Re: [PATCH v4 8/9] Implement kernel live patching for ppc64le (ABIv2)

[Torsten Duwe]

On Thu, Dec 03, 2015 at 05:24:45PM +0100, Petr Mladek wrote:
> > +++ b/arch/powerpc/include/asm/livepatch.h
> > @@ -0,0 +1,45 @@
> [...]
> > +#include 
> > +#include 
> > +
> > +#ifdef CONFIG_LIVEPATCH
> > +static inline int klp_check_compiler_support(void)
> > +{
> > +#if !defined(_CALL_ELF) || _CALL_ELF != 2
> 
> I am just curious why we do not check CC_USING_MPROFILE_KERNEL
> like in the other similar locations. It would look less cryptic.
> But I am not sure if it is precise enough.

Because a ppc with a gcc > 4.8.5 is not sufficient. The code
currently only works for the PPC ELF ABI v2, a.k.a. ppc64le.
But now that you say it, CC_USING_MPROFILE_KERNEL should go
into that condition as well. Thanks!

Torsten

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [PATCH v3 1/6] powerpc/mm: any thread in one core can be the first to setup TLB1

[Denis Kirjanov]

On 12/3/15, Scott Wood  wrote:
> On Wed, 2015-12-02 at 15:12 +0300, Denis Kirjanov wrote:
>> On 11/20/15, Chenhui Zhao  wrote:
>> > On e6500, in the case of cpu hotplug, either thread in one core
>> > may be the first thread initilzing the TLB1. The subsequent threads
>> > must not setup it again.
>> >
>> > The code is derived from the comment of Scott Wood.
>> >
>> > Signed-off-by: Chenhui Zhao 
>> > ---
>> >  arch/powerpc/include/asm/cputhreads.h | 7 +++
>> >  arch/powerpc/mm/tlb_nohash.c  | 4 +---
>> >  2 files changed, 8 insertions(+), 3 deletions(-)
>> >
>> > diff --git a/arch/powerpc/include/asm/cputhreads.h
>> > b/arch/powerpc/include/asm/cputhreads.h
>> > index ba42e46..b56cece 100644
>> > --- a/arch/powerpc/include/asm/cputhreads.h
>> > +++ b/arch/powerpc/include/asm/cputhreads.h
>> > @@ -94,6 +94,13 @@ static inline int cpu_last_thread_sibling(int cpu)
>> >return cpu | (threads_per_core - 1);
>> >  }
>> >
>> > +static inline u32 get_tensr(void)
>> > +{
>> > +  if (cpu_has_feature(CPU_FTR_SMT))
>> > +  return mfspr(SPRN_TENSR);
>> > +  else
>> > +  return 1;
>> > +}
>> If i get it right, SPRN_TENSR used in the code only if CONFIG_PPC64
>> is defined. Then we can make it noop on ppc32.
>
> Please don't.  It accomplishes nothing other than adding an obstacle to
> supporting this on ppc32.

The idea is make it noop since the function defined in header file and
some core parts include it like:

arch/powerpc/kernel/smp.c
arch/powerpc/kernel/setup-common.c


>
> -Scott
>
>
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[net-next v5 8/8] dpaa_eth: add trace points

[linuxppc-dev-bounces+archive=mail-archive . com]

From: Madalin Bucur 

Add trace points on the hot processing path.

Signed-off-by: Ruxandra Ioana Radulescu 
---
 drivers/net/ethernet/freescale/dpaa/Makefile   |   1 +
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c |  12 ++
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.h |   4 +
 .../net/ethernet/freescale/dpaa/dpaa_eth_trace.h   | 141 +
 4 files changed, 158 insertions(+)
 create mode 100644 drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h

diff --git a/drivers/net/ethernet/freescale/dpaa/Makefile 
b/drivers/net/ethernet/freescale/dpaa/Makefile
index 141ade4..15ed1c4 100644
--- a/drivers/net/ethernet/freescale/dpaa/Makefile
+++ b/drivers/net/ethernet/freescale/dpaa/Makefile
@@ -9,3 +9,4 @@ ccflags-y += -I$(FMAN)
 obj-$(CONFIG_FSL_DPAA_ETH) += fsl_dpa.o
 
 fsl_dpa-objs += dpaa_eth.o dpaa_eth_sg.o dpaa_eth_common.o dpaa_ethtool.o 
dpaa_eth_sysfs.o
+CFLAGS_dpaa_eth.o := -I$(src)
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 7d4d21a..76df948 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -57,6 +57,12 @@
 #include "dpaa_eth.h"
 #include "dpaa_eth_common.h"
 
+/* CREATE_TRACE_POINTS only needs to be defined once. Other dpa files
+ * using trace events only need to #include 
+ */
+#define CREATE_TRACE_POINTS
+#include "dpaa_eth_trace.h"
+
 /* Valid checksum indication */
 #define DPA_CSUM_VALID 0x
 
@@ -219,6 +225,9 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct 
qman_portal *portal,
priv = netdev_priv(net_dev);
dpa_bp = priv->dpa_bp;
 
+   /* Trace the Rx fd */
+   trace_dpa_rx_fd(net_dev, fq, >fd);
+
percpu_priv = this_cpu_ptr(priv->percpu_priv);
count_ptr = this_cpu_ptr(dpa_bp->percpu_count);
 
@@ -272,6 +281,9 @@ static enum qman_cb_dqrr_result conf_dflt_dqrr(struct 
qman_portal *portal,
net_dev = ((struct dpa_fq *)fq)->net_dev;
priv = netdev_priv(net_dev);
 
+   /* Trace the fd */
+   trace_dpa_tx_conf_fd(net_dev, fq, >fd);
+
percpu_priv = this_cpu_ptr(priv->percpu_priv);
 
if (dpaa_eth_napi_schedule(percpu_priv, portal))
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
index 9651e24..81a2abc 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -36,6 +36,7 @@
 
 #include "fman.h"
 #include "mac.h"
+#include "dpaa_eth_trace.h"
 
 extern int dpa_rx_extra_headroom;
 extern int dpa_max_frm;
@@ -392,6 +393,9 @@ static inline int dpa_xmit(struct dpa_priv *priv,
if (fd->bpid == FSL_DPAA_BPID_INV)
fd->cmd |= qman_fq_fqid(priv->conf_fqs[queue]);
 
+   /* Trace this Tx fd */
+   trace_dpa_tx_fd(priv->net_dev, egress_fq, fd);
+
for (i = 0; i < 10; i++) {
err = qman_enqueue(egress_fq, fd, 0);
if (err != -EBUSY)
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h
new file mode 100644
index 000..3b67477
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h
@@ -0,0 +1,141 @@
+/* Copyright 2013-2015 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ *  notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ *  notice, this list of conditions and the following disclaimer in the
+ *  documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ *  names of its contributors may be used to endorse or promote products
+ *  derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, 

Re: [PATCH 2/3] selftests/powerpc: Add test for forking inside transaction

[Michael Neuling]

On Tue, 2015-12-01 at 16:08 +1100, Rashmica Gupta wrote:
> This test does a fork syscall inside a transaction. Basic sniff test
> to see
> if we can enter the kernel during a transaction.

Can you add this description to the top of the test case as well?

Mikey

> 
> Signed-off-by: Rashmica Gupta 
> ---
>  tools/testing/selftests/powerpc/tm/.gitignore |  1 +
>  tools/testing/selftests/powerpc/tm/Makefile   |  2 +-
>  tools/testing/selftests/powerpc/tm/tm-fork.c  | 41
> +++
>  3 files changed, 43 insertions(+), 1 deletion(-)
>  create mode 100644 tools/testing/selftests/powerpc/tm/tm-fork.c
> 
> diff --git a/tools/testing/selftests/powerpc/tm/.gitignore
> b/tools/testing/selftests/powerpc/tm/.gitignore
> index e6668217ccd0..d0c7c97e9b13 100644
> --- a/tools/testing/selftests/powerpc/tm/.gitignore
> +++ b/tools/testing/selftests/powerpc/tm/.gitignore
> @@ -2,3 +2,4 @@ tm-resched-dscr
>  tm-syscall
>  tm-signal-msr-resv
>  tm-signal-stack
> +tm-fork
> diff --git a/tools/testing/selftests/powerpc/tm/Makefile
> b/tools/testing/selftests/powerpc/tm/Makefile
> index 578572a3700a..f7d4727662aa 100644
> --- a/tools/testing/selftests/powerpc/tm/Makefile
> +++ b/tools/testing/selftests/powerpc/tm/Makefile
> @@ -1,4 +1,4 @@
> -TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm
> -signal-stack
> +TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm
> -signal-stack tm-fork
>  
>  all: $(TEST_PROGS)
>  
> diff --git a/tools/testing/selftests/powerpc/tm/tm-fork.c
> b/tools/testing/selftests/powerpc/tm/tm-fork.c
> new file mode 100644
> index ..f571a48a59a0
> --- /dev/null
> +++ b/tools/testing/selftests/powerpc/tm/tm-fork.c
> @@ -0,0 +1,41 @@
> +/*
> + * Copyright 2015, Michael Neuling, IBM Corp.
> + * Licensed under GPLv2.
> + *
> + * Edited: Rashmica Gupta, Nov 2015
> + *
> + * Fork inside a transaction
> + */
> +
> +#include 
> +#include 
> +#include 
> +#include 
> +#include 
> +#include 
> +
> +#include "utils.h"
> +#include "tm.h"
> +
> +int test_fork(void)
> +{
> + SKIP_IF(!have_htm());
> +
> + asm __volatile__(
> + "tbegin.;"
> + "blt1f; "
> + "li 0, 2;"  /* fork syscall */
> + "sc  ;"
> + "tend.;"
> + "1: ;"
> + : : : "memory", "r0");
> + /* If we reach here, we've passed.  Otherwise we've probably
> crashed
> +  * the kernel */
> +
> + return 0;
> +}
> +
> +int main(int argc, char *argv[])
> +{
> + return test_harness(test_fork, "tm_fork");
> +}
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[net-next v5 7/8] dpaa_eth: add sysfs exports

[linuxppc-dev-bounces+archive=mail-archive . com]

From: Madalin Bucur 

Export Frame Queue and Buffer Pool IDs through sysfs.

Signed-off-by: Madalin Bucur 
---
 drivers/net/ethernet/freescale/dpaa/Makefile   |   2 +-
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c |   2 +
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.h |   3 +
 .../net/ethernet/freescale/dpaa/dpaa_eth_common.c  |   2 +
 .../net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c   | 167 +
 5 files changed, 175 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c

diff --git a/drivers/net/ethernet/freescale/dpaa/Makefile 
b/drivers/net/ethernet/freescale/dpaa/Makefile
index 9b75d52..141ade4 100644
--- a/drivers/net/ethernet/freescale/dpaa/Makefile
+++ b/drivers/net/ethernet/freescale/dpaa/Makefile
@@ -8,4 +8,4 @@ ccflags-y += -I$(FMAN)
 
 obj-$(CONFIG_FSL_DPAA_ETH) += fsl_dpa.o
 
-fsl_dpa-objs += dpaa_eth.o dpaa_eth_sg.o dpaa_eth_common.o dpaa_ethtool.o
+fsl_dpa-objs += dpaa_eth.o dpaa_eth_sg.o dpaa_eth_common.o dpaa_ethtool.o 
dpaa_eth_sysfs.o
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index f71a0d2..7d4d21a 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -691,6 +691,8 @@ static int dpaa_eth_probe(struct platform_device *pdev)
if (err < 0)
goto netdev_init_failed;
 
+   dpaa_eth_sysfs_init(_dev->dev);
+
netif_info(priv, probe, net_dev, "Probed interface %s\n",
   net_dev->name);
 
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
index 076d66a..9651e24 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -356,6 +356,9 @@ static inline u16 dpa_get_headroom(struct dpa_buffer_layout 
*bl)
return bl->data_align ? ALIGN(headroom, bl->data_align) : headroom;
 }
 
+void dpaa_eth_sysfs_remove(struct device *dev);
+void dpaa_eth_sysfs_init(struct device *dev);
+
 void dpa_napi_del(struct net_device *net_dev);
 
 static inline void clear_fd(struct qm_fd *fd)
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
index 2a7cff2..3003832 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
@@ -330,6 +330,8 @@ int dpa_remove(struct platform_device *pdev)
 
priv = netdev_priv(net_dev);
 
+   dpaa_eth_sysfs_remove(dev);
+
dev_set_drvdata(dev, NULL);
unregister_netdev(net_dev);
 
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c
new file mode 100644
index 000..56588e0
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c
@@ -0,0 +1,167 @@
+/* Copyright 2008-2015 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ *  notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ *  notice, this list of conditions and the following disclaimer in the
+ *  documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ *  names of its contributors may be used to endorse or promote products
+ *  derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF 
THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include 
+#include 
+#include 
+#include 
+#include 
+#include "dpaa_eth.h"
+#include "mac.h"
+
+static ssize_t dpaa_eth_show_addr(struct device *dev,
+

[PATCH 0/5] ftrace: fix ftrace misleading comments for arch using it

[Li Bin]

Fix the following similar misleading comments of ftrace for arch
ia64/metag/powerpc/sh/x86:

Note: Due to modules and __init, code can
 disappear and change, we need to protect against faulting
 as well as code changing. We do this by using the
 probe_kernel_* functions.

No real locking needed, this code is run through
kstop_machine, or before SMP starts.

Cc: Tony Luck 
Cc: Fenghua Yu 
Cc: linux-i...@vger.kernel.org
Cc: James Hogan 
Cc: linux-me...@vger.kernel.org
Cc: Benjamin Herrenschmidt 
Cc: Paul Mackerras 
Cc: Michael Ellerman  
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux...@vger.kernel.org
Cc: Thomas Gleixner 
"Cc: H. Peter Anvin" 
Cc: x...@kernel.org

Li Bin (5):
  ia64: ftrace: fix the comments for ftrace_modify_code
  metag: ftrace: fix the comments for ftrace_modify_code
  powerpc: ftrace: fix the comments for ftrace_modify_code
  sh: ftrace: fix the comments for ftrace_modify_code
  x86: ftrace: fix the comments for ftrace_modify_code_direct

 arch/ia64/kernel/ftrace.c|   13 ++---
 arch/metag/kernel/ftrace.c   |   12 ++--
 arch/powerpc/kernel/ftrace.c |   13 ++---
 arch/sh/kernel/ftrace.c  |   13 ++---
 arch/x86/kernel/ftrace.c |   13 ++---
 5 files changed, 30 insertions(+), 34 deletions(-)

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[PATCH 3/5] powerpc: ftrace: fix the comments for ftrace_modify_code

[Li Bin]

There is no need to worry about module and __init text disappearing
case, because that ftrace has a module notifier that is called when
a module is being unloaded and before the text goes away and this
code grabs the ftrace_lock mutex and removes the module functions
from the ftrace list, such that it will no longer do any
modifications to that module's text, the update to make functions
be traced or not is done under the ftrace_lock mutex as well.
And by now, __init section codes should not been modified
by ftrace, because it is black listed in recordmcount.c and
ignored by ftrace.

Cc: Benjamin Herrenschmidt 
Cc: Paul Mackerras 
Cc: Michael Ellerman 
Cc: linuxppc-dev@lists.ozlabs.org
Suggested-by: Steven Rostedt 
Signed-off-by: Li Bin 
---
 arch/powerpc/kernel/ftrace.c |   13 ++---
 1 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 44d4d8e..c6452b2 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -47,13 +47,12 @@ ftrace_modify_code(unsigned long ip, unsigned int old, 
unsigned int new)
unsigned int replaced;
 
/*
-* Note: Due to modules and __init, code can
-*  disappear and change, we need to protect against faulting
-*  as well as code changing. We do this by using the
-*  probe_kernel_* functions.
-*
-* No real locking needed, this code is run through
-* kstop_machine, or before SMP starts.
+* Note:
+* We are paranoid about modifying text, as if a bug were to happen, it
+* could cause us to read or write to someplace that could cause harm.
+* Carefully read and modify the code with aarch64_insn_*() which uses
+* probe_kernel_*(), and make sure what we read is what we expected it
+* to be before modifying it.
 */
 
/* read the text we want to modify */
-- 
1.7.1

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[net-next v5 4/8] dpaa_eth: add driver's Tx queue selection

[linuxppc-dev-bounces+archive=mail-archive . com]

From: Madalin Bucur 

Allow the selection of the transmission queue based on the CPU id.
The DPAA Ethernet driver defines a ndo_select_queue() callback for
optimal selection of the egress FQ. That will override the XPS support
for this netdevice and should provide a certain increase in performance.
Standard XPS support is available by deselecting the introduced kconfig
option.

Signed-off-by: Madalin Bucur 
---
 drivers/net/ethernet/freescale/dpaa/Kconfig   | 10 ++
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c|  3 +++
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.h|  6 ++
 drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c |  8 
 drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h |  4 
 5 files changed, 31 insertions(+)

diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig 
b/drivers/net/ethernet/freescale/dpaa/Kconfig
index 022d5aa..2577aac 100644
--- a/drivers/net/ethernet/freescale/dpaa/Kconfig
+++ b/drivers/net/ethernet/freescale/dpaa/Kconfig
@@ -11,6 +11,16 @@ menuconfig FSL_DPAA_ETH
 
 if FSL_DPAA_ETH
 
+config FSL_DPAA_ETH_USE_NDO_SELECT_QUEUE
+   bool "Use driver's Tx queue selection mechanism"
+   default y
+   ---help---
+ The DPAA Ethernet driver defines a ndo_select_queue() callback for 
optimal selection
+ of the egress FQ. That will override the XPS support for this 
netdevice.
+ If for whatever reason you want to be in control of the egress 
FQ-to-CPU selection and mapping,
+ or simply don't want to use the driver's ndo_select_queue() callback, 
then unselect this
+ and use the standard XPS support instead.
+
 config FSL_DPAA_ETH_FRIENDLY_IF_NAME
bool "Use fmX-macY names for the DPAA interfaces"
default y
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 67f89ab..6c16ddd 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -375,6 +375,9 @@ static struct net_device_ops dpaa_ops = {
.ndo_get_stats64 = dpa_get_stats64,
.ndo_set_mac_address = dpa_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
+#ifdef CONFIG_FSL_DPAA_ETH_USE_NDO_SELECT_QUEUE
+   .ndo_select_queue = dpa_select_queue,
+#endif
.ndo_change_mtu = dpa_change_mtu,
.ndo_set_rx_mode = dpa_set_rx_mode,
.ndo_init = dpa_ndo_init,
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
index 45dc62d..a990c7b 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -405,9 +405,15 @@ static inline void _dpa_assign_wq(struct dpa_fq *fq)
}
 }
 
+#ifdef CONFIG_FSL_DPAA_ETH_USE_NDO_SELECT_QUEUE
+/* Use in lieu of skb_get_queue_mapping() */
+#define dpa_get_queue_mapping(skb) \
+   raw_smp_processor_id()
+#else
 /* Use the queue selected by XPS */
 #define dpa_get_queue_mapping(skb) \
skb_get_queue_mapping(skb)
+#endif
 
 static inline void dpa_bp_free_pf(void *addr)
 {
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
index 1c82338..59a1920 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
@@ -619,6 +619,14 @@ bool dpa_bpid2pool_use(int bpid)
return false;
 }
 
+#ifdef CONFIG_FSL_DPAA_ETH_USE_NDO_SELECT_QUEUE
+u16 dpa_select_queue(struct net_device *net_dev, struct sk_buff *skb,
+void *accel_priv, select_queue_fallback_t fallback)
+{
+   return dpa_get_queue_mapping(skb);
+}
+#endif
+
 struct dpa_fq *dpa_fq_alloc(struct device *dev,
const struct fqid_cell *fqids,
struct list_head *list,
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h
index c3443e6..20facd1 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h
@@ -69,6 +69,10 @@ struct dpa_bp *dpa_bpid2pool(int bpid);
 void dpa_bpid2pool_map(int bpid, struct dpa_bp *dpa_bp);
 bool dpa_bpid2pool_use(int bpid);
 void dpa_bp_drain(struct dpa_bp *bp);
+#ifdef CONFIG_FSL_DPAA_ETH_USE_NDO_SELECT_QUEUE
+u16 dpa_select_queue(struct net_device *net_dev, struct sk_buff *skb,
+void *accel_priv, select_queue_fallback_t fallback);
+#endif
 struct dpa_fq *dpa_fq_alloc(struct device *dev,
const struct fqid_cell *fqids,
struct list_head *list,
-- 
1.7.11.7

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[net-next v5 0/8] dpaa_eth: Add the Freescale DPAA Ethernet driver

[linuxppc-dev-bounces+archive=mail-archive . com]

From: Madalin Bucur 

This patch series adds the Ethernet driver for the Freescale
QorIQ Data Path Acceleration Architecture (DPAA).

This version includes changes following the feedback received
on previous versions from Eric Dumazet, Bob Cochran, Joe Perches,
Paul Bolle, Joakim Tjernlund, Scott Wood, David Miller - thank you.

Together with the driver a managed version of alloc_percpu
is provided that simplifies the release of per-CPU memory.

The Freescale DPAA architecture consists in a series of hardware
blocks that support the Ethernet connectivity. The Ethernet driver
depends upon the following drivers that are currently in the Linux
kernel or in review (the underlying drivers are not inter-dependent):
 - Peripheral Access Memory Unit (PAMU)
drivers/iommu/fsl_*
 - Frame Manager (FMan)
drivers/net/ethernet/freescale/fman
 - Queue Manager (QMan), Buffer Manager (BMan)
drivers/soc/fsl/qbman

dpaa_eth interfaces mapping to FMan MACs:

  dpaa_eth   /eth0\ ...   /ethN\
  driver|  | |  |
  -      ---      -
   -Ports  / Tx  Rx \.../ Tx  Rx \
  FMan|  | |  |
   -MACs  |   MAC0   | |   MACN   |
 /   dtsec0   \  ...  /   dtsecN   \ (or tgec)
/  \ /  \(or memac)
  -  --  ---  --  -
  FMan, FMan Port, FMan SP, FMan MURAM drivers
  -
  FMan HW blocks: MURAM, MACs, Ports, SP
  -

dpaa_eth relation to QMan, FMan:
  
  dpaa_eth   /eth0\
  driver/  \
  -   -^-   -^-   -^-   ----
  QMan driver / \   / \   / \  \   /  | BMan|
 |Rx | |Rx | |Tx | |Tx |  | driver  |
  -  |Dfl| |Err| |Cnf| |FQs|  | |
  QMan HW|FQ | |FQ | |FQ | |   |  | |
 /   \ /   \ /   \  \ /   | |
  -   ---   ---   ---   -v--
|FMan QMI | |
| FMan HW   FMan BMI  | BMan HW |
  ---   

where the acronyms used above (and in the code) are:
DPAA = Data Path Acceleration Architecture
FMan = DPAA Frame Manager
QMan = DPAA Queue Manager
BMan = DPAA Buffers Manager
QMI = QMan interface in FMan
BMI = BMan interface in FMan
FMan SP = FMan Storage Profiles
MURAM = Multi-user RAM in FMan
FQ = QMan Frame Queue
Rx Dfl FQ = default reception FQ
Rx Err FQ = Rx error frames FQ
Tx Cnf FQ = Tx confirmation FQ
Tx FQs = transmission frame queues
dtsec = datapath three speed Ethernet controller (10/100/1000 Mbps)
tgec = ten gigabit Ethernet controller (10 Gbps)
memac = multirate Ethernet MAC (10/100/1000/1)

The latest FMan driver patches were submitted by Igal Liberman:
https://patchwork.ozlabs.org/project/netdev/list/?submitter=64715=*

The latest Q/BMan drivers were submitted by Roy Pledge:
https://patchwork.ozlabs.org/project/linuxppc-dev/list/?submitter=66331=*

Changes from v4:
 - addressed feedback from Scott Wood and Joe Perches
 - fixed spelling
 - fixed leak of uninitialized stack to userspace
 - fix prints
 - replace raw_cpu_ptr() with this_cpu_ptr()
 - remove _s from the end of structure names
 - remove underscores at start of functions, goto labels
 - remove likely in error paths
 - use container_of() instead of open casts
 - remove priv from the driver name
 - move return type on same line with function name
 - drop DPA_READ_SKB_PTR/DPA_WRITE_SKB_PTR

Changes from v3:
 - removed bogus delay and comment in .ndo_stop implementation
 - addressed minor issues reported by David Miller

Changes from v2:
 - removed debugfs, moved exports to ethtool statistics
 - removed congestion groups Kconfig params

Changes from v1:
 - bpool level Kconfig options removed
 - print format using pr_fmt, cleaned up prints
 - __hot/__cold removed
 - gratuitous unlikely() removed
 - code style aligned, consistent spacing for declarations
 - comment formatting

The complete patch set based on the latest net-next/master kernel
can be found in the public git at:
http://git.freescale.com/git/cgit.cgi/ppc/upstream/linux.git
under the tag ldup_public_git_20151202:
http://git.freescale.com/git/cgit.cgi/ppc/upstream/linux.git/tag/?h=ldup_public_git_20151202

There is one u-boot patch that one needs to make sure it's applied
to align u-boot to the latest device tree binding document specification
used by the FMan driver. Please make sure your u-boot includes this patch:

commit 97a8d010e029111e5711a45264a726bedbeb24c4
Author: Igal Liberman 
Date:   Tue Aug 18 14:47:05 2015 +0300

net/fman: Support both new and legacy FMan Compatibles

The patch was 

[net-next v5 6/8] dpaa_eth: add ethtool statistics

[linuxppc-dev-bounces+archive=mail-archive . com]

From: Madalin Bucur 

Add a series of counters to be exported through ethtool:
- add detailed counters for reception errors;
- add detailed counters for QMan enqueue reject events;
- count the number of fragmented skbs received from the stack;
- count all frames received on the Tx confirmation path;
- add congestion group statistics;
- count the number of interrupts for each CPU.

Signed-off-by: Ioana Ciornei 
Signed-off-by: Madalin Bucur 
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c |  12 ++
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.h |  34 
 .../net/ethernet/freescale/dpaa/dpaa_eth_common.c  |  40 -
 .../net/ethernet/freescale/dpaa/dpaa_eth_common.h  |   2 +
 drivers/net/ethernet/freescale/dpaa/dpaa_eth_sg.c  |   1 +
 drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c | 184 +
 6 files changed, 271 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 6c16ddd..f71a0d2 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -93,6 +93,15 @@ static void dpa_rx_error(struct net_device *net_dev,
 
percpu_priv->stats.rx_errors++;
 
+   if (fd->status & FM_FD_ERR_DMA)
+   percpu_priv->rx_errors.dme++;
+   if (fd->status & FM_FD_ERR_PHYSICAL)
+   percpu_priv->rx_errors.fpe++;
+   if (fd->status & FM_FD_ERR_SIZE)
+   percpu_priv->rx_errors.fse++;
+   if (fd->status & FM_FD_ERR_PRS_HDR_ERR)
+   percpu_priv->rx_errors.phe++;
+
dpa_fd_release(net_dev, fd);
 }
 
@@ -158,6 +167,8 @@ static void dpa_tx_conf(struct net_device *net_dev,
percpu_priv->stats.tx_errors++;
}
 
+   percpu_priv->tx_confirm++;
+
skb = dpa_cleanup_tx_fd(priv, fd);
 
dev_kfree_skb(skb);
@@ -287,6 +298,7 @@ static void priv_ern(struct qman_portal *portal,
 
percpu_priv->stats.tx_dropped++;
percpu_priv->stats.tx_fifo_errors++;
+   count_ern(percpu_priv, msg);
 
/* If we intended this buffer to go into the pool
 * when the FM was done, we need to put it in
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
index a990c7b..076d66a 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -183,6 +183,25 @@ struct dpa_bp {
void (*free_buf_cb)(void *addr);
 };
 
+struct dpa_rx_errors {
+   u64 dme;/* DMA Error */
+   u64 fpe;/* Frame Physical Error */
+   u64 fse;/* Frame Size Error */
+   u64 phe;/* Header Error */
+};
+
+/* Counters for QMan ERN frames - one counter per rejection code */
+struct dpa_ern_cnt {
+   u64 cg_tdrop;   /* Congestion group taildrop */
+   u64 wred;   /* WRED congestion */
+   u64 err_cond;   /* Error condition */
+   u64 early_window;   /* Order restoration, frame too early */
+   u64 late_window;/* Order restoration, frame too late */
+   u64 fq_tdrop;   /* FQ taildrop */
+   u64 fq_retired; /* FQ is retired */
+   u64 orp_zero;   /* ORP disabled */
+};
+
 struct dpa_napi_portal {
struct napi_struct napi;
struct qman_portal *p;
@@ -192,7 +211,13 @@ struct dpa_napi_portal {
 struct dpa_percpu_priv {
struct net_device *net_dev;
struct dpa_napi_portal *np;
+   u64 in_interrupt;
+   u64 tx_confirm;
+   /* fragmented (non-linear) skbuffs received from the stack */
+   u64 tx_frag_skbuffs;
struct rtnl_link_stats64 stats;
+   struct dpa_rx_errors rx_errors;
+   struct dpa_ern_cnt ern_cnt;
 };
 
 struct dpa_priv {
@@ -219,6 +244,14 @@ struct dpa_priv {
 * (and the same) congestion group.
 */
struct qman_cgr cgr;
+   /* If congested, when it began. Used for performance stats. */
+   u32 congestion_start_jiffies;
+   /* Number of jiffies the Tx port was congested. */
+   u32 congested_jiffies;
+   /* Counter for the number of times the CGR
+* entered congestion state
+*/
+   u32 cgr_congested_count;
} cgr_data;
/* Use a per-port CGR for ingress traffic. */
bool use_ingress_cgr;
@@ -276,6 +309,7 @@ static inline int dpaa_eth_napi_schedule(struct 
dpa_percpu_priv *percpu_priv,
 
np->p = portal;
napi_schedule(>napi);
+   percpu_priv->in_interrupt++;
return 1;
}
}
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c 

[net-next v5 2/8] dpaa_eth: add support for DPAA Ethernet

[linuxppc-dev-bounces+archive=mail-archive . com]

From: Madalin Bucur 

This introduces the Freescale Data Path Acceleration Architecture
(DPAA) Ethernet driver (dpaa_eth) that builds upon the DPAA QMan,
BMan, PAMU and FMan drivers to deliver Ethernet connectivity on
the Freescale DPAA QorIQ platforms.

Signed-off-by: Madalin Bucur 
---
 drivers/net/ethernet/freescale/Kconfig |2 +
 drivers/net/ethernet/freescale/Makefile|1 +
 drivers/net/ethernet/freescale/dpaa/Kconfig|   22 +
 drivers/net/ethernet/freescale/dpaa/Makefile   |   11 +
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c |  759 +++
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.h |  417 +++
 .../net/ethernet/freescale/dpaa/dpaa_eth_common.c  | 1316 
 .../net/ethernet/freescale/dpaa/dpaa_eth_common.h  |   97 ++
 drivers/net/ethernet/freescale/dpaa/dpaa_eth_sg.c  |  386 ++
 9 files changed, 3011 insertions(+)
 create mode 100644 drivers/net/ethernet/freescale/dpaa/Kconfig
 create mode 100644 drivers/net/ethernet/freescale/dpaa/Makefile
 create mode 100644 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
 create mode 100644 drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
 create mode 100644 drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
 create mode 100644 drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h
 create mode 100644 drivers/net/ethernet/freescale/dpaa/dpaa_eth_sg.c

diff --git a/drivers/net/ethernet/freescale/Kconfig 
b/drivers/net/ethernet/freescale/Kconfig
index f3f89cc..92198be 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -92,4 +92,6 @@ config GIANFAR
  and MPC86xx family of chips, the eTSEC on LS1021A and the FEC
  on the 8540.
 
+source "drivers/net/ethernet/freescale/dpaa/Kconfig"
+
 endif # NET_VENDOR_FREESCALE
diff --git a/drivers/net/ethernet/freescale/Makefile 
b/drivers/net/ethernet/freescale/Makefile
index 4097c58..ae13dc5 100644
--- a/drivers/net/ethernet/freescale/Makefile
+++ b/drivers/net/ethernet/freescale/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_FS_ENET) += fs_enet/
 obj-$(CONFIG_FSL_PQ_MDIO) += fsl_pq_mdio.o
 obj-$(CONFIG_FSL_XGMAC_MDIO) += xgmac_mdio.o
 obj-$(CONFIG_GIANFAR) += gianfar_driver.o
+obj-$(CONFIG_FSL_DPAA_ETH) += dpaa/
 obj-$(CONFIG_PTP_1588_CLOCK_GIANFAR) += gianfar_ptp.o
 gianfar_driver-objs := gianfar.o \
gianfar_ethtool.o
diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig 
b/drivers/net/ethernet/freescale/dpaa/Kconfig
new file mode 100644
index 000..022d5aa
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/Kconfig
@@ -0,0 +1,22 @@
+menuconfig FSL_DPAA_ETH
+   tristate "DPAA Ethernet"
+   depends on FSL_SOC && FSL_BMAN && FSL_QMAN && FSL_FMAN
+   select PHYLIB
+   select FSL_FMAN_MAC
+   ---help---
+ Data Path Acceleration Architecture Ethernet driver,
+ supporting the Freescale QorIQ chips.
+ Depends on Freescale Buffer Manager and Queue Manager
+ driver and Frame Manager Driver.
+
+if FSL_DPAA_ETH
+
+config FSL_DPAA_ETH_FRIENDLY_IF_NAME
+   bool "Use fmX-macY names for the DPAA interfaces"
+   default y
+   ---help---
+ The DPAA Ethernet netdevices are created for each FMan port available
+ on a certain board. Enable this to get interface names derived from
+ the underlying FMan hardware for a simple identification.
+
+endif # FSL_DPAA_ETH
diff --git a/drivers/net/ethernet/freescale/dpaa/Makefile 
b/drivers/net/ethernet/freescale/dpaa/Makefile
new file mode 100644
index 000..3847ec7
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/Makefile
@@ -0,0 +1,11 @@
+#
+# Makefile for the Freescale DPAA Ethernet controllers
+#
+
+# Include FMan headers
+FMAN= $(srctree)/drivers/net/ethernet/freescale/fman
+ccflags-y += -I$(FMAN)
+
+obj-$(CONFIG_FSL_DPAA_ETH) += fsl_dpa.o
+
+fsl_dpa-objs += dpaa_eth.o dpaa_eth_sg.o dpaa_eth_common.o
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
new file mode 100644
index 000..67f89ab
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -0,0 +1,759 @@
+/* Copyright 2008 - 2015 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ *  notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ *  notice, this list of conditions and the following disclaimer in the
+ *  documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ *  names of its contributors may be used to endorse or promote products
+ *  derived from this 

[net-next v5 3/8] dpaa_eth: add support for S/G frames

[linuxppc-dev-bounces+archive=mail-archive . com]

From: Madalin Bucur 

Add support for Scatter/Gather (S/G) frames. The FMan can place
the frame content into multiple buffers and provide a S/G Table
(SGT) into one first buffer with references to the others.

Signed-off-by: Madalin Bucur 
---
 .../net/ethernet/freescale/dpaa/dpaa_eth_common.c  |  54 +++-
 .../net/ethernet/freescale/dpaa/dpaa_eth_common.h  |   2 +
 drivers/net/ethernet/freescale/dpaa/dpaa_eth_sg.c  | 337 +++--
 3 files changed, 373 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
index c96995c..1c82338 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
@@ -117,6 +117,10 @@ int dpa_netdev_init(struct net_device *net_dev,
net_dev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 NETIF_F_LLTX);
 
+   net_dev->hw_features |= NETIF_F_SG | NETIF_F_HIGHDMA;
+   /* The kernels enables GSO automatically, if we declare NETIF_F_SG.
+* For conformity, we'll still declare GSO explicitly.
+*/
net_dev->features |= NETIF_F_GSO;
 
net_dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
@@ -1194,10 +1198,42 @@ void dpaa_eth_init_ports(struct mac_device *mac_dev,
  port_fqs->rx_defq, _layout[RX]);
 }
 
+void dpa_release_sgt(struct qm_sg_entry *sgt)
+{
+   struct dpa_bp *dpa_bp;
+   struct bm_buffer bmb[DPA_BUFF_RELEASE_MAX];
+   int i = 0, j, timeout = 100;
+
+   memset(bmb, 0, sizeof(bmb));
+
+   do {
+   dpa_bp = dpa_bpid2pool(sgt[i].bpid);
+   WARN_ON(!dpa_bp);
+
+   j = 0;
+   do {
+   WARN_ON(sgt[i].extension);
+
+   bmb[j].hi = sgt[i].addr_hi;
+   bmb[j].lo = be32_to_cpu(sgt[i].addr_lo);
+
+   j++; i++;
+   } while (j < ARRAY_SIZE(bmb) &&
+   !sgt[i - 1].final &&
+   sgt[i - 1].bpid == sgt[i].bpid);
+
+   while (bman_release(dpa_bp->pool, bmb, j, 0) && --timeout)
+   cpu_relax();
+   } while (!sgt[i - 1].final);
+}
+
 void dpa_fd_release(const struct net_device *net_dev, const struct qm_fd *fd)
 {
+   struct qm_sg_entry *sgt;
struct dpa_bp *dpa_bp;
struct bm_buffer bmb;
+   dma_addr_t addr;
+   void *vaddr;
int timeout = 100;
 
memset(, 0, sizeof(bmb));
@@ -1206,7 +1242,23 @@ void dpa_fd_release(const struct net_device *net_dev, 
const struct qm_fd *fd)
dpa_bp = dpa_bpid2pool(fd->bpid);
WARN_ON(!dpa_bp);
 
-   WARN_ON(fd->format == qm_fd_sg);
+   if (fd->format == qm_fd_sg) {
+   vaddr = phys_to_virt(fd->addr);
+   sgt = vaddr + dpa_fd_offset(fd);
+
+   dma_unmap_single(dpa_bp->dev, qm_fd_addr(fd), dpa_bp->size,
+DMA_BIDIRECTIONAL);
+
+   dpa_release_sgt(sgt);
+
+   addr = dma_map_single(dpa_bp->dev, vaddr, dpa_bp->size,
+ DMA_BIDIRECTIONAL);
+   if (dma_mapping_error(dpa_bp->dev, addr)) {
+   dev_err(dpa_bp->dev, "DMA mapping failed");
+   return;
+   }
+   bm_buffer_set64(, addr);
+   }
 
while (bman_release(dpa_bp->pool, , 1, 0) && --timeout)
cpu_relax();
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h
index 78a97d9..c3443e6 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h
@@ -37,6 +37,7 @@
 
 #include "dpaa_eth.h"
 
+#define DPA_SGT_MAX_ENTRIES 16 /* maximum number of entries in SG Table */
 #define DPA_BUFF_RELEASE_MAX 8 /* maximum number of buffers released at once */
 
 /* used in napi related functions */
@@ -89,6 +90,7 @@ void dpaa_eth_init_ports(struct mac_device *mac_dev,
 struct fm_port_fqs *port_fqs,
 struct dpa_buffer_layout *buf_layout,
 struct device *dev);
+void dpa_release_sgt(struct qm_sg_entry *sgt);
 void dpa_fd_release(const struct net_device *net_dev, const struct qm_fd *fd);
 int dpa_enable_tx_csum(struct dpa_priv *priv,
   struct sk_buff *skb,
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sg.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sg.c
index c913dd6..5fbc167 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sg.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sg.c
@@ -38,6 +38,32 @@
 #include "dpaa_eth.h"
 #include "dpaa_eth_common.h"
 
+/* DMA map and add a page frag back into the bpool.
+ * @vaddr fragment 

Re: [v9, 3/6] fsl/fman: Add FMan MAC support

[Kenneth Klette Jonassen]

> +/* PHY Control Register */
> +#define PHY_CR_PHY_RESET   0x8000
> +#define PHY_CR_SPEED0  0x2000
> +#define PHY_CR_ANE 0x1000
> +#define PHY_CR_RESET_AN0x0200
> +#define PHY_CR_FULLDUPLEX  0x0100
> +#define PHY_CR_SPEED1  0x0040

Reuse defines in mii.h? BMCR_SPEED1000, BMCR_*, etc.

> +#define PHY_TBICON_SRESET  0x8000
> +#define PHY_TBICON_CLK_SEL 0x0020

This is similarly named TBICON_CLK_SELECT in freescale/gianfar.h.
Perhaps use the same names, and if possible, use a shared header file?

It would be nice to define all bits of the TBI registers, if only for
completeness. Maybe along with a succinct description, e.g., that
"sreset" means soft reset. (Or just call it TBICON_SOFT_RESET.)

> +/* MII Configuration Control Memory Map Registers */
> +struct dtsec_mii_regs {
> +/* dTSEC Memory Map registers */
> +struct dtsec_regs {
> +static int mii_write_reg(struct fman_mac *dtsec, u8 addr, u8 reg, u16 data)
> +static int mii_read_reg(struct fman_mac *dtsec, u8 addr, u8 reg, u16 *data)

Any chance this patch overlaps significantly with fsl_pq_mdio.c?

http://lxr.free-electrons.com/source/drivers/net/ethernet/freescale/fsl_pq_mdio.c?v=4.3#L44
fsl_pq_mdio_write(),
fsl_pq_mdio_read(),
etc.

> +   if (dtsec->phy_if == PHY_INTERFACE_MODE_SGMII) {
> +   u16 tmp_reg16;
> +
> +   /* Configure the TBI PHY Control Register */
> +   tmp_reg16 = PHY_TBICON_CLK_SEL | PHY_TBICON_SRESET;
> +   mii_write_reg(dtsec, (u8)dtsec_drv_param->tbipa, 17,
> + tmp_reg16);
> +
> +   tmp_reg16 = PHY_TBICON_CLK_SEL;
> +   mii_write_reg(dtsec, (u8)dtsec_drv_param->tbipa, 17,
> + tmp_reg16);
> +
> +   tmp_reg16 =
> +   (PHY_CR_PHY_RESET | PHY_CR_ANE | PHY_CR_FULLDUPLEX |
> +PHY_CR_SPEED1);
> +   mii_write_reg(dtsec, (u8)dtsec_drv_param->tbipa, 0, 
> tmp_reg16);
> +
> +   if (dtsec->basex_if)
> +   tmp_reg16 = PHY_TBIANA_1000X;
> +   else
> +   tmp_reg16 = PHY_TBIANA_SGMII;
> +   mii_write_reg(dtsec, (u8)dtsec_drv_param->tbipa, 4, 
> tmp_reg16);
> +
> +   tmp_reg16 =
> +   (PHY_CR_ANE | PHY_CR_RESET_AN | PHY_CR_FULLDUPLEX |
> +PHY_CR_SPEED1);
> +
> +   mii_write_reg(dtsec, (u8)dtsec_drv_param->tbipa, 0, 
> tmp_reg16);
> +   }

Afaik, programming the TBI belongs in a separate PHY driver. See
drivers/net/phy/phy_device.c.

The same logic applies to gfar_configure_serdes() and uec_configure_serdes().

> +/* Internal PHY Registers - SGMII */
> +#define PHY_SGMII_CR_RESET_AN   0x0200
> +#define PHY_SGMII_CR_AN_ENABLE  0x1000

This namespace duplicates the intention of PHY_CR_*? (Which in turn
duplicated BMCR_*, ..)
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: more POLL... fun

[Arnd Bergmann]

On Friday 04 December 2015 06:38:25 Al Viro wrote:
> On cross-builds the __poll_t annotations had caught something interesting:
> void spufs_mfc_callback(struct spu *spu)
> {
>   
> mask = 0;
> if (free_elements & 0x)
> mask |= POLLOUT;
> if (tagstatus & ctx->tagwait)
> mask |= POLLIN;
> 
> kill_fasync(>mfc_fasync, SIGIO, mask);
>   
> }
> 
> That's arch/powerpc/platforms/cell/spufs/file.c.  WTF is kill_fasync()
> getting as the last argument here?  Valid values are
> #define POLL_IN (__SI_POLL|1)   /* data input available */
> #define POLL_OUT(__SI_POLL|2)   /* output buffers available */
> #define POLL_MSG(__SI_POLL|3)   /* input message available */
> #define POLL_ERR(__SI_POLL|4)   /* i/o error */
> #define POLL_PRI(__SI_POLL|5)   /* high priority input available */
> #define POLL_HUP(__SI_POLL|6)   /* device disconnected */
> 
> Use of POLLIN, POLLOUT, etc. here is wrong - kill_fasync() will step into
> BUG_ON((reason & __SI_MASK) != __SI_POLL);
> in send_sigio_to_task().  Other two callers of kill_fasync() in that file
> are trivially fixed by switching to POLL_IN and POLL_OUT; with this one
> I've no idea what had been intended.
> 
> What's more, I really wonder if it had _ever_ been tested - these 
> kill_fasync()
> calls had been introduced in
> commit 8b3d6663c6217e4f50cc3720935a96da9b984117
> Author: Arnd Bergmann 
> Date:   Tue Nov 15 15:53:52 2005 -0500
> 
> [PATCH] spufs: cooperative scheduler support
> more than 5 years after that BUG_ON() had been added - it goes back to
> +   /* Make sure we are called with one of the POLL_*
> +  reasons, otherwise we could leak kernel stack into
> +  userspace.  */
> +   if ((reason & __SI_MASK) != __SI_POLL)
> +   BUG();
> in 2.3.99pre-10-3, on May 25 2000.
> 
> What the hell am I missing here?  Has that code been DOA and never used by
> anyone in all the decade it had been in mainline?

I don't remember why we put in fasync support, but I have checked the libspe
implementation and found that it doesn't use it (not a big surprise there).
It always uses epoll() to get notifications from spufs, and based on your
explanation I assume everything else (there may have been one or two users
that used the low-level interfaces rather than libspe) did too.

Arnd
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[net-next v5 1/8] devres: add devm_alloc_percpu()

[linuxppc-dev-bounces+archive=mail-archive . com]

From: Madalin Bucur 

Introduce managed counterparts for alloc_percpu() and free_percpu().
Add devm_alloc_percpu() and devm_free_percpu() into the managed
interfaces list.

Signed-off-by: Madalin Bucur 
Tested-by: Madalin-Cristian Bucur 
---
 Documentation/driver-model/devres.txt |  4 +++
 drivers/base/devres.c | 64 +++
 include/linux/device.h| 19 +++
 3 files changed, 87 insertions(+)

diff --git a/Documentation/driver-model/devres.txt 
b/Documentation/driver-model/devres.txt
index 831a536..595fd1b 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -312,6 +312,10 @@ MEM
   devm_kvasprintf()
   devm_kzalloc()
 
+PER-CPU MEM
+  devm_alloc_percpu()
+  devm_free_percpu()
+
 PCI
   pcim_enable_device() : after success, all PCI ops become managed
   pcim_pin_device(): keep PCI device enabled after release
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 8fc654f..77e658f 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -10,6 +10,7 @@
 #include 
 #include 
 #include 
+#include 
 
 #include "base.h"
 
@@ -985,3 +986,66 @@ void devm_free_pages(struct device *dev, unsigned long 
addr)
   ));
 }
 EXPORT_SYMBOL_GPL(devm_free_pages);
+
+static void devm_percpu_release(struct device *dev, void *pdata)
+{
+   void __percpu *p;
+
+   p = *(void __percpu **)pdata;
+   free_percpu(p);
+}
+
+static int devm_percpu_match(struct device *dev, void *data, void *p)
+{
+   struct devres *devr = container_of(data, struct devres, data);
+
+   return *(void **)devr->data == p;
+}
+
+/**
+ * __devm_alloc_percpu - Resource-managed alloc_percpu
+ * @dev: Device to allocate per-cpu memory for
+ * @size: Size of per-cpu memory to allocate
+ * @align: Alignment of per-cpu memory to allocate
+ *
+ * Managed alloc_percpu. Per-cpu memory allocated with this function is
+ * automatically freed on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+void __percpu *__devm_alloc_percpu(struct device *dev, size_t size,
+   size_t align)
+{
+   void *p;
+   void __percpu *pcpu;
+
+   pcpu = __alloc_percpu(size, align);
+   if (!pcpu)
+   return NULL;
+
+   p = devres_alloc(devm_percpu_release, sizeof(void *), GFP_KERNEL);
+   if (!p)
+   return NULL;
+
+   *(void __percpu **)p = pcpu;
+
+   devres_add(dev, p);
+
+   return pcpu;
+}
+EXPORT_SYMBOL_GPL(__devm_alloc_percpu);
+
+/**
+ * devm_free_percpu - Resource-managed free_percpu
+ * @dev: Device this memory belongs to
+ * @pdata: Per-cpu memory to free
+ *
+ * Free memory allocated with devm_alloc_percpu().
+ */
+void devm_free_percpu(struct device *dev, void __percpu *pdata)
+{
+   WARN_ON(devres_destroy(dev, devm_percpu_release, devm_percpu_match,
+  (void *)pdata));
+}
+EXPORT_SYMBOL_GPL(devm_free_percpu);
diff --git a/include/linux/device.h b/include/linux/device.h
index b8f411b..ef9a86a 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -681,6 +681,25 @@ void __iomem *devm_ioremap_resource(struct device *dev, 
struct resource *res);
 int devm_add_action(struct device *dev, void (*action)(void *), void *data);
 void devm_remove_action(struct device *dev, void (*action)(void *), void 
*data);
 
+/**
+ * devm_alloc_percpu - Resource-managed alloc_percpu
+ * @dev: Device to allocate per-cpu memory for
+ * @type: Type to allocate per-cpu memory for
+ *
+ * Managed alloc_percpu. Per-cpu memory allocated with this function is
+ * automatically freed on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+#define devm_alloc_percpu(dev, type)  \
+   (typeof(type) __percpu *)__devm_alloc_percpu(dev, sizeof(type), \
+__alignof__(type))
+
+void __percpu *__devm_alloc_percpu(struct device *dev, size_t size,
+  size_t align);
+void devm_free_percpu(struct device *dev, void __percpu *pdata);
+
 struct device_dma_parameters {
/*
 * a low level driver may set these to teach IOMMU code about
-- 
1.7.11.7

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[net-next v5 5/8] dpaa_eth: add ethtool functionality

[linuxppc-dev-bounces+archive=mail-archive . com]

From: Madalin Bucur 

Add support for basic ethtool operations.

Signed-off-by: Madalin Bucur 
---
 drivers/net/ethernet/freescale/dpaa/Makefile   |   2 +-
 .../net/ethernet/freescale/dpaa/dpaa_eth_common.c  |   2 +
 .../net/ethernet/freescale/dpaa/dpaa_eth_common.h  |   3 +
 drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c | 230 +
 4 files changed, 236 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c

diff --git a/drivers/net/ethernet/freescale/dpaa/Makefile 
b/drivers/net/ethernet/freescale/dpaa/Makefile
index 3847ec7..9b75d52 100644
--- a/drivers/net/ethernet/freescale/dpaa/Makefile
+++ b/drivers/net/ethernet/freescale/dpaa/Makefile
@@ -8,4 +8,4 @@ ccflags-y += -I$(FMAN)
 
 obj-$(CONFIG_FSL_DPAA_ETH) += fsl_dpa.o
 
-fsl_dpa-objs += dpaa_eth.o dpaa_eth_sg.o dpaa_eth_common.o
+fsl_dpa-objs += dpaa_eth.o dpaa_eth_sg.o dpaa_eth_common.o dpaa_ethtool.o
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
index 59a1920..656c5a8 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.c
@@ -133,6 +133,8 @@ int dpa_netdev_init(struct net_device *net_dev,
memcpy(net_dev->perm_addr, mac_addr, net_dev->addr_len);
memcpy(net_dev->dev_addr, mac_addr, net_dev->addr_len);
 
+   net_dev->ethtool_ops = _ethtool_ops;
+
net_dev->needed_headroom = priv->tx_headroom;
net_dev->watchdog_timeo = msecs_to_jiffies(tx_timeout);
 
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h 
b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h
index 20facd1..8564bfa 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_common.h
@@ -43,6 +43,9 @@
 /* used in napi related functions */
 extern u16 qman_portal_max;
 
+/* from dpa_ethtool.c */
+extern const struct ethtool_ops dpa_ethtool_ops;
+
 int dpa_netdev_init(struct net_device *net_dev,
const struct net_device_ops *dpaa_ops,  u16 tx_timeout);
 int dpa_start(struct net_device *net_dev);
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c 
b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
new file mode 100644
index 000..ebf049f
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -0,0 +1,230 @@
+/* Copyright 2008-2015 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ *  notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ *  notice, this list of conditions and the following disclaimer in the
+ *  documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ *  names of its contributors may be used to endorse or promote products
+ *  derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF 
THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include 
+
+#include "dpaa_eth.h"
+#include "mac.h"
+#include "dpaa_eth_common.h"
+
+static int dpa_get_settings(struct net_device *net_dev,
+   struct ethtool_cmd *et_cmd)
+{
+   int err;
+   struct dpa_priv *priv;
+
+   priv = netdev_priv(net_dev);
+
+   if (!priv->mac_dev->phy_dev) {
+   netdev_dbg(net_dev, "phy device not initialized\n");
+   return 0;
+   }
+
+   err = phy_ethtool_gset(priv->mac_dev->phy_dev, et_cmd);
+
+   return err;
+}
+
+static int dpa_set_settings(struct net_device *net_dev,
+   struct 

Re: [PATCH v4 4/9] ppc64 ftrace_with_regs configuration variables

[Torsten Duwe]

On Thu, Dec 03, 2015 at 05:20:08PM +0100, Petr Mladek wrote:
>
> IMHO, we should not define CC_USING_MPROFILE_KERNEL if it is not
> supported by the compiler.

Yes, true.

> I took inspiration from the CC_USING_FENTRY handling in
> linux/Makefile. The following code worked for me:
>
> CC_USING_MPROFILE_KERNEL := $(call cc-option, -pg -mprofile-kernel 
> -DCC_USING_MPROFILE_KERNEL)
> CC_FLAGS_FTRACE := $(CC_USING_MPROFILE_KERNEL)
> KBUILD_CPPFLAGS += $(CC_USING_MPROFILE_KERNEL)

Excellent!

> I just do not understand why we need to add the flags also
> to KBUILD_CPPFLAGS. It seems that they are duplicated
> when compiling kernel/livepatch/core.o. But livepatching
> did not work without it. I wonder if you found the culprit.

Some assembler-with-cpp files also need to be notified?

My plan is to first get this working reliably and then fine tune.

Torsten

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: more POLL... fun

[Al Viro]

On Fri, Dec 04, 2015 at 10:16:50AM +0100, Arnd Bergmann wrote:

> I don't remember why we put in fasync support, but I have checked the libspe
> implementation and found that it doesn't use it (not a big surprise there).
> It always uses epoll() to get notifications from spufs, and based on your
> explanation I assume everything else (there may have been one or two users
> that used the low-level interfaces rather than libspe) did too.

OK...  So should we just rip ->{mfc,ibox,wbox}_fasync out, along with all
three kill_fasync() and ->fasync() instances in there?  We obviously need to
leave spufs_{mfc,ibox,wbox}_callback() in place for the sake of those
wake_up_all(>{mfc,ibox,wbox}_wq); in them...

I mean, fasync in there obviously never been used at all - it never delivered
a single SIGIO, and the first user to try would get the BUG_ON() in fcntl.c
instead.  Since nobody complained in more than 10 years...
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [PATCH v2 3/5] printk/nmi: Try hard to print Oops message in NMI context

[Petr Mladek]

On Tue 2015-12-01 23:44:37, Russell King - ARM Linux wrote:
> On Fri, Nov 27, 2015 at 12:09:30PM +0100, Petr Mladek wrote:
> > What we can do, though, is to zap all printk locks. We already do this
> > when a printk recursion is detected. This should be safe because
> > the system is crashing and there shouldn't be any printk caller
> > that would cause the deadlock.
> 
> What about serial consoles which may call out to subsystems like the
> clk subsystem to enable a clock, which would want to take their own
> spinlocks in addition to the serial console driver?

Yes, there might be more locks used by the serial console but I do
not know how to handle them all easily. IMHO, this patch is just better
than nothing.

> I don't see bust_spinlocks() dealing with any of these locks, so IMHO
> trying to make this work in NMI context strikes me as making the
> existing solution more unreliable on ARM systems.

bust_spinlocks() calls printk_nmi_flush() that would call printk()
that would zap "lockbuf_lock" and "console_sem" when in Oops and NMI.
Yes, there might be more locks blocked but we try to break at least
the first two walls. Also zapping is allowed only once per 30 seconds,
see zap_locks(). Why do you think that it might make things more
unreliable, please?


Thanks for looking,
Petr
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[PATCH v5 6/9] ppc64 ftrace: disable profiling for some functions

[Torsten Duwe]

At least POWER7/8 have MMUs that don't completely autoload;
a normal, recoverable memory fault might pass through these functions.
If a dynamic tracer function causes such a fault, any of these functions
being traced with -mprofile-kernel may cause an endless recursion.

Signed-off-by: Torsten Duwe 
---
 arch/powerpc/kernel/process.c|  2 +-
 arch/powerpc/mm/fault.c  |  2 +-
 arch/powerpc/mm/hash_utils_64.c  | 18 +-
 arch/powerpc/mm/hugetlbpage-hash64.c |  2 +-
 arch/powerpc/mm/hugetlbpage.c|  4 ++--
 arch/powerpc/mm/mem.c|  2 +-
 arch/powerpc/mm/pgtable_64.c |  2 +-
 arch/powerpc/mm/slb.c|  6 +++---
 arch/powerpc/mm/slice.c  |  8 
 9 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 646bf4d..5b3c19d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -733,7 +733,7 @@ static inline void __switch_to_tm(struct task_struct *prev)
  * don't know which of the checkpointed state and the transactional
  * state to use.
  */
-void restore_tm_state(struct pt_regs *regs)
+notrace void restore_tm_state(struct pt_regs *regs)
 {
unsigned long msr_diff;
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index a67c6d7..125be37 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -205,7 +205,7 @@ static int mm_fault_error(struct pt_regs *regs, unsigned 
long addr, int fault)
  * The return value is 0 if the fault was handled, or the signal
  * number if this is a kernel fault that can't be handled here.
  */
-int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
+notrace int __kprobes do_page_fault(struct pt_regs *regs, unsigned long 
address,
unsigned long error_code)
 {
enum ctx_state prev_state = exception_enter();
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 7f9616f..64f5b40 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -849,7 +849,7 @@ void early_init_mmu_secondary(void)
 /*
  * Called by asm hashtable.S for doing lazy icache flush
  */
-unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
+notrace unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int 
trap)
 {
struct page *page;
 
@@ -870,7 +870,7 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, 
pte_t pte, int trap)
 }
 
 #ifdef CONFIG_PPC_MM_SLICES
-static unsigned int get_paca_psize(unsigned long addr)
+static notrace unsigned int get_paca_psize(unsigned long addr)
 {
u64 lpsizes;
unsigned char *hpsizes;
@@ -899,7 +899,7 @@ unsigned int get_paca_psize(unsigned long addr)
  * For now this makes the whole process use 4k pages.
  */
 #ifdef CONFIG_PPC_64K_PAGES
-void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
+notrace void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
 {
if (get_slice_psize(mm, addr) == MMU_PAGE_4K)
return;
@@ -920,7 +920,7 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long 
addr)
  * Result is 0: full permissions, _PAGE_RW: read-only,
  * _PAGE_USER or _PAGE_USER|_PAGE_RW: no access.
  */
-static int subpage_protection(struct mm_struct *mm, unsigned long ea)
+static notrace int subpage_protection(struct mm_struct *mm, unsigned long ea)
 {
struct subpage_prot_table *spt = >context.spt;
u32 spp = 0;
@@ -968,7 +968,7 @@ void hash_failure_debug(unsigned long ea, unsigned long 
access,
trap, vsid, ssize, psize, lpsize, pte);
 }
 
-static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
+static notrace void check_paca_psize(unsigned long ea, struct mm_struct *mm,
 int psize, bool user_region)
 {
if (user_region) {
@@ -990,7 +990,7 @@ static void check_paca_psize(unsigned long ea, struct 
mm_struct *mm,
  * -1 - critical hash insertion error
  * -2 - access not permitted by subpage protection mechanism
  */
-int hash_page_mm(struct mm_struct *mm, unsigned long ea,
+notrace int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 unsigned long access, unsigned long trap,
 unsigned long flags)
 {
@@ -1187,7 +1187,7 @@ bail:
 }
 EXPORT_SYMBOL_GPL(hash_page_mm);
 
-int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
+notrace int hash_page(unsigned long ea, unsigned long access, unsigned long 
trap,
  unsigned long dsisr)
 {
unsigned long flags = 0;
@@ -1289,7 +1289,7 @@ out_exit:
 /* WARNING: This is called from hash_low_64.S, if you change this prototype,
  *  do not forget to update the assembly call site !
  */
-void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
+notrace void flush_hash_page(unsigned long vpn, real_pte_t pte, int 

[PATCH v5 9/9] Enable LIVEPATCH to be configured on ppc64le and add livepatch.o if it is selected.

[Torsten Duwe]

Signed-off-by: Torsten Duwe 
---
 arch/powerpc/Kconfig | 5 +
 arch/powerpc/kernel/Makefile | 1 +
 2 files changed, 6 insertions(+)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 89b1a2a..62a3f54 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -163,6 +163,9 @@ config PPC
select ARCH_HAS_DMA_SET_COHERENT_MASK
select HAVE_ARCH_SECCOMP_FILTER
 
+config HAVE_LIVEPATCH
+   def_bool PPC64 && CPU_LITTLE_ENDIAN
+
 config GENERIC_CSUM
def_bool CPU_LITTLE_ENDIAN
 
@@ -1095,3 +1098,5 @@ config PPC_LIB_RHEAP
bool
 
 source "arch/powerpc/kvm/Kconfig"
+
+source "kernel/livepatch/Kconfig"
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 0f417d5..f9a2925 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -119,6 +119,7 @@ obj-$(CONFIG_DYNAMIC_FTRACE)+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)+= ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)  += ftrace.o
 obj-$(CONFIG_TRACING)  += trace_clock.o
+obj-$(CONFIG_LIVEPATCH)+= livepatch.o
 
 ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
 obj-y  += iomap.o
-- 
1.8.5.6

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[PATCH v5 0/9] ftrace with regs + live patching for ppc64 LE (ABI v2)

[Torsten Duwe]

Changes since v4:
  * change comment style in entry_64.S to C89
(nobody is using assembler syntax comments there).
  * the bool function restore_r2 shouldn't return 2,
that's a little confusing.
  * Test whether the compiler supports -mprofile-kernel
and only then define CC_USING_MPROFILE_KERNEL
  * also make the return value of klp_check_compiler_support
depend on that.

Major changes since v3:
  * the graph tracer works now.
It turned out the stack frame it tried to manipulate does not
exist at that point.
  * changes only needed in order to support -mprofile-kernel are now
in a separate patch, prepended.
  * Kconfig cleanup so this is only selectable on ppc64le.



Torsten Duwe (9):
  ppc64 (le): prepare for -mprofile-kernel
  ppc64le FTRACE_WITH_REGS implementation
  ppc use ftrace_modify_all_code default
  ppc64 ftrace_with_regs configuration variables
  ppc64 ftrace_with_regs: spare early boot and low level
  ppc64 ftrace: disable profiling for some functions
  ppc64 ftrace: disable profiling for some files
  Implement kernel live patching for ppc64le (ABIv2)
  Enable LIVEPATCH to be configured on ppc64le and add livepatch.o if it
is selected.

 arch/powerpc/Kconfig |   7 ++
 arch/powerpc/Makefile|  10 +++
 arch/powerpc/include/asm/ftrace.h|   5 ++
 arch/powerpc/include/asm/livepatch.h |  45 ++
 arch/powerpc/kernel/Makefile |  13 +--
 arch/powerpc/kernel/entry_64.S   | 164 ++-
 arch/powerpc/kernel/ftrace.c |  88 ++-
 arch/powerpc/kernel/livepatch.c  |  38 
 arch/powerpc/kernel/module_64.c  |  38 +++-
 arch/powerpc/kernel/process.c|   2 +-
 arch/powerpc/lib/Makefile|   4 +-
 arch/powerpc/mm/fault.c  |   2 +-
 arch/powerpc/mm/hash_utils_64.c  |  18 ++--
 arch/powerpc/mm/hugetlbpage-hash64.c |   2 +-
 arch/powerpc/mm/hugetlbpage.c|   4 +-
 arch/powerpc/mm/mem.c|   2 +-
 arch/powerpc/mm/pgtable_64.c |   2 +-
 arch/powerpc/mm/slb.c|   6 +-
 arch/powerpc/mm/slice.c  |   8 +-
 kernel/trace/Kconfig |   5 ++
 20 files changed, 409 insertions(+), 54 deletions(-)
 create mode 100644 arch/powerpc/include/asm/livepatch.h
 create mode 100644 arch/powerpc/kernel/livepatch.c

-- 
1.8.5.6

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[PATCH v5 3/9] ppc use ftrace_modify_all_code default

[Torsten Duwe]

Convert ppc's arch_ftrace_update_code from its own function copy
to use the generic default functionality (without stop_machine --
our instructions are properly aligned and the replacements atomic ;)

With this we gain error checking and the much-needed function_trace_op
handling.

Signed-off-by: Torsten Duwe 
---
 arch/powerpc/kernel/ftrace.c | 16 
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 310137f..e419c7b 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -511,20 +511,12 @@ void ftrace_replace_code(int enable)
}
 }
 
+/* Use the default ftrace_modify_all_code, but without
+ * stop_machine().
+ */
 void arch_ftrace_update_code(int command)
 {
-   if (command & FTRACE_UPDATE_CALLS)
-   ftrace_replace_code(1);
-   else if (command & FTRACE_DISABLE_CALLS)
-   ftrace_replace_code(0);
-
-   if (command & FTRACE_UPDATE_TRACE_FUNC)
-   ftrace_update_ftrace_func(ftrace_trace_function);
-
-   if (command & FTRACE_START_FUNC_RET)
-   ftrace_enable_ftrace_graph_caller();
-   else if (command & FTRACE_STOP_FUNC_RET)
-   ftrace_disable_ftrace_graph_caller();
+   ftrace_modify_all_code(command);
 }
 
 int __init ftrace_dyn_arch_init(void)
-- 
1.8.5.6

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[PATCH v5 8/9] Implement kernel live patching for ppc64le (ABIv2)

[Torsten Duwe]

  * create the appropriate files+functions
arch/powerpc/include/asm/livepatch.h
klp_check_compiler_support,
klp_arch_set_pc
arch/powerpc/kernel/livepatch.c with a stub for
klp_write_module_reloc
This is architecture-independent work in progress.
  * introduce a fixup in arch/powerpc/kernel/entry_64.S
for local calls that are becoming global due to live patching.
And of course do the main KLP thing: return to a maybe different
address, possibly altered by the live patching ftrace op.

Signed-off-by: Torsten Duwe 
---
 arch/powerpc/include/asm/livepatch.h | 45 +++
 arch/powerpc/kernel/entry_64.S   | 51 +---
 arch/powerpc/kernel/livepatch.c  | 38 +++
 3 files changed, 130 insertions(+), 4 deletions(-)
 create mode 100644 arch/powerpc/include/asm/livepatch.h
 create mode 100644 arch/powerpc/kernel/livepatch.c

diff --git a/arch/powerpc/include/asm/livepatch.h 
b/arch/powerpc/include/asm/livepatch.h
new file mode 100644
index 000..3200c11
--- /dev/null
+++ b/arch/powerpc/include/asm/livepatch.h
@@ -0,0 +1,45 @@
+/*
+ * livepatch.h - powerpc-specific Kernel Live Patching Core
+ *
+ * Copyright (C) 2015 SUSE
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see .
+ */
+#ifndef _ASM_POWERPC64_LIVEPATCH_H
+#define _ASM_POWERPC64_LIVEPATCH_H
+
+#include 
+#include 
+
+#ifdef CONFIG_LIVEPATCH
+static inline int klp_check_compiler_support(void)
+{
+#if !defined(_CALL_ELF) || _CALL_ELF != 2 || !defined(CC_USING_MPROFILE_KERNEL)
+   return 1;
+#endif
+   return 0;
+}
+
+extern int klp_write_module_reloc(struct module *mod, unsigned long type,
+  unsigned long loc, unsigned long value);
+
+static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
+{
+   regs->nip = ip;
+}
+#else
+#error Live patching support is disabled; check CONFIG_LIVEPATCH
+#endif
+
+#endif /* _ASM_POWERPC64_LIVEPATCH_H */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 294a9ca..09af904 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -1265,6 +1265,9 @@ _GLOBAL(ftrace_caller)
mflrr3
std r3, _NIP(r1)
std r3, 16(r1)
+#ifdef CONFIG_LIVEPATCH
+   mr  r14,r3  /* remember old NIP */
+#endif
subir3, r3, MCOUNT_INSN_SIZE
mfmsr   r4
std r4, _MSR(r1)
@@ -1281,7 +1284,10 @@ ftrace_call:
nop
 
ld  r3, _NIP(r1)
-   mtlrr3
+   mtctr   r3  /* prepare to jump there */
+#ifdef CONFIG_LIVEPATCH
+   cmpdr14,r3  /* has NIP been altered? */
+#endif
 
REST_8GPRS(0,r1)
REST_8GPRS(8,r1)
@@ -1294,6 +1300,27 @@ ftrace_call:
mtlrr12
mr  r2,r0   /* restore callee's TOC */
 
+#ifdef CONFIG_LIVEPATCH
+   beq+4f  /* likely(old_NIP == new_NIP) */
+
+   /* For a local call, restore this TOC after calling the patch function.
+* For a global call, it does not matter what we restore here,
+* since the global caller does its own restore right afterwards,
+* anyway. Just insert a KLP_return_helper frame in any case,
+* so a patch function can always count on the changed stack offsets.
+*/
+   stdur1,-32(r1)  /* open new mini stack frame */
+   std r0,24(r1)   /* save TOC now, unconditionally. */
+   bl  5f
+5: mflrr12
+   addir12,r12,(KLP_return_helper+4-.)@l
+   std r12,LRSAVE(r1)
+   mtlrr12
+   mfctr   r12 /* allow for TOC calculation in newfunc */
+   bctr
+4:
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
stdur1, -112(r1)
 .globl ftrace_graph_call
@@ -1303,15 +1330,31 @@ _GLOBAL(ftrace_graph_stub)
addir1, r1, 112
 #endif
 
-   mflrr0  /* move this LR to CTR */
-   mtctr   r0
-
ld  r0,LRSAVE(r1)   /* restore callee's lr at _mcount site */
mtlrr0
bctr/* jump after _mcount site */
 #endif /* CC_USING_MPROFILE_KERNEL */
 _GLOBAL(ftrace_stub)
blr
+
+#ifdef CONFIG_LIVEPATCH
+/* Helper function for local calls that are becoming global
+   due to live patching.
+   We can't 

[PATCH v5 5/9] ppc64 ftrace_with_regs: spare early boot and low level

[Torsten Duwe]

Using -mprofile-kernel on early boot code not only confuses the
checker but is also useless, as the infrastructure is not yet in
place. Proceed like with -pg (remove it from CFLAGS), equally with
time.o and ftrace itself.

  * arch/powerpc/kernel/Makefile:
- remove -mprofile-kernel from low level and boot code objects'
  CFLAGS for FUNCTION_TRACER configurations.

Signed-off-by: Torsten Duwe 
---
 arch/powerpc/kernel/Makefile | 12 ++--
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ba33693..0f417d5 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -16,14 +16,14 @@ endif
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
-CFLAGS_REMOVE_cputable.o = -pg -mno-sched-epilog
-CFLAGS_REMOVE_prom_init.o = -pg -mno-sched-epilog
-CFLAGS_REMOVE_btext.o = -pg -mno-sched-epilog
-CFLAGS_REMOVE_prom.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_cputable.o = -pg -mno-sched-epilog -mprofile-kernel
+CFLAGS_REMOVE_prom_init.o = -pg -mno-sched-epilog -mprofile-kernel
+CFLAGS_REMOVE_btext.o = -pg -mno-sched-epilog -mprofile-kernel
+CFLAGS_REMOVE_prom.o = -pg -mno-sched-epilog -mprofile-kernel
 # do not trace tracer code
-CFLAGS_REMOVE_ftrace.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_ftrace.o = -pg -mno-sched-epilog -mprofile-kernel
 # timers used by tracing
-CFLAGS_REMOVE_time.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_time.o = -pg -mno-sched-epilog -mprofile-kernel
 endif
 
 obj-y  := cputable.o ptrace.o syscalls.o \
-- 
1.8.5.6

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[PATCH v5 4/9] ppc64 ftrace_with_regs configuration variables

[Torsten Duwe]

  * Makefile:
- globally use -mprofile-kernel in case it's configured
  and available.
  * arch/powerpc/Kconfig / kernel/trace/Kconfig:
- declare that ppc64le HAVE_MPROFILE_KERNEL and
  HAVE_DYNAMIC_FTRACE_WITH_REGS, and use it.

Signed-off-by: Torsten Duwe 
---
 arch/powerpc/Kconfig  |  2 ++
 arch/powerpc/Makefile | 10 ++
 kernel/trace/Kconfig  |  5 +
 3 files changed, 17 insertions(+)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index db49e0d..89b1a2a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -97,8 +97,10 @@ config PPC
select OF_RESERVED_MEM
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_DYNAMIC_FTRACE
+   select HAVE_DYNAMIC_FTRACE_WITH_REGS if PPC64 && CPU_LITTLE_ENDIAN
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
+   select HAVE_MPROFILE_KERNEL if PPC64 && CPU_LITTLE_ENDIAN
select SYSCTL_EXCEPTION_TRACE
select ARCH_WANT_OPTIONAL_GPIOLIB
select VIRT_TO_BUS if !PPC64
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 96efd82..2f9b527 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -133,6 +133,16 @@ else
 CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64
 endif
 
+ifeq ($(CONFIG_PPC64),y)
+ifdef CONFIG_HAVE_MPROFILE_KERNEL
+CC_USING_MPROFILE_KERNEL := $(call cc-option,-mprofile-kernel)
+ifdef CC_USING_MPROFILE_KERNEL
+CC_FLAGS_FTRACE:= -pg $(CC_USING_MPROFILE_KERNEL)
+KBUILD_CPPFLAGS+= -DCC_USING_MPROFILE_KERNEL
+endif
+endif
+endif
+
 CFLAGS-$(CONFIG_CELL_CPU) += $(call cc-option,-mcpu=cell)
 CFLAGS-$(CONFIG_POWER4_CPU) += $(call cc-option,-mcpu=power4)
 CFLAGS-$(CONFIG_POWER5_CPU) += $(call cc-option,-mcpu=power5)
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e45db6b..a138f6d 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -52,6 +52,11 @@ config HAVE_FENTRY
help
  Arch supports the gcc options -pg with -mfentry
 
+config HAVE_MPROFILE_KERNEL
+   bool
+   help
+ Arch supports the gcc options -pg with -mprofile-kernel
+
 config HAVE_C_RECORDMCOUNT
bool
help
-- 
1.8.5.6

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [PATCH v2 1/5] printk/nmi: Generic solution for safe printk in NMI

[Petr Mladek]

On Wed 2015-12-02 13:45:16, Michael Ellerman wrote:
> On Fri, 2015-11-27 at 12:09 +0100, Petr Mladek wrote:
> 
> > printk() takes some locks and could not be used a safe way in NMI
> > context.
> > 
> > The chance of a deadlock is real especially when printing
> > stacks from all CPUs. This particular problem has been addressed
> > on x86 by the commit a9edc8809328 ("x86/nmi: Perform a safe NMI stack
> > trace on all CPUs").
> 
> ...
> 
> > diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c
> > new file mode 100644
> > index ..3989e13a0021
> > --- /dev/null
> > +++ b/kernel/printk/nmi.c
> > @@ -0,0 +1,200 @@
> 
> ...
> 
> > +
> > +struct nmi_seq_buf {
> > +   atomic_tlen;/* length of written data */
> > +   struct irq_work work;   /* IRQ work that flushes the buffer */
> > +   unsigned char   buffer[PAGE_SIZE - sizeof(atomic_t) -
> > +  sizeof(struct irq_work)];
> > +};
> > +static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
> 
> 
> PAGE_SIZE isn't always 4K.
> 
> On typical powerpc systems this will give you 128K, and on some 512K, which is
> probably not what we wanted.

Good point!

> The existing code just did:
> 
> #define NMI_BUF_SIZE   4096

I will change this to 8192. The 4kB were not enough in some cases.

Best Regards,
Petr
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [PATCH] crypto: talitos - add new crypto modes

[Herbert Xu]

On Tue, Dec 01, 2015 at 12:44:15PM +0100, Christophe Leroy wrote:
> This patch adds the following algorithms to the talitos driver:
> * ecb(aes)
> * ctr(aes)
> * ecb(des)
> * cbc(des)
> * ecb(des3_ede)
> 
> Signed-off-by: Christophe Leroy 

Patch applied.  Thanks.
-- 
Email: Herbert Xu 
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[PATCH v5 2/9] ppc64le FTRACE_WITH_REGS implementation

[Torsten Duwe]

Implement FTRACE_WITH_REGS for powerpc64, on ELF ABI v2.
Initial work started by Vojtech Pavlik, used with permission.

  * arch/powerpc/kernel/entry_64.S:
- Implement an effective ftrace_caller that works from
  within the kernel binary as well as from modules.
  * arch/powerpc/kernel/ftrace.c:
- be prepared to deal with ppc64 ELF ABI v2, especially
  calls to _mcount that result from gcc -mprofile-kernel
- a little more error verbosity
  * arch/powerpc/kernel/module_64.c:
- do not save the TOC pointer on the trampoline when the
  destination is ftrace_caller. This trampoline jump happens from
  a function prologue before a new stack frame is set up, so bad
  things may happen otherwise...
- relax is_module_trampoline() to recognise the modified
  trampoline.

Signed-off-by: Torsten Duwe 
---
 arch/powerpc/include/asm/ftrace.h |  5 +++
 arch/powerpc/kernel/entry_64.S| 77 +++
 arch/powerpc/kernel/ftrace.c  | 60 +++---
 arch/powerpc/kernel/module_64.c   | 25 -
 4 files changed, 160 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/ftrace.h 
b/arch/powerpc/include/asm/ftrace.h
index ef89b14..50ca758 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -46,6 +46,8 @@
 extern void _mcount(void);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+# define FTRACE_ADDR ((unsigned long)ftrace_caller)
+# define FTRACE_REGS_ADDR FTRACE_ADDR
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
/* reloction of mcount call site is the same as the address */
@@ -58,6 +60,9 @@ struct dyn_arch_ftrace {
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#endif
 #endif
 
 #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && 
!defined(__ASSEMBLY__)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index c3b2e75..294a9ca 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -1212,6 +1212,7 @@ _GLOBAL(_mcount)
mtlrr0
bctr
 
+#ifndef CC_USING_MPROFILE_KERNEL
 _GLOBAL_TOC(ftrace_caller)
/* Taken from output of objdump from lib64/glibc */
mflrr3
@@ -1233,6 +1234,82 @@ _GLOBAL(ftrace_graph_stub)
ld  r0, 128(r1)
mtlrr0
addir1, r1, 112
+#else
+_GLOBAL(ftrace_caller)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+   mflrr0
+   bl  2f
+2: mflrr12
+   mtlrr0
+   mr  r0,r2   /* save callee's TOC */
+   addis   r2,r12,(.TOC.-ftrace_caller-8)@ha
+   addir2,r2,(.TOC.-ftrace_caller-8)@l
+#else
+   mr  r0,r2
+#endif
+   ld  r12,LRSAVE(r1)  /* get caller's address */
+
+   stdur1,-SWITCH_FRAME_SIZE(r1)
+
+   std r12, _LINK(r1)
+   SAVE_8GPRS(0,r1)
+   std r0, 24(r1)  /* save TOC */
+   SAVE_8GPRS(8,r1)
+   SAVE_8GPRS(16,r1)
+   SAVE_8GPRS(24,r1)
+
+   addis   r3,r2,function_trace_op@toc@ha
+   addir3,r3,function_trace_op@toc@l
+   ld  r5,0(r3)
+
+   mflrr3
+   std r3, _NIP(r1)
+   std r3, 16(r1)
+   subir3, r3, MCOUNT_INSN_SIZE
+   mfmsr   r4
+   std r4, _MSR(r1)
+   mfctr   r4
+   std r4, _CTR(r1)
+   mfxer   r4
+   std r4, _XER(r1)
+   mr  r4, r12
+   addir6, r1 ,STACK_FRAME_OVERHEAD
+
+.globl ftrace_call
+ftrace_call:
+   bl  ftrace_stub
+   nop
+
+   ld  r3, _NIP(r1)
+   mtlrr3
+
+   REST_8GPRS(0,r1)
+   REST_8GPRS(8,r1)
+   REST_8GPRS(16,r1)
+   REST_8GPRS(24,r1)
+
+   addi r1, r1, SWITCH_FRAME_SIZE
+
+   ld  r12, LRSAVE(r1)  /* get caller's address */
+   mtlrr12
+   mr  r2,r0   /* restore callee's TOC */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+   stdur1, -112(r1)
+.globl ftrace_graph_call
+ftrace_graph_call:
+   b   ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+   addir1, r1, 112
+#endif
+
+   mflrr0  /* move this LR to CTR */
+   mtctr   r0
+
+   ld  r0,LRSAVE(r1)   /* restore callee's lr at _mcount site */
+   mtlrr0
+   bctr/* jump after _mcount site */
+#endif /* CC_USING_MPROFILE_KERNEL */
 _GLOBAL(ftrace_stub)
blr
 #else
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 080c525..310137f 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -61,8 +61,11 @@ ftrace_modify_code(unsigned long ip, unsigned int old, 
unsigned int new)
return -EFAULT;
 
/* Make sure it is what we expect it to be */
-   if (replaced != old)
+   if (replaced != old) {
+   pr_err("%p: replaced (%#x) != old (%#x)",
+   (void *)ip, 

[PATCH v5 1/9] ppc64 (le): prepare for -mprofile-kernel

[Torsten Duwe]

The gcc switch -mprofile-kernel, available for ppc64 on gcc > 4.8.5,
allows to call _mcount very early in the function, which low-level
ASM code and code patching functions need to consider.
Especially the link register and the parameter registers are still
alive and not yet saved into a new stack frame.

Signed-off-by: Torsten Duwe 
---
 arch/powerpc/kernel/entry_64.S  | 44 +++--
 arch/powerpc/kernel/ftrace.c| 12 +--
 arch/powerpc/kernel/module_64.c | 13 
 3 files changed, 65 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index a94f155..c3b2e75 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -1206,7 +1206,11 @@ _GLOBAL(enter_prom)
 #ifdef CONFIG_DYNAMIC_FTRACE
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
-   blr
+   mflrr0
+   mtctr   r0
+   ld  r0,LRSAVE(r1)
+   mtlrr0
+   bctr
 
 _GLOBAL_TOC(ftrace_caller)
/* Taken from output of objdump from lib64/glibc */
@@ -1262,13 +1266,28 @@ _GLOBAL(ftrace_stub)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 _GLOBAL(ftrace_graph_caller)
+#ifdef CC_USING_MPROFILE_KERNEL
+   /* with -mprofile-kernel, parameter regs are still alive at _mcount */
+   std r10, 104(r1)
+   std r9, 96(r1)
+   std r8, 88(r1)
+   std r7, 80(r1)
+   std r6, 72(r1)
+   std r5, 64(r1)
+   std r4, 56(r1)
+   std r3, 48(r1)
+   mfctr   r4  /* ftrace_caller has moved local addr here */
+   std r4, 40(r1)
+   mflrr3  /* ftrace_caller has restored LR from stack */
+#else
/* load r4 with local address */
ld  r4, 128(r1)
-   subir4, r4, MCOUNT_INSN_SIZE
 
/* Grab the LR out of the caller stack frame */
ld  r11, 112(r1)
ld  r3, 16(r11)
+#endif
+   subir4, r4, MCOUNT_INSN_SIZE
 
bl  prepare_ftrace_return
nop
@@ -1277,6 +1296,26 @@ _GLOBAL(ftrace_graph_caller)
 * prepare_ftrace_return gives us the address we divert to.
 * Change the LR in the callers stack frame to this.
 */
+
+#ifdef CC_USING_MPROFILE_KERNEL
+   mtlrr3
+
+   ld  r0, 40(r1)
+   mtctr   r0
+   ld  r10, 104(r1)
+   ld  r9, 96(r1)
+   ld  r8, 88(r1)
+   ld  r7, 80(r1)
+   ld  r6, 72(r1)
+   ld  r5, 64(r1)
+   ld  r4, 56(r1)
+   ld  r3, 48(r1)
+
+   addir1, r1, 112
+   mflrr0
+   std r0, LRSAVE(r1)
+   bctr
+#else
ld  r11, 112(r1)
std r3, 16(r11)
 
@@ -1284,6 +1323,7 @@ _GLOBAL(ftrace_graph_caller)
mtlrr0
addir1, r1, 112
blr
+#endif
 
 _GLOBAL(return_to_handler)
/* need to save return values */
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 44d4d8e..080c525 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -306,11 +306,19 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long 
addr)
 * The load offset is different depending on the ABI. For simplicity
 * just mask it out when doing the compare.
 */
+#ifndef CC_USING_MPROFILE_KERNEL
if ((op[0] != 0x4808) || ((op[1] & 0x) != 0xe841)) {
-   pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]);
+   pr_err("Unexpected call sequence at %p: %x %x\n",
+   ip, op[0], op[1]);
return -EINVAL;
}
-
+#else
+   /* look for patched "NOP" on ppc64 with -mprofile-kernel */
+   if (op[0] != 0x6000) {
+   pr_err("Unexpected call at %p: %x\n", ip, op[0]);
+   return -EINVAL;
+   }
+#endif
/* If we never set up a trampoline to ftrace_caller, then bail */
if (!rec->arch.mod->arch.tramp) {
pr_err("No ftrace trampoline\n");
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 6838451..5312cd4 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -475,6 +475,19 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
 static int restore_r2(u32 *instruction, struct module *me)
 {
if (*instruction != PPC_INST_NOP) {
+#ifdef CC_USING_MPROFILE_KERNEL
+   /* -mprofile_kernel sequence starting with
+* mflr r0; std r0, LRSAVE(r1)
+*/
+   if (instruction[-3] == 0x7c0802a6 &&
+   instruction[-2] == 0xf8010010) {
+   /* Nothing to be done here, it's an _mcount
+* call location and r2 will have to be
+* restored in the _mcount function.
+*/
+   return 1;
+   };
+#endif
pr_err("%s: Expect noop after relocate, got 

[PATCH v5 7/9] ppc64 ftrace: disable profiling for some files

[Torsten Duwe]

This patch complements the "notrace" attribute for selected functions.
It adds -mprofile-kernel to the cc flags to be stripped from the command
line for code-patching.o and feature-fixups.o, in addition to "-pg"

Signed-off-by: Torsten Duwe 
---
 arch/powerpc/lib/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index a47e142..98e22b2 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -6,8 +6,8 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ccflags-$(CONFIG_PPC64):= $(NO_MINIMAL_TOC)
 
-CFLAGS_REMOVE_code-patching.o = -pg
-CFLAGS_REMOVE_feature-fixups.o = -pg
+CFLAGS_REMOVE_code-patching.o = -pg -mprofile-kernel
+CFLAGS_REMOVE_feature-fixups.o = -pg -mprofile-kernel
 
 obj-y += string.o alloc.o crtsavres.o ppc_ksyms.o code-patching.o \
 feature-fixups.o
-- 
1.8.5.6

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [PATCH v2 5/5] printk/nmi: Increase the size of the temporary buffer

[Petr Mladek]

On Wed 2015-12-02 16:20:41, David Laight wrote:
> From: yalin wang
> > Sent: 30 November 2015 16:42
> > > On Nov 27, 2015, at 19:09, Petr Mladek  wrote:
> > >
> > > Testing has shown that the backtrace sometimes does not fit
> > > into the 4kB temporary buffer that is used in NMI context.
> > >
> > > The warnings are gone when I double the temporary buffer size.
> 
> You are wasting a lot of memory for something that is infrequently used.
> There ought to be some way of copying partial tracebacks into the
> main buffer.

I have already tried to use a separate ring buffer that might be
shared between all CPUs. But it was rejected because it was too
complex. See
http://thread.gmane.org/gmane.linux.kernel/1700059/focus=1700066

If we would want to crate a lockless access to the main ring
buffer, we would end up with something like
kernel/trace/ring_buffer.c. It is even more complicated.
And reading of the messages is pretty slow.

Note that we already have this buffer allocated on x86 and arm.
It is used there for printing backtrace from all CPUs.
This patchset makes it usable for all NMI messages.

But I'll make the size configurable in the next version.

Thanks for review,
Petr
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [PATCH] of: Fix comparison of reserved memory regions

[Mitchel Humpherys]

On Wed, Nov 18 2015 at 09:46:38 PM, Michael Ellerman  
wrote:
> In order to check for overlapping reserved memory regions, we first need
> to sort the array of memory regions. This is implemented using sort(),
> and a custom comparison function __rmem_cmp().
>
> Unfortunatley __rmem_cmp() doesn't work in all cases. Because the two
> base values are phys_addr_t, they may be u64 on some platforms, in which
> case subtracting one from the other and then (implicitly) casting to int
> does not give us the -ve/0/+ve value we need.
>
> This leads to incorrect reports about overlaps, eg:
>
>   ibm,slw-image@1ffe60 (0x001ffe60--0x001ffe70) overlaps 
> with
>   ibm,firmware-allocs-memory@10 
> (0x0010--0x001000dc0200)
>
> Fix it by just doing the standard double if and return 0 logic.
>
> Fixes: ae1add247bf8 ("of: Check for overlap in reserved memory regions")
> Signed-off-by: Michael Ellerman 
> ---
>  drivers/of/of_reserved_mem.c | 8 +++-
>  1 file changed, 7 insertions(+), 1 deletion(-)

Woops, thanks.

Tested-by: Mitchel Humpherys 

-Mitch

-- 
Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [PATCH v2 3/5] printk/nmi: Try hard to print Oops message in NMI context

[Russell King - ARM Linux]

On Fri, Dec 04, 2015 at 04:27:09PM +0100, Petr Mladek wrote:
> On Tue 2015-12-01 23:44:37, Russell King - ARM Linux wrote:
> > On Fri, Nov 27, 2015 at 12:09:30PM +0100, Petr Mladek wrote:
> > > What we can do, though, is to zap all printk locks. We already do this
> > > when a printk recursion is detected. This should be safe because
> > > the system is crashing and there shouldn't be any printk caller
> > > that would cause the deadlock.
> > 
> > What about serial consoles which may call out to subsystems like the
> > clk subsystem to enable a clock, which would want to take their own
> > spinlocks in addition to the serial console driver?
> 
> Yes, there might be more locks used by the serial console but I do
> not know how to handle them all easily. IMHO, this patch is just better
> than nothing.

I have a slightly different view...

> > I don't see bust_spinlocks() dealing with any of these locks, so IMHO
> > trying to make this work in NMI context strikes me as making the
> > existing solution more unreliable on ARM systems.
> 
> bust_spinlocks() calls printk_nmi_flush() that would call printk()
> that would zap "lockbuf_lock" and "console_sem" when in Oops and NMI.
> Yes, there might be more locks blocked but we try to break at least
> the first two walls. Also zapping is allowed only once per 30 seconds,
> see zap_locks(). Why do you think that it might make things more
> unreliable, please?

Take the scenario where CPU1 is in the middle of a printk(), and is
holding its lock.

CPU0 comes along and decides to trigger a NMI backtrace.  This sends
a NMI to CPU1, which takes it in the middle of the serial console
output.

With the existing solution, the NMI output will be written to the
temporary buffer, and CPU1 has finished handling the NMI it resumes
the serial console output, eventually dropping the lock.  That then
allows CPU0 to print the contents of all buffers, and we get NMI
printk output.

With this solution, as I understand it, we'll instead end up with
CPU1's printk trying to output direct to the console, and although
we've busted a couple of locks, we won't have busted the serial
console locks, so CPU1 will deadlock - and that will stop any output
what so ever.

If this is correct, then the net result is that we go from NMI with
serial console producing output to NMI with serial console being
less reliable at producing output.

-- 
FTTC broadband for 0.8mile line: currently at 9.6Mbps down 400kbps up
according to speedtest.net.
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: kernel BUG at drivers/scsi/scsi_lib.c:1096!

[Takashi Iwai]

On Fri, 04 Dec 2015 18:02:58 +0100,
Jens Axboe wrote:
> 
> On 12/04/2015 09:59 AM, Takashi Iwai wrote:
> > On Wed, 25 Nov 2015 20:01:47 +0100,
> > Hannes Reinecke wrote:
> >>
> >> On 11/25/2015 07:01 PM, Mike Snitzer wrote:
> >>> On Wed, Nov 25 2015 at  4:04am -0500,
> >>> Hannes Reinecke  wrote:
> >>>
>  On 11/20/2015 04:28 PM, Ewan Milne wrote:
> > On Fri, 2015-11-20 at 15:55 +0100, Hannes Reinecke wrote:
> >> Can't we have a joint effort here?
> >> I've been spending a _LOT_ of time trying to debug things here, but
> >> none of the ideas I've come up with have been able to fix anything.
> >
> > Yes.  I'm not the one primarily looking at it, and we don't have a
> > reproducer in-house.  We just have the one dump right now.
> >
> >>
> >> I'm almost tempted to increase the count from scsi_alloc_sgtable()
> >> by one and be done with ...
> >>
> >
> > That might not fix it if it is a problem with the merge code, though.
> >
>  And indeed, it doesn't.
> >>>
> >>> How did you arrive at that?  Do you have a reproducer now?
> >>>
> >> Not a reproducer, but several dumps for analysis.
> >>
>  Seems I finally found the culprit.
> 
>  What happens is this:
>  We have two paths, with these seg_boundary_masks:
> 
>  path-1:seg_boundary_mask = 65535,
>  path-2:seg_boundary_mask = 4294967295,
> 
>  consequently the DM request queue has this:
> 
>  md-1:seg_boundary_mask = 65535,
> 
>  What happens now is that a request is being formatted, and sent
>  to path 2. During submission req->nr_phys_segments is formatted
>  with the limits of path 2, arriving at a count of 3.
>  Now the request gets retried on path 1, but as the NOMERGE request
>  flag is set req->nr_phys_segments is never updated.
>  But blk_rq_map_sg() ignores all counters, and just uses the
>  bi_vec directly, resulting in a count of 4 -> boom.
> 
>  So the culprit here is the NOMERGE flag,
> >>>
> >>> NOMERGE is always set in __blk_rq_prep_clone() for cloned requests.
> >>>
> >> Yes.
> >>
>  which is evaluated via
>  ->dm_dispatch_request()
>  ->blk_insert_cloned_request()
>    ->blk_rq_check_limits()
> >>>
> >>> blk_insert_cloned_request() is the only caller of blk_rq_check_limits();
> >>> anyway after reading your mail I'm still left wondering if your proposed
> >>> patch is correct.
> >>>
>  If the above assessment is correct, the following patch should
>  fix it:
> 
>  diff --git a/block/blk-core.c b/block/blk-core.c
>  index 801ced7..12cccd6 100644
>  --- a/block/blk-core.c
>  +++ b/block/blk-core.c
>  @@ -1928,7 +1928,7 @@ EXPORT_SYMBOL(submit_bio);
>  */
> int blk_rq_check_limits(struct request_queue *q, struct request *rq)
> {
>  -   if (!rq_mergeable(rq))
>  +   if (rq->cmd_type != REQ_TYPE_FS)
>    return 0;
> 
>    if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q,
>  rq->cmd_flags)) {
> 
> 
>  Mike? Jens?
>  Can you comment on it?
> >>>
> >>> You're not explaining the actual change in the patch very well; I think
> >>> you're correct but you're leaving the justification as an exercise to
> >>> the reviewer:
> >>>
> >>> blk_rq_check_limits() will call blk_recalc_rq_segments() after the
> >>> !rq_mergeable() check but you're saying for this case in question we
> >>> never get there -- due to the cloned request having NOMERGE set.
> >>>
> >>> So in blk_rq_check_limits() you've unrolled rq_mergeable() and
> >>> open-coded the lone remaining check (rq->cmd_type != REQ_TYPE_FS)
> >>>
> >>> I agree that the (rq->cmd_flags & REQ_NOMERGE_FLAGS) check in
> >>> the blk_insert_cloned_request() call-chain (via rq_mergeable()) makes no
> >>> sense for cloned requests that always have NOMERGE set.
> >>>
> >>> So you're saying that by having blk_rq_check_limits() go on to call
> >>> blk_recalc_rq_segments() this bug will be fixed?
> >>>
> >> That is the idea.
> >>
> >> I've already established that in all instances I have seen so far
> >> req->nr_phys_segments is _less_ than req->bio->bi_phys_segments.
> >>
> >> As it turns out, req->nr_phys_segemnts _would_ have been updated in
> >> blk_rq_check_limits(), but isn't due to the NOMERGE flag being set
> >> for the cloned request.
> >> So each cloned request inherits the values from the original request,
> >> despite the fact that req->nr_phys_segments _has_ to be evaluated in
> >> the final request_queue context, as the queue limits _might_ be
> >> different from the original (merged) queue limits of the multipath
> >> request queue.
> >>
> >>> BTW, I think blk_rq_check_limits()'s export should be removed and the
> >>> function made static and renamed to blk_clone_rq_check_limits(), again:
> >>> blk_insert_cloned_request() is the only caller of blk_rq_check_limits()
> >>>
> >> 

Re: more POLL... fun

[Arnd Bergmann]

On Friday 04 December 2015 15:21:33 Al Viro wrote:
> On Fri, Dec 04, 2015 at 10:16:50AM +0100, Arnd Bergmann wrote:
> 
> > I don't remember why we put in fasync support, but I have checked the libspe
> > implementation and found that it doesn't use it (not a big surprise there).
> > It always uses epoll() to get notifications from spufs, and based on your
> > explanation I assume everything else (there may have been one or two users
> > that used the low-level interfaces rather than libspe) did too.
> 
> OK...  So should we just rip ->{mfc,ibox,wbox}_fasync out, along with all
> three kill_fasync() and ->fasync() instances in there?  We obviously need to
> leave spufs_{mfc,ibox,wbox}_callback() in place for the sake of those
> wake_up_all(>{mfc,ibox,wbox}_wq); in them...
> 
> I mean, fasync in there obviously never been used at all - it never delivered
> a single SIGIO, and the first user to try would get the BUG_ON() in fcntl.c
> instead.  Since nobody complained in more than 10 years...

Yes, I think that would be best. Do you want me to send that patch, or do
you prefer to do it yourself? In theory that patch should also go into stable
kernels, but I suspect nobody who still owns a machine that is able to run
this code will ever upgrade to a stable release, so we probably don't need
that.

Arnd
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: more POLL... fun

[Al Viro]

On Fri, Dec 04, 2015 at 06:13:54PM +0100, Arnd Bergmann wrote:

> Yes, I think that would be best. Do you want me to send that patch, or do
> you prefer to do it yourself? In theory that patch should also go into stable
> kernels, but I suspect nobody who still owns a machine that is able to run
> this code will ever upgrade to a stable release, so we probably don't need
> that.

Probably better if it goes through ppc tree - the only relationship it has
to VFS is broken calls of kill_fasync() in now-removed code...  Something
like this, perhaps?

[spufs] get rid of broken fasync stuff
 
In all the years it's been in the tree it had never been used by
anything - it would instantly trigger BUG_ON() in fs/fcntl.c due
to bogus band argument passed to kill_fasync().  Since nobody
had ever used it in ten years, let's just rip it out and be
done with that.

Signed-off-by: Al Viro 
---

diff --git a/arch/powerpc/platforms/cell/spufs/file.c 
b/arch/powerpc/platforms/cell/spufs/file.c
index 5038fd5..88b7613 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -686,23 +686,13 @@ size_t spu_ibox_read(struct spu_context *ctx, u32 *data)
return ctx->ops->ibox_read(ctx, data);
 }
 
-static int spufs_ibox_fasync(int fd, struct file *file, int on)
-{
-   struct spu_context *ctx = file->private_data;
-
-   return fasync_helper(fd, file, on, >ibox_fasync);
-}
-
 /* interrupt-level ibox callback function. */
 void spufs_ibox_callback(struct spu *spu)
 {
struct spu_context *ctx = spu->ctx;
 
-   if (!ctx)
-   return;
-
-   wake_up_all(>ibox_wq);
-   kill_fasync(>ibox_fasync, SIGIO, POLLIN);
+   if (ctx)
+   wake_up_all(>ibox_wq);
 }
 
 /*
@@ -797,7 +787,6 @@ static const struct file_operations spufs_ibox_fops = {
.open   = spufs_pipe_open,
.read   = spufs_ibox_read,
.poll   = spufs_ibox_poll,
-   .fasync = spufs_ibox_fasync,
.llseek = no_llseek,
 };
 
@@ -835,26 +824,13 @@ size_t spu_wbox_write(struct spu_context *ctx, u32 data)
return ctx->ops->wbox_write(ctx, data);
 }
 
-static int spufs_wbox_fasync(int fd, struct file *file, int on)
-{
-   struct spu_context *ctx = file->private_data;
-   int ret;
-
-   ret = fasync_helper(fd, file, on, >wbox_fasync);
-
-   return ret;
-}
-
 /* interrupt-level wbox callback function. */
 void spufs_wbox_callback(struct spu *spu)
 {
struct spu_context *ctx = spu->ctx;
 
-   if (!ctx)
-   return;
-
-   wake_up_all(>wbox_wq);
-   kill_fasync(>wbox_fasync, SIGIO, POLLOUT);
+   if (ctx)
+   wake_up_all(>wbox_wq);
 }
 
 /*
@@ -947,7 +923,6 @@ static const struct file_operations spufs_wbox_fops = {
.open   = spufs_pipe_open,
.write  = spufs_wbox_write,
.poll   = spufs_wbox_poll,
-   .fasync = spufs_wbox_fasync,
.llseek = no_llseek,
 };
 
@@ -1523,28 +1498,8 @@ void spufs_mfc_callback(struct spu *spu)
 {
struct spu_context *ctx = spu->ctx;
 
-   if (!ctx)
-   return;
-
-   wake_up_all(>mfc_wq);
-
-   pr_debug("%s %s\n", __func__, spu->name);
-   if (ctx->mfc_fasync) {
-   u32 free_elements, tagstatus;
-   unsigned int mask;
-
-   /* no need for spu_acquire in interrupt context */
-   free_elements = ctx->ops->get_mfc_free_elements(ctx);
-   tagstatus = ctx->ops->read_mfc_tagstatus(ctx);
-
-   mask = 0;
-   if (free_elements & 0x)
-   mask |= POLLOUT;
-   if (tagstatus & ctx->tagwait)
-   mask |= POLLIN;
-
-   kill_fasync(>mfc_fasync, SIGIO, mask);
-   }
+   if (ctx)
+   wake_up_all(>mfc_wq);
 }
 
 static int spufs_read_mfc_tagstatus(struct spu_context *ctx, u32 *status)
@@ -1806,13 +1761,6 @@ static int spufs_mfc_fsync(struct file *file, loff_t 
start, loff_t end, int data
return err;
 }
 
-static int spufs_mfc_fasync(int fd, struct file *file, int on)
-{
-   struct spu_context *ctx = file->private_data;
-
-   return fasync_helper(fd, file, on, >mfc_fasync);
-}
-
 static const struct file_operations spufs_mfc_fops = {
.open= spufs_mfc_open,
.release = spufs_mfc_release,
@@ -1821,7 +1769,6 @@ static const struct file_operations spufs_mfc_fops = {
.poll= spufs_mfc_poll,
.flush   = spufs_mfc_flush,
.fsync   = spufs_mfc_fsync,
-   .fasync  = spufs_mfc_fasync,
.mmap= spufs_mfc_mmap,
.llseek  = no_llseek,
 };
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h 
b/arch/powerpc/platforms/cell/spufs/spufs.h
index bcfd6f0..aac7339 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -102,9 +102,6 @@ struct spu_context {
wait_queue_head_t stop_wq;
wait_queue_head_t 

Re: more POLL... fun

[Arnd Bergmann]

On Friday 04 December 2015 17:30:31 Al Viro wrote:
> On Fri, Dec 04, 2015 at 06:13:54PM +0100, Arnd Bergmann wrote:
> 
> > Yes, I think that would be best. Do you want me to send that patch, or do
> > you prefer to do it yourself? In theory that patch should also go into 
> > stable
> > kernels, but I suspect nobody who still owns a machine that is able to run
> > this code will ever upgrade to a stable release, so we probably don't need
> > that.
> 
> Probably better if it goes through ppc tree - the only relationship it has
> to VFS is broken calls of kill_fasync() in now-removed code...

Right.

>  Something like this, perhaps?
>
> [spufs] get rid of broken fasync stuff
>  
> In all the years it's been in the tree it had never been used by
> anything - it would instantly trigger BUG_ON() in fs/fcntl.c due
> to bogus band argument passed to kill_fasync().  Since nobody
> had ever used it in ten years, let's just rip it out and be
> done with that.
> 
> Signed-off-by: Al Viro 
> ---

Looks all good, thanks!

Acked-by: Arnd Bergmann 
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: kernel BUG at drivers/scsi/scsi_lib.c:1096!

[Takashi Iwai]

On Wed, 25 Nov 2015 20:01:47 +0100,
Hannes Reinecke wrote:
> 
> On 11/25/2015 07:01 PM, Mike Snitzer wrote:
> > On Wed, Nov 25 2015 at  4:04am -0500,
> > Hannes Reinecke  wrote:
> >
> >> On 11/20/2015 04:28 PM, Ewan Milne wrote:
> >>> On Fri, 2015-11-20 at 15:55 +0100, Hannes Reinecke wrote:
>  Can't we have a joint effort here?
>  I've been spending a _LOT_ of time trying to debug things here, but
>  none of the ideas I've come up with have been able to fix anything.
> >>>
> >>> Yes.  I'm not the one primarily looking at it, and we don't have a
> >>> reproducer in-house.  We just have the one dump right now.
> >>>
> 
>  I'm almost tempted to increase the count from scsi_alloc_sgtable()
>  by one and be done with ...
> 
> >>>
> >>> That might not fix it if it is a problem with the merge code, though.
> >>>
> >> And indeed, it doesn't.
> >
> > How did you arrive at that?  Do you have a reproducer now?
> >
> Not a reproducer, but several dumps for analysis.
> 
> >> Seems I finally found the culprit.
> >>
> >> What happens is this:
> >> We have two paths, with these seg_boundary_masks:
> >>
> >> path-1:seg_boundary_mask = 65535,
> >> path-2:seg_boundary_mask = 4294967295,
> >>
> >> consequently the DM request queue has this:
> >>
> >> md-1:seg_boundary_mask = 65535,
> >>
> >> What happens now is that a request is being formatted, and sent
> >> to path 2. During submission req->nr_phys_segments is formatted
> >> with the limits of path 2, arriving at a count of 3.
> >> Now the request gets retried on path 1, but as the NOMERGE request
> >> flag is set req->nr_phys_segments is never updated.
> >> But blk_rq_map_sg() ignores all counters, and just uses the
> >> bi_vec directly, resulting in a count of 4 -> boom.
> >>
> >> So the culprit here is the NOMERGE flag,
> >
> > NOMERGE is always set in __blk_rq_prep_clone() for cloned requests.
> >
> Yes.
> 
> >> which is evaluated via
> >> ->dm_dispatch_request()
> >>->blk_insert_cloned_request()
> >>  ->blk_rq_check_limits()
> >
> > blk_insert_cloned_request() is the only caller of blk_rq_check_limits();
> > anyway after reading your mail I'm still left wondering if your proposed
> > patch is correct.
> >
> >> If the above assessment is correct, the following patch should
> >> fix it:
> >>
> >> diff --git a/block/blk-core.c b/block/blk-core.c
> >> index 801ced7..12cccd6 100644
> >> --- a/block/blk-core.c
> >> +++ b/block/blk-core.c
> >> @@ -1928,7 +1928,7 @@ EXPORT_SYMBOL(submit_bio);
> >>*/
> >>   int blk_rq_check_limits(struct request_queue *q, struct request *rq)
> >>   {
> >> -   if (!rq_mergeable(rq))
> >> +   if (rq->cmd_type != REQ_TYPE_FS)
> >>  return 0;
> >>
> >>  if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q,
> >> rq->cmd_flags)) {
> >>
> >>
> >> Mike? Jens?
> >> Can you comment on it?
> >
> > You're not explaining the actual change in the patch very well; I think
> > you're correct but you're leaving the justification as an exercise to
> > the reviewer:
> >
> > blk_rq_check_limits() will call blk_recalc_rq_segments() after the
> > !rq_mergeable() check but you're saying for this case in question we
> > never get there -- due to the cloned request having NOMERGE set.
> >
> > So in blk_rq_check_limits() you've unrolled rq_mergeable() and
> > open-coded the lone remaining check (rq->cmd_type != REQ_TYPE_FS)
> >
> > I agree that the (rq->cmd_flags & REQ_NOMERGE_FLAGS) check in
> > the blk_insert_cloned_request() call-chain (via rq_mergeable()) makes no
> > sense for cloned requests that always have NOMERGE set.
> >
> > So you're saying that by having blk_rq_check_limits() go on to call
> > blk_recalc_rq_segments() this bug will be fixed?
> >
> That is the idea.
> 
> I've already established that in all instances I have seen so far
> req->nr_phys_segments is _less_ than req->bio->bi_phys_segments.
> 
> As it turns out, req->nr_phys_segemnts _would_ have been updated in
> blk_rq_check_limits(), but isn't due to the NOMERGE flag being set
> for the cloned request.
> So each cloned request inherits the values from the original request,
> despite the fact that req->nr_phys_segments _has_ to be evaluated in
> the final request_queue context, as the queue limits _might_ be 
> different from the original (merged) queue limits of the multipath
> request queue.
> 
> > BTW, I think blk_rq_check_limits()'s export should be removed and the
> > function made static and renamed to blk_clone_rq_check_limits(), again:
> > blk_insert_cloned_request() is the only caller of blk_rq_check_limits()
> >
> Actually, seeing Jens' last comment the check for REQ_TYPE_FS is 
> pointless, too, so we might as well remove the entire if-clause.
> 
> > Seems prudent to make that change now to be clear that this code is only
> > used by cloned requests.
> >
> Yeah, that would make sense. I'll be preparing a patch.
> With a more detailed description :-)

Do we have already a fix?  Right now 

Re: [PATCH v2 1/5] printk/nmi: Generic solution for safe printk in NMI

[Petr Mladek]

On Wed 2015-12-02 00:24:49, Jiri Kosina wrote:
> On Fri, 27 Nov 2015, Petr Mladek wrote:
> 
> > MN10300 has its own implementation for entering and exiting NMI 
> > handlers. It does not call nmi_enter() and nmi_exit(). Please, find 
> > below an updated patch that adds printk_nmi_enter() and 
> > printk_nmi_exit() to the custom entry points. Then we could add HAVE_NMI 
> > to arch/mn10300/Kconfig and avoid the above warning.
> 
> Hmm, so what exactly would go wrong if MN10300 (whatever that architecture 
> is) would call nmi_enter() and nmi_exit() at the places where it's 
> starting and finishing NMI handler?
> 
> >From a cursory look, it seems like most (if not all) of the things called 
> from nmi_{enter,exit}() would be nops there anyway.

Good point. Max mentioned in the other main that the NMI handler
should follow the NMI ruler. I do not why it could not work.
In fact, it might improve things, e.g. nmi_enter() blocks
recursive NMIs.

I think that it will move it into a separate patch, thought.

Best Regards,
Petr
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: kernel BUG at drivers/scsi/scsi_lib.c:1096!

[Jens Axboe]

On 12/04/2015 09:59 AM, Takashi Iwai wrote:

On Wed, 25 Nov 2015 20:01:47 +0100,
Hannes Reinecke wrote:


On 11/25/2015 07:01 PM, Mike Snitzer wrote:

On Wed, Nov 25 2015 at  4:04am -0500,
Hannes Reinecke  wrote:


On 11/20/2015 04:28 PM, Ewan Milne wrote:

On Fri, 2015-11-20 at 15:55 +0100, Hannes Reinecke wrote:

Can't we have a joint effort here?
I've been spending a _LOT_ of time trying to debug things here, but
none of the ideas I've come up with have been able to fix anything.


Yes.  I'm not the one primarily looking at it, and we don't have a
reproducer in-house.  We just have the one dump right now.



I'm almost tempted to increase the count from scsi_alloc_sgtable()
by one and be done with ...



That might not fix it if it is a problem with the merge code, though.


And indeed, it doesn't.


How did you arrive at that?  Do you have a reproducer now?


Not a reproducer, but several dumps for analysis.


Seems I finally found the culprit.

What happens is this:
We have two paths, with these seg_boundary_masks:

path-1:seg_boundary_mask = 65535,
path-2:seg_boundary_mask = 4294967295,

consequently the DM request queue has this:

md-1:seg_boundary_mask = 65535,

What happens now is that a request is being formatted, and sent
to path 2. During submission req->nr_phys_segments is formatted
with the limits of path 2, arriving at a count of 3.
Now the request gets retried on path 1, but as the NOMERGE request
flag is set req->nr_phys_segments is never updated.
But blk_rq_map_sg() ignores all counters, and just uses the
bi_vec directly, resulting in a count of 4 -> boom.

So the culprit here is the NOMERGE flag,


NOMERGE is always set in __blk_rq_prep_clone() for cloned requests.


Yes.


which is evaluated via
->dm_dispatch_request()
->blk_insert_cloned_request()
  ->blk_rq_check_limits()


blk_insert_cloned_request() is the only caller of blk_rq_check_limits();
anyway after reading your mail I'm still left wondering if your proposed
patch is correct.


If the above assessment is correct, the following patch should
fix it:

diff --git a/block/blk-core.c b/block/blk-core.c
index 801ced7..12cccd6 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1928,7 +1928,7 @@ EXPORT_SYMBOL(submit_bio);
*/
   int blk_rq_check_limits(struct request_queue *q, struct request *rq)
   {
-   if (!rq_mergeable(rq))
+   if (rq->cmd_type != REQ_TYPE_FS)
  return 0;

  if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q,
rq->cmd_flags)) {


Mike? Jens?
Can you comment on it?


You're not explaining the actual change in the patch very well; I think
you're correct but you're leaving the justification as an exercise to
the reviewer:

blk_rq_check_limits() will call blk_recalc_rq_segments() after the
!rq_mergeable() check but you're saying for this case in question we
never get there -- due to the cloned request having NOMERGE set.

So in blk_rq_check_limits() you've unrolled rq_mergeable() and
open-coded the lone remaining check (rq->cmd_type != REQ_TYPE_FS)

I agree that the (rq->cmd_flags & REQ_NOMERGE_FLAGS) check in
the blk_insert_cloned_request() call-chain (via rq_mergeable()) makes no
sense for cloned requests that always have NOMERGE set.

So you're saying that by having blk_rq_check_limits() go on to call
blk_recalc_rq_segments() this bug will be fixed?


That is the idea.

I've already established that in all instances I have seen so far
req->nr_phys_segments is _less_ than req->bio->bi_phys_segments.

As it turns out, req->nr_phys_segemnts _would_ have been updated in
blk_rq_check_limits(), but isn't due to the NOMERGE flag being set
for the cloned request.
So each cloned request inherits the values from the original request,
despite the fact that req->nr_phys_segments _has_ to be evaluated in
the final request_queue context, as the queue limits _might_ be
different from the original (merged) queue limits of the multipath
request queue.


BTW, I think blk_rq_check_limits()'s export should be removed and the
function made static and renamed to blk_clone_rq_check_limits(), again:
blk_insert_cloned_request() is the only caller of blk_rq_check_limits()


Actually, seeing Jens' last comment the check for REQ_TYPE_FS is
pointless, too, so we might as well remove the entire if-clause.


Seems prudent to make that change now to be clear that this code is only
used by cloned requests.


Yeah, that would make sense. I'll be preparing a patch.
With a more detailed description :-)


Do we have already a fix?  Right now I got (likely) this kernel BUG()
on the almost latest Linus tree (commit 25364a9e54fb8296).  It
happened while I started a KVM right after a fresh boot.  The machine
paniced even before that, so I hit this twice today.


Update to the tree as-of yesterday (or today) and it should work. 
25364a9e54fb8296 doesn't include the latest block fixes that were sent 
in yesterday, that should fix it. You need commit a88d32af18b8 or newer.


--

Re: [PATCH v3 1/6] powerpc/mm: any thread in one core can be the first to setup TLB1

[Scott Wood]

On Fri, 2015-12-04 at 11:04 +0300, Denis Kirjanov wrote:
> On 12/3/15, Scott Wood  wrote:
> > On Wed, 2015-12-02 at 15:12 +0300, Denis Kirjanov wrote:
> > > On 11/20/15, Chenhui Zhao  wrote:
> > > > On e6500, in the case of cpu hotplug, either thread in one core
> > > > may be the first thread initilzing the TLB1. The subsequent threads
> > > > must not setup it again.
> > > > 
> > > > The code is derived from the comment of Scott Wood.
> > > > 
> > > > Signed-off-by: Chenhui Zhao 
> > > > ---
> > > >  arch/powerpc/include/asm/cputhreads.h | 7 +++
> > > >  arch/powerpc/mm/tlb_nohash.c  | 4 +---
> > > >  2 files changed, 8 insertions(+), 3 deletions(-)
> > > > 
> > > > diff --git a/arch/powerpc/include/asm/cputhreads.h
> > > > b/arch/powerpc/include/asm/cputhreads.h
> > > > index ba42e46..b56cece 100644
> > > > --- a/arch/powerpc/include/asm/cputhreads.h
> > > > +++ b/arch/powerpc/include/asm/cputhreads.h
> > > > @@ -94,6 +94,13 @@ static inline int cpu_last_thread_sibling(int cpu)
> > > > return cpu | (threads_per_core - 1);
> > > >  }
> > > > 
> > > > +static inline u32 get_tensr(void)
> > > > +{
> > > > +   if (cpu_has_feature(CPU_FTR_SMT))
> > > > +   return mfspr(SPRN_TENSR);
> > > > +   else
> > > > +   return 1;
> > > > +}
> > > If i get it right, SPRN_TENSR used in the code only if CONFIG_PPC64
> > > is defined. Then we can make it noop on ppc32.
> > 
> > Please don't.  It accomplishes nothing other than adding an obstacle to
> > supporting this on ppc32.
> 
> The idea is make it noop since the function defined in header file and
> some core parts include it like:
> 
> arch/powerpc/kernel/smp.c
> arch/powerpc/kernel/setup-common.c

What does that have to do with making it a no-op on 32-bit?  I understand
ifdeffing on CONFIG_BOOKE due to the build issue, but not CONFIG_PPC64.

-Scott

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [net-next v5 2/8] dpaa_eth: add support for DPAA Ethernet

[David Miller]

From: Madalin Bucur 
Date: Thu, 3 Dec 2015 15:49:43 +0200

> @@ -0,0 +1,22 @@
> +menuconfig FSL_DPAA_ETH
> + tristate "DPAA Ethernet"
> + depends on FSL_SOC && FSL_BMAN && FSL_QMAN && FSL_FMAN
> + select PHYLIB
> + select FSL_FMAN_MAC

I do not see the FSL_FMAN_MAC Kconfig symbol defined anywhere in the
tree.
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [net-next v5 2/8] dpaa_eth: add support for DPAA Ethernet

[Joe Perches]

On Fri, 2015-12-04 at 14:55 -0500, David Miller wrote:
> From: Madalin Bucur 
> Date: Thu, 3 Dec 2015 15:49:43 +0200
> 
> > @@ -0,0 +1,22 @@
> > +menuconfig FSL_DPAA_ETH
> > + tristate "DPAA Ethernet"
> > + depends on FSL_SOC && FSL_BMAN && FSL_QMAN && FSL_FMAN
> > + select PHYLIB
> > + select FSL_FMAN_MAC
> 
> I do not see the FSL_FMAN_MAC Kconfig symbol defined anywhere in the
> tree.

I believe this patch series is dependent on two
other patch series mentioned in the cover letter.
---
The latest FMan driver patches were submitted by Igal Liberman:
https://patchwork.ozlabs.org/project/netdev/list/?submitter=64715=*

The latest Q/BMan drivers were submitted by Roy Pledge:
https://patchwork.ozlabs.org/project/linuxppc-dev/list/?submitter=66331=*
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [net-next v5 2/8] dpaa_eth: add support for DPAA Ethernet

[David Miller]

From: Joe Perches 
Date: Fri, 04 Dec 2015 12:00:35 -0800

> On Fri, 2015-12-04 at 14:55 -0500, David Miller wrote:
>> From: Madalin Bucur 
>> Date: Thu, 3 Dec 2015 15:49:43 +0200
>> 
>> > @@ -0,0 +1,22 @@
>> > +menuconfig FSL_DPAA_ETH
>> > + tristate "DPAA Ethernet"
>> > + depends on FSL_SOC && FSL_BMAN && FSL_QMAN && FSL_FMAN
>> > + select PHYLIB
>> > + select FSL_FMAN_MAC
>> 
>> I do not see the FSL_FMAN_MAC Kconfig symbol defined anywhere in the
>> tree.
> 
> I believe this patch series is dependent on two
> other patch series mentioned in the cover letter.

Then this shouldn't have been submitted.

The dependent series has been through a lot of changes and still needs
lots of work, and is very far from being applied.

Posting patches depending upon it is therefore wholly inapproprate.
That time and effort should be spent putting the dependent series
into proper shape.

Since I see what is happening here, I am going to simply ignore all
future submissions of dpaa_eth, until the dependencies are worked
out properly so don't bother posting this stuff again until that
happens.

Thanks.
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[PATCH] powerpc/e6500: add locking to hugetlb

[Scott Wood]

e6500 has threads but does not have TLB write conditional.  Thus,
the hugetlb code needs to take the same lock that the normal TLB miss
handlers take, to ensure that the tlbsx and tlbwe are atomic.

Signed-off-by: Scott Wood 
---
 arch/powerpc/mm/hugetlbpage-book3e.c | 46 
 1 file changed, 46 insertions(+)

diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c 
b/arch/powerpc/mm/hugetlbpage-book3e.c
index ba47aaf..180707e 100644
--- a/arch/powerpc/mm/hugetlbpage-book3e.c
+++ b/arch/powerpc/mm/hugetlbpage-book3e.c
@@ -51,6 +51,48 @@ static inline int mmu_get_tsize(int psize)
return mmu_psize_defs[psize].enc;
 }
 
+#if defined(CONFIG_PPC_FSL_BOOK3E) && defined(CONFIG_PPC64)
+#include 
+
+static inline void book3e_tlb_lock(void)
+{
+   struct paca_struct *paca = get_paca();
+   unsigned long tmp;
+   int token = smp_processor_id() + 1;
+
+   asm volatile("1: lbarx %0, 0, %1;"
+"cmpwi %0, 0;"
+"bne 2f;"
+"stbcx. %2, 0, %1;"
+"bne 1b;"
+"b 3f;"
+"2: lbzx %0, 0, %1;"
+"cmpwi %0, 0;"
+"bne 2b;"
+"b 1b;"
+"3:" 
+: "=" (tmp)
+: "r" (>tcd_ptr->lock), "r" (token)
+: "memory");
+}
+
+static inline void book3e_tlb_unlock(void)
+{
+   struct paca_struct *paca = get_paca();
+
+   isync();
+   paca->tcd_ptr->lock = 0;
+}
+#else
+static inline void book3e_tlb_lock(void)
+{
+}
+
+static inline void book3e_tlb_unlock(void)
+{
+}
+#endif
+
 static inline int book3e_tlb_exists(unsigned long ea, unsigned long pid)
 {
int found = 0;
@@ -109,7 +151,10 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, 
unsigned long ea,
 */
local_irq_save(flags);
 
+   book3e_tlb_lock();
+
if (unlikely(book3e_tlb_exists(ea, mm->context.id))) {
+   book3e_tlb_unlock();
local_irq_restore(flags);
return;
}
@@ -141,6 +186,7 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, 
unsigned long ea,
 
asm volatile ("tlbwe");
 
+   book3e_tlb_unlock();
local_irq_restore(flags);
 }
 
-- 
2.5.0

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

[PATCH v2] powerpc/e6500: add locking to hugetlb

[Scott Wood]

e6500 has threads but does not have TLB write conditional.  Thus,
the hugetlb code needs to take the same lock that the normal TLB miss
handlers take, to ensure that the tlbsx and tlbwe are atomic.

Signed-off-by: Scott Wood 
---
v2: Fix trailing whitespace

 arch/powerpc/mm/hugetlbpage-book3e.c | 46 
 1 file changed, 46 insertions(+)

diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c 
b/arch/powerpc/mm/hugetlbpage-book3e.c
index ba47aaf..180707e 100644
--- a/arch/powerpc/mm/hugetlbpage-book3e.c
+++ b/arch/powerpc/mm/hugetlbpage-book3e.c
@@ -51,6 +51,48 @@ static inline int mmu_get_tsize(int psize)
return mmu_psize_defs[psize].enc;
 }
 
+#if defined(CONFIG_PPC_FSL_BOOK3E) && defined(CONFIG_PPC64)
+#include 
+
+static inline void book3e_tlb_lock(void)
+{
+   struct paca_struct *paca = get_paca();
+   unsigned long tmp;
+   int token = smp_processor_id() + 1;
+
+   asm volatile("1: lbarx %0, 0, %1;"
+"cmpwi %0, 0;"
+"bne 2f;"
+"stbcx. %2, 0, %1;"
+"bne 1b;"
+"b 3f;"
+"2: lbzx %0, 0, %1;"
+"cmpwi %0, 0;"
+"bne 2b;"
+"b 1b;"
+"3:"
+: "=" (tmp)
+: "r" (>tcd_ptr->lock), "r" (token)
+: "memory");
+}
+
+static inline void book3e_tlb_unlock(void)
+{
+   struct paca_struct *paca = get_paca();
+
+   isync();
+   paca->tcd_ptr->lock = 0;
+}
+#else
+static inline void book3e_tlb_lock(void)
+{
+}
+
+static inline void book3e_tlb_unlock(void)
+{
+}
+#endif
+
 static inline int book3e_tlb_exists(unsigned long ea, unsigned long pid)
 {
int found = 0;
@@ -109,7 +151,10 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, 
unsigned long ea,
 */
local_irq_save(flags);
 
+   book3e_tlb_lock();
+
if (unlikely(book3e_tlb_exists(ea, mm->context.id))) {
+   book3e_tlb_unlock();
local_irq_restore(flags);
return;
}
@@ -141,6 +186,7 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, 
unsigned long ea,
 
asm volatile ("tlbwe");
 
+   book3e_tlb_unlock();
local_irq_restore(flags);
 }
 
-- 
2.5.0

___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [net-next v5 0/8] dpaa_eth: Add the Freescale DPAA Ethernet driver

[Timur Tabi]

On Thu, Dec 3, 2015 at 6:08 AM,  <> wrote:
> From: Madalin Bucur 
>
> This patch series adds the Ethernet driver for the Freescale
> QorIQ Data Path Acceleration Architecture (DPAA).

Please fix your git-send-email configuration, so that your emails are
formatted properly.  This is the From: header:

From: <>

-- 
Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev