3.4-stable patches

added patches:
	net_dma-mark-broken.patch
	sched-rt-fix-rq-s-cpupri-leak-while-enqueue-dequeue-child-rt-entities.patch

diff --git a/queue-3.4/net_dma-mark-broken.patch b/queue-3.4/net_dma-mark-broken.patch
new file mode 100644 (file)
index 0000000..bb6853e
--- /dev/null
+++ b/queue-3.4/net_dma-mark-broken.patch
@@ -0,0 +1,91 @@
+From 77873803363c9e831fc1d1e6895c084279090c22 Mon Sep 17 00:00:00 2001
+From: Dan Williams <dan.j.williams@intel.com>
+Date: Tue, 17 Dec 2013 10:09:32 -0800
+Subject: net_dma: mark broken
+
+From: Dan Williams <dan.j.williams@intel.com>
+
+commit 77873803363c9e831fc1d1e6895c084279090c22 upstream.
+
+net_dma can cause data to be copied to a stale mapping if a
+copy-on-write fault occurs during dma.  The application sees missing
+data.
+
+The following trace is triggered by modifying the kernel to WARN if it
+ever triggers copy-on-write on a page that is undergoing dma:
+
+ WARNING: CPU: 24 PID: 2529 at lib/dma-debug.c:485 debug_dma_assert_idle+0xd2/0x120()
+ ioatdma 0000:00:04.0: DMA-API: cpu touching an active dma mapped page [pfn=0x16bcd9]
+ Modules linked in: iTCO_wdt iTCO_vendor_support ioatdma lpc_ich pcspkr dca
+ CPU: 24 PID: 2529 Comm: linbug Tainted: G        W    3.13.0-rc1+ #353
+  00000000000001e5 ffff88016f45f688 ffffffff81751041 ffff88017ab0ef70
+  ffff88016f45f6d8 ffff88016f45f6c8 ffffffff8104ed9c ffffffff810f3646
+  ffff8801768f4840 0000000000000282 ffff88016f6cca10 00007fa2bb699349
+ Call Trace:
+  [<ffffffff81751041>] dump_stack+0x46/0x58
+  [<ffffffff8104ed9c>] warn_slowpath_common+0x8c/0xc0
+  [<ffffffff810f3646>] ? ftrace_pid_func+0x26/0x30
+  [<ffffffff8104ee86>] warn_slowpath_fmt+0x46/0x50
+  [<ffffffff8139c062>] debug_dma_assert_idle+0xd2/0x120
+  [<ffffffff81154a40>] do_wp_page+0xd0/0x790
+  [<ffffffff811582ac>] handle_mm_fault+0x51c/0xde0
+  [<ffffffff813830b9>] ? copy_user_enhanced_fast_string+0x9/0x20
+  [<ffffffff8175fc2c>] __do_page_fault+0x19c/0x530
+  [<ffffffff8175c196>] ? _raw_spin_lock_bh+0x16/0x40
+  [<ffffffff810f3539>] ? trace_clock_local+0x9/0x10
+  [<ffffffff810fa1f4>] ? rb_reserve_next_event+0x64/0x310
+  [<ffffffffa0014c00>] ? ioat2_dma_prep_memcpy_lock+0x60/0x130 [ioatdma]
+  [<ffffffff8175ffce>] do_page_fault+0xe/0x10
+  [<ffffffff8175c862>] page_fault+0x22/0x30
+  [<ffffffff81643991>] ? __kfree_skb+0x51/0xd0
+  [<ffffffff813830b9>] ? copy_user_enhanced_fast_string+0x9/0x20
+  [<ffffffff81388ea2>] ? memcpy_toiovec+0x52/0xa0
+  [<ffffffff8164770f>] skb_copy_datagram_iovec+0x5f/0x2a0
+  [<ffffffff8169d0f4>] tcp_rcv_established+0x674/0x7f0
+  [<ffffffff816a68c5>] tcp_v4_do_rcv+0x2e5/0x4a0
+  [..]
+ ---[ end trace e30e3b01191b7617 ]---
+ Mapped at:
+  [<ffffffff8139c169>] debug_dma_map_page+0xb9/0x160
+  [<ffffffff8142bf47>] dma_async_memcpy_pg_to_pg+0x127/0x210
+  [<ffffffff8142cce9>] dma_memcpy_pg_to_iovec+0x119/0x1f0
+  [<ffffffff81669d3c>] dma_skb_copy_datagram_iovec+0x11c/0x2b0
+  [<ffffffff8169d1ca>] tcp_rcv_established+0x74a/0x7f0:
+
+...the problem is that the receive path falls back to cpu-copy in
+several locations and this trace is just one of the areas.  A few
+options were considered to fix this:
+
+1/ sync all dma whenever a cpu copy branch is taken
+
+2/ modify the page fault handler to hold off while dma is in-flight
+
+Option 1 adds yet more cpu overhead to an "offload" that struggles to compete
+with cpu-copy.  Option 2 adds checks for behavior that is already documented as
+broken when using get_user_pages().  At a minimum a debug mode is warranted to
+catch and flag these violations of the dma-api vs get_user_pages().
+
+Thanks to David for his reproducer.
+
+Cc: Dave Jiang <dave.jiang@intel.com>
+Cc: Vinod Koul <vinod.koul@intel.com>
+Cc: Alexander Duyck <alexander.h.duyck@intel.com>
+Reported-by: David Whipple <whipple@securedatainnovations.ch>
+Acked-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Dan Williams <dan.j.williams@intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/dma/Kconfig |    1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/drivers/dma/Kconfig
++++ b/drivers/dma/Kconfig
+@@ -269,6 +269,7 @@ config NET_DMA
+       bool "Network: TCP receive copy offload"
+       depends on DMA_ENGINE && NET
+       default (INTEL_IOATDMA || FSL_DMA)
++      depends on BROKEN
+       help
+         This enables the use of DMA engines in the network stack to
+         offload receive copy-to-user operations, freeing CPU cycles.

diff --git a/queue-3.4/sched-rt-fix-rq-s-cpupri-leak-while-enqueue-dequeue-child-rt-entities.patch b/queue-3.4/sched-rt-fix-rq-s-cpupri-leak-while-enqueue-dequeue-child-rt-entities.patch
new file mode 100644 (file)
index 0000000..9450774
--- /dev/null
+++ b/queue-3.4/sched-rt-fix-rq-s-cpupri-leak-while-enqueue-dequeue-child-rt-entities.patch
@@ -0,0 +1,65 @@
+From 757dfcaa41844595964f1220f1d33182dae49976 Mon Sep 17 00:00:00 2001
+From: Kirill Tkhai <tkhai@yandex.ru>
+Date: Wed, 27 Nov 2013 19:59:13 +0400
+Subject: sched/rt: Fix rq's cpupri leak while enqueue/dequeue child RT entities
+
+From: Kirill Tkhai <tkhai@yandex.ru>
+
+commit 757dfcaa41844595964f1220f1d33182dae49976 upstream.
+
+This patch touches the RT group scheduling case.
+
+Functions inc_rt_prio_smp() and dec_rt_prio_smp() change (global) rq's
+priority, while rt_rq passed to them may be not the top-level rt_rq.
+This is wrong, because changing of priority on a child level does not
+guarantee that the priority is the highest all over the rq. So, this
+leak makes RT balancing unusable.
+
+The short example: the task having the highest priority among all rq's
+RT tasks (no one other task has the same priority) are waking on a
+throttle rt_rq.  The rq's cpupri is set to the task's priority
+equivalent, but real rq->rt.highest_prio.curr is less.
+
+The patch below fixes the problem.
+
+Signed-off-by: Kirill Tkhai <tkhai@yandex.ru>
+Signed-off-by: Peter Zijlstra <peterz@infradead.org>
+CC: Steven Rostedt <rostedt@goodmis.org>
+Link: http://lkml.kernel.org/r/49231385567953@web4m.yandex.ru
+Signed-off-by: Ingo Molnar <mingo@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/sched/rt.c |   14 ++++++++++++++
+ 1 file changed, 14 insertions(+)
+
+--- a/kernel/sched/rt.c
++++ b/kernel/sched/rt.c
+@@ -942,6 +942,13 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int
+ {
+       struct rq *rq = rq_of_rt_rq(rt_rq);
+ 
++#ifdef CONFIG_RT_GROUP_SCHED
++      /*
++       * Change rq's cpupri only if rt_rq is the top queue.
++       */
++      if (&rq->rt != rt_rq)
++              return;
++#endif
+       if (rq->online && prio < prev_prio)
+               cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
+ }
+@@ -951,6 +958,13 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int
+ {
+       struct rq *rq = rq_of_rt_rq(rt_rq);
+ 
++#ifdef CONFIG_RT_GROUP_SCHED
++      /*
++       * Change rq's cpupri only if rt_rq is the top queue.
++       */
++      if (&rq->rt != rt_rq)
++              return;
++#endif
+       if (rq->online && rt_rq->highest_prio.curr != prev_prio)
+               cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
+ }

diff --git a/queue-3.4/series b/queue-3.4/series
index 4ef2f6d535f5e59c0c04c62b9bc4ebc2f6ba6041..6fc7a29936f7391271db001151b279c37db6e594 100644 (file)
--- a/queue-3.4/series
+++ b/queue-3.4/series
@@ -13,3 +13,5 @@ intel_idle-initial-ivb-support.patch
 intel_idle-enable-ivb-xeon-support.patch
 ext4-fix-use-after-free-in-ext4_mb_new_blocks.patch
 ext4-check-for-overlapping-extents-in-ext4_valid_extent_entries.patch
+sched-rt-fix-rq-s-cpupri-leak-while-enqueue-dequeue-child-rt-entities.patch
+net_dma-mark-broken.patch