It didn't worked to well anyway.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Fix wrong compatible for A385 DB AP preventing using suspend
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iEYEABECAAYFAlYhNEwACgkQCwYYjhRyO9XX9gCgnabcvdHrfFqAD3IFICLCgkOM
U1AAnReiDUjcUhz6oTl6I2+e3PLHY7RO
=BkFw
-----END PGP SIGNATURE-----
Merge tag 'mvebu-fixes-4.3-2' of git://git.infradead.org/linux-mvebu into fixes
Merge "mvebu fixes for 4.3 (part 2)" from Gregory CLEMENT:
Fix wrong compatible for A385 DB AP preventing using suspend
* tag 'mvebu-fixes-4.3-2' of git://git.infradead.org/linux-mvebu:
ARM: mvebu: correct a385-db-ap compatible string
- Fix oops with LPAE and moew than 2GB of memory by enabling
ZONE_DMA for LPAE. Probably no need for stable on this one as we
only recently ran into this with the mainline kernel
- Fix imprecise external abort caused by bogus SRAM init. This affects
dm814x recently merged, so no need for stable on this one AFAIK
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=EP6s
-----END PGP SIGNATURE-----
Merge tag 'omap-for-v4.3/fixes-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap into fixes
Merge "Fixes for omaps for v4.3-rc cycle" from Tony Lindgren:
- Fix oops with LPAE and moew than 2GB of memory by enabling
ZONE_DMA for LPAE. Probably no need for stable on this one as we
only recently ran into this with the mainline kernel
- Fix imprecise external abort caused by bogus SRAM init. This affects
dm814x recently merged, so no need for stable on this one AFAIK
* tag 'omap-for-v4.3/fixes-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap:
ARM: OMAP2+: Fix imprecise external abort caused by bogus SRAM init
ARM: OMAP2+: Fix oops with LPAE and more than 2GB of memory
Configure ageing time to the HW for newly bridged device
CC: Scott Feldman <sfeldma@gmail.com>
CC: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Elad Raz <eladr@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is decrementing the pointer, instead of the value stored in the
pointer. KASan detects it as an out of bounds reference.
Reported-by: "Berry Cheng 程君(成淼)" <chengmiao.cj@alibaba-inc.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sometimes xennet_create_queues() may failed to created all requested
queues, we need to update num_queues to real created to avoid NULL
pointer dereference.
Signed-off-by: Joe Jin <joe.jin@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
reset transport and unlock if misc_register failed.
Signed-off-by: Gao feng <omarapazanadi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Philipp Kirchhofer says:
====================
net: mv643xx_eth: TSO TX data corruption fixes
as previously discussed [1] the mv643xx_eth driver has some
issues with data corruption when using TCP segmentation offload (TSO).
The following patch set improves this situation by fixing two data
corruption bugs in the TSO TX path.
Before applying the patches repeatedly accessing large files located on
a SMB share on my NSA325 NAS with TSO enabled resulted in different
hash sums, which confirmed that data corruption is happening during
file transfer. After applying the patches the hash sums were the same.
As this is my first patch submission please feel free to point out any
issues with the patch set.
[1] http://thread.gmane.org/gmane.linux.network/336530
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
To prevent a race between the TX DMA engine and the CPU the writing of the
first transmit descriptor must be deferred until all following descriptors
have been updated. The network card may otherwise start transmitting before
all packet descriptors are set up correctly, which leads to data corruption
or an aborted transmit operation.
This deferral is already done in the non-TSO TX path, implement it also in
the TSO TX path.
Signed-off-by: Philipp Kirchhofer <philipp@familie-kirchhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
The TX DMA engine requires that buffers with a size of 8 bytes or smaller
must be 64 bit aligned. This requirement may be violated when doing TSO,
as in this case larger skb frags can be broken up and transmitted in small
parts with then inappropriate alignment.
Fix this by checking for proper alignment before handing a buffer to the
DMA engine. If the data is misaligned realign it by copying it into the
TSO header data area.
Signed-off-by: Philipp Kirchhofer <philipp@familie-kirchhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
The hwcap string arrays used for generating the contents of
/proc/cpuinfo are currently arrays of non-const pointers.
There's no need for these pointers to be mutable, so this patch makes
them const so that they can be moved to .rodata.
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Use the system wide safe value from the new API for safer
decisions
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Christoffer Dall <christoffer.dall@linaro.org>
Cc: kvmarm@lists.cs.columbia.edu
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Use the system wide value of ID_AA64DFR0 to make safer decisions
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The FP/ASIMD is detected in fpsimd_init(), which is built-in
unconditionally. Lets move the hwcap handling to the central place.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Extend struct arm64_cpu_capabilities to handle the HWCAP detection
and make use of the system wide value of the feature registers for
a reliable set of HWCAPs.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Now that we can reliably read the system wide safe value for a
feature register, use that to compute the system capability.
This patch also replaces the 'feature-register-specific'
methods with a generic routine to check the capability.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
At the moment we run through the arm64_features capability list for
each CPU and set the capability if one of the CPU supports it. This
could be problematic in a heterogeneous system with differing capabilities.
Delay the CPU feature checks until all the enabled CPUs are up(i.e,
smp_cpus_done(), so that we can make better decisions based on the
overall system capability. Once we decide and advertise the capabilities
the alternatives can be applied. From this state, we cannot roll back
a feature to disabled based on the values from a new hotplugged CPU,
due to the runtime patching and other reasons. So, for all new CPUs,
we need to make sure that they have the established system capabilities.
Failing which, we bring the CPU down, preventing it from turning online.
Once the capabilities are decided, any new CPU booting up goes through
verification to ensure that it has all the enabled capabilities and also
invokes the respective enable() method on the CPU.
The CPU errata checks are not delayed and is still executed per-CPU
to detect the respective capabilities. If we ever come across a non-errata
capability that needs to be checked on each-CPU, we could introduce them via
a new capability table(or introduce a flag), which can be processed per CPU.
The next patch will make the feature checks use the system wide
safe value of a feature register.
NOTE: The enable() methods associated with the capability is scheduled
on all the CPUs (which is the only use case at the moment). If we need
a different type of 'enable()' which only needs to be run once on any CPU,
we should be able to handle that when needed.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
[catalin.marinas@arm.com: static variable and coding style fixes]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
check_cpu_capabilities runs through a given list of caps and
checks if the system has the cap, updates the system capability
bitmap and also runs any enable() methods associated with them.
All of this is not quite obvious from the name 'check'. This
patch splits the check_cpu_capabilities into two parts :
1) update_cpu_capabilities
=> Runs through the given list and updates the system
wide capability map.
2) enable_cpu_capabilities
=> Runs through the given list and invokes enable() (if any)
for the caps enabled on the system.
Cc: Andre Przywara <andre.przywara@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Suggested-by: Catalin Marinas <catalin.marinsa@arm.com>
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Make use of the system wide safe register to decide the support
for mixed endian.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Add an API for reading the safe CPUID value across the
system from the new infrastructure.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch consolidates the CPU Sanity check to the new infrastructure.
Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch adds an infrastructure to keep track of the CPU feature
registers on the system. For each register, the infrastructure keeps
track of the system wide safe value of the feature bits. Also, tracks
the which fields of a register should be matched strictly across all
the CPUs on the system for the SANITY check infrastructure.
The feature bits are classified into following 3 types depending on
the implication of the possible values. This information is used to
decide the safe value for a feature.
LOWER_SAFE - The smaller value is safer
HIGHER_SAFE - The bigger value is safer
EXACT - We can't decide between the two, so a predefined safe_value is used.
This infrastructure will be later used to make better decisions for:
- Kernel features (e.g, KVM, Debug)
- SANITY Check
- CPU capability
- ELF HWCAP
- Exposing CPU Feature register to userspace.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
[catalin.marinas@arm.com: whitespace fix]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Introduce a helper to extract cpuid feature for any given
width.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch moves the /proc/cpuinfo handling code:
arch/arm64/kernel/{setup.c to cpuinfo.c}
No functional changes
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Move the mixed endian support detection code to cpufeature.c
from cpuinfo.c. This also moves the update_cpu_features()
used by mixed endian detection code, which will get more
functionality.
Also moves the ID register field shifts to asm/sysreg.h,
where all the useful definitions will end up in later patches.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch moves the CPU feature detection code from
arch/arm64/kernel/{setup.c to cpufeature.c}
The plan is to consolidate all the CPU feature handling
in cpufeature.c.
Apart from changing pr_fmt from "alternatives" to "cpu features",
there are no functional changes.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
At the moment the boot CPU stores the cpuinfo long before the
PERCPU areas are initialised by the kernel. This could be problematic
as the non-boot CPU data structures might get copied with the data
from the boot CPU, giving us no chance to detect if a particular CPU
updated its cpuinfo. This patch delays the boot cpu store to
smp_prepare_boot_cpu().
Also kills the setup_processor() which no longer does meaningful
work.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Delay the ELF HWCAP initialisation until all the (enabled) CPUs are
up, i.e, smp_cpus_done(). This is in preparation for detecting the
common features across the CPUS and creating a consistent ELF HWCAP
for the system.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
At early boot, we print the CPU version/revision. On a heterogeneous
system, we could have different types of CPUs. Print the CPU info for
all active cpus. Also, the secondary CPUs prints the message only when
they turn online.
Also, remove the redundant 'revision' information which doesn't
make any sense without the 'variant' field.
Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The supplied script takes a signed module file and extracts the tailmost
signature (there could theoretically be more than one) and dumps all or
part of it or the unsigned file to stdout.
Call as:
scripts/extract-module-sig.pl -[0adnks] module-file >out
where the initial flag indicates which bit of the signed file you want dumping
to stdout:
(*) "-0". Dumps the unsigned data with the signature stripped.
(*) "-a". Dumps all of the signature data, including the magic number.
(*) "-d". Dumps the signature information block as a sequence of decimal
numbers in text form with spaces between (crypto algorithm type,
hash type, identifier type, signer's name length, key identifier
length and signature length).
(*) "-n". Dumps the signer's name contents.
(*) "-k". Dumps the key identifier contents.
(*) "-s". Dumps the cryptographic signature contents.
In the case that the signature is a PKCS#7 (or CMS) message, -n and -k will
print a warning to stderr and dump nothing to stdout, but will otherwise
complete okay; the entire PKCS#7/CMS message will be dumped by "-s"; and "-d"
will show "0 0 2 0 0 <pkcs#7-msg-len>".
Signed-off-by: David Howells <dhowells@redhat.com>
The supplied script takes a vmlinux file - and if necessary a System.map
file - locates the system certificates list and extracts it to the named
file.
Call as:
./scripts/extract-sys-certs vmlinux certs
if vmlinux contains symbols and:
./scripts/extract-sys-certs -s System.map vmlinux certs
if it does not.
It prints something like the following to stdout:
Have 27 sections
No symbols in vmlinux, trying System.map
Have 80088 symbols
Have 1346 bytes of certs at VMA 0xffffffff8201c540
Certificate list in section .init.data
Certificate list at file offset 0x141c540
If vmlinux contains symbols then that is used rather than System.map - even
if one is given.
Signed-off-by: David Howells <dhowells@redhat.com>
key->description and key->index_key.description are same because
they are unioned. But, for readability, using same name for
duplication and validation seems better.
Signed-off-by: Insu Yun <wuninsu@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Currently we see this in "git status" if we build in the source dir:
Untracked files:
(use "git add <file>..." to include in what will be committed)
certs/x509_certificate_list
It looks like it used to live in kernel/ so we squash that .gitignore
entry at the same time. I didn't bother to dig through git history to
see when it moved, since it is just a minor annoyance at most.
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: keyrings@linux-nfs.org
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: David Howells <dhowells@redhat.com>
There is no need to make a flag to tell that this memory is allocated by
kmalloc or vmalloc. Just use kvfree to free the memory.
Signed-off-by: Geliang Tang <geliangtang@163.com>
Signed-off-by: David Howells <dhowells@redhat.com>
a20135ffbc ("writeback: don't drain bdi_writeback_congested on bdi
destruction") added rbtree_postorder_for_each_entry_safe() which is
used to remove all entries; however, according to Cody, the iterator
isn't safe against operations which may rebalance the tree. Fix it by
switching to repeatedly removing rb_first() until empty.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Cody P Schafer <dev@codyps.com>
Fixes: a20135ffbc ("writeback: don't drain bdi_writeback_congested on bdi destruction")
Link: http://lkml.kernel.org/g/1443997973-1700-1-git-send-email-dev@codyps.com
Signed-off-by: Jens Axboe <axboe@fb.com>
Both start_branch_trace() and stop_branch_trace() are used in only one
location, and are both static. As they are small functions there is no
need to keep them separated out.
Link: http://lkml.kernel.org/r/1445000689-32596-1-git-send-email-0x7f454c46@gmail.com
Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Yuchung Cheng says:
====================
RACK loss detection
RACK (Recent ACK) loss recovery uses the notion of time instead of
packet sequence (FACK) or counts (dupthresh).
It's inspired by the FACK heuristic in tcp_mark_lost_retrans(): when a
limited transmit (new data packet) is sacked in recovery, then any
retransmission sent before that newly sacked packet was sent must have
been lost, since at least one round trip time has elapsed.
But that existing heuristic from tcp_mark_lost_retrans()
has several limitations:
1) it can't detect tail drops since it depends on limited transmit
2) it's disabled upon reordering (assumes no reordering)
3) it's only enabled in fast recovery but not timeout recovery
RACK addresses these limitations with a core idea: an unacknowledged
packet P1 is deemed lost if a packet P2 that was sent later is is
s/acked, since at least one round trip has passed.
Since RACK cares about the time sequence instead of the data sequence
of packets, it can detect tail drops when a later retransmission is
s/acked, while FACK or dupthresh can't. For reordering RACK uses a
dynamically adjusted reordering window ("reo_wnd") to reduce false
positives on ever (small) degree of reordering, similar to the delayed
Early Retransmit.
In the current patch set RACK is only a supplemental loss detection
and does not trigger fast recovery. However we are developing RACK
to replace or consolidate FACK/dupthresh, early retransmit, and
thin-dupack. These heuristics all implicitly bear the time notion.
For example, the delayed Early Retransmit is simply applying RACK
to trigger the fast recovery with small inflight.
RACK requires measuring the minimum RTT. Tracking a global min is less
robust due to traffic engineering pathing changes. Therefore it uses a
windowed filter by Kathleen Nichols. The min RTT can also be useful
for various other purposes like congestion control or stat monitoring.
This patch has been used on Google servers for well over 1 year. RACK
has also been implemented in the QUIC protocol. We are submitting an
IETF draft as well.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch implements the second half of RACK that uses the the most
recent transmit time among all delivered packets to detect losses.
tcp_rack_mark_lost() is called upon receiving a dubious ACK.
It then checks if an not-yet-sacked packet was sent at least
"reo_wnd" prior to the sent time of the most recently delivered.
If so the packet is deemed lost.
The "reo_wnd" reordering window starts with 1msec for fast loss
detection and changes to min-RTT/4 when reordering is observed.
We found 1msec accommodates well on tiny degree of reordering
(<3 pkts) on faster links. We use min-RTT instead of SRTT because
reordering is more of a path property but SRTT can be inflated by
self-inflicated congestion. The factor of 4 is borrowed from the
delayed early retransmit and seems to work reasonably well.
Since RACK is still experimental, it is now used as a supplemental
loss detection on top of existing algorithms. It is only effective
after the fast recovery starts or after the timeout occurs. The
fast recovery is still triggered by FACK and/or dupack threshold
instead of RACK.
We introduce a new sysctl net.ipv4.tcp_recovery for future
experiments of loss recoveries. For now RACK can be disabled by
setting it to 0.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is the first half of the RACK loss recovery.
RACK loss recovery uses the notion of time instead
of packet sequence (FACK) or counts (dupthresh). It's inspired by the
previous FACK heuristic in tcp_mark_lost_retrans(): when a limited
transmit (new data packet) is sacked, then current retransmitted
sequence below the newly sacked sequence must been lost,
since at least one round trip time has elapsed.
But it has several limitations:
1) can't detect tail drops since it depends on limited transmit
2) is disabled upon reordering (assumes no reordering)
3) only enabled in fast recovery ut not timeout recovery
RACK (Recently ACK) addresses these limitations with the notion
of time instead: a packet P1 is lost if a later packet P2 is s/acked,
as at least one round trip has passed.
Since RACK cares about the time sequence instead of the data sequence
of packets, it can detect tail drops when later retransmission is
s/acked while FACK or dupthresh can't. For reordering RACK uses a
dynamically adjusted reordering window ("reo_wnd") to reduce false
positives on ever (small) degree of reordering.
This patch implements tcp_advanced_rack() which tracks the
most recent transmission time among the packets that have been
delivered (ACKed or SACKed) in tp->rack.mstamp. This timestamp
is the key to determine which packet has been lost.
Consider an example that the sender sends six packets:
T1: P1 (lost)
T2: P2
T3: P3
T4: P4
T100: sack of P2. rack.mstamp = T2
T101: retransmit P1
T102: sack of P2,P3,P4. rack.mstamp = T4
T205: ACK of P4 since the hole is repaired. rack.mstamp = T101
We need to be careful about spurious retransmission because it may
falsely advance tp->rack.mstamp by an RTT or an RTO, causing RACK
to falsely mark all packets lost, just like a spurious timeout.
We identify spurious retransmission by the ACK's TS echo value.
If TS option is not applicable but the retransmission is acknowledged
less than min-RTT ago, it is likely to be spurious. We refrain from
using the transmission time of these spurious retransmissions.
The second half is implemented in the next patch that marks packet
lost using RACK timestamp.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
a helper to prepare the first main RACK patch.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
a helper to prepare the main RACK patch
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove the existing lost retransmit detection because RACK subsumes
it completely. This also stops the overloading the ack_seq field of
the skb control block.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Kathleen Nichols' algorithm for tracking the minimum RTT of a
data stream over some measurement window. It uses constant space
and constant time per update. Yet it almost always delivers
the same minimum as an implementation that has to keep all
the data in the window. The measurement window is tunable via
sysctl.net.ipv4.tcp_min_rtt_wlen with a default value of 5 minutes.
The algorithm keeps track of the best, 2nd best & 3rd best min
values, maintaining an invariant that the measurement time of
the n'th best >= n-1'th best. It also makes sure that the three
values are widely separated in the time window since that bounds
the worse case error when that data is monotonically increasing
over the window.
Upon getting a new min, we can forget everything earlier because
it has no value - the new min is less than everything else in the
window by definition and it's the most recent. So we restart fresh
on every new min and overwrites the 2nd & 3rd choices. The same
property holds for the 2nd & 3rd best.
Therefore we have to maintain two invariants to maximize the
information in the samples, one on values (1st.v <= 2nd.v <=
3rd.v) and the other on times (now-win <=1st.t <= 2nd.t <= 3rd.t <=
now). These invariants determine the structure of the code
The RTT input to the windowed filter is the minimum RTT measured
from ACK or SACK, or as the last resort from TCP timestamps.
The accessor tcp_min_rtt() returns the minimum RTT seen in the
window. ~0U indicates it is not available. The minimum is 1usec
even if the true RTT is below that.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently ca_seq_rtt_us does not use Kern's check. Fix that by
checking if any packet acked is a retransmit, for both RTT used
for RTT estimation and congestion control.
Fixes: 5b08e47ca ("tcp: prefer packet timing to TS-ECR for RTT")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiko Schocher says:
====================
net, phy, smsc: add posibility to disable energy detect mode
On some boards the energy enable detect mode leads in
trouble with some switches, so make the enabling of
this mode configurable through DT.
Therefore the property "smsc,disable-energy-detect" is
introduced.
Patch 1 introduces phy-handle support for the ti,cpsw
driver. This is needed now for the smsc phy.
Patch 2 adds the disable energy mode functionality
to the smsc phy
Changes in v2:
- add comments from Florian Fainelli
- I did not change disable property name into enable
because I fear to break existing behaviour
- add smsc vendor prefix
- remove CONFIG_OF and use __maybe_unused
- introduce "phy-handle" ability into ti,cpsw
driver, so I can remove bogus:
if (!of_node && dev->parent->of_node)
of_node = dev->parent->of_node;
construct. Therefore new patch for the ti,cpsw
driver is necessary.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
