* [PATCH v3 1/1] powerpc/85xx: Board support for ppa8548
From: Stef van Os @ 2013-02-13 14:09 UTC (permalink / raw)
To: Kumar Gala, linuxppc-dev
Cc: scottwood, Paul Mackerras, timur.tabi, Stef van Os
Initial board support for the Prodrive PPA8548 AMC module. Board
is an MPC8548 AMC platform used in RapidIO systems. This module is
also used to test/work on mainline linux RapidIO software.
PPA8548 overview:
- 1.3 GHz Freescale PowerQUICC III MPC8548 processor
- 1 GB DDR2 @ 266 MHz
- 8 MB NOR flash
- Serial RapidIO 1.2
- 1 x 10/100/1000 BASE-T front ethernet
- 1 x 1000 BASE-BX ethernet on AMC connector
Signed-off-by: Stef van Os <stef.van.os@prodrive.nl>
---
arch/powerpc/boot/dts/ppa8548.dts | 166 +++++++++++++++++++++++++++
arch/powerpc/configs/85xx/ppa8548_defconfig | 65 +++++++++++
arch/powerpc/platforms/85xx/Kconfig | 7 +
arch/powerpc/platforms/85xx/Makefile | 1 +
arch/powerpc/platforms/85xx/ppa8548.c | 98 ++++++++++++++++
5 files changed, 337 insertions(+), 0 deletions(-)
create mode 100644 arch/powerpc/boot/dts/ppa8548.dts
create mode 100644 arch/powerpc/configs/85xx/ppa8548_defconfig
create mode 100644 arch/powerpc/platforms/85xx/ppa8548.c
diff --git a/arch/powerpc/boot/dts/ppa8548.dts b/arch/powerpc/boot/dts/ppa8548.dts
new file mode 100644
index 0000000..f97ecee
--- /dev/null
+++ b/arch/powerpc/boot/dts/ppa8548.dts
@@ -0,0 +1,166 @@
+/*
+ * PPA8548 Device Tree Source (36-bit address map)
+ * Copyright 2013 Prodrive B.V.
+ *
+ * Based on:
+ * MPC8548 CDS Device Tree Source (36-bit address map)
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+/include/ "fsl/mpc8548si-pre.dtsi"
+
+/ {
+ model = "ppa8548";
+ compatible = "ppa8548";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ interrupt-parent = <&mpic>;
+
+ memory {
+ device_type = "memory";
+ reg = <0 0 0x0 0x40000000>;
+ };
+
+ lbc: localbus@fe0005000 {
+ reg = <0xf 0xe0005000 0 0x1000>;
+ ranges = <0x0 0x0 0xf 0xff800000 0x00800000>;
+ };
+
+ soc: soc8548@fe0000000 {
+ ranges = <0 0xf 0xe0000000 0x100000>;
+ };
+
+ pci0: pci@fe0008000 {
+ /* ppa8548 board doesn't support PCI */
+ status = "disabled";
+ };
+
+ pci1: pci@fe0009000 {
+ /* ppa8548 board doesn't support PCI */
+ status = "disabled";
+ };
+
+ pci2: pcie@fe000a000 {
+ /* ppa8548 board doesn't support PCI */
+ status = "disabled";
+ };
+
+ rio: rapidio@fe00c0000 {
+ reg = <0xf 0xe00c0000 0x0 0x11000>;
+ port1 {
+ ranges = <0x0 0x0 0x0 0x80000000 0x0 0x40000000>;
+ };
+ };
+};
+
+&lbc {
+ nor@0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "cfi-flash";
+ reg = <0x0 0x0 0x00800000>;
+ bank-width = <2>;
+ device-width = <2>;
+
+ partition@0 {
+ reg = <0x0 0x7A0000>;
+ label = "user";
+ };
+
+ partition@7A0000 {
+ reg = <0x7A0000 0x20000>;
+ label = "env";
+ read-only;
+ };
+
+ partition@7C0000 {
+ reg = <0x7C0000 0x40000>;
+ label = "u-boot";
+ read-only;
+ };
+ };
+};
+
+&soc {
+ i2c@3000 {
+ rtc@6f {
+ compatible = "intersil,isl1208";
+ reg = <0x6f>;
+ };
+ };
+
+ i2c@3100 {
+ };
+
+ /*
+ * Only ethernet controller @25000 and @26000 are used.
+ * Use alias enet2 and enet3 for the remainig controllers,
+ * to stay compatible with mpc8548si-pre.dtsi.
+ */
+ enet2: ethernet@24000 {
+ status = "disabled";
+ };
+
+ mdio@24520 {
+ phy0: ethernet-phy@0 {
+ interrupts = <7 1 0 0>;
+ reg = <0x0>;
+ device_type = "ethernet-phy";
+ };
+ phy1: ethernet-phy@1 {
+ interrupts = <8 1 0 0>;
+ reg = <0x1>;
+ device_type = "ethernet-phy";
+ };
+ tbi0: tbi-phy@11 {
+ reg = <0x11>;
+ device_type = "tbi-phy";
+ };
+ };
+
+ enet0: ethernet@25000 {
+ tbi-handle = <&tbi1>;
+ phy-handle = <&phy0>;
+ };
+
+ mdio@25520 {
+ tbi1: tbi-phy@11 {
+ reg = <0x11>;
+ device_type = "tbi-phy";
+ };
+ };
+
+ enet1: ethernet@26000 {
+ tbi-handle = <&tbi2>;
+ phy-handle = <&phy1>;
+ };
+
+ mdio@26520 {
+ tbi2: tbi-phy@11 {
+ reg = <0x11>;
+ device_type = "tbi-phy";
+ };
+ };
+
+ enet3: ethernet@27000 {
+ status = "disabled";
+ };
+
+ mdio@27520 {
+ tbi3: tbi-phy@11 {
+ reg = <0x11>;
+ device_type = "tbi-phy";
+ };
+ };
+
+ crypto@30000 {
+ status = "disabled";
+ };
+};
+
+/include/ "fsl/mpc8548si-post.dtsi"
diff --git a/arch/powerpc/configs/85xx/ppa8548_defconfig b/arch/powerpc/configs/85xx/ppa8548_defconfig
new file mode 100644
index 0000000..a11337d
--- /dev/null
+++ b/arch/powerpc/configs/85xx/ppa8548_defconfig
@@ -0,0 +1,65 @@
+CONFIG_PPC_85xx=y
+CONFIG_PPA8548=y
+CONFIG_DTC=y
+CONFIG_DEFAULT_UIMAGE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+# CONFIG_PCI is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_ADVANCED_OPTIONS=y
+CONFIG_LOWMEM_SIZE_BOOL=y
+CONFIG_LOWMEM_SIZE=0x40000000
+CONFIG_LOWMEM_CAM_NUM_BOOL=y
+CONFIG_LOWMEM_CAM_NUM=4
+CONFIG_PAGE_OFFSET_BOOL=y
+CONFIG_PAGE_OFFSET=0xb0000000
+CONFIG_KERNEL_START_BOOL=y
+CONFIG_KERNEL_START=0xb0000000
+# CONFIG_PHYSICAL_START_BOOL is not set
+CONFIG_PHYSICAL_START=0x00000000
+CONFIG_PHYSICAL_ALIGN=0x04000000
+CONFIG_TASK_SIZE_BOOL=y
+CONFIG_TASK_SIZE=0xb0000000
+
+CONFIG_FSL_LBC=y
+CONFIG_FSL_DMA=y
+CONFIG_FSL_RIO=y
+
+CONFIG_RAPIDIO=y
+CONFIG_RAPIDIO_DMA_ENGINE=y
+CONFIG_RAPIDIO_TSI57X=y
+CONFIG_RAPIDIO_TSI568=y
+CONFIG_RAPIDIO_CPS_XX=y
+CONFIG_RAPIDIO_CPS_GEN2=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_PROC_DEVICETREE=y
+
+CONFIG_MTD=y
+CONFIG_MTD_BLKDEVS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_CONCAT=y
+CONFIG_MTD_PARTITIONS=y
+CONFIG_MTD_PHYSMAP_OF=y
+
+CONFIG_I2C=y
+CONFIG_I2C_MPC=y
+CONFIG_I2C_CHARDEV
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_DRV_ISL1208=y
+
+CONFIG_NET=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_NETDEVICES=y
+CONFIG_MII=y
+CONFIG_GIANFAR=y
+CONFIG_MARVELL_PHY=y
+CONFIG_NFS_FS=y
+CONFIG_ROOT_NFS=y
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 02d02a0..803bfed 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -191,6 +191,13 @@ config SBC8548
help
This option enables support for the Wind River SBC8548 board
+config PPA8548
+ bool "Prodrive PPA8548"
+ help
+ This option enables support for the Prodrive PPA8548 board.
+ select DEFAULT_UIMAGE
+ select HAS_RAPIDIO
+
config GE_IMP3A
bool "GE Intelligent Platforms IMP3A"
select DEFAULT_UIMAGE
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index 76f679c..d5f4195 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_P5040_DS) += p5040_ds.o corenet_ds.o
obj-$(CONFIG_STX_GP3) += stx_gp3.o
obj-$(CONFIG_TQM85xx) += tqm85xx.o
obj-$(CONFIG_SBC8548) += sbc8548.o
+obj-$(CONFIG_PPA8548) += ppa8548.o
obj-$(CONFIG_SOCRATES) += socrates.o socrates_fpga_pic.o
obj-$(CONFIG_KSI8560) += ksi8560.o
obj-$(CONFIG_XES_MPC85xx) += xes_mpc85xx.o
diff --git a/arch/powerpc/platforms/85xx/ppa8548.c b/arch/powerpc/platforms/85xx/ppa8548.c
new file mode 100644
index 0000000..6a7704b
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/ppa8548.c
@@ -0,0 +1,98 @@
+/*
+ * ppa8548 setup and early boot code.
+ *
+ * Copyright 2009 Prodrive B.V..
+ *
+ * By Stef van Os (see MAINTAINERS for contact information)
+ *
+ * Based on the SBC8548 support - Copyright 2007 Wind River Systems Inc.
+ * Based on the MPC8548CDS support - Copyright 2005 Freescale Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/reboot.h>
+#include <linux/seq_file.h>
+#include <linux/of_platform.h>
+
+#include <asm/machdep.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+
+#include <sysdev/fsl_soc.h>
+
+static void __init ppa8548_pic_init(void)
+{
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
+ 0, 256, " OpenPIC ");
+ BUG_ON(mpic == NULL);
+ mpic_init(mpic);
+}
+
+/*
+ * Setup the architecture
+ */
+static void __init ppa8548_setup_arch(void)
+{
+ if (ppc_md.progress)
+ ppc_md.progress("ppa8548_setup_arch()", 0);
+}
+
+static void ppa8548_show_cpuinfo(struct seq_file *m)
+{
+ uint32_t svid, phid1;
+
+ svid = mfspr(SPRN_SVR);
+
+ seq_printf(m, "Vendor\t\t: Prodrive B.V.\n");
+ seq_printf(m, "SVR\t\t: 0x%x\n", svid);
+
+ /* Display cpu Pll setting */
+ phid1 = mfspr(SPRN_HID1);
+ seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f));
+}
+
+static struct of_device_id __initdata of_bus_ids[] = {
+ { .name = "soc", },
+ { .type = "soc", },
+ { .compatible = "simple-bus", },
+ { .compatible = "gianfar", },
+ { .compatible = "fsl,srio", },
+ {},
+};
+
+static int __init declare_of_platform_devices(void)
+{
+ of_platform_bus_probe(NULL, of_bus_ids, NULL);
+
+ return 0;
+}
+machine_device_initcall(ppa8548, declare_of_platform_devices);
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init ppa8548_probe(void)
+{
+ unsigned long root = of_get_flat_dt_root();
+
+ return of_flat_dt_is_compatible(root, "ppa8548");
+}
+
+define_machine(ppa8548) {
+ .name = "ppa8548",
+ .probe = ppa8548_probe,
+ .setup_arch = ppa8548_setup_arch,
+ .init_IRQ = ppa8548_pic_init,
+ .show_cpuinfo = ppa8548_show_cpuinfo,
+ .get_irq = mpic_get_irq,
+ .restart = fsl_rstcr_restart,
+ .calibrate_decr = generic_calibrate_decr,
+ .progress = udbg_progress,
+};
--
1.7.2.5
^ permalink raw reply related
* RE: [PATCH 2/2] powerpc: Make context bits depend on virtual addr size.
From: Aneesh Kumar K.V @ 2013-02-13 14:26 UTC (permalink / raw)
To: David Laight, Benjamin Herrenschmidt, phileas-fogg, geoff
Cc: paulus, linuxppc-dev
In-Reply-To: <AE90C24D6B3A694183C094C60CF0A2F6026B7148@saturn3.aculab.com>
David Laight <David.Laight@aculab.com> writes:
>> +#define CONTEXT_BITS 19
>> +#define USER_ESID_BITS 18
>> +#define USER_ESID_BITS_1T 6
>> +
>> +/*
>> + * 256MB segment
>> + * The proto-VSID space has 2^(CONTEX_BITS + USER_ESID_BITS) - 1 segments
>> + * available for user + kernel mapping. The top 4 contexts are used for
>> + * kernel mapping. Each segment contains 2^28 bytes. Each
>> + * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
>> + * (19 == 37 + 28 - 46).
>> + */
>
> I can't help feeling this would be easier to understand if a full
> 64? 80? bit address was shown with the various bit ranges identified.
>
> Given the comment, I'd have expected CONTEXT_BITS to be calculated
> from three other named constants - rather than being set to 19.
>
May be the comments were misleading. We build proto vsid using a
combination of context and ea bits.
Current code does the below:
for kernel:
proto_vsid = ea >> SID_SHIFT;
proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS));
for user:
proto_vsid = ea >> SID_SHIFT
proto_vsid |= context << USER_ESID_BITS
context range is 0 - (2^19 -1)
With this patch we _don't_ give kernel half the proto vsid range.
Instead, we reduce the proto vsid range and then the kernel is given
top 4 context. ie, kernel proto vsid is now
for kenel:
proto_vsid = ea >> SID_SHIFT;
context = (MAX_CONTEXT - 4) + ((effective address >> 60) - 0xc);
proto_vsid |= context << USER_ESID_BITS
-aneesh
^ permalink raw reply
* [PATCH] Enhanced support for MPC8xx/8xxx watchdog
From: Christophe Leroy @ 2013-02-13 15:19 UTC (permalink / raw)
To: Wim Van Sebroeck; +Cc: linuxppc-dev, linux-kernel, linux-watchdog
This patch modifies the behaviour of the MPC8xx/8xxx watchdog. On the MPC8xx,
at 133Mhz, the maximum timeout of the watchdog timer is 1s, which means it must
be pinged twice a second. This is not in line with the Linux watchdog concept
which is based on a default watchdog timeout around 60s.
This patch introduces an intermediate layer between the CPU and the userspace.
The kernel pings the watchdog at the required frequency at the condition that
userspace tools refresh it regularly.
The new parameter 'heartbeat' allows to set up the userspace timeout.
The driver also implements the WDIOC_SETTIMEOUT ioctl.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
diff -ur linux-3.7.7/drivers/watchdog/mpc8xxx_wdt.c linux/drivers/watchdog/mpc8xxx_wdt.c
--- linux-3.7.7/drivers/watchdog/mpc8xxx_wdt.c 2013-02-11 18:05:09.000000000 +0100
+++ linux/drivers/watchdog/mpc8xxx_wdt.c 2013-02-13 15:55:22.000000000 +0100
@@ -52,10 +52,17 @@
static struct mpc8xxx_wdt __iomem *wd_base;
static int mpc8xxx_wdt_init_late(void);
+#define WD_TIMO 10 /* Default heartbeat = 10 seconds */
+
+static int heartbeat = WD_TIMO;
+module_param(heartbeat, int, 0);
+MODULE_PARM_DESC(heartbeat,
+ "Watchdog SW heartbeat in seconds. (0 < heartbeat < 65536s, default="
+ __MODULE_STRING(WD_TIMO) "s)");
static u16 timeout = 0xffff;
module_param(timeout, ushort, 0);
MODULE_PARM_DESC(timeout,
- "Watchdog timeout in ticks. (0<timeout<65536, default=65535)");
+ "Watchdog HW timeout in ticks. (0<timeout<65536, default=65535)");
static bool reset = 1;
module_param(reset, bool, 0);
@@ -74,8 +81,10 @@
static int prescale = 1;
static unsigned int timeout_sec;
+static int wdt_auto = 1;
static unsigned long wdt_is_open;
static DEFINE_SPINLOCK(wdt_spinlock);
+static unsigned long wdt_last_ping;
static void mpc8xxx_wdt_keepalive(void)
{
@@ -91,9 +100,20 @@
static void mpc8xxx_wdt_timer_ping(unsigned long arg)
{
- mpc8xxx_wdt_keepalive();
- /* We're pinging it twice faster than needed, just to be sure. */
- mod_timer(&wdt_timer, jiffies + HZ * timeout_sec / 2);
+ if (wdt_auto)
+ wdt_last_ping = jiffies;
+
+ if (jiffies - wdt_last_ping <= heartbeat * HZ) {
+ mpc8xxx_wdt_keepalive();
+ /* We're pinging it twice faster than needed, to be sure. */
+ mod_timer(&wdt_timer, jiffies + HZ * timeout_sec / 2);
+ }
+}
+
+static void mpc8xxx_wdt_sw_keepalive(void)
+{
+ wdt_last_ping = jiffies;
+ mpc8xxx_wdt_timer_ping(0);
}
static void mpc8xxx_wdt_pr_warn(const char *msg)
@@ -106,7 +126,7 @@
size_t count, loff_t *ppos)
{
if (count)
- mpc8xxx_wdt_keepalive();
+ mpc8xxx_wdt_sw_keepalive();
return count;
}
@@ -130,7 +150,7 @@
out_be32(&wd_base->swcrr, tmp);
- del_timer_sync(&wdt_timer);
+ wdt_auto = 0;
return nonseekable_open(inode, file);
}
@@ -138,7 +158,8 @@
static int mpc8xxx_wdt_release(struct inode *inode, struct file *file)
{
if (!nowayout)
- mpc8xxx_wdt_timer_ping(0);
+ wdt_auto = 1;
+
else
mpc8xxx_wdt_pr_warn("watchdog closed");
clear_bit(0, &wdt_is_open);
@@ -163,10 +184,12 @@
case WDIOC_GETBOOTSTATUS:
return put_user(0, p);
case WDIOC_KEEPALIVE:
- mpc8xxx_wdt_keepalive();
+ mpc8xxx_wdt_sw_keepalive();
return 0;
case WDIOC_GETTIMEOUT:
- return put_user(timeout_sec, p);
+ return put_user(heartbeat, p);
+ case WDIOC_SETTIMEOUT:
+ return get_user(heartbeat, p);
default:
return -ENOTTY;
}
@@ -215,6 +238,8 @@
ret = -ENOSYS;
goto err_unmap;
}
+ if (enabled)
+ timeout = in_be32(&wd_base->swcrr) >> 16;
/* Calculate the timeout in seconds */
if (prescale)
@@ -273,6 +298,7 @@
.compatible = "fsl,mpc823-wdt",
.data = &(struct mpc8xxx_wdt_type) {
.prescaler = 0x800,
+ .hw_enabled = true,
},
},
{},
^ permalink raw reply
* Re: [PATCH v3 1/1] powerpc/85xx: Board support for ppa8548
From: Timur Tabi @ 2013-02-13 17:29 UTC (permalink / raw)
To: Stef van Os
Cc: scottwood@freescale.com, Paul Mackerras,
linuxppc-dev@lists.ozlabs.org
In-Reply-To: <1360764540-4185-1-git-send-email-stef.van.os@prodrive.nl>
On 02/13/2013 08:09 AM, Stef van Os wrote:
> Initial board support for the Prodrive PPA8548 AMC module. Board
> is an MPC8548 AMC platform used in RapidIO systems. This module is
> also used to test/work on mainline linux RapidIO software.
>
> PPA8548 overview:
> - 1.3 GHz Freescale PowerQUICC III MPC8548 processor
> - 1 GB DDR2 @ 266 MHz
> - 8 MB NOR flash
> - Serial RapidIO 1.2
> - 1 x 10/100/1000 BASE-T front ethernet
> - 1 x 1000 BASE-BX ethernet on AMC connector
>
> Signed-off-by: Stef van Os <stef.van.os@prodrive.nl>
Acked-by: Timur Tabi <timur@tabi.org>
^ permalink raw reply
* Re: BOOKE KVM calling load_up_fpu from C?
From: Scott Wood @ 2013-02-13 17:37 UTC (permalink / raw)
To: Bhushan Bharat-R65777
Cc: Wood Scott-B07421, Michael Neuling, linuxppc-dev@lists.ozlabs.org
In-Reply-To: <6A3DF150A5B70D4F9B66A25E3F7C888D065A3511@039-SN2MPN1-023.039d.mgd.msft.net>
On 02/12/2013 10:17:00 PM, Bhushan Bharat-R65777 wrote:
>=20
>=20
> > -----Original Message-----
> > From: Wood Scott-B07421
> > Sent: Wednesday, February 13, 2013 6:53 AM
> > To: Bhushan Bharat-R65777
> > Cc: Wood Scott-B07421; Michael Neuling; =20
> linuxppc-dev@lists.ozlabs.org
> > Subject: Re: BOOKE KVM calling load_up_fpu from C?
> >
> > On 02/12/2013 07:18:14 PM, Bhushan Bharat-R65777 wrote:
> > >
> > >
> > > > -----Original Message-----
> > > > From: Wood Scott-B07421
> > > > Sent: Wednesday, February 13, 2013 12:03 AM
> > > > To: Bhushan Bharat-R65777
> > > > Cc: Michael Neuling; Wood Scott-B07421;
> > > linuxppc-dev@lists.ozlabs.org
> > > > Subject: Re: BOOKE KVM calling load_up_fpu from C?
> > > >
> > > > On 64-bit, though, there's a store to the caller's stack frame
> > > > (yuck) which the kvm/booke.h caller is not prepared for.
> > >
> > > So if caller is using r12 then it can lead to come corruption, =20
> right ?
> >
> > No, r12 is a volatile register in the ABI, as is r9. The issue is =20
> that the
> > stack can be corrupted.
>=20
> What do you mean by stack is corrupted?
load_up_fpu() makes assumptions about the caller's stack frame that =20
aren't true when called from C code.
> My understanding is that when calling the assembly function from C =20
> function then stack frame will not be pushed and assembly function =20
> uses the caller stack frame.
Huh? Assembly functions obey the same ABI as C functions (at least, =20
asm functions meant to be callable from C do). If the above were true, =20
how would C code know that it's calling an asm function, and how would =20
it know how much stack to create and which portions would be clobbered?
The issue with load_up_fpu() is that it was apparently not meant to be =20
called directly from C code.
-Scott=
^ permalink raw reply
* RE: [PATCH 2/2] powerpc: Make context bits depend on virtual addr size.
From: Aneesh Kumar K.V @ 2013-02-13 18:07 UTC (permalink / raw)
To: David Laight, Benjamin Herrenschmidt, phileas-fogg, geoff
Cc: paulus, linuxppc-dev
In-Reply-To: <87mwv8jnmj.fsf@linux.vnet.ibm.com>
"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> writes:
> David Laight <David.Laight@aculab.com> writes:
>
>>> +#define CONTEXT_BITS 19
>>> +#define USER_ESID_BITS 18
>>> +#define USER_ESID_BITS_1T 6
>>> +
>>> +/*
>>> + * 256MB segment
>>> + * The proto-VSID space has 2^(CONTEX_BITS + USER_ESID_BITS) - 1 segments
>>> + * available for user + kernel mapping. The top 4 contexts are used for
>>> + * kernel mapping. Each segment contains 2^28 bytes. Each
>>> + * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
>>> + * (19 == 37 + 28 - 46).
>>> + */
>>
>> I can't help feeling this would be easier to understand if a full
>> 64? 80? bit address was shown with the various bit ranges identified.
>>
>> Given the comment, I'd have expected CONTEXT_BITS to be calculated
>> from three other named constants - rather than being set to 19.
>>
>
> May be the comments were misleading. We build proto vsid using a
> combination of context and ea bits.
>
> Current code does the below:
>
> for kernel:
> proto_vsid = ea >> SID_SHIFT;
> proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS));
> for user:
> proto_vsid = ea >> SID_SHIFT
> proto_vsid |= context << USER_ESID_BITS
>
> context range is 0 - (2^19 -1)
>
> With this patch we _don't_ give kernel half the proto vsid range.
> Instead, we reduce the proto vsid range and then the kernel is given
> top 4 context. ie, kernel proto vsid is now
>
> for kenel:
> proto_vsid = ea >> SID_SHIFT;
> context = (MAX_CONTEXT - 4) + ((effective address >> 60) - 0xc);
> proto_vsid |= context << USER_ESID_BITS
>
Hmm that may be an issue, considering ESID for kernel is 36 bits.
We have overlapping bits between shifted value of context and kernel
ESID.
-aneesh
^ permalink raw reply
* Re[2]: [PATCH 2/2] powerpc: Make context bits depend on virtual addr size.
From: Phileas Fogg @ 2013-02-13 18:13 UTC (permalink / raw)
To: Aneesh Kumar K.V; +Cc: geoff, linuxppc-dev, paulus
In-Reply-To: <87pq04jvb4.fsf@linux.vnet.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 481 bytes --]
>
>Ok. How about the below patch. This is based on the suggestion from
>Paulus. I still have to take care of few comments in the code.
>
>We now split the proto-vsid range differently.
> User: 0 to [2^(CONTEXT_BITS) - 4 + 2^(USER_ESID_BITS)]
> kernel: [2^(CONTEXT_BITS) - 4 + 2^(USER_ESID_BITS)] to 2^(VSID_BITS) - 1
>
>Phileas and Geoff,
>
>Can we check whether this fix the PS3 boot hang ?
Tested the new patch with Linux 3.8.0-rc7, it seems to be working well.
regards
[-- Attachment #2: Type: text/html, Size: 890 bytes --]
^ permalink raw reply
* Re: [PATCH 2/2] powerpc: Make context bits depend on virtual addr size.
From: Geoff Levand @ 2013-02-13 20:09 UTC (permalink / raw)
To: Aneesh Kumar K.V; +Cc: phileas-fogg, linuxppc-dev, paulus
In-Reply-To: <87pq04jvb4.fsf@linux.vnet.ibm.com>
Hi Aneesh,
On Wed, 2013-02-13 at 17:10 +0530, Aneesh Kumar K.V wrote:
> Ok. How about the below patch. This is based on the suggestion from
> Paulus. I still have to take care of few comments in the code.
>
> Phileas and Geoff,
>
> Can we check whether this fix the PS3 boot hang ?
I did a quick build and boot test, and this one seems to work OK.
-Geoff
^ permalink raw reply
* Re: PS3 platform is broken on Linux 3.7.0
From: Michael Ellerman @ 2013-02-13 22:37 UTC (permalink / raw)
To: Geoff Levand; +Cc: Phileas Fogg, cbe-oss-dev, linuxppc-dev
In-Reply-To: <1360740779.28936.20.camel@clam>
On Tue, Feb 12, 2013 at 11:32:59PM -0800, Geoff Levand wrote:
> Hi,
>
> On Fri, 2012-12-14 at 16:35 +0400, Phileas Fogg wrote:
> > I wanted to bring to your attention the fact that the PS3 platform is broken on Linux 3.7.0.
>
> > So i cloned the Linux powerpc GIT repository and tried to find out which commits broke the PS3 platform.
>
> > ---------------------------------------------------------------------------------------------
> >
> > commit 407821a34fce89b4f0b031dbab5cec7d059f46bc
> > Author: Michael Ellerman <michael@ellerman.id.au>
> > Date: Fri Sep 7 15:31:44 2012 +0000
> >
> > powerpc: Initialise paca.data_offset with poison
>
> I did a little more work on this, and it seems the change below
> will fix the problem introduced by Michael's change. I can only
> guess we need to use udbg_printf() here. I'll look at it some more
> as I have time.
Have you tried with the patch I posted yesterday?
cheers
^ permalink raw reply
* [PATCH] powerpc: Mark low level irq handlers NO_THREAD
From: Thomas Gleixner @ 2013-02-13 22:38 UTC (permalink / raw)
To: linuxppc-dev; +Cc: leroy christophe
These low level handlers cannot be threaded. Mark them NO_THREAD
Reported-by: leroy christophe <christophe.leroy@c-s.fr>
Tested-by: leroy christophe <christophe.leroy@c-s.fr>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/powerpc/platforms/8xx/m8xx_setup.c | 1 +
arch/powerpc/sysdev/cpm1.c | 1 +
2 files changed, 2 insertions(+)
Index: linux-stable/arch/powerpc/platforms/8xx/m8xx_setup.c
===================================================================
--- linux-stable.orig/arch/powerpc/platforms/8xx/m8xx_setup.c
+++ linux-stable/arch/powerpc/platforms/8xx/m8xx_setup.c
@@ -43,6 +43,7 @@ static irqreturn_t timebase_interrupt(in
static struct irqaction tbint_irqaction = {
.handler = timebase_interrupt,
+ .flags = IRQF_NO_THREAD,
.name = "tbint",
};
Index: linux-stable/arch/powerpc/sysdev/cpm1.c
===================================================================
--- linux-stable.orig/arch/powerpc/sysdev/cpm1.c
+++ linux-stable/arch/powerpc/sysdev/cpm1.c
@@ -120,6 +120,7 @@ static irqreturn_t cpm_error_interrupt(i
static struct irqaction cpm_error_irqaction = {
.handler = cpm_error_interrupt,
+ .flags = IRQF_NO_THREAD,
.name = "error",
};
^ permalink raw reply
* Re: [PATCH] powerpc: Apply early paca fixups to boot_paca and the boot cpu's paca
From: Geoff Levand @ 2013-02-14 0:57 UTC (permalink / raw)
To: Michael Ellerman; +Cc: phileas-fogg, linuxppc-dev, stable
In-Reply-To: <1360716290-15985-1-git-send-email-michael@ellerman.id.au>
On Wed, 2013-02-13 at 11:44 +1100, Michael Ellerman wrote:
> In commit 466921c we added a hack to set the paca data_offset to zero so
> that per-cpu accesses would work on the boot cpu prior to per-cpu areas
> being setup. This fixed a problem with lockdep touching per-cpu areas
> very early in boot.
>
> However if we combine CONFIG_LOCK_STAT=y with any of the PPC_EARLY_DEBUG
> options, we can hit the same problem in udbg_early_init(). To avoid that
> we need to set the data_offset of the boot_paca also. So factor out the
> fixup logic and call it for both the boot_paca, and "the paca of the
> boot cpu".
>
> Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Tested-by: Geoff Levand <geoff@infradead.org>
This fixes a boot hang on the PS3 with ps3_defconfig builds of
linux-3.7.
Please consider applying for linux-3.7.x stable.
-Geoff
^ permalink raw reply
* Re: [PATCH 15/17] powerpc: Add config option for transactional memory
From: Michael Neuling @ 2013-02-14 1:52 UTC (permalink / raw)
To: Kumar Gala; +Cc: linuxppc-dev, Matt Evans
In-Reply-To: <2AEBB52F-9DB5-4211-9DA7-B1D271F1D6E8@kernel.crashing.org>
Kumar Gala <galak@kernel.crashing.org> wrote:
>
> On Feb 12, 2013, at 10:31 PM, Michael Neuling wrote:
>
> > Kconfig option for transactional memory on powerpc.
> >
> > Signed-off-by: Matt Evans <matt@ozlabs.org>
> > Signed-off-by: Michael Neuling <mikey@neuling.org>
> > ---
> > arch/powerpc/Kconfig | 8 ++++++++
> > 1 file changed, 8 insertions(+)
> >
> > diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> > index 4b27edb..fbeb6d2 100644
> > --- a/arch/powerpc/Kconfig
> > +++ b/arch/powerpc/Kconfig
> > @@ -313,6 +313,14 @@ config MATH_EMULATION
> > unit, which will allow programs that use floating-point
> > instructions to run.
> >
> > +config PPC_TRANSACTIONAL_MEM
> > + bool "Transactional Memory support for POWERPC"
> > + depends on PPC64
>
> Should this really depend on PPC_BOOK3S_64 ?
OK, thanks.
Mikey
^ permalink raw reply
* Re: [PATCH 08/17] powerpc: Add FP/VSX and VMX register load functions for transactional memory
From: Michael Neuling @ 2013-02-14 1:53 UTC (permalink / raw)
To: Kumar Gala; +Cc: linuxppc-dev, Matt Evans
In-Reply-To: <0233B491-CB0D-4B0C-9859-8B486D3C3314@kernel.crashing.org>
> > +/* void do_load_up_fpu(struct thread_struct *thread)
>
> Comment is wrong, should be void do_load_up_transact_fpu(...)
Ooops, thanks for the catch.
> > +/* void do_load_up_altivec(struct thread_struct *thread)
>
> comment wrong.
Ooops again.
FYI I'm in Austin next week if you wanna grab a beer.
Mikey
^ permalink raw reply
* Re: [PATCH 06/17] powerpc: Add transactional memory paca scratch register to show_regs
From: Michael Neuling @ 2013-02-14 1:53 UTC (permalink / raw)
To: Kumar Gala; +Cc: linuxppc-dev, Matt Evans
In-Reply-To: <7B4CE428-128F-43FC-9ABE-CE3728B3CF93@kernel.crashing.org>
Kumar Gala <galak@kernel.crashing.org> wrote:
>
> On Feb 12, 2013, at 10:31 PM, Michael Neuling wrote:
>
> > Add transactional memory paca scratch register to show_regs. This is useful
> > for debugging.
> >
> > Signed-off-by: Matt Evans <matt@ozlabs.org>
> > Signed-off-by: Michael Neuling <mikey@neuling.org>
> > ---
> > arch/powerpc/include/asm/paca.h | 1 +
> > arch/powerpc/kernel/asm-offsets.c | 1 +
> > arch/powerpc/kernel/entry_64.S | 4 ++++
> > arch/powerpc/kernel/process.c | 3 +++
> > 4 files changed, 9 insertions(+)
> >
> > diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
> > index c47d687..07e9851 100644
> > --- a/arch/powerpc/include/asm/paca.h
> > +++ b/arch/powerpc/include/asm/paca.h
> > @@ -137,6 +137,7 @@ struct paca_struct {
> > u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */
> > u8 nap_state_lost; /* NV GPR values lost in power7_idle */
> > u64 sprg3; /* Saved user-visible sprg */
>
> #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
>
> > + u64 tm_scratch; /* TM scratch area for reclaim */
>
> #endif
Yep.. thanks again.
Mikey
^ permalink raw reply
* [PATCH 00/17] powerpc: Hardware transactional memory support for POWER8
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360729895-304-1-git-send-email-mikey@neuling.org>
POWER8 implements hardware transactional memory support. This patch series
adds kernel support so that user programs can use this hardware transactional
memory and the new state is properly context switched. It is not currently
used by the kernel itself.
This patch series was originally developed by Matt Evans.
v4 changes:
Incorporate reviews from Kumar.
v3 changes:
Incorporate review from benh (offline conversation):
- Improve IRQ disabling for tm_reclaim
- Improve IRQ disabling for early fp/vmx/vsx unavail handling
- Change CONFIG option to add PPC (now PPC_TRANSACTIONAL_MEM)
- strip some unneeded #defines
- micro optimisation to asm in early fp/vmx/vsx
- srdi r0, r12, MSR_TS_LG
- andi. r0, r0, 3
+ rldicl. r0, r12, (64-MSR_TS_LG), (64-2)
- do tabort on unmap only when current is using TM
- removed unneeded patch which moved when writing MSR back to the stack
v2 changes:
Adds signal handling
Removes some code for detecting when to restore all register or not
Added tabort for local tlb invalidates
Rebased on benh's next tree
Basic overview of a POWER8 hardware transaction memory
=====================================================
Hardware transactional memory is a feature that enables a different form of
atomic memory access. Several new instructions are presented to delimit
transactions; transactions are guaranteed to either complete atomically or roll
back and undo any partial changes.
A simple transaction looks like this:
begin_move_money:
tbegin
beq abort_handler
ld r4, SAVINGS_ACCT(r3)
ld r5, CURRENT_ACCT(r3)
subi r5, r5, 1
addi r4, r4, 1
std r4, SAVINGS_ACCT(r3)
std r5, CURRENT_ACCT(r3)
tend
b continue
abort_handler:
... test for odd failures ...
/* Retry the transaction if it failed because it conflicted with
* someone else: */
b begin_move_money
The 'tbegin' instruction denotes the start point, and 'tend' the end point.
Between these points the processor is in 'Transactional' state; any memory
references will complete in one go if there are no conflicts with other
transactional or non-transactional accesses within the system. In this
example, the transaction completes as though it were normal straight-line code
IF no other processor has touched SAVINGS_ACCT(r3) or CURRENT_ACCT(r3); an
atomic move of money from the current account to the savings account has been
performed. Even though the normal ld/std instructions are used (note no
lwarx/stwcx), either *both* SAVINGS_ACCT(r3) and CURRENT_ACCT(r3) will be
updated, or neither will be updated.
If, in the meantime, there is a conflict with the locations accessed by the
transaction, the transaction will be aborted by the CPU. Register and memory
state will roll back to that at the 'tbegin', and control will continue from
'tbegin+4'. The branch to abort_handler will be taken this second time; the
abort handler can check the cause of the failure, and retry.
Checkpointed registers include all GPRs, FPRs, VRs/VSRs, LR, CCR/CR, CTR, FPCSR
and a few other status/flag regs;
A preliminary ISA for TM can be found here:
https://www.power.org/documentation/power-isa-transactional-memory/
--
1.7.10.4
^ permalink raw reply
* [PATCH 01/17] powerpc: Add new CPU feature bit for transactional memory
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360808505-10086-1-git-send-email-mikey@neuling.org>
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/cputable.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 5f1938f..3636081 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -220,6 +220,13 @@ extern const char *powerpc_base_platform;
#define PPC_FEATURE_HAS_EFP_DOUBLE_COMP 0
#endif
+/* We only set the TM feature if the kernel was compiled with TM supprt */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+#define CPU_FTR_TM_COMP CPU_FTR_TM
+#else
+#define CPU_FTR_TM_COMP 0
+#endif
+
/* We need to mark all pages as being coherent if we're SMP or we have a
* 74[45]x and an MPC107 host bridge. Also 83xx and PowerQUICC II
* require it for PCI "streaming/prefetch" to work properly.
--
1.7.10.4
^ permalink raw reply related
* [PATCH 02/17] powerpc: Add new instructions for transactional memory
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360808505-10086-1-git-send-email-mikey@neuling.org>
Here we define the new instructions we need for transactional memory in the
kernel. This is so we can support compiling with binutils that don't support
the new transactional memory instructions.
Transactional memory results in two sets of architected state (GPRs/VSRs
etc).
treclaim allows us to read the checkpointed state (from the tbegin) so that we
can store it away on a context switch. It does this by overwriting the exiting
architected state, so you have to save that away before you treclaim. treclaim
will also abort a transaction, so you can give a register value which contains
an abort reason.
trecheckpoint allows us to inject into the checkpointed state as if it were at
the tbegin. It does this by copying the current architected state into the
checkpointed state.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/ppc-opcode.h | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 0fd1928..8752bc8 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -129,6 +129,9 @@
#define PPC_INST_TLBSRX_DOT 0x7c0006a5
#define PPC_INST_XXLOR 0xf0000510
#define PPC_INST_XVCPSGNDP 0xf0000780
+#define PPC_INST_TRECHKPT 0x7c0007dd
+#define PPC_INST_TRECLAIM 0x7c00075d
+#define PPC_INST_TABORT 0x7c00071d
#define PPC_INST_NAP 0x4c000364
#define PPC_INST_SLEEP 0x4c0003a4
@@ -294,4 +297,11 @@
#define PPC_NAP stringify_in_c(.long PPC_INST_NAP)
#define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP)
+/* Transactional memory instructions */
+#define TRECHKPT stringify_in_c(.long PPC_INST_TRECHKPT)
+#define TRECLAIM(r) stringify_in_c(.long PPC_INST_TRECLAIM \
+ | __PPC_RA(r))
+#define TABORT(r) stringify_in_c(.long PPC_INST_TABORT \
+ | __PPC_RA(r))
+
#endif /* _ASM_POWERPC_PPC_OPCODE_H */
--
1.7.10.4
^ permalink raw reply related
* [PATCH 03/17] powerpc: Add additional state needed for transactional memory to thread struct
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360808505-10086-1-git-send-email-mikey@neuling.org>
Set of new archtected state for saving away on context switch.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/processor.h | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 42ac53c..fc41ab3 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -246,6 +246,34 @@ struct thread_struct {
unsigned long spefscr; /* SPE & eFP status */
int used_spe; /* set if process has used spe */
#endif /* CONFIG_SPE */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ u64 tm_tfhar; /* Transaction fail handler addr */
+ u64 tm_texasr; /* Transaction exception & summary */
+ u64 tm_tfiar; /* Transaction fail instr address reg */
+ unsigned long tm_orig_msr; /* Thread's MSR on ctx switch */
+ struct pt_regs ckpt_regs; /* Checkpointed registers */
+
+ /*
+ * Transactional FP and VSX 0-31 register set.
+ * NOTE: the sense of these is the opposite of the integer ckpt_regs!
+ *
+ * When a transaction is active/signalled/scheduled etc., *regs is the
+ * most recent set of/speculated GPRs with ckpt_regs being the older
+ * checkpointed regs to which we roll back if transaction aborts.
+ *
+ * However, fpr[] is the checkpointed 'base state' of FP regs, and
+ * transact_fpr[] is the new set of transactional values.
+ * VRs work the same way.
+ */
+ double transact_fpr[32][TS_FPRWIDTH];
+ struct {
+ unsigned int pad;
+ unsigned int val; /* Floating point status */
+ } transact_fpscr;
+ vector128 transact_vr[32] __attribute__((aligned(16)));
+ vector128 transact_vscr __attribute__((aligned(16)));
+ unsigned long transact_vrsave;
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
void* kvm_shadow_vcpu; /* KVM internal data */
#endif /* CONFIG_KVM_BOOK3S_32_HANDLER */
--
1.7.10.4
^ permalink raw reply related
* [PATCH 04/17] powerpc: New macros for transactional memory support
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360808505-10086-1-git-send-email-mikey@neuling.org>
This adds new macros for saving and restoring checkpointed architected state
from and to the thread_struct.
It also adds some debugging macros for when your brain explodes trying to debug
your transactional memory enabled kernel.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/ppc_asm.h | 83 ++++++++++++++++++++++++++++++++++
arch/powerpc/include/asm/processor.h | 1 +
arch/powerpc/kernel/asm-offsets.c | 23 ++++++++++
arch/powerpc/kernel/fpu.S | 12 +++++
arch/powerpc/kernel/process.c | 7 +++
arch/powerpc/kernel/traps.c | 8 ++++
6 files changed, 134 insertions(+)
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index c2d0e58..54219ce 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -123,6 +123,89 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
#define REST_16VRS(n,b,base) REST_8VRS(n,b,base); REST_8VRS(n+8,b,base)
#define REST_32VRS(n,b,base) REST_16VRS(n,b,base); REST_16VRS(n+16,b,base)
+/* Save/restore FPRs, VRs and VSRs from their checkpointed backups in
+ * thread_struct:
+ */
+#define SAVE_FPR_TRANSACT(n, base) stfd n,THREAD_TRANSACT_FPR0+ \
+ 8*TS_FPRWIDTH*(n)(base)
+#define SAVE_2FPRS_TRANSACT(n, base) SAVE_FPR_TRANSACT(n, base); \
+ SAVE_FPR_TRANSACT(n+1, base)
+#define SAVE_4FPRS_TRANSACT(n, base) SAVE_2FPRS_TRANSACT(n, base); \
+ SAVE_2FPRS_TRANSACT(n+2, base)
+#define SAVE_8FPRS_TRANSACT(n, base) SAVE_4FPRS_TRANSACT(n, base); \
+ SAVE_4FPRS_TRANSACT(n+4, base)
+#define SAVE_16FPRS_TRANSACT(n, base) SAVE_8FPRS_TRANSACT(n, base); \
+ SAVE_8FPRS_TRANSACT(n+8, base)
+#define SAVE_32FPRS_TRANSACT(n, base) SAVE_16FPRS_TRANSACT(n, base); \
+ SAVE_16FPRS_TRANSACT(n+16, base)
+
+#define REST_FPR_TRANSACT(n, base) lfd n,THREAD_TRANSACT_FPR0+ \
+ 8*TS_FPRWIDTH*(n)(base)
+#define REST_2FPRS_TRANSACT(n, base) REST_FPR_TRANSACT(n, base); \
+ REST_FPR_TRANSACT(n+1, base)
+#define REST_4FPRS_TRANSACT(n, base) REST_2FPRS_TRANSACT(n, base); \
+ REST_2FPRS_TRANSACT(n+2, base)
+#define REST_8FPRS_TRANSACT(n, base) REST_4FPRS_TRANSACT(n, base); \
+ REST_4FPRS_TRANSACT(n+4, base)
+#define REST_16FPRS_TRANSACT(n, base) REST_8FPRS_TRANSACT(n, base); \
+ REST_8FPRS_TRANSACT(n+8, base)
+#define REST_32FPRS_TRANSACT(n, base) REST_16FPRS_TRANSACT(n, base); \
+ REST_16FPRS_TRANSACT(n+16, base)
+
+
+#define SAVE_VR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VR0+(16*(n)); \
+ stvx n,b,base
+#define SAVE_2VRS_TRANSACT(n,b,base) SAVE_VR_TRANSACT(n,b,base); \
+ SAVE_VR_TRANSACT(n+1,b,base)
+#define SAVE_4VRS_TRANSACT(n,b,base) SAVE_2VRS_TRANSACT(n,b,base); \
+ SAVE_2VRS_TRANSACT(n+2,b,base)
+#define SAVE_8VRS_TRANSACT(n,b,base) SAVE_4VRS_TRANSACT(n,b,base); \
+ SAVE_4VRS_TRANSACT(n+4,b,base)
+#define SAVE_16VRS_TRANSACT(n,b,base) SAVE_8VRS_TRANSACT(n,b,base); \
+ SAVE_8VRS_TRANSACT(n+8,b,base)
+#define SAVE_32VRS_TRANSACT(n,b,base) SAVE_16VRS_TRANSACT(n,b,base); \
+ SAVE_16VRS_TRANSACT(n+16,b,base)
+
+#define REST_VR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VR0+(16*(n)); \
+ lvx n,b,base
+#define REST_2VRS_TRANSACT(n,b,base) REST_VR_TRANSACT(n,b,base); \
+ REST_VR_TRANSACT(n+1,b,base)
+#define REST_4VRS_TRANSACT(n,b,base) REST_2VRS_TRANSACT(n,b,base); \
+ REST_2VRS_TRANSACT(n+2,b,base)
+#define REST_8VRS_TRANSACT(n,b,base) REST_4VRS_TRANSACT(n,b,base); \
+ REST_4VRS_TRANSACT(n+4,b,base)
+#define REST_16VRS_TRANSACT(n,b,base) REST_8VRS_TRANSACT(n,b,base); \
+ REST_8VRS_TRANSACT(n+8,b,base)
+#define REST_32VRS_TRANSACT(n,b,base) REST_16VRS_TRANSACT(n,b,base); \
+ REST_16VRS_TRANSACT(n+16,b,base)
+
+
+#define SAVE_VSR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VSR0+(16*(n)); \
+ STXVD2X(n,R##base,R##b)
+#define SAVE_2VSRS_TRANSACT(n,b,base) SAVE_VSR_TRANSACT(n,b,base); \
+ SAVE_VSR_TRANSACT(n+1,b,base)
+#define SAVE_4VSRS_TRANSACT(n,b,base) SAVE_2VSRS_TRANSACT(n,b,base); \
+ SAVE_2VSRS_TRANSACT(n+2,b,base)
+#define SAVE_8VSRS_TRANSACT(n,b,base) SAVE_4VSRS_TRANSACT(n,b,base); \
+ SAVE_4VSRS_TRANSACT(n+4,b,base)
+#define SAVE_16VSRS_TRANSACT(n,b,base) SAVE_8VSRS_TRANSACT(n,b,base); \
+ SAVE_8VSRS_TRANSACT(n+8,b,base)
+#define SAVE_32VSRS_TRANSACT(n,b,base) SAVE_16VSRS_TRANSACT(n,b,base); \
+ SAVE_16VSRS_TRANSACT(n+16,b,base)
+
+#define REST_VSR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VSR0+(16*(n)); \
+ LXVD2X(n,R##base,R##b)
+#define REST_2VSRS_TRANSACT(n,b,base) REST_VSR_TRANSACT(n,b,base); \
+ REST_VSR_TRANSACT(n+1,b,base)
+#define REST_4VSRS_TRANSACT(n,b,base) REST_2VSRS_TRANSACT(n,b,base); \
+ REST_2VSRS_TRANSACT(n+2,b,base)
+#define REST_8VSRS_TRANSACT(n,b,base) REST_4VSRS_TRANSACT(n,b,base); \
+ REST_4VSRS_TRANSACT(n+4,b,base)
+#define REST_16VSRS_TRANSACT(n,b,base) REST_8VSRS_TRANSACT(n,b,base); \
+ REST_8VSRS_TRANSACT(n+8,b,base)
+#define REST_32VSRS_TRANSACT(n,b,base) REST_16VSRS_TRANSACT(n,b,base); \
+ REST_16VSRS_TRANSACT(n+16,b,base)
+
/* Save the lower 32 VSRs in the thread VSR region */
#define SAVE_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); STXVD2X(n,R##base,R##b)
#define SAVE_2VSRS(n,b,base) SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index fc41ab3..7ff9eaa 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -152,6 +152,7 @@ typedef struct {
#define TS_FPROFFSET 0
#define TS_VSRLOWOFFSET 1
#define TS_FPR(i) fpr[i][TS_FPROFFSET]
+#define TS_TRANS_FPR(i) transact_fpr[i][TS_FPROFFSET]
struct thread_struct {
unsigned long ksp; /* Kernel stack pointer */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index beddba4..b67e4c3 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -125,6 +125,29 @@ int main(void)
#ifdef CONFIG_PPC_BOOK3S_64
DEFINE(THREAD_TAR, offsetof(struct thread_struct, tar));
#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
+ DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr));
+ DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar));
+ DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
+ DEFINE(THREAD_TRANSACT_VR0, offsetof(struct thread_struct,
+ transact_vr[0]));
+ DEFINE(THREAD_TRANSACT_VSCR, offsetof(struct thread_struct,
+ transact_vscr));
+ DEFINE(THREAD_TRANSACT_VRSAVE, offsetof(struct thread_struct,
+ transact_vrsave));
+ DEFINE(THREAD_TRANSACT_FPR0, offsetof(struct thread_struct,
+ transact_fpr[0]));
+ DEFINE(THREAD_TRANSACT_FPSCR, offsetof(struct thread_struct,
+ transact_fpscr));
+#ifdef CONFIG_VSX
+ DEFINE(THREAD_TRANSACT_VSR0, offsetof(struct thread_struct,
+ transact_fpr[0]));
+#endif
+ /* Local pt_regs on stack for Transactional Memory funcs. */
+ DEFINE(TM_FRAME_SIZE, STACK_FRAME_OVERHEAD +
+ sizeof(struct pt_regs) + 16);
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index e0ada05..adb1551 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -35,6 +35,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
2: REST_32VSRS(n,c,base); \
3:
+#define __REST_32FPVSRS_TRANSACT(n,c,base) \
+BEGIN_FTR_SECTION \
+ b 2f; \
+END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
+ REST_32FPRS_TRANSACT(n,base); \
+ b 3f; \
+2: REST_32VSRS_TRANSACT(n,c,base); \
+3:
+
#define __SAVE_32FPVSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
@@ -45,9 +54,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
3:
#else
#define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base)
+#define __REST_32FPVSRS_TRANSACT(n,b,base) REST_32FPRS(n, base)
#define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base)
#endif
#define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
+#define REST_32FPVSRS_TRANSACT(n,c,base) \
+ __REST_32FPVSRS_TRANSACT(n,__REG_##c,__REG_##base)
#define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
/*
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 96e31de..b0a0321 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -57,6 +57,13 @@
#include <linux/kprobes.h>
#include <linux/kdebug.h>
+/* Transactional Memory debug */
+#ifdef TM_DEBUG_SW
+#define TM_DEBUG(x...) printk(KERN_INFO x)
+#else
+#define TM_DEBUG(x...) do { } while(0)
+#endif
+
extern unsigned long _get_SP(void);
#ifndef CONFIG_SMP
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index a008cf5..bd5de5d 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -78,6 +78,13 @@ EXPORT_SYMBOL(__debugger_break_match);
EXPORT_SYMBOL(__debugger_fault_handler);
#endif
+/* Transactional Memory trap debug */
+#ifdef TM_DEBUG_SW
+#define TM_DEBUG(x...) printk(KERN_INFO x)
+#else
+#define TM_DEBUG(x...) do { } while(0)
+#endif
+
/*
* Trap & Exception support
*/
@@ -350,6 +357,7 @@ static inline int check_io_access(struct pt_regs *regs)
exception is in the MSR. */
#define get_reason(regs) ((regs)->msr)
#define get_mc_reason(regs) ((regs)->msr)
+#define REASON_TM 0x200000
#define REASON_FP 0x100000
#define REASON_ILLEGAL 0x80000
#define REASON_PRIVILEGED 0x40000
--
1.7.10.4
^ permalink raw reply related
* [PATCH 05/17] powerpc: Register defines for various transactional memory registers
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360808505-10086-1-git-send-email-mikey@neuling.org>
Defines for MSR bits and transactional memory related SPRs TFIAR, TEXASR and
TEXASRU.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/reg.h | 27 +++++++++++++++++++++++++++
1 file changed, 27 insertions(+)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index e09ac51..7844c28 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -29,6 +29,10 @@
#define MSR_SF_LG 63 /* Enable 64 bit mode */
#define MSR_ISF_LG 61 /* Interrupt 64b mode valid on 630 */
#define MSR_HV_LG 60 /* Hypervisor state */
+#define MSR_TS_T_LG 34 /* Trans Mem state: Transactional */
+#define MSR_TS_S_LG 33 /* Trans Mem state: Suspended */
+#define MSR_TS_LG 33 /* Trans Mem state (2 bits) */
+#define MSR_TM_LG 32 /* Trans Mem Available */
#define MSR_VEC_LG 25 /* Enable AltiVec */
#define MSR_VSX_LG 23 /* Enable VSX */
#define MSR_POW_LG 18 /* Enable Power Management */
@@ -98,6 +102,25 @@
#define MSR_RI __MASK(MSR_RI_LG) /* Recoverable Exception */
#define MSR_LE __MASK(MSR_LE_LG) /* Little Endian */
+#define MSR_TM __MASK(MSR_TM_LG) /* Transactional Mem Available */
+#define MSR_TS_N 0 /* Non-transactional */
+#define MSR_TS_S __MASK(MSR_TS_S_LG) /* Transaction Suspended */
+#define MSR_TS_T __MASK(MSR_TS_T_LG) /* Transaction Transactional */
+#define MSR_TS_MASK (MSR_TS_T | MSR_TS_S) /* Transaction State bits */
+#define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */
+#define MSR_TM_TRANSACTIONAL(x) (((x) & MSR_TS_MASK) == MSR_TS_T)
+#define MSR_TM_SUSPENDED(x) (((x) & MSR_TS_MASK) == MSR_TS_S)
+
+/* Reason codes describing kernel causes for transaction aborts. By
+ convention, bit0 is copied to TEXASR[56] (IBM bit 7) which is set if
+ the failure is persistent.
+*/
+#define TM_CAUSE_RESCHED 0xfe
+#define TM_CAUSE_TLBI 0xfc
+#define TM_CAUSE_FAC_UNAV 0xfa
+#define TM_CAUSE_SYSCALL 0xf9 /* Persistent */
+#define TM_CAUSE_MISC 0xf6
+
#if defined(CONFIG_PPC_BOOK3S_64)
#define MSR_64BIT MSR_SF
@@ -193,6 +216,10 @@
#define SPRN_UAMOR 0x9d /* User Authority Mask Override Register */
#define SPRN_AMOR 0x15d /* Authority Mask Override Register */
#define SPRN_ACOP 0x1F /* Available Coprocessor Register */
+#define SPRN_TFIAR 0x81 /* Transaction Failure Inst Addr */
+#define SPRN_TEXASR 0x82 /* Transaction EXception & Summary */
+#define SPRN_TEXASRU 0x83 /* '' '' '' Upper 32 */
+#define SPRN_TFHAR 0x80 /* Transaction Failure Handler Addr */
#define SPRN_CTRLF 0x088
#define SPRN_CTRLT 0x098
#define CTRL_CT 0xc0000000 /* current thread */
--
1.7.10.4
^ permalink raw reply related
* [PATCH 06/17] powerpc: Add transactional memory paca scratch register to show_regs
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360808505-10086-1-git-send-email-mikey@neuling.org>
Add transactional memory paca scratch register to show_regs. This is useful
for debugging.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/paca.h | 3 +++
arch/powerpc/kernel/asm-offsets.c | 1 +
arch/powerpc/kernel/entry_64.S | 4 ++++
arch/powerpc/kernel/process.c | 3 +++
4 files changed, 11 insertions(+)
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index c47d687..4cbcc7d 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -137,6 +137,9 @@ struct paca_struct {
u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */
u8 nap_state_lost; /* NV GPR values lost in power7_idle */
u64 sprg3; /* Saved user-visible sprg */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ u64 tm_scratch; /* TM scratch area for reclaim */
+#endif
#ifdef CONFIG_PPC_POWERNV
/* Pointer to OPAL machine check event structure set by the
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index b67e4c3..f9654b6 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -126,6 +126,7 @@ int main(void)
DEFINE(THREAD_TAR, offsetof(struct thread_struct, tar));
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch));
DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr));
DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar));
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 9ae8451..612ea13 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -785,6 +785,10 @@ fast_exception_return:
andc r4,r4,r0 /* r0 contains MSR_RI here */
mtmsrd r4,1
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* TM debug */
+ std r3, PACATMSCRATCH(r13) /* Stash returned-to MSR */
+#endif
/*
* r13 is our per cpu area, only restore it if we are returning to
* userspace the value stored in the stack frame may belong to
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index b0a0321..1cc4053 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -754,6 +754,9 @@ void show_regs(struct pt_regs * regs)
printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip);
printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link);
#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ printk("PACATMSCRATCH [%llx]\n", get_paca()->tm_scratch);
+#endif
show_stack(current, (unsigned long *) regs->gpr[1]);
if (!user_mode(regs))
show_instructions(regs);
--
1.7.10.4
^ permalink raw reply related
* [PATCH 07/17] powerpc: Add helper functions for transactional memory context switching
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360808505-10086-1-git-send-email-mikey@neuling.org>
Here we add the helper functions to be used when context switching. These
allow us to fully reclaim and recheckpoint a transaction.
We introduce a new paca field called tm_scratch to help us store away register
values when doing the low level tm reclaim register save.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/reg.h | 2 +-
arch/powerpc/include/asm/tm.h | 20 +++
arch/powerpc/kernel/Makefile | 2 +
arch/powerpc/kernel/tm.S | 388 ++++++++++++++++++++++++++++++++++++++++
4 files changed, 411 insertions(+), 1 deletion(-)
create mode 100644 arch/powerpc/include/asm/tm.h
create mode 100644 arch/powerpc/kernel/tm.S
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 7844c28..eee2a60 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -797,7 +797,7 @@
* HV mode in which case it is HSPRG0
*
* 64-bit server:
- * - SPRG0 unused (reserved for HV on Power4)
+ * - SPRG0 scratch for TM recheckpoint/reclaim (reserved for HV on Power4)
* - SPRG2 scratch for exception vectors
* - SPRG3 CPU and NUMA node for VDSO getcpu (user visible)
* - HSPRG0 stores PACA in HV mode
diff --git a/arch/powerpc/include/asm/tm.h b/arch/powerpc/include/asm/tm.h
new file mode 100644
index 0000000..4b4449a
--- /dev/null
+++ b/arch/powerpc/include/asm/tm.h
@@ -0,0 +1,20 @@
+/*
+ * Transactional memory support routines to reclaim and recheckpoint
+ * transactional process state.
+ *
+ * Copyright 2012 Matt Evans & Michael Neuling, IBM Corporation.
+ */
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+extern void do_load_up_transact_fpu(struct thread_struct *thread);
+extern void do_load_up_transact_altivec(struct thread_struct *thread);
+#endif
+
+extern void tm_enable(void);
+extern void tm_reclaim(struct thread_struct *thread,
+ unsigned long orig_msr, uint8_t cause);
+extern void tm_recheckpoint(struct thread_struct *thread,
+ unsigned long orig_msr);
+extern void tm_abort(uint8_t cause);
+extern void tm_save_sprs(struct thread_struct *thread);
+extern void tm_restore_sprs(struct thread_struct *thread);
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index b4f0e36..f960a79 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -121,6 +121,8 @@ ifneq ($(CONFIG_PPC_INDIRECT_IO),y)
obj-y += iomap.o
endif
+obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM) += tm.o
+
obj-$(CONFIG_PPC64) += $(obj64-y)
obj-$(CONFIG_PPC32) += $(obj32-y)
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
new file mode 100644
index 0000000..84dbace
--- /dev/null
+++ b/arch/powerpc/kernel/tm.S
@@ -0,0 +1,388 @@
+/*
+ * Transactional memory support routines to reclaim and recheckpoint
+ * transactional process state.
+ *
+ * Copyright 2012 Matt Evans & Michael Neuling, IBM Corporation.
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/ppc_asm.h>
+#include <asm/ppc-opcode.h>
+#include <asm/ptrace.h>
+#include <asm/reg.h>
+
+#ifdef CONFIG_VSX
+/* See fpu.S, this is very similar but to save/restore checkpointed FPRs/VSRs */
+#define __SAVE_32FPRS_VSRS_TRANSACT(n,c,base) \
+BEGIN_FTR_SECTION \
+ b 2f; \
+END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
+ SAVE_32FPRS_TRANSACT(n,base); \
+ b 3f; \
+2: SAVE_32VSRS_TRANSACT(n,c,base); \
+3:
+/* ...and this is just plain borrowed from there. */
+#define __REST_32FPRS_VSRS(n,c,base) \
+BEGIN_FTR_SECTION \
+ b 2f; \
+END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
+ REST_32FPRS(n,base); \
+ b 3f; \
+2: REST_32VSRS(n,c,base); \
+3:
+#else
+#define __SAVE_32FPRS_VSRS_TRANSACT(n,c,base) SAVE_32FPRS_TRANSACT(n, base)
+#define __REST_32FPRS_VSRS(n,c,base) REST_32FPRS(n, base)
+#endif
+#define SAVE_32FPRS_VSRS_TRANSACT(n,c,base) \
+ __SAVE_32FPRS_VSRS_TRANSACT(n,__REG_##c,__REG_##base)
+#define REST_32FPRS_VSRS(n,c,base) \
+ __REST_32FPRS_VSRS(n,__REG_##c,__REG_##base)
+
+/* Stack frame offsets for local variables. */
+#define TM_FRAME_L0 TM_FRAME_SIZE-16
+#define TM_FRAME_L1 TM_FRAME_SIZE-8
+#define STACK_PARAM(x) (48+((x)*8))
+
+
+/* In order to access the TM SPRs, TM must be enabled. So, do so: */
+_GLOBAL(tm_enable)
+ mfmsr r4
+ li r3, MSR_TM >> 32
+ sldi r3, r3, 32
+ and. r0, r4, r3
+ bne 1f
+ or r4, r4, r3
+ mtmsrd r4
+1: blr
+
+_GLOBAL(tm_save_sprs)
+ mfspr r0, SPRN_TFHAR
+ std r0, THREAD_TM_TFHAR(r3)
+ mfspr r0, SPRN_TEXASR
+ std r0, THREAD_TM_TEXASR(r3)
+ mfspr r0, SPRN_TFIAR
+ std r0, THREAD_TM_TFIAR(r3)
+ blr
+
+_GLOBAL(tm_restore_sprs)
+ ld r0, THREAD_TM_TFHAR(r3)
+ mtspr SPRN_TFHAR, r0
+ ld r0, THREAD_TM_TEXASR(r3)
+ mtspr SPRN_TEXASR, r0
+ ld r0, THREAD_TM_TFIAR(r3)
+ mtspr SPRN_TFIAR, r0
+ blr
+
+ /* Passed an 8-bit failure cause as first argument. */
+_GLOBAL(tm_abort)
+ TABORT(R3)
+ blr
+
+
+/* void tm_reclaim(struct thread_struct *thread,
+ * unsigned long orig_msr,
+ * uint8_t cause)
+ *
+ * - Performs a full reclaim. This destroys outstanding
+ * transactions and updates thread->regs.tm_ckpt_* with the
+ * original checkpointed state. Note that thread->regs is
+ * unchanged.
+ * - FP regs are written back to thread->transact_fpr before
+ * reclaiming. These are the transactional (current) versions.
+ *
+ * Purpose is to both abort transactions of, and preserve the state of,
+ * a transactions at a context switch. We preserve/restore both sets of process
+ * state to restore them when the thread's scheduled again. We continue in
+ * userland as though nothing happened, but when the transaction is resumed
+ * they will abort back to the checkpointed state we save out here.
+ *
+ * Call with IRQs off, stacks get all out of sync for some periods in here!
+ */
+_GLOBAL(tm_reclaim)
+ mfcr r6
+ mflr r0
+ std r6, 8(r1)
+ std r0, 16(r1)
+ std r2, 40(r1)
+ stdu r1, -TM_FRAME_SIZE(r1)
+
+ /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */
+
+ std r3, STACK_PARAM(0)(r1)
+ SAVE_NVGPRS(r1)
+
+ mfmsr r14
+ mr r15, r14
+ ori r15, r15, MSR_FP
+ oris r15, r15, MSR_VEC@h
+#ifdef CONFIG_VSX
+ BEGIN_FTR_SECTION
+ oris r15,r15, MSR_VSX@h
+ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+ mtmsrd r15
+ std r14, TM_FRAME_L0(r1)
+
+ /* Stash the stack pointer away for use after reclaim */
+ std r1, PACAR1(r13)
+
+ /* ******************** FPR/VR/VSRs ************
+ * Before reclaiming, capture the current/transactional FPR/VR
+ * versions /if used/.
+ *
+ * (If VSX used, FP and VMX are implied. Or, we don't need to look
+ * at MSR.VSX as copying FP regs if .FP, vector regs if .VMX covers it.)
+ *
+ * We're passed the thread's MSR as parameter 2.
+ *
+ * We enabled VEC/FP/VSX in the msr above, so we can execute these
+ * instructions!
+ */
+ andis. r0, r4, MSR_VEC@h
+ beq dont_backup_vec
+
+ SAVE_32VRS_TRANSACT(0, r6, r3) /* r6 scratch, r3 thread */
+ mfvscr vr0
+ li r6, THREAD_TRANSACT_VSCR
+ stvx vr0, r3, r6
+ mfspr r0, SPRN_VRSAVE
+ std r0, THREAD_TRANSACT_VRSAVE(r3)
+
+dont_backup_vec:
+ andi. r0, r4, MSR_FP
+ beq dont_backup_fp
+
+ SAVE_32FPRS_VSRS_TRANSACT(0, R6, R3) /* r6 scratch, r3 thread */
+
+ mffs fr0
+ stfd fr0,THREAD_TRANSACT_FPSCR(r3)
+
+dont_backup_fp:
+ /* The moment we treclaim, ALL of our GPRs will switch
+ * to user register state. (FPRs, CCR etc. also!)
+ * Use an sprg and a tm_scratch in the PACA to shuffle.
+ */
+ TRECLAIM(R5) /* Cause in r5 */
+
+ /* ******************** GPRs ******************** */
+ /* Stash the checkpointed r13 away in the scratch SPR and get the real
+ * paca
+ */
+ SET_SCRATCH0(r13)
+ GET_PACA(r13)
+
+ /* Stash the checkpointed r1 away in paca tm_scratch and get the real
+ * stack pointer back
+ */
+ std r1, PACATMSCRATCH(r13)
+ ld r1, PACAR1(r13)
+
+ /* Now get some more GPRS free */
+ std r7, GPR7(r1) /* Temporary stash */
+ std r12, GPR12(r1) /* '' '' '' */
+ ld r12, STACK_PARAM(0)(r1) /* Param 0, thread_struct * */
+
+ addi r7, r12, PT_CKPT_REGS /* Thread's ckpt_regs */
+
+ /* Make r7 look like an exception frame so that we
+ * can use the neat GPRx(n) macros. r7 is NOT a pt_regs ptr!
+ */
+ subi r7, r7, STACK_FRAME_OVERHEAD
+
+ /* Sync the userland GPRs 2-12, 14-31 to thread->regs: */
+ SAVE_GPR(0, r7) /* user r0 */
+ SAVE_GPR(2, r7) /* user r2 */
+ SAVE_4GPRS(3, r7) /* user r3-r6 */
+ SAVE_4GPRS(8, r7) /* user r8-r11 */
+ ld r3, PACATMSCRATCH(r13) /* user r1 */
+ ld r4, GPR7(r1) /* user r7 */
+ ld r5, GPR12(r1) /* user r12 */
+ GET_SCRATCH0(6) /* user r13 */
+ std r3, GPR1(r7)
+ std r4, GPR7(r7)
+ std r5, GPR12(r7)
+ std r6, GPR13(r7)
+
+ SAVE_NVGPRS(r7) /* user r14-r31 */
+
+ /* ******************** NIP ******************** */
+ mfspr r3, SPRN_TFHAR
+ std r3, _NIP(r7) /* Returns to failhandler */
+ /* The checkpointed NIP is ignored when rescheduling/rechkpting,
+ * but is used in signal return to 'wind back' to the abort handler.
+ */
+
+ /* ******************** CR,LR,CCR,MSR ********** */
+ mfctr r3
+ mflr r4
+ mfcr r5
+ mfxer r6
+
+ std r3, _CTR(r7)
+ std r4, _LINK(r7)
+ std r5, _CCR(r7)
+ std r6, _XER(r7)
+
+ /* MSR and flags: We don't change CRs, and we don't need to alter
+ * MSR.
+ */
+
+ /* TM regs, incl TEXASR -- these live in thread_struct. Note they've
+ * been updated by the treclaim, to explain to userland the failure
+ * cause (aborted).
+ */
+ mfspr r0, SPRN_TEXASR
+ mfspr r3, SPRN_TFHAR
+ mfspr r4, SPRN_TFIAR
+ std r0, THREAD_TM_TEXASR(r12)
+ std r3, THREAD_TM_TFHAR(r12)
+ std r4, THREAD_TM_TFIAR(r12)
+
+ /* AMR and PPR are checkpointed too, but are unsupported by Linux. */
+
+ /* Restore original MSR/IRQ state & clear TM mode */
+ ld r14, TM_FRAME_L0(r1) /* Orig MSR */
+ li r15, 0
+ rldimi r14, r15, MSR_TS_LG, (63-MSR_TS_LG)-1
+ mtmsrd r14
+
+ REST_NVGPRS(r1)
+
+ addi r1, r1, TM_FRAME_SIZE
+ ld r4, 8(r1)
+ ld r0, 16(r1)
+ mtcr r4
+ mtlr r0
+ ld r2, 40(r1)
+ blr
+
+
+ /* void tm_recheckpoint(struct thread_struct *thread,
+ * unsigned long orig_msr)
+ * - Restore the checkpointed register state saved by tm_reclaim
+ * when we switch_to a process.
+ *
+ * Call with IRQs off, stacks get all out of sync for
+ * some periods in here!
+ */
+_GLOBAL(tm_recheckpoint)
+ mfcr r5
+ mflr r0
+ std r5, 8(r1)
+ std r0, 16(r1)
+ std r2, 40(r1)
+ stdu r1, -TM_FRAME_SIZE(r1)
+
+ /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD].
+ * This is used for backing up the NVGPRs:
+ */
+ SAVE_NVGPRS(r1)
+
+ std r1, PACAR1(r13)
+
+ /* Load complete register state from ts_ckpt* registers */
+
+ addi r7, r3, PT_CKPT_REGS /* Thread's ckpt_regs */
+
+ /* Make r7 look like an exception frame so that we
+ * can use the neat GPRx(n) macros. r7 is now NOT a pt_regs ptr!
+ */
+ subi r7, r7, STACK_FRAME_OVERHEAD
+
+ SET_SCRATCH0(r1)
+
+ mfmsr r6
+ /* R4 = original MSR to indicate whether thread used FP/Vector etc. */
+
+ /* Enable FP/vec in MSR if necessary! */
+ lis r5, MSR_VEC@h
+ ori r5, r5, MSR_FP
+ and. r5, r4, r5
+ beq restore_gprs /* if neither, skip both */
+
+#ifdef CONFIG_VSX
+ BEGIN_FTR_SECTION
+ oris r5, r5, MSR_VSX@h
+ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+ or r5, r6, r5 /* Set MSR.FP+.VSX/.VEC */
+ mtmsr r5
+
+ /* FP and VEC registers: These are recheckpointed from thread.fpr[]
+ * and thread.vr[] respectively. The thread.transact_fpr[] version
+ * is more modern, and will be loaded subsequently by any FPUnavailable
+ * trap.
+ */
+ andis. r0, r4, MSR_VEC@h
+ beq dont_restore_vec
+
+ li r5, THREAD_VSCR
+ lvx vr0, r3, r5
+ mtvscr vr0
+ REST_32VRS(0, r5, r3) /* r5 scratch, r3 THREAD ptr */
+ ld r5, THREAD_VRSAVE(r3)
+ mtspr SPRN_VRSAVE, r5
+
+dont_restore_vec:
+ andi. r0, r4, MSR_FP
+ beq dont_restore_fp
+
+ lfd fr0, THREAD_FPSCR(r3)
+ MTFSF_L(fr0)
+ REST_32FPRS_VSRS(0, R4, R3)
+
+dont_restore_fp:
+ mtmsr r6 /* FP/Vec off again! */
+
+restore_gprs:
+ /* ******************** CR,LR,CCR,MSR ********** */
+ ld r3, _CTR(r7)
+ ld r4, _LINK(r7)
+ ld r5, _CCR(r7)
+ ld r6, _XER(r7)
+
+ mtctr r3
+ mtlr r4
+ mtcr r5
+ mtxer r6
+
+ /* MSR and flags: We don't change CRs, and we don't need to alter
+ * MSR.
+ */
+
+ REST_4GPRS(0, r7) /* GPR0-3 */
+ REST_GPR(4, r7) /* GPR4-6 */
+ REST_GPR(5, r7)
+ REST_GPR(6, r7)
+ REST_4GPRS(8, r7) /* GPR8-11 */
+ REST_2GPRS(12, r7) /* GPR12-13 */
+
+ REST_NVGPRS(r7) /* GPR14-31 */
+
+ ld r7, GPR7(r7) /* GPR7 */
+
+ /* Commit register state as checkpointed state: */
+ TRECHKPT
+
+ /* Our transactional state has now changed.
+ *
+ * Now just get out of here. Transactional (current) state will be
+ * updated once restore is called on the return path in the _switch-ed
+ * -to process.
+ */
+
+ GET_PACA(r13)
+ GET_SCRATCH0(r1)
+
+ REST_NVGPRS(r1)
+
+ addi r1, r1, TM_FRAME_SIZE
+ ld r4, 8(r1)
+ ld r0, 16(r1)
+ mtcr r4
+ mtlr r0
+ ld r2, 40(r1)
+ blr
+
+ /* ****************************************************************** */
--
1.7.10.4
^ permalink raw reply related
* [PATCH 08/17] powerpc: Add FP/VSX and VMX register load functions for transactional memory
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360808505-10086-1-git-send-email-mikey@neuling.org>
This adds functions to restore the state of the FP/VSX registers from
what's stored in the thread_struct. Two version for FP/VSX are required
since one restores them from transactional/checkpoint side of the
thread_struct and the other from the speculated side.
Similar functions are added for VMX registers.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/kernel/fpu.S | 54 ++++++++++++++++++++++++++++++++++++++++++
arch/powerpc/kernel/vector.S | 51 +++++++++++++++++++++++++++++++++++++++
2 files changed, 105 insertions(+)
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index adb1551..caeaabf 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -62,6 +62,60 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
__REST_32FPVSRS_TRANSACT(n,__REG_##c,__REG_##base)
#define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Wrapper to call load_up_fpu from C.
+ * void do_load_up_fpu(struct pt_regs *regs);
+ */
+_GLOBAL(do_load_up_fpu)
+ mflr r0
+ std r0, 16(r1)
+ stdu r1, -112(r1)
+
+ subi r6, r3, STACK_FRAME_OVERHEAD
+ /* load_up_fpu expects r12=MSR, r13=PACA, and returns
+ * with r12 = new MSR.
+ */
+ ld r12,_MSR(r6)
+ GET_PACA(r13)
+
+ bl load_up_fpu
+ std r12,_MSR(r6)
+
+ ld r0, 112+16(r1)
+ addi r1, r1, 112
+ mtlr r0
+ blr
+
+
+/* void do_load_up_transact_fpu(struct thread_struct *thread)
+ *
+ * This is similar to load_up_fpu but for the transactional version of the FP
+ * register set. It doesn't mess with the task MSR or valid flags.
+ * Furthermore, we don't do lazy FP with TM currently.
+ */
+_GLOBAL(do_load_up_transact_fpu)
+ mfmsr r6
+ ori r5,r6,MSR_FP
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+ oris r5,r5,MSR_VSX@h
+END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+ SYNC
+ MTMSRD(r5)
+
+ lfd fr0,THREAD_TRANSACT_FPSCR(r3)
+ MTFSF_L(fr0)
+ REST_32FPVSRS_TRANSACT(0, R4, R3)
+
+ /* FP/VSX off again */
+ MTMSRD(r6)
+ SYNC
+
+ blr
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
/*
* This task wants to use the FPU now.
* On UP, disable FP for the task which had the FPU previously,
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index e830289..9e20999 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -7,6 +7,57 @@
#include <asm/page.h>
#include <asm/ptrace.h>
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Wrapper to call load_up_altivec from C.
+ * void do_load_up_altivec(struct pt_regs *regs);
+ */
+_GLOBAL(do_load_up_altivec)
+ mflr r0
+ std r0, 16(r1)
+ stdu r1, -112(r1)
+
+ subi r6, r3, STACK_FRAME_OVERHEAD
+ /* load_up_altivec expects r12=MSR, r13=PACA, and returns
+ * with r12 = new MSR.
+ */
+ ld r12,_MSR(r6)
+ GET_PACA(r13)
+ bl load_up_altivec
+ std r12,_MSR(r6)
+
+ ld r0, 112+16(r1)
+ addi r1, r1, 112
+ mtlr r0
+ blr
+
+/* void do_load_up_transact_altivec(struct thread_struct *thread)
+ *
+ * This is similar to load_up_altivec but for the transactional version of the
+ * vector regs. It doesn't mess with the task MSR or valid flags.
+ * Furthermore, VEC laziness is not supported with TM currently.
+ */
+_GLOBAL(do_load_up_transact_altivec)
+ mfmsr r6
+ oris r5,r6,MSR_VEC@h
+ MTMSRD(r5)
+ isync
+
+ li r4,1
+ stw r4,THREAD_USED_VR(r3)
+
+ li r10,THREAD_TRANSACT_VSCR
+ lvx vr0,r10,r3
+ mtvscr vr0
+ REST_32VRS_TRANSACT(0,r4,r3)
+
+ /* Disable VEC again. */
+ MTMSRD(r6)
+ isync
+
+ blr
+#endif
+
/*
* load_up_altivec(unused, unused, tsk)
* Disable VMX for the task which had it previously,
--
1.7.10.4
^ permalink raw reply related
* [PATCH 09/17] powerpc: Add reclaim and recheckpoint functions for context switching transactional memory processes
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360808505-10086-1-git-send-email-mikey@neuling.org>
When we switch out a task, we need to save both the checkpointed and the
speculated state into the thread struct.
Similarly when we are switching in a task we need to load both the checkpointed
and speculated state. If the task was using FP, we non-lazily reload both the
original and the speculative FP register states. This is because the kernel
doesn't see if/when a TM rollback occurs, so if we take an FP unavoidable
later, we are unable to determine which set of FP regs need to be restored.
This simply adds these functions. It doesn't hook them into the existing code
yet.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/kernel/process.c | 112 +++++++++++++++++++++++++++++++++++++++++
1 file changed, 112 insertions(+)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 1cc4053..48a9875 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -50,6 +50,7 @@
#include <asm/runlatch.h>
#include <asm/syscalls.h>
#include <asm/switch_to.h>
+#include <asm/tm.h>
#include <asm/debug.h>
#ifdef CONFIG_PPC64
#include <asm/firmware.h>
@@ -467,6 +468,117 @@ static inline bool hw_brk_match(struct arch_hw_breakpoint *a,
return false;
return true;
}
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static inline void tm_reclaim_task(struct task_struct *tsk)
+{
+ /* We have to work out if we're switching from/to a task that's in the
+ * middle of a transaction.
+ *
+ * In switching we need to maintain a 2nd register state as
+ * oldtask->thread.ckpt_regs. We tm_reclaim(oldproc); this saves the
+ * checkpointed (tbegin) state in ckpt_regs and saves the transactional
+ * (current) FPRs into oldtask->thread.transact_fpr[].
+ *
+ * We also context switch (save) TFHAR/TEXASR/TFIAR in here.
+ */
+ struct thread_struct *thr = &tsk->thread;
+
+ if (!thr->regs)
+ return;
+
+ if (!MSR_TM_ACTIVE(thr->regs->msr))
+ goto out_and_saveregs;
+
+ /* Stash the original thread MSR, as giveup_fpu et al will
+ * modify it. We hold onto it to see whether the task used
+ * FP & vector regs.
+ */
+ thr->tm_orig_msr = thr->regs->msr;
+
+ TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, "
+ "ccr=%lx, msr=%lx, trap=%lx)\n",
+ tsk->pid, thr->regs->nip,
+ thr->regs->ccr, thr->regs->msr,
+ thr->regs->trap);
+
+ tm_reclaim(thr, thr->regs->msr, TM_CAUSE_RESCHED);
+
+ TM_DEBUG("--- tm_reclaim on pid %d complete\n",
+ tsk->pid);
+
+out_and_saveregs:
+ /* Always save the regs here, even if a transaction's not active.
+ * This context-switches a thread's TM info SPRs. We do it here to
+ * be consistent with the restore path (in recheckpoint) which
+ * cannot happen later in _switch().
+ */
+ tm_save_sprs(thr);
+}
+
+static inline void __maybe_unused tm_recheckpoint_new_task(struct task_struct *new)
+{
+ unsigned long msr;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return;
+
+ /* Recheckpoint the registers of the thread we're about to switch to.
+ *
+ * If the task was using FP, we non-lazily reload both the original and
+ * the speculative FP register states. This is because the kernel
+ * doesn't see if/when a TM rollback occurs, so if we take an FP
+ * unavoidable later, we are unable to determine which set of FP regs
+ * need to be restored.
+ */
+ if (!new->thread.regs)
+ return;
+
+ /* The TM SPRs are restored here, so that TEXASR.FS can be set
+ * before the trecheckpoint and no explosion occurs.
+ */
+ tm_restore_sprs(&new->thread);
+
+ if (!MSR_TM_ACTIVE(new->thread.regs->msr))
+ return;
+ msr = new->thread.tm_orig_msr;
+ /* Recheckpoint to restore original checkpointed register state. */
+ TM_DEBUG("*** tm_recheckpoint of pid %d "
+ "(new->msr 0x%lx, new->origmsr 0x%lx)\n",
+ new->pid, new->thread.regs->msr, msr);
+
+ /* This loads the checkpointed FP/VEC state, if used */
+ tm_recheckpoint(&new->thread, msr);
+
+ /* This loads the speculative FP/VEC state, if used */
+ if (msr & MSR_FP) {
+ do_load_up_transact_fpu(&new->thread);
+ new->thread.regs->msr |=
+ (MSR_FP | new->thread.fpexc_mode);
+ }
+ if (msr & MSR_VEC) {
+ do_load_up_transact_altivec(&new->thread);
+ new->thread.regs->msr |= MSR_VEC;
+ }
+ /* We may as well turn on VSX too since all the state is restored now */
+ if (msr & MSR_VSX)
+ new->thread.regs->msr |= MSR_VSX;
+
+ TM_DEBUG("*** tm_recheckpoint of pid %d complete "
+ "(kernel msr 0x%lx)\n",
+ new->pid, mfmsr());
+}
+
+static inline void __switch_to_tm(struct task_struct *prev)
+{
+ if (cpu_has_feature(CPU_FTR_TM)) {
+ tm_enable();
+ tm_reclaim_task(prev);
+ }
+}
+#else
+#define tm_recheckpoint_new_task(new)
+#define __switch_to_tm(prev)
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
struct task_struct *__switch_to(struct task_struct *prev,
struct task_struct *new)
--
1.7.10.4
^ permalink raw reply related
* [PATCH 10/17] powerpc: Add transactional memory unavaliable execption handler
From: Michael Neuling @ 2013-02-14 2:21 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Michael Neuling, linuxppc-dev, Matt Evans
In-Reply-To: <1360808505-10086-1-git-send-email-mikey@neuling.org>
These should never happen since we always turn on MSR TM when in userspace. We
don't do lazy TM.
Hence if we hit this, we barf and kill the task as something's gone horribly
wrong.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/kernel/exceptions-64s.S | 19 +++++++++++++++++++
arch/powerpc/kernel/traps.c | 21 +++++++++++++++++++++
2 files changed, 40 insertions(+)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 7a1c87c..d0cc657 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -313,6 +313,9 @@ vsx_unavailable_pSeries_1:
. = 0xf40
b vsx_unavailable_pSeries
+ . = 0xf60
+ b tm_unavailable_pSeries
+
#ifdef CONFIG_CBE_RAS
STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
@@ -528,6 +531,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20)
STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
+ STD_EXCEPTION_PSERIES(., 0xf60, tm_unavailable)
+ KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf60)
/*
* An interrupt came in while soft-disabled. We set paca->irq_happened, then:
@@ -817,6 +822,10 @@ vsx_unavailable_relon_pSeries_1:
. = 0x4f40
b vsx_unavailable_relon_pSeries
+tm_unavailable_relon_pSeries_1:
+ . = 0x4f60
+ b tm_unavailable_relon_pSeries
+
#ifdef CONFIG_CBE_RAS
STD_RELON_EXCEPTION_HV(0x5200, 0x1202, cbe_system_error)
#endif /* CONFIG_CBE_RAS */
@@ -1177,6 +1186,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
b .ret_from_except
.align 7
+ .globl tm_unavailable_common
+tm_unavailable_common:
+ EXCEPTION_PROLOG_COMMON(0xf60, PACA_EXGEN)
+ bl .save_nvgprs
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl .tm_unavailable_exception
+ b .ret_from_except
+
+ .align 7
.globl __end_handlers
__end_handlers:
@@ -1195,6 +1213,7 @@ __end_handlers:
STD_RELON_EXCEPTION_PSERIES(., 0xf00, performance_monitor)
STD_RELON_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable)
STD_RELON_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable)
+ STD_RELON_EXCEPTION_PSERIES(., 0xf60, tm_unavailable)
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
/*
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index bd5de5d..f829e05 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1168,6 +1168,27 @@ void vsx_unavailable_exception(struct pt_regs *regs)
die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
}
+void tm_unavailable_exception(struct pt_regs *regs)
+{
+ /* We restore the interrupt state now */
+ if (!arch_irq_disabled_regs(regs))
+ local_irq_enable();
+
+ /* Currently we never expect a TMU exception. Catch
+ * this and kill the process!
+ */
+ printk(KERN_EMERG "Unexpected TM unavailable exception at %lx "
+ "(msr %lx)\n",
+ regs->nip, regs->msr);
+
+ if (user_mode(regs)) {
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ return;
+ }
+
+ die("Unexpected TM unavailable exception", regs, SIGABRT);
+}
+
void performance_monitor_exception(struct pt_regs *regs)
{
__get_cpu_var(irq_stat).pmu_irqs++;
--
1.7.10.4
^ 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