Evan Green [Mon, 1 Jul 2019 17:30:30 +0000 (10:30 -0700)]
ALSA: hda: Fix widget_mutex incomplete protection
The widget_mutex was introduced to serialize callers to
hda_widget_sysfs_{re}init. However, its protection of the sysfs widget array
is incomplete. For example, it is acquired around the call to
hda_widget_sysfs_reinit(), which actually creates the new array, but isn't
still acquired when codec->num_nodes and codec->start_nid is updated. So
the lock ensures one thread sets up the new array at a time, but doesn't
ensure which thread's value will end up in codec->num_nodes. If a larger
num_nodes wins but a smaller array was set up, the next call to
refresh_widgets() will touch free memory as it iterates over codec->num_nodes
that aren't there.
The widget_lock really protects both the tree as well as codec->num_nodes,
start_nid, and end_nid, so make sure it's held across that update. It should
also be held during snd_hdac_get_sub_nodes(), so that a very old read from that
function doesn't end up clobbering a later update.
Fixes: ed180abba7f1 ("ALSA: hda: Fix race between creating and refreshing sysfs entries") Signed-off-by: Evan Green <[email protected]> Signed-off-by: Takashi Iwai <[email protected]>
ALSA: firewire-lib/fireworks: fix miss detection of received MIDI messages
In IEC 61883-6, 8 MIDI data streams are multiplexed into single
MIDI conformant data channel. The index of stream is calculated by
modulo 8 of the value of data block counter.
In fireworks, the value of data block counter in CIP header has a quirk
with firmware version v5.0.0, v5.7.3 and v5.8.0. This brings ALSA
IEC 61883-1/6 packet streaming engine to miss detection of MIDI
messages.
This commit fixes the miss detection to modify the value of data block
counter for the modulo calculation.
For maintainers, this bug exists since a commit 18f5ed365d3f ("ALSA:
fireworks/firewire-lib: add support for recent firmware quirk") in Linux
kernel v4.2. There're many changes since the commit. This fix can be
backported to Linux kernel v4.4 or later. I tagged a base commit to the
backport for your convenience.
Besides, my work for Linux kernel v5.3 brings heavy code refactoring and
some structure members are renamed in 'sound/firewire/amdtp-stream.h'.
The content of this patch brings conflict when merging -rc tree with
this patch and the latest tree. I request maintainers to solve the
conflict to replace 'tx_first_dbc' with 'ctx_data.tx.first_dbc'.
Colin Ian King [Fri, 28 Jun 2019 09:54:29 +0000 (10:54 +0100)]
ALSA: seq: fix incorrect order of dest_client/dest_ports arguments
There are two occurrances of a call to snd_seq_oss_fill_addr where
the dest_client and dest_port arguments are in the wrong order. Fix
this by swapping them around.
Colin Ian King [Thu, 27 Jun 2019 16:43:08 +0000 (17:43 +0100)]
ALSA: usb-audio: fix sign unintended sign extension on left shifts
There are a couple of left shifts of unsigned 8 bit values that
first get promoted to signed ints and hence get sign extended
on the shift if the top bit of the 8 bit values are set. Fix
this by casting the 8 bit values to unsigned ints to stop the
unintentional sign extension.
Richard Sailer [Wed, 19 Jun 2019 11:33:11 +0000 (13:33 +0200)]
ALSA: hda/realtek: Add quirks for several Clevo notebook barebones
This adds 4 SND_PCI_QUIRK(...) lines for several barebone models of the ODM
Clevo. The model names are written in regex syntax to describe/match all clevo
models that are similar enough and use the same PCI SSID that this fixup works
for them.
Additionally the lines regarding SSID 0x96e1 and 0x97e1 didn't fix audio for the
all our Clevo notebooks using these SSIDs (models Clevo P960* and P970*) since
ALC1220_FIXP_CLEVO_PB51ED_PINS swapped pins that are not necesarry to be
swapped. This patch initiates ALC1220_FIXUP_CLEVO_P950 instead for these model
and fixes the audio.
Takashi Iwai [Thu, 13 Jun 2019 15:33:34 +0000 (17:33 +0200)]
Merge tag 'asoc-fix-v5.2-rc4' of https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus
ASoC: Fixes for v5.2
There's an awful lot of fixes here, almost all for the newly introduced
SoF DSP drivers (including a few things it turned up in shared code).
This is a large and complex piece of code so it's not surprising that
there have been quite a few issues here, fortunately things seem to have
mostly calmed down now. Otherwise there's just a smattering of small fixes.
ALSA: ice1712: Check correct return value to snd_i2c_sendbytes (EWS/DMX 6Fire)
Check for exact and correct return value to snd_i2c_sendbytes
call for EWS/DMX 6Fire (snd_ice1712).
Fixes a systemic error on every boot starting from kernel 5.1
onwards to snd_ice1712 driver ("cannot send pca") on Terratec
EWS/DMX 6Fire PCI soundcards.
Check for exact and correct return value to snd_i2c_sendbytes
call for EWS/DMX 6Fire (snd_ice1712).
Fixes a systemic error on every boot to snd_ice1712 driver
("cannot send pca") on Terratec EWS/DMX 6Fire PCI soundcards.
Stanton SCS.1m can transfer isochronous packet with Multi Bit Linear
Audio data channels, therefore it allows software to capture PCM
substream. However, ALSA oxfw driver doesn't.
This commit changes the driver to add one PCM substream for capture
direction.
ASoC: core: Fix deadlock in snd_soc_instantiate_card()
Move the client_mutex lock to snd_soc_unbind_card() before
removing link components. This prevents the deadlock
in the error path in snd_soc_instantiate_card().
Fixes: 34ac3c3eb8 (ASoC: core: lock client_mutex while removing
link components) Reported-by: kernelci.org bot <[email protected]> Signed-off-by: Ranjani Sridharan <[email protected]> Signed-off-by: Mark Brown <[email protected]>
SoC: rt274: Fix internal jack assignment in set_jack callback
When we call snd_soc_component_set_jack(component, NULL, NULL) we should
set rt274->jack to passed jack, so when interrupt is triggered it calls
snd_soc_jack_report(rt274->jack, ...) with proper value.
This fixes problem in machine where in register, we call
snd_soc_register(component, &headset, NULL), which just calls
rt274_mic_detect via callback.
Now when machine driver is removed "headset" will be gone, so we
need to tell codec driver that it's gone with:
snd_soc_register(component, NULL, NULL), but we also need to be able
to handle NULL jack argument here gracefully.
If we don't set it to NULL, next time the rt274_irq runs it will call
snd_soc_jack_report with first argument being invalid pointer and there
will be Oops.
ALSA: hdac: fix memory release for SST and SOF drivers
During the integration of HDaudio support, we changed the way in which
we get hdev in snd_hdac_ext_bus_device_init() to use one preallocated
with devm_kzalloc(), however it still left kfree(hdev) in
snd_hdac_ext_bus_device_exit(). It leads to oopses when trying to
rmmod and modprobe. Fix it, by just removing kfree call.
SOF also uses some of the snd_hdac_ functions for HDAudio support but
allocated the memory with kzalloc. A matching fix is provided
separately to align all users of the snd_hdac_ library.
Fixes: 6298542fa33b ("ALSA: hdac: remove memory allocation from snd_hdac_ext_bus_device_init") Reviewed-by: Takashi Iwai <[email protected]> Signed-off-by: Amadeusz Sławiński <[email protected]> Signed-off-by: Pierre-Louis Bossart <[email protected]> Signed-off-by: Mark Brown <[email protected]>
Tzung-Bi Shih [Tue, 4 Jun 2019 03:31:02 +0000 (11:31 +0800)]
ASoC: core: move DAI pre-links initiation to snd_soc_instantiate_card
Kernel crashes when an ASoC component rebinding.
The dai_link->platforms has been reset to NULL by soc_cleanup_platform()
in soc_cleanup_card_resources() when un-registering component. However,
it has no chance to re-allocate the dai_link->platforms when registering
the component again.
Move the DAI pre-links initiation from snd_soc_register_card() to
snd_soc_instantiate_card() to make sure all DAI pre-links get initiated
when component rebinding.
As an example, by using the following commands:
- echo -n max98357a > /sys/bus/platform/drivers/max98357a/unbind
- echo -n max98357a > /sys/bus/platform/drivers/max98357a/bind
Got the error message:
"Unable to handle kernel NULL pointer dereference at virtual address".
The call trace:
snd_soc_is_matching_component+0x30/0x6c
soc_bind_dai_link+0x16c/0x240
snd_soc_bind_card+0x1e4/0xb10
snd_soc_add_component+0x270/0x300
snd_soc_register_component+0x54/0x6c
ASoC: Intel: cht_bsw_rt5672: fix kernel oops with platform_name override
The platform override code uses devm_ functions to allocate memory for
the new name but the card device is not initialized. Fix by moving the
init earlier.
Fixes: f403906da05cd ("ASoC: Intel: cht_bsw_rt5672: platform name fixup support") Signed-off-by: Pierre-Louis Bossart <[email protected]> Signed-off-by: Mark Brown <[email protected]>
ASoC: Intel: cht_bsw_nau8824: fix kernel oops with platform_name override
The platform override code uses devm_ functions to allocate memory for
the new name but the card device is not initialized. Fix by moving the
init earlier.
Fixes: 4506db8043341 ("ASoC: Intel: cht_bsw_nau8824: platform name fixup support") Signed-off-by: Pierre-Louis Bossart <[email protected]> Signed-off-by: Mark Brown <[email protected]>
ASoC: Intel: bytcht_es8316: fix kernel oops with platform_name override
The platform override code uses devm_ functions to allocate memory for
the new name but the card device is not initialized. Fix by moving the
init earlier.
Fixes: e4bc6b1195f64 ("ASoC: Intel: bytcht_es8316: platform name fixup support") Signed-off-by: Pierre-Louis Bossart <[email protected]> Signed-off-by: Mark Brown <[email protected]>
ASoC: Intel: cht_bsw_max98090: fix kernel oops with platform_name override
The platform override code uses devm_ functions to allocate memory for
the new name but the card device is not initialized. Fix by moving the
init earlier.
Fixes: 7e7e24d7c7ff0 ("ASoC: Intel: cht_bsw_max98090_ti: platform name fixup support") Signed-off-by: Pierre-Louis Bossart <[email protected]> Signed-off-by: Mark Brown <[email protected]>
Marcus Cooper [Mon, 3 Jun 2019 17:47:28 +0000 (19:47 +0200)]
ASoC: sun4i-i2s: Add offset to RX channel select
Whilst testing the capture functionality of the i2s on the newer
SoCs it was noticed that the recording was somewhat distorted.
This was due to the offset not being set correctly on the receiver
side.
Yu-Hsuan Hsu [Tue, 4 Jun 2019 10:49:09 +0000 (18:49 +0800)]
ASoC: max98090: remove 24-bit format support if RJ is 0
The supported formats are S16_LE and S24_LE now. However, by datasheet
of max98090, S24_LE is only supported when it is in the right justified
mode. We should remove 24-bit format if it is not in that mode to avoid
triggering error.
YueHaibing [Sat, 1 Jun 2019 08:51:44 +0000 (16:51 +0800)]
ASoC: da7219: Fix build error without CONFIG_I2C
Fix gcc build error while CONFIG_I2C is not set
sound/soc/codecs/da7219.c:2640:1: warning: data definition has no type or storage class
module_i2c_driver(da7219_i2c_driver);
^~~~~~~~~~~~~~~~~
sound/soc/codecs/da7219.c:2640:1: error: type defaults to int in declaration of module_i2c_driver [-Werror=implicit-int]
sound/soc/codecs/da7219.c:2640:1: warning: parameter names (without types) in function declaration
sound/soc/codecs/da7219.c:2629:26: warning: da7219_i2c_driver defined but not used [-Wunused-variable]
sound/soc/sof/intel/hda.o: In function `hda_dsp_probe':
hda.c:(.text+0x79c): undefined reference to `pci_ioremap_bar'
hda.c:(.text+0x79c): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `pci_ioremap_bar'
hda.c:(.text+0x7c4): undefined reference to `pci_ioremap_bar'
hda.c:(.text+0x7c4): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `pci_ioremap_bar'
Kai Vehmanen [Mon, 3 Jun 2019 16:18:15 +0000 (11:18 -0500)]
ASoC: SOF: fix DSP oops definitions in FW ABI
The definitions for DSP oops structures were not aligned
correctly to current FW ABI version 3.6.0, leading to
invalid data being printed out to debug logs. Fix the structs
and update related platform code accordingly.
ASoC: hda: fix unbalanced codec dev refcount for HDA_DEV_ASOC
HDA_DEV_ASOC type codec device refcounts are managed differently
from HDA_DEV_LEGACY devices. The refcount is released explicitly
in snd_hdac_ext_bus_device_remove() for ASOC type devices.
So, remove the put_device() call in snd_hda_codec_dev_free()
for such devices to make the refcount balanced. This will prevent
the NULL pointer exception when the codec driver is released
after the card is freed.
We had a couple of misses with ABI changes, e.g. for Xtensa oops
information and the integration of sound trigger, before we set-up a
formal process to track evolutions.
With this patch, the SOF kernel patches are officially aligned with
the firmware 3.6 level. Changing this level has no impact on existing
users and is fully backwards-compatible.
We missed these two definitions for GDB support and component
notifications, they are defined for the SOF firmware. Since they are
not used by the kernel so far, we can still add them without any ABI
change.
Kovács Tamás [Fri, 31 May 2019 17:22:26 +0000 (19:22 +0200)]
ASoC: Intel: Baytrail: add quirk for Aegex 10 (RU2) tablet
This tablet has an incorrect acpi identifier just like
Thinkpad10 tablet, which is why it is trying to load the RT5640 driver
instead of the RT5762 driver. The RT5640 driver, on the other hand, checks
the hardware ID, so no driver are loaded during boot. This fix resolves to
load the RT5672 driver on this tablet during boot. It also provides the
correct IO configuration, like the jack detect mode 3, for 1.8V pullup. I
would like to thank Pierre-Louis Bossart for helping with this patch.
Allwinner DAC seems to have a delay in the Speaker audio routing. When
playing a sound for the first time, the sound gets chopped. On a second
play the sound is played correctly. After some time (~5s) the issue gets
back.
This commit seems to be fixing the same issue as bf14da7 but
for another codepath.
This is the DTS that was used to debug the problem.
ALSA: fireface: Use ULL suffixes for 64-bit constants
With gcc 4.1:
sound/firewire/fireface/ff-protocol-latter.c: In function ‘latter_switch_fetching_mode’:
sound/firewire/fireface/ff-protocol-latter.c:97: warning: integer constant is too large for ‘long’ type
sound/firewire/fireface/ff-protocol-latter.c: In function ‘latter_begin_session’:
sound/firewire/fireface/ff-protocol-latter.c:170: warning: integer constant is too large for ‘long’ type
sound/firewire/fireface/ff-protocol-latter.c:197: warning: integer constant is too large for ‘long’ type
sound/firewire/fireface/ff-protocol-latter.c:205: warning: integer constant is too large for ‘long’ type
sound/firewire/fireface/ff-protocol-latter.c: In function ‘latter_finish_session’:
sound/firewire/fireface/ff-protocol-latter.c:214: warning: integer constant is too large for ‘long’ type
Fix this by adding the missing "ULL" suffixes.
Add the same suffix to the last constant, to maintain consistency.
Hui Wang [Wed, 29 May 2019 04:41:38 +0000 (12:41 +0800)]
ALSA: hda/realtek - Improve the headset mic for Acer Aspire laptops
We met another Acer Aspire laptop which has the problem on the
headset-mic, the Pin 0x19 is not set the corret configuration for a
mic and the pin presence can't be detected too after plugging a
headset. Kailang suggested that we should set the coeff to enable the
mic and apply the ALC269_FIXUP_LIFEBOOK_EXTMIC. After doing that,
both headset-mic presence and headset-mic work well.
The existing ALC255_FIXUP_ACER_MIC_NO_PRESENCE set the headset-mic
jack to be a phantom jack. Now since the jack can support presence
unsol event, let us imporve it to set the jack to be a normal jack.
Zhu Yingjiang [Fri, 24 May 2019 19:09:24 +0000 (14:09 -0500)]
ASoC: SOF: Intel: hda: fix the hda init chip
re-write hda_init_caps and remove the HDA reset, clean HDA
streams and clear interrupt steps in hda_dsp_probe so the
HDA init steps will not be called twice if the
CONFIG_SND_SOC_SOF_HDA is true.
ASoC: SOF: ipc: fix a race, leading to IPC timeouts
Currently on all supported platforms the IPC IRQ thread first signals
the sender when an IPC response is received from the DSP, then unmasks
the IPC interrupt. Those actions are performed without holding any
locks, so the thread can be interrupted between them. IPC timeouts
have been observed in such scenarios: if the sender is woken up and it
proceeds with sending the next message without unmasking the IPC
interrupt, it can miss the next response. This patch takes a spin-lock
to prevent the IRQ thread from being preempted at that point. It also
makes sure, that the next IPC transmission by the host cannot take
place before the IRQ thread has finished updating all the required IPC
registers.
Fixes: 53e0c72d98b ("ASoC: SOF: Add support for IPC IO between DSP and Host") Reviewed-by: Takashi Iwai <[email protected]> Signed-off-by: Guennadi Liakhovetski <[email protected]> Signed-off-by: Pierre-Louis Bossart <[email protected]> Signed-off-by: Mark Brown <[email protected]>
Keyon Jie [Fri, 24 May 2019 19:09:22 +0000 (14:09 -0500)]
ASoC: SOF: control: correct the copy size for bytes kcontrol put
The size for the bytes kcontrol should include the abi header, that is,
data->size + sizeof(*data), it is also aligned with get method after
this change.
ASoC: SOF: pcm: remove warning - initialize workqueue on open
If the SOF hw_params() fail, typically with an IPC error thrown by the
firmware, the period_elapsed workqueue is not initialized, but we
still cancel it in hw_free(), which results in a kernel warning.
Move the initialization to the .open callback. Tested on Broadwell
(Samus) and IceLake.
Fixes: e2803e610ae ("ASoC: SOF: PCM: add period_elapsed work to fix
race condition in interrupt context")
GitHub issue: https://github.com/thesofproject/linux/issues/932 Reviewed-by: Takashi Iwai <[email protected]> Signed-off-by: Pierre-Louis Bossart <[email protected]> Signed-off-by: Mark Brown <[email protected]>
Libin Yang [Fri, 24 May 2019 19:09:20 +0000 (14:09 -0500)]
ASoC: SOF: pcm: clear hw_params_upon_resume flag correctly
sof_pcm_hw_params() can only be called once to setup the FW hw_params.
So after calling sof_pcm_hw_params(), hw_params_upon_resume flag must
be cleared to avoid multiple invoking sof_pcm_hw_params() by prepare.
For example, after resume, there is an xrun happened, prepare() will
be called. As the hw_params_upon_resume flag is not cleared,
sof_pcm_hw_params() will be called and this will cause IPC timeout.
ASoC: SOF: core: fix error handling with the probe workqueue
In some configurations, it's a requirement to split the probe in two,
with a second part handled in a workqueue (e.g. for HDMI support
which depends on the DRM modules).
SOF already handles these configurations but the error flow is
incorrect. When an error occurs in the workqueue, the probe has
technically already completed. If we release the resources on errors,
this generates kernel oops/use-after-free when the resources are
released a second time on module removal.
GitHub issue: https://github.com/thesofproject/linux/issues/945 Fixes: c16211d6226 ("ASoC: SOF: Add Sound Open Firmware driver core") Reviewed-by: Takashi Iwai <[email protected]> Signed-off-by: Pierre-Louis Bossart <[email protected]> Signed-off-by: Mark Brown <[email protected]>
ASoC: SOF: core: remove DSP after unregistering machine driver
snd_sof_remove() disables the DSP and unmaps the DSP BAR.
Removing topology after disabling the DSP results in a
kernel panic while unloading the pipeline widget. This is
because pipeline widget unload attempts to power down
the core it is scheduled on by accessing the DSP registers.
So, the suggested fix here is to unregister the machine driver
first to remove the topology and then disable the DSP
to avoid the situation described above.
Note that the kernel panic only happens in cases where the
HDaudio link is not managed by the hdac library,
e.g. no codec or when HDMI is not supported.
When the hdac library is used, snd_sof_remove() calls
snd_hdac_ext_bus_device_remove() to remove the codec which
unregisters the component driver thereby also removing the
topology before the DSP is disabled.
Takashi Iwai [Tue, 28 May 2019 06:39:44 +0000 (08:39 +0200)]
ALSA: line6: Assure canceling delayed work at disconnection
The current code performs the cancel of a delayed work at the late
stage of disconnection procedure, which may lead to the access to the
already cleared state.
This patch assures to call cancel_delayed_work_sync() at the beginning
of the disconnection procedure for avoiding that race. The delayed
work object is now assigned in the common line6 object instead of its
derivative, so that we can call cancel_delayed_work_sync().
Along with the change, the startup function is called via the new
callback instead. This will make it easier to port other LINE6
drivers to use the delayed work for startup in later patches.
Bard Liao [Sun, 26 May 2019 16:58:32 +0000 (00:58 +0800)]
ALSA: hda - Force polling mode on CNL for fixing codec communication
We observed the same issue as reported by commit a8d7bde23e7130686b7662
("ALSA: hda - Force polling mode on CFL for fixing codec communication")
We don't have a better solution. So apply the same workaround to CNL.
ASoC: core: lock client_mutex while removing link components
Removing link components results in topology unloading. So,
acquire the client_mutex before removing components in
soc_remove_link_components. This will prevent the lockdep warning
seen when dai links are removed during topology removal.
Jon Hunter [Fri, 24 May 2019 08:54:04 +0000 (09:54 +0100)]
ASoC: simple-card: Restore original configuration of DAI format
Revert commit 069d037aea98 ("ASoC: simple-card: Fix configuration of
DAI format"). During further review, it turns out that the actual issue
was caused by an incorrectly formatted device-tree node describing the
soundcard.
The following is incorrect because the simple-audio-card
'bitclock-master' and 'frame-master' properties should not reference the
actual codec phandle ...
Kailang Yang [Thu, 23 May 2019 06:43:04 +0000 (14:43 +0800)]
ALSA: hda/realtek - Set default power save node to 0
I measured power consumption between power_save_node=1 and power_save_node=0.
It's almost the same.
Codec will enter to runtime suspend and suspend.
That pin also will enter to D3. Don't need to enter to D3 by single pin.
So, Disable power_save_node as default. It will avoid more issues.
Windows Driver also has not this option at runtime PM.
Kailang Yang [Thu, 16 May 2019 08:10:44 +0000 (16:10 +0800)]
ALSA: hda/realtek - Check headset type by unplug and resume
When system enable HDA power save mode.
This issue will happen on new platform which DMIC connect to PCH.
In Dell headset mode, it will recheck during runtime resume when
headset was plugged.
This patch will move check headset type on unplug and system resume.
Jon Hunter [Thu, 16 May 2019 17:51:26 +0000 (18:51 +0100)]
ASoC: simple-card: Fix configuration of DAI format
When configuring a codec to be both bit-clock and frame-master, it was
found that the codec was always configured as bit-clock and frame-slave.
Looking at the simple_dai_link_of() function there appears to be two
problems with the configuration of the DAI format, which are ...
1. The function asoc_simple_parse_daifmt() is called before the function
asoc_simple_parse_codec() and this means that the device-tree node
for the codec has not been parsed yet, which is needed by the
function asoc_simple_parse_daifmt() to determine who is the codec.
2. The phandle passed to asoc_simple_parse_daifmt() is the phandle to
the 'codec' node and not the phandle of the actual codec defined by
the 'sound-dai' property under the 'codec' node.
Fix the above by moving the call to asoc_simple_parse_daifmt() after the
the call to asoc_simple_parse_codec() and pass the phandle for the codec
to asoc_simple_parse_daifmt().
Curtis Malainey [Fri, 17 May 2019 01:43:40 +0000 (18:43 -0700)]
ASoC: rt5677-spi: Handle over reading when flipping bytes
There is a case when a we want to read a large number of bytes that
require a burst but is not a multiple of the word size (8). When this
happens rt5677_spi_reverse will run off the end of the buffer. The
solution is to tell spi_reverse the actual size of the destination and
stop if we reach it even if we have data left that we read.
Linus Torvalds [Sun, 19 May 2019 22:22:03 +0000 (15:22 -0700)]
Merge tag 'upstream-5.2-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs
Pull UBIFS fixes from Richard Weinberger:
- build errors wrt xattrs
- mismerge which lead to a wrong Kconfig ifdef
- missing endianness conversion
* tag 'upstream-5.2-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs:
ubifs: Convert xattr inum to host order
ubifs: Use correct config name for encryption
ubifs: Fix build error without CONFIG_UBIFS_FS_XATTR
Linus Torvalds [Sun, 19 May 2019 19:15:32 +0000 (12:15 -0700)]
Merge branch 'akpm' (patches from Andrew)
Merge yet more updates from Andrew Morton:
"A few final bits:
- large changes to vmalloc, yielding large performance benefits
- tweak the console-flush-on-panic code
- a few fixes"
* emailed patches from Andrew Morton <[email protected]>:
panic: add an option to replay all the printk message in buffer
initramfs: don't free a non-existent initrd
fs/writeback.c: use rcu_barrier() to wait for inflight wb switches going into workqueue when umount
mm/compaction.c: correct zone boundary handling when isolating pages from a pageblock
mm/vmap: add DEBUG_AUGMENT_LOWEST_MATCH_CHECK macro
mm/vmap: add DEBUG_AUGMENT_PROPAGATE_CHECK macro
mm/vmalloc.c: keep track of free blocks for vmap allocation
Linus Torvalds [Sun, 19 May 2019 18:53:58 +0000 (11:53 -0700)]
Merge tag 'kbuild-v5.2-2' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild
Pull more Kbuild updates from Masahiro Yamada:
- remove unneeded use of cc-option, cc-disable-warning, cc-ldoption
- exclude tracked files from .gitignore
- re-enable -Wint-in-bool-context warning
- refactor samples/Makefile
- stop building immediately if syncconfig fails
- do not sprinkle error messages when $(CC) does not exist
- move arch/alpha/defconfig to the configs subdirectory
- remove crappy header search path manipulation
- add comment lines to .config to clarify the end of menu blocks
- check uniqueness of module names (adding new warnings intentionally)
* tag 'kbuild-v5.2-2' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild: (24 commits)
kconfig: use 'else ifneq' for Makefile to improve readability
kbuild: check uniqueness of module names
kconfig: Terminate menu blocks with a comment in the generated config
kbuild: add LICENSES to KBUILD_ALLDIRS
kbuild: remove 'addtree' and 'flags' magic for header search paths
treewide: prefix header search paths with $(srctree)/
media: prefix header search paths with $(srctree)/
media: remove unneeded header search paths
alpha: move arch/alpha/defconfig to arch/alpha/configs/defconfig
kbuild: terminate Kconfig when $(CC) or $(LD) is missing
kbuild: turn auto.conf.cmd into a mandatory include file
.gitignore: exclude .get_maintainer.ignore and .gitattributes
kbuild: add all Clang-specific flags unconditionally
kbuild: Don't try to add '-fcatch-undefined-behavior' flag
kbuild: add some extra warning flags unconditionally
kbuild: add -Wvla flag unconditionally
arch: remove dangling asm-generic wrappers
samples: guard sub-directories with CONFIG options
kbuild: re-enable int-in-bool-context warning
MAINTAINERS: kbuild: Add pattern for scripts/*vmlinux*
...
Linus Torvalds [Sun, 19 May 2019 18:47:03 +0000 (11:47 -0700)]
Merge branch 'i2c/for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux
Pull i2c updates from Wolfram Sang:
"Some I2C core API additions which are kind of simple but enhance error
checking for users a lot, especially by returning errno now.
There are wrappers to still support the old API but it will be removed
once all users are converted"
* 'i2c/for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux:
i2c: core: add device-managed version of i2c_new_dummy
i2c: core: improve return value handling of i2c_new_device and i2c_new_dummy
Linus Torvalds [Sun, 19 May 2019 18:43:16 +0000 (11:43 -0700)]
Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 fixes from Ted Ts'o:
"Some bug fixes, and an update to the URL's for the final version of
Unicode 12.1.0"
* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
ext4: avoid panic during forced reboot due to aborted journal
ext4: fix block validity checks for journal inodes using indirect blocks
unicode: update to Unicode 12.1.0 final
unicode: add missing check for an error return from utf8lookup()
ext4: fix miscellaneous sparse warnings
ext4: unsigned int compared against zero
ext4: fix use-after-free in dx_release()
ext4: fix data corruption caused by overlapping unaligned and aligned IO
jbd2: fix potential double free
ext4: zero out the unused memory region in the extent tree block
Linus Torvalds [Sun, 19 May 2019 18:38:18 +0000 (11:38 -0700)]
Merge tag '5.2-rc-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6
Pull cifs fixes from Steve French:
"Minor cleanup and fixes, one for stable, four rdma (smbdirect)
related. Also adds SEEK_HOLE support"
* tag '5.2-rc-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6:
cifs: add support for SEEK_DATA and SEEK_HOLE
Fixed https://bugzilla.kernel.org/show_bug.cgi?id=202935 allow write on the same file
cifs: Allocate memory for all iovs in smb2_ioctl
cifs: Don't match port on SMBDirect transport
cifs:smbd Use the correct DMA direction when sending data
cifs:smbd When reconnecting to server, call smbd_destroy() after all MIDs have been called
cifs: use the right include for signal_pending()
smb3: trivial cleanup to smb2ops.c
cifs: cleanup smb2ops.c and normalize strings
smb3: display session id in debug data
Linus Torvalds [Sun, 19 May 2019 18:20:22 +0000 (11:20 -0700)]
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf tooling updates from Ingo Molnar:
"perf.data:
- Streaming compression of perf ring buffer into
PERF_RECORD_COMPRESSED user space records, resulting in ~3-5x
perf.data file size reduction on variety of tested workloads what
saves storage space on larger server systems where perf.data size
can easily reach several tens or even hundreds of GiBs, especially
when profiling with DWARF-based stacks and tracing of context
switches.
perf record:
- Improve -user-regs/intr-regs suggestions to overcome errors
perf annotate:
- Remove hist__account_cycles() from callback, speeding up branch
processing (perf record -b)
perf stat:
- Add a 'percore' event qualifier, e.g.: -e
cpu/event=0,umask=0x3,percore=1/, that sums up the event counts for
both hardware threads in a core.
We can already do this with --per-core, but it's often useful to do
this together with other metrics that are collected per hardware
thread.
I.e. now its possible to do this per-event, and have it mixed with
other events not aggregated by core.
arm64:
- Map Brahma-B53 CPUID to cortex-a53 events.
- Add Cortex-A57 and Cortex-A72 events.
csky:
- Add DWARF register mappings for libdw, allowing --call-graph=dwarf
to work on the C-SKY arch.
x86:
- Add support for recording and printing XMM registers, available,
for instance, on Icelake.
- Add uncore_upi (Intel's "Ultra Path Interconnect" events) JSON
support. UPI replaced the Intel QuickPath Interconnect (QPI) in
Xeon Skylake-SP.
Intel PT:
- Fix instructions sampling rate.
- Timestamp fixes.
- Improve exported-sql-viewer GUI, allowing, for instance, to
copy'n'paste the trees, useful for e-mailing"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (73 commits)
perf stat: Support 'percore' event qualifier
perf stat: Factor out aggregate counts printing
perf tools: Add a 'percore' event qualifier
perf docs: Add description for stderr
perf intel-pt: Fix sample timestamp wrt non-taken branches
perf intel-pt: Fix improved sample timestamp
perf intel-pt: Fix instructions sampling rate
perf regs x86: Add X86 specific arch__intr_reg_mask()
perf parse-regs: Add generic support for arch__intr/user_reg_mask()
perf parse-regs: Split parse_regs
perf vendor events arm64: Add Cortex-A57 and Cortex-A72 events
perf vendor events arm64: Map Brahma-B53 CPUID to cortex-a53 events
perf vendor events arm64: Remove [[:xdigit:]] wildcard
perf jevents: Remove unused variable
perf test zstd: Fixup verbose mode output
perf tests: Implement Zstd comp/decomp integration test
perf inject: Enable COMPRESSED record decompression
perf report: Implement perf.data record decompression
perf record: Implement -z,--compression_level[=<n>] option
perf report: Add stub processing of compressed events for -D
...
Linus Torvalds [Sun, 19 May 2019 18:11:20 +0000 (11:11 -0700)]
Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull clocksource updates from Ingo Molnar:
"Misc clocksource/clockevent driver updates that came in a bit late but
are ready for v5.2"
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
misc: atmel_tclib: Do not probe already used TCBs
clocksource/drivers/timer-atmel-tcb: Convert tc_clksrc_suspend|resume() to static
clocksource/drivers/tcb_clksrc: Rename the file for consistency
clocksource/drivers/timer-atmel-pit: Rework Kconfig option
clocksource/drivers/tcb_clksrc: Move Kconfig option
ARM: at91: Implement clocksource selection
clocksource/drivers/tcb_clksrc: Use tcb as sched_clock
clocksource/drivers/tcb_clksrc: Stop depending on atmel_tclib
ARM: at91: move SoC specific definitions to SoC folder
clocksource/drivers/timer-milbeaut: Cleanup common register accesses
clocksource/drivers/timer-milbeaut: Add shutdown function
clocksource/drivers/timer-milbeaut: Fix to enable one-shot timer
clocksource/drivers/tegra: Rework for compensation of suspend time
clocksource/drivers/sp804: Add COMPILE_TEST to CONFIG_ARM_TIMER_SP804
clocksource/drivers/sun4i: Add a compatible for suniv
dt-bindings: timer: Add Allwinner suniv timer
Linus Torvalds [Sun, 19 May 2019 17:58:45 +0000 (10:58 -0700)]
Merge branch 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull IRQ chip updates from Ingo Molnar:
"A late irqchips update:
- New TI INTR/INTA set of drivers
- Rewrite of the stm32mp1-exti driver as a platform driver
- Update the IOMMU MSI mapping API to be RT friendly
- A number of cleanups and other low impact fixes"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
iommu/dma-iommu: Remove iommu_dma_map_msi_msg()
irqchip/gic-v3-mbi: Don't map the MSI page in mbi_compose_m{b, s}i_msg()
irqchip/ls-scfg-msi: Don't map the MSI page in ls_scfg_msi_compose_msg()
irqchip/gic-v3-its: Don't map the MSI page in its_irq_compose_msi_msg()
irqchip/gicv2m: Don't map the MSI page in gicv2m_compose_msi_msg()
iommu/dma-iommu: Split iommu_dma_map_msi_msg() in two parts
genirq/msi: Add a new field in msi_desc to store an IOMMU cookie
arm64: arch_k3: Enable interrupt controller drivers
irqchip/ti-sci-inta: Add msi domain support
soc: ti: Add MSI domain bus support for Interrupt Aggregator
irqchip/ti-sci-inta: Add support for Interrupt Aggregator driver
dt-bindings: irqchip: Introduce TISCI Interrupt Aggregator bindings
irqchip/ti-sci-intr: Add support for Interrupt Router driver
dt-bindings: irqchip: Introduce TISCI Interrupt router bindings
gpio: thunderx: Use the default parent apis for {request,release}_resources
genirq: Introduce irq_chip_{request,release}_resource_parent() apis
firmware: ti_sci: Add helper apis to manage resources
firmware: ti_sci: Add RM mapping table for am654
firmware: ti_sci: Add support for IRQ management
firmware: ti_sci: Add support for RM core ops
...
Linus Torvalds [Sun, 19 May 2019 17:33:26 +0000 (10:33 -0700)]
Merge branch 'efi-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull EFI fix from Ingo Molnar:
"Fix an EFI-fb regression that affects certain x86 systems"
* 'efi-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
fbdev/efifb: Ignore framebuffer memmap entries that lack any memory types
Linus Torvalds [Sun, 19 May 2019 17:23:24 +0000 (10:23 -0700)]
Merge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull core fixes from Ingo Molnar:
"This fixes a particularly thorny munmap() bug with MPX, plus fixes a
host build environment assumption in objtool"
* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
objtool: Allow AR to be overridden with HOSTAR
x86/mpx, mm/core: Fix recursive munmap() corruption
Linus Torvalds [Sun, 19 May 2019 17:16:39 +0000 (10:16 -0700)]
Merge tag 'armsoc-late' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc
Pull ARM SoC late updates from Olof Johansson:
"This is some material that we picked up into our tree late. Most of it
are smaller fixes and additions, some defconfig updates due to recent
development, etc.
Code-wise the largest portion is a series of PM updates for the at91
platform, and those have been in linux-next a while through the at91
tree before we picked them up"
* tag 'armsoc-late' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc: (29 commits)
arm64: dts: sprd: Add clock properties for serial devices
Opt out of scripts/get_maintainer.pl
ARM: ixp4xx: Remove duplicated include from common.c
soc: ixp4xx: qmgr: Fix an NULL vs IS_ERR() check in probe
arm64: tegra: Disable XUSB support on Jetson TX2
arm64: tegra: Enable SMMU translation for PCI on Tegra186
arm64: tegra: Fix insecure SMMU users for Tegra186
arm64: tegra: Select ARM_GIC_PM
amba: tegra-ahb: Mark PM functions as __maybe_unused
ARM: dts: logicpd-som-lv: Fix MMC1 card detect
ARM: mvebu: drop return from void function
ARM: mvebu: prefix coprocessor operand with p
ARM: mvebu: drop unnecessary label
ARM: mvebu: fix a leaked reference by adding missing of_node_put
ARM: socfpga_defconfig: enable LTC2497
ARM: mvebu: kirkwood: remove error message when retrieving mac address
ARM: at91: sama5: make ov2640 as a module
ARM: OMAP1: ams-delta: fix early boot crash when LED support is disabled
ARM: at91: remove HAVE_FB_ATMEL for sama5 SoC as they use DRM
soc/fsl/qe: Fix an error code in qe_pin_request()
...
Linus Torvalds [Sun, 19 May 2019 17:10:15 +0000 (10:10 -0700)]
Merge tag 'powerpc-5.2-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc fixes from Michael Ellerman:
"One fix going back to stable, for a bug on 32-bit introduced when we
added support for THREAD_INFO_IN_TASK.
A fix for a typo in a recent rework of our hugetlb code that leads to
crashes on 64-bit when using hugetlbfs with a 4K PAGE_SIZE.
Two fixes for our recent rework of the address layout on 64-bit hash
CPUs, both only triggered when userspace tries to access addresses
outside the user or kernel address ranges.
Finally a fix for a recently introduced double free in an error path
in our cacheinfo code.
Thanks to: Aneesh Kumar K.V, Christophe Leroy, Sachin Sant, Tobin C.
Harding"
* tag 'powerpc-5.2-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
powerpc/cacheinfo: Remove double free
powerpc/mm/hash: Fix get_region_id() for invalid addresses
powerpc/mm: Drop VM_BUG_ON in get_region_id()
powerpc/mm: Fix crashes with hugepages & 4K pages
powerpc/32s: fix flush_hash_pages() on SMP
Linus Torvalds [Sun, 19 May 2019 16:56:36 +0000 (09:56 -0700)]
Merge tag 'riscv-for-linus-5.2-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux
Pull RISC-V updates from Palmer Dabbelt:
"This contains an assortment of RISC-V related patches that I'd like to
target for the 5.2 merge window. Most of the patches are cleanups, but
there are a handful of user-visible changes:
- The nosmp and nr_cpus command-line arguments are now supported,
which work like normal.
- The SBI console no longer installs itself as a preferred console,
we rely on standard mechanisms (/chosen, command-line, hueristics)
instead.
- sfence_remove_sfence_vma{,_asid} now pass their arguments along to
the SBI call.
- Modules now support BUG().
- A missing sfence.vma during boot has been added. This bug only
manifests during boot.
- The arch/riscv support for SiFive's L2 cache controller has been
merged, which should un-block the EDAC framework work.
I've only tested this on QEMU again, as I didn't have time to get
things running on the Unleashed. The latest master from this morning
merges in cleanly and passes the tests as well"
* tag 'riscv-for-linus-5.2-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux: (31 commits)
riscv: fix locking violation in page fault handler
RISC-V: sifive_l2_cache: Add L2 cache controller driver for SiFive SoCs
RISC-V: Add DT documentation for SiFive L2 Cache Controller
RISC-V: Avoid using invalid intermediate translations
riscv: Support BUG() in kernel module
riscv: Add the support for c.ebreak check in is_valid_bugaddr()
riscv: support trap-based WARN()
riscv: fix sbi_remote_sfence_vma{,_asid}.
riscv: move switch_mm to its own file
riscv: move flush_icache_{all,mm} to cacheflush.c
tty: Don't force RISCV SBI console as preferred console
RISC-V: Access CSRs using CSR numbers
RISC-V: Add interrupt related SCAUSE defines in asm/csr.h
RISC-V: Use tabs to align macro values in asm/csr.h
RISC-V: Fix minor checkpatch issues.
RISC-V: Support nr_cpus command line option.
RISC-V: Implement nosmp commandline option.
RISC-V: Add RISC-V specific arch_match_cpu_phys_id
riscv: vdso: drop unnecessary cc-ldoption
riscv: call pm_power_off from machine_halt / machine_power_off
...
Masahiro Yamada [Sat, 18 May 2019 08:07:48 +0000 (17:07 +0900)]
kconfig: use 'else ifneq' for Makefile to improve readability
'ifeq ... else ifneq ... endif' notation is supported by GNU Make 3.81
or later, which is the requirement for building the kernel since
commit 37d69ee30808 ("docs: bump minimal GNU Make version to 3.81").
Feng Tang [Fri, 17 May 2019 21:31:50 +0000 (14:31 -0700)]
panic: add an option to replay all the printk message in buffer
Currently on panic, kernel will lower the loglevel and print out pending
printk msg only with console_flush_on_panic().
Add an option for users to configure the "panic_print" to replay all
dmesg in buffer, some of which they may have never seen due to the
loglevel setting, which will help panic debugging .
Steven Price [Fri, 17 May 2019 21:31:47 +0000 (14:31 -0700)]
initramfs: don't free a non-existent initrd
Since commit 54c7a8916a88 ("initramfs: free initrd memory if opening
/initrd.image fails"), the kernel has unconditionally attempted to free
the initrd even if it doesn't exist.
In the non-existent case this causes a boot-time splat if
CONFIG_DEBUG_VIRTUAL is enabled due to a call to virt_to_phys() with a
NULL address.
Instead we should check that the initrd actually exists and only attempt
to free it if it does.
Jiufei Xue [Fri, 17 May 2019 21:31:44 +0000 (14:31 -0700)]
fs/writeback.c: use rcu_barrier() to wait for inflight wb switches going into workqueue when umount
synchronize_rcu() didn't wait for call_rcu() callbacks, so inode wb
switch may not go to the workqueue after synchronize_rcu(). Thus
previous scheduled switches was not finished even flushing the
workqueue, which will cause a NULL pointer dereferenced followed below.
VFS: Busy inodes after unmount of vdd. Self-destruct in 5 seconds. Have a nice day...
BUG: unable to handle kernel NULL pointer dereference at 0000000000000278
evict+0xb3/0x180
iput+0x1b0/0x230
inode_switch_wbs_work_fn+0x3c0/0x6a0
worker_thread+0x4e/0x490
? process_one_work+0x410/0x410
kthread+0xe6/0x100
ret_from_fork+0x39/0x50
Replace the synchronize_rcu() call with a rcu_barrier() to wait for all
pending callbacks to finish. And inc isw_nr_in_flight after call_rcu()
in inode_switch_wbs() to make more sense.
There is no reproducer and it is difficult to hit -- 1 crash every few
days. The issue is very similar to the fix in commit 6b0868c820ff
("mm/compaction.c: correct zone boundary handling when resetting pageblock
skip hints"). When isolating free pages around a target pageblock, the
boundary handling is off by one and can stray into the next pageblock.
Triggering the syzbot error requires that the end of pageblock is section
or zone aligned, and that the next section is unpopulated.
A more subtle consequence of the bug is that pageblocks were being
improperly used as migration targets which potentially hurts fragmentation
avoidance in the long-term one page at a time.
A debugging patch revealed that it's definitely possible to stray outside
of a pageblock which is not intended. While syzbot cannot be used to
verify this patch, it was confirmed that the debugging warning no longer
triggers with this patch applied. It has also been confirmed that the THP
allocation stress tests are not degraded by this patch.
mm/vmalloc.c: keep track of free blocks for vmap allocation
Patch series "improve vmap allocation", v3.
Objective
---------
Please have a look for the description at:
https://lkml.org/lkml/2018/10/19/786
but let me also summarize it a bit here as well.
The current implementation has O(N) complexity. Requests with different
permissive parameters can lead to long allocation time. When i say
"long" i mean milliseconds.
Description
-----------
This approach organizes the KVA memory layout into free areas of the
1-ULONG_MAX range, i.e. an allocation is done over free areas lookups,
instead of finding a hole between two busy blocks. It allows to have
lower number of objects which represent the free space, therefore to have
less fragmented memory allocator. Because free blocks are always as large
as possible.
It uses the augment tree where all free areas are sorted in ascending
order of va->va_start address in pair with linked list that provides
O(1) access to prev/next elements.
Since the tree is augment, we also maintain the "subtree_max_size" of VA
that reflects a maximum available free block in its left or right
sub-tree. Knowing that, we can easily traversal toward the lowest (left
most path) free area.
Allocation: ~O(log(N)) complexity. It is sequential allocation method
therefore tends to maximize locality. The search is done until a first
suitable block is large enough to encompass the requested parameters.
Bigger areas are split.
I copy paste here the description of how the area is split, since i
described it in https://lkml.org/lkml/2018/10/19/786
<snip>
A free block can be split by three different ways. Their names are
FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they
correspond to how requested size and alignment fit to a free block.
FL_FIT_TYPE - in this case a free block is just removed from the free
list/tree because it fully fits. Comparing with current design there is
an extra work with rb-tree updating.
LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do
is just cutting a free block. It is as fast as a current design. Most of
the vmalloc allocations just end up with this case, because the edge is
always aligned to 1.
NE_FIT_TYPE - Is much less common case. Basically it happens when
requested size and alignment does not fit left nor right edges, i.e. it
is between them. In this case during splitting we have to build a
remaining left free area and place it back to the free list/tree.
Comparing with current design there are two extra steps. First one is we
have to allocate a new vmap_area structure. Second one we have to insert
that remaining free block to the address sorted list/tree.
In order to optimize a first case there is a cache with free_vmap objects.
Instead of allocating from slab we just take an object from the cache and
reuse it.
Second one is pretty optimized. Since we know a start point in the tree
we do not do a search from the top. Instead a traversal begins from a
rb-tree node we split.
<snip>
De-allocation. ~O(log(N)) complexity. An area is not inserted straight
away to the tree/list, instead we identify the spot first, checking if it
can be merged around neighbors. The list provides O(1) access to
prev/next, so it is pretty fast to check it. Summarizing. If merged then
large coalesced areas are created, if not the area is just linked making
more fragments.
There is one more thing that i should mention here. After modification of
VA node, its subtree_max_size is updated if it was/is the biggest area in
its left or right sub-tree. Apart of that it can also be populated back
to upper levels to fix the tree. For more details please have a look at
the __augment_tree_propagate_from() function and the description.
Tests and stressing
-------------------
I use the "test_vmalloc.sh" test driver available under
"tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo
./test_vmalloc.sh" to find out how to deal with it.
Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA.
Regarding last one, i do not have any physical access to NUMA system,
therefore i emulated it. The time of stressing is days.
If you run the test driver in "stress mode", you also need the patch that
is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it:
After massive testing, i have not identified any problems like memory
leaks, crashes or kernel panics. I find it stable, but more testing would
be good.
Performance analysis
--------------------
I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and
another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas
Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1
as well, but the results have not been ready by time i an writing this.
Currently it consist of 8 tests. There are three of them which correspond
to different types of splitting(to compare with default). We have 3
ones(see above). Another 5 do allocations in different conditions.
a) sudo ./test_vmalloc.sh performance
When the test driver is run in "performance" mode, it runs all available
tests pinned to first online CPU with sequential execution test order. We
do it in order to get stable and repeatable results. Take a look at time
difference in "long_busy_list_alloc_test". It is not surprising because
the worst case is O(N).
# i5-3320M
How many cycles all tests took:
CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles
# See detailed table with results here:
ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt
ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt
# Hikey960 8x CPUs
How many cycles all tests took:
CPU0=3478683207 cycles vs CPU0=463767978 cycles
# See detailed table with results here:
ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt
ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt
b) time sudo ./test_vmalloc.sh test_repeat_count=1
With this configuration, all tests are run on all available online CPUs.
Before running each CPU shuffles its tests execution order. It gives
random allocation behaviour. So it is rough comparison, but it puts in
the picture for sure.
# i5-3320M
<default> vs <patched>
real 101m22.813s real 0m56.805s
user 0m0.011s user 0m0.015s
sys 0m5.076s sys 0m0.023s
# See detailed table with results here:
ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt
ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt
# Hikey960 8x CPUs
<default> vs <patched>
real unknown real 4m25.214s
user unknown user 0m0.011s
sys unknown sys 0m0.670s
I did not manage to complete this test on "default Hikey960" kernel
version. After 24 hours it was still running, therefore i had to cancel
it. That is why real/user/sys are "unknown".
This patch (of 3):
Currently an allocation of the new vmap area is done over busy list
iteration(complexity O(n)) until a suitable hole is found between two busy
areas. Therefore each new allocation causes the list being grown. Due to
over fragmented list and different permissive parameters an allocation can
take a long time. For example on embedded devices it is milliseconds.
This patch organizes the KVA memory layout into free areas of the
1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks
sorted by their offsets in pair with linked list keeping the free space in
order of increasing addresses.
Nodes are augmented with the size of the maximum available free block in
its left or right sub-tree. Thus, that allows to take a decision and
traversal toward the block that will fit and will have the lowest start
address, i.e. it is sequential allocation.
Allocation: to allocate a new block a search is done over the tree until a
suitable lowest(left most) block is large enough to encompass: the
requested size, alignment and vstart point. If the block is bigger than
requested size - it is split.
De-allocation: when a busy vmap area is freed it can either be merged or
inserted to the tree. Red-black tree allows efficiently find a spot
whereas a linked list provides a constant-time access to previous and next
blocks to check if merging can be done. In case of merging of
de-allocated memory chunk a large coalesced area is created.
Ingo Molnar [Sat, 18 May 2019 08:24:43 +0000 (10:24 +0200)]
Merge tag 'perf-core-for-mingo-5.2-20190517' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
perf.data:
Alexey Budankov:
- Streaming compression of perf ring buffer into PERF_RECORD_COMPRESSED
user space records, resulting in ~3-5x perf.data file size reduction
on variety of tested workloads what saves storage space on larger
server systems where perf.data size can easily reach several tens or
even hundreds of GiBs, especially when profiling with DWARF-based
stacks and tracing of context switches.
perf record:
Arnaldo Carvalho de Melo
- Improve -user-regs/intr-regs suggestions to overcome errors.
perf annotate:
Jin Yao:
- Remove hist__account_cycles() from callback, speeding up branch processing
(perf record -b).
perf stat:
- Add a 'percore' event qualifier, e.g.: -e cpu/event=0,umask=0x3,percore=1/,
that sums up the event counts for both hardware threads in a core.
We can already do this with --per-core, but it's often useful to do
this together with other metrics that are collected per hardware thread.
I.e. now its possible to do this per-event, and have it mixed with other
events not aggregated by core.
core libraries:
Donald Yandt:
- Check for errors when doing fgets(/proc/version).
Jiri Olsa:
- Speed up report for perf compiled with linbunwind.
tools headers:
Arnaldo Carvalho de Melo
- Update memcpy_64.S, x86's kvm.h and pt_regs.h.
arm64:
Florian Fainelli:
- Map Brahma-B53 CPUID to cortex-a53 events.
- Add Cortex-A57 and Cortex-A72 events.
csky:
Mao Han:
- Add DWARF register mappings for libdw, allowing --call-graph=dwarf to work
on the C-SKY arch.
x86:
Andi Kleen/Kan Liang:
- Add support for recording and printing XMM registers, available, for
instance, on Icelake.
Kan Liang:
- Add uncore_upi (Intel's "Ultra Path Interconnect" events) JSON support.
UPI replaced the Intel QuickPath Interconnect (QPI) in Xeon Skylake-SP.
Intel PT:
Adrian Hunter
. Fix instructions sampling rate.
. Timestamp fixes.
. Improve exported-sql-viewer GUI, allowing, for instance, to copy'n'paste
the trees, useful for e-mailing.
Documentation:
Thomas Richter:
- Add description for 'perf --debug stderr=1', which redirects stderr to stdout.
Masahiro Yamada [Fri, 17 May 2019 16:07:15 +0000 (01:07 +0900)]
kbuild: check uniqueness of module names
In the recent build test of linux-next, Stephen saw a build error
caused by a broken .tmp_versions/*.mod file:
https://lkml.org/lkml/2019/5/13/991
drivers/net/phy/asix.ko and drivers/net/usb/asix.ko have the same
basename, and there is a race in generating .tmp_versions/asix.mod
Kbuild has not checked this before, and it suddenly shows up with
obscure error messages when this kind of race occurs.
Non-unique module names cause various sort of problems, but it is
not trivial to catch them by eyes.
Hence, this script.
It checks not only real modules, but also built-in modules (i.e.
controlled by tristate CONFIG option, but currently compiled with =y).
Non-unique names for built-in modules also cause problems because
/sys/modules/ would fall over.
For the latest kernel, I tested "make allmodconfig all" (or more
quickly "make allyesconfig modules"), and it detected the following:
warning: same basename if the following are built as modules:
drivers/regulator/88pm800.ko
drivers/mfd/88pm800.ko
warning: same basename if the following are built as modules:
drivers/gpu/drm/bridge/adv7511/adv7511.ko
drivers/media/i2c/adv7511.ko
warning: same basename if the following are built as modules:
drivers/net/phy/asix.ko
drivers/net/usb/asix.ko
warning: same basename if the following are built as modules:
fs/coda/coda.ko
drivers/media/platform/coda/coda.ko
warning: same basename if the following are built as modules:
drivers/net/phy/realtek.ko
drivers/net/dsa/realtek.ko
Alexander Popov [Fri, 17 May 2019 19:42:22 +0000 (22:42 +0300)]
kconfig: Terminate menu blocks with a comment in the generated config
Currently menu blocks start with a pretty header but end with nothing in
the generated config. So next config options stick together with the
options from the menu block.
Let's terminate menu blocks in the generated config with a comment and
a newline if needed. Example:
Masahiro Yamada [Mon, 13 May 2019 06:22:17 +0000 (15:22 +0900)]
kbuild: remove 'addtree' and 'flags' magic for header search paths
The 'addtree' and 'flags' in scripts/Kbuild.include are so compilecated
and ugly.
As I mentioned in [1], Kbuild should stop automatic prefixing of header
search path options.
I fixed up (almost) all Makefiles in the kernel. Now 'addtree' and
'flags' have been removed.
Kbuild still caters to add $(srctree)/$(src) and $(objtree)/$(obj)
to the header search path for O= building, but never touches extra
compiler options from ccflags-y etc.
Masahiro Yamada [Mon, 13 May 2019 06:22:16 +0000 (15:22 +0900)]
treewide: prefix header search paths with $(srctree)/
Currently, the Kbuild core manipulates header search paths in a crazy
way [1].
To fix this mess, I want all Makefiles to add explicit $(srctree)/ to
the search paths in the srctree. Some Makefiles are already written in
that way, but not all. The goal of this work is to make the notation
consistent, and finally get rid of the gross hacks.
Having whitespaces after -I does not matter since commit 48f6e3cf5bc6
("kbuild: do not drop -I without parameter").
Masahiro Yamada [Mon, 13 May 2019 06:22:15 +0000 (15:22 +0900)]
media: prefix header search paths with $(srctree)/
Currently, the Kbuild core manipulates header search paths in a crazy
way [1].
To fix this mess, I want all Makefiles to add explicit $(srctree)/ to
the search paths in the srctree. Some Makefiles are already written in
that way, but not all. The goal of this work is to make the notation
consistent, and finally get rid of the gross hacks.
Having whitespaces after -I does not matter since commit 48f6e3cf5bc6
("kbuild: do not drop -I without parameter").
The arch/$(ARCH)/defconfig is the hard-coded default in Kconfig,
and I want to deprecate it after evacuating the remaining defconfig
into the standard location, arch/*/configs/.
Define KBUILD_DEFCONFIG like other architectures, and move defconfig
into the configs/ subdirectory.
Masahiro Yamada [Thu, 9 May 2019 07:35:55 +0000 (16:35 +0900)]
kbuild: terminate Kconfig when $(CC) or $(LD) is missing
If the compiler specified by $(CC) is not present, the Kconfig stage
sprinkles 'not found' messages, then succeeds.
$ make CROSS_COMPILE=foo defconfig
/bin/sh: 1: foogcc: not found
/bin/sh: 1: foogcc: not found
*** Default configuration is based on 'x86_64_defconfig'
./scripts/gcc-version.sh: 17: ./scripts/gcc-version.sh: foogcc: not found
./scripts/gcc-version.sh: 18: ./scripts/gcc-version.sh: foogcc: not found
./scripts/gcc-version.sh: 19: ./scripts/gcc-version.sh: foogcc: not found
./scripts/gcc-version.sh: 17: ./scripts/gcc-version.sh: foogcc: not found
./scripts/gcc-version.sh: 18: ./scripts/gcc-version.sh: foogcc: not found
./scripts/gcc-version.sh: 19: ./scripts/gcc-version.sh: foogcc: not found
./scripts/clang-version.sh: 11: ./scripts/clang-version.sh: foogcc: not found
./scripts/gcc-plugin.sh: 11: ./scripts/gcc-plugin.sh: foogcc: not found
init/Kconfig:16:warning: 'GCC_VERSION': number is invalid
#
# configuration written to .config
#
Terminate parsing files immediately if $(CC) or $(LD) is not found.
"make *config" will fail more nicely.
$ make CROSS_COMPILE=foo defconfig
*** Default configuration is based on 'x86_64_defconfig'
scripts/Kconfig.include:34: compiler 'foogcc' not found
make[1]: *** [scripts/kconfig/Makefile;82: defconfig] Error 1
make: *** [Makefile;557: defconfig] Error 2
Masahiro Yamada [Sun, 12 May 2019 02:13:48 +0000 (11:13 +0900)]
kbuild: turn auto.conf.cmd into a mandatory include file
syncconfig is responsible for keeping auto.conf up-to-date, so if it
fails for any reason, the build must be terminated immediately.
However, since commit 9390dff66a52 ("kbuild: invoke syncconfig if
include/config/auto.conf.cmd is missing"), Kbuild continues running
even after syncconfig fails.
You can confirm this by intentionally making syncconfig error out:
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 08ba146..307b9de 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -1023,6 +1023,9 @@ int conf_write_autoconf(int overwrite)
FILE *out, *tristate, *out_h;
int i;
+ if (overwrite)
+ return 1;
+
if (!overwrite && is_present(autoconf_name))
return 0;
Then, syncconfig fails, but Make would not stop:
$ make -s mrproper allyesconfig defconfig
$ make
scripts/kconfig/conf --syncconfig Kconfig
GNU Make knows this rule is responsible for making all the three files
simultaneously. As far as examined, auto.conf.cmd is the target in
question when this rule is invoked. It is probably because auto.conf.cmd
is included below the inclusion of auto.conf.
The inclusion of auto.conf is mandatory, while that of auto.conf.cmd
is optional. GNU Make does not care about the failure in the process
of updating optional include files.
I filed this issue (https://savannah.gnu.org/bugs/?56301) in case this
behavior could be improved somehow in future releases of GNU Make.
Anyway, it is quite easy to fix our Makefile.
Given that auto.conf is already a mandatory include file, there is no
reason to stick auto.conf.cmd optional. Make it mandatory as well.
Cc: linux-stable <[email protected]> # 5.0+ Fixes: 9390dff66a52 ("kbuild: invoke syncconfig if include/config/auto.conf.cmd is missing") Signed-off-by: Masahiro Yamada <[email protected]>
projects / linux.git / log