User specifies the clock selection by using -w CLOCK or --clock=CLOCK
where CLOCK=[REALTIME, TAI, BOOTTIME, MONOTONIC].
The default CLOCK selection is MONOTONIC.
The implementation of clock selection parsing is borrowed from
iproute2/tc/q_taprio.c
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211230035447.523177-4-boon.leong.ong@intel.com
To set Dest MAC address (-G|--tx-dmac) only:
$ xdpsock -i eth0 -t -N -z -G aa:bb:cc:dd:ee:ff
To set Source MAC address (-H|--tx-smac) only:
$ xdpsock -i eth0 -t -N -z -H 11:22:33:44:55:66
To set both Dest and Source MAC address:
$ xdpsock -i eth0 -t -N -z -G aa:bb:cc:dd:ee:ff \
-H 11:22:33:44:55:66
The default Dest and Source MAC address remain the same as before.
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/20211230035447.523177-3-boon.leong.ong@intel.com
In multi-queue environment testing, the support for VLAN-tag based
steering is useful. So, this patch adds the capability to add
VLAN tag (VLAN ID and Priority) to the generated Tx frame.
To set the VLAN ID=10 and Priority=2 for Tx only through TxQ=3:
$ xdpsock -i eth0 -t -N -z -q 3 -V -J 10 -K 2
If VLAN ID (-J) and Priority (-K) is set, it default to
VLAN ID = 1
VLAN Priority = 0.
For example, VLAN-tagged Tx only, xdp copy mode through TxQ=1:
$ xdpsock -i eth0 -t -N -c -q 1 -V
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211230035447.523177-2-boon.leong.ong@intel.com
This defines the mapping from ABI names to X registers.
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
This is a riscv port of commit d6e2cc5647 ("arm64: extable: add `type`
and `data` fields").
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
This is a riscv port of commit 819771cc28 ("arm64: extable:
consolidate definitions").
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
uaccess functions such __asm_copy_to_user(), __arch_copy_from_user()
and __clear_user() place their exception fixups in the `.fixup` section
without any clear association with themselves. If we backtrace the
fixup code, it will be symbolized as an offset from the nearest prior
symbol.
Similar as arm64 does, we must move fixups into the body of the
functions themselves, after the usual fast-path returns.
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
The var name "fixup" is a bit confusing, since this is a
exception_table_entry. Use "ex" instead to refer to an entire entry.
In subsequent patches we'll use `fixup` to refer to the fixup
field specifically.
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
The return values of fixup_exception() and riscv_bpf_fixup_exception()
represent a boolean condition rather than an error code, so it's better
to return `bool` rather than `int`.
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
This is to group riscv related extable related functions signature
into one file.
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Similar as other architectures such as arm64, x86 and so on, use
offsets relative to the exception table entry values rather than
absolute addresses for both the exception locationand the fixup.
However, RISCV label difference will actually produce two relocations,
a pair of R_RISCV_ADD32 and R_RISCV_SUB32. Take below simple code for
example:
$ cat test.S
.section .text
1:
nop
.section __ex_table,"a"
.balign 4
.long (1b - .)
.previous
$ riscv64-linux-gnu-gcc -c test.S
$ riscv64-linux-gnu-readelf -r test.o
Relocation section '.rela__ex_table' at offset 0x100 contains 2 entries:
Offset Info Type Sym. Value Sym. Name + Addend
000000000000 000600000023 R_RISCV_ADD32 0000000000000000 .L1^B1 + 0
000000000000 000500000027 R_RISCV_SUB32 0000000000000000 .L0 + 0
The modpost will complain the R_RISCV_SUB32 relocation, so we need to
patch modpost.c to skip this relocation for .rela__ex_table section.
After this patch, the __ex_table section size of defconfig vmlinux is
reduced from 7072 Bytes to 3536 Bytes.
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Consolidate all the __ex_table constuction code with a _ASM_EXTABLE
helper.
There should be no functional change as a result of this patch.
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Commit 21e743300d ("clk: stm32mp1: new compatible for secure RCC support")
introduced a new Kconfig option COMMON_CLK_STM32MP157_SCMI which is not
used anywhere.
Further, it looks like this Kconfig option is just to select bunch of other
options which doesn't sound correct to me. There is no need for another
SCMI firmware based clock driver and hence the same applies for the config
option too.
Let us just drop the unused COMMON_CLK_STM32MP157_SCMI before it gives
someone idea to write a specific clock driver for this SoC/platform.
Cc: Etienne Carriere <etienne.carriere@foss.st.com>
Cc: Gabriel Fernandez <gabriel.fernandez@foss.st.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20211015150043.140793-1-sudeep.holla@arm.com
Reviewed-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
In order to avoid having duplicated addresses within the DT,
only have one unit-address per clockgen and each driver within
the clockgen should look at the parent node (overall clockgen)
to figure out the reg property. Such behavior is already in
place in other STi platform clock drivers such as clk-flexgen
and clkgen-pll. Keep backward compatibility by first looking
at reg within the node before looking into the parent node.
Signed-off-by: Alain Volmat <avolmat@me.com>
Link: https://lore.kernel.org/r/20211218211157.188214-3-avolmat@me.com
Reviewed-by: Patrice Chotard <patrice.chotard@foss.st.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
In order to avoid having duplicated addresses within the DT,
only have one unit-address per clockgen and each driver within
the clockgen should look at the parent node (overall clockgen)
to figure out the reg property. Such behavior is already in
place in other STi platform clock drivers such as clk-flexgen
and clkgen-pll. Keep backward compatibility by first looking
at reg within the node before looking into the parent node.
Signed-off-by: Alain Volmat <avolmat@me.com>
Link: https://lore.kernel.org/r/20211218211157.188214-2-avolmat@me.com
Reviewed-by: Patrice Chotard <patrice.chotard@foss.st.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The registers for some clocks in the SOC area, which are under the power
domain are required to be enabled before accessing them. During the
clk_summary if the power-domains are not enabled they could result into
NoC errors.
Thus ensure the register access of the clock controller is done with
pm_untime_get/put functions.
Signed-off-by: Taniya Das <tdas@codeaurora.org>
Link: https://lore.kernel.org/r/1640018638-19436-3-git-send-email-tdas@codeaurora.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Aleksander Jan Bajkowski says:
====================
net: lantiq_xrx200: improve ethernet performance
This patchset improves Ethernet performance by 15%.
NAT Performance results on BT Home Hub 5A (kernel 5.10.89, mtu 1500):
Down Up
Before 539 Mbps 599 Mbps
After 624 Mbps 695 Mbps
====================
Link: https://lore.kernel.org/r/20220104151144.181736-1-olek2@wp.pl
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We can increase the efficiency of rx path by using buffers to receive
packets then build SKBs around them just before passing into the network
stack. In contrast, preallocating SKBs too early reduces CPU cache
efficiency.
NAT Performance results on BT Home Hub 5A (kernel 5.10.89, mtu 1500):
Down Up
Before 577 Mbps 648 Mbps
After 624 Mbps 695 Mbps
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
NAT Performance results on BT Home Hub 5A (kernel 5.10.89, mtu 1500):
Down Up
Before 545 Mbps 625 Mbps
After 577 Mbps 648 Mbps
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
NAT Performance results on BT Home Hub 5A (kernel 5.10.89, mtu 1500):
Down Up
Before 539 Mbps 599 Mbps
After 545 Mbps 625 Mbps
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add support for common interface of the common clock and reset driver
for Toshiba Visconti5 and its SoC, TMPV7708. The PIPLLCT provides the PLL,
and the PISMU provides clock and reset functionality.
Each drivers are provided in this patch.
Signed-off-by: Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp>
Link: https://lore.kernel.org/r/20211025031038.4180686-4-nobuhiro1.iwamatsu@toshiba.co.jp
[sboyd@kernel.org: Add bitfield.h include to pll.c]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
When the -L option of the testptp utility is specified with other
options (e.g. -p to enable PPS output), the user probably wants to
apply it to the pin configured by the -L option.
Reorder the code to set the pin function before other function requests
to avoid confusing users.
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Link: https://lore.kernel.org/r/20220105152506.3256026-1-mlichvar@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----
iQFHBAABCgAxFiEEK3kIWJt9yTYMP3ehqclaivrt76kFAmHWBHkTHG1rbEBwZW5n
dXRyb25peC5kZQAKCRCpyVqK+u3vqaY0CACb2NOHCl09a20N6REAmKzdXEq6LO0C
52fSdeAhRffWh7GqlQED7+XgzuGimsQ5DYWMzP1dzCCVuI/f1gZwrMKJU/e3rZjE
wR9VgIwTUulauW1KMUz/R8qJP5R7xq5wKXflm9iPcDo7buzTDf441vTt8WhQILIB
ajl94ZSzhpy4yNk+YBJObanMALRTSjBPrIlEjzDdsex/IjkPDkTm8NYe7SRWzMf3
UQR6rEAIecKBwnl0Q3bwcOU5GL8j333Xem2bxDsnm93tjfBwEtBfBX6XM1UX2B2L
9WooLHmJHibkmp/1vNMzlGvi9crdTrMhWnFweTaAsr29yG3JZ4r2PytO
=bCV1
-----END PGP SIGNATURE-----
Merge tag 'linux-can-fixes-for-5.16-20220105' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can
Marc Kleine-Budde says:
====================
pull-request: can 2022-01-05
It consists of 2 patches, both by me. The first one fixes the use of
an uninitialized variable in the gs_usb driver the other one a
skb_over_panic in the ISOTP stack in case of reception of too large
ISOTP messages.
* tag 'linux-can-fixes-for-5.16-20220105' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can:
can: isotp: convert struct tpcon::{idx,len} to unsigned int
can: gs_usb: fix use of uninitialized variable, detach device on reception of invalid USB data
====================
Link: https://lore.kernel.org/r/20220105205443.1274709-1-mkl@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Use the devm_platform_ioremap_resource() helper instead of
calling platform_get_resource() and devm_ioremap_resource()
separately
Signed-off-by: Cai Huoqing <caihuoqing@baidu.com>
Link: https://lore.kernel.org/r/20210907085144.4458-1-caihuoqing@baidu.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Use the devm_platform_ioremap_resource() helper instead of
calling platform_get_resource() and devm_ioremap_resource()
separately
Signed-off-by: Cai Huoqing <caihuoqing@baidu.com>
Link: https://lore.kernel.org/r/20210907085137.4407-1-caihuoqing@baidu.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The assignment operation after a & mask operation is redundant, the
variables being assigned are not used afterwards. Replace the &=
operator with just & operator.
Cleans up two clang-scan warnings:
drivers/clk/socfpga/clk-gate.c:37:10: warning: Although the value stored
to 'l4_src' is used in the enclosing expression, the value is never
actually read from 'l4_src' [deadcode.DeadStores]
return l4_src &= 0x1;
^ ~~~
drivers/clk/socfpga/clk-gate.c:46:10: warning: Although the value stored
to 'perpll_src' is used in the enclosing expression, the value is never
actually read from 'perpll_src' [deadcode.DeadStores]
return perpll_src &= 0x3;
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://lore.kernel.org/r/20211230150321.167576-1-colin.i.king@gmail.com
Acked-by: Dinh Nguyen <dinguyen@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The variable parent_rate is being divided by div and the result
is re-assigned to parent_rate before being returned. The assignment
is redundant, replace /= operator with just / operator.
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://lore.kernel.org/r/20211221003750.212780-1-colin.i.king@gmail.com
Acked-by: Dinh Nguyen <dinguyen@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Optimize two problems
a)Turn off low voltage detection register.During the esd test,
the low-voltage detection ic may be triggered to enter the slpin state,
so a black screen occurs on the panel.
b)Optimize CMD2 page1 gamma.
Signed-off-by: yangcong <yangcong5@huaqin.corp-partner.google.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20211231045056.118640-1-yangcong5@huaqin.corp-partner.google.com
This introduces bindings and drivers for the global clock controllers
found in SDX65, SM8450 and MSM8976, as well as RPMh clock support for
SDX65 and SM8450.
It cleans up the SMD RPM clock driver and it adds includes for
clk-provider.h throughout the clock providers that was lacking this.
-----BEGIN PGP SIGNATURE-----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=PGNc
-----END PGP SIGNATURE-----
Merge tag 'qcom-clk-for-5.17' of https://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux into clk-qcom
Pull qcom clk driver updates from Bjorn Andersson:
This introduces bindings and drivers for the global clock controllers
found in SDX65, SM8450 and MSM8976, as well as RPMh clock support for
SDX65 and SM8450.
It cleans up the SMD RPM clock driver and it adds includes for
clk-provider.h throughout the clock providers that was lacking this.
* tag 'qcom-clk-for-5.17' of https://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux: (23 commits)
clk: qcom: turingcc-qcs404: explicitly include clk-provider.h
clk: qcom: q6sstop-qcs404: explicitly include clk-provider.h
clk: qcom: mmcc-apq8084: explicitly include clk-provider.h
clk: qcom: lpasscc-sdm845: explicitly include clk-provider.h
clk: qcom: lpasscc-sc7280: explicitly include clk-provider.h
clk: qcom: gcc-sm6350: explicitly include clk-provider.h
clk: qcom: gcc-msm8994: explicitly include clk-provider.h
clk: qcom: gcc-sm8350: explicitly include clk-provider.h
clk: qcom: Add MSM8976/56 Global Clock Controller (GCC) driver
dt-bindings: clk: qcom: Document MSM8976 Global Clock Controller
clk: qcom: Add clock driver for SM8450
clk: qcom: Add SDX65 GCC support
clk: qcom: Add LUCID_EVO PLL type for SDX65
dt-bindings: clock: Add SM8450 GCC clock bindings
dt-bindings: clock: Add SDX65 GCC clock bindings
clk: qcom: rpmh: add support for SM8450 rpmh clocks
dt-bindings: clock: Add RPMHCC bindings for SM8450
clk: qcom: smd-rpm: Drop binary value handling for buffered clock
clk: qcom: smd-rpm: Drop the use of struct rpm_cc
clk: qcom: smd-rpm: Drop MFD qcom-rpm reference
...
The gcc cfg noc lpass clock is required to be always enabled for the
LPASS core and audio drivers to be functional.
Fixes: a3cc092196 ("clk: qcom: Add Global Clock controller (GCC) driver for SC7280")
Signed-off-by: Taniya Das <tdas@codeaurora.org>
Link: https://lore.kernel.org/r/1640018638-19436-4-git-send-email-tdas@codeaurora.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
PLL poll for lock detection can take more than 100us for certain type
of Lucid PLLs and also the new PLLs types(Lucid EVO), thus update to 200us.
Signed-off-by: Taniya Das <tdas@codeaurora.org>
Link: https://lore.kernel.org/r/1640018638-19436-2-git-send-email-tdas@codeaurora.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The documentation for "drm_plane_funcs.format_mod_supported" reads:
This *optional* hook is used for the DRM to determine if the given
format/modifier combination is valid for the plane. This allows the
DRM to generate the correct format bitmask (which formats apply to
which modifier), and to validate modifiers at atomic_check time.
*If not present*, then any modifier in the plane's modifier
list is allowed with any of the plane's formats.
However, where the function is not present, an invalid IN_FORMATS blob
property with modifiers but no formats is exposed to user-space.
This breaks the latest Weston [1]. For testing purposes, I extracted the
affected code to a standalone program [2].
Make "create_in_format_blob" behave as documented.
[1] https://gitlab.freedesktop.org/wayland/weston/-/blob/9.0/libweston/backend-drm/kms.c#L431
[2] https://github.com/JoseExposito/drm-sandbox/blob/main/in_formats.c
Signed-off-by: José Expósito <jose.exposito89@gmail.com>
Reviewed-by: Simon Ser <contact@emersion.fr>
Signed-off-by: Simon Ser <contact@emersion.fr>
Link: https://patchwork.freedesktop.org/patch/msgid/20211226112503.31771-2-jose.exposito89@gmail.com
With the new osnoise tracer, we are seeing the below splat:
Kernel attempted to read user page (c7d880000) - exploit attempt? (uid: 0)
BUG: Unable to handle kernel data access on read at 0xc7d880000
Faulting instruction address: 0xc0000000002ffa10
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries
...
NIP [c0000000002ffa10] __trace_array_vprintk.part.0+0x70/0x2f0
LR [c0000000002ff9fc] __trace_array_vprintk.part.0+0x5c/0x2f0
Call Trace:
[c0000008bdd73b80] [c0000000001c49cc] put_prev_task_fair+0x3c/0x60 (unreliable)
[c0000008bdd73be0] [c000000000301430] trace_array_printk_buf+0x70/0x90
[c0000008bdd73c00] [c0000000003178b0] trace_sched_switch_callback+0x250/0x290
[c0000008bdd73c90] [c000000000e70d60] __schedule+0x410/0x710
[c0000008bdd73d40] [c000000000e710c0] schedule+0x60/0x130
[c0000008bdd73d70] [c000000000030614] interrupt_exit_user_prepare_main+0x264/0x270
[c0000008bdd73de0] [c000000000030a70] syscall_exit_prepare+0x150/0x180
[c0000008bdd73e10] [c00000000000c174] system_call_vectored_common+0xf4/0x278
osnoise tracer on ppc64le is triggering osnoise_taint() for negative
duration in get_int_safe_duration() called from
trace_sched_switch_callback()->thread_exit().
The problem though is that the check for a valid trace_percpu_buffer is
incorrect in get_trace_buf(). The check is being done after calculating
the pointer for the current cpu, rather than on the main percpu pointer.
Fix the check to be against trace_percpu_buffer.
Link: https://lkml.kernel.org/r/a920e4272e0b0635cf20c444707cbce1b2c8973d.1640255304.git.naveen.n.rao@linux.vnet.ibm.com
Cc: stable@vger.kernel.org
Fixes: e2ace00117 ("tracing: Choose static tp_printk buffer by explicit nesting count")
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
If repeated legacy kprobes on same function in one process,
libbpf will register using the same probe name and got -EBUSY
error. So append index to the probe name format to fix this
problem.
Co-developed-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Qiang Wang <wangqiang.wq.frank@bytedance.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211227130713.66933-2-wangqiang.wq.frank@bytedance.com
In order to complete a scsi command and guarantee that the HCA will never
perform an access violation when retrying a send operation we must
complete a scsi request only when both send and receive completions has
arrived. This is a preparation commit that remove the send completions
suppression. Next step will be taking care of the local invalidation
mechanism and adding a reference counter for commands. Currently, we
don't do anything upon getting the send completion and just "consume" it.
Link: https://lore.kernel.org/r/20211215135721.3662-5-mgurtovoy@nvidia.com
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Use more common name for return values ("ret"). This commit doesn't change
any logic.
Link: https://lore.kernel.org/r/20211215135721.3662-4-mgurtovoy@nvidia.com
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Some users complain about RNR errors on the target, when heavy
high-priority tasks run on the initiator. After the investigation, we
found out that the receive WRs were exhausted, because the initiator could
not post them on time.
Receive work reqeusts are posted in chunks to reduce the number of hits to
the HCA. The WRs are posted in the receive completion handler when the
number of free receive buffers reaches the threshold. But on a high-loaded
host, receive CQEs processing can be delayed and all receive WRs will be
exhausted. In this case, the target will get an RNR error.
To avoid this, we post receive WR, as soon as possible and not in a
batch. This increases the number of hits to the HCA, but also the common
implementation in most of Linux ULPs (e.g. NVMe-oF/RDMA). As a rule of
thumb, performance improvements and heuristics are being added to the RDMA
core layer or vendors low level drivers and it's about time to align iSER
as well.
Link: https://lore.kernel.org/r/20211215135721.3662-3-mgurtovoy@nvidia.com
Signed-off-by: Sergey Gorenko <sergeygo@nvidia.com>
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
No need for this dead code. This commit doesn't change any functionality
since one can still run "modprobe ib_iser pi_guard=<type>".
Link: https://lore.kernel.org/r/20211215135721.3662-2-mgurtovoy@nvidia.com
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
