New allocator type MEM_TYPE_PAGE_POOL for page_pool usage.
The registered allocator page_pool pointer is not available directly
from xdp_rxq_info, but it could be (if needed). For now, the driver
should keep separate track of the page_pool pointer, which it should
use for RX-ring page allocation.
As suggested by Saeed, to maintain a symmetric API it is the drivers
responsibility to allocate/create and free/destroy the page_pool.
Thus, after the driver have called xdp_rxq_info_unreg(), it is drivers
responsibility to free the page_pool, but with a RCU free call. This
is done easily via the page_pool helper page_pool_destroy() (which
avoids touching any driver code during the RCU callback, which could
happen after the driver have been unloaded).
V8: address issues found by kbuild test robot
- Address sparse should be static warnings
- Allow xdp.o to be compiled without page_pool.o
V9: Remove inline from .c file, compiler knows best
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Need a fast page recycle mechanism for ndo_xdp_xmit API for returning
pages on DMA-TX completion time, which have good cross CPU
performance, given DMA-TX completion time can happen on a remote CPU.
Refurbish my page_pool code, that was presented[1] at MM-summit 2016.
Adapted page_pool code to not depend the page allocator and
integration into struct page. The DMA mapping feature is kept,
even-though it will not be activated/used in this patchset.
[1] http://people.netfilter.org/hawk/presentations/MM-summit2016/generic_page_pool_mm_summit2016.pdf
V2: Adjustments requested by Tariq
- Changed page_pool_create return codes, don't return NULL, only
ERR_PTR, as this simplifies err handling in drivers.
V4: many small improvements and cleanups
- Add DOC comment section, that can be used by kernel-doc
- Improve fallback mode, to work better with refcnt based recycling
e.g. remove a WARN as pointed out by Tariq
e.g. quicker fallback if ptr_ring is empty.
V5: Fixed SPDX license as pointed out by Alexei
V6: Adjustments requested by Eric Dumazet
- Adjust ____cacheline_aligned_in_smp usage/placement
- Move rcu_head in struct page_pool
- Free pages quicker on destroy, minimize resources delayed an RCU period
- Remove code for forward/backward compat ABI interface
V8: Issues found by kbuild test robot
- Address sparse should be static warnings
- Only compile+link when a driver use/select page_pool,
mlx5 selects CONFIG_PAGE_POOL, although its first used in two patches
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use the IDA infrastructure for getting a cyclic increasing ID number,
that is used for keeping track of each registered allocator per
RX-queue xdp_rxq_info. Instead of using the IDR infrastructure, which
uses a radix tree, use a dynamic rhashtable, for creating ID to
pointer lookup table, because this is faster.
The problem that is being solved here is that, the xdp_rxq_info
pointer (stored in xdp_buff) cannot be used directly, as the
guaranteed lifetime is too short. The info is needed on a
(potentially) remote CPU during DMA-TX completion time . In an
xdp_frame the xdp_mem_info is stored, when it got converted from an
xdp_buff, which is sufficient for the simple page refcnt based recycle
schemes.
For more advanced allocators there is a need to store a pointer to the
registered allocator. Thus, there is a need to guard the lifetime or
validity of the allocator pointer, which is done through this
rhashtable ID map to pointer. The removal and validity of of the
allocator and helper struct xdp_mem_allocator is guarded by RCU. The
allocator will be created by the driver, and registered with
xdp_rxq_info_reg_mem_model().
It is up-to debate who is responsible for freeing the allocator
pointer or invoking the allocator destructor function. In any case,
this must happen via RCU freeing.
Use the IDA infrastructure for getting a cyclic increasing ID number,
that is used for keeping track of each registered allocator per
RX-queue xdp_rxq_info.
V4: Per req of Jason Wang
- Use xdp_rxq_info_reg_mem_model() in all drivers implementing
XDP_REDIRECT, even-though it's not strictly necessary when
allocator==NULL for type MEM_TYPE_PAGE_SHARED (given it's zero).
V6: Per req of Alex Duyck
- Introduce rhashtable_lookup() call in later patch
V8: Address sparse should be static warnings (from kbuild test robot)
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now all the users of ndo_xdp_xmit have been converted to use xdp_return_frame.
This enable a different memory model, thus activating another code path
in the xdp_return_frame API.
V2: Fixed issues pointed out by Tariq.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Also convert driver i40e, which very recently got XDP_REDIRECT support
in commit d9314c474d ("i40e: add support for XDP_REDIRECT").
V7: This patch got added in V7 of this patchset.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The generic xdp_frame format, was inspired by the cpumap own internal
xdp_pkt format. It is now time to convert it over to the generic
xdp_frame format. The cpumap needs one extra field dev_rx.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The virtio_net driver assumes XDP frames are always released based on
page refcnt (via put_page). Thus, is only queues the XDP data pointer
address and uses virt_to_head_page() to retrieve struct page.
Use the XDP return API to get away from such assumptions. Instead
queue an xdp_frame, which allow us to use the xdp_return_frame API,
when releasing the frame.
V8: Avoid endianness issues (found by kbuild test robot)
V9: Change __virtnet_xdp_xmit from bool to int return value (found by Dan Carpenter)
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The tuntap driver invented it's own driver specific way of queuing
XDP packets, by storing the xdp_buff information in the top of
the XDP frame data.
Convert it over to use the more generic xdp_frame structure. The
main problem with the in-driver method is that the xdp_rxq_info pointer
cannot be trused/used when dequeueing the frame.
V3: Remove check based on feedback from Jason
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is needed to convert drivers tuntap and virtio_net.
This is a generalization of what is done inside cpumap, which will be
converted later.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is done to prepare for the next patch, and it is also
nice to move this XDP related struct out of filter.h.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Extend struct ixgbe_tx_buffer to store the xdp_mem_info.
Notice that this could be optimized further by putting this into
a union in the struct ixgbe_tx_buffer, but this patchset
works towards removing this again. Thus, this is not done.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce an xdp_return_frame API, and convert over cpumap as
the first user, given it have queued XDP frame structure to leverage.
V3: Cleanup and remove C99 style comments, pointed out by Alex Duyck.
V6: Remove comment that id will be added later (Req by Alex Duyck)
V8: Rename enum mem_type to xdp_mem_type (found by kbuild test robot)
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This implements basic XDP redirect support in mlx5 driver.
Notice that the ndo_xdp_xmit() is NOT implemented, because that API
need some changes that this patchset is working towards.
The main purpose of this patch is have different drivers doing
XDP_REDIRECT to show how different memory models behave in a cross
driver world.
Update(pre-RFCv2 Tariq): Need to DMA unmap page before xdp_do_redirect,
as the return API does not exist yet to to keep this mapped.
Update(pre-RFCv3 Saeed): Don't mix XDP_TX and XDP_REDIRECT flushing,
introduce xdpsq.db.redirect_flush boolian.
V9: Adjust for commit 121e892754 ("net/mlx5e: Refactor RQ XDP_TX indication")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To ensure that qrtr can be loaded automatically, when needed, if it is compiled
as module.
Signed-off-by: Nicolas Dechesne <nicolas.dechesne@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
1. Added red_drops stats. Inbound packets dropped by RED, buffer exhaustion
2. Included fcs_err, jabber_err, l2_err and frame_err errors under
rx_errors
3. Included fifo_err, dmac_drop, red_drops, fw_err_pko, fw_err_link and
fw_err_drop under rx_dropped
4. Included max_collision_fail, max_deferral_fail, total_collisions,
fw_err_pko, fw_err_link, fw_err_drop and fw_err_pki under tx_dropped
5. Counting dma mapping errors
6. Added some firmware stats description and removed for some
Signed-off-by: Intiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: Derek Chickles <derek.chickles@cavium.com>
Acked-by: Satanand Burla <satananda.burla@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit c1eef220c1 ("vsock: always call
vsock_init_tables()") introduced a module_init() function without a
corresponding module_exit() function.
Modules with an init function can only be removed if they also have an
exit function. Therefore the vsock module was considered "permanent"
and could not be removed.
This patch adds an empty module_exit() function so that "rmmod vsock"
works. No explicit cleanup is required because:
1. Transports call vsock_core_exit() upon exit and cannot be removed
while sockets are still alive.
2. vsock_diag.ko does not perform any action that requires cleanup by
vsock.ko.
Fixes: c1eef220c1 ("vsock: always call vsock_init_tables()")
Reported-by: Xiumei Mu <xmu@redhat.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
xenbus_command_reply() did not actually copy the response string and
leaked stack content instead.
Fixes: 9a6161fe73 ("xen: return xenstore command failures via response instead of rc")
Signed-off-by: Simon Gaiser <simon@invisiblethingslab.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
This is the sync up with the canonical definition of the sound
protocol in Xen:
1. Protocol version was referenced in the protocol description,
but missed its definition. Fixed by adding a constant
for current protocol version.
2. Some of the request descriptions have "reserved" fields
missed: fixed by adding corresponding entries.
3. Extend the size of the requests and responses to 64 octets.
Bump protocol version to 2.
4. Add explicit back and front synchronization
In order to provide explicit synchronization between backend and
frontend the following changes are introduced in the protocol:
- add new ring buffer for sending asynchronous events from
backend to frontend to report number of bytes played by the
frontend (XENSND_EVT_CUR_POS)
- introduce trigger events for playback control: start/stop/pause/resume
- add "req-" prefix to event-channel and ring-ref to unify naming
of the Xen event channels for requests and events
5. Add explicit back and front parameter negotiation
In order to provide explicit stream parameter negotiation between
backend and frontend the following changes are introduced in the protocol:
add XENSND_OP_HW_PARAM_QUERY request to read/update
configuration space for the parameters given: request passes
desired parameter's intervals/masks and the response to this request
returns allowed min/max intervals/masks to be used.
Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Signed-off-by: Oleksandr Grytsov <oleksandr_grytsov@epam.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
We might need to do some actions before the shadow variable is freed.
For example, we might need to remove it from a list or free some data
that it points to.
This is already possible now. The user can get the shadow variable
by klp_shadow_get(), do the necessary actions, and then call
klp_shadow_free().
This patch allows to do it a more elegant way. The user could implement
the needed actions in a callback that is passed to klp_shadow_free()
as a parameter. The callback usually does reverse operations to
the constructor callback that can be called by klp_shadow_*alloc().
It is especially useful for klp_shadow_free_all(). There we need to do
these extra actions for each found shadow variable with the given ID.
Note that the memory used by the shadow variable itself is still released
later by rcu callback. It is needed to protect internal structures that
keep all shadow variables. But the destructor is called immediately.
The shadow variable must not be access anyway after klp_shadow_free()
is called. The user is responsible to protect this any suitable way.
Be aware that the destructor is called under klp_shadow_lock. It is
the same as for the contructor in klp_shadow_alloc().
Signed-off-by: Petr Mladek <pmladek@suse.com>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
The existing API allows to pass a sample data to initialize the shadow
data. It works well when the data are position independent. But it fails
miserably when we need to set a pointer to the shadow structure itself.
Unfortunately, we might need to initialize the pointer surprisingly
often because of struct list_head. It is even worse because the list
might be hidden in other common structures, for example, struct mutex,
struct wait_queue_head.
For example, this was needed to fix races in ALSA sequencer. It required
to add mutex into struct snd_seq_client. See commit b3defb791b
("ALSA: seq: Make ioctls race-free") and commit d15d662e89
("ALSA: seq: Fix racy pool initializations")
This patch makes the API more safe. A custom constructor function and data
are passed to klp_shadow_*alloc() functions instead of the sample data.
Note that ctor_data are no longer a template for shadow->data. It might
point to any data that might be necessary when the constructor is called.
Also note that the constructor is called under klp_shadow_lock. It is
an internal spin_lock that synchronizes alloc() vs. get() operations,
see klp_shadow_get_or_alloc(). On one hand, this adds a risk of ABBA
deadlocks. On the other hand, it allows to do some operations safely.
For example, we could add the new structure into an existing list.
This must be done only once when the structure is allocated.
Reported-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
If there is no d-cache-size property in the device tree, l1d_size could
be zero. We don't actually expect that to happen, it's only been seen
on mambo (simulator) in some configurations.
A zero-size l1d_size leads to the loop in the asm wrapping around to
2^64-1, and then walking off the end of the fallback area and
eventually causing a page fault which is fatal.
Just default to 64K which is correct on some CPUs, and sane enough to
not cause a crash on others.
Fixes: aa8a5e0062 ('powerpc/64s: Add support for RFI flush of L1-D cache')
Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
[mpe: Rewrite comment and change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The struct sigaction for user space in arch/s390/include/uapi/asm/signal.h
is ill defined. The kernel uses two structures 'struct sigaction' and
'struct old_sigaction', the correlation in the kernel for both 31 and
64 bit is as follows
sys_sigaction -> struct old_sigaction
sys_rt_sigaction -> struct sigaction
The correlation of the (single) uapi definition for 'struct sigaction'
under '#ifndef __KERNEL__':
31-bit: sys_sigaction -> uapi struct sigaction
31-bit: sys_rt_sigaction -> no structure available
64-bit: sys_sigaction -> no structure available
64-bit: sys_rt_sigaction -> uapi struct sigaction
This is quite confusing. To make it a bit less confusing make the
uapi definition of 'struct sigaction' usable for sys_rt_sigaction for
both 31-bit and 64-bit.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This tracepoint was replaced by inet_sock_set_state in 563e0bb and not
used anywhere in the kernel anymore. Remove it.
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit says:
====================
PCI: add two more values for PCIe Max_Read_Request_Size and initially use them in r8169 network driver
In r8169 network driver I stumbled across a magic number translating
to PCI MRRS size 4K. The PCI core is still missing constants for
values 2K and 4K (as defined in PCI standard).
So let's add these two constants and use the 4K constant in r8169.
Second patch depends on the first one, therefore both patches
preferrably should go through either PCI or netdev tree.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace magic number "0x5 << MAX_READ_REQUEST_SHIFT" with the
appropriate constant as defined in PCI core.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds missing values for the max read request size.
E.g. network driver r8169 uses a value of 4K.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make lib/textsearch.c usable as kernel-doc.
Add textsearch() function family to kernel-api documentation.
Fix kernel-doc warnings in <linux/textsearch.h>:
../include/linux/textsearch.h:65: warning: Incorrect use of kernel-doc format:
* get_next_block - fetch next block of data
../include/linux/textsearch.h:82: warning: Incorrect use of kernel-doc format:
* finish - finalize/clean a series of get_next_block() calls
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jose Abreu says:
====================
net: stmmac: Stop using hard-coded callbacks
This a starting point for a cleanup and re-organization of stmmac.
In this series we stop using hard-coded callbacks along the code and use
instead helpers which are defined in a single place ("hwif.h").
This brings several advantages:
1) Less typing :)
2) Guaranteed function pointer check
3) More flexibility
By 2) we stop using the repeated pattern of:
if (priv->hw->mac->some_func)
priv->hw->mac->some_func(...)
I didn't check but I expect the final .ko will be bigger with this series
because *all* of function pointers are checked.
Anyway, I hope this can make the code more readable and more flexible now.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Switch stmmac_mode_ops to generic Hardware Interface Helpers instead of
using hard-coded callbacks. This makes the code more readable and more
flexible.
No functional change.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Switch stmmac_hwtimestamp to generic Hardware Interface Helpers instead
of using hard-coded callbacks. This makes the code more readable and
more flexible.
No functional change.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Switch stmmac_ops to generic Hardware Interface Helpers instead of using
hard-coded callbacks. This makes the code more readable and more
flexible.
No functional change.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Switch stmmac_dma_ops to generic Hardware Interface Helpers instead of
using hard-coded callbacks. This makes the code more readable and more
flexible.
No functional change.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Switch stmmac_desc_ops to generic Hardware Interface Helpers instead of
using hard-coded callbacks. This makes the code more readable and more
flexible.
No functional change.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet says:
====================
tcp: add zero copy receive
This patch series add mmap() support to TCP sockets for RX zero copy.
While tcp_mmap() patch itself is quite small (~100 LOC), optimal support
for asynchronous mmap() required better SO_RCVLOWAT behavior, and a
test program to demonstrate how mmap() on TCP sockets can be used.
Note that mmap() (and associated munmap()) calls are adding more
pressure on per-process VM semaphore, so might not show benefit
for processus with high number of threads.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This is a reference program showing how mmap() can be used
on TCP flows to implement receive zero copy.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some networks can make sure TCP payload can exactly fit 4KB pages,
with well chosen MSS/MTU and architectures.
Implement mmap() system call so that applications can avoid
copying data without complex splice() games.
Note that a successful mmap( X bytes) on TCP socket is consuming
bytes, as if recvmsg() has been done. (tp->copied += X)
Only PROT_READ mappings are accepted, as skb page frags
are fundamentally shared and read only.
If tcp_mmap() finds data that is not a full page, or a patch of
urgent data, -EINVAL is returned, no bytes are consumed.
Application must fallback to recvmsg() to read the problematic sequence.
mmap() wont block, regardless of socket being in blocking or
non-blocking mode. If not enough bytes are in receive queue,
mmap() would return -EAGAIN, or -EIO if socket is in a state
where no other bytes can be added into receive queue.
An application might use SO_RCVLOWAT, poll() and/or ioctl( FIONREAD)
to efficiently use mmap()
On the sender side, MSG_EOR might help to clearly separate unaligned
headers and 4K-aligned chunks if necessary.
Tested:
mlx4 (cx-3) 40Gbit NIC, with tcp_mmap program provided in following patch.
MTU set to 4168 (4096 TCP payload, 40 bytes IPv6 header, 32 bytes TCP header)
Without mmap() (tcp_mmap -s)
received 32768 MB (0 % mmap'ed) in 8.13342 s, 33.7961 Gbit,
cpu usage user:0.034 sys:3.778, 116.333 usec per MB, 63062 c-switches
received 32768 MB (0 % mmap'ed) in 8.14501 s, 33.748 Gbit,
cpu usage user:0.029 sys:3.997, 122.864 usec per MB, 61903 c-switches
received 32768 MB (0 % mmap'ed) in 8.11723 s, 33.8635 Gbit,
cpu usage user:0.048 sys:3.964, 122.437 usec per MB, 62983 c-switches
received 32768 MB (0 % mmap'ed) in 8.39189 s, 32.7552 Gbit,
cpu usage user:0.038 sys:4.181, 128.754 usec per MB, 55834 c-switches
With mmap() on receiver (tcp_mmap -s -z)
received 32768 MB (100 % mmap'ed) in 8.03083 s, 34.2278 Gbit,
cpu usage user:0.024 sys:1.466, 45.4712 usec per MB, 65479 c-switches
received 32768 MB (100 % mmap'ed) in 7.98805 s, 34.4111 Gbit,
cpu usage user:0.026 sys:1.401, 43.5486 usec per MB, 65447 c-switches
received 32768 MB (100 % mmap'ed) in 7.98377 s, 34.4296 Gbit,
cpu usage user:0.028 sys:1.452, 45.166 usec per MB, 65496 c-switches
received 32768 MB (99.9969 % mmap'ed) in 8.01838 s, 34.281 Gbit,
cpu usage user:0.02 sys:1.446, 44.7388 usec per MB, 65505 c-switches
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
SO_RCVLOWAT is properly handled in tcp_poll(), so that POLLIN is only
generated when enough bytes are available in receive queue, after
David change (commit c7004482e8 "tcp: Respect SO_RCVLOWAT in tcp_poll().")
But TCP still calls sk->sk_data_ready() for each chunk added in receive
queue, meaning thread is awaken, and goes back to sleep shortly after.
Tested:
tcp_mmap test program, receiving 32768 MB of data with SO_RCVLOWAT set to 512KB
-> Should get ~2 wakeups (c-switches) per MB, regardless of how many
(tiny or big) packets were received.
High speed (mostly full size GRO packets)
received 32768 MB (100 % mmap'ed) in 8.03112 s, 34.2266 Gbit,
cpu usage user:0.037 sys:1.404, 43.9758 usec per MB, 65497 c-switches
received 32768 MB (99.9954 % mmap'ed) in 7.98453 s, 34.4263 Gbit,
cpu usage user:0.03 sys:1.422, 44.3115 usec per MB, 65485 c-switches
Low speed (sender is ratelimited and sends 1-MSS at a time, so GRO is not helping)
received 22474.5 MB (100 % mmap'ed) in 6015.35 s, 0.0313414 Gbit,
cpu usage user:0.05 sys:1.586, 72.7952 usec per MB, 44950 c-switches
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We should not delay acks if there are not enough bytes
in receive queue to satisfy SO_RCVLOWAT.
Since [E]POLLIN event is not going to be generated, there is little
hope for a delayed ack to be useful.
In fact, delaying ACK prevents sender from completing
the transfer.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Applications might use SO_RCVLOWAT on TCP socket hoping to receive
one [E]POLLIN event only when a given amount of bytes are ready in socket
receive queue.
Problem is that receive autotuning is not aware of this constraint,
meaning sk_rcvbuf might be too small to allow all bytes to be stored.
Add a new (struct proto_ops)->set_rcvlowat method so that a protocol
can override the default setsockopt(SO_RCVLOWAT) behavior.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove unnecessary check on update_lft variable in
addrconf_prefix_rcv_add_addr routine since it is always set to 0.
Moreover remove update_lft re-initialization to 0
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet says:
====================
tipc: Better check user provided attributes
syzbot reported a crash in __tipc_nl_net_set()
While fixing it, I also had to fix an old bug involving TIPC_NLA_NET_ADDR
====================
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
syzbot reported a crash in __tipc_nl_net_set() caused by NULL dereference.
We need to check that both TIPC_NLA_NET_NODEID and TIPC_NLA_NET_NODEID_W1
are present.
We also need to make sure userland provided u64 attributes.
Fixes: d50ccc2d39 ("tipc: add 128-bit node identifier")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Before syzbot/KMSAN bites, add the missing policy for TIPC_NLA_NET_ADDR
Fixes: 27c2141672 ("tipc: add net set to new netlink api")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull parisc build fix from Helge Deller:
"Fix build error because of missing binfmt_elf32.o file which is still
mentioned in the Makefile"
* 'parisc-4.17-3' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
parisc: Fix missing binfmt_elf32.o build error
The MIPS kernel memset / bzero implementation includes a small_memset
branch which is used when the region to be set is smaller than a long (4
bytes on 32bit, 8 bytes on 64bit). The current small_memset
implementation uses a simple store byte loop to write the destination.
There are 2 issues with this implementation:
1. When EVA mode is active, user and kernel address spaces may overlap.
Currently the use of the sb instruction means kernel mode addressing is
always used and an intended write to userspace may actually overwrite
some critical kernel data.
2. If the write triggers a page fault, for example by calling
__clear_user(NULL, 2), instead of gracefully handling the fault, an OOPS
is triggered.
Fix these issues by replacing the sb instruction with the EX() macro,
which will emit EVA compatible instuctions as required. Additionally
implement a fault fixup for small_memset which sets a2 to the number of
bytes that could not be cleared (as defined by __clear_user).
Reported-by: Chuanhua Lei <chuanhua.lei@intel.com>
Signed-off-by: Matt Redfearn <matt.redfearn@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: stable@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/18975/
Signed-off-by: James Hogan <jhogan@kernel.org>
Pull missed timer updates from Thomas Gleixner:
"This is a branch which got forgotten during the merge window, but it
contains only fixes and hardware enablement. No fundamental changes.
- Various fixes for the imx-tpm clocksource driver
- A new timer driver for the NCPM7xx SoC family"
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
clocksource/drivers/imx-tpm: Add different counter width support
clocksource/drivers/imx-tpm: Correct some registers operation flow
clocksource/drivers/imx-tpm: Fix typo of clock name
dt-bindings: timer: tpm: fix typo of clock name
clocksource/drivers/npcm: Add NPCM7xx timer driver
dt-binding: timer: document NPCM7xx timer DT bindings
Both ecryptfs_filldir() and ecryptfs_readlink_lower() use
ecryptfs_decode_and_decrypt_filename() to translate lower filenames to
upper filenames. The function correctly passes up lower filenames,
unchanged, when filename encryption isn't in use. However, it was also
passing up lower filenames when the filename wasn't encrypted or
when decryption failed. Since 88ae4ab980, eCryptfs refuses to lookup
lower plaintext names when filename encryption is enabled so this
resulted in a situation where userspace would see lower plaintext
filenames in calls to getdents(2) but then not be able to lookup those
filenames.
An example of this can be seen when enabling filename encryption on an
eCryptfs mount at the root directory of an Ext4 filesystem:
$ ls -1i /lower
12 ECRYPTFS_FNEK_ENCRYPTED.FWYZD8TcW.5FV-TKTEYOHsheiHX9a-w.NURCCYIMjI8pn5BDB9-h3fXwrE--
11 lost+found
$ ls -1i /upper
ls: cannot access '/upper/lost+found': No such file or directory
? lost+found
12 test
With this change, the lower lost+found dentry is ignored:
$ ls -1i /lower
12 ECRYPTFS_FNEK_ENCRYPTED.FWYZD8TcW.5FV-TKTEYOHsheiHX9a-w.NURCCYIMjI8pn5BDB9-h3fXwrE--
11 lost+found
$ ls -1i /upper
12 test
Additionally, some potentially noisy error/info messages in the related
code paths are turned into debug messages so that the logs can't be
easily filled.
Fixes: 88ae4ab980 ("ecryptfs_lookup(): try either only encrypted or plaintext name")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
writing nested virtualization tests.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)
iQEcBAABAgAGBQJa1MZMAAoJEL/70l94x66DupgH/jIRQ6wsZ9Hq5qBJ39sLFXNe
cAIAbaCUAck4tl5YNDgv/SOQ644ClmDVP/4CgezqosoY29eLY0+P71GQZEIQ7aB5
Taa7UI5qYnIctBmxFwD1+iV717Vyb+QLpRnMb8zjLkfT/3S8HsQvpcYJlQrrN3PP
w4VIvhZjPx11wvXDCuY6ire7sBEb/vSQQewGWg9dLt4hnDz1tRFMtAg/7GVT+rG9
SjuH57NrXAKWiNVlQvYfLSfaTyPf5J41i49nwFJJVPY1kMaXvOSDDOfejTD/SjTs
pYye7o8TGbrsY9O8H85gxdppHz4K0+sP9xNunUqk1wQ+zo9lWTejIaDoN2rzyuA=
=GKBC
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm fixes from Paolo Bonzini:
"Bug fixes, plus a new test case and the associated infrastructure for
writing nested virtualization tests"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
kvm: selftests: add vmx_tsc_adjust_test
kvm: x86: move MSR_IA32_TSC handling to x86.c
X86/KVM: Properly update 'tsc_offset' to represent the running guest
kvm: selftests: add -std=gnu99 cflags
x86: Add check for APIC access address for vmentry of L2 guests
KVM: X86: fix incorrect reference of trace_kvm_pi_irte_update
X86/KVM: Do not allow DISABLE_EXITS_MWAIT when LAPIC ARAT is not available
kvm: selftests: fix spelling mistake: "divisable" and "divisible"
X86/VMX: Disable VMX preemption timer if MWAIT is not intercepted
The |= operator will let us end up with an invalid PTE. Use
the correct &= instead.
[ The bug was also independently reported by Shuah Khan ]
Fixes: fb43d6cb91 ('x86/mm: Do not auto-massage page protections')
Acked-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
