* [Buildroot] [PATCH] toolchain: Bump ARC tools to arc-2016.09-rc1
From: Vlad Zakharov @ 2016-11-14 17:56 UTC (permalink / raw)
To: buildroot
As described at:
4520524ba055706236db9f00dd79f1b2e2e87fde
this commit continues a series of updates of ARC tools.
This time we're updating tools to arc-2016.09-rc1.
This update contains a lot of important fixes, e.g. it fixes:
http://autobuild.buildroot.net/results/4c7/4c77f33c842b37bf28cb931edf1b290e1bf4d93c//
http://autobuild.buildroot.net/results/902/902729a0b98675ad803939e3ecdcf230065a6012//
and other failures.
Other important change is that we also update gdb. Now we are
using gdb 7.12.
This version of gdb requires C++ toolchain support so we add
corresponding dependency to gdb Config.in file.
Signed-off-by: Vlad Zakharov <vzakhar@synopsys.com>
---
package/binutils/Config.in.host | 2 +-
.../{arc-2016.09-eng015 => arc-2016.09-rc1}/0300-ld-makefile.patch | 0
.../0301-check-ldrunpath-length.patch | 0
.../0500-add-sysroot-fix-from-bug-3049.patch | 0
.../0600-poison-system-directories.patch | 0
package/binutils/binutils.hash | 2 +-
package/binutils/binutils.mk | 2 +-
package/gcc/Config.in.host | 2 +-
.../301-missing-execinfo_h.patch | 0
.../gcc/{arc-2016.09-eng015 => arc-2016.09-rc1}/860-cilk-wchar.patch | 0
.../940-uclinux-enable-threads.patch | 0
package/gcc/gcc.hash | 2 +-
package/gdb/Config.in | 2 ++
package/gdb/Config.in.host | 2 +-
package/gdb/gdb.hash | 2 +-
15 files changed, 9 insertions(+), 7 deletions(-)
rename package/binutils/{arc-2016.09-eng015 => arc-2016.09-rc1}/0300-ld-makefile.patch (100%)
rename package/binutils/{arc-2016.09-eng015 => arc-2016.09-rc1}/0301-check-ldrunpath-length.patch (100%)
rename package/binutils/{arc-2016.09-eng015 => arc-2016.09-rc1}/0500-add-sysroot-fix-from-bug-3049.patch (100%)
rename package/binutils/{arc-2016.09-eng015 => arc-2016.09-rc1}/0600-poison-system-directories.patch (100%)
rename package/gcc/{arc-2016.09-eng015 => arc-2016.09-rc1}/301-missing-execinfo_h.patch (100%)
rename package/gcc/{arc-2016.09-eng015 => arc-2016.09-rc1}/860-cilk-wchar.patch (100%)
rename package/gcc/{arc-2016.09-eng015 => arc-2016.09-rc1}/940-uclinux-enable-threads.patch (100%)
diff --git a/package/binutils/Config.in.host b/package/binutils/Config.in.host
index 3e0c357..af9339e 100644
--- a/package/binutils/Config.in.host
+++ b/package/binutils/Config.in.host
@@ -22,7 +22,7 @@ endchoice
config BR2_BINUTILS_VERSION
string
- default "arc-2016.09-eng015" if BR2_arc
+ default "arc-2016.09-rc1" if BR2_arc
default "2.25.1" if BR2_BINUTILS_VERSION_2_25_X
default "2.26.1" if BR2_BINUTILS_VERSION_2_26_X
default "2.27" if BR2_BINUTILS_VERSION_2_27_X
diff --git a/package/binutils/arc-2016.09-eng015/0300-ld-makefile.patch b/package/binutils/arc-2016.09-rc1/0300-ld-makefile.patch
similarity index 100%
rename from package/binutils/arc-2016.09-eng015/0300-ld-makefile.patch
rename to package/binutils/arc-2016.09-rc1/0300-ld-makefile.patch
diff --git a/package/binutils/arc-2016.09-eng015/0301-check-ldrunpath-length.patch b/package/binutils/arc-2016.09-rc1/0301-check-ldrunpath-length.patch
similarity index 100%
rename from package/binutils/arc-2016.09-eng015/0301-check-ldrunpath-length.patch
rename to package/binutils/arc-2016.09-rc1/0301-check-ldrunpath-length.patch
diff --git a/package/binutils/arc-2016.09-eng015/0500-add-sysroot-fix-from-bug-3049.patch b/package/binutils/arc-2016.09-rc1/0500-add-sysroot-fix-from-bug-3049.patch
similarity index 100%
rename from package/binutils/arc-2016.09-eng015/0500-add-sysroot-fix-from-bug-3049.patch
rename to package/binutils/arc-2016.09-rc1/0500-add-sysroot-fix-from-bug-3049.patch
diff --git a/package/binutils/arc-2016.09-eng015/0600-poison-system-directories.patch b/package/binutils/arc-2016.09-rc1/0600-poison-system-directories.patch
similarity index 100%
rename from package/binutils/arc-2016.09-eng015/0600-poison-system-directories.patch
rename to package/binutils/arc-2016.09-rc1/0600-poison-system-directories.patch
diff --git a/package/binutils/binutils.hash b/package/binutils/binutils.hash
index f41b39b..80ac9dd 100644
--- a/package/binutils/binutils.hash
+++ b/package/binutils/binutils.hash
@@ -5,4 +5,4 @@ sha512 9d9165609fd3b0f20d616f9891fc8e2b466eb13e2bfce40125e12427f8f201d20e2b8322
sha512 cf276f84935312361a2ca077e04d0b469d23a3aed979d8ba5d92ea590904ffb2c2e7ed12cc842822bfc402836be86f479660cef3791aa62f3753d8a1a6f564cb binutils-2.27.tar.bz2
# Locally calculated (fetched from Github)
-sha512 f8cc7529fbe3cb52b666b92e1353063a8a36ea07fa8c5aa8359252f4222feaed15253b6a137033c74dabc0ae784daf8a7978e69ebdb8bf8cd6b8bb61c84bf181 binutils-arc-2016.09-eng015.tar.gz
+sha512 d0befdeb0a7b76efd1ad655fc062cde2aa67be7b26210c913ab2709e069d815c4ff2863ce7add1f6434da5a2f4faf1ce5a5bc3d0e64f3e04548a7479f24edcbc binutils-arc-2016.09-rc1.tar.gz
diff --git a/package/binutils/binutils.mk b/package/binutils/binutils.mk
index ca481d2..61486a2 100644
--- a/package/binutils/binutils.mk
+++ b/package/binutils/binutils.mk
@@ -9,7 +9,7 @@
BINUTILS_VERSION = $(call qstrip,$(BR2_BINUTILS_VERSION))
ifeq ($(BINUTILS_VERSION),)
ifeq ($(BR2_arc),y)
-BINUTILS_VERSION = arc-2016.09-eng015
+BINUTILS_VERSION = arc-2016.09-rc1
else
BINUTILS_VERSION = 2.25.1
endif
diff --git a/package/gcc/Config.in.host b/package/gcc/Config.in.host
index 0a63e6a..d10798b 100644
--- a/package/gcc/Config.in.host
+++ b/package/gcc/Config.in.host
@@ -98,7 +98,7 @@ config BR2_GCC_VERSION
default "4.9.4" if BR2_GCC_VERSION_4_9_X
default "5.4.0" if BR2_GCC_VERSION_5_X
default "6.2.0" if BR2_GCC_VERSION_6_X
- default "arc-2016.09-eng015" if BR2_GCC_VERSION_ARC
+ default "arc-2016.09-rc1" if BR2_GCC_VERSION_ARC
config BR2_EXTRA_GCC_CONFIG_OPTIONS
string "Additional gcc options"
diff --git a/package/gcc/arc-2016.09-eng015/301-missing-execinfo_h.patch b/package/gcc/arc-2016.09-rc1/301-missing-execinfo_h.patch
similarity index 100%
rename from package/gcc/arc-2016.09-eng015/301-missing-execinfo_h.patch
rename to package/gcc/arc-2016.09-rc1/301-missing-execinfo_h.patch
diff --git a/package/gcc/arc-2016.09-eng015/860-cilk-wchar.patch b/package/gcc/arc-2016.09-rc1/860-cilk-wchar.patch
similarity index 100%
rename from package/gcc/arc-2016.09-eng015/860-cilk-wchar.patch
rename to package/gcc/arc-2016.09-rc1/860-cilk-wchar.patch
diff --git a/package/gcc/arc-2016.09-eng015/940-uclinux-enable-threads.patch b/package/gcc/arc-2016.09-rc1/940-uclinux-enable-threads.patch
similarity index 100%
rename from package/gcc/arc-2016.09-eng015/940-uclinux-enable-threads.patch
rename to package/gcc/arc-2016.09-rc1/940-uclinux-enable-threads.patch
diff --git a/package/gcc/gcc.hash b/package/gcc/gcc.hash
index ce738ef..e5d96f4 100644
--- a/package/gcc/gcc.hash
+++ b/package/gcc/gcc.hash
@@ -12,4 +12,4 @@ sha512 2941cc950c8f2409a314df497631f9b0266211aa74746c1839c46e04f1c7c299afe2528d
sha512 1e8b826a3d44b9d5899309894e20c03abeb352bf3d273b8ad63af814c0ee2911f1a83ce1cd4cdd2d1cb0b3e3c34e9b7ae1b2ab83dfc649ee817ab05247c76198 gcc-6.2.0.tar.bz2
# Locally calculated (fetched from Github)
-sha512 9f365452f746ae91875d935c2ec5ed16cd11a2973f69bd23193fec9fc6b557e0dd66bb169e7efb7ec63fd78af36139005abcf5a5a1d89d6f49788b2ed7b334fb gcc-arc-2016.09-eng015.tar.gz
+sha512 7029d7ae1316b9385880f32283aa6c4979b1257500bb21e3fb234475ecb20082f46b114d8b7022c75a8dcf0c0c7b6b02e9384b49dd3189adc3d454502b8b0c26 gcc-arc-2016.09-rc1.tar.gz
diff --git a/package/gdb/Config.in b/package/gdb/Config.in
index 809e02d..e025fe0 100644
--- a/package/gdb/Config.in
+++ b/package/gdb/Config.in
@@ -11,6 +11,8 @@ config BR2_PACKAGE_GDB
(!BR2_PACKAGE_GDB_DEBUGGER && !BR2_TOOLCHAIN_EXTERNAL_GDB_SERVER_COPY)
depends on BR2_TOOLCHAIN_HAS_THREADS && BR2_TOOLCHAIN_HAS_THREADS_DEBUG
depends on !BR2_nios2 && !BR2_bfin
+ # Since ARC gdb moved to 7.12 toolchain requires C++ support to build gdb.
+ depends on !BR2_arc || BR2_TOOLCHAIN_BUILDROOT_CXX
help
GDB, the GNU Project debugger, allows you to see what is
going on `inside' another program while it executes -- or
diff --git a/package/gdb/Config.in.host b/package/gdb/Config.in.host
index a36dc0f..b6eb41f 100644
--- a/package/gdb/Config.in.host
+++ b/package/gdb/Config.in.host
@@ -56,7 +56,7 @@ endif
config BR2_GDB_VERSION
string
depends on BR2_PACKAGE_GDB || BR2_PACKAGE_HOST_GDB
- default "arc-2016.03-gdb" if BR2_arc
+ default "arc-2016.09-rc1-gdb" if BR2_arc
default "6be65fb56ea6694a9260733a536a023a1e2d4d57" if BR2_microblaze
default "7.9.1" if BR2_GDB_VERSION_7_9
default "7.10.1" if BR2_GDB_VERSION_7_10 || !BR2_PACKAGE_HOST_GDB
diff --git a/package/gdb/gdb.hash b/package/gdb/gdb.hash
index 611a75c..8c0d51b 100644
--- a/package/gdb/gdb.hash
+++ b/package/gdb/gdb.hash
@@ -5,4 +5,4 @@ sha512 f80ec6c8a0f0b54c8b945666e875809174402b7e121efb378ebac931a91f9a1cc0048568
# Locally calculated (fetched from Github)
sha512 0a467091d4b01fbecabb4b8da1cb743025c70e7f4874a0b5c8fa2ec623569a39bde6762b91806de0be6e63711aeb6909715cfbe43860de73d8aec6159a9f10a7 gdb-6be65fb56ea6694a9260733a536a023a1e2d4d57.tar.gz
-sha512 1abef1357896c2b57cfa7f7414eedc49d0de26b54321c680c2d027b1a27ec453d421e7f89a5281336047542379fd4820685802059efbd32b87c5ccffbaf2bd16 gdb-arc-2016.03-gdb.tar.gz
+sha512 e6019ac0d6b1354943d3c06c84f353ba49fef105b07c1a04ad90cc5b65f91e38fe6c671e0c34a9541ee282d0f42cf24579c011a0469d19faaa4d00d64a17afe2 gdb-arc-2016.09-rc1-gdb.tar.gz
--
2.6.3
^ permalink raw reply related
* [PATCH tip/core/rcu 3/7] list: Split list_del() debug checking into separate function
From: Paul E. McKenney @ 2016-11-14 17:55 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, dvhart, fweisbec, oleg,
bobby.prani, Kees Cook, Paul E. McKenney
In-Reply-To: <20161114175500.GA21637@linux.vnet.ibm.com>
From: Kees Cook <keescook@chromium.org>
Similar to the list_add() debug consolidation, this commit consolidates
the debug checking performed during CONFIG_DEBUG_LIST into a new
__list_del_entry_valid() function, and stops list updates when corruption
is found.
Refactored from same hardening in PaX and Grsecurity.
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Rik van Riel <riel@redhat.com>
---
include/linux/list.h | 15 +++++++++------
lib/list_debug.c | 53 +++++++++++++++++++++++-----------------------------
2 files changed, 32 insertions(+), 36 deletions(-)
diff --git a/include/linux/list.h b/include/linux/list.h
index b6da9b1dce4d..d1039ecaf94f 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -32,6 +32,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list)
extern bool __list_add_valid(struct list_head *new,
struct list_head *prev,
struct list_head *next);
+extern bool __list_del_entry_valid(struct list_head *entry);
#else
static inline bool __list_add_valid(struct list_head *new,
struct list_head *prev,
@@ -39,6 +40,10 @@ static inline bool __list_add_valid(struct list_head *new,
{
return true;
}
+static inline bool __list_del_entry_valid(struct list_head *entry)
+{
+ return true;
+}
#endif
/*
@@ -106,22 +111,20 @@ static inline void __list_del(struct list_head * prev, struct list_head * next)
* Note: list_empty() on entry does not return true after this, the entry is
* in an undefined state.
*/
-#ifndef CONFIG_DEBUG_LIST
static inline void __list_del_entry(struct list_head *entry)
{
+ if (!__list_del_entry_valid(entry))
+ return;
+
__list_del(entry->prev, entry->next);
}
static inline void list_del(struct list_head *entry)
{
- __list_del(entry->prev, entry->next);
+ __list_del_entry(entry);
entry->next = LIST_POISON1;
entry->prev = LIST_POISON2;
}
-#else
-extern void __list_del_entry(struct list_head *entry);
-extern void list_del(struct list_head *entry);
-#endif
/**
* list_replace - replace old entry by new one
diff --git a/lib/list_debug.c b/lib/list_debug.c
index d0b89b9d0736..276565fca2a6 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -39,41 +39,34 @@ bool __list_add_valid(struct list_head *new, struct list_head *prev,
}
EXPORT_SYMBOL(__list_add_valid);
-void __list_del_entry(struct list_head *entry)
+bool __list_del_entry_valid(struct list_head *entry)
{
struct list_head *prev, *next;
prev = entry->prev;
next = entry->next;
- if (WARN(next == LIST_POISON1,
- "list_del corruption, %p->next is LIST_POISON1 (%p)\n",
- entry, LIST_POISON1) ||
- WARN(prev == LIST_POISON2,
- "list_del corruption, %p->prev is LIST_POISON2 (%p)\n",
- entry, LIST_POISON2) ||
- WARN(prev->next != entry,
- "list_del corruption. prev->next should be %p, "
- "but was %p\n", entry, prev->next) ||
- WARN(next->prev != entry,
- "list_del corruption. next->prev should be %p, "
- "but was %p\n", entry, next->prev))
- return;
-
- __list_del(prev, next);
-}
-EXPORT_SYMBOL(__list_del_entry);
+ if (unlikely(next == LIST_POISON1)) {
+ WARN(1, "list_del corruption, %p->next is LIST_POISON1 (%p)\n",
+ entry, LIST_POISON1);
+ return false;
+ }
+ if (unlikely(prev == LIST_POISON2)) {
+ WARN(1, "list_del corruption, %p->prev is LIST_POISON2 (%p)\n",
+ entry, LIST_POISON2);
+ return false;
+ }
+ if (unlikely(prev->next != entry)) {
+ WARN(1, "list_del corruption. prev->next should be %p, but was %p\n",
+ entry, prev->next);
+ return false;
+ }
+ if (unlikely(next->prev != entry)) {
+ WARN(1, "list_del corruption. next->prev should be %p, but was %p\n",
+ entry, next->prev);
+ return false;
+ }
+ return true;
-/**
- * list_del - deletes entry from list.
- * @entry: the element to delete from the list.
- * Note: list_empty on entry does not return true after this, the entry is
- * in an undefined state.
- */
-void list_del(struct list_head *entry)
-{
- __list_del_entry(entry);
- entry->next = LIST_POISON1;
- entry->prev = LIST_POISON2;
}
-EXPORT_SYMBOL(list_del);
+EXPORT_SYMBOL(__list_del_entry_valid);
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 2/7] rculist: Consolidate DEBUG_LIST for list_add_rcu()
From: Paul E. McKenney @ 2016-11-14 17:55 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, dvhart, fweisbec, oleg,
bobby.prani, Kees Cook, Paul E. McKenney
In-Reply-To: <20161114175500.GA21637@linux.vnet.ibm.com>
From: Kees Cook <keescook@chromium.org>
This commit consolidates the debug checking for list_add_rcu() into the
new single __list_add_valid() debug function. Notably, this commit fixes
the sanity check that was added in commit 17a801f4bfeb ("list_debug:
WARN for adding something already in the list"), which wasn't checking
RCU-protected lists.
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Rik van Riel <riel@redhat.com>
---
include/linux/rculist.h | 8 +++-----
lib/list_debug.c | 19 -------------------
2 files changed, 3 insertions(+), 24 deletions(-)
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 8beb98dcf14f..4f7a9561b8c4 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -45,19 +45,17 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
* This is only for internal list manipulation where we know
* the prev/next entries already!
*/
-#ifndef CONFIG_DEBUG_LIST
static inline void __list_add_rcu(struct list_head *new,
struct list_head *prev, struct list_head *next)
{
+ if (!__list_add_valid(new, prev, next))
+ return;
+
new->next = next;
new->prev = prev;
rcu_assign_pointer(list_next_rcu(prev), new);
next->prev = new;
}
-#else
-void __list_add_rcu(struct list_head *new,
- struct list_head *prev, struct list_head *next);
-#endif
/**
* list_add_rcu - add a new entry to rcu-protected list
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 149dd57b583b..d0b89b9d0736 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -77,22 +77,3 @@ void list_del(struct list_head *entry)
entry->prev = LIST_POISON2;
}
EXPORT_SYMBOL(list_del);
-
-/*
- * RCU variants.
- */
-void __list_add_rcu(struct list_head *new,
- struct list_head *prev, struct list_head *next)
-{
- WARN(next->prev != prev,
- "list_add_rcu corruption. next->prev should be prev (%p), but was %p. (next=%p).\n",
- prev, next->prev, next);
- WARN(prev->next != next,
- "list_add_rcu corruption. prev->next should be next (%p), but was %p. (prev=%p).\n",
- next, prev->next, prev);
- new->next = next;
- new->prev = prev;
- rcu_assign_pointer(list_next_rcu(prev), new);
- next->prev = new;
-}
-EXPORT_SYMBOL(__list_add_rcu);
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 1/7] list: Split list_add() debug checking into separate function
From: Paul E. McKenney @ 2016-11-14 17:55 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, dvhart, fweisbec, oleg,
bobby.prani, Kees Cook, Paul E. McKenney
In-Reply-To: <20161114175500.GA21637@linux.vnet.ibm.com>
From: Kees Cook <keescook@chromium.org>
Right now, __list_add() code is repeated either in list.h or in
list_debug.c, but the only differences between the two versions
are the debug checks. This commit therefore extracts these debug
checks into a separate __list_add_valid() function and consolidates
__list_add(). Additionally this new __list_add_valid() function will stop
list manipulations if a corruption is detected, instead of allowing for
further corruption that may lead to even worse conditions.
This is slight refactoring of the same hardening done in PaX and Grsecurity.
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Rik van Riel <riel@redhat.com>
---
include/linux/list.h | 22 ++++++++++++++++------
lib/list_debug.c | 48 +++++++++++++++++++++++-------------------------
2 files changed, 39 insertions(+), 31 deletions(-)
diff --git a/include/linux/list.h b/include/linux/list.h
index 5809e9a2de5b..b6da9b1dce4d 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -28,27 +28,37 @@ static inline void INIT_LIST_HEAD(struct list_head *list)
list->prev = list;
}
+#ifdef CONFIG_DEBUG_LIST
+extern bool __list_add_valid(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next);
+#else
+static inline bool __list_add_valid(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next)
+{
+ return true;
+}
+#endif
+
/*
* Insert a new entry between two known consecutive entries.
*
* This is only for internal list manipulation where we know
* the prev/next entries already!
*/
-#ifndef CONFIG_DEBUG_LIST
static inline void __list_add(struct list_head *new,
struct list_head *prev,
struct list_head *next)
{
+ if (!__list_add_valid(new, prev, next))
+ return;
+
next->prev = new;
new->next = next;
new->prev = prev;
WRITE_ONCE(prev->next, new);
}
-#else
-extern void __list_add(struct list_head *new,
- struct list_head *prev,
- struct list_head *next);
-#endif
/**
* list_add - add a new entry
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 3859bf63561c..149dd57b583b 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -2,8 +2,7 @@
* Copyright 2006, Red Hat, Inc., Dave Jones
* Released under the General Public License (GPL).
*
- * This file contains the linked list implementations for
- * DEBUG_LIST.
+ * This file contains the linked list validation for DEBUG_LIST.
*/
#include <linux/export.h>
@@ -13,33 +12,32 @@
#include <linux/rculist.h>
/*
- * Insert a new entry between two known consecutive entries.
- *
- * This is only for internal list manipulation where we know
- * the prev/next entries already!
+ * Check that the data structures for the list manipulations are reasonably
+ * valid. Failures here indicate memory corruption (and possibly an exploit
+ * attempt).
*/
-void __list_add(struct list_head *new,
- struct list_head *prev,
- struct list_head *next)
+bool __list_add_valid(struct list_head *new, struct list_head *prev,
+ struct list_head *next)
{
- WARN(next->prev != prev,
- "list_add corruption. next->prev should be "
- "prev (%p), but was %p. (next=%p).\n",
- prev, next->prev, next);
- WARN(prev->next != next,
- "list_add corruption. prev->next should be "
- "next (%p), but was %p. (prev=%p).\n",
- next, prev->next, prev);
- WARN(new == prev || new == next,
- "list_add double add: new=%p, prev=%p, next=%p.\n",
- new, prev, next);
- next->prev = new;
- new->next = next;
- new->prev = prev;
- WRITE_ONCE(prev->next, new);
+ if (unlikely(next->prev != prev)) {
+ WARN(1, "list_add corruption. next->prev should be prev (%p), but was %p. (next=%p).\n",
+ prev, next->prev, next);
+ return false;
+ }
+ if (unlikely(prev->next != next)) {
+ WARN(1, "list_add corruption. prev->next should be next (%p), but was %p. (prev=%p).\n",
+ next, prev->next, prev);
+ return false;
+ }
+ if (unlikely(new == prev || new == next)) {
+ WARN(1, "list_add double add: new=%p, prev=%p, next=%p.\n",
+ new, prev, next);
+ return false;
+ }
+ return true;
}
-EXPORT_SYMBOL(__list_add);
+EXPORT_SYMBOL(__list_add_valid);
void __list_del_entry(struct list_head *entry)
{
--
2.5.2
^ permalink raw reply related
* Re: [Qemu-devel] [PATCH V11 1/1] fsdev: add IO throttle support to fsdev devices
From: Greg Kurz @ 2016-11-14 17:57 UTC (permalink / raw)
To: Pradeep Jagadeesh
Cc: Pradeep Jagadeesh, Aneesh Kumar K.V, Alberto Garcia, qemu-devel,
Claudio Fontana
In-Reply-To: <591b301b-91a1-45b1-f10b-b94929d4d0d0@huawei.com>
On Mon, 14 Nov 2016 10:03:40 +0100
Pradeep Jagadeesh <pradeep.jagadeesh@huawei.com> wrote:
> On 11/12/2016 3:13 PM, Greg Kurz wrote:
> > On Fri, 11 Nov 2016 03:54:27 -0500
> > Pradeep Jagadeesh <pradeepkiruvale@gmail.com> wrote:
> >
> >> Uses throttling APIs to limit I/O bandwidth and number of operations on the
> >> devices which use 9p-local driver.
> >>
> >> Signed-off-by: Pradeep Jagadeesh <pradeep.jagadeesh@huawei.com>
> >> Reviewed-by: Alberto Garcia" <berto@igalia.com>
> >> ---
> >
> > Hi Pradeep,
> >
> > I'll have a look next week but I'm not sure this can go to 2.8 since we're
> > already in soft feature freeze (only bug fixes are accepted).
>
> Hi Greg,
>
> It is ok even if it does not make it to 2.8.I just want to complete this
> work from my side.
>
Hi Pradeep,
The patch looks good to me now. Since we're no more in a hurry to get this
merged, maybe you can now try to address the code duplication issue with
the command line options ? Ideally this should be done in a preparatory
patch.
Cheers.
--
Greg
> Thanks,
> Pradeep
> >
> > Cheers.
> >
> > --
> > Greg
> >
> >> fsdev/Makefile.objs | 2 +-
> >> fsdev/file-op-9p.h | 3 ++
> >> fsdev/qemu-fsdev-opts.c | 77 ++++++++++++++++++++++++++++-
> >> fsdev/qemu-fsdev-throttle.c | 117 ++++++++++++++++++++++++++++++++++++++++++++
> >> fsdev/qemu-fsdev-throttle.h | 39 +++++++++++++++
> >> hw/9pfs/9p-local.c | 8 +++
> >> hw/9pfs/9p.c | 5 ++
> >> hw/9pfs/cofile.c | 2 +
> >> 8 files changed, 251 insertions(+), 2 deletions(-)
> >> create mode 100644 fsdev/qemu-fsdev-throttle.c
> >> create mode 100644 fsdev/qemu-fsdev-throttle.h
> >>
> >> This adds the support for the 9p-local driver.
> >> For now this functionality can be enabled only through qemu cli options.
> >> QMP interface and support to other drivers need further extensions.
> >> To make it simple for other drivers, the throttle code has been put in
> >> separate files.
> >>
> >> v1 -> v2:
> >>
> >> -Fixed FsContext redeclaration issue
> >> -Removed couple of function declarations from 9p-throttle.h
> >> -Fixed some of the .help messages
> >>
> >> v2 -> v3:
> >>
> >> -Addressed follwing comments by Claudio Fontana
> >> -Removed redundant memset calls in fsdev_throttle_configure_iolimits function
> >> -Checking throttle structure validity before initializing other structures
> >> in fsdev_throttle_configure_iolimits
> >>
> >> -Addressed following comments by Greg Kurz
> >> -Moved the code from 9pfs directory to fsdev directory, because the throttling
> >> is for the fsdev devices.Renamed the files and functions to fsdev_ from 9pfs_
> >> -Renamed throttling cli options to throttling.*, as in QMP cli options
> >> -Removed some of the unwanted .h files from qemu-fsdev-throttle.[ch]
> >> -Using throttle_enabled() function to set the thottle enabled flag for fsdev.
> >>
> >> v3 -> v4:
> >>
> >> -Addressed following comments by Alberto Garcia
> >> -Removed the unwanted locking and other data structures in qemu-fsdev-throttle.[ch]
> >>
> >> -Addressed following comments by Greg Kurz
> >> -Removed fsdev_iolimitsenable/disable functions, instead using throttle_enabled function
> >>
> >> v4 -> V5:
> >> -Fixed the issue with the larger block size accounting.
> >> (i.e, when the 9pfs mounted using msize=xxx option)
> >>
> >> V5 -> V6:
> >> -Addressed the comments by Alberto Garcia
> >> -Removed the fsdev_throttle_timer_cb()
> >> -Simplified the fsdev_throttle_schedule_next_request() as suggested
> >>
> >> V6 -> V7:
> >> -Addressed the comments by Alberto Garcia
> >> -changed the fsdev_throttle_schedule_next_request() as suggested
> >>
> >> v7 -> v8:
> >> -Addressed comments by Alberto Garcia
> >> -Fixed some indentation issues and split the configure_io_limit function
> >> -Inlined throttle_timer_check code
> >>
> >> V8 -> v9:
> >> -Addressed the comments by Greg Kurz
> >> -Inlined the fsdev_throttle_schedule_next_request() code into
> >> fsdev_co_throttle_request ()
> >>
> >> v9 -> v10:
> >> -Addressed the comments by alberto garcia
> >> -fixed the indentation issues and minor issues
> >>
> >> v10 -> v11:
> >> -Addressed the comments by alberto garcia
> >> -renamed err variable to errp issues
> >>
> >>
> >> diff --git a/fsdev/Makefile.objs b/fsdev/Makefile.objs
> >> index 1b120a4..659df6e 100644
> >> --- a/fsdev/Makefile.objs
> >> +++ b/fsdev/Makefile.objs
> >> @@ -5,7 +5,7 @@ common-obj-y = qemu-fsdev.o 9p-marshal.o 9p-iov-marshal.o
> >> else
> >> common-obj-y = qemu-fsdev-dummy.o
> >> endif
> >> -common-obj-y += qemu-fsdev-opts.o
> >> +common-obj-y += qemu-fsdev-opts.o qemu-fsdev-throttle.o
> >>
> >> # Toplevel always builds this; targets without virtio will put it in
> >> # common-obj-y
> >> diff --git a/fsdev/file-op-9p.h b/fsdev/file-op-9p.h
> >> index 6db9fea..33fe822 100644
> >> --- a/fsdev/file-op-9p.h
> >> +++ b/fsdev/file-op-9p.h
> >> @@ -17,6 +17,7 @@
> >> #include <dirent.h>
> >> #include <utime.h>
> >> #include <sys/vfs.h>
> >> +#include "qemu-fsdev-throttle.h"
> >>
> >> #define SM_LOCAL_MODE_BITS 0600
> >> #define SM_LOCAL_DIR_MODE_BITS 0700
> >> @@ -74,6 +75,7 @@ typedef struct FsDriverEntry {
> >> char *path;
> >> int export_flags;
> >> FileOperations *ops;
> >> + FsThrottle fst;
> >> } FsDriverEntry;
> >>
> >> typedef struct FsContext
> >> @@ -83,6 +85,7 @@ typedef struct FsContext
> >> int export_flags;
> >> struct xattr_operations **xops;
> >> struct extended_ops exops;
> >> + FsThrottle *fst;
> >> /* fs driver specific data */
> >> void *private;
> >> } FsContext;
> >> diff --git a/fsdev/qemu-fsdev-opts.c b/fsdev/qemu-fsdev-opts.c
> >> index 1dd8c7a..385423f0 100644
> >> --- a/fsdev/qemu-fsdev-opts.c
> >> +++ b/fsdev/qemu-fsdev-opts.c
> >> @@ -37,8 +37,83 @@ static QemuOptsList qemu_fsdev_opts = {
> >> }, {
> >> .name = "sock_fd",
> >> .type = QEMU_OPT_NUMBER,
> >> + }, {
> >> + .name = "throttling.iops-total",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "limit total I/O operations per second",
> >> + }, {
> >> + .name = "throttling.iops-read",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "limit read operations per second",
> >> + }, {
> >> + .name = "throttling.iops-write",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "limit write operations per second",
> >> + }, {
> >> + .name = "throttling.bps-total",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "limit total bytes per second",
> >> + }, {
> >> + .name = "throttling.bps-read",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "limit read bytes per second",
> >> + }, {
> >> + .name = "throttling.bps-write",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "limit write bytes per second",
> >> + }, {
> >> + .name = "throttling.iops-total-max",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "I/O operations burst",
> >> + }, {
> >> + .name = "throttling.iops-read-max",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "I/O operations read burst",
> >> + }, {
> >> + .name = "throttling.iops-write-max",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "I/O operations write burst",
> >> + }, {
> >> + .name = "throttling.bps-total-max",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "total bytes burst",
> >> + }, {
> >> + .name = "throttling.bps-read-max",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "total bytes read burst",
> >> + }, {
> >> + .name = "throttling.bps-write-max",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "total bytes write burst",
> >> + }, {
> >> + .name = "throttling.iops-total-max-length",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "length of the iops-total-max burst period, in seconds",
> >> + }, {
> >> + .name = "throttling.iops-read-max-length",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "length of the iops-read-max burst period, in seconds",
> >> + }, {
> >> + .name = "throttling.iops-write-max-length",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "length of the iops-write-max burst period, in seconds",
> >> + }, {
> >> + .name = "throttling.bps-total-max-length",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "length of the bps-total-max burst period, in seconds",
> >> + }, {
> >> + .name = "throttling.bps-read-max-length",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "length of the bps-read-max burst period, in seconds",
> >> + }, {
> >> + .name = "throttling.bps-write-max-length",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "length of the bps-write-max burst period, in seconds",
> >> + }, {
> >> + .name = "throttling.iops-size",
> >> + .type = QEMU_OPT_NUMBER,
> >> + .help = "when limiting by iops max size of an I/O in bytes",
> >> },
> >> -
> >> { /*End of list */ }
> >> },
> >> };
> >> diff --git a/fsdev/qemu-fsdev-throttle.c b/fsdev/qemu-fsdev-throttle.c
> >> new file mode 100644
> >> index 0000000..193ad26
> >> --- /dev/null
> >> +++ b/fsdev/qemu-fsdev-throttle.c
> >> @@ -0,0 +1,117 @@
> >> +/*
> >> + * Fsdev Throttle
> >> + *
> >> + * Copyright (C) 2016 Huawei Technologies Duesseldorf GmbH
> >> + *
> >> + * Author: Pradeep Jagadeesh <pradeep.jagadeesh@huawei.com>
> >> + *
> >> + * This work is licensed under the terms of the GNU GPL, version 2 or
> >> + * (at your option) any later version.
> >> + *
> >> + * See the COPYING file in the top-level directory for details.
> >> + *
> >> + */
> >> +
> >> +#include "qemu/osdep.h"
> >> +#include "qemu/error-report.h"
> >> +#include "qemu-fsdev-throttle.h"
> >> +#include "qemu/iov.h"
> >> +
> >> +static void fsdev_throttle_read_timer_cb(void *opaque)
> >> +{
> >> + FsThrottle *fst = opaque;
> >> + qemu_co_enter_next(&fst->throttled_reqs[false]);
> >> +}
> >> +
> >> +static void fsdev_throttle_write_timer_cb(void *opaque)
> >> +{
> >> + FsThrottle *fst = opaque;
> >> + qemu_co_enter_next(&fst->throttled_reqs[true]);
> >> +}
> >> +
> >> +void fsdev_throttle_parse_opts(QemuOpts *opts, FsThrottle *fst, Error **errp)
> >> +{
> >> + fst->cfg.buckets[THROTTLE_BPS_TOTAL].avg =
> >> + qemu_opt_get_number(opts, "throttling.bps-total", 0);
> >> + fst->cfg.buckets[THROTTLE_BPS_READ].avg =
> >> + qemu_opt_get_number(opts, "throttling.bps-read", 0);
> >> + fst->cfg.buckets[THROTTLE_BPS_WRITE].avg =
> >> + qemu_opt_get_number(opts, "throttling.bps-write", 0);
> >> + fst->cfg.buckets[THROTTLE_OPS_TOTAL].avg =
> >> + qemu_opt_get_number(opts, "throttling.iops-total", 0);
> >> + fst->cfg.buckets[THROTTLE_OPS_READ].avg =
> >> + qemu_opt_get_number(opts, "throttling.iops-read", 0);
> >> + fst->cfg.buckets[THROTTLE_OPS_WRITE].avg =
> >> + qemu_opt_get_number(opts, "throttling.iops-write", 0);
> >> +
> >> + fst->cfg.buckets[THROTTLE_BPS_TOTAL].max =
> >> + qemu_opt_get_number(opts, "throttling.bps-total-max", 0);
> >> + fst->cfg.buckets[THROTTLE_BPS_READ].max =
> >> + qemu_opt_get_number(opts, "throttling.bps-read-max", 0);
> >> + fst->cfg.buckets[THROTTLE_BPS_WRITE].max =
> >> + qemu_opt_get_number(opts, "throttling.bps-write-max", 0);
> >> + fst->cfg.buckets[THROTTLE_OPS_TOTAL].max =
> >> + qemu_opt_get_number(opts, "throttling.iops-total-max", 0);
> >> + fst->cfg.buckets[THROTTLE_OPS_READ].max =
> >> + qemu_opt_get_number(opts, "throttling.iops-read-max", 0);
> >> + fst->cfg.buckets[THROTTLE_OPS_WRITE].max =
> >> + qemu_opt_get_number(opts, "throttling.iops-write-max", 0);
> >> +
> >> + fst->cfg.buckets[THROTTLE_BPS_TOTAL].burst_length =
> >> + qemu_opt_get_number(opts, "throttling.bps-total-max-length", 1);
> >> + fst->cfg.buckets[THROTTLE_BPS_READ].burst_length =
> >> + qemu_opt_get_number(opts, "throttling.bps-read-max-length", 1);
> >> + fst->cfg.buckets[THROTTLE_BPS_WRITE].burst_length =
> >> + qemu_opt_get_number(opts, "throttling.bps-write-max-length", 1);
> >> + fst->cfg.buckets[THROTTLE_OPS_TOTAL].burst_length =
> >> + qemu_opt_get_number(opts, "throttling.iops-total-max-length", 1);
> >> + fst->cfg.buckets[THROTTLE_OPS_READ].burst_length =
> >> + qemu_opt_get_number(opts, "throttling.iops-read-max-length", 1);
> >> + fst->cfg.buckets[THROTTLE_OPS_WRITE].burst_length =
> >> + qemu_opt_get_number(opts, "throttling.iops-write-max-length", 1);
> >> + fst->cfg.op_size =
> >> + qemu_opt_get_number(opts, "throttling.iops-size", 0);
> >> +
> >> + throttle_is_valid(&fst->cfg, errp);
> >> +}
> >> +
> >> +void fsdev_throttle_init(FsThrottle *fst)
> >> +{
> >> + if (throttle_enabled(&fst->cfg)) {
> >> + throttle_init(&fst->ts);
> >> + throttle_timers_init(&fst->tt,
> >> + qemu_get_aio_context(),
> >> + QEMU_CLOCK_REALTIME,
> >> + fsdev_throttle_read_timer_cb,
> >> + fsdev_throttle_write_timer_cb,
> >> + fst);
> >> + throttle_config(&fst->ts, &fst->tt, &fst->cfg);
> >> + qemu_co_queue_init(&fst->throttled_reqs[0]);
> >> + qemu_co_queue_init(&fst->throttled_reqs[1]);
> >> + }
> >> +}
> >> +
> >> +void coroutine_fn fsdev_co_throttle_request(FsThrottle *fst, bool is_write,
> >> + struct iovec *iov, int iovcnt)
> >> +{
> >> + if (throttle_enabled(&fst->cfg)) {
> >> + if (throttle_schedule_timer(&fst->ts, &fst->tt, is_write) ||
> >> + !qemu_co_queue_empty(&fst->throttled_reqs[is_write])) {
> >> + qemu_co_queue_wait(&fst->throttled_reqs[is_write]);
> >> + }
> >> +
> >> + throttle_account(&fst->ts, is_write, iov_size(iov, iovcnt));
> >> +
> >> + if (!qemu_co_queue_empty(&fst->throttled_reqs[is_write]) &&
> >> + !throttle_schedule_timer(&fst->ts, &fst->tt, is_write)) {
> >> + qemu_co_queue_next(&fst->throttled_reqs[is_write]);
> >> + }
> >> + }
> >> +}
> >> +
> >> +void fsdev_throttle_cleanup(FsThrottle *fst)
> >> +{
> >> + if (throttle_enabled(&fst->cfg)) {
> >> + throttle_timers_destroy(&fst->tt);
> >> + }
> >> +}
> >> diff --git a/fsdev/qemu-fsdev-throttle.h b/fsdev/qemu-fsdev-throttle.h
> >> new file mode 100644
> >> index 0000000..e418643
> >> --- /dev/null
> >> +++ b/fsdev/qemu-fsdev-throttle.h
> >> @@ -0,0 +1,39 @@
> >> +/*
> >> + * Fsdev Throttle
> >> + *
> >> + * Copyright (C) 2016 Huawei Technologies Duesseldorf GmbH
> >> + *
> >> + * Author: Pradeep Jagadeesh <pradeep.jagadeesh@huawei.com>
> >> + *
> >> + * This work is licensed under the terms of the GNU GPL, version 2 or
> >> + * (at your option) any later version.
> >> + *
> >> + * See the COPYING file in the top-level directory for details.
> >> + *
> >> + */
> >> +
> >> +#ifndef _FSDEV_THROTTLE_H
> >> +#define _FSDEV_THROTTLE_H
> >> +
> >> +#include "block/aio.h"
> >> +#include "qemu/main-loop.h"
> >> +#include "qemu/coroutine.h"
> >> +#include "qapi/error.h"
> >> +#include "qemu/throttle.h"
> >> +
> >> +typedef struct FsThrottle {
> >> + ThrottleState ts;
> >> + ThrottleTimers tt;
> >> + ThrottleConfig cfg;
> >> + CoQueue throttled_reqs[2];
> >> +} FsThrottle;
> >> +
> >> +void fsdev_throttle_parse_opts(QemuOpts *, FsThrottle *, Error **);
> >> +
> >> +void fsdev_throttle_init(FsThrottle *);
> >> +
> >> +void coroutine_fn fsdev_co_throttle_request(FsThrottle *, bool ,
> >> + struct iovec *, int);
> >> +
> >> +void fsdev_throttle_cleanup(FsThrottle *);
> >> +#endif /* _FSDEV_THROTTLE_H */
> >> diff --git a/hw/9pfs/9p-local.c b/hw/9pfs/9p-local.c
> >> index 845675e..828348d 100644
> >> --- a/hw/9pfs/9p-local.c
> >> +++ b/hw/9pfs/9p-local.c
> >> @@ -1209,6 +1209,7 @@ static int local_parse_opts(QemuOpts *opts, struct FsDriverEntry *fse)
> >> {
> >> const char *sec_model = qemu_opt_get(opts, "security_model");
> >> const char *path = qemu_opt_get(opts, "path");
> >> + Error *err = NULL;
> >>
> >> if (!sec_model) {
> >> error_report("Security model not specified, local fs needs security model");
> >> @@ -1237,6 +1238,13 @@ static int local_parse_opts(QemuOpts *opts, struct FsDriverEntry *fse)
> >> error_report("fsdev: No path specified");
> >> return -1;
> >> }
> >> +
> >> + fsdev_throttle_parse_opts(opts, &fse->fst, &err);
> >> + if (err) {
> >> + error_reportf_err(err, "Throttle configuration is not valid: ");
> >> + return -1;
> >> + }
> >> +
> >> fse->path = g_strdup(path);
> >>
> >> return 0;
> >> diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c
> >> index e88cf25..8d46a91 100644
> >> --- a/hw/9pfs/9p.c
> >> +++ b/hw/9pfs/9p.c
> >> @@ -3506,6 +3506,10 @@ int v9fs_device_realize_common(V9fsState *s, Error **errp)
> >> error_setg(errp, "share path %s is not a directory", fse->path);
> >> goto out;
> >> }
> >> +
> >> + s->ctx.fst = &fse->fst;
> >> + fsdev_throttle_init(s->ctx.fst);
> >> +
> >> v9fs_path_free(&path);
> >>
> >> rc = 0;
> >> @@ -3520,6 +3524,7 @@ out:
> >>
> >> void v9fs_device_unrealize_common(V9fsState *s, Error **errp)
> >> {
> >> + fsdev_throttle_cleanup(s->ctx.fst);
> >> g_free(s->ctx.fs_root);
> >> g_free(s->tag);
> >> }
> >> diff --git a/hw/9pfs/cofile.c b/hw/9pfs/cofile.c
> >> index 120e267..88791bc 100644
> >> --- a/hw/9pfs/cofile.c
> >> +++ b/hw/9pfs/cofile.c
> >> @@ -247,6 +247,7 @@ int coroutine_fn v9fs_co_pwritev(V9fsPDU *pdu, V9fsFidState *fidp,
> >> if (v9fs_request_cancelled(pdu)) {
> >> return -EINTR;
> >> }
> >> + fsdev_co_throttle_request(s->ctx.fst, true, iov, iovcnt);
> >> v9fs_co_run_in_worker(
> >> {
> >> err = s->ops->pwritev(&s->ctx, &fidp->fs, iov, iovcnt, offset);
> >> @@ -266,6 +267,7 @@ int coroutine_fn v9fs_co_preadv(V9fsPDU *pdu, V9fsFidState *fidp,
> >> if (v9fs_request_cancelled(pdu)) {
> >> return -EINTR;
> >> }
> >> + fsdev_co_throttle_request(s->ctx.fst, false, iov, iovcnt);
> >> v9fs_co_run_in_worker(
> >> {
> >> err = s->ops->preadv(&s->ctx, &fidp->fs, iov, iovcnt, offset);
> >
>
^ permalink raw reply
* Re: Debugging Ethernet issues
From: Sebastian Frias @ 2016-11-14 17:59 UTC (permalink / raw)
To: Florian Fainelli, Mason, Andrew Lunn
Cc: netdev, Mans Rullgard, Sergei Shtylyov, Tom Lendacky, Zach Brown,
Shaohui Xie, Tim Beale, Brian Hill, Vince Bridgers,
Balakumaran Kannan, David S. Miller, Kirill Kapranov
In-Reply-To: <3313424a-8d45-0883-5257-ffdc250dd45b@gmail.com>
On 11/14/2016 06:32 PM, Florian Fainelli wrote:
> On 11/14/2016 07:33 AM, Mason wrote:
>> On 14/11/2016 15:58, Mason wrote:
>>
>>> nb8800 26000.ethernet eth0: Link is Up - 100Mbps/Full - flow control rx/tx
>>> vs
>>> nb8800 26000.ethernet eth0: Link is Up - 100Mbps/Full - flow control off
>>>
>>> I'm not sure whether "flow control" is relevant...
>>
>> Based on phy_print_status()
>> phydev->pause ? "rx/tx" : "off"
>> I added the following patch.
>>
>> diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
>> index defc22a15f67..4e758c1cfa4e 100644
>> --- a/drivers/net/ethernet/aurora/nb8800.c
>> +++ b/drivers/net/ethernet/aurora/nb8800.c
>> @@ -667,6 +667,8 @@ static void nb8800_link_reconfigure(struct net_device *dev)
>> struct phy_device *phydev = priv->phydev;
>> int change = 0;
>>
>> + printk("%s from %pf\n", __func__, __builtin_return_address(0));
>> +
>> if (phydev->link) {
>> if (phydev->speed != priv->speed) {
>> priv->speed = phydev->speed;
>> @@ -1274,9 +1276,9 @@ static int nb8800_hw_init(struct net_device *dev)
>> nb8800_writeb(priv, NB8800_PQ2, val & 0xff);
>>
>> /* Auto-negotiate by default */
>> - priv->pause_aneg = true;
>> - priv->pause_rx = true;
>> - priv->pause_tx = true;
>> + priv->pause_aneg = false;
>> + priv->pause_rx = false;
>> + priv->pause_tx = false;
>>
>> nb8800_mc_init(dev, 0);
>>
>>
>> Connected to 1000 Mbps switch:
>>
>> # time udhcpc | while read LINE; do date; echo $LINE; done
>> Thu Jan 1 00:00:22 UTC 1970
>> udhcpc (v1.22.1) started
>> Thu Jan 1 00:00:22 UTC 1970
>> Sending discover...
>> [ 24.565346] nb8800_link_reconfigure from phy_state_machine
>> Thu Jan 1 00:00:25 UTC 1970
>> Sending discover...
>> [ 26.575402] nb8800_link_reconfigure from phy_state_machine
>> [ 26.580972] nb8800 26000.ethernet eth0: Link is Up - 1Gbps/Full - flow control rx/tx
>> Thu Jan 1 00:00:28 UTC 1970
>> Sending discover...
>> Thu Jan 1 00:00:29 UTC 1970
>> Sending select for 172.27.64.58...
>> Thu Jan 1 00:00:29 UTC 1970
>> Lease of 172.27.64.58 obtained, lease time 604800
>> Thu Jan 1 00:00:29 UTC 1970
>> deleting routers
>> Thu Jan 1 00:00:29 UTC 1970
>> adding dns 172.27.0.17
>>
>> real 0m7.388s
>> user 0m0.040s
>> sys 0m0.090s
>>
>>
>>
>> Connected to 100 Mbps switch:
>>
>> # time udhcpc | while read LINE; do date; echo $LINE; done
>> Thu Jan 1 00:00:14 UTC 1970
>> udhcpc (v1.22.1) started
>> Thu Jan 1 00:00:15 UTC 1970
>> Sending discover...
>> [ 16.968621] nb8800_link_reconfigure from phy_state_machine
>> [ 17.975359] nb8800_link_reconfigure from phy_state_machine
>> [ 17.980923] nb8800 26000.ethernet eth0: Link is Up - 100Mbps/Full - flow control rx/tx
>> Thu Jan 1 00:00:18 UTC 1970
>> Sending discover...
>> Thu Jan 1 00:00:19 UTC 1970
>> Sending select for 172.27.64.58...
>> Thu Jan 1 00:00:19 UTC 1970
>> Lease of 172.27.64.58 obtained, lease time 604800
>> Thu Jan 1 00:00:19 UTC 1970
>> deleting routers
>> Thu Jan 1 00:00:19 UTC 1970
>> adding dns 172.27.0.17
>>
>> real 0m4.355s
>> user 0m0.043s
>> sys 0m0.083s
>>
>
> And the time difference is clearly accounted for auto-negotiation time
> here, as you can see it takes about 3 seconds for Gigabit Ethernet to
> auto-negotiate and that seems completely acceptable and normal to me
> since it is a more involved process than lower speeds.
>
>>
>>
>> OK, so now it works (by accident?) even on 100 Mbps switch, but it still
>> prints "flow control rx/tx"...
>
> Because your link partner advertises flow control, and that's what
> phydev->pause and phydev->asym_pause report (I know it's confusing, but
> that's what it is at the moment).
Thanks.
Could you confirm that Mason's patch is correct and/or that it does not
has negative side-effects?
Right now we know that Mason's patch makes this work, but we do not understand
why nor its implications.
>
>>
>> # ethtool -a eth0
>> Pause parameters for eth0:
>> Autonegotiate: off
>> RX: off
>> TX: off
>>
>> These values make sense considering my changes in the driver.
>>
>> Are 100 Mbps switches supposed to support these pause features,
>> and are they supposed to be able to auto-negotiate them?
>
> Yes, switches can support flow control aka pause frames, and unless they
> are configurable, they typically advertise what their EEPROM has defined
> for them, so most likely the full auto-negotiated spectrum:
> 10/100/1000Mbps and support for flow control, but your mileage may vary
> of course.
>
^ permalink raw reply
* Re: New option for wall to limit message by group?
From: Jim Patterson @ 2016-11-14 17:59 UTC (permalink / raw)
To: kerolasa; +Cc: util-linux
In-Reply-To: <CAG27Bk3hONs8GZ_4GvwJYHu-kMntNzvmVn-qzSO7p6EBDS8xog@mail.gmail.com>
Hi Sami,
I think can handle the code without difficulty, but I'm open to help
from anyone we wants to help, and of course code review and feedback
is always welcome.
Thanks for heads up about the maintainer, sounds like a great holiday.
Jim P
On Mon, Nov 14, 2016 at 12:18 PM, Sami Kerola <kerolasa@iki.fi> wrote:
> On 14 November 2016 at 16:31, Jim Patterson <jimp@wegrok.net> wrote:
>> The company that I work for has an old terminal application that is
>> still in use today. This app used to run on AIX boxes but has been
>> moved to modern Linux based systems. The users on this application
>> are in groups and under AIX we used the "-g" switch on wall to be able
>> to send a message to a single group at a time. The wall on Linux does
>> not offer this option. I will either be adding this option to wall or
>> writing a custom tool to support sending a message based on the user's
>> groups.
>>
>> Is there any interest in a pull request supporting such an option in
>> the standard wall? And if so, does anyone have any particular
>> concerns about implementation details?
>>
>> The AIX man page does not describe the implementation details, but
>> experimenting with the command on an AIX system shows that the the
>> message is sent to all users that have the specified group in the
>> primary or supplementary groups. My plan for doing this on a Linux
>> system is to use the username in the utmp entry to lookup the user's
>> primary and supplementary groups, then skip the utmp entry if the user
>> does not have the specified group.
>>
>> Thanks in advance,
>> Jim P
>>
>> PS. I'm not subscribed to the group, so please reply to this address also.
>
> Hi Jim,
>
> Adding -g, --group <groupname|gid> option should be doable. Do you want
> to write this change or prefer someone else doing the work? Either way I
> don't mind helping a bit.
>
> Reference: http://www.ibm.com/support/knowledgecenter/ssw_aix_61/com.ibm.aix.cmds6/wall.htm
>
> p.s. Maintainer is off-line
> http://marc.info/?l=util-linux-ng&m=147877091818853&w=2
>
> --
> Sami Kerola
> http://www.iki.fi/kerolasa/
^ permalink raw reply
* [PATCH tip/core/rcu 0/2] Torture-test changes for 4.10
From: Paul E. McKenney @ 2016-11-14 17:59 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, dvhart, fweisbec, oleg,
bobby.prani
Hello!
This series contains a couple of torture-test changes:
1. Remove obsolete files from the rcutorture .gitignore file.
2. Prevent the --jitter flag from delaying --build-only runs.
Thanx, Paul
------------------------------------------------------------------------
.gitignore | 2 --
bin/kvm.sh | 5 +++++
2 files changed, 5 insertions(+), 2 deletions(-)
^ permalink raw reply
* Re: [PATCH v1 1/2] net/i40e: fix incorrect xstats value mapping
From: Kevin Traynor @ 2016-11-14 17:59 UTC (permalink / raw)
To: Remy Horton, dev; +Cc: Helin Zhang, Jingjing Wu, stable, Yuanhan Liu
In-Reply-To: <1479104089-27862-2-git-send-email-remy.horton@intel.com>
On 11/14/2016 06:14 AM, Remy Horton wrote:
> The offsets used in rte_i40evf_stats_strings for transmission
> statistics were wrong, returning the total byte count rather than
> the respective (unicast, multicast, broadcast, drop, & error)
> packet counts.
>
> Fixes: da61cd084976 ("i40evf: add extended stats")
This should go to the LTS branch also.
Acked-by: Kevin Traynor <ktraynor@redhat.com>
>
> Signed-off-by: Remy Horton <remy.horton@intel.com>
> ---
> drivers/net/i40e/i40e_ethdev_vf.c | 10 +++++-----
> 1 file changed, 5 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/net/i40e/i40e_ethdev_vf.c b/drivers/net/i40e/i40e_ethdev_vf.c
> index aa306d6..afae2ec 100644
> --- a/drivers/net/i40e/i40e_ethdev_vf.c
> +++ b/drivers/net/i40e/i40e_ethdev_vf.c
> @@ -176,11 +176,11 @@ static const struct rte_i40evf_xstats_name_off rte_i40evf_stats_strings[] = {
> {"rx_unknown_protocol_packets", offsetof(struct i40e_eth_stats,
> rx_unknown_protocol)},
> {"tx_bytes", offsetof(struct i40e_eth_stats, tx_bytes)},
> - {"tx_unicast_packets", offsetof(struct i40e_eth_stats, tx_bytes)},
> - {"tx_multicast_packets", offsetof(struct i40e_eth_stats, tx_bytes)},
> - {"tx_broadcast_packets", offsetof(struct i40e_eth_stats, tx_bytes)},
> - {"tx_dropped_packets", offsetof(struct i40e_eth_stats, tx_bytes)},
> - {"tx_error_packets", offsetof(struct i40e_eth_stats, tx_bytes)},
> + {"tx_unicast_packets", offsetof(struct i40e_eth_stats, tx_unicast)},
> + {"tx_multicast_packets", offsetof(struct i40e_eth_stats, tx_multicast)},
> + {"tx_broadcast_packets", offsetof(struct i40e_eth_stats, tx_broadcast)},
> + {"tx_dropped_packets", offsetof(struct i40e_eth_stats, tx_discards)},
> + {"tx_error_packets", offsetof(struct i40e_eth_stats, tx_errors)},
> };
>
> #define I40EVF_NB_XSTATS (sizeof(rte_i40evf_stats_strings) / \
>
^ permalink raw reply
* Re: [PATCH] binutils: Fix build for c293pcie PPC machine
From: Khem Raj @ 2016-11-14 17:59 UTC (permalink / raw)
To: Fabio Berton; +Cc: Patches and discussions about the oe-core layer
In-Reply-To: <1479126495-14047-1-git-send-email-fabio.berton@ossystems.com.br>
On Mon, Nov 14, 2016 at 4:28 AM, Fabio Berton
<fabio.berton@ossystems.com.br> wrote:
> The following patch fix build for c293pcie PPC machine :
> https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;a=commitdiff;h=8941017b
>
> This patch is a backport from master branch.
>
> Fix error:
> /
> |ERROR: binutils-2.27-r0 do_package: runstrip: ''powerpc-fslc-linux-gnuspe-strip'
> |--remove-section=.comment --remove-section=.note --strip-unneeded
> |'../tmp/work/ppce500v2-fslc-linux-gnuspe/binutils/2.27-r0/package/usr/lib/
> |libbfd-2.27.0.20160806.so'' strip command failed with 1
> |(b'powerpc-fslc-linux-gnuspe-strip: ../tmp/work/ppce500v2-fslc-linux-gnuspe/
> |binutils/2.27-r0/package/usr/lib/stJMAEnm: Not enough room for program headers,
> |try linking with -N\npowerpc-fslc-linux-gnuspe-strip:../tmp/work/
> |ppce500v2-fslc-linux-gnuspe/binutils/2.27-r0/package/usr/lib/stJMAEnm
> |[.note.gnu.build-id]: Bad value\n')
> \
This is ok.
>
> Signed-off-by: Fabio Berton <fabio.berton@ossystems.com.br>
> ---
> meta/recipes-devtools/binutils/binutils-2.27.inc | 1 +
> ...01-ppc-apuinfo-for-spe-parsed-incorrectly.patch | 37 ++++++++++++++++++++++
> 2 files changed, 38 insertions(+)
> create mode 100644 meta/recipes-devtools/binutils/binutils/0001-ppc-apuinfo-for-spe-parsed-incorrectly.patch
>
> diff --git a/meta/recipes-devtools/binutils/binutils-2.27.inc b/meta/recipes-devtools/binutils/binutils-2.27.inc
> index fc81721..75180ea 100644
> --- a/meta/recipes-devtools/binutils/binutils-2.27.inc
> +++ b/meta/recipes-devtools/binutils/binutils-2.27.inc
> @@ -37,6 +37,7 @@ SRC_URI = "\
> file://0015-binutils-mips-gas-pic-relax-linkonce.diff \
> file://0015-Refine-.cfi_sections-check-to-only-consider-compact-.patch \
> file://0016-Fix-seg-fault-in-ARM-linker-when-trying-to-parse-a-b.patch \
> + file://0001-ppc-apuinfo-for-spe-parsed-incorrectly.patch \
> "
> S = "${WORKDIR}/git"
>
> diff --git a/meta/recipes-devtools/binutils/binutils/0001-ppc-apuinfo-for-spe-parsed-incorrectly.patch b/meta/recipes-devtools/binutils/binutils/0001-ppc-apuinfo-for-spe-parsed-incorrectly.patch
> new file mode 100644
> index 0000000..d82a0b6
> --- /dev/null
> +++ b/meta/recipes-devtools/binutils/binutils/0001-ppc-apuinfo-for-spe-parsed-incorrectly.patch
> @@ -0,0 +1,37 @@
> +From 8941017bc0226b60ce306d5271df15820ce66a53 Mon Sep 17 00:00:00 2001
> +From: Alan Modra <amodra@gmail.com>
> +Date: Tue, 30 Aug 2016 20:57:32 +0930
> +Subject: [PATCH] ppc apuinfo for spe parsed incorrectly
> +Organization: O.S. Systems Software LTDA.
> +
> +apuinfo saying SPE resulted in mach = bfd_mach_ppc_vle due to a
> +missing break.
> +
> + PR 20531
> + * elf32-ppc.c (_bfd_elf_ppc_set_arch): Add missing "break".
> +
> +
> +Backport from :
> +https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;a=commitdiff;h=8941017b
> +
> +Upstream-Status: Backport
> +Signed-off-by: Fabio Berton <fabio.berton@ossystems.com.br>
> +---
> + bfd/elf32-ppc.c | 1 +
> + 1 file changed, 1 insertion(+)
> +
> +diff --git a/bfd/elf32-ppc.c b/bfd/elf32-ppc.c
> +index 95ce1dc..e42ef1c 100644
> +--- a/bfd/elf32-ppc.c
> ++++ b/bfd/elf32-ppc.c
> +@@ -2246,6 +2246,7 @@ _bfd_elf_ppc_set_arch (bfd *abfd)
> + case PPC_APUINFO_BRLOCK:
> + if (mach != bfd_mach_ppc_vle)
> + mach = bfd_mach_ppc_e500;
> ++ break;
> +
> + case PPC_APUINFO_VLE:
> + mach = bfd_mach_ppc_vle;
> +--
> +2.1.4
> +
> --
> 2.1.4
>
> --
> _______________________________________________
> Openembedded-core mailing list
> Openembedded-core@lists.openembedded.org
> http://lists.openembedded.org/mailman/listinfo/openembedded-core
^ permalink raw reply
* [PATCH tip/core/rcu 1/2] torture: Remove obsolete files from rcutorture .gitignore
From: Paul E. McKenney @ 2016-11-14 17:59 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, dvhart, fweisbec, oleg,
bobby.prani, Paul E. McKenney
In-Reply-To: <20161114175924.GA23488@linux.vnet.ibm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
tools/testing/selftests/rcutorture/.gitignore | 2 --
1 file changed, 2 deletions(-)
diff --git a/tools/testing/selftests/rcutorture/.gitignore b/tools/testing/selftests/rcutorture/.gitignore
index 05838f6f2ebe..ccc240275d1c 100644
--- a/tools/testing/selftests/rcutorture/.gitignore
+++ b/tools/testing/selftests/rcutorture/.gitignore
@@ -1,6 +1,4 @@
initrd
-linux-2.6
b[0-9]*
-rcu-test-image
res
*.swp
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 2/2] torture: Prevent jitter from delaying build-only runs
From: Paul E. McKenney @ 2016-11-14 17:59 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, dvhart, fweisbec, oleg,
bobby.prani, Paul E. McKenney
In-Reply-To: <20161114175924.GA23488@linux.vnet.ibm.com>
Currently, if the --jitter flag specifies jitter for a --build-only
run, the system will obediently build a kernel, refuse to launch it,
launch the requested number of jitter processes, and wait for the
specified kernel run time, which defaults to 30 minutes. This is
of course quite pointless.
This commit therefore disables jitter on build-only runs.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
tools/testing/selftests/rcutorture/bin/kvm.sh | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 0aed965f0062..3b3c1b693ee1 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -303,6 +303,7 @@ then
fi
___EOF___
awk < $T/cfgcpu.pack \
+ -v TORTURE_BUILDONLY="$TORTURE_BUILDONLY" \
-v CONFIGDIR="$CONFIGFRAG/" \
-v KVM="$KVM" \
-v ncpus=$cpus \
@@ -375,6 +376,10 @@ function dump(first, pastlast, batchnum)
njitter = ncpus;
else
njitter = ja[1];
+ if (TORTURE_BUILDONLY && njitter != 0) {
+ njitter = 0;
+ print "echo Build-only run, so suppressing jitter >> " rd "/log"
+ }
for (j = 0; j < njitter; j++)
print "jitter.sh " j " " dur " " ja[2] " " ja[3] "&"
print "wait"
--
2.5.2
^ permalink raw reply related
* Re: [PATCH nf-next 1/4] netfilter: nf_conntrack_tuple_common.h: fix #include
From: mikko.rapeli @ 2016-11-14 17:59 UTC (permalink / raw)
To: dcaratti
Cc: davem, fw, yoshfuji, jmorris, kadlec, pablo, kaber, coreteam,
netfilter-devel, kuznet
In-Reply-To: <1479132117.2430.66.camel@redhat.com>
Hi,
Am Mo. Nov. 14 15:01:57 2016 GMT+0100 schrieb Davide Caratti:
> On Fri, 2016-11-11 at 13:02 +0100, Davide Caratti wrote:
> >
> > > Is there a kernel side conflict between uapi and net/netns headers?
> >
> > Looks like a circular dependency is here, or nf_conntrack_tuple_common.h
> > is including the wrong netfilter.h. From within net/netns/conntrack.h I
> > can include only those UAPI files that don't include <linux/netfilter.h>
> > (for example, nf_conntrack_tcp.h that uses '2' instead of
> > IP_CT_DIR_MAX).
>
> hello Mikko,
>
> I looked at the dependency issue:
>
> current include/linux/netfilter.h needs include/net/net_namespace.h (i.e.
> nf_hook() needs struct net), and include/net/net_namespace.h needs
> include/net/netns/conntrack.h (i.e. struct net needs struct netns_ct).
>
> That's why it's not possible to do #include <linux/netfilter.h> in
> include/net/netns/conntrack.h, and it's not possible in
> include/net/netns/conntrack.h to include any linux/netfilter/*.h UAPI
> header where #include <linux/netfilter.h> line is present: the
> preprocessor will prefer including include/linux/netfilter.h before
> include/uapi/linux/netfilter.h, thus generating the dependency error.
Thanks for digging into this. In many other subsystems the kernel side headers start by including the matching uapi header and then add the kernel side stuff. It seems netfilter has not done this and the split to uapi is not always clear.
> One possible fix for the above issue is to modify
> include/uapi/nf_conntrack_tuple_common.h in a way that it avoids including
> <linux/netfilter.h> when kernel sources are being built, and still exposes
> to userspace applications the same contents as commit 1ffad83dffd6
> ("netfilter: fix include files for compilation"):
>
> <...>
> #include <linux/types.h>
> #ifndef __KERNEL__
> #include <linux/netfilter.h>
> #endif
> #include <linux/netfilter/nf_conntrack_common.h> /* for IP_CT_IS_REPLY */
> <...>
>
> BTW, include/uapi/linux/capi.h apparently does something similar with
> linux/kernelcapi.h. With the above change, also the output of
>
> $ pushd usr/include
> $ ../../scripts/headers_compile_test.sh -k | grep FAILED
> $ popd
>
> is preserved.
>
> Are you ok if I post a v2 where the above change (and a minor fix: use
> _UAPI_NF_CONNTRACK_TUPLE_COMMON_H in place of NF_CONNTRACK_TUPLE_COMMON_H
> on the first lines) is done to nf_conntrack_tuple_common.h?
Yes, this looks ok for me.
-Mikko
> regards,
> --
> davide
>
>
--
Sent from my Jolla
^ permalink raw reply
* Re: [PATCHSET] Add support for simplified async direct-io
From: Christoph Hellwig @ 2016-11-14 18:00 UTC (permalink / raw)
To: Jens Axboe; +Cc: Christoph Hellwig, axboe, linux-block
In-Reply-To: <71ce9ae3-214d-b248-3507-cc96bea41a9b@fb.com>
On Mon, Nov 14, 2016 at 10:47:46AM -0700, Jens Axboe wrote:
> This seems less clean in basically all ways, not sure I agree with you.
> We already have 4 vecs inlined in a generic bio, and we might as well
> use the fs bioset instead of creating our own. You also add a smallish
> dio to track things, I don't think we need that.
We need it unless we want unbounded allocations for the biovec. With a
1GB I/O we're at a page size allocation, and with 64MB I/Os that aren't
unheard of we'd be up to a 64 pages or an order 6 allocation which will
take down the VM. We also need to pin down all the user memory while
doing the I/O instead of having throttling on the bio mempool before
doing the get_user_pages.
^ permalink raw reply
* Re: [Qemu-devel] [PATCH v7 RFC] block/vxhs: Initial commit to add Veritas HyperScale VxHS block device support
From: ashish mittal @ 2016-11-14 18:01 UTC (permalink / raw)
To: Stefan Hajnoczi
Cc: qemu-devel, Paolo Bonzini, Kevin Wolf, Markus Armbruster,
Daniel P. Berrange, Jeff Cody, Fam Zheng, Ashish Mittal,
Ketan Nilangekar, Abhijit Dey, Venkatesha.Mg, Buddhi.Madhav
In-Reply-To: <CAJSP0QW3EGxW+PYmb=ThEfv33+BH1xTyxWBEY1YZO+w21wtgSw@mail.gmail.com>
Will look into these ASAP.
On Mon, Nov 14, 2016 at 7:05 AM, Stefan Hajnoczi <stefanha@gmail.com> wrote:
> On Wed, Sep 28, 2016 at 10:45 PM, Stefan Hajnoczi <stefanha@gmail.com> wrote:
>> On Tue, Sep 27, 2016 at 09:09:49PM -0700, Ashish Mittal wrote:
>>
>> Review of .bdrv_open() and .bdrv_aio_writev() code paths.
>>
>> The big issues I see in this driver and libqnio:
>>
>> 1. Showstoppers like broken .bdrv_open() and leaking memory on every
>> reply message.
>> 2. Insecure due to missing input validation (network packets and
>> configuration) and incorrect string handling.
>> 3. Not fully asynchronous so QEMU and the guest may hang.
>>
>> Please think about the whole codebase and not just the lines I've
>> pointed out in this review when fixing these sorts of issues. There may
>> be similar instances of these bugs elsewhere and it's important that
>> they are fixed so that this can be merged.
>
> Ping?
>
> You didn't respond to the comments I raised. The libqnio buffer
> overflows and other issues from this email are still present.
>
> I put a lot of time into reviewing this patch series and libqnio. If
> you want to get reviews please address feedback before sending a new
> patch series.
>
>>
>>> +/*
>>> + * Structure per vDisk maintained for state
>>> + */
>>> +typedef struct BDRVVXHSState {
>>> + int fds[2];
>>> + int64_t vdisk_size;
>>> + int64_t vdisk_blocks;
>>> + int64_t vdisk_flags;
>>> + int vdisk_aio_count;
>>> + int event_reader_pos;
>>> + VXHSAIOCB *qnio_event_acb;
>>> + void *qnio_ctx;
>>> + QemuSpin vdisk_lock; /* Lock to protect BDRVVXHSState */
>>> + QemuSpin vdisk_acb_lock; /* Protects ACB */
>>
>> These comments are insufficient for documenting locking. Not all fields
>> are actually protected by these locks. Please order fields according to
>> lock coverage:
>>
>> typedef struct VXHSAIOCB {
>> ...
>>
>> /* Protected by BDRVVXHSState->vdisk_acb_lock */
>> int segments;
>> ...
>> };
>>
>> typedef struct BDRVVXHSState {
>> ...
>>
>> /* Protected by vdisk_lock */
>> QemuSpin vdisk_lock;
>> int vdisk_aio_count;
>> QSIMPLEQ_HEAD(aio_retryq, VXHSAIOCB) vdisk_aio_retryq;
>> ...
>> }
>>
>>> +static void vxhs_qnio_iio_close(BDRVVXHSState *s, int idx)
>>> +{
>>> + /*
>>> + * Close vDisk device
>>> + */
>>> + if (s->vdisk_hostinfo[idx].vdisk_rfd >= 0) {
>>> + iio_devclose(s->qnio_ctx, 0, s->vdisk_hostinfo[idx].vdisk_rfd);
>>
>> libqnio comment:
>> Why does iio_devclose() take an unused cfd argument? Perhaps it can be
>> dropped.
>>
>>> + s->vdisk_hostinfo[idx].vdisk_rfd = -1;
>>> + }
>>> +
>>> + /*
>>> + * Close QNIO channel against cached channel-fd
>>> + */
>>> + if (s->vdisk_hostinfo[idx].qnio_cfd >= 0) {
>>> + iio_close(s->qnio_ctx, s->vdisk_hostinfo[idx].qnio_cfd);
>>
>> libqnio comment:
>> Why does iio_devclose() take an int32_t cfd argument but iio_close()
>> takes a uint32_t cfd argument?
>>
>>> + s->vdisk_hostinfo[idx].qnio_cfd = -1;
>>> + }
>>> +}
>>> +
>>> +static int vxhs_qnio_iio_open(int *cfd, const char *of_vsa_addr,
>>> + int *rfd, const char *file_name)
>>> +{
>>> + /*
>>> + * Open qnio channel to storage agent if not opened before.
>>> + */
>>> + if (*cfd < 0) {
>>> + *cfd = iio_open(global_qnio_ctx, of_vsa_addr, 0);
>>
>> libqnio comments:
>>
>> 1.
>> There is a buffer overflow in qnio_create_channel(). strncpy() is used
>> incorrectly so long hostname or port (both can be 99 characters long)
>> will overflow channel->name[] (64 characters) or channel->port[] (8
>> characters).
>>
>> strncpy(channel->name, hostname, strlen(hostname) + 1);
>> strncpy(channel->port, port, strlen(port) + 1);
>>
>> The third argument must be the size of the *destination* buffer, not the
>> source buffer. Also note that strncpy() doesn't NUL-terminate the
>> destination string so you must do that manually to ensure there is a NUL
>> byte at the end of the buffer.
>>
>> 2.
>> channel is leaked in the "Failed to open single connection" error case
>> in qnio_create_channel().
>>
>> 3.
>> If host is longer the 63 characters then the ioapi_ctx->channels and
>> qnio_ctx->channels maps will use different keys due to string truncation
>> in qnio_create_channel(). This means "Channel already exists" in
>> qnio_create_channel() and possibly other things will not work as
>> expected.
>>
>>> + if (*cfd < 0) {
>>> + trace_vxhs_qnio_iio_open(of_vsa_addr);
>>> + return -ENODEV;
>>> + }
>>> + }
>>> +
>>> + /*
>>> + * Open vdisk device
>>> + */
>>> + *rfd = iio_devopen(global_qnio_ctx, *cfd, file_name, 0);
>>
>> libqnio comment:
>> Buffer overflow in iio_devopen() since chandev[128] is not large enough
>> to hold channel[100] + " " + devpath[arbitrary length] chars:
>>
>> sprintf(chandev, "%s %s", channel, devpath);
>>
>>> +
>>> + if (*rfd < 0) {
>>> + if (*cfd >= 0) {
>>
>> This check is always true. Otherwise the return -ENODEV would have been
>> taken above. The if statement isn't necessary.
>>
>>> +static void vxhs_check_failover_status(int res, void *ctx)
>>> +{
>>> + BDRVVXHSState *s = ctx;
>>> +
>>> + if (res == 0) {
>>> + /* found failover target */
>>> + s->vdisk_cur_host_idx = s->vdisk_ask_failover_idx;
>>> + s->vdisk_ask_failover_idx = 0;
>>> + trace_vxhs_check_failover_status(
>>> + s->vdisk_hostinfo[s->vdisk_cur_host_idx].hostip,
>>> + s->vdisk_guid);
>>> + qemu_spin_lock(&s->vdisk_lock);
>>> + OF_VDISK_RESET_IOFAILOVER_IN_PROGRESS(s);
>>> + qemu_spin_unlock(&s->vdisk_lock);
>>> + vxhs_handle_queued_ios(s);
>>> + } else {
>>> + /* keep looking */
>>> + trace_vxhs_check_failover_status_retry(s->vdisk_guid);
>>> + s->vdisk_ask_failover_idx++;
>>> + if (s->vdisk_ask_failover_idx == s->vdisk_nhosts) {
>>> + /* pause and cycle through list again */
>>> + sleep(QNIO_CONNECT_RETRY_SECS);
>>
>> This code is called from a QEMU thread via vxhs_aio_rw(). It is not
>> permitted to call sleep() since it will freeze QEMU and probably the
>> guest.
>>
>> If you need a timer you can use QEMU's timer APIs. See aio_timer_new(),
>> timer_new_ns(), timer_mod(), timer_del(), timer_free().
>>
>>> + s->vdisk_ask_failover_idx = 0;
>>> + }
>>> + res = vxhs_switch_storage_agent(s);
>>> + }
>>> +}
>>> +
>>> +static int vxhs_failover_io(BDRVVXHSState *s)
>>> +{
>>> + int res = 0;
>>> +
>>> + trace_vxhs_failover_io(s->vdisk_guid);
>>> +
>>> + s->vdisk_ask_failover_idx = 0;
>>> + res = vxhs_switch_storage_agent(s);
>>> +
>>> + return res;
>>> +}
>>> +
>>> +static void vxhs_iio_callback(int32_t rfd, uint32_t reason, void *ctx,
>>> + uint32_t error, uint32_t opcode)
>>
>> This function is doing too much. Especially the failover code should
>> run in the AioContext since it's complex. Don't do failover here
>> because this function is outside the AioContext lock. Do it from
>> AioContext using a QEMUBH like block/rbd.c.
>>
>>> +static int32_t
>>> +vxhs_qnio_iio_writev(void *qnio_ctx, uint32_t rfd, QEMUIOVector *qiov,
>>> + uint64_t offset, void *ctx, uint32_t flags)
>>> +{
>>> + struct iovec cur;
>>> + uint64_t cur_offset = 0;
>>> + uint64_t cur_write_len = 0;
>>> + int segcount = 0;
>>> + int ret = 0;
>>> + int i, nsio = 0;
>>> + int iovcnt = qiov->niov;
>>> + struct iovec *iov = qiov->iov;
>>> +
>>> + errno = 0;
>>> + cur.iov_base = 0;
>>> + cur.iov_len = 0;
>>> +
>>> + ret = iio_writev(qnio_ctx, rfd, iov, iovcnt, offset, ctx, flags);
>>
>> libqnio comments:
>>
>> 1.
>> There are blocking connect(2) and getaddrinfo(3) calls in iio_writev()
>> so this may hang for arbitrary amounts of time. This is not permitted
>> in .bdrv_aio_readv()/.bdrv_aio_writev(). Please make qnio actually
>> asynchronous.
>>
>> 2.
>> Where does client_callback() free reply? It looks like every reply
>> message causes a memory leak!
>>
>> 3.
>> Buffer overflow in iio_writev() since device[128] cannot fit the device
>> string generated from the vdisk_guid.
>>
>> 4.
>> Buffer overflow in iio_writev() due to
>> strncpy(msg->hinfo.target,device,strlen(device)) where device[128] is
>> larger than target[64]. Also note the previous comments about strncpy()
>> usage.
>>
>> 5.
>> I don't see any endianness handling or portable alignment of struct
>> fields in the network protocol code. Binary network protocols need to
>> take care of these issue for portability. This means libqnio compiled
>> for different architectures will not work. Do you plan to support any
>> other architectures besides x86?
>>
>> 6.
>> The networking code doesn't look robust: kvset uses assert() on input
>> from the network so the other side of the connection could cause SIGABRT
>> (coredump), the client uses the msg pointer as the cookie for the
>> response packet so the server can easily crash the client by sending a
>> bogus cookie value, etc. Even on the client side these things are
>> troublesome but on a server they are guaranteed security issues. I
>> didn't look into it deeply. Please audit the code.
>>
>>> +static int vxhs_qemu_init(QDict *options, BDRVVXHSState *s,
>>> + int *cfd, int *rfd, Error **errp)
>>> +{
>>> + QDict *backing_options = NULL;
>>> + QemuOpts *opts, *tcp_opts;
>>> + const char *vxhs_filename;
>>> + char *of_vsa_addr = NULL;
>>> + Error *local_err = NULL;
>>> + const char *vdisk_id_opt;
>>> + char *file_name = NULL;
>>> + size_t num_servers = 0;
>>> + char *str = NULL;
>>> + int ret = 0;
>>> + int i;
>>> +
>>> + opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
>>> + qemu_opts_absorb_qdict(opts, options, &local_err);
>>> + if (local_err) {
>>> + error_propagate(errp, local_err);
>>> + ret = -EINVAL;
>>> + goto out;
>>> + }
>>> +
>>> + vxhs_filename = qemu_opt_get(opts, VXHS_OPT_FILENAME);
>>> + if (vxhs_filename) {
>>> + trace_vxhs_qemu_init_filename(vxhs_filename);
>>> + }
>>> +
>>> + vdisk_id_opt = qemu_opt_get(opts, VXHS_OPT_VDISK_ID);
>>> + if (!vdisk_id_opt) {
>>> + error_setg(&local_err, QERR_MISSING_PARAMETER, VXHS_OPT_VDISK_ID);
>>> + ret = -EINVAL;
>>> + goto out;
>>> + }
>>> + s->vdisk_guid = g_strdup(vdisk_id_opt);
>>> + trace_vxhs_qemu_init_vdisk(vdisk_id_opt);
>>> +
>>> + num_servers = qdict_array_entries(options, VXHS_OPT_SERVER);
>>> + if (num_servers < 1) {
>>> + error_setg(&local_err, QERR_MISSING_PARAMETER, "server");
>>> + ret = -EINVAL;
>>> + goto out;
>>> + } else if (num_servers > VXHS_MAX_HOSTS) {
>>> + error_setg(&local_err, QERR_INVALID_PARAMETER, "server");
>>> + error_append_hint(errp, "Maximum %d servers allowed.\n",
>>> + VXHS_MAX_HOSTS);
>>> + ret = -EINVAL;
>>> + goto out;
>>> + }
>>> + trace_vxhs_qemu_init_numservers(num_servers);
>>> +
>>> + for (i = 0; i < num_servers; i++) {
>>> + str = g_strdup_printf(VXHS_OPT_SERVER"%d.", i);
>>> + qdict_extract_subqdict(options, &backing_options, str);
>>> +
>>> + /* Create opts info from runtime_tcp_opts list */
>>> + tcp_opts = qemu_opts_create(&runtime_tcp_opts, NULL, 0, &error_abort);
>>> + qemu_opts_absorb_qdict(tcp_opts, backing_options, &local_err);
>>> + if (local_err) {
>>> + qdict_del(backing_options, str);
>>
>> backing_options is leaked and there's no need to delete the str key.
>>
>>> + qemu_opts_del(tcp_opts);
>>> + g_free(str);
>>> + ret = -EINVAL;
>>> + goto out;
>>> + }
>>> +
>>> + s->vdisk_hostinfo[i].hostip = g_strdup(qemu_opt_get(tcp_opts,
>>> + VXHS_OPT_HOST));
>>> + s->vdisk_hostinfo[i].port = g_ascii_strtoll(qemu_opt_get(tcp_opts,
>>> + VXHS_OPT_PORT),
>>> + NULL, 0);
>>
>> This will segfault if the port option was missing.
>>
>>> +
>>> + s->vdisk_hostinfo[i].qnio_cfd = -1;
>>> + s->vdisk_hostinfo[i].vdisk_rfd = -1;
>>> + trace_vxhs_qemu_init(s->vdisk_hostinfo[i].hostip,
>>> + s->vdisk_hostinfo[i].port);
>>
>> It's not safe to use the %s format specifier for a trace event with a
>> NULL value. In the case where hostip is NULL this could crash on some
>> systems.
>>
>>> +
>>> + qdict_del(backing_options, str);
>>> + qemu_opts_del(tcp_opts);
>>> + g_free(str);
>>> + }
>>
>> backing_options is leaked.
>>
>>> +
>>> + s->vdisk_nhosts = i;
>>> + s->vdisk_cur_host_idx = 0;
>>> + file_name = g_strdup_printf("%s%s", vdisk_prefix, s->vdisk_guid);
>>> + of_vsa_addr = g_strdup_printf("of://%s:%d",
>>> + s->vdisk_hostinfo[s->vdisk_cur_host_idx].hostip,
>>> + s->vdisk_hostinfo[s->vdisk_cur_host_idx].port);
>>
>> Can we get here with num_servers == 0? In that case this would access
>> uninitialized memory. I guess num_servers == 0 does not make sense and
>> there should be an error case for it.
>>
>>> +
>>> + /*
>>> + * .bdrv_open() and .bdrv_create() run under the QEMU global mutex.
>>> + */
>>> + if (global_qnio_ctx == NULL) {
>>> + global_qnio_ctx = vxhs_setup_qnio();
>>
>> libqnio comment:
>> The client epoll thread should mask all signals (like
>> qemu_thread_create()). Otherwise it may receive signals that it cannot
>> deal with.
>>
>>> + if (global_qnio_ctx == NULL) {
>>> + error_setg(&local_err, "Failed vxhs_setup_qnio");
>>> + ret = -EINVAL;
>>> + goto out;
>>> + }
>>> + }
>>> +
>>> + ret = vxhs_qnio_iio_open(cfd, of_vsa_addr, rfd, file_name);
>>> + if (!ret) {
>>> + error_setg(&local_err, "Failed qnio_iio_open");
>>> + ret = -EIO;
>>> + }
>>
>> The return value of vxhs_qnio_iio_open() is 0 for success or -errno for
>> error.
>>
>> I guess you never ran this code! The block driver won't even open
>> successfully.
>>
>>> +
>>> +out:
>>> + g_free(file_name);
>>> + g_free(of_vsa_addr);
>>> + qemu_opts_del(opts);
>>> +
>>> + if (ret < 0) {
>>> + for (i = 0; i < num_servers; i++) {
>>> + g_free(s->vdisk_hostinfo[i].hostip);
>>> + }
>>> + g_free(s->vdisk_guid);
>>> + s->vdisk_guid = NULL;
>>> + errno = -ret;
>>
>> There is no need to set errno here. The return value already contains
>> the error and the caller doesn't look at errno.
>>
>>> + }
>>> + error_propagate(errp, local_err);
>>> +
>>> + return ret;
>>> +}
>>> +
>>> +static int vxhs_open(BlockDriverState *bs, QDict *options,
>>> + int bdrv_flags, Error **errp)
>>> +{
>>> + BDRVVXHSState *s = bs->opaque;
>>> + AioContext *aio_context;
>>> + int qemu_qnio_cfd = -1;
>>> + int device_opened = 0;
>>> + int qemu_rfd = -1;
>>> + int ret = 0;
>>> + int i;
>>> +
>>> + ret = vxhs_qemu_init(options, s, &qemu_qnio_cfd, &qemu_rfd, errp);
>>> + if (ret < 0) {
>>> + trace_vxhs_open_fail(ret);
>>> + return ret;
>>> + }
>>> +
>>> + device_opened = 1;
>>> + s->qnio_ctx = global_qnio_ctx;
>>> + s->vdisk_hostinfo[0].qnio_cfd = qemu_qnio_cfd;
>>> + s->vdisk_hostinfo[0].vdisk_rfd = qemu_rfd;
>>> + s->vdisk_size = 0;
>>> + QSIMPLEQ_INIT(&s->vdisk_aio_retryq);
>>> +
>>> + /*
>>> + * Create a pipe for communicating between two threads in different
>>> + * context. Set handler for read event, which gets triggered when
>>> + * IO completion is done by non-QEMU context.
>>> + */
>>> + ret = qemu_pipe(s->fds);
>>> + if (ret < 0) {
>>> + trace_vxhs_open_epipe('.');
>>> + ret = -errno;
>>> + goto errout;
>>
>> This leaks s->vdisk_guid, s->vdisk_hostinfo[i].hostip, etc.
>> bdrv_close() will not be called so this function must do cleanup itself.
>>
>>> + }
>>> + fcntl(s->fds[VDISK_FD_READ], F_SETFL, O_NONBLOCK);
>>> +
>>> + aio_context = bdrv_get_aio_context(bs);
>>> + aio_set_fd_handler(aio_context, s->fds[VDISK_FD_READ],
>>> + false, vxhs_aio_event_reader, NULL, s);
>>> +
>>> + /*
>>> + * Initialize the spin-locks.
>>> + */
>>> + qemu_spin_init(&s->vdisk_lock);
>>> + qemu_spin_init(&s->vdisk_acb_lock);
>>> +
>>> + return 0;
>>> +
>>> +errout:
>>> + /*
>>> + * Close remote vDisk device if it was opened earlier
>>> + */
>>> + if (device_opened) {
>>
>> This is always true. The device_opened variable can be removed.
>>
>>> +/*
>>> + * This allocates QEMU-VXHS callback for each IO
>>> + * and is passed to QNIO. When QNIO completes the work,
>>> + * it will be passed back through the callback.
>>> + */
>>> +static BlockAIOCB *vxhs_aio_rw(BlockDriverState *bs,
>>> + int64_t sector_num, QEMUIOVector *qiov,
>>> + int nb_sectors,
>>> + BlockCompletionFunc *cb,
>>> + void *opaque, int iodir)
>>> +{
>>> + VXHSAIOCB *acb = NULL;
>>> + BDRVVXHSState *s = bs->opaque;
>>> + size_t size;
>>> + uint64_t offset;
>>> + int iio_flags = 0;
>>> + int ret = 0;
>>> + void *qnio_ctx = s->qnio_ctx;
>>> + uint32_t rfd = s->vdisk_hostinfo[s->vdisk_cur_host_idx].vdisk_rfd;
>>> +
>>> + offset = sector_num * BDRV_SECTOR_SIZE;
>>> + size = nb_sectors * BDRV_SECTOR_SIZE;
>>> +
>>> + acb = qemu_aio_get(&vxhs_aiocb_info, bs, cb, opaque);
>>> + /*
>>> + * Setup or initialize VXHSAIOCB.
>>> + * Every single field should be initialized since
>>> + * acb will be picked up from the slab without
>>> + * initializing with zero.
>>> + */
>>> + acb->io_offset = offset;
>>> + acb->size = size;
>>> + acb->ret = 0;
>>> + acb->flags = 0;
>>> + acb->aio_done = VXHS_IO_INPROGRESS;
>>> + acb->segments = 0;
>>> + acb->buffer = 0;
>>> + acb->qiov = qiov;
>>> + acb->direction = iodir;
>>> +
>>> + qemu_spin_lock(&s->vdisk_lock);
>>> + if (OF_VDISK_FAILED(s)) {
>>> + trace_vxhs_aio_rw(s->vdisk_guid, iodir, size, offset);
>>> + qemu_spin_unlock(&s->vdisk_lock);
>>> + goto errout;
>>> + }
>>> + if (OF_VDISK_IOFAILOVER_IN_PROGRESS(s)) {
>>> + QSIMPLEQ_INSERT_TAIL(&s->vdisk_aio_retryq, acb, retry_entry);
>>> + s->vdisk_aio_retry_qd++;
>>> + OF_AIOCB_FLAGS_SET_QUEUED(acb);
>>> + qemu_spin_unlock(&s->vdisk_lock);
>>> + trace_vxhs_aio_rw_retry(s->vdisk_guid, acb, 1);
>>> + goto out;
>>> + }
>>> + s->vdisk_aio_count++;
>>> + qemu_spin_unlock(&s->vdisk_lock);
>>> +
>>> + iio_flags = (IIO_FLAG_DONE | IIO_FLAG_ASYNC);
>>> +
>>> + switch (iodir) {
>>> + case VDISK_AIO_WRITE:
>>> + vxhs_inc_acb_segment_count(acb, 1);
>>> + ret = vxhs_qnio_iio_writev(qnio_ctx, rfd, qiov,
>>> + offset, (void *)acb, iio_flags);
>>> + break;
>>> + case VDISK_AIO_READ:
>>> + vxhs_inc_acb_segment_count(acb, 1);
>>> + ret = vxhs_qnio_iio_readv(qnio_ctx, rfd, qiov,
>>> + offset, (void *)acb, iio_flags);
>>> + break;
>>> + default:
>>> + trace_vxhs_aio_rw_invalid(iodir);
>>> + goto errout;
>>
>> s->vdisk_aio_count must be decremented before returning.
>>
>>> +static void vxhs_close(BlockDriverState *bs)
>>> +{
>>> + BDRVVXHSState *s = bs->opaque;
>>> + int i;
>>> +
>>> + trace_vxhs_close(s->vdisk_guid);
>>> + close(s->fds[VDISK_FD_READ]);
>>> + close(s->fds[VDISK_FD_WRITE]);
>>> +
>>> + /*
>>> + * Clearing all the event handlers for oflame registered to QEMU
>>> + */
>>> + aio_set_fd_handler(bdrv_get_aio_context(bs), s->fds[VDISK_FD_READ],
>>> + false, NULL, NULL, NULL);
>>
>> Please remove the event handler before closing the fd. I don't think it
>> matters in this case but in other scenarios there could be race
>> conditions if another thread opens an fd and the file descriptor number
>> is reused.
^ permalink raw reply
* Re: Freescale Yocto Question - Building imx6dl-riotboard
From: Eric.Zaluzec @ 2016-11-14 18:00 UTC (permalink / raw)
To: daiane.list; +Cc: meta-freescale
In-Reply-To: <CA+jg_OWhzifJv1FEAWpMbL_ijuZv_SWZNQOhHmeWxbfaDfmzZQ@mail.gmail.com>
Thanks Daiane, maybe I am getting ahead of myself with the questions.
Under the FSL Community BSP's "Support Board List", I see the "imx6dl-riotboard / RIotboard / i.MX6S / meta-fsl-arm-extra".
http://freescale.github.io/doc/release-notes/2.1/index.html#supported-boards
Is this imx6dl-riotboard BSP and machine configuration file the one that can run on the RIoTboard evaluation platform found on http://riotboard.org/ ?
If it is not, do you have reference or a web URL for the one RIoTboard that you support?
Regards,
-Eric Zaluzec
(Eric.Zaluzec@Emerson.com)
-----Original Message-----
From: angolini@gmail.com [mailto:angolini@gmail.com] On Behalf Of Daiane Angolini
Sent: Monday, November 14, 2016 11:20 AM
To: Zaluzec, Eric [NETPWR/AL]
Cc: meta-freescale@yoctoproject.org
Subject: Re: [meta-freescale] Freescale Yocto Question - Building imx6dl-riotboard
On Fri, Nov 11, 2016 at 3:12 PM, <Eric.Zaluzec@emerson.com> wrote:
> Greeting,
>
> I have a quick question concerning the imx6dl-riotboard machine
> configuration file, maintained by the Yocto Freescale community.
>
> We have an upcoming project for which we are considering a i.MX6 Dual
> Lite processor. But since there are no Dual Lite evaluation boards, at
> this time, we were provided an i.mx6 solo RIoTboard to use for initial
> testing, by Avnet and NXP distributors.
>
>
>
> First off, thank you for providing up-to-date Yocto build repositories
> and documentation! This makes kicking-off a new Yocto BSP Project much simpler!
> Cheers.
>
> I read the Freescale Yocto User Guide here:
> http://www.bcmcom.com/CustomerDL/AR6MX/Yocto/Freescale_Yocto_Project_U
> ser's_Guide.pdf I then read the RIoTboard Yocto build guide here:
> https://www.element14.com/community/community/designcenter/single-boar
> d-computers/riotboard/blog/2014/09/22/riotboard-yocto-part1-getting-st
> arted
>
> Using both resources, I successfully built a Yocto image and was able
> to install onto my RIoTboard.
>
>
>
>
>
> Now, using Yocto, I would like to build a RIoTboard image with a fido
> or krogoth branch of Yocto, to make use of the updated packages &
> bitbake recipes, like boost and java, These versions are dependencies
> to my metadata layer’s packages.
>
> I went to the fsl-arm-yocto-bsp git repository site and found the
> imx-4.1-krogoth branch:
> http://git.freescale.com/git/cgit.cgi/imx/fsl-arm-yocto-bsp.git/?h=imx
> -4.1-krogoth
>
>
>
> I followed the User Guide steps, but this time cloned the
> imx-4.1-krogoth branch. I noticed the riotboard.conf machine
> configuration file no longer existed, but a imx6dl-riotboard machine
> was present in the meta-fsl-arm-extra & meta-freescale-3rdparty
> metadata layers. I successfully built an image with this machine conf
> file, but then realized that it was ‘dl’ (Dual Lite?) and would not
> boot with the solo RIoTboard that I was using.
>
>
>
> Question :
>
> Are there any branches on for the fsl-arm-yocto-bsp repository that
> are fido/jethro/krogoth compatible, that include the riotboard solo
> machine configuration file?
> http://git.freescale.com/git/cgit.cgi/imx/fsl-arm-yocto-bsp.git
>
> If not, is it possible for users, like me, to base a riotboard solo
> machine conf file off the imx6dl-riotboard machine and create a
> successful BSP image? Or are these unavoidable conflicts?
>
>
>
> The critical piece here is not necessarily having a v4.1 kernel but
> just the use of the updated package recipes & the dependency to custom
> packages trying to be installed & tested on the riotboard!
>
>
>
> Any help, suggestions, or feedback would greatly be appreciated! Right
> now I am just tinkering with learning about the riotboard machine conf
> file to see if I can port it to the imx-4.1-krogoth branch.
>
I'm not sure you're going to be able to use imx-4.1-krogoth branch with the riot board. Please, take a look at [1]
We have support for one riot board, double check if this is what you are looking for.
[1] http://freescale.github.io/doc/release-notes/2.1/index.html#the-differences-between-project-name-and-freescale-release-name
Daiane
>
>
> Thanks!
> -Eric Zaluzec
> (Eric.Zaluzec@Emerson.com)
>
>
>
>
> --
> _______________________________________________
> meta-freescale mailing list
> meta-freescale@yoctoproject.org
> https://lists.yoctoproject.org/listinfo/meta-freescale
>
^ permalink raw reply
* Re: [RFC/PATCH 0/2] git diff <(command1) <(command2)
From: Junio C Hamano @ 2016-11-14 18:01 UTC (permalink / raw)
To: Michael J Gruber
Cc: Johannes Schindelin, Jacob Keller, Dennis Kaarsemaker,
Git mailing list
In-Reply-To: <0c39be16-76f8-0800-41a2-b7b1dccdd652@drmicha.warpmail.net>
Michael J Gruber <git@drmicha.warpmail.net> writes:
> *My* idea of --no-index was for it to behave as similar to the
> --index-version as possible, regarding formatting etc., and to be a good
> substitute for ordinary diff. The proposed patch achieves exactly that -
Does it? It looks to me that it does a lot more.
> why should a *file* argument (which is not a pathspec in --no-index
> mode) not be treated in the same way in which every other command treats
> a file argument? The patch un-breaks the most natural expectation.
I think a filename given as a command line argument, e.g. <(cmd), is
now treated more sensibly with [2/2]. Something that is not a
directory to be descended into and is not a regular file needs to be
made into a form that we can use as a blob, and reading it into an
in-core buffer is a workable way to do so.
However, when taken together with [1/2], doesn't the proposed patch
"achieves" a lot more than "exactly that", namely, by not treating
symbolic links discovered during traversals of directories given
from the command line as such and dereferencing?
^ permalink raw reply
* [U-Boot] [ANN] U-Boot v2016.11 is released
From: Jagan Teki @ 2016-11-14 18:02 UTC (permalink / raw)
To: u-boot
In-Reply-To: <20161114164605.GI27304@bill-the-cat>
On Mon, Nov 14, 2016 at 10:16 PM, Tom Rini <trini@konsulko.com> wrote:
> Hey all,
>
> I've released v2016.11 and it's now live on git and FTP and ACD (along
> with PGP sig file).
>
> In many ways it feels good to say that the highlights of the last
> release once again apply. We've had more DM conversion work, Kconfig
> conversion work and arch / SoC / platform updates. We've also had some
> important filesystem fixes come in and equally as important, test cases
> added. We also now support the new and default enabled ext4 64bit flag
> (thanks again Stefan!).
>
> And what I want to highlight here is going forward both relative ease
> of, and expectations on testing. Last time I talked about test.py and
> how I'm using it more myself now. This time, I want to talk about
> travis-ci support. If you use github you can get a more-or-less world
> build and test.py for all of the QEMU targets we support today done in
> about 2 and a half hours, wall clock. I don't expect people to do this
> for iterative development or "trivial" changes, but if you have a series
> that touches a lot of areas I think it's reasonable to expect that
> you'll test things out this way. And I'll say now it's not 100%. About
> once every 10 builds I'll have to go and re-start a sub-job because it
> will fail to fetch one of the PPAs we use for no apparent reason. But
> to be clear, it's a few minutes worth of setup and then you push a
> change and you get build coverage and test coverage. This is really
> awesome and I wish I had been paying more attention to this sooner.
>
> As always, I know I'm missing pointing out a few things that I should
> point out and would encourage folks to chime in if there's anything they
> would like to highlight.
>
> Thanks again everyone!
Unfortunately "Amarula Solutions" is not listed in Employers list [1]
for this I sent a domain-map mail to Wolfgang Denk during MW, any edit
for this?
[1] http://www.denx.de/wiki/U-Boot/UbootStat_2016_11
--
Jagan Teki
Free Software Engineer | www.openedev.com
U-Boot, Linux | Upstream Maintainer
Hyderabad, India.
^ permalink raw reply
* Re: [PATCHSET] Add support for simplified async direct-io
From: Jens Axboe @ 2016-11-14 18:02 UTC (permalink / raw)
To: Christoph Hellwig; +Cc: axboe, linux-block
In-Reply-To: <20161114180052.GA24476@infradead.org>
On 11/14/2016 11:00 AM, Christoph Hellwig wrote:
> On Mon, Nov 14, 2016 at 10:47:46AM -0700, Jens Axboe wrote:
>> This seems less clean in basically all ways, not sure I agree with you.
>> We already have 4 vecs inlined in a generic bio, and we might as well
>> use the fs bioset instead of creating our own. You also add a smallish
>> dio to track things, I don't think we need that.
>
> We need it unless we want unbounded allocations for the biovec. With a
> 1GB I/O we're at a page size allocation, and with 64MB I/Os that aren't
> unheard of we'd be up to a 64 pages or an order 6 allocation which will
> take down the VM. We also need to pin down all the user memory while
> doing the I/O instead of having throttling on the bio mempool before
> doing the get_user_pages.
Just add the iterator and loop for every X pages? We can even put a plug
around it, if we have to.
--
Jens Axboe
^ permalink raw reply
* Re: [Qemu-devel] [PATCH v6 1/2] block/vxhs.c: Add support for a new block device type called "vxhs"
From: Fam Zheng @ 2016-11-14 18:03 UTC (permalink / raw)
To: Stefan Hajnoczi
Cc: Ashish Mittal, qemu-devel, pbonzini, kwolf, armbru, berrange,
jcody, ashish.mittal, Rakesh.Ranjan, Buddhi.Madhav,
Ketan.Nilangekar, Abhijit.Dey, Venkatesha.Mg
In-Reply-To: <20161114165034.GA1352@stefanha-x1.localdomain>
On Mon, 11/14 16:50, Stefan Hajnoczi wrote:
> On Mon, Nov 14, 2016 at 11:49:06PM +0800, Fam Zheng wrote:
> > On Mon, 11/14 15:07, Stefan Hajnoczi wrote:
> > > On Mon, Nov 07, 2016 at 04:59:44PM -0800, Ashish Mittal wrote:
> > > > diff --git a/block/vxhs.c b/block/vxhs.c
> > > > new file mode 100644
> > > > index 0000000..8913e8f
> > > > --- /dev/null
> > > > +++ b/block/vxhs.c
> > > > @@ -0,0 +1,689 @@
> > > > +/*
> > > > + * QEMU Block driver for Veritas HyperScale (VxHS)
> > > > + *
> > > > + * This work is licensed under the terms of the GNU GPL, version 2 or later.
> > > > + * See the COPYING file in the top-level directory.
> > > > + *
> > > > + */
> > > > +
> > > > +#include "qemu/osdep.h"
> > > > +#include "block/block_int.h"
> > > > +#include <qnio/qnio_api.h>
> > >
> > > Please move system headers (<>) above user headers (""). This way you
> > > can be sure the system header isn't affected by any macros defined by
> > > user headers.
> >
> > Yes, but still after "qemu/osdep.h", which prepares necessary bits for any other
> > headers.
>
> I disagree. qnio_api.h is a third-party library that doesn't need QEMU
> headers to fix up the environment for it.
>
> By including osdep.h first you mask bugs in qnio_api.h. Perhaps
> qnio_api.h forgot to include a header and we won't notice because
> osdep.h happened to bring in those headers first...
>
> Can you explain the rationale for your statement?
I point this out just because I rememebr this effort happened not long ago,
which is to make osdep.h always included first (there is also a
./scripts/clean-includes to reorder the include):
https://lists.nongnu.org/archive/html/qemu-devel/2015-12/msg01110.html
I think it is mostly for uncommon compilers that should have little to do with
libqnio in particular, but this is a common practice of current QEMU.
Fam
^ permalink raw reply
* Re: [PATCHSET] Add support for simplified async direct-io
From: Christoph Hellwig @ 2016-11-14 18:05 UTC (permalink / raw)
To: Jens Axboe; +Cc: Christoph Hellwig, axboe, linux-block
In-Reply-To: <4f30a528-9996-4c6a-9513-8aa2054e4d4b@fb.com>
On Mon, Nov 14, 2016 at 11:02:47AM -0700, Jens Axboe wrote:
> > We need it unless we want unbounded allocations for the biovec. With a
> > 1GB I/O we're at a page size allocation, and with 64MB I/Os that aren't
> > unheard of we'd be up to a 64 pages or an order 6 allocation which will
> > take down the VM. We also need to pin down all the user memory while
> > doing the I/O instead of having throttling on the bio mempool before
> > doing the get_user_pages.
>
> Just add the iterator and loop for every X pages? We can even put a plug
> around it, if we have to.
That's pretty much what my patch does..
^ permalink raw reply
* [PATCH v3 00/11]powerpc: "paca->soft_enabled" based local atomic operation implementation
From: Madhavan Srinivasan @ 2016-11-14 18:04 UTC (permalink / raw)
To: mpe, benh; +Cc: anton, paulus, npiggin, linuxppc-dev, Madhavan Srinivasan
Local atomic operations are fast and highly reentrant per CPU counters.
Used for percpu variable updates. Local atomic operations only guarantee
variable modification atomicity wrt the CPU which owns the data and
these needs to be executed in a preemption safe way.
Here is the design of the patchset. Since local_* operations
are only need to be atomic to interrupts (IIUC), we have two options.
Either replay the "op" if interrupted or replay the interrupt after
the "op". Initial patchset posted was based on implementing local_* operation
based on CR5 which replay's the "op". Patchset had issues in case of
rewinding the address pointor from an array. This make the slow patch
really slow. Since CR5 based implementation proposed using __ex_table to find
the rewind address, this rasied concerns about size of __ex_table and vmlinux.
https://lists.ozlabs.org/pipermail/linuxppc-dev/2014-December/123115.html
But this patchset uses Benjamin Herrenschmidt suggestion of using
arch_local_irq_disable() to soft_disable interrupts (including PMIs).
After finishing the "op", arch_local_irq_restore() called and correspondingly
interrupts are replayed if any occured.
Current paca->soft_enabled logic is reserved and MASKABLE_EXCEPTION_* macros
are extended to support this feature.
patch re-write the current local_* functions to use arch_local_irq_disbale.
Base flow for each function is
{
powerpc_local_irq_pmu_save(flags)
load
..
store
powerpc_local_irq_pmu_restore(flags)
}
Reason for the approach is that, currently l[w/d]arx/st[w/d]cx.
instruction pair is used for local_* operations, which are heavy
on cycle count and they dont support a local variant. So to
see whether the new implementation helps, used a modified
version of Rusty's benchmark code on local_t.
https://lkml.org/lkml/2008/12/16/450
Modifications to Rusty's benchmark code:
- Executed only local_t test
Here are the values with the patch.
Time in ns per iteration
Local_t Without Patch With Patch
_inc 28 8
_add 28 8
_read 3 3
_add_return 28 7
Currently only asm/local.h has been rewrite, and also
the entire change is tested only in PPC64 (pseries guest)
and PPC64 LE host. Have only compile tested ppc64e_*.
First five are the clean up patches which lays the foundation
to make things easier. Fifth patch in the patchset reverse the
current soft_enabled logic and commit message details the reason and
need for this change. Six and seventh patch refactor's the __EXPECTION_PROLOG_1
code to support addition of a new parameter to MASKABLE_* macros. New parameter
will give the possible mask for the interrupt. Rest of the patches are
to add support for maskable PMI and implementation of local_t using powerpc_local_irq_pmu_*().
Since the patchset is experimental, testing done only on pseries and
powernv platforms. Have only compile tested the patchset for Book3e.
Other suggestions from Nick: (planned to be handled via separate follow up patchset):
1)Rename the soft_enabled to soft_disable_mask
2)builtin_constants for the soft_enabled manipulation functions
3)Update the proper clobber for "r13->soft_enabled" updates and add barriers()
to caller functions
Changelog v2:
Rebased to latest upstream
Changelog v1:
1)squashed patches 1/2 together and 8/9/10 together for readability
2)Created a separate patch for the kconfig changes
3)Moved the new mask value commit to patch 11.
4)Renamed local_irq_pmu_*() to powerpc_irq_pmu_*() to avoid
namespaces matches with generic kernel local_irq*() functions
5)Renamed __EXCEPTION_PROLOG_1 macro to MASKABLE_EXCEPTION_PROLOG_1 macro
6)Made changes to commit messages
7)Add more comments to codes
Changelog RFC v5:
1)Implemented new set of soft_enabled manipulation functions
2)rewritten arch_local_irq_* functions to use the new soft_enabled_*()
3)Add WARN_ON to identify invalid soft_enabled transitions
4)Added powerpc_local_irq_pmu_save() and powerpc_local_irq_pmu_restore() to
support masking of irqs (with PMI).
5)Added local_irq_pmu_*()s macros with trace_hardirqs_on|off() to match
include/linux/irqflags.h
Changelog RFC v4:
1)Fix build breaks in in ppc64e_defconfig compilation
2)Merged PMI replay code with the exception vector changes patch
3)Renamed the new API to set PMI mask bit as suggested
4)Modified the current arch_local_save and new API function call to
"OR" and store the value to ->soft_enabled instead of just store.
5)Updated the check in the arch_local_irq_restore() to alway check for
greather than or zero to _LINUX mask bit.
6)Updated the commit messages.
Changelog RFC v3:
1)Squashed PMI masked interrupt patch and replay patch together
2)Have created a new patch which includes a new Kconfig and set_irq_set_mask()
3)Fixed the compilation issue with IRQ_DISABLE_MASK_* macros in book3e_*
Changelog RFC v2:
1)Renamed IRQ_DISABLE_LEVEL_* to IRQ_DISABLE_MASK_* and made logic changes
to treat soft_enabled as a mask and not a flag or level.
2)Added a new Kconfig variable to support a WARN_ON
3)Refactored patchset for eaiser review.
4)Made changes to commit messages.
5)Made changes for BOOK3E version
Changelog RFC v1:
1)Commit messages are improved.
2)Renamed the arch_local_irq_disable_var to soft_irq_set_level as suggested
3)Renamed the LAZY_INTERRUPT* macro to IRQ_DISABLE_LEVEL_* as suggested
4)Extended the MASKABLE_EXCEPTION* macros to support additional parameter.
5)Each MASKABLE_EXCEPTION_* macro will carry a "mask_level"
6)Logic to decide on jump to maskable_handler in SOFTEN_TEST is now based on
"mask_level"
7)__EXCEPTION_PROLOG_1 is factored out to support "mask_level" parameter.
This reduced the code changes needed for supporting "mask_level" parameters.
Madhavan Srinivasan (11):
powerpc: Add #defs for paca->soft_enabled flags
powerpc: move set_soft_enabled() and rename
powerpc: Use soft_enabled_set api to update paca->soft_enabled
powerpc: Add soft_enabled manipulation functions
powerpc: reverse the soft_enable logic
powerpc: Avoid using EXCEPTION_PROLOG_1 macro in MASKABLE_*
powerpc: Add support to take additional parameter in MASKABLE_* macro
powerpc: Add support to mask perf interrupts and replay them
powerpc:Add new kconfig IRQ_DEBUG_SUPPORT
powerpc: Add new set of soft_enabled_ functions
powerpc: rewrite local_t using soft_irq
arch/powerpc/Kconfig | 4 +
arch/powerpc/include/asm/exception-64s.h | 99 +++++++++------
arch/powerpc/include/asm/head-64.h | 40 +++---
arch/powerpc/include/asm/hw_irq.h | 112 +++++++++++++++--
arch/powerpc/include/asm/irqflags.h | 8 +-
arch/powerpc/include/asm/kvm_ppc.h | 2 +-
arch/powerpc/include/asm/local.h | 201 +++++++++++++++++++++++++++++++
arch/powerpc/kernel/entry_64.S | 24 ++--
arch/powerpc/kernel/exceptions-64e.S | 8 +-
arch/powerpc/kernel/exceptions-64s.S | 38 +++---
arch/powerpc/kernel/head_64.S | 5 +-
arch/powerpc/kernel/idle_book3e.S | 3 +-
arch/powerpc/kernel/idle_power4.S | 3 +-
arch/powerpc/kernel/irq.c | 48 ++++++--
arch/powerpc/kernel/process.c | 3 +-
arch/powerpc/kernel/setup_64.c | 5 +-
arch/powerpc/kernel/time.c | 6 +-
arch/powerpc/mm/hugetlbpage.c | 2 +-
arch/powerpc/perf/core-book3s.c | 2 +-
19 files changed, 490 insertions(+), 123 deletions(-)
--
2.7.4
^ permalink raw reply
* [PATCH v3 02/11] powerpc: move set_soft_enabled() and rename
From: Madhavan Srinivasan @ 2016-11-14 18:04 UTC (permalink / raw)
To: mpe, benh; +Cc: anton, paulus, npiggin, linuxppc-dev, Madhavan Srinivasan
In-Reply-To: <1479146692-15726-1-git-send-email-maddy@linux.vnet.ibm.com>
Move set_soft_enabled() from powerpc/kernel/irq.c to
asm/hw_irq.c, to force updates to paca-soft_enabled
done via these access function. Add "memory" clobber
to hint compiler since paca->soft_enabled memory is the target
here
Renaming it as soft_enabled_set() will make
namespaces works better as prefix than a postfix
when new soft_enabled manipulation functions introduced.
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/hw_irq.h | 15 +++++++++++++++
arch/powerpc/kernel/irq.c | 12 +++---------
2 files changed, 18 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 05b81bca15e9..ab1e6da7825c 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -47,6 +47,21 @@ extern void unknown_exception(struct pt_regs *regs);
#ifdef CONFIG_PPC64
#include <asm/paca.h>
+/*
+ *TODO:
+ * Currently none of the soft_eanbled modification helpers have clobbers
+ * for modifying the r13->soft_enabled memory itself. Secondly they only
+ * include "memory" clobber as a hint. Ideally, if all the accesses to
+ * soft_enabled go via these helpers, we could avoid the "memory" clobber.
+ * Former could be taken care by having location in the constraints.
+ */
+static inline notrace void soft_enabled_set(unsigned long enable)
+{
+ __asm__ __volatile__("stb %0,%1(13)"
+ : : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled))
+ : "memory");
+}
+
static inline unsigned long arch_local_save_flags(void)
{
unsigned long flags;
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index c6f1e13ff441..204fa51cdc9e 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -108,12 +108,6 @@ static inline notrace unsigned long get_irq_happened(void)
return happened;
}
-static inline notrace void set_soft_enabled(unsigned long enable)
-{
- __asm__ __volatile__("stb %0,%1(13)"
- : : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
-}
-
static inline notrace int decrementer_check_overflow(void)
{
u64 now = get_tb_or_rtc();
@@ -213,7 +207,7 @@ notrace void arch_local_irq_restore(unsigned long en)
unsigned int replay;
/* Write the new soft-enabled value */
- set_soft_enabled(en);
+ soft_enabled_set(en);
if (en == IRQ_DISABLE_MASK_LINUX)
return;
/*
@@ -259,7 +253,7 @@ notrace void arch_local_irq_restore(unsigned long en)
}
#endif /* CONFIG_TRACE_IRQFLAGS */
- set_soft_enabled(IRQ_DISABLE_MASK_LINUX);
+ soft_enabled_set(IRQ_DISABLE_MASK_LINUX);
/*
* Check if anything needs to be re-emitted. We haven't
@@ -269,7 +263,7 @@ notrace void arch_local_irq_restore(unsigned long en)
replay = __check_irq_replay();
/* We can soft-enable now */
- set_soft_enabled(IRQ_DISABLE_MASK_NONE);
+ soft_enabled_set(IRQ_DISABLE_MASK_NONE);
/*
* And replay if we have to. This will return with interrupts
--
2.7.4
^ permalink raw reply related
* [PATCH v3 03/11] powerpc: Use soft_enabled_set api to update paca->soft_enabled
From: Madhavan Srinivasan @ 2016-11-14 18:04 UTC (permalink / raw)
To: mpe, benh; +Cc: anton, paulus, npiggin, linuxppc-dev, Madhavan Srinivasan
In-Reply-To: <1479146692-15726-1-git-send-email-maddy@linux.vnet.ibm.com>
Force use of soft_enabled_set() wrapper to update paca-soft_enabled
wherever possisble. Also add a new wrapper function, soft_enabled_set_return(),
added to force the paca->soft_enabled updates.
Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/hw_irq.h | 14 ++++++++++++++
arch/powerpc/include/asm/kvm_ppc.h | 2 +-
arch/powerpc/kernel/irq.c | 2 +-
arch/powerpc/kernel/setup_64.c | 4 ++--
arch/powerpc/kernel/time.c | 6 +++---
5 files changed, 21 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index ab1e6da7825c..88f6a8e2b5e3 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -62,6 +62,20 @@ static inline notrace void soft_enabled_set(unsigned long enable)
: "memory");
}
+static inline notrace unsigned long soft_enabled_set_return(unsigned long enable)
+{
+ unsigned long flags;
+
+ asm volatile(
+ "lbz %0,%1(13); stb %2,%1(13)"
+ : "=r" (flags)
+ : "i" (offsetof(struct paca_struct, soft_enabled)),\
+ "r" (enable)
+ : "memory");
+
+ return flags;
+}
+
static inline unsigned long arch_local_save_flags(void)
{
unsigned long flags;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 7d8d2b40c6a8..2263d2443d94 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -735,7 +735,7 @@ static inline void kvmppc_fix_ee_before_entry(void)
/* Only need to enable IRQs by hard enabling them after this */
local_paca->irq_happened = 0;
- local_paca->soft_enabled = IRQ_DISABLE_MASK_NONE;
+ soft_enabled_set(IRQ_DISABLE_MASK_NONE);
#endif
}
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 204fa51cdc9e..5a995183dafb 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -337,7 +337,7 @@ bool prep_irq_for_idle(void)
* of entering the low power state.
*/
local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
- local_paca->soft_enabled = IRQ_DISABLE_MASK_NONE;
+ soft_enabled_set(IRQ_DISABLE_MASK_NONE);
/* Tell the caller to enter the low power state */
return true;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index f31930b9bfc1..f0f882166dcc 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -197,7 +197,7 @@ static void __init fixup_boot_paca(void)
/* Allow percpu accesses to work until we setup percpu data */
get_paca()->data_offset = 0;
/* Mark interrupts disabled in PACA */
- get_paca()->soft_enabled = IRQ_DISABLE_MASK_LINUX;
+ soft_enabled_set(IRQ_DISABLE_MASK_LINUX);
}
static void __init configure_exceptions(void)
@@ -334,7 +334,7 @@ void __init early_setup(unsigned long dt_ptr)
void early_setup_secondary(void)
{
/* Mark interrupts disabled in PACA */
- get_paca()->soft_enabled = 0;
+ soft_enabled_set(IRQ_DISABLE_MASK_LINUX);
/* Initialize the hash table or TLB handling */
early_init_mmu_secondary();
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 334144e300ca..42a39a2cea0a 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -260,7 +260,7 @@ static u64 scan_dispatch_log(u64 stop_tb)
void accumulate_stolen_time(void)
{
u64 sst, ust;
- u8 save_soft_enabled = local_paca->soft_enabled;
+ unsigned long save_soft_enabled;
struct cpu_accounting_data *acct = &local_paca->accounting;
/* We are called early in the exception entry, before
@@ -269,7 +269,7 @@ void accumulate_stolen_time(void)
* needs to reflect that so various debug stuff doesn't
* complain
*/
- local_paca->soft_enabled = IRQ_DISABLE_MASK_LINUX;
+ save_soft_enabled = soft_enabled_set_return(IRQ_DISABLE_MASK_LINUX);
sst = scan_dispatch_log(acct->starttime_user);
ust = scan_dispatch_log(acct->starttime);
@@ -277,7 +277,7 @@ void accumulate_stolen_time(void)
acct->user_time -= ust;
local_paca->stolen_time += ust + sst;
- local_paca->soft_enabled = save_soft_enabled;
+ soft_enabled_set(save_soft_enabled);
}
static inline u64 calculate_stolen_time(u64 stop_tb)
--
2.7.4
^ permalink raw reply related
* [PATCH v3 05/11] powerpc: reverse the soft_enable logic
From: Madhavan Srinivasan @ 2016-11-14 18:04 UTC (permalink / raw)
To: mpe, benh; +Cc: anton, paulus, npiggin, linuxppc-dev, Madhavan Srinivasan
In-Reply-To: <1479146692-15726-1-git-send-email-maddy@linux.vnet.ibm.com>
"paca->soft_enabled" is used as a flag to mask some of interrupts.
Currently supported flags values and their details:
soft_enabled MSR[EE]
0 0 Disabled (PMI and HMI not masked)
1 1 Enabled
"paca->soft_enabled" is initialized to 1 to make the interripts as
enabled. arch_local_irq_disable() will toggle the value when interrupts
needs to disbled. At this point, the interrupts are not actually disabled,
instead, interrupt vector has code to check for the flag and mask it when it occurs.
By "mask it", it update interrupt paca->irq_happened and return.
arch_local_irq_restore() is called to re-enable interrupts, which checks and
replays interrupts if any occured.
Now, as mentioned, current logic doesnot mask "performance monitoring interrupts"
and PMIs are implemented as NMI. But this patchset depends on local_irq_*
for a successful local_* update. Meaning, mask all possible interrupts during
local_* update and replay them after the update.
So the idea here is to reserve the "paca->soft_enabled" logic. New values and
details:
soft_enabled MSR[EE]
1 0 Disabled (PMI and HMI not masked)
0 1 Enabled
Reason for the this change is to create foundation for a third mask value "0x2"
for "soft_enabled" to add support to mask PMIs. When ->soft_enabled is
set to a value "3", PMI interrupts are mask and when set to a value
of "1", PMI are not mask.
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/hw_irq.h | 4 ++--
arch/powerpc/kernel/entry_64.S | 5 ++---
2 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index c292ef4b4bc5..8359fbf83376 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -30,8 +30,8 @@
/*
* flags for paca->soft_enabled
*/
-#define IRQ_DISABLE_MASK_NONE 1
-#define IRQ_DISABLE_MASK_LINUX 0
+#define IRQ_DISABLE_MASK_NONE 0
+#define IRQ_DISABLE_MASK_LINUX 1
#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 8e347ffca14e..7ef3064ddde1 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -132,8 +132,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
*/
#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_BUG)
lbz r10,PACASOFTIRQEN(r13)
- xori r10,r10,IRQ_DISABLE_MASK_NONE
-1: tdnei r10,0
+1: tdnei r10,IRQ_DISABLE_MASK_NONE
EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
#endif
@@ -1010,7 +1009,7 @@ _GLOBAL(enter_rtas)
* check it with the asm equivalent of WARN_ON
*/
lbz r0,PACASOFTIRQEN(r13)
-1: tdnei r0,IRQ_DISABLE_MASK_LINUX
+1: tdeqi r0,IRQ_DISABLE_MASK_NONE
EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
#endif
--
2.7.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.