */
- __u64 tb_update_count; /* Timebase atomicity ctr 0x50 */
- __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */
- __u32 tz_dsttime; /* Type of dst correction 0x5C */
+ __u64 tb_to_xs; /* (NU) Inverse of TB to 2^20 0x40 */
+ __u64 stamp_xsec; /* (NU) 0x48 */
+ __u64 tb_update_count; /* (NU) Timebase atomicity ctr 0x50 */
+ __u32 tz_minuteswest; /* (NU) Min. west of Greenwich 0x58 */
+ __u32 tz_dsttime; /* (NU) Type of dst correction 0x5C */
__u32 dcache_size; /* L1 d-cache size 0x60 */
__u32 dcache_line_size; /* L1 d-cache line size 0x64 */
__u32 icache_size; /* L1 i-cache size 0x68 */
@@ -78,14 +79,10 @@ struct vdso_data {
__u32 icache_block_size; /* L1 i-cache block size */
__u32 dcache_log_block_size; /* L1 d-cache log block size */
__u32 icache_log_block_size; /* L1 i-cache log block size */
- __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */
- __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */
- __s64 wtom_clock_sec; /* Wall to monotonic clock sec */
- __s64 stamp_xtime_sec; /* xtime secs as at tb_orig_stamp */
- __s64 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */
- __u32 hrtimer_res; /* hrtimer resolution */
__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */
__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
+
+ struct vdso_data data[CS_BASES];
};
#else /* CONFIG_PPC64 */
@@ -93,26 +90,15 @@ struct vdso_data {
/*
* And here is the simpler 32 bits version
*/
-struct vdso_data {
- __u64 tb_orig_stamp; /* Timebase at boot 0x30 */
+struct vdso_arch_data {
__u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */
- __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */
- __u64 stamp_xsec; /* 0x48 */
- __u32 tb_update_count; /* Timebase atomicity ctr 0x50 */
- __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */
- __u32 tz_dsttime; /* Type of dst correction 0x5C */
- __s32 wtom_clock_sec; /* Wall to monotonic clock */
- __s32 wtom_clock_nsec;
- __s32 stamp_xtime_sec; /* xtime seconds as at tb_orig_stamp */
- __s32 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */
- __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */
- __u32 hrtimer_res; /* hrtimer resolution */
__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
+ struct vdso_data data[CS_BASES];
};
#endif /* CONFIG_PPC64 */
-extern struct vdso_data *vdso_data;
+extern struct vdso_arch_data *vdso_data;
#else /* __ASSEMBLY__ */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c2722ff36e98..a2dcb8ed79b9 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -398,47 +398,16 @@ int main(void)
#endif /* ! CONFIG_PPC64 */
/* datapage offsets for use by vdso */
- OFFSET(CFG_TB_ORIG_STAMP, vdso_data, tb_orig_stamp);
- OFFSET(CFG_TB_TICKS_PER_SEC, vdso_data, tb_ticks_per_sec);
- OFFSET(CFG_TB_TO_XS, vdso_data, tb_to_xs);
- OFFSET(CFG_TB_UPDATE_COUNT, vdso_data, tb_update_count);
- OFFSET(CFG_TZ_MINUTEWEST, vdso_data, tz_minuteswest);
- OFFSET(CFG_TZ_DSTTIME, vdso_data, tz_dsttime);
- OFFSET(CFG_SYSCALL_MAP32, vdso_data, syscall_map_32);
- OFFSET(WTOM_CLOCK_SEC, vdso_data, wtom_clock_sec);
- OFFSET(WTOM_CLOCK_NSEC, vdso_data, wtom_clock_nsec);
- OFFSET(STAMP_XTIME_SEC, vdso_data, stamp_xtime_sec);
- OFFSET(STAMP_XTIME_NSEC, vdso_data, stamp_xtime_nsec);
- OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction);
- OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res);
+ OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data);
+ OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec);
+ OFFSET(CFG_SYSCALL_MAP32, vdso_arch_data, syscall_map_32);
#ifdef CONFIG_PPC64
- OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size);
- OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size);
- OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size);
- OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_data, dcache_log_block_size);
- OFFSET(CFG_SYSCALL_MAP64, vdso_data, syscall_map_64);
- OFFSET(TVAL64_TV_SEC, __kernel_old_timeval, tv_sec);
- OFFSET(TVAL64_TV_USEC, __kernel_old_timeval, tv_usec);
-#endif
- OFFSET(TSPC64_TV_SEC, __kernel_timespec, tv_sec);
- OFFSET(TSPC64_TV_NSEC, __kernel_timespec, tv_nsec);
- OFFSET(TVAL32_TV_SEC, old_timeval32, tv_sec);
- OFFSET(TVAL32_TV_USEC, old_timeval32, tv_usec);
- OFFSET(TSPC32_TV_SEC, old_timespec32, tv_sec);
- OFFSET(TSPC32_TV_NSEC, old_timespec32, tv_nsec);
- /* timeval/timezone offsets for use by vdso */
- OFFSET(TZONE_TZ_MINWEST, timezone, tz_minuteswest);
- OFFSET(TZONE_TZ_DSTTIME, timezone, tz_dsttime);
-
- /* Other bits used by the vdso */
- DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
- DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
- DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
- DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
- DEFINE(CLOCK_MAX, CLOCK_TAI);
- DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
- DEFINE(EINVAL, EINVAL);
- DEFINE(KTIME_LOW_RES, KTIME_LOW_RES);
+ OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size);
+ OFFSET(CFG_DCACHE_BLOCKSZ, vdso_arch_data, dcache_block_size);
+ OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_arch_data, icache_log_block_size);
+ OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_arch_data, dcache_log_block_size);
+ OFFSET(CFG_SYSCALL_MAP64, vdso_arch_data, syscall_map_64);
+#endif
#ifdef CONFIG_BUG
DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 74efe46f5532..92481463f9dc 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -82,6 +82,7 @@ static struct clocksource clocksource_timebase = {
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
.mask = CLOCKSOURCE_MASK(64),
.read = timebase_read,
+ .vdso_clock_mode = VDSO_CLOCKMODE_ARCHTIMER,
};
#define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
@@ -831,95 +832,6 @@ static notrace u64 timebase_read(struct clocksource *cs)
return (u64)get_tb();
}
-
-void update_vsyscall(struct timekeeper *tk)
-{
- struct timespec64 xt;
- struct clocksource *clock = tk->tkr_mono.clock;
- u32 mult = tk->tkr_mono.mult;
- u32 shift = tk->tkr_mono.shift;
- u64 cycle_last = tk->tkr_mono.cycle_last;
- u64 new_tb_to_xs, new_stamp_xsec;
- u64 frac_sec;
-
- if (clock != &clocksource_timebase)
- return;
-
- xt.tv_sec = tk->xtime_sec;
- xt.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
-
- /* Make userspace gettimeofday spin until we're done. */
- ++vdso_data->tb_update_count;
- smp_mb();
-
- /*
- * This computes ((2^20 / 1e9) * mult) >> shift as a
- * 0.64 fixed-point fraction.
- * The computation in the else clause below won't overflow
- * (as long as the timebase frequency is >= 1.049 MHz)
- * but loses precision because we lose the low bits of the constant
- * in the shift. Note that 19342813113834067 ~= 2^(20+64) / 1e9.
- * For a shift of 24 the error is about 0.5e-9, or about 0.5ns
- * over a second. (Shift values are usually 22, 23 or 24.)
- * For high frequency clocks such as the 512MHz timebase clock
- * on POWER[6789], the mult value is small (e.g. 32768000)
- * and so we can shift the constant by 16 initially
- * (295147905179 ~= 2^(20+64-16) / 1e9) and then do the
- * remaining shifts after the multiplication, which gives a
- * more accurate result (e.g. with mult = 32768000, shift = 24,
- * the error is only about 1.2e-12, or 0.7ns over 10 minutes).
- */
- if (mult <= 62500000 && clock->shift >= 16)
- new_tb_to_xs = ((u64) mult * 295147905179ULL) >> (clock->shift - 16);
- else
- new_tb_to_xs = (u64) mult * (19342813113834067ULL >> clock->shift);
-
- /*
- * Compute the fractional second in units of 2^-32 seconds.
- * The fractional second is tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift
- * in nanoseconds, so multiplying that by 2^32 / 1e9 gives
- * it in units of 2^-32 seconds.
- * We assume shift <= 32 because clocks_calc_mult_shift()
- * generates shift values in the range 0 - 32.
- */
- frac_sec = tk->tkr_mono.xtime_nsec << (32 - shift);
- do_div(frac_sec, NSEC_PER_SEC);
-
- /*
- * Work out new stamp_xsec value for any legacy users of systemcfg.
- * stamp_xsec is in units of 2^-20 seconds.
- */
- new_stamp_xsec = frac_sec >> 12;
- new_stamp_xsec += tk->xtime_sec * XSEC_PER_SEC;
-
- /*
- * tb_update_count is used to allow the userspace gettimeofday code
- * to assure itself that it sees a consistent view of the tb_to_xs and
- * stamp_xsec variables. It reads the tb_update_count, then reads
- * tb_to_xs and stamp_xsec and then reads tb_update_count again. If
- * the two values of tb_update_count match and are even then the
- * tb_to_xs and stamp_xsec values are consistent. If not, then it
- * loops back and reads them again until this criteria is met.
- */
- vdso_data->tb_orig_stamp = cycle_last;
- vdso_data->stamp_xsec = new_stamp_xsec;
- vdso_data->tb_to_xs = new_tb_to_xs;
- vdso_data->wtom_clock_sec = tk->wall_to_monotonic.tv_sec;
- vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec;
- vdso_data->stamp_xtime_sec = xt.tv_sec;
- vdso_data->stamp_xtime_nsec = xt.tv_nsec;
- vdso_data->stamp_sec_fraction = frac_sec;
- vdso_data->hrtimer_res = hrtimer_resolution;
- smp_wmb();
- ++(vdso_data->tb_update_count);
-}
-
-void update_vsyscall_tz(void)
-{
- vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
- vdso_data->tz_dsttime = sys_tz.tz_dsttime;
-}
-
static void __init clocksource_init(void)
{
struct clocksource *clock = &clocksource_timebase;
@@ -1079,7 +991,6 @@ void __init time_init(void)
sys_tz.tz_dsttime = 0;
}
- vdso_data->tb_update_count = 0;
vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
/* initialise and enable the large decrementer (if we have one) */
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 8dad44262e75..23208a051af5 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -17,6 +17,7 @@
#include <linux/elf.h>
#include <linux/security.h>
#include <linux/memblock.h>
+#include <vdso/datapage.h>
#include <asm/processor.h>
#include <asm/mmu.h>
@@ -70,10 +71,10 @@ static int vdso_ready;
* with it, it will become dynamically allocated
*/
static union {
- struct vdso_data data;
+ struct vdso_arch_data data;
u8 page[PAGE_SIZE];
} vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+struct vdso_arch_data *vdso_data = &vdso_data_store.data;
/* Format of the patch table */
struct vdso_patch_def
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index 73eada6bc8cd..853545a19a1e 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -2,8 +2,20 @@
# List of files in the vdso, has to be asm only for now
+ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN
+include $(srctree)/lib/vdso/Makefile
+
obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
+ifneq ($(c-gettimeofday-y),)
+ CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+ CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector)
+ CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING
+ CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables
+ CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
+endif
+
# Build rules
ifdef CROSS32_COMPILE
@@ -15,6 +27,7 @@ endif
CC32FLAGS :=
ifdef CONFIG_PPC64
CC32FLAGS += -m32
+KBUILD_CFLAGS := $(filter-out -mcmodel=medium,$(KBUILD_CFLAGS))
endif
targets := $(obj-vdso32) vdso32.so vdso32.so.dbg
@@ -23,6 +36,7 @@ obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
GCOV_PROFILE := n
KCOV_INSTRUMENT := n
UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
-Wl,-soname=linux-vdso32.so.1 -Wl,--hash-style=both
@@ -36,8 +50,8 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc
$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
# link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE
- $(call if_changed,vdso32ld)
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday.o FORCE
+ $(call if_changed,vdso32ld_and_check)
# strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -47,12 +61,16 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
# assembly rules for the .S files
$(obj-vdso32): %.o: %.S FORCE
$(call if_changed_dep,vdso32as)
+$(obj)/vgettimeofday.o: %.o: %.c FORCE
+ $(call if_changed_dep,vdso32cc)
# actual build commands
-quiet_cmd_vdso32ld = VDSO32L $@
- cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
+quiet_cmd_vdso32ld_and_check = VDSO32L $@
+ cmd_vdso32ld_and_check = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check)
quiet_cmd_vdso32as = VDSO32A $@
cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $<
+quiet_cmd_vdso32cc = VDSO32C $@
+ cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $<
# install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index e7f8f9f1b3f4..fd7b01c51281 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -12,13 +12,7 @@
#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
-
-/* Offset for the low 32-bit part of a field of long type */
-#ifdef CONFIG_PPC64
-#define LOPART 4
-#else
-#define LOPART 0
-#endif
+#include <asm/vdso/gettimeofday.h>
.text
/*
@@ -28,32 +22,7 @@
*
*/
V_FUNCTION_BEGIN(__kernel_gettimeofday)
- .cfi_startproc
- mflr r12
- .cfi_register lr,r12
-
- mr. r10,r3 /* r10 saves tv */
- mr r11,r4 /* r11 saves tz */
- get_datapage r9, r0
- beq 3f
- LOAD_REG_IMMEDIATE(r7, 1000000) /* load up USEC_PER_SEC */
- bl __do_get_tspec@local /* get sec/usec from tb & kernel */
- stw r3,TVAL32_TV_SEC(r10)
- stw r4,TVAL32_TV_USEC(r10)
-
-3: cmplwi r11,0 /* check if tz is NULL */
- mtlr r12
- crclr cr0*4+so
- li r3,0
- beqlr
-
- lwz r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */
- lwz r5,CFG_TZ_DSTTIME(r9)
- stw r4,TZONE_TZ_MINWEST(r11)
- stw r5,TZONE_TZ_DSTTIME(r11)
-
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_gettimeofday
V_FUNCTION_END(__kernel_gettimeofday)
/*
@@ -63,127 +32,7 @@ V_FUNCTION_END(__kernel_gettimeofday)
*
*/
V_FUNCTION_BEGIN(__kernel_clock_gettime)
- .cfi_startproc
- /* Check for supported clock IDs */
- cmpli cr0,r3,CLOCK_REALTIME
- cmpli cr1,r3,CLOCK_MONOTONIC
- cror cr0*4+eq,cr0*4+eq,cr1*4+eq
-
- cmpli cr5,r3,CLOCK_REALTIME_COARSE
- cmpli cr6,r3,CLOCK_MONOTONIC_COARSE
- cror cr5*4+eq,cr5*4+eq,cr6*4+eq
-
- cror cr0*4+eq,cr0*4+eq,cr5*4+eq
- bne cr0, .Lgettime_fallback
-
- mflr r12 /* r12 saves lr */
- .cfi_register lr,r12
- mr r11,r4 /* r11 saves tp */
- get_datapage r9, r0
- LOAD_REG_IMMEDIATE(r7, NSEC_PER_SEC) /* load up NSEC_PER_SEC */
- beq cr5, .Lcoarse_clocks
-.Lprecise_clocks:
- bl __do_get_tspec@local /* get sec/nsec from tb & kernel */
- bne cr1, .Lfinish /* not monotonic -> all done */
-
- /*
- * CLOCK_MONOTONIC
- */
-
- /* now we must fixup using wall to monotonic. We need to snapshot
- * that value and do the counter trick again. Fortunately, we still
- * have the counter value in r8 that was returned by __do_get_xsec.
- * At this point, r3,r4 contain our sec/nsec values, r5 and r6
- * can be used, r7 contains NSEC_PER_SEC.
- */
-
- lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9)
- lwz r6,WTOM_CLOCK_NSEC(r9)
-
- /* We now have our offset in r5,r6. We create a fake dependency
- * on that value and re-check the counter
- */
- or r0,r6,r5
- xor r0,r0,r0
- add r9,r9,r0
- lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
- cmpl cr0,r8,r0 /* check if updated */
- bne- .Lprecise_clocks
- b .Lfinish_monotonic
-
- /*
- * For coarse clocks we get data directly from the vdso data page, so
- * we don't need to call __do_get_tspec, but we still need to do the
- * counter trick.
- */
-.Lcoarse_clocks:
- lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
- andi. r0,r8,1 /* pending update ? loop */
- bne- .Lcoarse_clocks
- add r9,r9,r0 /* r0 is already 0 */
-
- /*
- * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
- * too
- */
- lwz r3,STAMP_XTIME_SEC+LOPART(r9)
- lwz r4,STAMP_XTIME_NSEC+LOPART(r9)
- bne cr6,1f
-
- /* CLOCK_MONOTONIC_COARSE */
- lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9)
- lwz r6,WTOM_CLOCK_NSEC(r9)
-
- /* check if counter has updated */
- or r0,r6,r5
-1: or r0,r0,r3
- or r0,r0,r4
- xor r0,r0,r0
- add r3,r3,r0
- lwz r0,CFG_TB_UPDATE_COUNT+LOPART(r9)
- cmpl cr0,r0,r8 /* check if updated */
- bne- .Lcoarse_clocks
-
- /* Counter has not updated, so continue calculating proper values for
- * sec and nsec if monotonic coarse, or just return with the proper
- * values for realtime.
- */
- bne cr6, .Lfinish
-
- /* Calculate and store result. Note that this mimics the C code,
- * which may cause funny results if nsec goes negative... is that
- * possible at all ?
- */
-.Lfinish_monotonic:
- add r3,r3,r5
- add r4,r4,r6
- cmpw cr0,r4,r7
- cmpwi cr1,r4,0
- blt 1f
- subf r4,r7,r4
- addi r3,r3,1
-1: bge cr1, .Lfinish
- addi r3,r3,-1
- add r4,r4,r7
-
-.Lfinish:
- stw r3,TSPC32_TV_SEC(r11)
- stw r4,TSPC32_TV_NSEC(r11)
-
- mtlr r12
- crclr cr0*4+so
- li r3,0
- blr
-
- /*
- * syscall fallback
- */
-.Lgettime_fallback:
- li r0,__NR_clock_gettime
- .cfi_restore lr
- sc
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_clock_gettime
V_FUNCTION_END(__kernel_clock_gettime)
@@ -194,37 +43,7 @@ V_FUNCTION_END(__kernel_clock_gettime)
*
*/
V_FUNCTION_BEGIN(__kernel_clock_getres)
- .cfi_startproc
- /* Check for supported clock IDs */
- cmplwi cr0, r3, CLOCK_MAX
- cmpwi cr1, r3, CLOCK_REALTIME_COARSE
- cmpwi cr7, r3, CLOCK_MONOTONIC_COARSE
- bgt cr0, 99f
- LOAD_REG_IMMEDIATE(r5, KTIME_LOW_RES)
- beq cr1, 1f
- beq cr7, 1f
-
- mflr r12
- .cfi_register lr,r12
- get_datapage r3, r0
- lwz r5, CLOCK_HRTIMER_RES(r3)
- mtlr r12
-1: li r3,0
- cmpli cr0,r4,0
- crclr cr0*4+so
- beqlr
- stw r3,TSPC32_TV_SEC(r4)
- stw r5,TSPC32_TV_NSEC(r4)
- blr
-
- /*
- * syscall fallback
- */
-99:
- li r0,__NR_clock_getres
- sc
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_clock_getres
V_FUNCTION_END(__kernel_clock_getres)
@@ -235,105 +54,5 @@ V_FUNCTION_END(__kernel_clock_getres)
*
*/
V_FUNCTION_BEGIN(__kernel_time)
- .cfi_startproc
- mflr r12
- .cfi_register lr,r12
-
- mr r11,r3 /* r11 holds t */
- get_datapage r9, r0
-
- lwz r3,STAMP_XTIME_SEC+LOPART(r9)
-
- cmplwi r11,0 /* check if t is NULL */
- mtlr r12
- crclr cr0*4+so
- beqlr
- stw r3,0(r11) /* store result at *t */
- blr
- .cfi_endproc
+ cvdso_call_time __c_kernel_time
V_FUNCTION_END(__kernel_time)
-
-/*
- * This is the core of clock_gettime() and gettimeofday(),
- * it returns the current time in r3 (seconds) and r4.
- * On entry, r7 gives the resolution of r4, either USEC_PER_SEC
- * or NSEC_PER_SEC, giving r4 in microseconds or nanoseconds.
- * It expects the datapage ptr in r9 and doesn't clobber it.
- * It clobbers r0, r5 and r6.
- * On return, r8 contains the counter value that can be reused.
- * This clobbers cr0 but not any other cr field.
- */
-__do_get_tspec:
- .cfi_startproc
- /* Check for update count & load values. We use the low
- * order 32 bits of the update count
- */
-1: lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
- andi. r0,r8,1 /* pending update ? loop */
- bne- 1b
- xor r0,r8,r8 /* create dependency */
- add r9,r9,r0
-
- /* Load orig stamp (offset to TB) */
- lwz r5,CFG_TB_ORIG_STAMP(r9)
- lwz r6,(CFG_TB_ORIG_STAMP+4)(r9)
-
- /* Get a stable TB value */
-2: MFTBU(r3)
- MFTBL(r4)
- MFTBU(r0)
- cmplw cr0,r3,r0
- bne- 2b
-
- /* Subtract tb orig stamp and shift left 12 bits.
- */
- subfc r4,r6,r4
- subfe r0,r5,r3
- slwi r0,r0,12
- rlwimi. r0,r4,12,20,31
- slwi r4,r4,12
-
- /*
- * Load scale factor & do multiplication.
- * We only use the high 32 bits of the tb_to_xs value.
- * Even with a 1GHz timebase clock, the high 32 bits of
- * tb_to_xs will be at least 4 million, so the error from
- * ignoring the low 32 bits will be no more than 0.25ppm.
- * The error will just make the clock run very very slightly
- * slow until the next time the kernel updates the VDSO data,
- * at which point the clock will catch up to the kernel's value,
- * so there is no long-term error accumulation.
- */
- lwz r5,CFG_TB_TO_XS(r9) /* load values */
- mulhwu r4,r4,r5
- li r3,0
-
- beq+ 4f /* skip high part computation if 0 */
- mulhwu r3,r0,r5
- mullw r5,r0,r5
- addc r4,r4,r5
- addze r3,r3
-4:
- /* At this point, we have seconds since the xtime stamp
- * as a 32.32 fixed-point number in r3 and r4.
- * Load & add the xtime stamp.
- */
- lwz r5,STAMP_XTIME_SEC+LOPART(r9)
- lwz r6,STAMP_SEC_FRAC(r9)
- addc r4,r4,r6
- adde r3,r3,r5
-
- /* We create a fake dependency on the result in r3/r4
- * and re-check the counter
- */
- or r6,r4,r3
- xor r0,r6,r6
- add r9,r9,r0
- lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
- cmplw cr0,r8,r0 /* check if updated */
- bne- 1b
-
- mulhwu r4,r4,r7 /* convert to micro or nanoseconds */
-
- blr
- .cfi_endproc
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 7eadac74c7f9..51e9b3f3f88a 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -111,6 +111,7 @@ SECTIONS
*(.note.GNU-stack)
*(.data .data.* .gnu.linkonce.d.* .sdata*)
*(.bss .sbss .dynbss .dynsbss)
+ *(.got1)
}
}
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index dfd34f68bfa1..4a8c5e4d25c0 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -1,8 +1,20 @@
# SPDX-License-Identifier: GPL-2.0
# List of files in the vdso, has to be asm only for now
+ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN
+include $(srctree)/lib/vdso/Makefile
+
obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
+ifneq ($(c-gettimeofday-y),)
+ CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+ CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector)
+ CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING
+ CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables
+ CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
+endif
+
# Build rules
targets := $(obj-vdso64) vdso64.so vdso64.so.dbg
@@ -11,6 +23,7 @@ obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
GCOV_PROFILE := n
KCOV_INSTRUMENT := n
UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
-Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both
@@ -20,12 +33,14 @@ obj-y += vdso64_wrapper.o
targets += vdso64.lds
CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
+$(obj)/vgettimeofday.o: %.o: %.c FORCE
+
# Force dependency (incbin is bad)
$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
# link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
- $(call if_changed,vdso64ld)
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday.o FORCE
+ $(call if_changed,vdso64ld_and_check)
# strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -33,8 +48,8 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
$(call if_changed,objcopy)
# actual build commands
-quiet_cmd_vdso64ld = VDSO64L $@
- cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
+quiet_cmd_vdso64ld_and_check = VDSO64L $@
+ cmd_vdso64ld_and_check = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check)
# install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 20f8be40c653..d7a7bfb51081 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -12,6 +12,7 @@
#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
+#include <asm/vdso/gettimeofday.h>
.text
/*
@@ -21,31 +22,7 @@
*
*/
V_FUNCTION_BEGIN(__kernel_gettimeofday)
- .cfi_startproc
- mflr r12
- .cfi_register lr,r12
-
- mr r11,r3 /* r11 holds tv */
- mr r10,r4 /* r10 holds tz */
- get_datapage r3, r0
- cmpldi r11,0 /* check if tv is NULL */
- beq 2f
- lis r7,1000000@ha /* load up USEC_PER_SEC */
- addi r7,r7,1000000@l
- bl V_LOCAL_FUNC(__do_get_tspec) /* get sec/us from tb & kernel */
- std r4,TVAL64_TV_SEC(r11) /* store sec in tv */
- std r5,TVAL64_TV_USEC(r11) /* store usec in tv */
-2: cmpldi r10,0 /* check if tz is NULL */
- beq 1f
- lwz r4,CFG_TZ_MINUTEWEST(r3)/* fill tz */
- lwz r5,CFG_TZ_DSTTIME(r3)
- stw r4,TZONE_TZ_MINWEST(r10)
- stw r5,TZONE_TZ_DSTTIME(r10)
-1: mtlr r12
- crclr cr0*4+so
- li r3,0 /* always success */
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_gettimeofday
V_FUNCTION_END(__kernel_gettimeofday)
@@ -56,120 +33,7 @@ V_FUNCTION_END(__kernel_gettimeofday)
*
*/
V_FUNCTION_BEGIN(__kernel_clock_gettime)
- .cfi_startproc
- /* Check for supported clock IDs */
- cmpwi cr0,r3,CLOCK_REALTIME
- cmpwi cr1,r3,CLOCK_MONOTONIC
- cror cr0*4+eq,cr0*4+eq,cr1*4+eq
-
- cmpwi cr5,r3,CLOCK_REALTIME_COARSE
- cmpwi cr6,r3,CLOCK_MONOTONIC_COARSE
- cror cr5*4+eq,cr5*4+eq,cr6*4+eq
-
- cror cr0*4+eq,cr0*4+eq,cr5*4+eq
- bne cr0,99f
-
- mflr r12 /* r12 saves lr */
- .cfi_register lr,r12
- mr r11,r4 /* r11 saves tp */
- get_datapage r3, r0
- lis r7,NSEC_PER_SEC@h /* want nanoseconds */
- ori r7,r7,NSEC_PER_SEC@l
- beq cr5,70f
-50: bl V_LOCAL_FUNC(__do_get_tspec) /* get time from tb & kernel */
- bne cr1,80f /* if not monotonic, all done */
-
- /*
- * CLOCK_MONOTONIC
- */
-
- /* now we must fixup using wall to monotonic. We need to snapshot
- * that value and do the counter trick again. Fortunately, we still
- * have the counter value in r8 that was returned by __do_get_tspec.
- * At this point, r4,r5 contain our sec/nsec values.
- */
-
- ld r6,WTOM_CLOCK_SEC(r3)
- lwa r9,WTOM_CLOCK_NSEC(r3)
-
- /* We now have our result in r6,r9. We create a fake dependency
- * on that result and re-check the counter
- */
- or r0,r6,r9
- xor r0,r0,r0
- add r3,r3,r0
- ld r0,CFG_TB_UPDATE_COUNT(r3)
- cmpld cr0,r0,r8 /* check if updated */
- bne- 50b
- b 78f
-
- /*
- * For coarse clocks we get data directly from the vdso data page, so
- * we don't need to call __do_get_tspec, but we still need to do the
- * counter trick.
- */
-70: ld r8,CFG_TB_UPDATE_COUNT(r3)
- andi. r0,r8,1 /* pending update ? loop */
- bne- 70b
- add r3,r3,r0 /* r0 is already 0 */
-
- /*
- * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
- * too
- */
- ld r4,STAMP_XTIME_SEC(r3)
- ld r5,STAMP_XTIME_NSEC(r3)
- bne cr6,75f
-
- /* CLOCK_MONOTONIC_COARSE */
- ld r6,WTOM_CLOCK_SEC(r3)
- lwa r9,WTOM_CLOCK_NSEC(r3)
-
- /* check if counter has updated */
- or r0,r6,r9
-75: or r0,r0,r4
- or r0,r0,r5
- xor r0,r0,r0
- add r3,r3,r0
- ld r0,CFG_TB_UPDATE_COUNT(r3)
- cmpld cr0,r0,r8 /* check if updated */
- bne- 70b
-
- /* Counter has not updated, so continue calculating proper values for
- * sec and nsec if monotonic coarse, or just return with the proper
- * values for realtime.
- */
- bne cr6,80f
-
- /* Add wall->monotonic offset and check for overflow or underflow */
-78: add r4,r4,r6
- add r5,r5,r9
- cmpd cr0,r5,r7
- cmpdi cr1,r5,0
- blt 79f
- subf r5,r7,r5
- addi r4,r4,1
-79: bge cr1,80f
- addi r4,r4,-1
- add r5,r5,r7
-
-80: std r4,TSPC64_TV_SEC(r11)
- std r5,TSPC64_TV_NSEC(r11)
-
- mtlr r12
- crclr cr0*4+so
- li r3,0
- blr
-
- /*
- * syscall fallback
- */
-99:
- li r0,__NR_clock_gettime
- .cfi_restore lr
- sc
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_clock_gettime
V_FUNCTION_END(__kernel_clock_gettime)
@@ -180,34 +44,7 @@ V_FUNCTION_END(__kernel_clock_gettime)
*
*/
V_FUNCTION_BEGIN(__kernel_clock_getres)
- .cfi_startproc
- /* Check for supported clock IDs */
- cmpwi cr0,r3,CLOCK_REALTIME
- cmpwi cr1,r3,CLOCK_MONOTONIC
- cror cr0*4+eq,cr0*4+eq,cr1*4+eq
- bne cr0,99f
-
- mflr r12
- .cfi_register lr,r12
- get_datapage r3, r0
- lwz r5, CLOCK_HRTIMER_RES(r3)
- mtlr r12
- li r3,0
- cmpldi cr0,r4,0
- crclr cr0*4+so
- beqlr
- std r3,TSPC64_TV_SEC(r4)
- std r5,TSPC64_TV_NSEC(r4)
- blr
-
- /*
- * syscall fallback
- */
-99:
- li r0,__NR_clock_getres
- sc
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_clock_getres
V_FUNCTION_END(__kernel_clock_getres)
/*
@@ -217,74 +54,5 @@ V_FUNCTION_END(__kernel_clock_getres)
*
*/
V_FUNCTION_BEGIN(__kernel_time)
- .cfi_startproc
- mflr r12
- .cfi_register lr,r12
-
- mr r11,r3 /* r11 holds t */
- get_datapage r3, r0
-
- ld r4,STAMP_XTIME_SEC(r3)
-
- cmpldi r11,0 /* check if t is NULL */
- beq 2f
- std r4,0(r11) /* store result at *t */
-2: mtlr r12
- crclr cr0*4+so
- mr r3,r4
- blr
- .cfi_endproc
+ cvdso_call_time __c_kernel_time
V_FUNCTION_END(__kernel_time)
-
-
-/*
- * This is the core of clock_gettime() and gettimeofday(),
- * it returns the current time in r4 (seconds) and r5.
- * On entry, r7 gives the resolution of r5, either USEC_PER_SEC
- * or NSEC_PER_SEC, giving r5 in microseconds or nanoseconds.
- * It expects the datapage ptr in r3 and doesn't clobber it.
- * It clobbers r0, r6 and r9.
- * On return, r8 contains the counter value that can be reused.
- * This clobbers cr0 but not any other cr field.
- */
-V_FUNCTION_BEGIN(__do_get_tspec)
- .cfi_startproc
- /* check for update count & load values */
-1: ld r8,CFG_TB_UPDATE_COUNT(r3)
- andi. r0,r8,1 /* pending update ? loop */
- bne- 1b
- xor r0,r8,r8 /* create dependency */
- add r3,r3,r0
-
- /* Get TB & offset it. We use the MFTB macro which will generate
- * workaround code for Cell.
- */
- MFTB(r6)
- ld r9,CFG_TB_ORIG_STAMP(r3)
- subf r6,r9,r6
-
- /* Scale result */
- ld r5,CFG_TB_TO_XS(r3)
- sldi r6,r6,12 /* compute time since stamp_xtime */
- mulhdu r6,r6,r5 /* in units of 2^-32 seconds */
-
- /* Add stamp since epoch */
- ld r4,STAMP_XTIME_SEC(r3)
- lwz r5,STAMP_SEC_FRAC(r3)
- or r0,r4,r5
- or r0,r0,r6
- xor r0,r0,r0
- add r3,r3,r0
- ld r0,CFG_TB_UPDATE_COUNT(r3)
- cmpld r0,r8 /* check if updated */
- bne- 1b /* reload if so */
-
- /* convert to seconds & nanoseconds and add to stamp */
- add r6,r6,r5 /* add on fractional seconds of xtime */
- mulhwu r5,r6,r7 /* compute micro or nanoseconds and */
- srdi r6,r6,32 /* seconds since stamp_xtime */
- clrldi r5,r5,32
- add r4,r4,r6
- blr
- .cfi_endproc
-V_FUNCTION_END(__do_get_tspec)
diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S
index 256fb9720298..71be083b24ed 100644
--- a/arch/powerpc/kernel/vdso64/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S
@@ -61,7 +61,6 @@ SECTIONS
.gcc_except_table : { *(.gcc_except_table) }
.rela.dyn ALIGN(8) : { *(.rela.dyn) }
- .opd ALIGN(8) : { KEEP (*(.opd)) }
.got ALIGN(8) : { *(.got .toc) }
_end = .;
@@ -111,6 +110,7 @@ SECTIONS
*(.branch_lt)
*(.data .data.* .gnu.linkonce.d.* .sdata*)
*(.bss .sbss .dynbss .dynsbss)
+ *(.opd)
}
}
--
2.25.1
^ permalink raw reply related
* [PATCH v14 7/9] powerpc/vdso: Save and restore TOC pointer on PPC64
From: Michael Ellerman @ 2020-11-26 13:10 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <20201126131006.2431205-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@csgroup.eu>
On PPC64, the TOC pointer needs to be saved and restored.
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/bf21fd9762a124ce3afec34a8e403a44dfdf2f84.1604426550.git.christophe.leroy@csgroup.eu
---
arch/powerpc/include/asm/vdso/gettimeofday.h | 12 ++++++++++++
1 file changed, 12 insertions(+)
v14: unchanged
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index 43dd1dc47c37..6f56a6bce615 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -19,10 +19,16 @@
.cfi_register lr, r0
PPC_STLU r1, -PPC_MIN_STKFRM(r1)
PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+#ifdef __powerpc64__
+ PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1)
+#endif
get_datapage r5, r0
addi r5, r5, VDSO_DATA_OFFSET
bl DOTSYM(\funct)
PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+#ifdef __powerpc64__
+ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1)
+#endif
cmpwi r3, 0
mtlr r0
.cfi_restore lr
@@ -42,10 +48,16 @@
.cfi_register lr, r0
PPC_STLU r1, -PPC_MIN_STKFRM(r1)
PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+#ifdef __powerpc64__
+ PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1)
+#endif
get_datapage r4, r0
addi r4, r4, VDSO_DATA_OFFSET
bl DOTSYM(\funct)
PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+#ifdef __powerpc64__
+ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1)
+#endif
crclr so
mtlr r0
.cfi_restore lr
--
2.25.1
^ permalink raw reply related
* [PATCH v14 6/9] powerpc/vdso: Prepare for switching VDSO to generic C implementation.
From: Michael Ellerman @ 2020-11-26 13:10 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <20201126131006.2431205-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Prepare for switching VDSO to generic C implementation in following
patch. Here, we:
- Prepare the helpers to call the C VDSO functions
- Prepare the required callbacks for the C VDSO functions
- Prepare the clocksource.h files to define VDSO_ARCH_CLOCKMODES
- Add the C trampolines to the generic C VDSO functions
powerpc is a bit special for VDSO as well as system calls in the
way that it requires setting CR SO bit which cannot be done in C.
Therefore, entry/exit needs to be performed in ASM.
Implementing __arch_get_vdso_data() would clobber the link register,
requiring the caller to save it. As the ASM calling function already
has to set a stack frame and saves the link register before calling
the C vdso function, retriving the vdso data pointer there is lighter.
Implement __arch_vdso_capable() and always return true.
Provide vdso_shift_ns(), as the generic x >> s gives the following
bad result:
18: 35 25 ff e0 addic. r9,r5,-32
1c: 41 80 00 10 blt 2c <shift+0x14>
20: 7c 64 4c 30 srw r4,r3,r9
24: 38 60 00 00 li r3,0
...
2c: 54 69 08 3c rlwinm r9,r3,1,0,30
30: 21 45 00 1f subfic r10,r5,31
34: 7c 84 2c 30 srw r4,r4,r5
38: 7d 29 50 30 slw r9,r9,r10
3c: 7c 63 2c 30 srw r3,r3,r5
40: 7d 24 23 78 or r4,r9,r4
In our case the shift is always <= 32. In addition, the upper 32 bits
of the result are likely nul. Lets GCC know it, it also optimises the
following calculations.
With the patch, we get:
0: 21 25 00 20 subfic r9,r5,32
4: 7c 69 48 30 slw r9,r3,r9
8: 7c 84 2c 30 srw r4,r4,r5
c: 7d 24 23 78 or r4,r9,r4
10: 7c 63 2c 30 srw r3,r3,r5
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
[mpe: Tweak include guards]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/b734c0bd0b65a538e8d2ab2367a46184d097fc55.1604426550.git.christophe.leroy@csgroup.eu
---
arch/powerpc/include/asm/clocksource.h | 7 +
arch/powerpc/include/asm/ppc_asm.h | 2 +
arch/powerpc/include/asm/vdso/clocksource.h | 7 +
arch/powerpc/include/asm/vdso/gettimeofday.h | 187 +++++++++++++++++++
arch/powerpc/kernel/vdso32/vgettimeofday.c | 28 +++
arch/powerpc/kernel/vdso64/vgettimeofday.c | 29 +++
6 files changed, 260 insertions(+)
create mode 100644 arch/powerpc/include/asm/clocksource.h
create mode 100644 arch/powerpc/include/asm/vdso/clocksource.h
create mode 100644 arch/powerpc/include/asm/vdso/gettimeofday.h
create mode 100644 arch/powerpc/kernel/vdso32/vgettimeofday.c
create mode 100644 arch/powerpc/kernel/vdso64/vgettimeofday.c
v14: mpe: Tweak include guards
diff --git a/arch/powerpc/include/asm/clocksource.h b/arch/powerpc/include/asm/clocksource.h
new file mode 100644
index 000000000000..0a26ef13a34a
--- /dev/null
+++ b/arch/powerpc/include/asm/clocksource.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CLOCKSOURCE_H
+#define _ASM_POWERPC_CLOCKSOURCE_H
+
+#include <asm/vdso/clocksource.h>
+
+#endif /* _ASM_POWERPC_CLOCKSOURCE_H */
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 101986d4a29d..cfa814824285 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -251,6 +251,8 @@ GLUE(.,name):
#define _GLOBAL_TOC(name) _GLOBAL(name)
+#define DOTSYM(a) a
+
#endif
/*
diff --git a/arch/powerpc/include/asm/vdso/clocksource.h b/arch/powerpc/include/asm/vdso/clocksource.h
new file mode 100644
index 000000000000..c1ba56b82ee5
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/clocksource.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_VDSO_CLOCKSOURCE_H
+#define _ASM_POWERPC_VDSO_CLOCKSOURCE_H
+
+#define VDSO_ARCH_CLOCKMODES VDSO_CLOCKMODE_ARCHTIMER
+
+#endif
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
new file mode 100644
index 000000000000..43dd1dc47c37
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -0,0 +1,187 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_VDSO_GETTIMEOFDAY_H
+#define _ASM_POWERPC_VDSO_GETTIMEOFDAY_H
+
+#ifdef __ASSEMBLY__
+
+#include <asm/ppc_asm.h>
+
+/*
+ * The macros sets two stack frames, one for the caller and one for the callee
+ * because there are no requirement for the caller to set a stack frame when
+ * calling VDSO so it may have omitted to set one, especially on PPC64
+ */
+
+.macro cvdso_call funct
+ .cfi_startproc
+ PPC_STLU r1, -PPC_MIN_STKFRM(r1)
+ mflr r0
+ .cfi_register lr, r0
+ PPC_STLU r1, -PPC_MIN_STKFRM(r1)
+ PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+ get_datapage r5, r0
+ addi r5, r5, VDSO_DATA_OFFSET
+ bl DOTSYM(\funct)
+ PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+ cmpwi r3, 0
+ mtlr r0
+ .cfi_restore lr
+ addi r1, r1, 2 * PPC_MIN_STKFRM
+ crclr so
+ beqlr+
+ crset so
+ neg r3, r3
+ blr
+ .cfi_endproc
+.endm
+
+.macro cvdso_call_time funct
+ .cfi_startproc
+ PPC_STLU r1, -PPC_MIN_STKFRM(r1)
+ mflr r0
+ .cfi_register lr, r0
+ PPC_STLU r1, -PPC_MIN_STKFRM(r1)
+ PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+ get_datapage r4, r0
+ addi r4, r4, VDSO_DATA_OFFSET
+ bl DOTSYM(\funct)
+ PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+ crclr so
+ mtlr r0
+ .cfi_restore lr
+ addi r1, r1, 2 * PPC_MIN_STKFRM
+ blr
+ .cfi_endproc
+.endm
+
+#else
+
+#include <asm/vdso/timebase.h>
+#include <asm/barrier.h>
+#include <asm/unistd.h>
+#include <uapi/linux/time.h>
+
+#define VDSO_HAS_CLOCK_GETRES 1
+
+#define VDSO_HAS_TIME 1
+
+static __always_inline int do_syscall_2(const unsigned long _r0, const unsigned long _r3,
+ const unsigned long _r4)
+{
+ register long r0 asm("r0") = _r0;
+ register unsigned long r3 asm("r3") = _r3;
+ register unsigned long r4 asm("r4") = _r4;
+ register int ret asm ("r3");
+
+ asm volatile(
+ " sc\n"
+ " bns+ 1f\n"
+ " neg %0, %0\n"
+ "1:\n"
+ : "=r" (ret), "+r" (r4), "+r" (r0)
+ : "r" (r3)
+ : "memory", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "cr0", "ctr");
+
+ return ret;
+}
+
+static __always_inline
+int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz)
+{
+ return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz);
+}
+
+static __always_inline
+int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts);
+}
+
+#ifdef CONFIG_VDSO32
+
+#define BUILD_VDSO32 1
+
+static __always_inline
+int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+ return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
+int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+ return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts);
+}
+#endif
+
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
+ const struct vdso_data *vd)
+{
+ return get_tb();
+}
+
+const struct vdso_data *__arch_get_vdso_data(void);
+
+static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+{
+ return true;
+}
+#define vdso_clocksource_ok vdso_clocksource_ok
+
+/*
+ * powerpc specific delta calculation.
+ *
+ * This variant removes the masking of the subtraction because the
+ * clocksource mask of all VDSO capable clocksources on powerpc is U64_MAX
+ * which would result in a pointless operation. The compiler cannot
+ * optimize it away as the mask comes from the vdso data and is not compile
+ * time constant.
+ */
+static __always_inline u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
+{
+ return (cycles - last) * mult;
+}
+#define vdso_calc_delta vdso_calc_delta
+
+#ifndef __powerpc64__
+static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift)
+{
+ u32 hi = ns >> 32;
+ u32 lo = ns;
+
+ lo >>= shift;
+ lo |= hi << (32 - shift);
+ hi >>= shift;
+
+ if (likely(hi == 0))
+ return lo;
+
+ return ((u64)hi << 32) | lo;
+}
+#define vdso_shift_ns vdso_shift_ns
+#endif
+
+#ifdef __powerpc64__
+int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
+ const struct vdso_data *vd);
+int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
+ const struct vdso_data *vd);
+#else
+int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
+ const struct vdso_data *vd);
+int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
+ const struct vdso_data *vd);
+#endif
+int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
+ const struct vdso_data *vd);
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time,
+ const struct vdso_data *vd);
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/powerpc/kernel/vdso32/vgettimeofday.c b/arch/powerpc/kernel/vdso32/vgettimeofday.c
new file mode 100644
index 000000000000..0d4bc217529e
--- /dev/null
+++ b/arch/powerpc/kernel/vdso32/vgettimeofday.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Powerpc userspace implementations of gettimeofday() and similar.
+ */
+#include <linux/types.h>
+
+int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_gettime32_data(vd, clock, ts);
+}
+
+int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
+ const struct vdso_data *vd)
+{
+ return __cvdso_gettimeofday_data(vd, tv, tz);
+}
+
+int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_getres_time32_data(vd, clock_id, res);
+}
+
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd)
+{
+ return __cvdso_time_data(vd, time);
+}
diff --git a/arch/powerpc/kernel/vdso64/vgettimeofday.c b/arch/powerpc/kernel/vdso64/vgettimeofday.c
new file mode 100644
index 000000000000..5b5500058344
--- /dev/null
+++ b/arch/powerpc/kernel/vdso64/vgettimeofday.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Powerpc userspace implementations of gettimeofday() and similar.
+ */
+#include <linux/time.h>
+#include <linux/types.h>
+
+int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_gettime_data(vd, clock, ts);
+}
+
+int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
+ const struct vdso_data *vd)
+{
+ return __cvdso_gettimeofday_data(vd, tv, tz);
+}
+
+int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_getres_data(vd, clock_id, res);
+}
+
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd)
+{
+ return __cvdso_time_data(vd, time);
+}
--
2.25.1
^ permalink raw reply related
* [PATCH v14 5/9] powerpc/barrier: Use CONFIG_PPC64 for barrier selection
From: Michael Ellerman @ 2020-11-26 13:10 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <20201126131006.2431205-1-mpe@ellerman.id.au>
Currently we use ifdef __powerpc64__ in barrier.h to decide if we
should use lwsync or eieio for SMPWMB which is then used by
__smp_wmb().
That means when we are building the compat VDSO we will use eieio,
because it's 32-bit code, even though we're building a 64-bit kernel
for a 64-bit CPU.
Although eieio should work, it would be cleaner if we always used the
same barrier, even for the 32-bit VDSO.
So change the ifdef to CONFIG_PPC64, so that the selection is made
based on the bitness of the kernel we're building for, not the current
compilation unit.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/barrier.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
v14: new
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index f53c42380832..aecfde829d5d 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -40,7 +40,7 @@
#define wmb() __asm__ __volatile__ ("sync" : : : "memory")
/* The sub-arch has lwsync */
-#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC)
+#if defined(CONFIG_PPC64) || defined(CONFIG_PPC_E500MC)
# define SMPWMB LWSYNC
#else
# define SMPWMB eieio
--
2.25.1
^ permalink raw reply related
* [PATCH v14 4/9] powerpc/time: Fix mftb()/get_tb() for use with the compat VDSO
From: Michael Ellerman @ 2020-11-26 13:10 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <20201126131006.2431205-1-mpe@ellerman.id.au>
When we're building the compat VDSO we are building 32-bit code but in
the context of a 64-bit kernel configuration.
To make this work we need to be careful in some places when using
ifdefs to differentiate between CONFIG_PPC64 and __powerpc64__.
CONFIG_PPC64 indicates the kernel we're building is 64-bit, but it
doesn't tell us that we're currently building 64-bit code - we could
be building 32-bit code for the compat VDSO.
On the other hand __powerpc64__ tells us that we are currently
building 64-bit code (and therefore we must also be building a 64-bit
kernel).
In the case of get_tb() we want to use the 32-bit code sequence
regardless of whether the kernel we're building for is 64-bit or
32-bit, what matters is the word size of the current object. So we
need to check __powerpc64__ to decide if we use mftb() or the
mftbu()/mftb() sequence.
For mftb() the logic for CPU_FTR_CELL_TB_BUG only makes sense if we're
building 64-bit code, so guard that with a __powerpc64__ check.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/vdso/timebase.h | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
v14: new
diff --git a/arch/powerpc/include/asm/vdso/timebase.h b/arch/powerpc/include/asm/vdso/timebase.h
index ac6769b348c6..b558b07959ce 100644
--- a/arch/powerpc/include/asm/vdso/timebase.h
+++ b/arch/powerpc/include/asm/vdso/timebase.h
@@ -8,7 +8,11 @@
#include <asm/reg.h>
-#if defined(CONFIG_PPC_CELL) || defined(CONFIG_E500)
+/*
+ * We use __powerpc64__ here because we want the compat VDSO to use the 32-bit
+ * version below in the else case of the ifdef.
+ */
+#if defined(__powerpc64__) && (defined(CONFIG_PPC_CELL) || defined(CONFIG_E500))
#define mftb() ({unsigned long rval; \
asm volatile( \
"90: mfspr %0, %2;\n" \
@@ -49,7 +53,11 @@ static inline u64 get_tb(void)
{
unsigned int tbhi, tblo, tbhi2;
- if (IS_ENABLED(CONFIG_PPC64))
+ /*
+ * We use __powerpc64__ here not CONFIG_PPC64 because we want the compat
+ * VDSO to use the 32-bit compatible version in the while loop below.
+ */
+ if (__is_defined(__powerpc64__))
return mftb();
do {
--
2.25.1
^ permalink raw reply related
* [PATCH v14 3/9] powerpc/time: Move timebase functions into new asm/vdso/timebase.h
From: Michael Ellerman @ 2020-11-26 13:10 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <20201126131006.2431205-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@csgroup.eu>
In order to easily use get_tb() from C VDSO, move timebase
functions into a new header named asm/vdso/timebase.h
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
[mpe: Move into asm/vdso, drop dubious historical authorship comments,
move mftb() etc. also]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/2d03f4b466156c0a0bfe5494c8874dcac952445c.1604426550.git.christophe.leroy@csgroup.eu
---
arch/powerpc/include/asm/reg.h | 31 -----------
arch/powerpc/include/asm/time.h | 30 +---------
arch/powerpc/include/asm/timex.h | 2 +-
arch/powerpc/include/asm/vdso/timebase.h | 71 ++++++++++++++++++++++++
4 files changed, 73 insertions(+), 61 deletions(-)
create mode 100644 arch/powerpc/include/asm/vdso/timebase.h
v14: mpe: Move into asm/vdso, drop dubious historical authorship comments, move mftb() etc. also.
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f877a576b338..602236e223c4 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1419,37 +1419,6 @@ static inline void msr_check_and_clear(unsigned long bits)
__msr_check_and_clear(bits);
}
-#if defined(CONFIG_PPC_CELL) || defined(CONFIG_E500)
-#define mftb() ({unsigned long rval; \
- asm volatile( \
- "90: mfspr %0, %2;\n" \
- ASM_FTR_IFSET( \
- "97: cmpwi %0,0;\n" \
- " beq- 90b;\n", "", %1) \
- : "=r" (rval) \
- : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \
- rval;})
-#elif defined(CONFIG_PPC_8xx)
-#define mftb() ({unsigned long rval; \
- asm volatile("mftbl %0" : "=r" (rval)); rval;})
-#else
-#define mftb() ({unsigned long rval; \
- asm volatile("mfspr %0, %1" : \
- "=r" (rval) : "i" (SPRN_TBRL)); rval;})
-#endif /* !CONFIG_PPC_CELL */
-
-#if defined(CONFIG_PPC_8xx)
-#define mftbu() ({unsigned long rval; \
- asm volatile("mftbu %0" : "=r" (rval)); rval;})
-#else
-#define mftbu() ({unsigned long rval; \
- asm volatile("mfspr %0, %1" : "=r" (rval) : \
- "i" (SPRN_TBRU)); rval;})
-#endif
-
-#define mttbl(v) asm volatile("mttbl %0":: "r"(v))
-#define mttbu(v) asm volatile("mttbu %0":: "r"(v))
-
#ifdef CONFIG_PPC32
#define mfsrin(v) ({unsigned int rval; \
asm volatile("mfsrin %0,%1" : "=r" (rval) : "r" (v)); \
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 2f566c1a754c..a59f8030f020 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -15,6 +15,7 @@
#include <asm/processor.h>
#include <asm/cpu_has_feature.h>
+#include <asm/vdso/timebase.h>
/* time.c */
extern unsigned long tb_ticks_per_jiffy;
@@ -38,12 +39,6 @@ struct div_result {
u64 result_low;
};
-/* For compatibility, get_tbl() is defined as get_tb() on ppc64 */
-static inline unsigned long get_tbl(void)
-{
- return mftb();
-}
-
static inline u64 get_vtb(void)
{
#ifdef CONFIG_PPC_BOOK3S_64
@@ -53,29 +48,6 @@ static inline u64 get_vtb(void)
return 0;
}
-static inline u64 get_tb(void)
-{
- unsigned int tbhi, tblo, tbhi2;
-
- if (IS_ENABLED(CONFIG_PPC64))
- return mftb();
-
- do {
- tbhi = mftbu();
- tblo = mftb();
- tbhi2 = mftbu();
- } while (tbhi != tbhi2);
-
- return ((u64)tbhi << 32) | tblo;
-}
-
-static inline void set_tb(unsigned int upper, unsigned int lower)
-{
- mtspr(SPRN_TBWL, 0);
- mtspr(SPRN_TBWU, upper);
- mtspr(SPRN_TBWL, lower);
-}
-
/* Accessor functions for the decrementer register.
* The 4xx doesn't even have a decrementer. I tried to use the
* generic timer interrupt code, which seems OK, with the 4xx PIT
diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h
index 95988870a57b..fa2e76e4093a 100644
--- a/arch/powerpc/include/asm/timex.h
+++ b/arch/powerpc/include/asm/timex.h
@@ -9,7 +9,7 @@
*/
#include <asm/cputable.h>
-#include <asm/reg.h>
+#include <asm/vdso/timebase.h>
#define CLOCK_TICK_RATE 1024000 /* Underlying HZ */
diff --git a/arch/powerpc/include/asm/vdso/timebase.h b/arch/powerpc/include/asm/vdso/timebase.h
new file mode 100644
index 000000000000..ac6769b348c6
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/timebase.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Common timebase prototypes and such for all ppc machines.
+ */
+
+#ifndef _ASM_POWERPC_VDSO_TIMEBASE_H
+#define _ASM_POWERPC_VDSO_TIMEBASE_H
+
+#include <asm/reg.h>
+
+#if defined(CONFIG_PPC_CELL) || defined(CONFIG_E500)
+#define mftb() ({unsigned long rval; \
+ asm volatile( \
+ "90: mfspr %0, %2;\n" \
+ ASM_FTR_IFSET( \
+ "97: cmpwi %0,0;\n" \
+ " beq- 90b;\n", "", %1) \
+ : "=r" (rval) \
+ : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \
+ rval;})
+#elif defined(CONFIG_PPC_8xx)
+#define mftb() ({unsigned long rval; \
+ asm volatile("mftbl %0" : "=r" (rval)); rval;})
+#else
+#define mftb() ({unsigned long rval; \
+ asm volatile("mfspr %0, %1" : \
+ "=r" (rval) : "i" (SPRN_TBRL)); rval;})
+#endif /* !CONFIG_PPC_CELL */
+
+#if defined(CONFIG_PPC_8xx)
+#define mftbu() ({unsigned long rval; \
+ asm volatile("mftbu %0" : "=r" (rval)); rval;})
+#else
+#define mftbu() ({unsigned long rval; \
+ asm volatile("mfspr %0, %1" : "=r" (rval) : \
+ "i" (SPRN_TBRU)); rval;})
+#endif
+
+#define mttbl(v) asm volatile("mttbl %0":: "r"(v))
+#define mttbu(v) asm volatile("mttbu %0":: "r"(v))
+
+/* For compatibility, get_tbl() is defined as get_tb() on ppc64 */
+static inline unsigned long get_tbl(void)
+{
+ return mftb();
+}
+
+static inline u64 get_tb(void)
+{
+ unsigned int tbhi, tblo, tbhi2;
+
+ if (IS_ENABLED(CONFIG_PPC64))
+ return mftb();
+
+ do {
+ tbhi = mftbu();
+ tblo = mftb();
+ tbhi2 = mftbu();
+ } while (tbhi != tbhi2);
+
+ return ((u64)tbhi << 32) | tblo;
+}
+
+static inline void set_tb(unsigned int upper, unsigned int lower)
+{
+ mtspr(SPRN_TBWL, 0);
+ mtspr(SPRN_TBWU, upper);
+ mtspr(SPRN_TBWL, lower);
+}
+
+#endif /* _ASM_POWERPC_VDSO_TIMEBASE_H */
--
2.25.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox