| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
The transition_delay_us (struct cpufreq_policy) is currently defined
as:
Preferred average time interval between consecutive invocations of
the driver to set the frequency for this policy. To be set by the
scaling driver (0, which is the default, means no preference).
The transition_latency represents the amount of time necessary for a
CPU to change its frequency.
A PCCT table advertises mutliple values:
- pcc_nominal: Expected latency to process a command, in microseconds
- pcc_mpar: The maximum number of periodic requests that the subspace
channel can support, reported in commands per minute. 0 indicates no
limitation.
- pcc_mrtt: The minimum amount of time that OSPM must wait after the
completion of a command before issuing the next command,
in microseconds.
cppc_get_transition_latency() allows to get the max of them.
commit d4f3388afd48 ("cpufreq / CPPC: Set platform specific
transition_delay_us") allows to select transition_delay_us based on
the platform, and fallbacks to cppc_get_transition_latency()
otherwise.
If _CPC objects are not using PCC channels (no PPCT table), the
transition_delay_us is set to CPUFREQ_ETERNAL, leading to really long
periods between frequency updates (~4s).
If the desired_reg, where performance requests are written, is in
SystemMemory or SystemIo ACPI address space, there is no delay
in requests. So return 0 instead of CPUFREQ_ETERNAL, leading to
transition_delay_us being set to LATENCY_MULTIPLIER us (1000 us).
This patch also adds two macros to check the address spaces.
Signed-off-by: Pierre Gondois <[email protected]>
Reviewed-by: Sudeep Holla <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
The _OSC method allows the OS and firmware to communicate about
supported features/capabitlities. It also allows the OS to take
control of some features.
In ACPI 6.4, s6.2.11.2 Platform-Wide OSPM Capabilities, the CPPC
(resp. v2) bit should be set by the OS if it 'supports controlling
processor performance via the interfaces described in the _CPC
object'.
The OS supports CPPC and parses the _CPC object only if
CONFIG_ACPI_CPPC_LIB is set. Replace the x86 specific
boot_cpu_has(X86_FEATURE_HWP) dynamic check with an arch
generic CONFIG_ACPI_CPPC_LIB build-time check.
Note:
CONFIG_X86_INTEL_PSTATE selects CONFIG_ACPI_CPPC_LIB.
Signed-off-by: Pierre Gondois <[email protected]>
Reviewed-by: Sudeep Holla <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
ACPI 6.2 Section 6.2.11.2 'Platform-Wide OSPM Capabilities':
Starting with ACPI Specification 6.2, all _CPC registers can be in
PCC, System Memory, System IO, or Functional Fixed Hardware address
spaces. OSPM support for this more flexible register space scheme is
indicated by the “Flexible Address Space for CPPC Registers” _OSC bit
Otherwise (cf ACPI 6.1, s8.4.7.1.1.X), _CPC registers must be in:
- PCC or Functional Fixed Hardware address space if defined
- SystemMemory address space (NULL register) if not defined
Add the corresponding _OSC bit and check it when parsing _CPC objects.
Signed-off-by: Pierre Gondois <[email protected]>
Reviewed-by: Sudeep Holla <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
Module removal fails because cht_int33fe_typec_remove()
tries to access driver data that does not exist. Fixing by
assigning the data at the end of probe.
Fixes: 915623a80b5a ("platform/x86: intel_cht_int33fe: Switch to DMI modalias based loading")
Signed-off-by: Heikki Krogerus <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Reviewed-by: Hans de Goede <[email protected]>
Signed-off-by: Hans de Goede <[email protected]>
|
|
Previously, during suspend, intel_pch_thermal driver logs for every
cooling iteration, about the current PCH temperature and number of cooling
iterations that have been tried, like below
[ 100.955526] intel_pch_thermal 0000:00:14.2: CPU-PCH current temp [53C] higher than the threshold temp [50C], sleep 1 times for 100 ms duration
[ 101.064156] intel_pch_thermal 0000:00:14.2: CPU-PCH current temp [53C] higher than the threshold temp [50C], sleep 2 times for 100 ms duration
After changing the default delay_cnt to 600, in practice, it is common to
see tens of the above messages if the system is suspended when PCH
overheats. Thus, change this log message from dev_warn to dev_dbg because
it is only useful when we want to check the temperature trend.
At the same time, there is always a one-line message given by the driver
with the patch applied, with below four possibilities.
1. PCH is cool, no cooling delay needed
[ 1791.902853] intel_pch_thermal 0000:00:12.0: CPU-PCH is cool [48C]
2. PCH overheats and becomes cool after the cooling delays
[ 1475.511617] intel_pch_thermal 0000:00:12.0: CPU-PCH is cool [49C] after 30700 ms delay
3. PCH still overheats after the overall cooling timeout
[ 2250.157487] intel_pch_thermal 0000:00:12.0: CPU-PCH is hot [60C] after 60000 ms delay. S0ix might fail
4. PCH aborts cooling because of wakeup event detected during the delay
[ 1933.639509] intel_pch_thermal 0000:00:12.0: Wakeup event detected, abort cooling
Signed-off-by: Zhang Rui <[email protected]>
Tested-by: Sumeet Pawnikar <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
Commit ef63b043ac86 ("thermal: intel: pch: fix S0ix failure due to PCH
temperature above threshold") introduces delay loop mechanism that allows
PCH temperature to go down below threshold during suspend so it won't
block S0ix. And the default overall delay timeout is 1 second.
However, in practice, we found that the time it takes to cool the PCH down
below threshold highly depends on the initial PCH temperature when the
delay starts, as well as the ambient temperature.
And in some cases, the 1 second delay is not sufficient. As a result, the
system stays in a shallower power state like PCx instead of S0ix, and
drains the battery power, without user' notice.
To make sure S0ix is not blocked by the PCH overheating, we
1. expand the default overall timeout to 60 seconds.
2. make sure the temperature is below threshold rather than equal to it.
At the same time, as the cooling delay can be much longer and many wakeup
events (ACPI Power Button press, USB mouse move, etc) becomes valid in the
suspend_noirq phase, add detection of wakeup event so that the driver
does not delay blindly when the system suspend is likely to abort soon.
This patch may introduce longer suspend time, but only in the cases when
the system overheats and Linux used to enter a shallower S2idle state,
say, PCx instead of S0ix.
Signed-off-by: Zhang Rui <[email protected]>
Tested-by: Sumeet Pawnikar <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
Move the PCH Thermal driver suspend callback to suspend_noirq to do
cooling while the system is more quiescent.
Signed-off-by: Zhang Rui <[email protected]>
Tested-by: Sumeet Pawnikar <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
intel_pch_thermal driver needs a long delay to cool itself (60 seconds
in maximum) during suspend. When a wakeup event occures during the
delay, it is better for the intel_pch_thermal driver to detect this and
quit cooling because the suspend is likely to abort anyway.
Thus expose pm_wakeup_pending to modules so that intel_pch_thermal
driver can be aware of the wakeup events.
Signed-off-by: Zhang Rui <[email protected]>
Tested-by: Sumeet Pawnikar <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
intel_hid_dsm_fn_mask is a bit mask containing one bit for each function
index. Fix the function index check in intel_hid_evaluate_method
accordingly, which was missed in commit 97ab4516205e ("platform/x86:
intel-hid: fix _DSM function index handling").
Fixes: 97ab4516205e ("platform/x86: intel-hid: fix _DSM function index handling")
Cc: [email protected]
Signed-off-by: Michael Niewöhner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Reviewed-by: Hans de Goede <[email protected]>
Signed-off-by: Hans de Goede <[email protected]>
|
|
The intent is to use a genpd governor when there are some states that needs
to be managed. Although, the current code ends up to never assign a
governor, let's fix this.
Fixes: 6abf32f1d9c50 ("cpuidle: Add RISC-V SBI CPU idle driver")
Signed-off-by: Ulf Hansson <[email protected]>
Reviewed-by: Anup Patel <[email protected]>
Tested-by: Anup Patel <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
While factoring out the PM domain related code from PSCI domain driver into
a set of library functions, a regression when initializing the genpds got
introduced. More precisely, we fail to assign a genpd governor, so let's
fix this.
Fixes: 9d976d6721df ("cpuidle: Factor-out power domain related code from PSCI domain driver")
Signed-off-by: Ulf Hansson <[email protected]>
Reviewed-by: Anup Patel <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
Each devfreq governor specifies the supported governor event
such as GOV_START and GOV_STOP. When not-supported event is required,
just return non-error. But, commit ce9a0d88d97a ("PM / devfreq: Add
cpu based scaling support to passive governor") returned the error
value. So that return non-error value when not-supported event is required.
Fixes: ce9a0d88d97a ("PM / devfreq: Add cpu based scaling support to passive governor")
Reported-by: Marek Szyprowski <[email protected]>
Signed-off-by: Chanwoo Choi <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/thermal/linux
Pull thermal control material for 5.19-rc1 from Daniel Lezcano:
- Add the new k3 j72xx bangdap driver and the corresponding bindings (Keerthy)
- Fix the missing of_node_put() in the SC iMX driver at probe timer (Miaoqian Lin)
- Fix memory leak in __thermal_cooling_device_register() when device_register()
fails by calling thermal_cooling_device_destroy_sysfs() (Yang Yingliang)
- Add sc8180x and sc8280xp compatible string in the DT bindings and lMH support
for QCom tsens driver (Bjorn Andersson)
- Fix OTP Calibration Register values conforming to the documentation on RZ/G2L
and bindings documentation for RZ/G2UL (Biju Das)
- Fix type in kerneldoc description for __thermal_bind_params (Corentin Labbe)
- Remove unneeded semi colon in libthermal and tools thermal as reported by
cocci (Jiapeng Chong)
- Fix potential NULL dereference in sr_thermal_probe() on Broadcom platform
(Zheng Yongjun)
- Add thermal library and thermal tools to encapsulate the netlink into event
based callbacks (Daniel Lezcano)
- Add change mode ops for the thermal-of sensor (Manaf Meethalavalappu
Pallikunhi)
- Fix non negative value support by preventing the value to be clamp to zero
(Stefan Wahren)
- Add compatible string and DT bindings for MSM8960 tsens driver (Dmitry
Baryshkov)
- Add hwmon support for K3 driver (Massimiliano Minella)
- Refactor and add multiple generations support for QCom ADC driver (Jishnu
Prakash)
- Use platform_get_irq_optional() to get the interrupt on RCar driver and
document Document RZ/V2L bindings (Lad Prabhakar)
* tag 'thermal-v5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/thermal/linux: (28 commits)
thermal: k3_j72xx_bandgap: Add the bandgap driver support
dt-bindings: thermal: k3-j72xx: Add VTM bindings documentation
thermal/drivers/imx_sc_thermal: Fix refcount leak in imx_sc_thermal_probe
thermal/core: Fix memory leak in __thermal_cooling_device_register()
dt-bindings: thermal: tsens: Add sc8280xp compatible
dt-bindings: thermal: lmh: Add Qualcomm sc8180x compatible
thermal/drivers/qcom/lmh: Add sc8180x compatible
thermal/drivers/rz2gl: Fix OTP Calibration Register values
dt-bindings: thermal: rzg2l-thermal: Document RZ/G2UL bindings
thermal: thermal_of: fix typo on __thermal_bind_params
tools/thermal: remove unneeded semicolon
tools/lib/thermal: remove unneeded semicolon
thermal/drivers/broadcom: Fix potential NULL dereference in sr_thermal_probe
tools/thermal: Add thermal daemon skeleton
tools/thermal: Add a temperature capture tool
tools/thermal: Add util library
tools/lib/thermal: Add a thermal library
thermal/drivers/thermal_of: Add change_mode ops support for thermal_of sensor
thermal/drivers/bcm2711: Don't clamp temperature at zero
thermal/drivers/tsens: Add compat string for the qcom,msm8960
...
|
|
Follow the best practice for allocating a variable-sized structure.
Signed-off-by: Zhang Jianhua <[email protected]>
[ebiggers: adjusted commit message]
Signed-off-by: Eric Biggers <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux
Pull parisc architecture fixes from Helge Deller:
"We had two big outstanding issues after v5.18-rc6:
a) 32-bit kernels on 64-bit machines (e.g. on a C3700 which is able
to run 32- and 64-bit kernels) failed early in userspace.
b) 64-bit kernels on PA8800/PA8900 CPUs (e.g. in a C8000) showed
random userspace segfaults. We assumed that those problems were
caused by the tmpalias flushes.
Dave did a lot of testing and reorganization of the current flush code
and fixed the 32-bit cache flushing. For PA8800/PA8900 CPUs he
switched the code to flush using the virtual address of user and
kernel pages instead of using tmpalias flushes. The tmpalias flushes
don't seem to work reliable on such CPUs.
We tested the patches on a wide range machines (715/64, B160L, C3000,
C3700, C8000, rp3440) and they have been in for-next without any
conflicts.
Summary:
- Rewrite the cache flush code for PA8800/PA8900 CPUs to flush using
the virtual address of user and kernel pages instead of using
tmpalias flushes. Testing showed, that tmpalias flushes don't work
reliably on PA8800/PA8900 CPUs
- Fix flush code to allow 32-bit kernels to run on 64-bit capable
machines, e.g. a 32-bit kernel on C3700 machines"
* tag 'for-5.18/parisc-4' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
parisc: Fix patch code locking and flushing
parisc: Rewrite cache flush code for PA8800/PA8900
parisc: Disable debug code regarding cache flushes in handle_nadtlb_fault()
|
|
Pull ARM fixes from Russell King:
"Two further fixes for Spectre-BHB from Ard for Cortex A15 and to use
the wide branch instruction for Thumb2"
* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm:
ARM: 9197/1: spectre-bhb: fix loop8 sequence for Thumb2
ARM: 9196/1: spectre-bhb: enable for Cortex-A15
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl
Pull pin control fixes from Linus Walleij:
- Fix an altmode in the Ocelot driver
- Fix the IES control pins in the Mediatek MT8365 driver
- Sunxi (AMLogic) driver:
- Fix the UART2 function pin assignments
- Fix the signal name of the PA2 SPI pin
* tag 'pinctrl-v5.18-3' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl:
pinctrl: sunxi: f1c100s: Fix signal name comment for PA2 SPI pin
pinctrl: sunxi: fix f1c100s uart2 function
pinctrl: mediatek: mt8365: fix IES control pins
pinctrl: ocelot: Fix for lan966x alt mode
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from can, xfrm and netfilter subtrees.
Notably this reverts a recent TCP/DCCP netns-related change to address
a possible UaF.
Current release - regressions:
- tcp: revert "tcp/dccp: get rid of inet_twsk_purge()"
- xfrm: set dst dev to blackhole_netdev instead of loopback_dev in
ifdown
Previous releases - regressions:
- netfilter: flowtable: fix TCP flow teardown
- can: revert "can: m_can: pci: use custom bit timings for Elkhart
Lake"
- xfrm: check encryption module availability consistency
- eth: vmxnet3: fix possible use-after-free bugs in
vmxnet3_rq_alloc_rx_buf()
- eth: mlx5: initialize flow steering during driver probe
- eth: ice: fix crash when writing timestamp on RX rings
Previous releases - always broken:
- mptcp: fix checksum byte order
- eth: lan966x: fix assignment of the MAC address
- eth: mlx5: remove HW-GRO from reported features
- eth: ftgmac100: disable hardware checksum on AST2600"
* tag 'net-5.18-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (50 commits)
net: bridge: Clear offload_fwd_mark when passing frame up bridge interface.
ptp: ocp: change sysfs attr group handling
selftests: forwarding: fix missing backslash
netfilter: nf_tables: disable expression reduction infra
netfilter: flowtable: move dst_check to packet path
netfilter: flowtable: fix TCP flow teardown
net: ftgmac100: Disable hardware checksum on AST2600
igb: skip phy status check where unavailable
nfc: pn533: Fix buggy cleanup order
mptcp: Do TCP fallback on early DSS checksum failure
mptcp: fix checksum byte order
net: af_key: check encryption module availability consistency
net: af_key: add check for pfkey_broadcast in function pfkey_process
net/mlx5: Drain fw_reset when removing device
net/mlx5e: CT: Fix setting flow_source for smfs ct tuples
net/mlx5e: CT: Fix support for GRE tuples
net/mlx5e: Remove HW-GRO from reported features
net/mlx5e: Properly block HW GRO when XDP is enabled
net/mlx5e: Properly block LRO when XDP is enabled
net/mlx5e: Block rx-gro-hw feature in switchdev mode
...
|
|
There are currently two separate batched entropy implementations, for
u32 and u64, with nearly identical code, with the goal of avoiding
unaligned memory accesses and letting the buffers be used more
efficiently. Having to maintain these two functions independently is a
bit of a hassle though, considering that they always need to be kept in
sync.
This commit factors them out into a type-generic macro, so that the
expansion produces the same code as before, such that diffing the
assembly shows no differences. This will also make it easier in the
future to add u16 and u8 batches.
This was initially tested using an always_inline function and letting
gcc constant fold the type size in, but the code gen was less efficient,
and in general it was more verbose and harder to follow. So this patch
goes with the boring macro solution, similar to what's already done for
the _wait functions in random.h.
Cc: Dominik Brodowski <[email protected]>
Signed-off-by: Jason A. Donenfeld <[email protected]>
|
|
randomize_page is an mm function. It is documented like one. It contains
the history of one. It has the naming convention of one. It looks
just like another very similar function in mm, randomize_stack_top().
And it has always been maintained and updated by mm people. There is no
need for it to be in random.c. In the "which shape does not look like
the other ones" test, pointing to randomize_page() is correct.
So move randomize_page() into mm/util.c, right next to the similar
randomize_stack_top() function.
This commit contains no actual code changes.
Cc: Andrew Morton <[email protected]>
Signed-off-by: Jason A. Donenfeld <[email protected]>
|
|
The register_random_ready_notifier() notifier is somewhat complicated,
and was already recently rewritten to use notifier blocks. It is only
used now by one consumer in the kernel, vsprintf.c, for which the async
mechanism is really overly complex for what it actually needs. This
commit removes register_random_ready_notifier() and unregister_random_
ready_notifier(), because it just adds complication with little utility,
and changes vsprintf.c to just check on `!rng_is_initialized() &&
!rng_has_arch_random()`, which will eventually be true. Performance-
wise, that code was already using a static branch, so there's basically
no overhead at all to this change.
Cc: Steven Rostedt <[email protected]>
Cc: Sergey Senozhatsky <[email protected]>
Acked-by: Petr Mladek <[email protected]> # for vsprintf.c
Reviewed-by: Petr Mladek <[email protected]>
Signed-off-by: Jason A. Donenfeld <[email protected]>
|
|
The RNG incorporates RDRAND into its state at boot and every time it
reseeds, so there's no reason for callers to use it directly. The
hashing that the RNG does on it is preferable to using the bytes raw.
The only current use case of get_random_bytes_arch() is vsprintf's
siphash key for pointer hashing, which uses it to initialize the pointer
secret earlier than usual if RDRAND is available. In order to replace
this narrow use case, just expose whether RDRAND is mixed into the RNG,
with a new function called rng_has_arch_random(). With that taken care
of, there are no users of get_random_bytes_arch() left, so it can be
removed.
Later, if trust_cpu gets turned on by default (as most distros are
doing), this one use of rng_has_arch_random() can probably go away as
well.
Cc: Steven Rostedt <[email protected]>
Cc: Sergey Senozhatsky <[email protected]>
Acked-by: Petr Mladek <[email protected]> # for vsprintf.c
Signed-off-by: Jason A. Donenfeld <[email protected]>
|
|
Much of random.c is devoted to initializing the rng and accounting for
when a sufficient amount of entropy has been added. In a perfect world,
this would all happen during init, and so we could mark these functions
as __init. But in reality, this isn't the case: sometimes the rng only
finishes initializing some seconds after system init is finished.
For this reason, at the moment, a whole host of functions that are only
used relatively close to system init and then never again are intermixed
with functions that are used in hot code all the time. This creates more
cache misses than necessary.
In order to pack the hot code closer together, this commit moves the
initialization functions that can't be marked as __init into
.text.unlikely by way of the __cold attribute.
Of particular note is moving credit_init_bits() into a macro wrapper
that inlines the crng_ready() static branch check. This avoids a
function call to a nop+ret, and most notably prevents extra entropy
arithmetic from being computed in mix_interrupt_randomness().
Reviewed-by: Dominik Brodowski <[email protected]>
Signed-off-by: Jason A. Donenfeld <[email protected]>
|
|
The current code was a mix of "nbytes", "count", "size", "buffer", "in",
and so forth. Instead, let's clean this up by naming input parameters
"buf" (or "ubuf") and "len", so that you always understand that you're
reading this variety of function argument.
Signed-off-by: Jason A. Donenfeld <[email protected]>
|
|
Before these were returning signed values, but the API is intended to be
used with unsigned values.
Signed-off-by: Jason A. Donenfeld <[email protected]>
|
|
Accoriding to the kernel style guide, having `extern` on functions in
headers is old school and deprecated, and doesn't add anything. So remove
them from random.h, and tidy up the file a little bit too.
Signed-off-by: Jason A. Donenfeld <[email protected]>
|
|
Since crng_ready() is only false briefly during initialization and then
forever after becomes true, we don't need to evaluate it after, making
it a prime candidate for a static branch.
One complication, however, is that it changes state in a particular call
to credit_init_bits(), which might be made from atomic context, which
means we must kick off a workqueue to change the static key. Further
complicating things, credit_init_bits() may be called sufficiently early
on in system initialization such that system_wq is NULL.
Fortunately, there exists the nice function execute_in_process_context(),
which will immediately execute the function if !in_interrupt(), and
otherwise defer it to a workqueue. During early init, before workqueues
are available, in_interrupt() is always false, because interrupts
haven't even been enabled yet, which means the function in that case
executes immediately. Later on, after workqueues are available,
in_interrupt() might be true, but in that case, the work is queued in
system_wq and all goes well.
Cc: Theodore Ts'o <[email protected]>
Cc: Sultan Alsawaf <[email protected]>
Reviewed-by: Dominik Brodowski <[email protected]>
Signed-off-by: Jason A. Donenfeld <[email protected]>
|
|
It turned out that polling period for MMC_SEND_OP_COND, that currently is
set to 1ms, still isn't sufficient. In particular a Micron eMMC on a
Beaglebone platform, is reported to sometimes fail to initialize.
Additional test, shows that extending the period to 4ms is working fine, so
let's make that change.
Reported-by: Jean Rene Dawin <[email protected]>
Tested-by: Jean Rene Dawin <[email protected]>
Fixes: 1760fdb6fe9f (mmc: core: Restore (almost) the busy polling for MMC_SEND_OP_COND")
Fixes: 76bfc7ccc2fa ("mmc: core: adjust polling interval for CMD1")
Cc: [email protected]
Signed-off-by: Ulf Hansson <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
|
|
The function has only a single caller and two lines. Just remove it
since it is pointless and just harming readability.
Signed-off-by: Jan Kara <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>
|
|
We store struct bfq_io_cq pointer in rq->elv.priv[0] in bfq_init_rq().
Thus a call to icq_to_bic() in RQ_BIC() is wrong. Luckily it does no
harm currently because struct io_iq is the first one in struct
bfq_io_cq.
Signed-off-by: Jan Kara <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>
|
|
The code in bfq_check_waker() ignores wake up events from the current
waker. This makes it more likely we select a new tentative waker
although the current one is generating more wake up events. Treat
current waker the same way as any other process and allow it to reset
the waker detection logic.
Fixes: 71217df39dc6 ("block, bfq: make waker-queue detection more robust")
Signed-off-by: Jan Kara <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>
|
|
Currently we look for waker only if current queue has no requests. This
makes sense for bfq queues with a single process however for shared
queues when there is a larger number of processes the condition that
queue has no requests is difficult to meet because often at least one
process has some request in flight although all the others are waiting
for the waker to do the work and this harms throughput. Relax the "no
queued request for bfq queue" condition to "the current task has no
queued requests yet". For this, we also need to start tracking number of
requests in flight for each task.
This patch (together with the following one) restores the performance
for dbench with 128 clients that regressed with commit c65e6fd460b4
("bfq: Do not let waker requests skip proper accounting") because
this commit makes requests of wakers properly enter BFQ queues and thus
these queues become ineligible for the old waker detection logic.
Dbench results:
Vanilla 5.18-rc3 5.18-rc3 + revert 5.18-rc3 patched
Mean 1237.36 ( 0.00%) 950.16 * 23.21%* 988.35 * 20.12%*
Numbers are time to complete workload so lower is better.
Fixes: c65e6fd460b4 ("bfq: Do not let waker requests skip proper accounting")
Signed-off-by: Jan Kara <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>
|
|
When running as dom0less guest (HVM domain on ARM) the xenstore event
channel is available at domain creation but the shared xenstore
interface page only becomes available later on.
In that case, wait for a notification on the xenstore event channel,
then complete the xenstore initialization later, when the shared page
is actually available.
The xenstore page has few extra field. Add them to the shared struct.
One of the field is "connection", when the connection is ready, it is
zero. If the connection is not-zero, wait for a notification.
Signed-off-by: Luca Miccio <[email protected]>
Signed-off-by: Stefano Stabellini <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Juergen Gross <[email protected]>
|
|
Sync the xs_wire.h header file in Linux with the one in Xen.
Signed-off-by: Stefano Stabellini <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Juergen Gross <[email protected]>
|
|
Since commit 4d65adfcd119 ("x86: xen: insn: Decode Xen and KVM
emulate-prefix signature"), objtool is able to correctly parse the
prefixed instruction in xen_cpuid and emit correct orc unwind
information. Hence, marking the function as STACKFRAME_NON_STANDARD is
no longer needed.
This commit is basically a revert of commit 983bb6d254c7 ("x86/xen: Mark
xen_cpuid() stack frame as non-standard").
Signed-off-by: Maximilian Heyne <[email protected]>
Reviewed-by: Juergen Gross <[email protected]>
CC: Josh Poimboeuf <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Juergen Gross <[email protected]>
|
|
and feature_persistent
SeongJae is currently listed as a contact point for some blk{back,front}
features, but he will not work for XEN for a while. This commit
therefore updates the contact point to his colleague, Maximilian, who is
understanding the context and actively working with the features now.
Signed-off-by: SeongJae Park <[email protected]>
Signed-off-by: Maximilian Heyne <[email protected]>
Acked-by: Roger Pau Monné <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Juergen Gross <[email protected]>
|
|
Commit 505a666ee3fc ("writeback: plug writeback in wb_writeback() and
writeback_inodes_wb()") has us holding a plug during wb_writeback, which
may cause a potential ABBA dead lock:
wb_writeback fat_file_fsync
blk_start_plug(&plug)
for (;;) {
iter i-1: some reqs have been added into plug->mq_list // LOCK A
iter i:
progress = __writeback_inodes_wb(wb, work)
. writeback_sb_inodes // fat's bdev
. __writeback_single_inode
. . generic_writepages
. . __block_write_full_page
. . . . __generic_file_fsync
. . . . sync_inode_metadata
. . . . writeback_single_inode
. . . . __writeback_single_inode
. . . . fat_write_inode
. . . . __fat_write_inode
. . . . sync_dirty_buffer // fat's bdev
. . . . lock_buffer(bh) // LOCK B
. . . . submit_bh
. . . . blk_mq_get_tag // LOCK A
. . . trylock_buffer(bh) // LOCK B
. . . redirty_page_for_writepage
. . . wbc->pages_skipped++
. . --wbc->nr_to_write
. wrote += write_chunk - wbc.nr_to_write // wrote > 0
. requeue_inode
. redirty_tail_locked
if (progress) // progress > 0
continue;
iter i+1:
queue_io
// similar process with iter i, infinite for-loop !
}
blk_finish_plug(&plug) // flush plug won't be called
Above process triggers a hungtask like:
[ 399.044861] INFO: task bb:2607 blocked for more than 30 seconds.
[ 399.046824] Not tainted 5.18.0-rc1-00005-gefae4d9eb6a2-dirty
[ 399.051539] task:bb state:D stack: 0 pid: 2607 ppid:
2426 flags:0x00004000
[ 399.051556] Call Trace:
[ 399.051570] __schedule+0x480/0x1050
[ 399.051592] schedule+0x92/0x1a0
[ 399.051602] io_schedule+0x22/0x50
[ 399.051613] blk_mq_get_tag+0x1d3/0x3c0
[ 399.051640] __blk_mq_alloc_requests+0x21d/0x3f0
[ 399.051657] blk_mq_submit_bio+0x68d/0xca0
[ 399.051674] __submit_bio+0x1b5/0x2d0
[ 399.051708] submit_bio_noacct+0x34e/0x720
[ 399.051718] submit_bio+0x3b/0x150
[ 399.051725] submit_bh_wbc+0x161/0x230
[ 399.051734] __sync_dirty_buffer+0xd1/0x420
[ 399.051744] sync_dirty_buffer+0x17/0x20
[ 399.051750] __fat_write_inode+0x289/0x310
[ 399.051766] fat_write_inode+0x2a/0xa0
[ 399.051783] __writeback_single_inode+0x53c/0x6f0
[ 399.051795] writeback_single_inode+0x145/0x200
[ 399.051803] sync_inode_metadata+0x45/0x70
[ 399.051856] __generic_file_fsync+0xa3/0x150
[ 399.051880] fat_file_fsync+0x1d/0x80
[ 399.051895] vfs_fsync_range+0x40/0xb0
[ 399.051929] __x64_sys_fsync+0x18/0x30
In my test, 'need_resched()' (which is imported by 590dca3a71 "fs-writeback:
unplug before cond_resched in writeback_sb_inodes") in function
'writeback_sb_inodes()' seldom comes true, unless cond_resched() is deleted
from write_cache_pages().
Fix it by correcting wrote number according number of skipped pages
in writeback_sb_inodes().
Goto Link to find a reproducer.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=215837
Cc: [email protected] # v4.3
Signed-off-by: Zhihao Cheng <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>
|
|
There is no external user of xenbus_grant_ring() left, so merge it into
the only caller xenbus_setup_ring().
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Oleksandr Tyshchenko <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>
|
|
Simplify sndfront's ring creation and removal via xenbus_setup_ring()
and xenbus_teardown_ring().
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Oleksandr Tyshchenko <[email protected]>
Tested-by: Oleksandr Tyshchenko <[email protected]> # Arm64 only
Signed-off-by: Juergen Gross <[email protected]>
|
|
Simplify xen-hcd's ring creation and removal via xenbus_setup_ring()
and xenbus_teardown_ring().
Signed-off-by: Juergen Gross <[email protected]>
Acked-by: Greg Kroah-Hartman <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>
|
|
Simplify scsifront's ring creation and removal via xenbus_setup_ring()
and xenbus_teardown_ring().
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>
|
|
Simplify pcifront's shared page creation and removal via
xenbus_setup_ring() and xenbus_teardown_ring().
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>
|
|
Simplify drmfront's ring creation and removal via xenbus_setup_ring()
and xenbus_teardown_ring().
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Oleksandr Tyshchenko <[email protected]>
Tested-by: Oleksandr Tyshchenko <[email protected]> # Arm64 only
Signed-off-by: Juergen Gross <[email protected]>
|
|
Simplify tpmfront's ring creation and removal via xenbus_setup_ring()
and xenbus_teardown_ring(), which are provided exactly for the use
pattern as seen in this driver.
Signed-off-by: Juergen Gross <[email protected]>
|
|
Simplify netfront's ring creation and removal via xenbus_setup_ring()
and xenbus_teardown_ring().
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>
|
|
Simplify blkfront's ring creation and removal via xenbus_setup_ring()
and xenbus_teardown_ring().
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Acked-by: Roger Pau Monné <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>
|
|
Most PV device frontends share very similar code for setting up shared
ring buffers:
- allocate page(s)
- init the ring admin data
- give the backend access to the ring via grants
Tearing down the ring requires similar actions in all frontends again:
- remove grants
- free the page(s)
Provide service functions xenbus_setup_ring() and xenbus_teardown_ring()
for that purpose.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>
|
|
Update include/xen/interface/io/ring.h to its newest version.
Switch the two improper use cases of RING_HAS_UNCONSUMED_RESPONSES() to
XEN_RING_NR_UNCONSUMED_RESPONSES() in order to avoid the nasty
XEN_RING_HAS_UNCONSUMED_IS_BOOL #define.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>
|
|
Instead of using a private macro for an invalid grant reference use
the common one.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Reviewed-by: Oleksandr Tyshchenko <[email protected]>
Tested-by: Oleksandr Tyshchenko <[email protected]> # Arm64 only
Signed-off-by: Juergen Gross <[email protected]>
|
|
Instead of using a private macro for an invalid grant reference use
the common one.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: Boris Ostrovsky <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>
|