Iommu would get page fault with following path:
vop_disable:
1, disable all windows and set vop config done
2, vop enter to standy, all windows not works, but their registers
are not clean, when you read window's enable bit, may found the
window is enable.
vop_enable:
1, memcpy(vop->regsbak, vop->regs, len)
save current vop registers to vop->regsbak, then you can found
window is enable on regsbak.
2, VOP_WIN_SET(vop, win, gate, 1);
force enable window gate, but gate and enable are on same
hardware register, then window enable bit rewrite to vop hardware.
3, vop power on, and vop might try to scan destroyed buffer,
then iommu get page fault.
Move windows disable after vop regsbak restore, then vop regsbak mechanism
would keep tracing the modify, everything would be safe.
Signed-off-by: Mark Yao <mark.yao@rock-chips.com>
Reviewed-by: Sandy huang <sandy.huang@rock-chips.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1501494582-6934-1-git-send-email-mark.yao@rock-chips.com
Iommu would get page fault with following path:
vop_disable:
1, disable all windows and set vop config done
2, vop enter to standy, all windows not works, but their registers
are not clean, when you read window's enable bit, may found the
window is enable.
vop_enable:
1, memcpy(vop->regsbak, vop->regs, len)
save current vop registers to vop->regsbak, then you can found
window is enable on regsbak.
2, VOP_WIN_SET(vop, win, gate, 1);
force enable window gate, but gate and enable are on same
hardware register, then window enable bit rewrite to vop hardware.
3, vop power on, and vop might try to scan destroyed buffer,
then iommu get page fault.
Move windows disable after vop regsbak restore, then vop regsbak mechanism
would keep tracing the modify, everything would be safe.
Signed-off-by: Mark Yao <mark.yao@rock-chips.com>
Reviewed-by: Sandy huang <sandy.huang@rock-chips.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1501494582-6934-1-git-send-email-mark.yao@rock-chips.com
pci_device_id are not supposed to change at runtime. All functions
working with pci_device_id provided by <linux/pci.h> work with
const pci_device_id. So mark the non-const structs as const.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
pci_device_id are not supposed to change at runtime. All functions
working with pci_device_id provided by <linux/pci.h> work with
const pci_device_id. So mark the non-const structs as const.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
pci_device_id are not supposed to change at runtime. All functions
working with pci_device_id provided by <linux/pci.h> work with
const pci_device_id. So mark the non-const structs as const.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
pci_device_id are not supposed to change at runtime. All functions
working with pci_device_id provided by <linux/pci.h> work with
const pci_device_id. So mark the non-const structs as const.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
pci_device_id are not supposed to change at runtime. All functions
working with pci_device_id provided by <linux/pci.h> work with
const pci_device_id. So mark the non-const structs as const.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
pci_device_id are not supposed to change at runtime. All functions
working with pci_device_id provided by <linux/pci.h> work with
const pci_device_id. So mark the non-const structs as const.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
pci_device_id are not supposed to change at runtime. All functions
working with pci_device_id provided by <linux/pci.h> work with
const pci_device_id. So mark the non-const structs as const.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
pci_device_id are not supposed to change at runtime. All functions
working with pci_device_id provided by <linux/pci.h> work with
const pci_device_id. So mark the non-const structs as const.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
pci_device_id are not supposed to change at runtime. All functions
working with pci_device_id provided by <linux/pci.h> work with
const pci_device_id. So mark the non-const structs as const.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Willem de Bruijn says:
====================
socket sendmsg MSG_ZEROCOPY
Introduce zerocopy socket send flag MSG_ZEROCOPY. This extends the
shared page support (SKBTX_SHARED_FRAG) from sendpage to sendmsg.
Implement the feature for TCP initially, as large writes benefit
most.
On a send call with MSG_ZEROCOPY, the kernel pins user pages and
links these directly into the skbuff frags[] array.
Each send call with MSG_ZEROCOPY that transmits data will eventually
queue a completion notification on the error queue: a per-socket u32
incremented on each such call. A request may have to revert to copy
to succeed, for instance when a device cannot support scatter-gather
IO. In that case a flag is passed along to notify that the operation
succeeded without zerocopy optimization.
The implementation extends the existing zerocopy infra for tuntap,
vhost and xen with features needed for TCP, notably reference
counting to handle cloning on retransmit and GSO.
For more details, see also the netdev 2.1 paper and presentation at
https://netdevconf.org/2.1/session.html?debruijn
Changelog:
v3 -> v4:
- dropped UDP, RAW and PF_PACKET for now
Without loopback support, datagrams are usually smaller than
the ~8KB size threshold needed to benefit from zerocopy.
- style: a few reverse chrismas tree
- minor: SO_ZEROCOPY returns ENOTSUPP on unsupported protocols
- minor: squashed SO_EE_CODE_ZEROCOPY_COPIED patch
- minor: rebased on top of net-next with kmap_atomic fix
v2 -> v3:
- fix rebase conflict: SO_ZEROCOPY 59 -> 60
v1 -> v2:
- fix (kbuild-bot): do not remove uarg until patch 5
- fix (kbuild-bot): move zerocopy_sg_from_iter doc with function
- fix: remove unused extern in header file
RFCv2 -> v1:
- patch 2
- review comment: in skb_copy_ubufs, always allocate order-0
page, also when replacing compound source pages.
- patch 3
- fix: always queue completion notification on MSG_ZEROCOPY,
also if revert to copy.
- fix: on syscall abort, correctly revert notification state
- minor: skip queue notification on SOCK_DEAD
- minor: replace BUG_ON with WARN_ON in recoverable error
- patch 4
- new: add socket option SOCK_ZEROCOPY.
only honor MSG_ZEROCOPY if set, ignore for legacy apps.
- patch 5
- fix: clear zerocopy state on skb_linearize
- patch 6
- fix: only coalesce if prev errqueue elem is zerocopy
- minor: try coalescing with list tail instead of head
- minor: merge bytelen limit patch
- patch 7
- new: signal when data had to be copied
- patch 8 (tcp)
- optimize: avoid setting PSH bit when exceeding max frags.
that limits GRO on the client. do not goto new_segment.
- fix: fail on MSG_ZEROCOPY | MSG_FASTOPEN
- minor: do not wait for memory: does not work for optmem
- minor: simplify alloc
- patch 9 (udp)
- new: add PF_INET6
- fix: attach zerocopy notification even if revert to copy
- minor: simplify alloc size arithmetic
- patch 10 (raw hdrinc)
- new: add PF_INET6
- patch 11 (pf_packet)
- minor: simplify slightly
- patch 12
- new msg_zerocopy regression test: use veth pair to test
all protocols: ipv4/ipv6/packet, tcp/udp/raw, cork
all relevant ethtool settings: rx off, sg off
all relevant packet lengths: 0, <MAX_HEADER, max size
RFC -> RFCv2:
- review comment: do not loop skb with zerocopy frags onto rx:
add skb_orphan_frags_rx to orphan even refcounted frags
call this in __netif_receive_skb_core, deliver_skb and tun:
same as commit 1080e512d4 ("net: orphan frags on receive")
- fix: hold an explicit sk reference on each notification skb.
previously relied on the reference (or wmem) held by the
data skb that would trigger notification, but this breaks
on skb_orphan.
- fix: when aborting a send, do not inc the zerocopy counter
this caused gaps in the notification chain
- fix: in packet with SOCK_DGRAM, pull ll headers before calling
zerocopy_sg_from_iter
- fix: if sock_zerocopy_realloc does not allow coalescing,
do not fail, just allocate a new ubuf
- fix: in tcp, check return value of second allocation attempt
- chg: allocate notification skbs from optmem
to avoid affecting tcp write queue accounting (TSQ)
- chg: limit #locked pages (ulimit) per user instead of per process
- chg: grow notification ids from 16 to 32 bit
- pass range [lo, hi] through 32 bit fields ee_info and ee_data
- chg: rebased to davem-net-next on top of v4.10-rc7
- add: limit notification coalescing
sharing ubufs limits overhead, but delays notification until
the last packet is released, possibly unbounded. Add a cap.
- tests: add snd_zerocopy_lo pf_packet test
- tests: two bugfixes (add do_flush_tcp, ++sent not only in debug)
Limitations / Known Issues:
- TCP may build slightly smaller than max TSO packets due to
exceeding MAX_SKB_FRAGS frags when zerocopy pages are unaligned.
- All SKBTX_SHARED_FRAG may require additional __skb_linearize or
skb_copy_ubufs calls in u32, skb_find_text, similar to
skb_checksum_help.
Notification skbuffs are allocated from optmem. For sockets that
cannot effectively coalesce notifications, the optmem max may need
to be increased to avoid hitting -ENOBUFS:
sysctl -w net.core.optmem_max=1048576
In application load, copy avoidance shows a roughly 5% systemwide
reduction in cycles when streaming large flows and a 4-8% reduction in
wall clock time on early tensorflow test workloads.
For the single-machine veth tests to succeed, loopback support has to
be temporarily enabled by making skb_orphan_frags_rx map to
skb_orphan_frags.
* Performance
The below table shows cycles reported by perf for a netperf process
sending a single 10 Gbps TCP_STREAM. The first three columns show
Mcycles spent in the netperf process context. The second three columns
show time spent systemwide (-a -C A,B) on the two cpus that run the
process and interrupt handler. Reported is the median of at least 3
runs. std is a standard netperf, zc uses zerocopy and % is the ratio.
Netperf is pinned to cpu 2, network interrupts to cpu3, rps and rfs
are disabled and the kernel is booted with idle=halt.
NETPERF=./netperf -t TCP_STREAM -H $host -T 2 -l 30 -- -m $size
perf stat -e cycles $NETPERF
perf stat -C 2,3 -a -e cycles $NETPERF
--process cycles-- ----cpu cycles----
std zc % std zc %
4K 27,609 11,217 41 49,217 39,175 79
16K 21,370 3,823 18 43,540 29,213 67
64K 20,557 2,312 11 42,189 26,910 64
256K 21,110 2,134 10 43,006 27,104 63
1M 20,987 1,610 8 42,759 25,931 61
Perf record indicates the main source of these differences. Process
cycles only at 1M writes (perf record; perf report -n):
std:
Samples: 42K of event 'cycles', Event count (approx.): 21258597313
79.41% 33884 netperf [kernel.kallsyms] [k] copy_user_generic_string
3.27% 1396 netperf [kernel.kallsyms] [k] tcp_sendmsg
1.66% 694 netperf [kernel.kallsyms] [k] get_page_from_freelist
0.79% 325 netperf [kernel.kallsyms] [k] tcp_ack
0.43% 188 netperf [kernel.kallsyms] [k] __alloc_skb
zc:
Samples: 1K of event 'cycles', Event count (approx.): 1439509124
30.36% 584 netperf.zerocop [kernel.kallsyms] [k] gup_pte_range
14.63% 284 netperf.zerocop [kernel.kallsyms] [k] __zerocopy_sg_from_iter
8.03% 159 netperf.zerocop [kernel.kallsyms] [k] skb_zerocopy_add_frags_iter
4.84% 96 netperf.zerocop [kernel.kallsyms] [k] __alloc_skb
3.10% 60 netperf.zerocop [kernel.kallsyms] [k] kmem_cache_alloc_node
* Safety
The number of pages that can be pinned on behalf of a user with
MSG_ZEROCOPY is bound by the locked memory ulimit.
While the kernel holds process memory pinned, a process cannot safely
reuse those pages for other purposes. Packets looped onto the receive
stack and queued to a socket can be held indefinitely. Avoid unbounded
notification latency by restricting user pages to egress paths only.
skb_orphan_frags_rx() will create a private copy of pages even for
refcounted packets when these are looped, as did skb_orphan_frags for
the original tun zerocopy implementation.
Pages are not remapped read-only. Processes can modify packet contents
while packets are in flight in the kernel path. Bytes on which kernel
control flow depends (headers) are copied to avoid TOCTTOU attacks.
Datapath integrity does not otherwise depend on payload, with three
exceptions: checksums, optional sk_filter/tc u32/.. and device +
driver logic. The effect of wrong checksums is limited to the
misbehaving process. TC filters that access contents may have to be
excluded by adding an skb_orphan_frags_rx.
Processes can also safely avoid OOM conditions by bounding the number
of bytes passed with MSG_ZEROCOPY and by removing shared pages after
transmission from their own memory map.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce regression test for msg_zerocopy feature. Send traffic from
one process to another with and without zerocopy.
Evaluate tcp, udp, raw and packet sockets, including variants
- udp: corking and corking with mixed copy/zerocopy calls
- raw: with and without hdrincl
- packet: at both raw and dgram level
Test on both ipv4 and ipv6, optionally with ethtool changes to
disable scatter-gather, tx checksum or tso offload. All of these
can affect zerocopy behavior.
The regression test can be run on a single machine if over a veth
pair. Then skb_orphan_frags_rx must be modified to be identical to
skb_orphan_frags to allow forwarding zerocopy locally.
The msg_zerocopy.sh script will setup the veth pair in network
namespaces and run all tests.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Enable support for MSG_ZEROCOPY to the TCP stack. TSO and GSO are
both supported. Only data sent to remote destinations is sent without
copying. Packets looped onto a local destination have their payload
copied to avoid unbounded latency.
Tested:
A 10x TCP_STREAM between two hosts showed a reduction in netserver
process cycles by up to 70%, depending on packet size. Systemwide,
savings are of course much less pronounced, at up to 20% best case.
msg_zerocopy.sh 4 tcp:
without zerocopy
tx=121792 (7600 MB) txc=0 zc=n
rx=60458 (7600 MB)
with zerocopy
tx=286257 (17863 MB) txc=286257 zc=y
rx=140022 (17863 MB)
This test opens a pair of sockets over veth, one one calls send with
64KB and optionally MSG_ZEROCOPY and on the other reads the initial
bytes. The receiver truncates, so this is strictly an upper bound on
what is achievable. It is more representative of sending data out of
a physical NIC (when payload is not touched, either).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bound the number of pages that a user may pin.
Follow the lead of perf tools to maintain a per-user bound on memory
locked pages commit 789f90fcf6 ("perf_counter: per user mlock gift")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the simple case, each sendmsg() call generates data and eventually
a zerocopy ready notification N, where N indicates the Nth successful
invocation of sendmsg() with the MSG_ZEROCOPY flag on this socket.
TCP and corked sockets can cause send() calls to append new data to an
existing sk_buff and, thus, ubuf_info. In that case the notification
must hold a range. odify ubuf_info to store a inclusive range [N..N+m]
and add skb_zerocopy_realloc() to optionally extend an existing range.
Also coalesce notifications in this common case: if a notification
[1, 1] is about to be queued while [0, 0] is the queue tail, just modify
the head of the queue to read [0, 1].
Coalescing is limited to a few TSO frames worth of data to bound
notification latency.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Prepare the datapath for refcounted ubuf_info. Clone ubuf_info with
skb_zerocopy_clone() wherever needed due to skb split, merge, resize
or clone.
Split skb_orphan_frags into two variants. The split, merge, .. paths
support reference counted zerocopy buffers, so do not do a deep copy.
Add skb_orphan_frags_rx for paths that may loop packets to receive
sockets. That is not allowed, as it may cause unbounded latency.
Deep copy all zerocopy copy buffers, ref-counted or not, in this path.
The exact locations to modify were chosen by exhaustively searching
through all code that might modify skb_frag references and/or the
the SKBTX_DEV_ZEROCOPY tx_flags bit.
The changes err on the safe side, in two ways.
(1) legacy ubuf_info paths virtio and tap are not modified. They keep
a 1:1 ubuf_info to sk_buff relationship. Calls to skb_orphan_frags
still call skb_copy_ubufs and thus copy frags in this case.
(2) not all copies deep in the stack are addressed yet. skb_shift,
skb_split and skb_try_coalesce can be refined to avoid copying.
These are not in the hot path and this patch is hairy enough as
is, so that is left for future refinement.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The send call ignores unknown flags. Legacy applications may already
unwittingly pass MSG_ZEROCOPY. Continue to ignore this flag unless a
socket opts in to zerocopy.
Introduce socket option SO_ZEROCOPY to enable MSG_ZEROCOPY processing.
Processes can also query this socket option to detect kernel support
for the feature. Older kernels will return ENOPROTOOPT.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The kernel supports zerocopy sendmsg in virtio and tap. Expand the
infrastructure to support other socket types. Introduce a completion
notification channel over the socket error queue. Notifications are
returned with ee_origin SO_EE_ORIGIN_ZEROCOPY. ee_errno is 0 to avoid
blocking the send/recv path on receiving notifications.
Add reference counting, to support the skb split, merge, resize and
clone operations possible with SOCK_STREAM and other socket types.
The patch does not yet modify any datapaths.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Refine skb_copy_ubufs to support compound pages. With upcoming TCP
zerocopy sendmsg, such fragments may appear.
The existing code replaces each page one for one. Splitting each
compound page into an independent number of regular pages can result
in exceeding limit MAX_SKB_FRAGS if data is not exactly page aligned.
Instead, fill all destination pages but the last to PAGE_SIZE.
Split the existing alloc + copy loop into separate stages:
1. compute bytelength and minimum number of pages to store this.
2. allocate
3. copy, filling each page except the last to PAGE_SIZE bytes
4. update skb frag array
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add sock_omalloc and sock_ofree to be able to allocate control skbs,
for instance for looping errors onto sk_error_queue.
The transmit budget (sk_wmem_alloc) is involved in transmit skb
shaping, most notably in TCP Small Queues. Using this budget for
control packets would impact transmission.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If the decrementer wraps again and de-asserts the decrementer
exception while hard-disabled, __check_irq_replay() has a test to
notice the wrap when interrupts are re-enabled.
The decrementer check must be done when clearing the PACA_IRQ_HARD_DIS
flag, not when the PACA_IRQ_DEC flag is tested. Previously this worked
because the decrementer interrupt was always the first one checked
after clearing the hard disable flag, but HMI check was moved ahead of
that, which introduced this bug.
This can cause a missed decrementer interrupt if we soft-disable
interrupts then take an HMI which is recorded in irq_happened, then
hard-disable interrupts for > 4s to wrap the decrementer.
Fixes: e0e0d6b739 ("powerpc/64: Replay hypervisor maintenance interrupt first")
Cc: stable@vger.kernel.org # v4.9+
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
POWER9 DD2 PMU can stop after a state-loss idle in some conditions.
A solution is to set then clear MMCRA[60] after wake from state-loss
idle. MMCRA[60] is a non-architected bit, see the user manual for
details.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Reviewed-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Acked-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Just a few small fixes for 4.13.
* 'drm-fixes-4.13' of git://people.freedesktop.org/~agd5f/linux:
drm/amdgpu: Use list_del_init in amdgpu_mn_unregister
drm/amdgpu: Fix undue fallthroughs in golden registers initialization
drm/amdgpu: fix header on gfx9 clear state
rcar-du updates, contains vsp1 updates as well.
* tag 'drm-next-du-20170803' of git://linuxtv.org/pinchartl/media: (24 commits)
drm: rcar-du: Use new iterator macros
drm: rcar-du: Repair vblank for DRM page flips using the VSP
drm: rcar-du: Fix race condition when disabling planes at CRTC stop
drm: rcar-du: Wait for flip completion instead of vblank in commit tail
drm: rcar-du: Use the VBK interrupt for vblank events
drm: rcar-du: Add HDMI outputs to R8A7796 device description
drm: rcar-du: Remove an unneeded NULL check
drm: rcar-du: Setup planes before enabling CRTC to avoid flicker
drm: rcar-du: Configure DPAD0 routing through last group on Gen3
drm: rcar-du: Restrict DPLL duty cycle workaround to H3 ES1.x
drm: rcar-du: Support multiple sources from the same VSP
drm: rcar-du: Fix comments to comply with the kernel coding style
drm: rcar-du: Use of_graph_get_remote_endpoint()
v4l: vsp1: Add support for header display lists in continuous mode
v4l: vsp1: Add support for multiple DRM pipelines
v4l: vsp1: Add support for multiple LIF instances
v4l: vsp1: Add support for new VSP2-BS, VSP2-DL and VSP2-D instances
v4l: vsp1: Add support for the BRS entity
v4l: vsp1: Add pipe index argument to the VSP-DU API
v4l: vsp1: Don't create links for DRM pipeline
...
The CCP supports a limited set of unit-size values. Change the check
for this parameter such that acceptable values match the enumeration.
Then clarify the conditions under which we must use the fallback
implementation.
Signed-off-by: Gary R Hook <gary.hook@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Version 5 CCPs have some new requirements for XTS-AES: the type field
must be specified, and the key requires 512 bits, with each part
occupying 256 bits and padded with zeroes.
cc: <stable@vger.kernel.org> # 4.9.x+
Signed-off-by: Gary R Hook <ghook@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
For the final round, avoid the expanded and padded lookup tables
exported by the generic AES driver. Instead, for encryption, we can
perform byte loads from the same table we used for the inner rounds,
which will still be hot in the caches. For decryption, use the inverse
AES Sbox directly, which is 4x smaller than the inverse lookup table
exported by the generic driver.
This should significantly reduce the Dcache footprint of our code,
which makes the code more robust against timing attacks. It does not
introduce any additional module dependencies, given that we already
rely on the core AES module for the shared key expansion routines.
It also frees up register x18, which is not available as a scratch
register on all platforms, which and so avoiding it improves
shareability of this code.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
For the final round, avoid the expanded and padded lookup tables
exported by the generic AES driver. Instead, for encryption, we can
perform byte loads from the same table we used for the inner rounds,
which will still be hot in the caches. For decryption, use the inverse
AES Sbox directly, which is 4x smaller than the inverse lookup table
exported by the generic driver.
This should significantly reduce the Dcache footprint of our code,
which makes the code more robust against timing attacks. It does not
introduce any additional module dependencies, given that we already
rely on the core AES module for the shared key expansion routines.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Implement a NEON fallback for systems that do support NEON but have
no support for the optional 64x64->128 polynomial multiplication
instruction that is part of the ARMv8 Crypto Extensions. It is based
on the paper "Fast Software Polynomial Multiplication on ARM Processors
Using the NEON Engine" by Danilo Camara, Conrado Gouvea, Julio Lopez and
Ricardo Dahab (https://hal.inria.fr/hal-01506572), but has been reworked
extensively for the AArch64 ISA.
On a low-end core such as the Cortex-A53 found in the Raspberry Pi3, the
NEON based implementation is 4x faster than the table based one, and
is time invariant as well, making it less vulnerable to timing attacks.
When combined with the bit-sliced NEON implementation of AES-CTR, the
AES-GCM performance increases by 2x (from 58 to 29 cycles per byte).
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Implement a NEON fallback for systems that do support NEON but have
no support for the optional 64x64->128 polynomial multiplication
instruction that is part of the ARMv8 Crypto Extensions. It is based
on the paper "Fast Software Polynomial Multiplication on ARM Processors
Using the NEON Engine" by Danilo Camara, Conrado Gouvea, Julio Lopez and
Ricardo Dahab (https://hal.inria.fr/hal-01506572)
On a 32-bit guest executing under KVM on a Cortex-A57, the new code is
not only 4x faster than the generic table based GHASH driver, it is also
time invariant. (Note that the existing vmull.p64 code is 16x faster on
this core).
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Currently, the AES-GCM implementation for arm64 systems that support the
ARMv8 Crypto Extensions is based on the generic GCM module, which combines
the AES-CTR implementation using AES instructions with the PMULL based
GHASH driver. This is suboptimal, given the fact that the input data needs
to be loaded twice, once for the encryption and again for the MAC
calculation.
On Cortex-A57 (r1p2) and other recent cores that implement micro-op fusing
for the AES instructions, AES executes at less than 1 cycle per byte, which
means that any cycles wasted on loading the data twice hurt even more.
So implement a new GCM driver that combines the AES and PMULL instructions
at the block level. This improves performance on Cortex-A57 by ~37% (from
3.5 cpb to 2.6 cpb)
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Of the various chaining modes implemented by the bit sliced AES driver,
only CTR is exposed as a synchronous cipher, and requires a fallback in
order to remain usable once we update the kernel mode NEON handling logic
to disallow nested use. So wire up the existing CTR fallback C code.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
To accommodate systems that disallow the use of kernel mode NEON in
some circumstances, take the return value of may_use_simd into
account when deciding whether to invoke the C fallback routine.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
To accommodate systems that may disallow use of the NEON in kernel mode
in some circumstances, introduce a C fallback for synchronous AES in CTR
mode, and use it if may_use_simd() returns false.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The arm64 kernel will shortly disallow nested kernel mode NEON.
So honour this in the ARMv8 Crypto Extensions implementation of
CCM-AES, and fall back to a scalar implementation using the generic
crypto helpers for AES, XOR and incrementing the CTR counter.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The arm64 kernel will shortly disallow nested kernel mode NEON, so
add a fallback to scalar code that can be invoked in that case.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
In order to be able to reuse the generic AES code as a fallback for
situations where the NEON may not be used, update the key handling
to match the byte order of the generic code: it stores round keys
as sequences of 32-bit quantities rather than streams of bytes, and
so our code needs to be updated to reflect that.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The arm64 kernel will shortly disallow nested kernel mode NEON, so
add a fallback to scalar code that can be invoked in that case.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The arm64 kernel will shortly disallow nested kernel mode NEON, so
add a fallback to scalar C code that can be invoked in that case.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The arm64 kernel will shortly disallow nested kernel mode NEON, so
add a fallback to scalar C code that can be invoked in that case.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
