The issue cause by the commit :
721255b527(drm/syncobj: flatten dma_fence_chains on transfer).
Because it use the point of dma_fence incorrectly
Correct the point of dma_fence by fence array
Signed-off-by: jie1zhan <jesse.zhang(a)amd.com>
Reviewed-by: Christian König <christian.koenig(a)amd.com>
Reviewed-by: Nirmoy Das <nirmoy.das(a)linux.intel.com>
---
drivers/gpu/drm/drm_syncobj.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 7e48dcd1bee4..d5db818f1c76 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -887,7 +887,7 @@ static int drm_syncobj_flatten_chain(struct dma_fence **f)
goto free_fences;
dma_fence_put(*f);
- *f = &array->base;
+ *f = array->fences[0];
return 0;
free_fences:
--
2.25.1
As we're currently discussing about making kernel-doc issues fatal when
CONFIG_WERROR is enable, let's fix all 60 kernel-doc warnings
inside linux-next:
arch/x86/include/uapi/asm/sgx.h:19: warning: Enum value 'SGX_PAGE_MEASURE' not described in enum 'sgx_page_flags'
arch/x86/include/uapi/asm/sgx.h:97: warning: Function parameter or member 'rdi' not described in 'sgx_enclave_user_handler_t'
arch/x86/include/uapi/asm/sgx.h:97: warning: Function parameter or member 'rsi' not described in 'sgx_enclave_user_handler_t'
arch/x86/include/uapi/asm/sgx.h:97: warning: Function parameter or member 'rdx' not described in 'sgx_enclave_user_handler_t'
arch/x86/include/uapi/asm/sgx.h:97: warning: Function parameter or member 'rsp' not described in 'sgx_enclave_user_handler_t'
arch/x86/include/uapi/asm/sgx.h:97: warning: Function parameter or member 'r8' not described in 'sgx_enclave_user_handler_t'
arch/x86/include/uapi/asm/sgx.h:97: warning: Function parameter or member 'r9' not described in 'sgx_enclave_user_handler_t'
arch/x86/include/uapi/asm/sgx.h:124: warning: Function parameter or member 'reserved' not described in 'sgx_enclave_run'
drivers/devfreq/devfreq.c:707: warning: Function parameter or member 'val' not described in 'qos_min_notifier_call'
drivers/devfreq/devfreq.c:707: warning: Function parameter or member 'ptr' not described in 'qos_min_notifier_call'
drivers/devfreq/devfreq.c:717: warning: Function parameter or member 'val' not described in 'qos_max_notifier_call'
drivers/devfreq/devfreq.c:717: warning: Function parameter or member 'ptr' not described in 'qos_max_notifier_call'
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:5095: warning: expecting prototype for amdgpu_device_gpu_recover_imp(). Prototype was for amdgpu_device_gpu_recover() instead
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:544: warning: Function parameter or member 'dmub_outbox_params' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:544: warning: Function parameter or member 'num_of_edps' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:544: warning: Function parameter or member 'disable_hpd_irq' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:544: warning: Function parameter or member 'dmub_aux_transfer_done' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:544: warning: Function parameter or member 'delayed_hpd_wq' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/include/amd_shared.h:224: warning: Enum value 'PP_GFX_DCS_MASK' not described in enum 'PP_FEATURE_MASK'
drivers/gpu/drm/scheduler/sched_main.c:999: warning: Function parameter or member 'dev' not described in 'drm_sched_init'
drivers/usb/dwc3/core.h:1328: warning: Function parameter or member 'async_callbacks' not described in 'dwc3'
drivers/usb/dwc3/gadget.c:675: warning: Function parameter or member 'mult' not described in 'dwc3_gadget_calc_tx_fifo_size'
fs/attr.c:36: warning: Function parameter or member 'ia_vfsuid' not described in 'chown_ok'
fs/attr.c:36: warning: Excess function parameter 'uid' description in 'chown_ok'
fs/attr.c:63: warning: Function parameter or member 'ia_vfsgid' not described in 'chgrp_ok'
fs/attr.c:63: warning: Excess function parameter 'gid' description in 'chgrp_ok'
fs/namei.c:649: warning: Function parameter or member 'mnt' not described in 'path_connected'
fs/namei.c:649: warning: Function parameter or member 'dentry' not described in 'path_connected'
fs/namei.c:1089: warning: Function parameter or member 'inode' not described in 'may_follow_link'
include/drm/gpu_scheduler.h:463: warning: Function parameter or member 'dev' not described in 'drm_gpu_scheduler'
include/linux/dcache.h:309: warning: expecting prototype for dget, dget_dlock(). Prototype was for dget_dlock() instead
include/linux/fscache.h:270: warning: Function parameter or member 'cookie' not described in 'fscache_use_cookie'
include/linux/fscache.h:270: warning: Excess function parameter 'object' description in 'fscache_use_cookie'
include/linux/fscache.h:287: warning: Function parameter or member 'cookie' not described in 'fscache_unuse_cookie'
include/linux/fscache.h:287: warning: Excess function parameter 'object' description in 'fscache_unuse_cookie'
include/linux/genalloc.h:54: warning: Function parameter or member 'start_addr' not described in 'genpool_algo_t'
include/linux/kfence.h:221: warning: Function parameter or member 'slab' not described in '__kfence_obj_info'
include/linux/regulator/driver.h:434: warning: Function parameter or member 'n_ramp_values' not described in 'regulator_desc'
include/linux/textsearch.h:51: warning: Function parameter or member 'list' not described in 'ts_ops'
include/linux/usb/typec_altmode.h:132: warning: Function parameter or member 'altmode' not described in 'typec_altmode_get_orientation'
include/net/cfg80211.h:391: warning: Function parameter or member 'bw' not described in 'ieee80211_eht_mcs_nss_supp'
include/net/cfg80211.h:437: warning: Function parameter or member 'eht_cap' not described in 'ieee80211_sband_iftype_data'
include/net/cfg80211.h:507: warning: Function parameter or member 's1g' not described in 'ieee80211_sta_s1g_cap'
include/net/cfg80211.h:1390: warning: Function parameter or member 'counter_offset_beacon' not described in 'cfg80211_color_change_settings'
include/net/cfg80211.h:1390: warning: Function parameter or member 'counter_offset_presp' not described in 'cfg80211_color_change_settings'
include/net/cfg80211.h:1430: warning: Enum value 'STATION_PARAM_APPLY_STA_TXPOWER' not described in enum 'station_parameters_apply_mask'
include/net/cfg80211.h:2195: warning: Function parameter or member 'dot11MeshConnectedToAuthServer' not described in 'mesh_config'
include/net/cfg80211.h:2341: warning: Function parameter or member 'short_ssid' not described in 'cfg80211_scan_6ghz_params'
include/net/cfg80211.h:3328: warning: Function parameter or member 'kck_len' not described in 'cfg80211_gtk_rekey_data'
include/net/cfg80211.h:3698: warning: Function parameter or member 'ftm' not described in 'cfg80211_pmsr_result'
include/net/cfg80211.h:3828: warning: Function parameter or member 'global_mcast_stypes' not described in 'mgmt_frame_regs'
include/net/cfg80211.h:4977: warning: Function parameter or member 'ftm' not described in 'cfg80211_pmsr_capabilities'
include/net/cfg80211.h:5742: warning: Function parameter or member 'u' not described in 'wireless_dev'
include/net/cfg80211.h:5742: warning: Function parameter or member 'links' not described in 'wireless_dev'
include/net/cfg80211.h:5742: warning: Function parameter or member 'valid_links' not described in 'wireless_dev'
include/net/cfg80211.h:6076: warning: Function parameter or member 'is_amsdu' not described in 'ieee80211_data_to_8023_exthdr'
include/net/cfg80211.h:6949: warning: Function parameter or member 'sig_dbm' not described in 'cfg80211_notify_new_peer_candidate'
include/net/mac80211.h:6250: warning: Function parameter or member 'vif' not described in 'ieee80211_channel_switch_disconnect'
mm/memory.c:1729: warning: Function parameter or member 'mt' not described in 'unmap_vmas'
net/mac80211/sta_info.h:569: warning: Function parameter or member 'cur_max_bandwidth' not described in 'link_sta_info'
Mauro Carvalho Chehab (22):
net: cfg80211: fix kernel-doc warnings all over the file
net: mac80211: add a missing comma at kernel-doc markup
net: mac80211: sta_info: fix a missing kernel-doc struct element
x86/sgx: fix kernel-doc markups
fscache: fix kernel-doc documentation
fs: attr: update vfs uid/gid parameters at kernel-doc
fs: namei: address some kernel-doc issues
devfreq: shut up kernel-doc warnings
drm: amdgpu: amdgpu_dm: fix kernel-doc markups
drm: amdgpu: amdgpu_device.c: fix a kernel-doc markup
drm: amd: amd_shared.h: Add missing doc for PP_GFX_DCS_MASK
drm: gpu_scheduler: fix a kernel-doc warning
drm: scheduler: add a missing kernel-doc parameter
kfence: fix a kernel-doc parameter
mm: document maple tree pointer at unmap_vmas() at memory.c
genalloc: add a description for start_addr parameter
textsearch: document list inside struct ts_ops
regulator: fix a kernel-doc warning
dcache: fix a kernel-doc warning
usb: typec_altmode: add a missing "@" at a kernel-doc parameter
usb: dwc3: document async_callbacks field
usb: dwc3: gadget: fix a kernel-doc warning
arch/x86/include/uapi/asm/sgx.h | 10 +++++--
drivers/devfreq/devfreq.c | 4 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h | 7 +++++
drivers/gpu/drm/amd/include/amd_shared.h | 1 +
drivers/gpu/drm/scheduler/sched_main.c | 1 +
drivers/usb/dwc3/core.h | 2 ++
drivers/usb/dwc3/gadget.c | 1 +
fs/attr.c | 4 +--
fs/namei.c | 3 ++
include/drm/gpu_scheduler.h | 1 +
include/linux/dcache.h | 2 +-
include/linux/fscache.h | 4 +--
include/linux/genalloc.h | 1 +
include/linux/kfence.h | 1 +
include/linux/regulator/driver.h | 1 +
include/linux/textsearch.h | 1 +
include/linux/usb/typec_altmode.h | 2 +-
include/net/cfg80211.h | 28 ++++++++++++++-----
include/net/mac80211.h | 2 +-
mm/memory.c | 2 ++
net/mac80211/sta_info.h | 2 ++
22 files changed, 65 insertions(+), 17 deletions(-)
--
2.36.1
This patch series revisits the proposal for a GPU cgroup controller to
track and limit memory allocations by various device/allocator
subsystems. The patch series also contains a simple prototype to
illustrate how Android intends to implement DMA-BUF allocator
attribution using the GPU cgroup controller. The prototype does not
include resource limit enforcements.
Changelog:
v7:
Hide gpucg and gpucg_bucket struct definitions per Michal Koutný.
This means gpucg_register_bucket now returns an internally allocated
struct gpucg_bucket.
Move all public function documentation to the cgroup_gpu.h header.
Remove comment in documentation about duplicate name rejection which
is not relevant to cgroups users per Michal Koutný.
v6:
Move documentation into cgroup-v2.rst per Tejun Heo.
Rename BINDER_FD{A}_FLAG_SENDER_NO_NEED ->
BINDER_FD{A}_FLAG_XFER_CHARGE per Carlos Llamas.
Return error on transfer failure per Carlos Llamas.
v5:
Rebase on top of v5.18-rc3
Drop the global GPU cgroup "total" (sum of all device totals) portion
of the design since there is no currently known use for this per
Tejun Heo.
Fix commit message which still contained the old name for
dma_buf_transfer_charge per Michal Koutný.
Remove all GPU cgroup code except what's necessary to support charge transfer
from dma_buf. Previously charging was done in export, but for non-Android
graphics use-cases this is not ideal since there may be a delay between
allocation and export, during which time there is no accounting.
Merge dmabuf: Use the GPU cgroup charge/uncharge APIs patch into
dmabuf: heaps: export system_heap buffers with GPU cgroup charging as a
result of above.
Put the charge and uncharge code in the same file (system_heap_allocate,
system_heap_dma_buf_release) instead of splitting them between the heap and
the dma_buf_release. This avoids asymmetric management of the gpucg charges.
Modify the dma_buf_transfer_charge API to accept a task_struct instead
of a gpucg. This avoids requiring the caller to manage the refcount
of the gpucg upon failure and confusing ownership transfer logic.
Support all strings for gpucg_register_bucket instead of just string
literals.
Enforce globally unique gpucg_bucket names.
Constrain gpucg_bucket name lengths to 64 bytes.
Append "-heap" to gpucg_bucket names from dmabuf-heaps.
Drop patch 7 from the series, which changed the types of
binder_transaction_data's sender_pid and sender_euid fields. This was
done in another commit here:
https://lore.kernel.org/all/20220210021129.3386083-4-masahiroy@kernel.org/
Rename:
gpucg_try_charge -> gpucg_charge
find_cg_rpool_locked -> cg_rpool_find_locked
init_cg_rpool -> cg_rpool_init
get_cg_rpool_locked -> cg_rpool_get_locked
"gpu cgroup controller" -> "GPU controller"
gpucg_device -> gpucg_bucket
usage -> size
Tests:
Support both binder_fd_array_object and binder_fd_object. This is
necessary because new versions of Android will use binder_fd_object
instead of binder_fd_array_object, and we need to support both.
Tests for both binder_fd_array_object and binder_fd_object.
For binder_utils return error codes instead of
struct binder{fs}_ctx.
Use ifdef __ANDROID__ to choose platform-dependent temp path instead
of a runtime fallback.
Ensure binderfs_mntpt ends with a trailing '/' character instead of
prepending it where used.
v4:
Skip test if not run as root per Shuah Khan
Add better test logging for abnormal child termination per Shuah Khan
Adjust ordering of charge/uncharge during transfer to avoid potentially
hitting cgroup limit per Michal Koutný
Adjust gpucg_try_charge critical section for charge transfer functionality
Fix uninitialized return code error for dmabuf_try_charge error case
v3:
Remove Upstreaming Plan from gpu-cgroup.rst per John Stultz
Use more common dual author commit message format per John Stultz
Remove android from binder changes title per Todd Kjos
Add a kselftest for this new behavior per Greg Kroah-Hartman
Include details on behavior for all combinations of kernel/userspace
versions in changelog (thanks Suren Baghdasaryan) per Greg Kroah-Hartman.
Fix pid and uid types in binder UAPI header
v2:
See the previous revision of this change submitted by Hridya Valsaraju
at: https://lore.kernel.org/all/20220115010622.3185921-1-hridya@google.com/
Move dma-buf cgroup charge transfer from a dma_buf_op defined by every
heap to a single dma-buf function for all heaps per Daniel Vetter and
Christian König. Pointers to struct gpucg and struct gpucg_device
tracking the current associations were added to the dma_buf struct to
achieve this.
Fix incorrect Kconfig help section indentation per Randy Dunlap.
History of the GPU cgroup controller
====================================
The GPU/DRM cgroup controller came into being when a consensus[1]
was reached that the resources it tracked were unsuitable to be integrated
into memcg. Originally, the proposed controller was specific to the DRM
subsystem and was intended to track GEM buffers and GPU-specific
resources[2]. In order to help establish a unified memory accounting model
for all GPU and all related subsystems, Daniel Vetter put forth a
suggestion to move it out of the DRM subsystem so that it can be used by
other DMA-BUF exporters as well[3]. This RFC proposes an interface that
does the same.
[1]: https://patchwork.kernel.org/project/dri-devel/cover/20190501140438.9506-1-…
[2]: https://lore.kernel.org/amd-gfx/20210126214626.16260-1-brian.welty@intel.co…
[3]: https://lore.kernel.org/amd-gfx/YCVOl8%2F87bqRSQei@phenom.ffwll.local/
Hridya Valsaraju (3):
gpu: rfc: Proposal for a GPU cgroup controller
cgroup: gpu: Add a cgroup controller for allocator attribution of GPU
memory
binder: Add flags to relinquish ownership of fds
T.J. Mercier (3):
dmabuf: heaps: export system_heap buffers with GPU cgroup charging
dmabuf: Add gpu cgroup charge transfer function
selftests: Add binder cgroup gpu memory transfer tests
Documentation/admin-guide/cgroup-v2.rst | 23 +
drivers/android/binder.c | 31 +-
drivers/dma-buf/dma-buf.c | 80 ++-
drivers/dma-buf/dma-heap.c | 38 ++
drivers/dma-buf/heaps/system_heap.c | 28 +-
include/linux/cgroup_gpu.h | 146 +++++
include/linux/cgroup_subsys.h | 4 +
include/linux/dma-buf.h | 49 +-
include/linux/dma-heap.h | 15 +
include/uapi/linux/android/binder.h | 23 +-
init/Kconfig | 7 +
kernel/cgroup/Makefile | 1 +
kernel/cgroup/gpu.c | 390 +++++++++++++
.../selftests/drivers/android/binder/Makefile | 8 +
.../drivers/android/binder/binder_util.c | 250 +++++++++
.../drivers/android/binder/binder_util.h | 32 ++
.../selftests/drivers/android/binder/config | 4 +
.../binder/test_dmabuf_cgroup_transfer.c | 526 ++++++++++++++++++
18 files changed, 1632 insertions(+), 23 deletions(-)
create mode 100644 include/linux/cgroup_gpu.h
create mode 100644 kernel/cgroup/gpu.c
create mode 100644 tools/testing/selftests/drivers/android/binder/Makefile
create mode 100644 tools/testing/selftests/drivers/android/binder/binder_util.c
create mode 100644 tools/testing/selftests/drivers/android/binder/binder_util.h
create mode 100644 tools/testing/selftests/drivers/android/binder/config
create mode 100644 tools/testing/selftests/drivers/android/binder/test_dmabuf_cgroup_transfer.c
--
2.36.0.512.ge40c2bad7a-goog
Hi Andy,
Am 21.06.22 um 12:17 schrieb Andy.Hsieh:
> On 2/16/21 4:39 AM, Nicolas Dufresne wrote:
> > Le lundi 15 février 2021 à 09:58 +0100, Christian König a écrit :
> >> Hi guys,
> >>
> >> we are currently working an Freesync and direct scan out from system
> >> memory on AMD APUs in A+A laptops.
> >>
> >> On problem we stumbled over is that our display hardware needs to scan
> >> out from uncached system memory and we currently don't have a way to
> >> communicate that through DMA-buf.
> >>
> >> For our specific use case at hand we are going to implement something
> >> driver specific, but the question is should we have something more
> >> generic for this?
> >
> > Hopefully I'm getting this right, but this makes me think of a long standing
> > issue I've met with Intel DRM and UVC driver. If I let the UVC driver allocate
> > the buffer, and import the resulting DMABuf (cacheable memory written with a cpu
> > copy in the kernel) into DRM, we can see cache artifact being displayed. While
> > if I use the DRM driver memory (dumb buffer in that case) it's clean because
> > there is a driver specific solution to that.
> >
> > There is no obvious way for userspace application to know what's is right/wrong
> > way and in fact it feels like the kernel could solve this somehow without having
> > to inform userspace (perhaps).
> >
> >>
> >> After all the system memory access pattern is a PCIe extension and as
> >> such something generic.
> >>
> >> Regards,
> >> Christian.
> >
> >
>
> Hi All,
>
> We also encountered the UVC cache issue on ARMv8 CPU in Mediatek SoC when
> using UVC dmabuf-export and feeding the dmabuf to the DRM display by the
> following GStreamer command:
>
> # gst-launch-1.0 v4l2src device=/dev/video0 io-mode=dmabuf ! kmssink
>
> UVC driver uses videobuf2-vmalloc to allocate buffers and is able to export
> them as dmabuf. But UVC uses memcpy() to fill the frame buffer by CPU without
> flushing the cache. So if the display hardware directly uses the buffer, the
> image shown on the screen will be dirty.
>
> Here are some experiments:
>
> 1. By doing some memory operations (e.g. devmem) when streaming the UVC,
> the issue is mitigated. I guess the cache is swapped rapidly.
> 2. By replacing the memcpy() with memcpy_flushcache() in the UVC driver,
> the issue disappears.
> 3. By adding .finish callback in videobuf2-vmalloc.c to flush the cache
> before returning the buffer, the issue disappears.
>
> It seems to lack a cache flush stage in either UVC or Display. We may also
> need communication between the producer and consumer. Then, they can decide
> who is responsible for the flushing to avoid flushing cache unconditionally
> leading to the performance impact.
Well, that's not what this mail thread was all about.
The issue you are facing is that somebody is forgetting to flush caches,
but the issue discussed in this thread here is that we have hardware
which bypasses caches altogether.
As far as I can see in your case UVC just allocates normal cached system
memory through videobuf2-vmalloc() and it is perfectly valid to fill
that using memcpy().
If some hardware then accesses those buffers bypassing CPU caches then
it is the responsibility of the importing driver and/or DMA subsystem to
flush the caches accordingly.
Regards,
Christian.
>
> Regards,
> Andy Hsieh
>
> ************* MEDIATEK Confidentiality Notice ********************
> The information contained in this e-mail message (including any
> attachments) may be confidential, proprietary, privileged, or otherwise
> exempt from disclosure under applicable laws. It is intended to be
> conveyed only to the designated recipient(s). Any use, dissemination,
> distribution, printing, retaining or copying of this e-mail (including its
> attachments) by unintended recipient(s) is strictly prohibited and may
> be unlawful. If you are not an intended recipient of this e-mail, or believe
> that you have received this e-mail in error, please notify the sender
> immediately (by replying to this e-mail), delete any and all copies of
> this e-mail (including any attachments) from your system, and do not
> disclose the content of this e-mail to any other person. Thank you!
Processes can pin shared memory by keeping a handle to it through a
file descriptor; for instance dmabufs, memfd, and ashmem (in Android).
In the case of a memory leak, to identify the process pinning the
memory, userspace needs to:
- Iterate the /proc/<pid>/fd/* for each process
- Do a readlink on each entry to identify the type of memory from
the file path.
- stat() each entry to get the size of the memory.
The file permissions on /proc/<pid>/fd/* only allows for the owner
or root to perform the operations above; and so is not suitable for
capturing the system-wide state in a production environment.
This issue was addressed for dmabufs by making /proc/*/fdinfo/*
accessible to a process with PTRACE_MODE_READ_FSCREDS credentials[1]
To allow the same kind of tracking for other types of shared memory,
add the following fields to /proc/<pid>/fdinfo/<fd>:
path - This allows identifying the type of memory based on common
prefixes: e.g. "/memfd...", "/dmabuf...", "/dev/ashmem..."
This was not an issued when dmabuf tracking was introduced
because the exp_name field of dmabuf fdinfo could be used
to distinguish dmabuf fds from other types.
size - To track the amount of memory that is being pinned.
dmabufs expose size as an additional field in fdinfo. Remove
this and make it a common field for all fds.
Access to /proc/<pid>/fdinfo is governed by PTRACE_MODE_READ_FSCREDS
-- the same as for /proc/<pid>/maps which also exposes the path and
size for mapped memory regions.
This allows for a system process with PTRACE_MODE_READ_FSCREDS to
account the pinned per-process memory via fdinfo.
-----
There was some concern about exposing the file path in the RFC[2], to that
effect the change was split into separte patches. Also retrieving the file
path from fdinfo is guarded by the same capability (PTRACE_MODE_READ) as
/proc/<pid>/maps which also exposes file path, so this may not be an issue.
[1] https://lore.kernel.org/r/20210308170651.919148-1-kaleshsingh@google.com/
[2] https://lore.kernel.org/r/20220519214021.3572840-1-kaleshsingh@google.com/
Kalesh Singh (2):
procfs: Add 'size' to /proc/<pid>/fdinfo/
procfs: Add 'path' to /proc/<pid>/fdinfo/
Documentation/filesystems/proc.rst | 22 ++++++++++++++++++++--
drivers/dma-buf/dma-buf.c | 1 -
fs/proc/fd.c | 13 +++++++++----
3 files changed, 29 insertions(+), 7 deletions(-)
base-commit: 8ab2afa23bd197df47819a87f0265c0ac95c5b6a
--
2.36.1.255.ge46751e96f-goog
Add a warning that this UAPI wasn't such a good idea and shouldn't be
used by anybody.
That should give us a better chance to remove it at some point and
prevents others from running into the same issues.
Signed-off-by: Christian König <christian.koenig(a)amd.com>
---
drivers/dma-buf/Kconfig | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig
index 541efe01abc7..e4dc53a36428 100644
--- a/drivers/dma-buf/Kconfig
+++ b/drivers/dma-buf/Kconfig
@@ -75,7 +75,7 @@ menuconfig DMABUF_HEAPS
between drivers.
menuconfig DMABUF_SYSFS_STATS
- bool "DMA-BUF sysfs statistics"
+ bool "DMA-BUF sysfs statistics (DEPRECATED)"
depends on DMA_SHARED_BUFFER
help
Choose this option to enable DMA-BUF sysfs statistics
@@ -85,6 +85,10 @@ menuconfig DMABUF_SYSFS_STATS
statistics for the DMA-BUF with the unique inode number
<inode_number>.
+ This option is deprecated and should sooner or later be removed.
+ Android is the only user of this and it turned out that this resulted
+ in quite some performance problems.
+
source "drivers/dma-buf/heaps/Kconfig"
endmenu
--
2.25.1
Recently, we noticed an issue where a process went into direct reclaim
while holding the kernfs rw semaphore for sysfs in write (exclusive)
mode. This caused processes who were doing DMA-BUF exports and releases
to go into uninterruptible sleep since they needed to acquire the same
semaphore for the DMA-BUF sysfs entry creation/deletion. In order to avoid
blocking DMA-BUF export for an indeterminate amount of time while
another process is holding the sysfs rw semaphore in exclusive mode,
this patch moves the per-buffer sysfs file creation to the default work
queue. Note that this can lead to a short-term inaccuracy in the dmabuf
sysfs statistics, but this is a tradeoff to prevent the hot path from
being blocked. A work_struct is added to dma_buf to achieve this, but as
it is unioned with the kobject in the sysfs_entry, dma_buf does not
increase in size.
Fixes: bdb8d06dfefd ("dmabuf: Add the capability to expose DMA-BUF stats in sysfs")
Originally-by: Hridya Valsaraju <hridya(a)google.com>
Signed-off-by: T.J. Mercier <tjmercier(a)google.com>
---
See the originally submitted patch by Hridya Valsaraju here:
https://lkml.org/lkml/2022/1/4/1066
v2 changes:
- Defer only sysfs creation instead of creation and teardown per
Christian König
- Use a work queue instead of a kthread for deferred work per
Christian König
---
drivers/dma-buf/dma-buf-sysfs-stats.c | 56 ++++++++++++++++++++-------
include/linux/dma-buf.h | 14 ++++++-
2 files changed, 54 insertions(+), 16 deletions(-)
diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.c b/drivers/dma-buf/dma-buf-sysfs-stats.c
index 2bba0babcb62..67b0a298291c 100644
--- a/drivers/dma-buf/dma-buf-sysfs-stats.c
+++ b/drivers/dma-buf/dma-buf-sysfs-stats.c
@@ -11,6 +11,7 @@
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/sysfs.h>
+#include <linux/workqueue.h>
#include "dma-buf-sysfs-stats.h"
@@ -168,10 +169,46 @@ void dma_buf_uninit_sysfs_statistics(void)
kset_unregister(dma_buf_stats_kset);
}
+static void sysfs_add_workfn(struct work_struct *work)
+{
+ struct dma_buf_sysfs_entry *sysfs_entry =
+ container_of(work, struct dma_buf_sysfs_entry, sysfs_add_work);
+ struct dma_buf *dmabuf = sysfs_entry->dmabuf;
+
+ /*
+ * A dmabuf is ref-counted via its file member. If this handler holds the only
+ * reference to the dmabuf, there is no need for sysfs kobject creation. This is an
+ * optimization and a race; when the reference count drops to 1 immediately after
+ * this check it is not harmful as the sysfs entry will still get cleaned up in
+ * dma_buf_stats_teardown, which won't get called until the final dmabuf reference
+ * is released, and that can't happen until the end of this function.
+ */
+ if (file_count(dmabuf->file) > 1) {
+ /*
+ * kobject_init_and_add expects kobject to be zero-filled, but we have populated it
+ * (the sysfs_add_work union member) to trigger this work function.
+ */
+ memset(&dmabuf->sysfs_entry->kobj, 0, sizeof(dmabuf->sysfs_entry->kobj));
+ dmabuf->sysfs_entry->kobj.kset = dma_buf_per_buffer_stats_kset;
+ if (kobject_init_and_add(&dmabuf->sysfs_entry->kobj, &dma_buf_ktype, NULL,
+ "%lu", file_inode(dmabuf->file)->i_ino)) {
+ kobject_put(&dmabuf->sysfs_entry->kobj);
+ dmabuf->sysfs_entry = NULL;
+ }
+ } else {
+ /*
+ * Free the sysfs_entry and reset the pointer so dma_buf_stats_teardown doesn't
+ * attempt to operate on it.
+ */
+ kfree(dmabuf->sysfs_entry);
+ dmabuf->sysfs_entry = NULL;
+ }
+ dma_buf_put(dmabuf);
+}
+
int dma_buf_stats_setup(struct dma_buf *dmabuf)
{
struct dma_buf_sysfs_entry *sysfs_entry;
- int ret;
if (!dmabuf || !dmabuf->file)
return -EINVAL;
@@ -181,25 +218,16 @@ int dma_buf_stats_setup(struct dma_buf *dmabuf)
return -EINVAL;
}
- sysfs_entry = kzalloc(sizeof(struct dma_buf_sysfs_entry), GFP_KERNEL);
+ sysfs_entry = kmalloc(sizeof(struct dma_buf_sysfs_entry), GFP_KERNEL);
if (!sysfs_entry)
return -ENOMEM;
- sysfs_entry->kobj.kset = dma_buf_per_buffer_stats_kset;
sysfs_entry->dmabuf = dmabuf;
-
dmabuf->sysfs_entry = sysfs_entry;
- /* create the directory for buffer stats */
- ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL,
- "%lu", file_inode(dmabuf->file)->i_ino);
- if (ret)
- goto err_sysfs_dmabuf;
+ INIT_WORK(&dmabuf->sysfs_entry->sysfs_add_work, sysfs_add_workfn);
+ get_dma_buf(dmabuf); /* This reference will be dropped in sysfs_add_workfn. */
+ schedule_work(&dmabuf->sysfs_entry->sysfs_add_work);
return 0;
-
-err_sysfs_dmabuf:
- kobject_put(&sysfs_entry->kobj);
- dmabuf->sysfs_entry = NULL;
- return ret;
}
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 2097760e8e95..0200caa3c515 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -22,6 +22,7 @@
#include <linux/fs.h>
#include <linux/dma-fence.h>
#include <linux/wait.h>
+#include <linux/workqueue.h>
struct device;
struct dma_buf;
@@ -365,7 +366,7 @@ struct dma_buf {
*/
const char *name;
- /** @name_lock: Spinlock to protect name acces for read access. */
+ /** @name_lock: Spinlock to protect name access for read access. */
spinlock_t name_lock;
/**
@@ -441,6 +442,7 @@ struct dma_buf {
__poll_t active;
} cb_in, cb_out;
+
#ifdef CONFIG_DMABUF_SYSFS_STATS
/**
* @sysfs_entry:
@@ -449,7 +451,15 @@ struct dma_buf {
* `DMA-BUF statistics`_ for the uapi this enables.
*/
struct dma_buf_sysfs_entry {
- struct kobject kobj;
+ union {
+ struct kobject kobj;
+
+ /** @sysfs_add_work:
+ *
+ * For deferred sysfs kobject creation using a workqueue.
+ */
+ struct work_struct sysfs_add_work;
+ };
struct dma_buf *dmabuf;
} *sysfs_entry;
#endif
--
2.36.0.550.gb090851708-goog
