diff options
799 files changed, 10796 insertions, 3845 deletions
@@ -66,6 +66,11 @@ Alex Hung <alexhung@gmail.com> <alex.hung@canonical.com> Alex Shi <alexs@kernel.org> <alex.shi@intel.com> Alex Shi <alexs@kernel.org> <alex.shi@linaro.org> Alex Shi <alexs@kernel.org> <alex.shi@linux.alibaba.com> +Alice Mikityanska <alice.kernel@fastmail.im> <maxtram95@gmail.com> +Alice Mikityanska <alice.kernel@fastmail.im> <maximmi@mellanox.com> +Alice Mikityanska <alice.kernel@fastmail.im> <maximmi@nvidia.com> +Alice Mikityanska <alice.kernel@fastmail.im> <maxim@isovalent.com> +Alice Mikityanska <alice.kernel@fastmail.im> <alice@isovalent.com> Aloka Dixit <quic_alokad@quicinc.com> <alokad@codeaurora.org> Al Viro <viro@ftp.linux.org.uk> Al Viro <viro@zenIV.linux.org.uk> @@ -399,6 +404,7 @@ Jens Axboe <axboe@kernel.dk> <jens.axboe@oracle.com> Jens Axboe <axboe@kernel.dk> <axboe@fb.com> Jens Axboe <axboe@kernel.dk> <axboe@meta.com> Jens Osterkamp <Jens.Osterkamp@de.ibm.com> +Jens Wiklander <jenswi@kernel.org> <jens.wiklander@linaro.org> Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net> Jesper Dangaard Brouer <hawk@kernel.org> <brouer@redhat.com> Jesper Dangaard Brouer <hawk@kernel.org> <hawk@comx.dk> @@ -584,8 +590,6 @@ Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@osg.samsung.com> Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@redhat.com> Mauro Carvalho Chehab <mchehab@kernel.org> <m.chehab@samsung.com> Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@s-opensource.com> -Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@mellanox.com> -Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@nvidia.com> Maxime Ripard <mripard@kernel.org> <maxime@cerno.tech> Maxime Ripard <mripard@kernel.org> <maxime.ripard@bootlin.com> Maxime Ripard <mripard@kernel.org> <maxime.ripard@free-electrons.com> @@ -594,8 +598,8 @@ Mayuresh Janorkar <mayur@ti.com> Md Sadre Alam <quic_mdalam@quicinc.com> <mdalam@codeaurora.org> Miaoqing Pan <quic_miaoqing@quicinc.com> <miaoqing@codeaurora.org> Michael Buesch <m@bues.ch> -Michal Grzeschik <mgr@kernel.org> <m.grzeschik@pengutronix.de> -Michal Grzeschik <mgr@kernel.org> <mgr@pengutronix.de> +Michael Grzeschik <mgr@kernel.org> <m.grzeschik@pengutronix.de> +Michael Grzeschik <mgr@kernel.org> <mgr@pengutronix.de> Michael Riesch <michael.riesch@collabora.com> <michael.riesch@wolfvision.net> Michal Simek <michal.simek@amd.com> <michal.simek@xilinx.com> Michel Dänzer <michel@tungstengraphics.com> @@ -816,6 +820,7 @@ Simon Wunderlich <sw@simonwunderlich.de> <simon.wunderlich@s2003.tu-chemnitz.de> Simon Wunderlich <sw@simonwunderlich.de> <simon.wunderlich@saxnet.de> Simon Wunderlich <sw@simonwunderlich.de> <simon@open-mesh.com> Simon Wunderlich <sw@simonwunderlich.de> <siwu@hrz.tu-chemnitz.de> +SJ Park <sj@kernel.org> Sricharan Ramabadhran <quic_srichara@quicinc.com> <sricharan@codeaurora.org> Srinivas Kandagatla <srini@kernel.org> <srinivas.kandagatla@st.com> Srinivas Kandagatla <srini@kernel.org> <srinivas.kandagatla@linaro.org> @@ -825,8 +830,8 @@ Sriram Yagnaraman <sriram.yagnaraman@ericsson.com> <sriram.yagnaraman@est.tech> Stanislav Fomichev <sdf@fomichev.me> <sdf@google.com> Stanislav Fomichev <sdf@fomichev.me> <stfomichev@gmail.com> Stefan Wahren <wahrenst@gmx.net> <stefan.wahren@i2se.com> -Stéphane Grosjean <stephane.grosjean@hms-networks.com> <s.grosjean@peak-system.com> -Stéphane Grosjean <stephane.grosjean@hms-networks.com> <stephane.grosjean@free.fr> +Stéphane Grosjean <s.grosjean@peak-system.fr> <s.grosjean@peak-system.com> +Stéphane Grosjean <s.grosjean@peak-system.fr> <stephane.grosjean@free.fr> Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr> Stephen Hemminger <stephen@networkplumber.org> <shemminger@linux-foundation.org> Stephen Hemminger <stephen@networkplumber.org> <shemminger@osdl.org> @@ -3626,6 +3626,13 @@ S: 69 rue Dunois S: 75013 Paris S: France +N: Wolfram Sang +E: wsa@kernel.org +W: sang-engineering.com +P: rsa4096/140DE4CC14A029B6 3991 B1EA B9E2 6751 A4F7 645D 140D E4CC 14A0 29B6 +D: I2C Maintainer 2012 - 2026 +S: Berlin, Germany + N: Aleksa Sarai E: cyphar@cyphar.com W: https://www.cyphar.com/ diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-damon b/Documentation/ABI/testing/sysfs-kernel-mm-damon index b73e6bc28ea5..4fdec63a47d4 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-damon +++ b/Documentation/ABI/testing/sysfs-kernel-mm-damon @@ -1,26 +1,26 @@ what: /sys/kernel/mm/damon/ Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Interface for Data Access MONitoring (DAMON). Contains files for controlling DAMON. For more details on DAMON itself, please refer to Documentation/admin-guide/mm/damon/index.rst. What: /sys/kernel/mm/damon/admin/ Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Interface for privileged users of DAMON. Contains files for controlling DAMON that aimed to be used by privileged users. What: /sys/kernel/mm/damon/admin/kdamonds/nr_kdamonds Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a number 'N' to this file creates the number of directories for controlling each DAMON worker thread (kdamond) named '0' to 'N-1' under the kdamonds/ directory. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/state Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing 'on' or 'off' to this file makes the kdamond starts or stops, respectively. Reading the file returns the keywords based on the current status. Writing 'commit' to this file @@ -40,33 +40,33 @@ Description: Writing 'on' or 'off' to this file makes the kdamond starts or What: /sys/kernel/mm/damon/admin/kdamonds/<K>/pid Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the pid of the kdamond if it is running. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/refresh_ms Date: Jul 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the time interval for automatic DAMON status file contents update. Writing '0' disables the update. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/nr_contexts Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a number 'N' to this file creates the number of directories for controlling each DAMON context named '0' to 'N-1' under the contexts/ directory. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/avail_operations Date: Apr 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the available monitoring operations sets on the currently running kernel. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/operations Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a keyword for a monitoring operations set ('vaddr' for virtual address spaces monitoring, 'fvaddr' for fixed virtual address ranges monitoring, and 'paddr' for the physical address @@ -79,42 +79,42 @@ Description: Writing a keyword for a monitoring operations set ('vaddr' for What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/addr_unit Date: Aug 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing an integer to this file sets the 'address unit' parameter of the given operations set of the context. Reading the file returns the last-written 'address unit' value. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/pause Date: Mar 2026 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a boolean keyword to this file sets the 'pause' request parameter for the context. Reading the file returns the last-written 'pause' value. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/intervals/sample_us Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the sampling interval of the DAMON context in microseconds as the value. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/intervals/aggr_us Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the aggregation interval of the DAMON context in microseconds as the value. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/intervals/update_us Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the update interval of the DAMON context in microseconds as the value. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/intervals/intrvals_goal/access_bp Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the monitoring intervals auto-tuning target DAMON-observed access events ratio within the given time interval (aggrs in same directory), in bp @@ -122,7 +122,7 @@ Description: Writing a value to this file sets the monitoring intervals What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/intervals/intrvals_goal/aggrs Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the time interval to achieve the monitoring intervals auto-tuning target DAMON-observed access events ratio (access_bp in same directory) within. @@ -130,14 +130,14 @@ Description: Writing a value to this file sets the time interval to achieve What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/intervals/intrvals_goal/min_sample_us Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the minimum value of auto-tuned sampling interval in microseconds. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/intervals/intrvals_goal/max_sample_us Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the maximum value of auto-tuned sampling interval in microseconds. Reading this file returns the value. @@ -145,42 +145,42 @@ Description: Writing a value to this file sets the maximum value of What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/nr_regions/min WDate: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the minimum number of monitoring regions of the DAMON context as the value. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/nr_regions/max Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the maximum number of monitoring regions of the DAMON context as the value. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/targets/nr_targets Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a number 'N' to this file creates the number of directories for controlling each DAMON target of the context named '0' to 'N-1' under the contexts/ directory. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/targets/<T>/pid_target Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the pid of the target process if the context is for virtual address spaces monitoring, respectively. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/targets/<T>/obsolete_target Date: Oct 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the obsoleteness of the matching parameters commit destination target. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/targets/<T>/regions/nr_regions Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a number 'N' to this file creates the number of directories for setting each DAMON target memory region of the context named '0' to 'N-1' under the regions/ directory. In @@ -190,181 +190,181 @@ Description: Writing a number 'N' to this file creates the number of What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/targets/<T>/regions/<R>/start Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the start address of the monitoring region. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/targets/<T>/regions/<R>/end Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the end address of the monitoring region. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/nr_schemes Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a number 'N' to this file creates the number of directories for controlling each DAMON-based operation scheme of the context named '0' to 'N-1' under the schemes/ directory. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/action Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the action of the scheme. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/target_nid Date: Jun 2024 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Action's target NUMA node id. Supported by only relevant actions. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/apply_interval_us Date: Sep 2023 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a value to this file sets the action apply interval of the scheme in microseconds. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/access_pattern/sz/min Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the minimum size of the scheme's target regions in bytes. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/access_pattern/sz/max Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the maximum size of the scheme's target regions in bytes. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/access_pattern/nr_accesses/min Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the manimum 'nr_accesses' of the scheme's target regions. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/access_pattern/nr_accesses/max Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the maximum 'nr_accesses' of the scheme's target regions. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/access_pattern/age/min Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the minimum 'age' of the scheme's target regions. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/access_pattern/age/max Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the maximum 'age' of the scheme's target regions. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/ms Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the time quota of the scheme in milliseconds. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/bytes Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the size quota of the scheme in bytes. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/effective_bytes Date: Feb 2024 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading from this file gets the effective size quota of the scheme in bytes, which adjusted for the time quota and goals. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/reset_interval_ms Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the quotas charge reset interval of the scheme in milliseconds. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/nr_goals Date: Nov 2023 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a number 'N' to this file creates the number of directories for setting automatic tuning of the scheme's aggressiveness named '0' to 'N-1' under the goals/ directory. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/<G>/target_metric Date: Feb 2024 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the quota auto-tuning goal metric. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/<G>/target_value Date: Nov 2023 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the target value of the goal metric. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/<G>/current_value Date: Nov 2023 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the current value of the goal metric. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/<G>/nid Date: Apr 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the nid parameter of the goal. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/<G>/path Date: Oct 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the path parameter of the goal. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goal_tuner Date: Mar 2026 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the goal-based effective quota auto-tuning algorithm to use. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/fail_charge_num Date: Mar 2026 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the action-failed memory quota charging ratio numerator. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/fail_charge_denom Date: Mar 2026 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the action-failed memory quota charging ratio denominator. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/weights/sz_permil Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the under-quota limit regions prioritization weight for 'size' in permil. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/weights/nr_accesses_permil Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the under-quota limit regions prioritization weight for 'nr_accesses' in permil. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/weights/age_permil Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the under-quota limit regions prioritization weight for 'age' in permil. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/watermarks/metric Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the metric of the watermarks for the scheme. The writable/readable keywords for this file are 'none' for disabling the watermarks @@ -373,44 +373,44 @@ Description: Writing to and reading from this file sets and gets the metric What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/watermarks/interval_us Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the metric check interval of the watermarks for the scheme in microseconds. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/watermarks/high Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the high watermark of the scheme in permil. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/watermarks/mid Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the mid watermark of the scheme in permil. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/watermarks/low Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the low watermark of the scheme in permil. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Directory for DAMON core layer-handled DAMOS filters. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters/nr_filters Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a number 'N' to this file creates the number of directories for setting filters of the scheme named '0' to 'N-1' under the core_filters/ directory. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters/<F>/type Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the type of the memory of the interest. 'anon' for anonymous pages, 'memcg' for specific memory cgroup, 'young' for young pages, @@ -419,62 +419,62 @@ Description: Writing to and reading from this file sets and gets the type of What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters/<F>/memcg_path Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: If 'memcg' is written to the 'type' file, writing to and reading from this file sets and gets the path to the memory cgroup of the interest. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters/<F>/addr_start Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: If 'addr' is written to the 'type' file, writing to or reading from this file sets or gets the start address of the address range for the filter. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters/<F>/addr_end Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: If 'addr' is written to the 'type' file, writing to or reading from this file sets or gets the end address of the address range for the filter. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters/<F>/min Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: If 'hugepage_size' is written to the 'type' file, writing to or reading from this file sets or gets the minimum size of the hugepage for the filter. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters/<F>/max Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: If 'hugepage_size' is written to the 'type' file, writing to or reading from this file sets or gets the maximum size of the hugepage for the filter. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters/<F>/damon_target_idx Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: If 'target' is written to the 'type' file, writing to or reading from this file sets or gets the index of the DAMON monitoring target of the interest. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters/<F>/matching Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing 'Y' or 'N' to this file sets whether the filter is for the memory of the 'type', or all except the 'type'. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters/<F>/allow Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing 'Y' or 'N' to this file sets whether to allow or reject applying the scheme's action to the memory that satisfies the 'type' and the 'matching' of the directory. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/ops_filters Date: Feb 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Directory for DAMON operations set layer-handled DAMOS filters. Files under this directory works same to those of /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/core_filters @@ -482,7 +482,7 @@ Description: Directory for DAMON operations set layer-handled DAMOS filters. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/filters Date: Dec 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Directory for DAMOS filters. Files under this directory works same to those of /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/{core,ops}_filters @@ -491,14 +491,14 @@ Description: Directory for DAMOS filters. Files under this directory works What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/dests/nr_dests Date: Jul 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a number 'N' to this file creates the number of directories for setting action destinations of the scheme named '0' to 'N-1' under the dests/ directory. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/dests/<D>/id Date: Jul 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the id of the DAMOS action destination. For DAMOS_MIGRATE_{HOT,COLD} actions, the destination node's node id can be written and @@ -506,98 +506,98 @@ Description: Writing to and reading from this file sets and gets the id of What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/dests/<D>/weight Date: Jul 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the weight of the DAMOS action destination to select as the destination of each action among the destinations. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/nr_tried Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the number of regions that the action of the scheme has tried to be applied. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/sz_tried Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the total size of regions that the action of the scheme has tried to be applied in bytes. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/nr_applied Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the number of regions that the action of the scheme has successfully applied. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/sz_applied Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the total size of regions that the action of the scheme has successfully applied in bytes. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/sz_ops_filter_passed Date: Dec 2024 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the total size of memory that passed DAMON operations layer-handled filters of the scheme in bytes. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/qt_exceeds Date: Mar 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the number of the exceed events of the scheme's quotas. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/nr_snapshots Date: Dec 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the total number of DAMON snapshots that the scheme has tried to be applied. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/max_nr_snapshots Date: Dec 2025 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Writing a number to this file sets the upper limit of nr_snapshots that deactivates the scheme when the limit is reached or exceeded. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/total_bytes Date: Jul 2023 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the total amount of memory that corresponding DAMON-based Operation Scheme's action has tried to be applied. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/<R>/start Date: Oct 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the start address of a memory region that corresponding DAMON-based Operation Scheme's action has tried to be applied. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/<R>/end Date: Oct 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the end address of a memory region that corresponding DAMON-based Operation Scheme's action has tried to be applied. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/<R>/nr_accesses Date: Oct 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the 'nr_accesses' of a memory region that corresponding DAMON-based Operation Scheme's action has tried to be applied. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/<R>/age Date: Oct 2022 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the 'age' of a memory region that corresponding DAMON-based Operation Scheme's action has tried to be applied. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/<R>/sz_filter_passed Date: Dec 2024 -Contact: SeongJae Park <sj@kernel.org> +Contact: SJ Park <sj@kernel.org> Description: Reading this file returns the size of the memory in the region that passed DAMON operations layer-handled filters of the scheme in bytes. diff --git a/Documentation/admin-guide/cgroup-v1/rdma.rst b/Documentation/admin-guide/cgroup-v1/rdma.rst index e69369b7252e..abddf34d2667 100644 --- a/Documentation/admin-guide/cgroup-v1/rdma.rst +++ b/Documentation/admin-guide/cgroup-v1/rdma.rst @@ -9,6 +9,7 @@ RDMA Controller 1-2. Why RDMA controller needed? 1-3. How is RDMA controller implemented? 2. Usage Examples + 3. RDMA Interface Files 1. Overview =========== @@ -115,3 +116,68 @@ Following resources can be accounted by rdma controller. (d) Delete resource limit:: echo mlx4_0 hca_handle=max hca_object=max > /sys/fs/cgroup/rdma/1/rdma.max + +3. RDMA Interface Files +======================== + +The following interface files are available in each non-root RDMA cgroup. + + rdma.max + A read-write file which describes the configured resource limit + for an RDMA/IB device. See the Usage Examples above. + + rdma.current + A read-only file which describes the current resource usage. + + rdma.peak + A read-only nested-keyed file which shows the historical high + watermark of resource usage per device since the cgroup was created. + + An example for mlx4 and ocrdma device follows:: + + mlx4_0 hca_handle=1 hca_object=20 + ocrdma1 hca_handle=0 hca_object=23 + + rdma.events + A read-only nested-keyed file which exists on non-root cgroups + and contains the following keys: + + max + The number of times a process in this cgroup or its + descendants attempted an RDMA resource allocation that + was rejected because a rdma.max limit in the subtree + was reached. This is a hierarchical counter propagated + upward to all ancestor cgroups. A value change in this + file generates a file modified event. + + alloc_fail + The number of RDMA resource allocation attempts that + originated in this cgroup or its descendants and failed + due to a rdma.max limit being reached. This is a + hierarchical counter propagated upward. + + An example for mlx4 device follows:: + + mlx4_0 hca_handle.max=5 hca_handle.alloc_fail=3 hca_object.max=0 hca_object.alloc_fail=0 + + rdma.events.local + Similar to rdma.events but the fields are local to the cgroup, + i.e. not hierarchical. The file modified event generated on this + file reflects only the local events. + + The following nested keys are defined. + + max + The number of times a process in this cgroup or its + descendants attempted an RDMA resource allocation that + was rejected because this cgroup's own rdma.max limit + was reached. + + alloc_fail + The number of RDMA resource allocation attempts + originating from this cgroup that failed due to this + cgroup's or an ancestor's rdma.max limit. + + An example for mlx4 device follows:: + + mlx4_0 hca_handle.max=5 hca_handle.alloc_fail=0 hca_object.max=0 hca_object.alloc_fail=0 diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 993446ab66d0..14b8c571c0d1 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1570,7 +1570,7 @@ The following nested keys are defined. sock (npn) Amount of memory used in network transmission buffers - vmalloc (npn) + vmalloc Amount of memory used for vmap backed memory. shmem @@ -1735,7 +1735,7 @@ The following nested keys are defined. Number of pages written from zswap to swap. zswap_incomp - Number of incompressible pages currently stored in zswap + Amount of memory used by incompressible pages currently stored in zswap without compression. These pages could not be compressed to a size smaller than PAGE_SIZE, so they are stored as-is. @@ -2257,10 +2257,11 @@ groups D and F will influence each other. Group G will influence nobody:: So the ideal way to configure this is to set io.latency in groups A, B, and C. Generally you do not want to set a value lower than the latency your device supports. Experiment to find the value that works best for your workload. -Start at higher than the expected latency for your device and watch the -avg_lat value in io.stat for your workload group to get an idea of the -latency you see during normal operation. Use the avg_lat value as a basis for -your real setting, setting at 10-15% higher than the value in io.stat. +Start at higher than the expected latency for your device and, with +blkcg_debug_stats enabled, watch the avg_lat value in io.stat for your +workload group to get an idea of the latency you see during normal operation. +Use the avg_lat value as a basis for your real setting, setting at 10-15% +higher than the value in io.stat. How IO Latency Throttling Works ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -2298,7 +2299,9 @@ IO Latency Interface Files io.stat If the controller is enabled you will see extra stats in io.stat in - addition to the normal ones. + addition to the normal ones. These debug stats are only emitted when + the blkcg_debug_stats module parameter is enabled (it is disabled by + default). depth This is the current queue depth for the group. @@ -2934,7 +2937,8 @@ include/linux/misc_cgroup.h. Misc Interface Files ~~~~~~~~~~~~~~~~~~~~ -Miscellaneous controller provides 3 interface files. If two misc resources (res_a and res_b) are registered then: +Miscellaneous controller provides the following interface files. If two misc +resources (res_a and res_b) are registered then: misc.capacity A read-only flat-keyed file shown only in the root cgroup. It shows diff --git a/Documentation/crypto/libcrypto-blockcipher.rst b/Documentation/crypto/libcrypto-blockcipher.rst index dd5ce2f8b515..fd85e27fab8d 100644 --- a/Documentation/crypto/libcrypto-blockcipher.rst +++ b/Documentation/crypto/libcrypto-blockcipher.rst @@ -6,14 +6,14 @@ Block ciphers AES --- -Support for the AES block cipher. +This API provides support for the AES block cipher. .. kernel-doc:: include/crypto/aes.h DES --- -Support for the DES block cipher. This algorithm is obsolete and is supported -only for backwards compatibility. +This API provides support for the DES block cipher. This algorithm is obsolete +and is supported only for backwards compatibility. .. kernel-doc:: include/crypto/des.h diff --git a/Documentation/crypto/libcrypto-hash.rst b/Documentation/crypto/libcrypto-hash.rst index 4248e6fdc952..fa4c54236af6 100644 --- a/Documentation/crypto/libcrypto-hash.rst +++ b/Documentation/crypto/libcrypto-hash.rst @@ -6,81 +6,83 @@ Hash functions, MACs, and XOFs AES-CMAC and AES-XCBC-MAC ------------------------- -Support for the AES-CMAC and AES-XCBC-MAC message authentication codes. +This API provides support for the AES-CMAC and AES-XCBC-MAC message +authentication codes. .. kernel-doc:: include/crypto/aes-cbc-macs.h BLAKE2b ------- -Support for the BLAKE2b cryptographic hash function. +This API provides support for the BLAKE2b cryptographic hash function. .. kernel-doc:: include/crypto/blake2b.h BLAKE2s ------- -Support for the BLAKE2s cryptographic hash function. +This API provides support for the BLAKE2s cryptographic hash function. .. kernel-doc:: include/crypto/blake2s.h GHASH and POLYVAL ----------------- -Support for the GHASH and POLYVAL universal hash functions. These algorithms -are used only as internal components of other algorithms. +This API provides support for the GHASH and POLYVAL universal hash functions. +These algorithms are used only as internal components of other algorithms. .. kernel-doc:: include/crypto/gf128hash.h MD5 --- -Support for the MD5 cryptographic hash function and HMAC-MD5. This algorithm is -obsolete and is supported only for backwards compatibility. +This API provides support for the MD5 cryptographic hash function and HMAC-MD5. +This algorithm is obsolete and is supported only for backwards compatibility. .. kernel-doc:: include/crypto/md5.h NH -- -Support for the NH universal hash function. This algorithm is used only as an -internal component of other algorithms. +This API provides support for the NH universal hash function. This algorithm is +used only as an internal component of other algorithms. .. kernel-doc:: include/crypto/nh.h Poly1305 -------- -Support for the Poly1305 universal hash function. This algorithm is used only -as an internal component of other algorithms. +This API provides support for the Poly1305 universal hash function. This +algorithm is used only as an internal component of other algorithms. .. kernel-doc:: include/crypto/poly1305.h SHA-1 ----- -Support for the SHA-1 cryptographic hash function and HMAC-SHA1. This algorithm -is obsolete and is supported only for backwards compatibility. +This API provides support for the SHA-1 cryptographic hash function and +HMAC-SHA1. This algorithm is obsolete and is supported only for backwards +compatibility. .. kernel-doc:: include/crypto/sha1.h SHA-2 ----- -Support for the SHA-2 family of cryptographic hash functions, including SHA-224, -SHA-256, SHA-384, and SHA-512. This also includes their corresponding HMACs: -HMAC-SHA224, HMAC-SHA256, HMAC-SHA384, and HMAC-SHA512. +This API provides support for the SHA-2 family of cryptographic hash functions, +including SHA-224, SHA-256, SHA-384, and SHA-512. This also includes their +corresponding HMACs: HMAC-SHA224, HMAC-SHA256, HMAC-SHA384, and HMAC-SHA512. .. kernel-doc:: include/crypto/sha2.h SHA-3 ----- -The SHA-3 functions are documented in :ref:`sha3`. +The SHA-3 API is documented in :ref:`sha3`. SM3 --- -Support for the SM3 cryptographic hash function. +This API provides support for the SM3 cryptographic hash function. .. kernel-doc:: include/crypto/sm3.h diff --git a/Documentation/crypto/libcrypto-signature.rst b/Documentation/crypto/libcrypto-signature.rst index e80d59fa51b6..2a6dc793f0de 100644 --- a/Documentation/crypto/libcrypto-signature.rst +++ b/Documentation/crypto/libcrypto-signature.rst @@ -6,6 +6,6 @@ Digital signature algorithms ML-DSA ------ -Support for the ML-DSA digital signature algorithm. +This API provides support for the ML-DSA digital signature algorithm. .. kernel-doc:: include/crypto/mldsa.h diff --git a/Documentation/crypto/libcrypto.rst b/Documentation/crypto/libcrypto.rst index a1557d45b0e5..0733e603d229 100644 --- a/Documentation/crypto/libcrypto.rst +++ b/Documentation/crypto/libcrypto.rst @@ -4,8 +4,9 @@ Crypto library ============== -``lib/crypto/`` provides faster and easier access to cryptographic algorithms -than the traditional crypto API. +The Linux kernel's crypto library (``lib/crypto/``) provides kernel-internal +users of cryptographic algorithms with faster and easier access to those +algorithms than the traditional kernel crypto API. Each cryptographic algorithm is supported via a set of dedicated functions. "Crypto agility", where needed, is left to calling code. diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.yaml b/Documentation/devicetree/bindings/mmc/mtk-sd.yaml index eb3755bdfdf7..a4d032224dce 100644 --- a/Documentation/devicetree/bindings/mmc/mtk-sd.yaml +++ b/Documentation/devicetree/bindings/mmc/mtk-sd.yaml @@ -193,7 +193,6 @@ allOf: - mediatek,mt8183-mmc - mediatek,mt8186-mmc - mediatek,mt8188-mmc - - mediatek,mt8189-mmc - mediatek,mt8195-mmc - mediatek,mt8196-mmc - mediatek,mt8516-mmc @@ -348,6 +347,34 @@ allOf: - const: axi_cg - const: ahb_cg + - if: + properties: + compatible: + contains: + const: mediatek,mt8189-mmc + then: + properties: + clocks: + minItems: 6 + items: + - description: source clock + - description: HCLK which used for host + - description: independent source clock gate + - description: bus clock used for internal register access + - description: peripheral bus clock gate + - description: AXI bus clock gate + - description: crypto clock used for data encrypt/decrypt (optional) + clock-names: + minItems: 6 + items: + - const: source + - const: hclk + - const: source_cg + - const: bus_clk + - const: pclk_cg + - const: axi_cg + - const: crypto + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/sound/qcom,lpass-rx-macro.yaml b/Documentation/devicetree/bindings/sound/qcom,lpass-rx-macro.yaml index 2eed2277511f..4988e7ed6e34 100644 --- a/Documentation/devicetree/bindings/sound/qcom,lpass-rx-macro.yaml +++ b/Documentation/devicetree/bindings/sound/qcom,lpass-rx-macro.yaml @@ -21,6 +21,7 @@ properties: - qcom,sc8280xp-lpass-rx-macro - items: - enum: + - qcom,eliza-lpass-rx-macro - qcom,kaanapali-lpass-rx-macro - qcom,sm8650-lpass-rx-macro - qcom,sm8750-lpass-rx-macro diff --git a/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml b/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml index e5e65e226a02..d8682ff2e82c 100644 --- a/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml +++ b/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml @@ -21,6 +21,7 @@ properties: - qcom,sc8280xp-lpass-tx-macro - items: - enum: + - qcom,eliza-lpass-tx-macro - qcom,kaanapali-lpass-tx-macro - qcom,sm8650-lpass-tx-macro - qcom,sm8750-lpass-tx-macro diff --git a/Documentation/devicetree/bindings/sound/qcom,lpass-va-macro.yaml b/Documentation/devicetree/bindings/sound/qcom,lpass-va-macro.yaml index 5c42b2b323ee..aea31fbdad37 100644 --- a/Documentation/devicetree/bindings/sound/qcom,lpass-va-macro.yaml +++ b/Documentation/devicetree/bindings/sound/qcom,lpass-va-macro.yaml @@ -21,6 +21,7 @@ properties: - qcom,sc8280xp-lpass-va-macro - items: - enum: + - qcom,eliza-lpass-va-macro - qcom,glymur-lpass-va-macro - qcom,kaanapali-lpass-va-macro - qcom,sm8650-lpass-va-macro diff --git a/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml b/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml index d5f22b5cf021..9fedd80532e2 100644 --- a/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml +++ b/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml @@ -20,6 +20,7 @@ properties: - qcom,sc8280xp-lpass-wsa-macro - items: - enum: + - qcom,eliza-lpass-wsa-macro - qcom,glymur-lpass-wsa-macro - qcom,kaanapali-lpass-wsa-macro - qcom,sm8650-lpass-wsa-macro diff --git a/Documentation/devicetree/bindings/sound/qcom,sm8250.yaml b/Documentation/devicetree/bindings/sound/qcom,sm8250.yaml index 15f38622b98b..dae440ecab59 100644 --- a/Documentation/devicetree/bindings/sound/qcom,sm8250.yaml +++ b/Documentation/devicetree/bindings/sound/qcom,sm8250.yaml @@ -23,6 +23,7 @@ properties: - const: qcom,sdm845-sndcard - items: - enum: + - qcom,eliza-sndcard - qcom,kaanapali-sndcard - qcom,sm8550-sndcard - qcom,sm8650-sndcard diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index 892979da098e..68c26a70bb64 100644 --- a/Documentation/netlink/specs/rt-link.yaml +++ b/Documentation/netlink/specs/rt-link.yaml @@ -1585,31 +1585,31 @@ attribute-sets: type: u32 - name: mode - type: flag + type: u8 - name: guard - type: flag + type: u8 - name: protect - type: flag + type: u8 - name: fast-leave - type: flag + type: u8 - name: learning - type: flag + type: u8 - name: unicast-flood - type: flag + type: u8 - name: proxyarp - type: flag + type: u8 - name: learning-sync - type: flag + type: u8 - name: proxyarp-wifi - type: flag + type: u8 - name: root-id type: binary @@ -1656,34 +1656,34 @@ attribute-sets: type: pad - name: mcast-flood - type: flag + type: u8 - name: mcast-to-ucast - type: flag + type: u8 - name: vlan-tunnel - type: flag + type: u8 - name: bcast-flood - type: flag + type: u8 - name: group-fwd-mask type: u16 - name: neigh-suppress - type: flag + type: u8 - name: isolated - type: flag + type: u8 - name: backup-port type: u32 - name: mrp-ring-open - type: flag + type: u8 - name: mrp-in-open - type: flag + type: u8 - name: mcast-eht-hosts-limit type: u32 @@ -1692,10 +1692,10 @@ attribute-sets: type: u32 - name: locked - type: flag + type: u8 - name: mab - type: flag + type: u8 - name: mcast-n-groups type: u32 @@ -1704,7 +1704,7 @@ attribute-sets: type: u32 - name: neigh-vlan-suppress - type: flag + type: u8 - name: backup-nhid type: u32 diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 4b1ffd03f516..2771ea4cc14a 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -493,8 +493,9 @@ a freshly woken up task gets on a CPU. Where to Look ============= -* ``include/linux/sched/ext.h`` defines the core data structures, ops table - and constants. +* ``include/linux/sched/ext.h`` defines the core data structures and + constants, while the ops table (``struct sched_ext_ops``) is defined in + ``kernel/sched/ext/internal.h``. * ``kernel/sched/ext/ext.c`` contains sched_ext core implementation and helpers. The functions prefixed with ``scx_bpf_`` can be called from the BPF @@ -555,7 +556,8 @@ ABI Instability =============== The APIs provided by sched_ext to BPF schedulers programs have no stability -guarantees. This includes the ops table callbacks and constants defined in +guarantees. This includes the ops table callbacks defined in +``kernel/sched/ext/internal.h`` and the constants defined in ``include/linux/sched/ext.h``, as well as the ``scx_bpf_`` kfuncs defined in ``kernel/sched/ext/ext.c`` and ``kernel/sched/ext/idle.c``. diff --git a/Documentation/watchdog/watchdog-parameters.rst b/Documentation/watchdog/watchdog-parameters.rst index ec5f67c060cb..502cb6adbeda 100644 --- a/Documentation/watchdog/watchdog-parameters.rst +++ b/Documentation/watchdog/watchdog-parameters.rst @@ -59,7 +59,7 @@ advantechwdt: alim1535_wdt: timeout: - Watchdog timeout in seconds. (0 < timeout < 18000, default=60 + Watchdog timeout in seconds. (0 < timeout < 18000, default=60) nowayout: Watchdog cannot be stopped once started (default=kernel config parameter) @@ -68,7 +68,7 @@ alim1535_wdt: alim7101_wdt: timeout: - Watchdog timeout in seconds. (1<=timeout<=3600, default=30 + Watchdog timeout in seconds. (1<=timeout<=3600, default=30) use_gpio: Use the gpio watchdog (required by old cobalt boards). default=0/off/no diff --git a/MAINTAINERS b/MAINTAINERS index 806bd2d80d15..ff93f3954fd1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2767,12 +2767,12 @@ F: arch/arm/mach-ep93xx/ F: drivers/iio/adc/ep93xx_adc.c ARM/CIX SOC SUPPORT -M: Peter Chen <peter.chen@cixtech.com> +M: Gary Yang <gary.yang@cixtech.com> M: Fugang Duan <fugang.duan@cixtech.com> R: CIX Linux Kernel Upstream Group <cix-kernel-upstream@cixtech.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/cix.git +T: git https://github.com/cixtech/linux-mainline.git F: Documentation/devicetree/bindings/arm/cix.yaml F: Documentation/devicetree/bindings/mailbox/cix,sky1-mbox.yaml F: arch/arm64/boot/dts/cix/ @@ -6209,6 +6209,7 @@ F: include/dt-bindings/sound/cs* F: include/linux/mfd/cs42l43* F: include/sound/cs* F: sound/hda/codecs/cirrus* +F: sound/hda/codecs/side-codecs/cirrus* F: sound/hda/codecs/side-codecs/cs* F: sound/hda/codecs/side-codecs/hda_component* F: sound/soc/codecs/cs* @@ -6477,7 +6478,7 @@ L: linux-cifs@vger.kernel.org L: samba-technical@lists.samba.org (moderated for non-subscribers) S: Supported W: https://wiki.samba.org/index.php/LinuxCIFS -T: git https://git.samba.org/sfrench/cifs-2.6.git +T: git https://git.samba.org/sfrench/cifs-2.6.git for-next F: Documentation/admin-guide/cifs/ F: fs/smb/client/ F: fs/smb/common/ @@ -7124,7 +7125,7 @@ W: https://docs.dasharo.com/ F: drivers/platform/x86/dasharo-acpi.c DAMON -M: SeongJae Park <sj@kernel.org> +M: SJ Park <sj@kernel.org> L: damon@lists.linux.dev L: linux-mm@kvack.org S: Maintained @@ -14141,7 +14142,7 @@ R: Sergey Senozhatsky <senozhatsky@chromium.org> R: Tom Talpey <tom@talpey.com> L: linux-cifs@vger.kernel.org S: Maintained -T: git https://git.samba.org/ksmbd.git +T: git https://git.samba.org/ksmbd.git ksmbd-for-next F: Documentation/filesystems/smb/ksmbd.rst F: fs/smb/common/ F: fs/smb/server/ @@ -14191,6 +14192,7 @@ F: virt/kvm/* KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) M: Marc Zyngier <maz@kernel.org> M: Oliver Upton <oupton@kernel.org> +R: Fuad Tabba <tabba@google.com> R: Joey Gouly <joey.gouly@arm.com> R: Steffen Eiden <seiden@linux.ibm.com> R: Suzuki K Poulose <suzuki.poulose@arm.com> @@ -17255,6 +17257,7 @@ R: Ryan Roberts <ryan.roberts@arm.com> R: Dev Jain <dev.jain@arm.com> R: Barry Song <baohua@kernel.org> R: Lance Yang <lance.yang@linux.dev> +R: Usama Arif <usama.arif@linux.dev> L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org @@ -19106,6 +19109,7 @@ F: drivers/nfc/ F: include/net/nfc/ F: include/uapi/linux/nfc.h F: net/nfc/ +F: tools/testing/selftests/nci/ NFC VIRTUAL NCI DEVICE DRIVER M: Bongsu Jeon <bongsu.jeon@samsung.com> @@ -20195,7 +20199,7 @@ W: http://www.onsemi.com F: drivers/net/phy/ncn* OP-TEE DRIVER -M: Jens Wiklander <jens.wiklander@linaro.org> +M: Jens Wiklander <jenswi@kernel.org> L: op-tee@lists.trustedfirmware.org (moderated for non-subscribers) S: Maintained F: Documentation/ABI/testing/sysfs-bus-optee-devices @@ -23313,7 +23317,7 @@ L: spacemit@lists.linux.dev S: Maintained W: https://github.com/spacemit-com/linux/wiki C: irc://irc.libera.chat/spacemit -T: git https://github.com/spacemit-com/linux +T: https://git.kernel.org/pub/scm/linux/kernel/git/spacemit/linux.git F: arch/riscv/boot/dts/spacemit/ N: spacemit K: spacemit @@ -23572,7 +23576,7 @@ F: Documentation/devicetree/bindings/media/allwinner,sun8i-a83t-de2-rotate.yaml F: drivers/media/platform/sunxi/sun8i-rotate/ RPMB SUBSYSTEM -M: Jens Wiklander <jens.wiklander@linaro.org> +M: Jens Wiklander <jenswi@kernel.org> L: linux-kernel@vger.kernel.org S: Supported F: drivers/misc/rpmb-core.c @@ -25970,8 +25974,9 @@ F: Documentation/devicetree/bindings/phy/st,stm32mp25-combophy.yaml F: drivers/phy/st/phy-stm32-combophy.c STMMAC ETHERNET DRIVER +M: Maxime Chevallier <maxime.chevallier@bootlin.com> L: netdev@vger.kernel.org -S: Orphan +S: Maintained F: Documentation/networking/device_drivers/ethernet/stmicro/ F: drivers/net/ethernet/stmicro/stmmac/ @@ -26526,7 +26531,7 @@ F: drivers/media/i2c/tw9910.c F: include/media/i2c/tw9910.h TEE SUBSYSTEM -M: Jens Wiklander <jens.wiklander@linaro.org> +M: Jens Wiklander <jenswi@kernel.org> R: Sumit Garg <sumit.garg@kernel.org> L: op-tee@lists.trustedfirmware.org (moderated for non-subscribers) S: Maintained @@ -27927,7 +27932,6 @@ F: drivers/usb/isp1760/* USB LAN78XX ETHERNET DRIVER M: Thangaraj Samynathan <Thangaraj.S@microchip.com> -M: Rengarajan Sundararajan <Rengarajan.S@microchip.com> M: UNGLinuxDriver@microchip.com L: netdev@vger.kernel.org S: Maintained @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index f930396d9dae..870e5291b7db 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -67,7 +67,6 @@ CONFIG_SERIAL_OF_PLATFORM=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_CORE=y -CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_DRM=m CONFIG_DRM_I2C_ADV7511=m diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 6b779dee5ea0..d45e4d335998 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -67,7 +67,6 @@ CONFIG_SERIAL_OF_PLATFORM=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_CORE=y -CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index a89b50d5369d..f986c0205f13 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -67,7 +67,6 @@ CONFIG_SERIAL_OF_PLATFORM=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_CORE=y -CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_DRM=m CONFIG_DRM_I2C_ADV7511=m diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 865fbc19ef03..6e396a9ddb8b 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -61,7 +61,6 @@ CONFIG_SERIAL_8250_DW=y CONFIG_I2C=y # CONFIG_I2C_COMPAT is not set CONFIG_I2C_DESIGNWARE_CORE=y -CONFIG_I2C_DESIGNWARE_PLATFORM=y CONFIG_GPIO_SYSFS=y # CONFIG_HWMON is not set # CONFIG_USB_SUPPORT is not set diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index b2f2c59279a6..2d99dffed0ce 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -22,6 +22,7 @@ #include <linux/irqdomain.h> #include <linux/export.h> #include <linux/of_fdt.h> +#include <linux/string.h> #include <asm/mach_desc.h> #include <asm/setup.h> @@ -43,9 +44,10 @@ static int __init arc_get_cpu_map(const char *name, struct cpumask *cpumask) { unsigned long dt_root = of_get_flat_dt_root(); const char *buf; + int len; - buf = of_get_flat_dt_prop(dt_root, name, NULL); - if (!buf) + buf = of_get_flat_dt_prop(dt_root, name, &len); + if (!buf || !memchr(buf, '\0', len)) return -EINVAL; if (cpulist_parse(buf, cpumask)) diff --git a/arch/arm/mach-ixp4xx/Kconfig b/arch/arm/mach-ixp4xx/Kconfig index cb46802f5ce5..7f812020e082 100644 --- a/arch/arm/mach-ixp4xx/Kconfig +++ b/arch/arm/mach-ixp4xx/Kconfig @@ -14,6 +14,5 @@ menuconfig ARCH_IXP4XX select IXP4XX_TIMER select USB_EHCI_BIG_ENDIAN_DESC select USB_EHCI_BIG_ENDIAN_MMIO - select USE_OF help Support for Intel's IXP4XX (XScale) family of processors. diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig index 66e26990e2c8..c478fb8a6f78 100644 --- a/arch/arm/mach-pxa/Kconfig +++ b/arch/arm/mach-pxa/Kconfig @@ -22,7 +22,6 @@ config MACH_PXA25X_DT select PINCTRL select POWER_SUPPLY select PXA25x - select USE_OF help Include support for Marvell PXA25x based platforms using the device tree. Needn't select any other machine while @@ -33,7 +32,6 @@ config MACH_PXA27X_DT select PINCTRL select POWER_SUPPLY select PXA27x - select USE_OF help Include support for Marvell PXA27x based platforms using the device tree. Needn't select any other machine while @@ -47,7 +45,6 @@ config MACH_PXA3XX_DT select PINCTRL select POWER_SUPPLY select PXA3xx - select USE_OF help Include support for Marvell PXA3xx based platforms using the device tree. Needn't select any other machine while diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi index 8e0c51e496e2..820670dd6042 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi @@ -5355,7 +5355,7 @@ #size-cells = <0>; cpu0_0: cpu@0 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x00000>; @@ -5374,7 +5374,7 @@ }; cpu0_1: cpu@100 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x00100>; @@ -5393,7 +5393,7 @@ }; cpu0_2: cpu@200 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x00200>; @@ -5412,7 +5412,7 @@ }; cpu0_3: cpu@300 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x00300>; @@ -5431,7 +5431,7 @@ }; cpu1_0: cpu@10000 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x10000>; @@ -5450,7 +5450,7 @@ }; cpu1_1: cpu@10100 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x10100>; @@ -5469,7 +5469,7 @@ }; cpu1_2: cpu@10200 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x10200>; @@ -5488,7 +5488,7 @@ }; cpu1_3: cpu@10300 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x10300>; @@ -5507,7 +5507,7 @@ }; cpu2_0: cpu@20000 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x20000>; @@ -5526,7 +5526,7 @@ }; cpu2_1: cpu@20100 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x20100>; @@ -5545,7 +5545,7 @@ }; cpu2_2: cpu@20200 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x20200>; @@ -5564,7 +5564,7 @@ }; cpu2_3: cpu@20300 { - compatible = "arm,cortex-a78"; + compatible = "arm,cortex-a78ae"; device_type = "cpu"; reg = <0x20300>; diff --git a/arch/arm64/boot/dts/nvidia/tegra264.dtsi b/arch/arm64/boot/dts/nvidia/tegra264.dtsi index 2d8e7e37830f..2d2cb1a3d95c 100644 --- a/arch/arm64/boot/dts/nvidia/tegra264.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra264.dtsi @@ -3208,7 +3208,7 @@ }; gpcdma: dma-controller@8400000 { - compatible = "nvidia,tegra264-gpcdma", "nvidia,tegra186-gpcdma"; + compatible = "nvidia,tegra264-gpcdma"; reg = <0x0 0x08400000 0x0 0x210000>; interrupts = <GIC_SPI 584 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 585 IRQ_TYPE_LEVEL_HIGH>, @@ -4070,7 +4070,7 @@ d-cache-sets = <256>; }; - cpu1: cpu@1 { + cpu1: cpu@10000 { compatible = "arm,neoverse-v3ae"; device_type = "cpu"; reg = <0x10000>; diff --git a/arch/arm64/boot/dts/renesas/r8a78000-ironhide.dts b/arch/arm64/boot/dts/renesas/r8a78000-ironhide.dts index d2b3fc08954a..0ab303863155 100644 --- a/arch/arm64/boot/dts/renesas/r8a78000-ironhide.dts +++ b/arch/arm64/boot/dts/renesas/r8a78000-ironhide.dts @@ -107,6 +107,47 @@ reg = <0x0 0x8c400000 0x0 0x02000000>; no-map; }; + + /* DRAM controller inline ECC areas */ + ecc@10cccc0000 { + reg = <0x10 0xcccc0000 0x0 0x33340000>; + no-map; + }; + + ecc@12cccc0000 { + reg = <0x12 0xcccc0000 0x0 0x33340000>; + no-map; + }; + + ecc@14cccc0000 { + reg = <0x14 0xcccc0000 0x0 0x33340000>; + no-map; + }; + + ecc@16cccc0000 { + reg = <0x16 0xcccc0000 0x0 0x33340000>; + no-map; + }; + + ecc@18cccc0000 { + reg = <0x18 0xcccc0000 0x0 0x33340000>; + no-map; + }; + + ecc@1a66660000 { + reg = <0x1a 0x66660000 0x0 0x999a0000>; + no-map; + }; + + ecc@1c66660000 { + reg = <0x1c 0x66660000 0x0 0x999a0000>; + no-map; + }; + + ecc@1e66660000 { + reg = <0x1e 0x66660000 0x0 0x999a0000>; + no-map; + }; }; }; diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index cdf3e8422ea1..012d711034d1 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -388,6 +388,14 @@ struct s1_walk_result { bool failed; }; +static inline void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool s1ptw) +{ + wr->fst = fst; + wr->ptw = s1ptw; + wr->s2 = s1ptw; + wr->failed = true; +} + int __kvm_translate_va(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, struct s1_walk_result *wr, u64 va); int __kvm_find_s1_desc_level(struct kvm_vcpu *vcpu, u64 va, u64 ipa, diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index b8ded434c63f..640f2dc00a8b 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -11,14 +11,6 @@ #include <asm/kvm_mmu.h> #include <asm/lsui.h> -static void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool s1ptw) -{ - wr->fst = fst; - wr->ptw = s1ptw; - wr->s2 = s1ptw; - wr->failed = true; -} - #define S1_MMU_DISABLED (-127) static int get_ia_size(struct s1_walk_info *wi) diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index e688bc5139c1..3c82f392845d 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -2746,17 +2746,33 @@ static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr) (spsr & PSR_MODE32_BIT) || (vcpu_el2_tge_is_set(vcpu) && (mode == PSR_MODE_EL1t || mode == PSR_MODE_EL1h))) { + u64 mask; + /* - * The guest is playing with our nerves. Preserve EL, SP, - * masks, flags from the existing PSTATE, and set IL. - * The HW will then generate an Illegal State Exception - * immediately after ERET. + * On an illegal exception return, the flags and masks are + * taken from the SPSR while PSTATE.{EL,SP,nRW} and, if + * FEAT_GCS, PSTATE.EXLOCK are unchanged (R_VWJHB). Set IL + * so the HW generates an Illegal State Exception right + * after ERET. */ - spsr = *vcpu_cpsr(vcpu); + mask = PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | + PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT; + + if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR1_EL1, PAN, IMP)) + mask |= PSR_PAN_BIT; + if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, NMI, IMP)) + mask |= ALLINT_ALLINT; + /* FEAT_SPE_EXC and FEAT_TRBE_EXC also gate PSTATE.PM one day... */ + if (kvm_has_feat(vcpu->kvm, ID_AA64DFR1_EL1, EBEP, IMP)) + mask |= BIT_ULL(32); /* SPSR_ELx.PM */ + + spsr &= mask; - spsr &= (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | - PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT | - PSR_MODE_MASK | PSR_MODE32_BIT); + mask = PSR_MODE_MASK | PSR_MODE32_BIT; + if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, GCS, IMP)) + mask |= BIT_ULL(34); /* PSTATE.EXLOCK */ + + spsr |= *vcpu_cpsr(vcpu) & mask; spsr |= PSR_IL_BIT; } @@ -2784,7 +2800,7 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) * ERET handling, and the guest will have a little surprise. */ if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE) && !(spsr & PSR_IL_BIT)) { - esr &= ESR_ELx_ERET_ISS_ERETA; + esr &= (ESR_ELx_ERET_ISS_ERETA | ESR_ELx_IL); esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_FPAC); kvm_inject_nested_sync(vcpu, esr); return; @@ -2826,6 +2842,7 @@ static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2, break; case except_type_serror: kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SERR); + vcpu_write_sys_reg(vcpu, esr_el2, ESR_EL2); break; default: WARN_ONCE(1, "Unsupported EL2 exception injection %d\n", type); @@ -2950,6 +2967,6 @@ int kvm_inject_nested_serror(struct kvm_vcpu *vcpu, u64 esr) * vSError injection. Manually populate EC for an emulated SError * exception. */ - esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SERROR); + esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SERROR) | ESR_ELx_IL; return kvm_inject_nested(vcpu, esr, except_type_serror); } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 18131e395e24..4bf624a49591 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -448,16 +448,19 @@ static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) static inline bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) { + u64 spsr; + *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); arm64_mops_reset_regs(vcpu_gp_regs(vcpu), vcpu->arch.fault.esr_el2); write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); /* * Finish potential single step before executing the prologue - * instruction. + * instruction. Modify the hardware SPSR_EL2 directly, as vcpu_cpsr() + * may hold a synthetic (vEL2) value for a guest hypervisor. */ - *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; - write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR); + spsr = read_sysreg_el2(SYS_SPSR); + write_sysreg_el2(spsr & ~DBG_SPSR_SS, SYS_SPSR); return true; } @@ -602,8 +605,6 @@ static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) return false; break; case ESR_ELx_EC_SYS64: - if (WARN_ON_ONCE(!is_hyp_ctxt(vcpu))) - return false; fallthrough; case ESR_ELx_EC_SVE: if (!sve_guest) diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index 1af722771178..a327c2bbb6b6 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -352,7 +352,7 @@ static u32 __ffa_host_share_ranges(struct ffa_mem_region_addr_range *ranges, u64 sz = (u64)range->pg_cnt * FFA_PAGE_SIZE; u64 pfn = hyp_phys_to_pfn(range->address); - if (!PAGE_ALIGNED(sz)) + if (!PAGE_ALIGNED(sz | range->address)) break; if (__pkvm_host_share_ffa(pfn, sz / PAGE_SIZE)) @@ -372,7 +372,7 @@ static u32 __ffa_host_unshare_ranges(struct ffa_mem_region_addr_range *ranges, u64 sz = (u64)range->pg_cnt * FFA_PAGE_SIZE; u64 pfn = hyp_phys_to_pfn(range->address); - if (!PAGE_ALIGNED(sz)) + if (!PAGE_ALIGNED(sz | range->address)) break; if (__pkvm_host_unshare_ffa(pfn, sz / PAGE_SIZE)) @@ -476,11 +476,12 @@ static void __do_ffa_mem_xfer(const u64 func_id, DECLARE_REG(u32, fraglen, ctxt, 2); DECLARE_REG(u64, addr_mbz, ctxt, 3); DECLARE_REG(u32, npages_mbz, ctxt, 4); + u32 offset, nr_ranges, checked_offset, em_mem_access_off; struct ffa_mem_region_attributes *ep_mem_access; struct ffa_composite_mem_region *reg; struct ffa_mem_region *buf; - u32 offset, nr_ranges, checked_offset; int ret = 0; + size_t mem_region_len = FFA_MEM_REGION_SZ(hyp_ffa_version); if (addr_mbz || npages_mbz || fraglen > len || fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) { @@ -488,8 +489,7 @@ static void __do_ffa_mem_xfer(const u64 func_id, goto out; } - if (fraglen < sizeof(struct ffa_mem_region) + - sizeof(struct ffa_mem_region_attributes)) { + if (fraglen < mem_region_len + ffa_emad_size_get(hyp_ffa_version)) { ret = FFA_RET_INVALID_PARAMETERS; goto out; } @@ -508,8 +508,13 @@ static void __do_ffa_mem_xfer(const u64 func_id, buf = hyp_buffers.tx; memcpy(buf, host_buffers.tx, fraglen); - ep_mem_access = (void *)buf + - ffa_mem_desc_offset(buf, 0, hyp_ffa_version); + em_mem_access_off = ffa_mem_desc_offset(buf, 0, hyp_ffa_version); + if ((u64)em_mem_access_off + ffa_emad_size_get(hyp_ffa_version) > fraglen) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + ep_mem_access = (void *)buf + em_mem_access_off; offset = ep_mem_access->composite_off; if (!offset || buf->ep_count != 1 || buf->sender_id != HOST_FFA_ID) { ret = FFA_RET_INVALID_PARAMETERS; @@ -574,9 +579,9 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res, DECLARE_REG(u32, handle_lo, ctxt, 1); DECLARE_REG(u32, handle_hi, ctxt, 2); DECLARE_REG(u32, flags, ctxt, 3); + u32 offset, len, fraglen, fragoff, em_mem_access_off; struct ffa_mem_region_attributes *ep_mem_access; struct ffa_composite_mem_region *reg; - u32 offset, len, fraglen, fragoff; struct ffa_mem_region *buf; int ret = 0; u64 handle; @@ -599,16 +604,22 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res, len = res->a1; fraglen = res->a2; - ep_mem_access = (void *)buf + - ffa_mem_desc_offset(buf, 0, hyp_ffa_version); + em_mem_access_off = ffa_mem_desc_offset(buf, 0, hyp_ffa_version); + if ((u64)em_mem_access_off + ffa_emad_size_get(hyp_ffa_version) > fraglen) { + ret = FFA_RET_INVALID_PARAMETERS; + ffa_rx_release(res); + goto out_unlock; + } + + ep_mem_access = (void *)buf + em_mem_access_off; offset = ep_mem_access->composite_off; /* * We can trust the SPMD to get this right, but let's at least * check that we end up with something that doesn't look _completely_ * bogus. */ - if (WARN_ON(offset > len || - fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE)) { + if (offset + CONSTITUENTS_OFFSET(0) > len || + fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) { ret = FFA_RET_ABORTED; ffa_rx_release(res); goto out_unlock; @@ -636,11 +647,16 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res, ffa_rx_release(res); } + reg = (void *)buf + offset; + if (offset + CONSTITUENTS_OFFSET(reg->addr_range_cnt) > len) { + ret = FFA_RET_ABORTED; + goto out_unlock; + } + ffa_mem_reclaim(res, handle_lo, handle_hi, flags); if (res->a0 != FFA_SUCCESS) goto out_unlock; - reg = (void *)buf + offset; /* If the SPMD was happy, then we should be too. */ WARN_ON(ffa_host_unshare_ranges(reg->constituents, reg->addr_range_cnt)); @@ -864,7 +880,7 @@ out_unlock: bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id) { - struct arm_smccc_1_2_regs res; + struct arm_smccc_1_2_regs res = {0}; /* * There's no way we can tell what a non-standard SMC call might diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 3b2c4fbc34d8..24d6f164129a 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -1056,7 +1056,8 @@ static u64 __pkvm_memshare_page_req(struct kvm_vcpu *vcpu, u64 ipa) /* Fake up a data abort (level 3 translation fault on write) */ vcpu->arch.fault.esr_el2 = (ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT) | - ESR_ELx_WNR | ESR_ELx_FSC_FAULT | + ESR_ELx_IL | ESR_ELx_WNR | + ESR_ELx_FSC_FAULT | FIELD_PREP(ESR_ELx_FSC_LEVEL, 3); /* Shuffle the IPA around into the HPFAR */ diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 8c3fbb413a06..b1411fb54139 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -268,6 +268,7 @@ static void inject_sync64(struct kvm_vcpu *vcpu, u64 esr) write_sysreg_el1(esr, SYS_ESR); write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR); + write_sysreg_el1(read_sysreg_el2(SYS_SPSR), SYS_SPSR); write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR); } @@ -278,7 +279,7 @@ static void inject_sync64(struct kvm_vcpu *vcpu, u64 esr) */ static void inject_undef64(struct kvm_vcpu *vcpu) { - inject_sync64(vcpu, (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT)); + inject_sync64(vcpu, (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT) | ESR_ELx_IL); } static u64 read_id_reg(const struct kvm_vcpu *vcpu, diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 91a7dfad6686..b74dd5ce1efd 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -1370,16 +1370,19 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, if (prot & KVM_PGTABLE_PROT_W) set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; - ret = stage2_set_xn_attr(prot, &xn); - if (ret) - return ret; + if (prot & KVM_PGTABLE_PROT_X) { + ret = stage2_set_xn_attr(prot, &xn); + if (ret) + return ret; - set |= xn & KVM_PTE_LEAF_ATTR_HI_S2_XN; - clr |= ~xn & KVM_PTE_LEAF_ATTR_HI_S2_XN; + set |= xn & KVM_PTE_LEAF_ATTR_HI_S2_XN; + clr |= ~xn & KVM_PTE_LEAF_ATTR_HI_S2_XN; + } ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, flags); if (!ret || ret == -EAGAIN) - kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level); + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, + (ret == -EAGAIN) ? TLBI_TTL_UNKNOWN : level); return ret; } diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 89982bd3345f..d6c4fc16f879 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -138,11 +138,10 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr pend_sync_exception(vcpu); /* - * Build an {i,d}abort, depending on the level and the - * instruction set. Report an external synchronous abort. + * Build an {i,d}abort, depending on the level. + * Report an external synchronous abort. */ - if (kvm_vcpu_trap_il_is32bit(vcpu)) - esr |= ESR_ELx_IL; + esr |= ESR_ELx_IL; /* * Here, the guest runs in AArch64 mode when in EL1. If we get @@ -170,14 +169,7 @@ void kvm_inject_sync(struct kvm_vcpu *vcpu, u64 esr) static void inject_undef64(struct kvm_vcpu *vcpu) { - u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); - - /* - * Build an unknown exception, depending on the instruction - * set. - */ - if (kvm_vcpu_trap_il_is32bit(vcpu)) - esr |= ESR_ELx_IL; + u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT) | ESR_ELx_IL; kvm_inject_sync(vcpu, esr); } @@ -389,7 +381,7 @@ int kvm_inject_serror_esr(struct kvm_vcpu *vcpu, u64 esr) */ if (!serror_is_masked(vcpu)) { pend_serror_exception(vcpu); - esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SERROR); + esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SERROR) | ESR_ELx_IL; vcpu_write_sys_reg(vcpu, esr, exception_esr_elx(vcpu)); return 1; } diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c index e2285ed8c91d..d1c3a352d5a2 100644 --- a/arch/arm64/kvm/mmio.c +++ b/arch/arm64/kvm/mmio.c @@ -126,6 +126,10 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu) len = kvm_vcpu_dabt_get_as(vcpu); data = kvm_mmio_read_buf(run->mmio.data, len); + trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, + &data); + data = vcpu_data_host_to_guest(vcpu, data, len); + if (kvm_vcpu_dabt_issext(vcpu) && len < sizeof(unsigned long)) { mask = 1U << ((len * 8) - 1); @@ -135,9 +139,6 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu) if (!kvm_vcpu_dabt_issf(vcpu)) data = data & 0xffffffff; - trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, - &data); - data = vcpu_data_host_to_guest(vcpu, data, len); vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu), data); } diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index fb54f6dad995..dfb96edbdc43 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -24,6 +24,7 @@ struct vncr_tlb { struct s1_walk_result wr; u64 hpa; + bool hpa_writable; /* -1 when not mapped on a CPU */ int cpu; @@ -1401,15 +1402,19 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem) gfn = vt->wr.pa >> PAGE_SHIFT; memslot = gfn_to_memslot(vcpu->kvm, gfn); - if (!memslot) + if (!memslot) { + fail_s1_walk(&vt->wr, ESR_ELx_FSC_EXTABT, false); return -EFAULT; + } *is_gmem = kvm_slot_has_gmem(memslot); if (!*is_gmem) { pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0, &writable, &page); - if (is_error_noslot_pfn(pfn) || (write_fault && !writable)) + if (is_error_noslot_pfn(pfn)) { + fail_s1_walk(&vt->wr, ESR_ELx_FSC_EXTABT, false); return -EFAULT; + } } else { ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, &page, NULL); if (ret) { @@ -1417,6 +1422,19 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem) write_fault, false, false); return ret; } + + writable = !(memslot->flags & KVM_MEM_READONLY); + } + + /* + * FIXME: This check is too restrictive as KVM allows cacheable memory + * attributes for PFNMAP VMAs that have cacheable attributes in host + * stage-1. + */ + if (!pfn_is_map_memory(pfn)) { + kvm_release_faultin_page(vcpu->kvm, page, true, false); + fail_s1_walk(&vt->wr, ESR_ELx_FSC_EXTABT, false); + return -EINVAL; } scoped_guard(write_lock, &vcpu->kvm->mmu_lock) { @@ -1427,116 +1445,100 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem) vt->gva = va; vt->hpa = pfn << PAGE_SHIFT; + vt->hpa_writable = writable; vt->valid = true; vt->cpu = -1; kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu); - kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw); + kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw && vt->hpa_writable); } - if (vt->wr.pw) + if (vt->wr.pw && vt->hpa_writable) mark_page_dirty(vcpu->kvm, gfn); return 0; } -static void inject_vncr_perm(struct kvm_vcpu *vcpu) +static void handle_vncr_perm(struct kvm_vcpu *vcpu) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; u64 esr = kvm_vcpu_get_esr(vcpu); + u64 fsc; + + /* + * Promote to an external abort if the stage-1 permits writes but the + * HPA is read-only (e.g. RO memslot). + */ + if (kvm_is_write_fault(vcpu) && vt->wr.pw && !vt->hpa_writable) + fsc = ESR_ELx_FSC_EXTABT; + /* + * Otherwise, inject a permission fault using the guest's translation + * level rather than the host's. + */ + else + fsc = ESR_ELx_FSC_PERM_L(vt->wr.level); - /* Adjust the fault level to reflect that of the guest's */ esr &= ~ESR_ELx_FSC; - esr |= FIELD_PREP(ESR_ELx_FSC, - ESR_ELx_FSC_PERM_L(vt->wr.level)); + esr |= FIELD_PREP(ESR_ELx_FSC, fsc); kvm_inject_nested_sync(vcpu, esr); } -static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu) -{ - struct vncr_tlb *vt = vcpu->arch.vncr_tlb; - - lockdep_assert_held_read(&vcpu->kvm->mmu_lock); - - if (!vt->valid) - return false; - - if (read_vncr_el2(vcpu) != vt->gva) - return false; - - if (vt->wr.nG) - return get_asid_by_regime(vcpu, TR_EL20) == vt->wr.asid; - - return true; -} - int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; u64 esr = kvm_vcpu_get_esr(vcpu); + bool is_gmem = false; + bool perm; + int ret; WARN_ON_ONCE(!(esr & ESR_ELx_VNCR)); if (kvm_vcpu_abt_issea(vcpu)) return kvm_handle_guest_sea(vcpu); - if (esr_fsc_is_permission_fault(esr)) { - inject_vncr_perm(vcpu); - } else if (esr_fsc_is_translation_fault(esr)) { - bool valid, is_gmem = false; - int ret; - - scoped_guard(read_lock, &vcpu->kvm->mmu_lock) - valid = kvm_vncr_tlb_lookup(vcpu); - - if (!valid) - ret = kvm_translate_vncr(vcpu, &is_gmem); - else - ret = -EPERM; - - switch (ret) { - case -EAGAIN: - /* Let's try again... */ - break; - case -ENOMEM: - /* - * For guest_memfd, this indicates that it failed to - * create a folio to back the memory. Inform userspace. - */ - if (is_gmem) - return 0; - /* Otherwise, let's try again... */ - break; - case -EFAULT: - case -EIO: - case -EHWPOISON: - if (is_gmem) - return 0; - fallthrough; - case -EINVAL: - case -ENOENT: - case -EACCES: - /* - * Translation failed, inject the corresponding - * exception back to EL2. - */ - BUG_ON(!vt->wr.failed); + if (!esr_fsc_is_translation_fault(esr) && !esr_fsc_is_permission_fault(esr)) { + KVM_BUG(1, vcpu->kvm, "Unhandled VNCR abort, ESR=%llx\n", esr); + return -EIO; + } - esr &= ~ESR_ELx_FSC; - esr |= FIELD_PREP(ESR_ELx_FSC, vt->wr.fst); + ret = kvm_translate_vncr(vcpu, &is_gmem); + switch (ret) { + case -EAGAIN: + /* Let's try again... */ + return 1; + case -ENOMEM: + /* + * For guest_memfd, this indicates that it failed to + * create a folio to back the memory. Inform userspace. + */ + if (is_gmem) + return 0; + /* Otherwise, let's try again... */ + break; + case -EFAULT: + case -EIO: + case -EHWPOISON: + if (is_gmem) + return 0; + fallthrough; + case -EINVAL: + case -ENOENT: + case -EACCES: + /* + * Translation failed, inject the corresponding + * exception back to EL2. + */ + esr &= ~ESR_ELx_FSC; + esr |= FIELD_PREP(ESR_ELx_FSC, vt->wr.fst); - kvm_inject_nested_sync(vcpu, esr); - break; - case -EPERM: - /* Hack to deal with POE until we get kernel support */ - inject_vncr_perm(vcpu); - break; - case 0: - break; - } - } else { - WARN_ONCE(1, "Unhandled VNCR abort, ESR=%llx\n", esr); + kvm_inject_nested_sync(vcpu, esr); + break; + case 0: + perm = kvm_is_write_fault(vcpu) ? vt->wr.pw && vt->hpa_writable : vt->wr.pr; + if (!perm) + handle_vncr_perm(vcpu); + break; } return 1; @@ -1574,7 +1576,7 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu) vt->cpu = smp_processor_id(); - if (vt->wr.pw && vt->wr.pr) + if (vt->hpa_writable && vt->wr.pw && vt->wr.pr) prot = PAGE_KERNEL; else if (vt->wr.pr) prot = PAGE_KERNEL_RO; diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index 053e4f733e4b..428723b1b0f5 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -352,7 +352,7 @@ static int __pkvm_pgtable_stage2_reclaim(struct kvm_pgtable *pgt, u64 start, u64 page = pfn_to_page(mapping->pfn); WARN_ON_ONCE(mapping->nr_pages != 1); unpin_user_pages_dirty_lock(&page, 1, true); - account_locked_vm(current->mm, 1, false); + account_locked_vm(kvm->mm, 1, false); pkvm_mapping_remove(mapping, &pgt->pkvm_mappings); kfree(mapping); } diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 4477f870c7b3..740b39875728 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -508,6 +508,8 @@ static struct vgic_its *__vgic_doorbell_to_its(struct kvm *kvm, gpa_t db) struct kvm_io_device *kvm_io_dev; struct vgic_io_device *iodev; + guard(srcu)(&kvm->srcu); + kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, db); if (!kvm_io_dev) return ERR_PTR(-EINVAL); diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 5a4768d8cd4f..ccb7e3a90cd0 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -203,6 +203,7 @@ void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { if (irq_is_lpi(vcpu->kvm, irq->intid)) { raw_spin_lock(&irq->irq_lock); + irq->pending_latch = false; list_del(&irq->ap_list); irq->vcpu = NULL; raw_spin_unlock(&irq->irq_lock); @@ -792,7 +793,11 @@ retry: continue; } - /* This interrupt looks like it has to be migrated. */ + /* + * This interrupt looks like it has to be migrated, + * make sure it is kept alive while locks are dropped. + */ + vgic_get_irq_ref(irq); raw_spin_unlock(&irq->irq_lock); raw_spin_unlock(&vgic_cpu->ap_list_lock); @@ -815,15 +820,16 @@ retry: raw_spin_lock(&irq->irq_lock); /* - * If the affinity has been preserved, move the - * interrupt around. Otherwise, it means things have - * changed while the interrupt was unlocked, and we - * need to replay this. + * If the interrupt is still ours and its affinity has + * been preserved, move it around. Otherwise, it means + * things have changed while the interrupt was unlocked + * (it may even have been taken off the list with its + * affinity left untouched), and we need to replay this. * * In all cases, we cannot trust the list not to have * changed, so we restart from the beginning. */ - if (target_vcpu == vgic_target_oracle(irq)) { + if (irq->vcpu == vcpu && target_vcpu == vgic_target_oracle(irq)) { struct vgic_cpu *new_cpu = &target_vcpu->arch.vgic_cpu; list_del(&irq->ap_list); @@ -836,6 +842,8 @@ retry: raw_spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock); raw_spin_unlock(&vcpuA->arch.vgic_cpu.ap_list_lock); + deleted_lpis |= vgic_put_irq_norelease(vcpu->kvm, irq); + if (target_vcpu_needs_kick) { kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu); kvm_vcpu_kick(target_vcpu); diff --git a/arch/m68k/include/asm/page_mm.h b/arch/m68k/include/asm/page_mm.h index ed782609ca41..0971a0651d49 100644 --- a/arch/m68k/include/asm/page_mm.h +++ b/arch/m68k/include/asm/page_mm.h @@ -55,10 +55,12 @@ static inline void clear_page(void *page) #define clear_user_page(addr, vaddr, page) \ do { clear_page(addr); \ flush_dcache_page(page); \ + (void)(vaddr); \ } while (0) #define copy_user_page(to, from, vaddr, page) \ do { copy_page(to, from); \ flush_dcache_page(page); \ + (void)(vaddr); \ } while (0) extern unsigned long m68k_memoffset; diff --git a/arch/powerpc/include/asm/preempt.h b/arch/powerpc/include/asm/preempt.h deleted file mode 100644 index 000e2b9681f3..000000000000 --- a/arch/powerpc/include/asm/preempt.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_POWERPC_PREEMPT_H -#define __ASM_POWERPC_PREEMPT_H - -#include <asm-generic/preempt.h> - -#if defined(CONFIG_PREEMPT_DYNAMIC) -#include <linux/jump_label.h> -DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); -#define need_irq_preemption() \ - (static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) -#else -#define need_irq_preemption() (IS_ENABLED(CONFIG_PREEMPTION)) -#endif - -#endif /* __ASM_POWERPC_PREEMPT_H */ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 7b8c56962c31..49039074b33f 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -537,7 +537,7 @@ static inline void __user *mask_user_address(const void __user *ptr) if (IS_ENABLED(CONFIG_PPC64)) return mask_user_address_simple(ptr); - if (IS_ENABLED(CONFIG_E500)) + if (IS_ENABLED(CONFIG_PPC_E500)) return mask_user_address_isel(ptr); if (TASK_SIZE <= UL(SZ_2G) && border >= UL(SZ_2G)) return mask_user_address_simple(ptr); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 3af6c06af02f..e5853daa6a48 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -704,6 +704,15 @@ static void __init cpufeatures_setup_start(u32 isa) if (isa >= ISA_V3_1) { cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_31; cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_1; + + /* + * CPU_FTR_P11_PVR is a kernel-internal flag to identify + * Power11 and later processors. While ISA v3.1 is supported + * by Power10+, this flag specifically indicates Power11+ + * for code that needs to distinguish between P10 and P11. + */ + if (PVR_VER(mfspr(SPRN_PVR)) >= PVR_POWER11) + cur_cpu_spec->cpu_features |= CPU_FTR_P11_PVR; } } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 3460d1a5a97c..11145c40183d 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -377,7 +377,6 @@ void vtime_task_switch(struct task_struct *prev) } } -#ifdef CONFIG_NO_HZ_COMMON /** * vtime_reset - Fast forward vtime entry clocks * @@ -394,6 +393,7 @@ void vtime_reset(void) #endif } +#ifdef CONFIG_NO_HZ_COMMON /** * vtime_dyntick_start - Inform vtime about entry to idle-dynticks * @@ -933,6 +933,7 @@ static void __init set_decrementer_max(void) static void __init init_decrementer_clockevent(void) { register_decrementer_clockevent(smp_processor_id()); + vtime_reset(); } void secondary_cpu_time_init(void) @@ -948,6 +949,7 @@ void secondary_cpu_time_init(void) /* FIME: Should make unrelated change to move snapshot_timebase * call here ! */ register_decrementer_clockevent(smp_processor_id()); + vtime_reset(); } /* diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index 57e897b60db8..cc9fb72cb4eb 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -46,7 +46,7 @@ int exit_vmx_usercopy(void) * set and we are preemptible. The hack here is to schedule a * decrementer to fire here and reschedule for us if necessary. */ - if (need_irq_preemption() && need_resched()) + if (need_resched()) set_dec(1); return 0; } diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c index 757811155587..c11deb2f50ed 100644 --- a/arch/powerpc/platforms/85xx/common.c +++ b/arch/powerpc/platforms/85xx/common.c @@ -42,6 +42,8 @@ static const struct of_device_id mpc85xx_common_ids[] __initconst = { { .compatible = "fsl,qoriq-pcie-v2.3", }, { .compatible = "fsl,qoriq-pcie-v2.2", }, { .compatible = "fsl,fman", }, + /* IFC NAND and NOR controllers */ + { .compatible = "fsl,ifc", }, {}, }; diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index f6de8c1169d5..de7494748fec 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -268,10 +268,12 @@ static int spufs_mem_mmap_access(struct vm_area_struct *vma, if (write && !(vma->vm_flags & VM_WRITE)) return -EACCES; + if (offset >= LS_SIZE) + return -EFAULT; if (spu_acquire(ctx)) return -EINTR; - if ((offset + len) > vma->vm_end) - len = vma->vm_end - offset; + if ((offset + len) > LS_SIZE) + len = LS_SIZE - offset; local_store = ctx->ops->get_ls(ctx); if (write) memcpy_toio(local_store + offset, buf, len); diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index f7052b131a4c..74910ce3a541 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -154,6 +154,7 @@ config HV_PERF_CTRS config VPA_PMU tristate "VPA PMU events" depends on KVM_BOOK3S_64_HV && HV_PERF_CTRS + default m help Enable access to the VPA PMU counters via perf. This enables code that support measurement for KVM on PowerVM(KoP) feature. diff --git a/arch/powerpc/platforms/pseries/papr_platform_attributes.c b/arch/powerpc/platforms/pseries/papr_platform_attributes.c index c6159870de0e..9c3758aa54c6 100644 --- a/arch/powerpc/platforms/pseries/papr_platform_attributes.c +++ b/arch/powerpc/platforms/pseries/papr_platform_attributes.c @@ -271,11 +271,9 @@ retry: esi_buf_size = ESI_HDR_SIZE + (CURR_MAX_ESI_ATTRS * max_esi_attrs); temp_esi_buf = krealloc(esi_buf, esi_buf_size, GFP_KERNEL); - if (temp_esi_buf) - esi_buf = temp_esi_buf; - else - return -ENOMEM; - + if (!temp_esi_buf) + goto out_free_esi_buf; + esi_buf = temp_esi_buf; goto retry; } diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c0a6992933e4..f7028caaeae0 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -157,7 +157,7 @@ config RISCV select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS if MMU select HAVE_DYNAMIC_FTRACE if MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) - select FUNCTION_ALIGNMENT_4B if HAVE_DYNAMIC_FTRACE && RISCV_ISA_C + select FUNCTION_ALIGNMENT_4B if DYNAMIC_FTRACE && RISCV_ISA_C select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS if HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS if (DYNAMIC_FTRACE_WITH_ARGS && !CFI) select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 8cfe59483a8f..c2b0a2928f06 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -40,7 +40,7 @@ do { \ flush_icache_mm(vma->vm_mm, 0); \ } while (0) -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) /* This is accessed in assembly code. cpumask_var_t would be too complex. */ extern DECLARE_BITMAP(new_valid_map_cpus, NR_CPUS); extern char _end[]; @@ -56,7 +56,8 @@ static inline void mark_new_valid_map(void) #define flush_cache_vmap flush_cache_vmap static inline void flush_cache_vmap(unsigned long start, unsigned long end) { - if (is_vmalloc_or_module_addr((void *)start)) + if (is_vmalloc_or_module_addr((void *)start) || + (start >= VMEMMAP_START && end <= VMEMMAP_END)) mark_new_valid_map(); } #define flush_cache_vmap_early(start, end) local_flush_tlb_kernel_range(start, end) diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index 09bb5f57a9d3..92d5f831f349 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -102,12 +102,14 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_ar(addr)) #define readsw(addr, buffer, count) __readsw(addr, buffer, count) #define readsl(addr, buffer, count) __readsl(addr, buffer, count) +#ifdef CONFIG_HAS_IOPORT __io_reads_ins(ins, u8, b, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr)) #define insb(addr, buffer, count) __insb(PCI_IOBASE + (addr), buffer, count) #define insw(addr, buffer, count) __insw(PCI_IOBASE + (addr), buffer, count) #define insl(addr, buffer, count) __insl(PCI_IOBASE + (addr), buffer, count) +#endif __io_writes_outs(writes, u8, b, __io_bw(), __io_aw()) __io_writes_outs(writes, u16, w, __io_bw(), __io_aw()) @@ -116,26 +118,32 @@ __io_writes_outs(writes, u32, l, __io_bw(), __io_aw()) #define writesw(addr, buffer, count) __writesw(addr, buffer, count) #define writesl(addr, buffer, count) __writesl(addr, buffer, count) +#ifdef CONFIG_HAS_IOPORT __io_writes_outs(outs, u8, b, __io_pbw(), __io_paw()) __io_writes_outs(outs, u16, w, __io_pbw(), __io_paw()) __io_writes_outs(outs, u32, l, __io_pbw(), __io_paw()) #define outsb(addr, buffer, count) __outsb(PCI_IOBASE + (addr), buffer, count) #define outsw(addr, buffer, count) __outsw(PCI_IOBASE + (addr), buffer, count) #define outsl(addr, buffer, count) __outsl(PCI_IOBASE + (addr), buffer, count) +#endif #ifdef CONFIG_64BIT __io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr)) #define readsq(addr, buffer, count) __readsq(addr, buffer, count) +#ifdef CONFIG_HAS_IOPORT __io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr)) #define insq(addr, buffer, count) __insq(PCI_IOBASE + (addr), buffer, count) +#endif __io_writes_outs(writes, u64, q, __io_bw(), __io_aw()) #define writesq(addr, buffer, count) __writesq(addr, buffer, count) +#ifdef CONFIG_HAS_IOPORT __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) #define outsq(addr, buffer, count) __outsq(PCI_IOBASE + (addr), buffer, count) #endif +#endif #include <asm-generic/io.h> diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 60017ceec9d2..e2d5808169e4 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -209,13 +209,13 @@ struct kvm_vcpu_arch { /* * VCPU interrupts * - * We have a lockless approach for tracking pending VCPU interrupts - * implemented using atomic bitops. The irqs_pending bitmap represent - * pending interrupts whereas irqs_pending_mask represent bits changed - * in irqs_pending. Our approach is modeled around multiple producer - * and single consumer problem where the consumer is the VCPU itself. + * The irqs_pending bitmap represents pending interrupts whereas + * irqs_pending_mask represents bits changed in irqs_pending. Updates + * to these bitmaps are serialized so vcpu interrupt sync/flush cannot + * drop a newly injected interrupt while syncing guest-visible HVIP. */ #define KVM_RISCV_VCPU_NR_IRQS 64 + raw_spinlock_t irqs_pending_lock; DECLARE_BITMAP(irqs_pending, KVM_RISCV_VCPU_NR_IRQS); DECLARE_BITMAP(irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 08df724e13b9..d799c4e56f80 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -137,7 +137,7 @@ SYM_CODE_START(handle_exception) .Lrestore_kernel_tpsp: csrr tp, CSR_SCRATCH -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) /* * The RISC-V kernel does not flush TLBs on all CPUS after each new * vmalloc mapping or kfence_unprotect(), which may result in diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index 1659d31fd288..caf6762427c8 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -450,6 +450,7 @@ static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs, if (cpusetsize > cpumask_size()) cpusetsize = cpumask_size(); + cpumask_clear(&cpus); ret = copy_from_user(&cpus, cpus_user, cpusetsize); if (ret) return -EFAULT; diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index a842dc034571..43ee881f6c6f 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -69,9 +69,9 @@ CPPFLAGS_$(vdso_lds) += -DHAS_VGETTIMEOFDAY endif # Disable -pg to prevent insert call site -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) -CFLAGS_REMOVE_getrandom.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) -CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_LTO) +CFLAGS_REMOVE_getrandom.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_LTO) +CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_LTO) # Force dependency $(obj)/$(vdso_o): $(obj)/$(vdso_so) diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S index e82987dc3739..d6f96b1abe40 100644 --- a/arch/riscv/kernel/vdso/rt_sigreturn.S +++ b/arch/riscv/kernel/vdso/rt_sigreturn.S @@ -7,11 +7,19 @@ #include <asm/unistd.h> #include <asm/assembler.h> +/* + * WARNING: Do NOT add a CFI landing pad at the start of this function. + * Unwinders such as libgcc identify the sigreturn trampoline by matching the + * instruction sequence. Adding a landing pad here would break unwinding from + * signal handlers. + * + * This trampoline is used only for signal return and not via an indirect + * call/jump from userspace, so adding CFI landing pad is unnecessary. + */ .text SYM_FUNC_START(__vdso_rt_sigreturn) .cfi_startproc .cfi_signal_frame - vdso_lpad li a7, __NR_rt_sigreturn ecall .cfi_endproc diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index bafb009c5ce5..9a653b4ad40a 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -53,12 +53,15 @@ void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu) struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; unsigned long mask, val; + lockdep_assert_held(&vcpu->arch.irqs_pending_lock); + if (!kvm_riscv_aia_available()) return; - if (READ_ONCE(vcpu->arch.irqs_pending_mask[1])) { - mask = xchg_acquire(&vcpu->arch.irqs_pending_mask[1], 0); - val = READ_ONCE(vcpu->arch.irqs_pending[1]) & mask; + mask = vcpu->arch.irqs_pending_mask[1]; + if (mask) { + vcpu->arch.irqs_pending_mask[1] = 0; + val = vcpu->arch.irqs_pending[1] & mask; csr->hviph &= ~mask; csr->hviph |= val; @@ -69,6 +72,8 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + lockdep_assert_held(&vcpu->arch.irqs_pending_lock); + if (kvm_riscv_aia_available()) csr->vsieh = ncsr_read(CSR_VSIEH); } @@ -77,13 +82,22 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) { unsigned long seip; +#ifdef CONFIG_32BIT + unsigned long flags; + bool pending; +#endif if (!kvm_riscv_aia_available()) return false; #ifdef CONFIG_32BIT - if (READ_ONCE(vcpu->arch.irqs_pending[1]) & - (vcpu->arch.aia_context.guest_csr.vsieh & upper_32_bits(mask))) + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + pending = vcpu->arch.irqs_pending[1] & + (vcpu->arch.aia_context.guest_csr.vsieh & + upper_32_bits(mask)); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); + + if (pending) return true; #endif @@ -207,6 +221,9 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); +#ifdef CONFIG_32BIT + unsigned long flags; +#endif if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) return -ENOENT; @@ -219,8 +236,12 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, ((unsigned long *)csr)[reg_num] = val; #ifdef CONFIG_32BIT - if (reg_num == KVM_REG_RISCV_CSR_AIA_REG(siph)) - WRITE_ONCE(vcpu->arch.irqs_pending_mask[1], 0); + if (reg_num == KVM_REG_RISCV_CSR_AIA_REG(siph)) { + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + vcpu->arch.irqs_pending_mask[1] = 0; + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, + flags); + } #endif } diff --git a/arch/riscv/kvm/gstage.c b/arch/riscv/kvm/gstage.c index c4c3b79567f1..b0474fcf065a 100644 --- a/arch/riscv/kvm/gstage.c +++ b/arch/riscv/kvm/gstage.c @@ -5,11 +5,13 @@ */ #include <linux/bitops.h> +#include <linux/cpufeature.h> #include <linux/errno.h> #include <linux/kvm_host.h> #include <linux/module.h> #include <linux/pgtable.h> #include <asm/kvm_gstage.h> +#include <asm/hwcap.h> #ifdef CONFIG_64BIT unsigned long kvm_riscv_gstage_max_pgd_levels __ro_after_init = 3; @@ -171,8 +173,10 @@ int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage, } if (pte_val(*ptep) != pte_val(map->pte)) { + bool was_invalid = !pte_val(*ptep); set_pte(ptep, map->pte); - if (gstage_pte_leaf(ptep)) + if (gstage_pte_leaf(ptep) && + !(was_invalid && riscv_has_extension_unlikely(RISCV_ISA_EXT_SVVPTC))) gstage_tlb_flush(gstage, current_level, map->addr); } diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 082f9b261733..8a0aa5e0e216 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -41,6 +41,7 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa, pgprot_t prot; unsigned long pfn; phys_addr_t addr, end; + unsigned long pgd_levels = kvm->arch.pgd_levels; struct kvm_mmu_memory_cache pcache = { .gfp_custom = (in_atomic) ? GFP_ATOMIC | __GFP_ACCOUNT : 0, .gfp_zero = __GFP_ZERO, @@ -63,7 +64,7 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa, if (!writable) map.pte = pte_wrprotect(map.pte); - ret = kvm_mmu_topup_memory_cache(&pcache, kvm->arch.pgd_levels); + ret = __kvm_mmu_topup_memory_cache(&pcache, pgd_levels, pgd_levels); if (ret) goto out; diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index cf6e231e76e2..977e36ab83d3 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -80,6 +80,7 @@ static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu, static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset) { + unsigned long flags; bool loaded; /** @@ -104,8 +105,10 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset) kvm_riscv_vcpu_aia_reset(vcpu); + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); bitmap_zero(vcpu->arch.irqs_pending, KVM_RISCV_VCPU_NR_IRQS); bitmap_zero(vcpu->arch.irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); kvm_riscv_vcpu_pmu_reset(vcpu); @@ -151,6 +154,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Setup VCPU hfence queue */ spin_lock_init(&vcpu->arch.hfence_lock); + raw_spin_lock_init(&vcpu->arch.irqs_pending_lock); spin_lock_init(&vcpu->arch.reset_state.lock); @@ -352,10 +356,14 @@ void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; unsigned long mask, val; + unsigned long flags; - if (READ_ONCE(vcpu->arch.irqs_pending_mask[0])) { - mask = xchg_acquire(&vcpu->arch.irqs_pending_mask[0], 0); - val = READ_ONCE(vcpu->arch.irqs_pending[0]) & mask; + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + + mask = vcpu->arch.irqs_pending_mask[0]; + if (mask) { + vcpu->arch.irqs_pending_mask[0] = 0; + val = vcpu->arch.irqs_pending[0] & mask; csr->hvip &= ~mask; csr->hvip |= val; @@ -363,11 +371,14 @@ void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu) /* Flush AIA high interrupts */ kvm_riscv_vcpu_aia_flush_interrupts(vcpu); + + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); } void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) { unsigned long hvip; + unsigned long flags; struct kvm_vcpu_arch *v = &vcpu->arch; struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; @@ -376,34 +387,41 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) /* Sync-up HVIP.VSSIP bit changes does by Guest */ hvip = ncsr_read(CSR_HVIP); + + raw_spin_lock_irqsave(&v->irqs_pending_lock, flags); + if ((csr->hvip ^ hvip) & (1UL << IRQ_VS_SOFT)) { if (hvip & (1UL << IRQ_VS_SOFT)) { - if (!test_and_set_bit(IRQ_VS_SOFT, - v->irqs_pending_mask)) - set_bit(IRQ_VS_SOFT, v->irqs_pending); + if (!__test_and_set_bit(IRQ_VS_SOFT, + v->irqs_pending_mask)) + __set_bit(IRQ_VS_SOFT, v->irqs_pending); } else { - if (!test_and_set_bit(IRQ_VS_SOFT, - v->irqs_pending_mask)) - clear_bit(IRQ_VS_SOFT, v->irqs_pending); + if (!__test_and_set_bit(IRQ_VS_SOFT, + v->irqs_pending_mask)) + __clear_bit(IRQ_VS_SOFT, v->irqs_pending); } } /* Sync up the HVIP.LCOFIP bit changes (only clear) by the guest */ if ((csr->hvip ^ hvip) & (1UL << IRQ_PMU_OVF)) { if (!(hvip & (1UL << IRQ_PMU_OVF)) && - !test_and_set_bit(IRQ_PMU_OVF, v->irqs_pending_mask)) - clear_bit(IRQ_PMU_OVF, v->irqs_pending); + !__test_and_set_bit(IRQ_PMU_OVF, v->irqs_pending_mask)) + __clear_bit(IRQ_PMU_OVF, v->irqs_pending); } /* Sync-up AIA high interrupts */ kvm_riscv_vcpu_aia_sync_interrupts(vcpu); + raw_spin_unlock_irqrestore(&v->irqs_pending_lock, flags); + /* Sync-up timer CSRs */ kvm_riscv_vcpu_timer_sync(vcpu); } int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) { + unsigned long flags; + /* * We only allow VS-mode software, timer, and external * interrupts when irq is one of the local interrupts @@ -416,9 +434,10 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) irq != IRQ_PMU_OVF) return -EINVAL; - set_bit(irq, vcpu->arch.irqs_pending); - smp_mb__before_atomic(); - set_bit(irq, vcpu->arch.irqs_pending_mask); + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + __set_bit(irq, vcpu->arch.irqs_pending); + __set_bit(irq, vcpu->arch.irqs_pending_mask); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); kvm_vcpu_kick(vcpu); @@ -427,6 +446,8 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) { + unsigned long flags; + /* * We only allow VS-mode software, timer, counter overflow and external * interrupts when irq is one of the local interrupts @@ -439,26 +460,33 @@ int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) irq != IRQ_PMU_OVF) return -EINVAL; - clear_bit(irq, vcpu->arch.irqs_pending); - smp_mb__before_atomic(); - set_bit(irq, vcpu->arch.irqs_pending_mask); + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + __clear_bit(irq, vcpu->arch.irqs_pending); + __set_bit(irq, vcpu->arch.irqs_pending_mask); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); return 0; } bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) { + unsigned long flags; unsigned long ie; + bool ret; + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); ie = ((vcpu->arch.guest_csr.vsie & VSIP_VALID_MASK) << VSIP_TO_HVIP_SHIFT) & (unsigned long)mask; ie |= vcpu->arch.guest_csr.vsie & ~IRQ_LOCAL_MASK & (unsigned long)mask; - if (READ_ONCE(vcpu->arch.irqs_pending[0]) & ie) - return true; + ret = vcpu->arch.irqs_pending[0] & ie; + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); /* Check AIA high interrupts */ - return kvm_riscv_vcpu_aia_has_interrupts(vcpu, mask); + if (!ret) + ret = kvm_riscv_vcpu_aia_has_interrupts(vcpu, mask); + + return ret; } void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu) diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index 0bb0c51e3c89..6c8530b9f29e 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -38,6 +38,25 @@ static int gstage_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, return kvm_riscv_vcpu_mmio_store(vcpu, run, fault_addr, trap->htinst); + case EXC_INST_GUEST_PAGE_FAULT: { + /* + * No memslot backs this GPA and an instruction fetch + * cannot be emulated as MMIO. On bare metal a fetch + * from an unbacked physical address raises an + * instruction access fault, so reflect that back to + * the guest. + */ + struct kvm_cpu_trap inst_trap = { + .sepc = trap->sepc, + .scause = EXC_INST_ACCESS, + .stval = trap->stval, + .htval = 0, + .htinst = 0, + }; + + kvm_riscv_vcpu_trap_redirect(vcpu, &inst_trap); + return 1; + } default: return -EOPNOTSUPP; }; diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index bb920e8923c9..99b9107b1ac1 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -50,19 +50,13 @@ static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu, reg_val = vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK; break; case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size): - if (kvm_riscv_isa_check_host(ZICBOM)) - return -ENOENT; - reg_val = riscv_cbom_block_size; + reg_val = (kvm_riscv_isa_check_host(ZICBOM)) ? 0 : riscv_cbom_block_size; break; case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size): - if (kvm_riscv_isa_check_host(ZICBOZ)) - return -ENOENT; - reg_val = riscv_cboz_block_size; + reg_val = (kvm_riscv_isa_check_host(ZICBOZ)) ? 0 : riscv_cboz_block_size; break; case KVM_REG_RISCV_CONFIG_REG(zicbop_block_size): - if (kvm_riscv_isa_check_host(ZICBOP)) - return -ENOENT; - reg_val = riscv_cbop_block_size; + reg_val = (kvm_riscv_isa_check_host(ZICBOP)) ? 0 : riscv_cbop_block_size; break; case KVM_REG_RISCV_CONFIG_REG(mvendorid): reg_val = vcpu->arch.mvendorid; @@ -144,21 +138,15 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu, } break; case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size): - if (kvm_riscv_isa_check_host(ZICBOM)) - return -ENOENT; - if (reg_val != riscv_cbom_block_size) + if (reg_val && reg_val != riscv_cbom_block_size) return -EINVAL; break; case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size): - if (kvm_riscv_isa_check_host(ZICBOZ)) - return -ENOENT; - if (reg_val != riscv_cboz_block_size) + if (reg_val && reg_val != riscv_cboz_block_size) return -EINVAL; break; case KVM_REG_RISCV_CONFIG_REG(zicbop_block_size): - if (kvm_riscv_isa_check_host(ZICBOP)) - return -ENOENT; - if (reg_val != riscv_cbop_block_size) + if (reg_val && reg_val != riscv_cbop_block_size) return -EINVAL; break; case KVM_REG_RISCV_CONFIG_REG(mvendorid): @@ -298,6 +286,7 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu, { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); + unsigned long flags; if (reg_num >= regs_max) return -ENOENT; @@ -311,8 +300,11 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu, ((unsigned long *)csr)[reg_num] = reg_val; - if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) - WRITE_ONCE(vcpu->arch.irqs_pending_mask[0], 0); + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + vcpu->arch.irqs_pending_mask[0] = 0; + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); + } return 0; } @@ -614,20 +606,6 @@ static int copy_config_reg_indices(const struct kvm_vcpu *vcpu, u64 size; u64 reg; - /* - * Avoid reporting config reg if the corresponding extension - * was not available. - */ - if (i == KVM_REG_RISCV_CONFIG_REG(zicbom_block_size) && - kvm_riscv_isa_check_host(ZICBOM)) - continue; - else if (i == KVM_REG_RISCV_CONFIG_REG(zicboz_block_size) && - kvm_riscv_isa_check_host(ZICBOZ)) - continue; - else if (i == KVM_REG_RISCV_CONFIG_REG(zicbop_block_size) && - kvm_riscv_isa_check_host(ZICBOP)) - continue; - size = IS_ENABLED(CONFIG_32BIT) ? KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CONFIG | i; diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index bb46dcbfb24d..2025b664961c 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -586,7 +586,7 @@ int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, } } /* Start the counters that have been configured and requested by the guest */ - for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { + for_each_set_bit(i, &ctr_mask, BITS_PER_LONG) { pmc_index = array_index_nospec(i + ctr_base, RISCV_KVM_MAX_COUNTERS); if (!test_bit(pmc_index, kvpmu->pmc_in_use)) @@ -658,7 +658,7 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, } /* Stop the counters that have been configured and requested by the guest */ - for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { + for_each_set_bit(i, &ctr_mask, BITS_PER_LONG) { pmc_index = array_index_nospec(i + ctr_base, RISCV_KVM_MAX_COUNTERS); if (!test_bit(pmc_index, kvpmu->pmc_in_use)) diff --git a/arch/riscv/kvm/vcpu_sbi_fwft.c b/arch/riscv/kvm/vcpu_sbi_fwft.c index ab39ac464ffd..1342adb3180c 100644 --- a/arch/riscv/kvm/vcpu_sbi_fwft.c +++ b/arch/riscv/kvm/vcpu_sbi_fwft.c @@ -327,9 +327,11 @@ static int kvm_sbi_fwft_set(struct kvm_vcpu *vcpu, u32 feature, if (conf->flags & SBI_FWFT_SET_FLAG_LOCK) return SBI_ERR_DENIED_LOCKED; - conf->flags = flags; + ret = conf->feature->set(vcpu, conf, false, value); + if (ret == SBI_SUCCESS) + conf->flags = flags; - return conf->feature->set(vcpu, conf, false, value); + return ret; } static int kvm_sbi_fwft_get(struct kvm_vcpu *vcpu, unsigned long feature, diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c index 62d2fb77bb9b..3708616e2c32 100644 --- a/arch/riscv/kvm/vcpu_vector.c +++ b/arch/riscv/kvm/vcpu_vector.c @@ -10,6 +10,7 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/cpufeature.h> #include <asm/kvm_isa.h> @@ -129,11 +130,20 @@ static int kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu, return -ENOENT; } } else if (reg_num <= KVM_REG_RISCV_VECTOR_REG(31)) { + unsigned long reg_offset; + if (reg_size != vlenb) return -EINVAL; WARN_ON(!cntx->vector.datap); - *reg_addr = cntx->vector.datap + - (reg_num - KVM_REG_RISCV_VECTOR_REG(0)) * vlenb; + /* + * The reg_num is derived from the userspace-provided ONE_REG + * id. Sanitize it with array_index_nospec() to prevent + * speculative out-of-bounds access to the vector register + * buffer (32 vector registers: v0..v31). + */ + reg_offset = array_index_nospec( + reg_num - KVM_REG_RISCV_VECTOR_REG(0), 32); + *reg_addr = cntx->vector.datap + reg_offset * vlenb; } else { return -ENOENT; } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 5b1b3c88b4d1..3e450890be07 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -37,7 +37,9 @@ #include "../kernel/head.h" +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) DECLARE_BITMAP(new_valid_map_cpus, NR_CPUS); +#endif struct kernel_mapping kernel_map __ro_after_init; EXPORT_SYMBOL(kernel_map); diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 7aa655664ecc..2076ac22e2c4 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -15,6 +15,7 @@ #include <linux/init.h> #include <linux/miscdevice.h> #include <linux/perf_event.h> +#include <linux/nospec.h> #include <asm/cpu_mf.h> #include <asm/hwctrset.h> @@ -768,6 +769,7 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) if (!is_userspace_event(ev)) { if (ev >= ARRAY_SIZE(cpumf_generic_events_user)) return -EOPNOTSUPP; + ev = array_index_nospec(ev, ARRAY_SIZE(cpumf_generic_events_user)); ev = cpumf_generic_events_user[ev]; } } else if (!attr->exclude_kernel && attr->exclude_user) { @@ -778,6 +780,7 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) if (!is_userspace_event(ev)) { if (ev >= ARRAY_SIZE(cpumf_generic_events_basic)) return -EOPNOTSUPP; + ev = array_index_nospec(ev, ARRAY_SIZE(cpumf_generic_events_basic)); ev = cpumf_generic_events_basic[ev]; } } diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index bd0df61d1907..2b989bebd220 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -65,6 +65,7 @@ ATOMIC_NOTIFIER_HEAD(s390_epoch_delta_notifier); EXPORT_SYMBOL(s390_epoch_delta_notifier); unsigned char ptff_function_mask[16]; +EXPORT_SYMBOL(ptff_function_mask); static unsigned long lpar_offset; static unsigned long initial_leap_seconds; diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index 5f1960ec982d..ed4259d17629 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -570,6 +570,8 @@ static long dat_crste_walk_range(gfn_t start, gfn_t end, struct crst_table *tabl else if (walk->ops->pte_entry) rc = dat_pte_walk_range(max(start, cur), min(end, next), dereference_pmd(crste.pmd), walk); + if (rc) + break; } } return rc; diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c index 298fbaecec28..8abb4f55b306 100644 --- a/arch/s390/kvm/gmap.c +++ b/arch/s390/kvm/gmap.c @@ -1374,8 +1374,13 @@ struct gmap *gmap_create_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *pare /* Only allow one real-space gmap shadow. */ list_for_each_entry(sg, &parent->children, list) { if (sg->guest_asce.r) { - scoped_guard(write_lock, &parent->kvm->mmu_lock) + if (write_trylock(&parent->kvm->mmu_lock)) { gmap_unshadow(sg); + write_unlock(&parent->kvm->mmu_lock); + } else { + gmap_put(new); + return ERR_PTR(-EAGAIN); + } break; } } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 23c817595e28..150b5dd2170e 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1280,8 +1280,10 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm) * PGSTEs might have cmma_d set. */ WRITE_ONCE(kvm->arch.migration_mode, 0); - if (kvm->arch.use_cmma) - kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION); + if (!kvm->arch.use_cmma) + return 0; + + kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION); /* Clear cmma_d on all existing PGSTEs and set cmma_dirty_pages to 0. */ gmap_set_cmma_all_clean(kvm->arch.gmap); atomic64_set(&kvm->arch.cmma_dirty_pages, 0); diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 5b075c38998e..720bb58cabe2 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -300,9 +300,14 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, gaite->gisc = fib->fmt0.isc; gaite->count++; - gaite->aisbo = fib->fmt0.aisbo; - gaite->aisb = virt_to_phys(page_address(aisb_page) + (fib->fmt0.aisb & - ~PAGE_MASK)); + if (fib->fmt0.sum == 1) { + gaite->aisbo = fib->fmt0.aisbo; + gaite->aisb = virt_to_phys(page_address(aisb_page) + + (fib->fmt0.aisb & ~PAGE_MASK)); + } else { + gaite->aisbo = 0; + gaite->aisb = 0; + } aift->kzdev[zdev->aisb] = zdev->kzdev; spin_unlock_irq(&aift->gait_lock); @@ -328,6 +333,7 @@ unpin2: unpin1: unpin_user_page(aibv_page); out: + kvm_s390_gisc_unregister(kvm, fib->fmt0.isc); return rc; } diff --git a/arch/s390/lib/csum-partial.c b/arch/s390/lib/csum-partial.c index 458abd9bac70..9d74ceff136c 100644 --- a/arch/s390/lib/csum-partial.c +++ b/arch/s390/lib/csum-partial.c @@ -23,7 +23,7 @@ static __always_inline __wsum csum_copy(void *dst, const void *src, int len, __w if (!cpu_has_vx()) { if (copy) memcpy(dst, src, len); - return cksm(dst, len, sum); + return cksm(src, len, sum); } kernel_fpu_begin(&vxstate, KERNEL_VXR_V16V23); fpu_vlvgf(16, (__force u32)sum, 1); diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index f196b1d1ddf8..aed27604c11f 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -184,10 +184,15 @@ static unsigned long get_cmdline_acpi_rsdp(void) char val[MAX_ADDR_LEN] = { }; int ret; - ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN); + ret = cmdline_find_option("acpi_rsdp", val, sizeof(val)); if (ret < 0) return 0; + if (ret >= sizeof(val)) { + warn("acpi_rsdp= value too long; ignoring"); + return 0; + } + if (boot_kstrtoul(val, 16, &addr)) return 0; #endif diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c index 023bf1c3de8b..5b83beab89e1 100644 --- a/arch/x86/boot/early_serial_console.c +++ b/arch/x86/boot/early_serial_console.c @@ -117,7 +117,7 @@ static unsigned int probe_baud(int port) static void parse_console_uart8250(void) { char optstr[64], *options; - int baud = DEFAULT_BAUD; + int baud; int port = 0; /* @@ -136,10 +136,13 @@ static void parse_console_uart8250(void) else return; - if (options && (options[0] == ',')) - baud = simple_strtoull(options + 1, &options, 0); - else + if (options && (options[0] == ',')) { + baud = simple_strtoull(options + 1, NULL, 0); + if (!baud) + baud = DEFAULT_BAUD; + } else { baud = probe_baud(port); + } if (port) early_serial_init(port, baud); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index d2e8a849f180..5b1070ec85d9 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -46,7 +46,6 @@ obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o -obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_CPU_SUP_ZHAOXIN) += zhaoxin.o obj-$(CONFIG_CPU_SUP_VORTEX_32) += vortex.o diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 8c62c6d4d5c1..cb8ac4b9b0d7 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -488,8 +488,10 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) { ret = kvm_pi_update_irte(irqfd, &irqfd->irq_entry); - if (ret) + if (ret) { kvm->arch.nr_possible_bypass_irqs--; + irqfd->producer = NULL; + } } spin_unlock_irq(&kvm->irqfds.lock); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 6f30bbdddb5a..48b019114c19 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2052,7 +2052,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use) ktimer->expired_tscdeadline = ktimer->tscdeadline; - if (!from_timer_fn && apic->apicv_active) { + if (!from_timer_fn && apic->apicv_active && vcpu->wants_to_run) { WARN_ON(kvm_get_running_vcpu() != vcpu); kvm_apic_inject_pending_timer_irqs(apic); return; @@ -3371,6 +3371,12 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, struct kvm_lapic *apic) { int vector; + + if (unlikely(!pv_eoi_enabled(vcpu))) { + __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); + return; + } + /* * PV EOI state is derived from KVM_APIC_PV_EOI_PENDING in host * and KVM_PV_EOI_ENABLED in guest memory as follows: @@ -3382,8 +3388,6 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, * KVM_APIC_PV_EOI_PENDING is set, KVM_PV_EOI_ENABLED is unset: * -> host enabled PV EOI, guest executed EOI. */ - BUG_ON(!pv_eoi_enabled(vcpu)); - if (pv_eoi_test_and_clr_pending(vcpu)) return; vector = apic_set_eoi(apic); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 234d0a95abf5..22cf222d3033 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2642,6 +2642,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, */ if (tdp_enabled && invalid_list && child->role.guest_mode && + !child->root_count && !atomic_long_read(&child->parent_ptes.val)) return kvm_mmu_prepare_zap_page(kvm, child, invalid_list); @@ -4852,16 +4853,17 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r != RET_PF_CONTINUE) return r; - r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (is_page_fault_stale(vcpu, fault)) - goto out_unlock; - r = make_mmu_pages_available(vcpu); if (r) goto out_unlock; + if (is_page_fault_stale(vcpu, fault)) { + r = RET_PF_RETRY; + goto out_unlock; + } + r = direct_map(vcpu, fault); out_unlock: @@ -7574,7 +7576,9 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) static void mmu_destroy_caches(void) { kmem_cache_destroy(pte_list_desc_cache); + pte_list_desc_cache = NULL; kmem_cache_destroy(mmu_page_header_cache); + mmu_page_header_cache = NULL; } static void kvm_wake_nx_recovery_thread(struct kvm *kvm) diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index df3ae0c7ec2c..1ba840a73b7a 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -864,15 +864,17 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault } #endif - r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (is_page_fault_stale(vcpu, fault)) - goto out_unlock; - r = make_mmu_pages_available(vcpu); if (r) goto out_unlock; + + if (is_page_fault_stale(vcpu, fault)) { + r = RET_PF_RETRY; + goto out_unlock; + } + r = FNAME(fetch)(vcpu, fault, &walker); out_unlock: diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 427229347876..944aaea6501f 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2129,8 +2129,9 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) if (ret) return ret; + /* Do not allow SNP VM migration until additional state transfer is implemented */ if (kvm->arch.vm_type != source_kvm->arch.vm_type || - sev_guest(kvm) || !sev_guest(source_kvm)) { + sev_guest(kvm) || !sev_guest(source_kvm) || sev_snp_guest(source_kvm)) { ret = -EINVAL; goto out_unlock; } @@ -2851,8 +2852,9 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) * disallow out-of-band SEV/SEV-ES init if the target is already an * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being * created after SEV/SEV-ES initialization, e.g. to init intercepts. + * Also do not allow SNP VM mirroring until additional state transfer is implemented. */ - if (sev_guest(kvm) || !sev_guest(source_kvm) || + if (sev_guest(kvm) || !sev_guest(source_kvm) || sev_snp_guest(source_kvm) || is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) { ret = -EINVAL; goto e_unlock; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 4d2bacd00ec4..d0971685034b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -571,7 +571,12 @@ static int svm_enable_virtualization_cpu(void) return r; sd = per_cpu_ptr(&svm_data, me); - sd->asid_generation = 1; + /* + * Bump the current asid_generation value to ensure any vCPU that + * previously ran on this CPU sees a stale generation and is forced + * to acquire a new ASID, preventing a latent ASID collision. + */ + sd->asid_generation++; sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; sd->next_asid = sd->max_asid + 1; sd->min_asid = max_sev_asid + 1; diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 0db25bba17f6..93de876c318c 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -490,7 +490,7 @@ TRACE_EVENT(kvm_inj_exception, TP_printk("%s%s%s%s%s", __print_symbolic(__entry->exception, kvm_trace_sym_exc), !__entry->has_error ? "" : " (", - !__entry->has_error ? "" : __print_symbolic(__entry->error_code, { }), + !__entry->has_error ? "" : __print_symbolic(__entry->error_code), !__entry->has_error ? "" : ")", __entry->reinjected ? " [reinjected]" : "") ); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 6957bb6f5cf7..ddf6df7bee93 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -336,6 +336,7 @@ static void nested_put_vmcs12_pages(struct kvm_vcpu *vcpu) static void free_nested(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs *shadow_vmcs; if (WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01)) vmx_switch_vmcs(vcpu, &vmx->vmcs01); @@ -353,9 +354,15 @@ static void free_nested(struct kvm_vcpu *vcpu) vmx->nested.current_vmptr = INVALID_GPA; if (enable_shadow_vmcs) { vmx_disable_shadow_vmcs(vmx); - vmcs_clear(vmx->vmcs01.shadow_vmcs); - free_vmcs(vmx->vmcs01.shadow_vmcs); + + /* + * Keep the pointer visible until after VMCLEAR, so migration + * can clear an active shadow VMCS on the old CPU. + */ + shadow_vmcs = vmx->vmcs01.shadow_vmcs; + vmcs_clear(shadow_vmcs); vmx->vmcs01.shadow_vmcs = NULL; + free_vmcs(shadow_vmcs); } kfree(vmx->nested.cached_vmcs12); vmx->nested.cached_vmcs12 = NULL; @@ -582,6 +589,9 @@ static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { + gpa_t vtpr_gpa = vmcs12->virtual_apic_page_addr + APIC_TASKPRI; + u32 vtpr; + if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) return 0; @@ -591,6 +601,32 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, if (CC(!nested_cpu_has_vid(vmcs12) && vmcs12->tpr_threshold >> 4)) return -EINVAL; + /* + * Do the illegal vTPR vs. TPR Threshold consistency check if and only + * if KVM is configured to WARN on missed consistency checks, otherwise + * it's a waste of time. KVM needs to rely on hardware to fully detect + * an illegal combination due to the vTPR being writable by L1 at all + * times (it's an in-memory value, not a VMCS field). I.e. even if the + * check passes now, it might fail at the actual VM-Enter. + * + * If reading guest memory fails, skip the check as KVM's de facto ABI + * for VMX instruction accesses to non-existent memory is to provide + * PCI Bus Error semantics (reads return 0xFFs), in which case the vTPR + * is guaranteed to greater than or equal to the threshold. + * + * Note! Deliberately use the VM-scoped API when reading guest memory, + * to ensure the read doesn't hit SMRAM when restoring L2 state on RSM, + * and only perform the check when in KVM_RUN, to avoid a false failure + * if userspace hasn't yet configured memslots during state restore. + */ + if (warn_on_missed_cc && vcpu->wants_to_run && + nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW) && + !nested_cpu_has_vid(vmcs12) && + !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) && + !kvm_read_guest(vcpu->kvm, vtpr_gpa, &vtpr, sizeof(vtpr)) && + CC((vmcs12->tpr_threshold & GENMASK(3, 0)) > ((vtpr >> 4) & GENMASK(3, 0)))) + return -EINVAL; + return 0; } @@ -3104,38 +3140,6 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, return 0; } -static int nested_vmx_check_controls_late(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) -{ - void *vapic = to_vmx(vcpu)->nested.virtual_apic_map.hva; - u32 vtpr = vapic ? (*(u32 *)(vapic + APIC_TASKPRI)) >> 4 : 0; - - /* - * Don't bother with the consistency checks if KVM isn't configured to - * WARN on missed consistency checks, as KVM needs to rely on hardware - * to fully detect an illegal vTPR vs. TRP Threshold combination due to - * the vTPR being writable by L1 at all times (it's an in-memory value, - * not a VMCS field). I.e. even if the check passes now, it might fail - * at the actual VM-Enter. - * - * Keying off the module param also allows treating an invalid vAPIC - * mapping as a consistency check failure without increasing the risk - * of breaking a "real" VM. - */ - if (!warn_on_missed_cc) - return 0; - - if ((exec_controls_get(to_vmx(vcpu)) & CPU_BASED_TPR_SHADOW) && - nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW) && - !nested_cpu_has_vid(vmcs12) && - !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) && - (CC(!vapic) || - CC((vmcs12->tpr_threshold & GENMASK(3, 0)) > (vtpr & GENMASK(3, 0))))) - return -EINVAL; - - return 0; -} - static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -3661,19 +3665,14 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, &vmx->nested.pre_vmenter_ssp_tbl); /* - * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled. In the - * event of a "late" VM-Fail, i.e. a VM-Fail detected by hardware but - * not KVM, KVM must unwind its software model to the pre-VM-Entry host - * state. When EPT is disabled, GUEST_CR3 holds KVM's shadow CR3, not - * L1's "real" CR3, which causes nested_vmx_restore_host_state() to - * corrupt vcpu->arch.cr3. Stuffing vmcs01.GUEST_CR3 results in the - * unwind naturally setting arch.cr3 to the correct value. Smashing - * vmcs01.GUEST_CR3 is safe because nested VM-Exits, and the unwind, - * reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is guaranteed to be - * overwritten with a shadow CR3 prior to re-entering L1. + * Stash L1's CR3, so that in the event of a "late" VM-Fail, i.e. a + * VM-Fail detected by hardware but not KVM, KVM can unwind its + * software model to the pre-VM-Entry host state. When EPT is + * disabled, GUEST_CR3 holds KVM's shadow CR3, not L1's "real" CR3, + * and so simply restoring from vmcs01.GUEST_CR3 would corrupt + * vcpu->arch.cr3. */ - if (!enable_ept) - vmcs_writel(GUEST_CR3, vcpu->arch.cr3); + vmx->nested.pre_vmenter_cr3 = kvm_read_cr3(vcpu); vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); @@ -3685,11 +3684,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, return NVMX_VMENTRY_KVM_INTERNAL_ERROR; } - if (nested_vmx_check_controls_late(vcpu, vmcs12)) { - vmx_switch_vmcs(vcpu, &vmx->vmcs01); - return NVMX_VMENTRY_VMFAIL; - } - if (nested_vmx_check_guest_state(vcpu, vmcs12, &entry_failure_code)) { exit_reason.basic = EXIT_REASON_INVALID_STATE; @@ -3774,6 +3768,8 @@ vmentry_fail_vmexit: if (!from_vmentry) return NVMX_VMENTRY_VMEXIT; + nested_put_vmcs12_pages(vcpu); + load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason.full; if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)) @@ -4990,7 +4986,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW)); nested_ept_uninit_mmu_context(vcpu); - vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + vcpu->arch.cr3 = vmx->nested.pre_vmenter_cr3; kvm_register_mark_available(vcpu, VCPU_REG_CR3); /* diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 989ab29b8c6f..545b03d9d10b 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -2797,7 +2797,11 @@ static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd) goto out; } - if (init_vm->cpuid.padding) { + /* + * Reject the request if userspace changes cpuid.nent between the + * initial read and the subsequent copy. + */ + if (init_vm->cpuid.padding || init_vm->cpuid.nent != nr_user_entries) { ret = -EINVAL; goto out; } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index de9de0d2016c..dc8517f15bc4 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -160,6 +160,13 @@ struct nested_vmx { bool preemption_timer_expired; /* + * Used to restore L1's CR3 if hardware detects a VM-Fail Consistency + * Check that KVM does not, in which case KVM needs to unwind CR3 back + * to its pre-VM-Enter state, NOT to vmcs01.HOST_CR3. + */ + unsigned long pre_vmenter_cr3; + + /* * Used to snapshot MSRs that are conditionally loaded on VM-Enter in * order to propagate the guest's pre-VM-Enter value into vmcs02. For * emulation of VMLAUNCH/VMRESUME, the snapshot will be of L1's value. diff --git a/block/bio.c b/block/bio.c index f2a5f4d0a967..6a2f6fc3413e 100644 --- a/block/bio.c +++ b/block/bio.c @@ -555,6 +555,14 @@ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, bio = bio_alloc_percpu_cache(bs); } else { opf &= ~REQ_ALLOC_CACHE; + } + + /* + * For a bioset without a percpu cache, or when the percpu cache was + * empty, try a slab allocation with optimistic GFP_ flags before + * falling back to the mempool. + */ + if (!bio) { p = kmem_cache_alloc(bs->bio_slab, gfp); if (p) bio = p + bs->front_pad; @@ -1191,7 +1199,7 @@ void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter) * for the next iteration. */ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter, - unsigned len_align_mask) + struct bio_vec *bv, unsigned len_align_mask) { size_t nbytes = bio->bi_iter.bi_size & len_align_mask; @@ -1200,23 +1208,16 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter, iov_iter_revert(iter, nbytes); bio->bi_iter.bi_size -= nbytes; - do { - struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; - - if (nbytes < bv->bv_len) { - bv->bv_len -= nbytes; - break; - } - + while (nbytes >= bv->bv_len) { if (bio_flagged(bio, BIO_PAGE_PINNED)) unpin_user_page(bv->bv_page); - bio->bi_vcnt--; + if (!--bio->bi_vcnt) + return -EFAULT; nbytes -= bv->bv_len; - } while (nbytes); - - if (!bio->bi_vcnt) - return -EFAULT; + bv--; + } + bv->bv_len -= nbytes; return 0; } @@ -1276,7 +1277,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter, if (is_pci_p2pdma_page(bio->bi_io_vec->bv_page)) bio->bi_opf |= REQ_NOMERGE; - return bio_iov_iter_align_down(bio, iter, len_align_mask); + return bio_iov_iter_align_down(bio, iter, + &bio->bi_io_vec[bio->bi_vcnt - 1], len_align_mask); } static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size, @@ -1285,7 +1287,8 @@ static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size, struct folio *folio; while (*size > minsize) { - folio = folio_alloc(gfp | __GFP_NORETRY, get_order(*size)); + folio = folio_alloc(gfp | __GFP_NORETRY | __GFP_NOWARN, + get_order(*size)); if (folio) return folio; *size = rounddown_pow_of_two(*size - 1); @@ -1302,7 +1305,7 @@ static void bio_free_folios(struct bio *bio) bio_for_each_bvec_all(bv, bio, i) { struct folio *folio = bvec_folio(bv); - if (!is_zero_folio(folio)) + if (!is_zero_folio(folio) && !is_huge_zero_folio(folio)) folio_put(folio); } } @@ -1360,7 +1363,8 @@ static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter, if (!bio->bi_iter.bi_size) return -ENOMEM; - return bio_iov_iter_align_down(bio, iter, minsize - 1); + return bio_iov_iter_align_down(bio, iter, + &bio->bi_io_vec[bio->bi_vcnt - 1], minsize - 1); } static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, @@ -1368,21 +1372,18 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, { size_t len = min3(iov_iter_count(iter), maxlen, SZ_1M); struct folio *folio; + ssize_t ret; folio = folio_alloc_greedy(GFP_KERNEL, &len, minsize); if (!folio) return -ENOMEM; do { - ssize_t ret; - ret = iov_iter_extract_bvecs(iter, bio->bi_io_vec + 1, len, &bio->bi_vcnt, bio->bi_max_vecs - 1, 0); if (ret <= 0) { - if (!bio->bi_vcnt) { - folio_put(folio); - return ret; - } + if (!bio->bi_vcnt) + goto out_folio_put; break; } len -= ret; @@ -1398,7 +1399,20 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, bvec_set_folio(&bio->bi_io_vec[0], folio, bio->bi_iter.bi_size, 0); if (iov_iter_extract_will_pin(iter)) bio_set_flag(bio, BIO_PAGE_PINNED); - return bio_iov_iter_align_down(bio, iter, minsize - 1); + + /* The first vec stores the bounce buffer, so do not subtract 1 here. */ + ret = bio_iov_iter_align_down(bio, iter, + &bio->bi_io_vec[bio->bi_vcnt], minsize - 1); + if (ret) + goto out_folio_put; + + /* Update the bounc buffer bv_len to the aligned down size. */ + bio->bi_io_vec[0].bv_len = bio->bi_iter.bi_size; + return 0; + +out_folio_put: + folio_put(folio); + return ret; } /** diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index d2a1f5903f24..d9676126c5b5 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -434,15 +434,15 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, blkg->pd[i]->online = true; } } + blkg->online = true; } - blkg->online = true; spin_unlock(&blkcg->lock); if (!ret) return blkg; /* @blkg failed fully initialized, use the usual release path */ - blkg_put(blkg); + percpu_ref_kill(&blkg->refcnt); return ERR_PTR(ret); err_free_blkg: diff --git a/block/blk-map.c b/block/blk-map.c index 768549f19f97..d1d6bbe0ecf1 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -653,6 +653,7 @@ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, gfp_t gfp_mask) { unsigned long addr = (unsigned long) kbuf; + bool do_copy; struct bio *bio; int ret; @@ -661,7 +662,8 @@ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, if (!len || !kbuf) return -EINVAL; - if (!blk_rq_aligned(rq->q, addr, len) || object_is_on_stack(kbuf)) + do_copy = !blk_rq_aligned(rq->q, addr, len) || object_is_on_stack(kbuf); + if (do_copy) bio = bio_copy_kern(rq, kbuf, len, gfp_mask); else bio = bio_map_kern(rq, kbuf, len, gfp_mask); @@ -670,8 +672,11 @@ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, return PTR_ERR(bio); ret = blk_rq_append_bio(rq, bio); - if (unlikely(ret)) + if (unlikely(ret)) { + if (do_copy) + bio_free_pages(bio); blk_mq_map_bio_put(bio); + } return ret; } EXPORT_SYMBOL(blk_rq_map_kern); diff --git a/block/blk.h b/block/blk.h index fb95d3c58950..eaac05815cb0 100644 --- a/block/blk.h +++ b/block/blk.h @@ -717,6 +717,7 @@ static inline int req_ref_read(struct request *req) static inline u64 blk_time_get_ns(void) { struct blk_plug *plug = current->plug; + u64 now; if (!plug || !in_task()) return ktime_get_ns(); @@ -725,12 +726,18 @@ static inline u64 blk_time_get_ns(void) * 0 could very well be a valid time, but rather than flag "this is * a valid timestamp" separately, just accept that we'll do an extra * ktime_get_ns() if we just happen to get 0 as the current time. + * + * cur_ktime can be zeroed by pre-emption the moment PF_BLOCK_TS is set. */ - if (!plug->cur_ktime) { - plug->cur_ktime = ktime_get_ns(); + now = READ_ONCE(plug->cur_ktime); + if (!now) { + now = ktime_get_ns(); + WRITE_ONCE(plug->cur_ktime, now); + /* Ensure PF_BLOCK_TS is set after cur_ktime. */ + barrier(); current->flags |= PF_BLOCK_TS; } - return plug->cur_ktime; + return now; } static inline ktime_t blk_time_get(void) diff --git a/block/elevator.c b/block/elevator.c index 3bcd37c2aa34..2161b6eea680 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -812,8 +812,13 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, * reference during concurrent disk deletion: * update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del) * kn->active -> update_nr_hwq_lock (via this sysfs write path) + * + * Use the writer lock instead of the reader lock of update_nr_hwq_lock + * to serialize the two-stage elevator switch steps in + * elevator_change(): the core switch step under the elevator lock and + * the elevator_change_done() step outside the elevator lock. */ - if (!down_read_trylock(&set->update_nr_hwq_lock)) { + if (!down_write_trylock(&set->update_nr_hwq_lock)) { ret = -EBUSY; goto out; } @@ -824,7 +829,7 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, } else { ret = -ENOENT; } - up_read(&set->update_nr_hwq_lock); + up_write(&set->update_nr_hwq_lock); out: if (ctx.type) diff --git a/block/error-injection.c b/block/error-injection.c index cfb83138960c..e14bc4b723ef 100644 --- a/block/error-injection.c +++ b/block/error-injection.c @@ -276,9 +276,10 @@ static int blk_error_injection_show(struct seq_file *s, void *private) rcu_read_lock(); list_for_each_entry_rcu(inj, &disk->error_injection_list, entry) { - seq_printf(s, "%llu:%llu status=%s,chance=%u", - inj->start, inj->end, - blk_status_to_tag(inj->status), inj->chance); + seq_printf(s, "%llu:%llu op=%s,status=%s,chance=%u", + inj->start, inj->end, + blk_op_str(inj->op), + blk_status_to_tag(inj->status), inj->chance); seq_putc(s, '\n'); } rcu_read_unlock(); diff --git a/block/partitions/aix.c b/block/partitions/aix.c index f3c4174e003e..689837deba27 100644 --- a/block/partitions/aix.c +++ b/block/partitions/aix.c @@ -208,7 +208,14 @@ int aix_partition(struct parsed_partitions *state) if (n) { int foundlvs = 0; - for (i = 0; foundlvs < numlvs && i < state->limit; i += 1) { + /* + * The lvd array was read as a single sector; only the + * struct lvd entries that fit in it are valid. Bound the + * scan so an on-disk numlvs larger than that cannot walk + * the read buffer out of bounds. + */ + for (i = 0; foundlvs < numlvs && i < state->limit && + i < SECTOR_SIZE / (int)sizeof(struct lvd); i++) { lvip[i].pps_per_lv = be16_to_cpu(p[i].num_lps); if (lvip[i].pps_per_lv) foundlvs += 1; diff --git a/crypto/Kconfig b/crypto/Kconfig index f1e372195273..b61401bd3ef6 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -358,8 +358,8 @@ config CRYPTO_AES tristate "AES (Advanced Encryption Standard)" select CRYPTO_ALGAPI select CRYPTO_LIB_AES - select CRYPTO_LIB_AES_CBC_MACS if CRYPTO_CMAC || CRYPTO_XCBC || CRYPTO_CCM - select CRYPTO_HASH if CRYPTO_CMAC || CRYPTO_XCBC || CRYPTO_CCM + select CRYPTO_LIB_AES_CBC_MACS if CRYPTO_CMAC != n || CRYPTO_XCBC != n || CRYPTO_CCM != n + select CRYPTO_HASH if CRYPTO_CMAC != n || CRYPTO_XCBC != n || CRYPTO_CCM != n help AES cipher algorithms (Rijndael)(FIPS-197, ISO/IEC 18033-3) diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 8f8df9d04ec5..31a414c3f0d9 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -577,6 +577,7 @@ void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job) amdxdna_arg_bos_put(job); amdxdna_gem_put_obj(job->cmd_bo); dma_fence_put(job->fence); + mmdrop(job->mm); } int amdxdna_cmd_submit(struct amdxdna_client *client, @@ -590,6 +591,10 @@ int amdxdna_cmd_submit(struct amdxdna_client *client, int ret, idx; XDNA_DBG(xdna, "Command BO hdl %d, Arg BO count %d", cmd_bo_hdl, arg_bo_cnt); + + if (!xdna->dev_info->ops->cmd_submit) + return -EOPNOTSUPP; + job = kzalloc_flex(*job, bos, arg_bo_cnt); if (!job) return -ENOMEM; @@ -603,6 +608,16 @@ int amdxdna_cmd_submit(struct amdxdna_client *client, ret = -EINVAL; goto free_job; } + } else if (!drv_cmd) { + /* + * Only internal driver commands (drv_cmd != NULL) may omit a + * command BO. A user command submission with the invalid handle + * would leave job->cmd_bo NULL and later fault when the scheduler + * dereferences it in amdxdna_cmd_set_state(). + */ + XDNA_DBG(xdna, "Command BO handle required for user submission"); + ret = -EINVAL; + goto free_job; } ret = amdxdna_arg_bos_lookup(client, job, arg_bo_hdls, arg_bo_cnt); @@ -628,6 +643,7 @@ int amdxdna_cmd_submit(struct amdxdna_client *client, job->hwctx = hwctx; job->mm = current->mm; + mmgrab(job->mm); job->fence = amdxdna_fence_create(hwctx); if (!job->fence) { @@ -662,6 +678,8 @@ put_bos: cmd_put: amdxdna_gem_put_obj(job->cmd_bo); free_job: + if (job->mm) + mmdrop(job->mm); kfree(job); return ret; } diff --git a/drivers/accel/ivpu/ivpu_fw_log.c b/drivers/accel/ivpu/ivpu_fw_log.c index 275baf844b56..716467aa3156 100644 --- a/drivers/accel/ivpu/ivpu_fw_log.c +++ b/drivers/accel/ivpu/ivpu_fw_log.c @@ -43,6 +43,10 @@ static int fw_log_from_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *off ivpu_dbg(vdev, FW_BOOT, "Invalid header size 0x%x\n", log->header_size); return -EINVAL; } + if (log->size < log->header_size) { + ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x\n", log->size); + return -EINVAL; + } if ((char *)log + log->size > (char *)ivpu_bo_vaddr(bo) + ivpu_bo_size(bo)) { ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x\n", log->size); return -EINVAL; diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.c b/drivers/accel/ivpu/ivpu_hw_btrs.c index dac935164e11..a17c829adb89 100644 --- a/drivers/accel/ivpu/ivpu_hw_btrs.c +++ b/drivers/accel/ivpu/ivpu_hw_btrs.c @@ -927,7 +927,7 @@ static void diagnose_failure_mtl(struct ivpu_device *vdev) static void diagnose_failure_lnl(struct ivpu_device *vdev) { - u32 reg = REGB_RD32(VPU_HW_BTRS_MTL_INTERRUPT_STAT) & BTRS_LNL_IRQ_MASK; + u32 reg = REGB_RD32(VPU_HW_BTRS_LNL_INTERRUPT_STAT) & BTRS_LNL_IRQ_MASK; if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, ATS_ERR, reg)) { ivpu_err(vdev, "ATS_ERR_LOG1 0x%08x ATS_ERR_LOG2 0x%08x\n", diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index 4fc22ce4bd9a..8e3fc713891a 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -19,7 +19,6 @@ #include <linux/device.h> #include <linux/dmaengine.h> #include <linux/of.h> -#include <linux/of_irq.h> #include <linux/platform_device.h> #include <linux/phy/phy.h> #include <linux/libata.h> @@ -226,7 +225,6 @@ static int sata_dwc_dma_init_old(struct platform_device *pdev, struct sata_dwc_device *hsdev) { struct device *dev = &pdev->dev; - struct device_node *np = dev->of_node; hsdev->dma = devm_kzalloc(dev, sizeof(*hsdev->dma), GFP_KERNEL); if (!hsdev->dma) @@ -236,11 +234,9 @@ static int sata_dwc_dma_init_old(struct platform_device *pdev, hsdev->dma->id = pdev->id; /* Get SATA DMA interrupt number */ - hsdev->dma->irq = irq_of_parse_and_map(np, 1); - if (!hsdev->dma->irq) { - dev_err(dev, "no SATA DMA irq\n"); - return -ENODEV; - } + hsdev->dma->irq = platform_get_irq(pdev, 1); + if (hsdev->dma->irq < 0) + return hsdev->dma->irq; /* Get physical SATA DMA register base address */ hsdev->dma->regs = devm_platform_ioremap_resource(pdev, 1); @@ -398,8 +394,7 @@ static void clear_serror(struct ata_port *ap) static void clear_interrupt_bit(struct sata_dwc_device *hsdev, u32 bit) { - sata_dwc_writel(&hsdev->sata_dwc_regs->intpr, - sata_dwc_readl(&hsdev->sata_dwc_regs->intpr)); + sata_dwc_writel(&hsdev->sata_dwc_regs->intpr, bit); } static u32 qcmd_tag_to_mask(u8 tag) @@ -612,14 +607,9 @@ DRVSTILLBUSY: status = ap->ops->sff_check_status(ap); dev_dbg(ap->dev, "%s ATA status register=0x%x\n", __func__, status); - tag = 0; while (tag_mask) { - while (!(tag_mask & 0x00000001)) { - tag++; - tag_mask <<= 1; - } - - tag_mask &= (~0x00000001); + tag = __ffs(tag_mask); + tag_mask &= ~(1U << tag); qc = ata_qc_from_tag(ap, tag); if (unlikely(!qc)) { dev_err(ap->dev, "failed to get qc"); @@ -1126,7 +1116,6 @@ static const struct ata_port_info sata_dwc_port_info[] = { static int sata_dwc_probe(struct platform_device *ofdev) { struct device *dev = &ofdev->dev; - struct device_node *np = dev->of_node; struct sata_dwc_device *hsdev; u32 idr, versionr; char *ver = (char *)&versionr; @@ -1169,18 +1158,13 @@ static int sata_dwc_probe(struct platform_device *ofdev) /* Save dev for later use in dev_xxx() routines */ hsdev->dev = dev; - /* Enable SATA Interrupts */ - sata_dwc_enable_interrupts(hsdev); - /* Get SATA interrupt number */ - irq = irq_of_parse_and_map(np, 0); - if (!irq) { - dev_err(dev, "no SATA DMA irq\n"); - return -ENODEV; - } + irq = platform_get_irq(ofdev, 0); + if (irq < 0) + return irq; #ifdef CONFIG_SATA_DWC_OLD_DMA - if (!of_property_present(np, "dmas")) { + if (!of_property_present(dev->of_node, "dmas")) { err = sata_dwc_dma_init_old(ofdev, hsdev); if (err) return err; @@ -1204,6 +1188,8 @@ static int sata_dwc_probe(struct platform_device *ofdev) if (err) dev_err(dev, "failed to activate host"); + /* Enable SATA Interrupts */ + sata_dwc_enable_interrupts(hsdev); return 0; error_out: diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 310de0463beb..1faecef33009 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1113,6 +1113,7 @@ static void __loop_clr_fd(struct loop_device *lo) struct queue_limits lim; struct file *filp; gfp_t gfp = lo->old_gfp_mask; + int err; spin_lock_irq(&lo->lo_lock); filp = lo->lo_backing_file; @@ -1146,26 +1147,21 @@ static void __loop_clr_fd(struct loop_device *lo) disk_force_media_change(lo->lo_disk); - if (lo->lo_flags & LO_FLAGS_PARTSCAN) { - int err; - - /* - * open_mutex has been held already in release path, so don't - * acquire it if this function is called in such case. - * - * If the reread partition isn't from release path, lo_refcnt - * must be at least one and it can only become zero when the - * current holder is released. - */ - err = bdev_disk_changed(lo->lo_disk, false); - if (err) - pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", - __func__, lo->lo_number, err); - /* Device is gone, no point in returning error */ - } + /* + * Remove all partitions, including partitions added manually with + * BLKPG, which may exist even if LO_FLAGS_PARTSCAN is not set. + * + * open_mutex has been held already in release path, so don't acquire + * it here. + */ + err = bdev_disk_changed(lo->lo_disk, false); + if (err) + pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", + __func__, lo->lo_number, err); + /* Device is gone, no point in returning error */ /* - * lo->lo_state is set to Lo_unbound here after above partscan has + * lo->lo_state is set to Lo_unbound here after removing partitions has * finished. There cannot be anybody else entering __loop_clr_fd() as * Lo_rundown state protects us from all the other places trying to * change the 'lo' device. diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index 04ebe290bc78..10c496eaea2c 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -415,7 +415,7 @@ static int qca_tlv_check_data(struct hci_dev *hdev, idx = 0; data = tlv->data; - while (idx < length - sizeof(struct tlv_type_nvm)) { + while (idx + sizeof(struct tlv_type_nvm) <= length) { tlv_nvm = (struct tlv_type_nvm *)(data + idx); tag_id = le16_to_cpu(tlv_nvm->tag_id); diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 49ecb18fea45..7f54d2d2d13a 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -797,8 +797,9 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, } BT_DBG("length=%x offset=%x index %d", patch_length, patch_offset, i); - min_size = patch_offset + patch_length; - if (btrtl_dev->fw_len < min_size) + if (patch_length < sizeof(epatch_info->fw_version) || + patch_offset > btrtl_dev->fw_len || + patch_length > btrtl_dev->fw_len - patch_offset) return -EINVAL; /* Copy the firmware into a new buffer and write the version at diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 08c0a99a62c5..8f7ed469cac6 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2782,7 +2782,9 @@ static int btusb_setup_realtek(struct hci_dev *hdev) static int btusb_recv_event_realtek(struct hci_dev *hdev, struct sk_buff *skb) { - if (skb->data[0] == HCI_VENDOR_PKT && skb->data[2] == RTK_SUB_EVENT_CODE_COREDUMP) { + if (skb->len >= HCI_EVENT_HDR_SIZE + 1 && + skb->data[0] == HCI_VENDOR_PKT && + skb->data[2] == RTK_SUB_EVENT_CODE_COREDUMP) { struct rtk_dev_coredump_hdr hdr = { .code = RTK_DEVCOREDUMP_CODE_MEMDUMP, }; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index b2d1ee3a3d11..1222f97800f4 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -1087,6 +1087,10 @@ static void qca_controller_memdump(struct work_struct *work) if (!(qca_memdump->ram_dump_size)) { bt_dev_err(hu->hdev, "Rx invalid memdump size"); kfree(qca_memdump); + qca->qca_memdump = NULL; + qca->memdump_state = QCA_MEMDUMP_COLLECTED; + clear_and_wake_up_bit(QCA_MEMDUMP_COLLECTION, &qca->flags); + clear_bit(QCA_IBS_DISABLED, &qca->flags); kfree_skb(skb); mutex_unlock(&qca->hci_memdump_lock); return; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 507224c9ecd3..b898b6544069 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2586,6 +2586,9 @@ static void cpufreq_update_pressure(struct cpufreq_policy *policy) cpu = cpumask_first(policy->related_cpus); max_freq = arch_scale_freq_ref(cpu); + if (!max_freq) + max_freq = policy->cpuinfo.max_freq; + capped_freq = policy->max; /* diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 5a0eeb84d382..6e984c114d96 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1058,12 +1058,14 @@ static void hybrid_clear_cpu_capacity(unsigned int cpunum) static void hybrid_get_capacity_perf(struct cpudata *cpu) { + u64 hwp_cap = READ_ONCE(cpu->hwp_cap_cached); + if (READ_ONCE(global.no_turbo)) { - cpu->capacity_perf = cpu->pstate.max_pstate_physical; + cpu->capacity_perf = HWP_GUARANTEED_PERF(hwp_cap); return; } - cpu->capacity_perf = HWP_HIGHEST_PERF(READ_ONCE(cpu->hwp_cap_cached)); + cpu->capacity_perf = HWP_HIGHEST_PERF(hwp_cap); } static void hybrid_set_capacity_of_cpus(void) diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index bced421c0d65..08f57bc1294d 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -224,21 +224,22 @@ static int begin_cpu_udmabuf(struct dma_buf *buf, { struct udmabuf *ubuf = buf->priv; struct device *dev = ubuf->device->this_device; - int ret = 0; if (!ubuf->sg) { ubuf->sg = get_sg_table(dev, buf, direction); if (IS_ERR(ubuf->sg)) { + int ret; + ret = PTR_ERR(ubuf->sg); ubuf->sg = NULL; + return ret; } else { ubuf->sg_dir = direction; } - } else { - dma_sync_sgtable_for_cpu(dev, ubuf->sg, direction); } - return ret; + dma_sync_sgtable_for_cpu(dev, ubuf->sg, direction); + return 0; } static int end_cpu_udmabuf(struct dma_buf *buf, diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index bf729cde796a..5703667593a7 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -567,6 +567,9 @@ dpll_msg_add_pin_ref_sync(struct sk_buff *msg, struct dpll_pin *pin, if (!dpll_pin_available(ref_sync_pin)) continue; ref_sync_pin_priv = dpll_pin_on_dpll_priv(dpll, ref_sync_pin); + /* Pin may have been unregistered from this dpll already */ + if (!ref_sync_pin_priv) + continue; if (WARN_ON(!ops->ref_sync_get)) return -EOPNOTSUPP; ret = ops->ref_sync_get(pin, pin_priv, ref_sync_pin, diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 0f468362c288..8654b3365c9b 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -32,6 +32,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/kernel.h> +#include <linux/minmax.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/mutex.h> @@ -59,7 +60,9 @@ (FIELD_PREP(SENDER_ID_MASK, (s)) | FIELD_PREP(RECEIVER_ID_MASK, (r))) #define RXTX_MAP_MIN_BUFSZ_MASK GENMASK(1, 0) -#define RXTX_MAP_MIN_BUFSZ(x) ((x) & RXTX_MAP_MIN_BUFSZ_MASK) +#define RXTX_MAP_MAX_BUFSZ_MASK GENMASK(31, 16) +#define RXTX_MAP_MIN_BUFSZ(x) (FIELD_GET(RXTX_MAP_MIN_BUFSZ_MASK, (x))) +#define RXTX_MAP_MAX_BUFSZ(x) (FIELD_GET(RXTX_MAP_MAX_BUFSZ_MASK, (x))) #define FFA_MAX_NOTIFICATIONS 64 @@ -713,30 +716,39 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, struct ffa_composite_mem_region *composite; struct ffa_mem_region_addr_range *constituents; struct ffa_mem_region_attributes *ep_mem_access; - u32 idx, frag_len, length, buf_sz = 0, num_entries = sg_nents(args->sg); + u32 idx, frag_len, length, buf_sz = 0, num_entries = sg_nents(args->sg), ep_offset; + u32 emad_end, emad_size = ffa_emad_size_get(drv_info->version); mem_region->tag = args->tag; mem_region->flags = args->flags; mem_region->sender_id = drv_info->vm_id; mem_region->attributes = ffa_memory_attributes_get(func_id); + + ffa_mem_region_additional_setup(drv_info->version, mem_region); composite_offset = ffa_mem_desc_offset(buffer, args->nattrs, drv_info->version); + if (composite_offset + sizeof(*composite) > max_fragsize) + return -ENXIO; for (idx = 0; idx < args->nattrs; idx++) { - ep_mem_access = buffer + - ffa_mem_desc_offset(buffer, idx, drv_info->version); + ep_offset = ffa_mem_desc_offset(buffer, idx, drv_info->version); + if (check_add_overflow(ep_offset, emad_size, &emad_end)) + return -ENXIO; + + if (emad_end > max_fragsize) + return -ENXIO; + + ep_mem_access = buffer + ep_offset; + memset(ep_mem_access, 0, emad_size); ep_mem_access->receiver = args->attrs[idx].receiver; ep_mem_access->attrs = args->attrs[idx].attrs; ep_mem_access->composite_off = composite_offset; - ep_mem_access->flag = 0; - ep_mem_access->reserved = 0; ffa_emad_impdef_value_init(drv_info->version, ep_mem_access->impdef_val, args->attrs[idx].impdef_val); } mem_region->handle = 0; mem_region->ep_count = args->nattrs; - ffa_mem_region_additional_setup(drv_info->version, mem_region); composite = buffer + composite_offset; composite->total_pg_cnt = ffa_get_num_pages_sg(args->sg); @@ -769,7 +781,7 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, constituents = buffer; } - if ((void *)constituents - buffer > max_fragsize) { + if ((void *)constituents + sizeof(*constituents) - buffer > max_fragsize) { pr_err("Memory Region Fragment > Tx Buffer size\n"); return -EFAULT; } @@ -778,7 +790,7 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, constituents->pg_cnt = args->sg->length / FFA_PAGE_SIZE; constituents->reserved = 0; constituents++; - frag_len += sizeof(struct ffa_mem_region_addr_range); + frag_len += sizeof(*constituents); } while ((args->sg = sg_next(args->sg))); return ffa_transmit_fragment(func_id, addr, buf_sz, frag_len, @@ -1139,7 +1151,7 @@ static int ffa_partition_info_get(const char *uuid_str, uuid_t uuid; struct ffa_partition_info *pbuf; - if (uuid_parse(uuid_str, &uuid)) { + if (!uuid_str || uuid_parse(uuid_str, &uuid)) { pr_err("invalid uuid (%s)\n", uuid_str); return -ENODEV; } @@ -2101,7 +2113,7 @@ static int ffa_probe(struct platform_device *pdev) { int ret; u32 buf_sz; - size_t rxtx_bufsz = SZ_4K; + size_t rxtx_min_bufsz = SZ_4K, rxtx_max_bufsz = 0, rxtx_bufsz; if (IS_BUILTIN(CONFIG_ARM_FFA_TRANSPORT) && is_protected_kvm_enabled() && !is_pkvm_initialized()) @@ -2132,15 +2144,18 @@ static int ffa_probe(struct platform_device *pdev) ret = ffa_features(FFA_FN_NATIVE(RXTX_MAP), 0, &buf_sz, NULL); if (!ret) { if (RXTX_MAP_MIN_BUFSZ(buf_sz) == 1) - rxtx_bufsz = SZ_64K; + rxtx_min_bufsz = SZ_64K; else if (RXTX_MAP_MIN_BUFSZ(buf_sz) == 2) - rxtx_bufsz = SZ_16K; + rxtx_min_bufsz = SZ_16K; else - rxtx_bufsz = SZ_4K; + rxtx_min_bufsz = SZ_4K; + + rxtx_max_bufsz = RXTX_MAP_MAX_BUFSZ(buf_sz) * SZ_4K; + if (rxtx_max_bufsz != 0 && rxtx_max_bufsz < rxtx_min_bufsz) + rxtx_max_bufsz = rxtx_min_bufsz; } - rxtx_bufsz = PAGE_ALIGN(rxtx_bufsz); - drv_info->rxtx_bufsz = rxtx_bufsz; + rxtx_bufsz = min_not_zero(PAGE_ALIGN(rxtx_min_bufsz), rxtx_max_bufsz); drv_info->rx_buffer = alloc_pages_exact(rxtx_bufsz, GFP_KERNEL); if (!drv_info->rx_buffer) { ret = -ENOMEM; @@ -2156,10 +2171,17 @@ static int ffa_probe(struct platform_device *pdev) ret = ffa_rxtx_map(virt_to_phys(drv_info->tx_buffer), virt_to_phys(drv_info->rx_buffer), rxtx_bufsz / FFA_PAGE_SIZE); + if (ret == -EINVAL && !rxtx_max_bufsz && rxtx_min_bufsz < rxtx_bufsz) { + rxtx_bufsz = rxtx_min_bufsz; + ret = ffa_rxtx_map(virt_to_phys(drv_info->tx_buffer), + virt_to_phys(drv_info->rx_buffer), + rxtx_bufsz / FFA_PAGE_SIZE); + } if (ret) { pr_err("failed to register FFA RxTx buffers\n"); goto free_pages; } + drv_info->rxtx_bufsz = rxtx_bufsz; mutex_init(&drv_info->rx_lock); mutex_init(&drv_info->tx_lock); diff --git a/drivers/firmware/arm_scmi/Kconfig b/drivers/firmware/arm_scmi/Kconfig index e3fb36825978..783c24a20e29 100644 --- a/drivers/firmware/arm_scmi/Kconfig +++ b/drivers/firmware/arm_scmi/Kconfig @@ -96,7 +96,7 @@ config ARM_SCMI_POWER_CONTROL firmware. This driver can also be built as a module. If so, the module will be - called scmi_power_control. Note this may needed early in boot to catch - early shutdown/reboot SCMI requests. + called scmi_power_control. Note this may be needed early in boot to + catch early shutdown/reboot SCMI requests. endmenu diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c index 42e666a628c7..0278705d809e 100644 --- a/drivers/firmware/arm_scmi/clock.c +++ b/drivers/firmware/arm_scmi/clock.c @@ -718,7 +718,7 @@ static int scmi_clock_rate_set(const struct scmi_protocol_handle *ph, static int scmi_clock_determine_rate(const struct scmi_protocol_handle *ph, u32 clk_id, unsigned long *rate) { - u64 fmin, fmax, ftmp; + u64 fmin, fmax, ftmp, step; struct scmi_clock_info *clk; struct scmi_clock_desc *clkd; struct clock_info *ci = ph->get_priv(ph); @@ -749,11 +749,14 @@ static int scmi_clock_determine_rate(const struct scmi_protocol_handle *ph, return 0; } + step = clkd->r.rates[RATE_STEP]; + if (!step) + return -EINVAL; + ftmp = *rate - fmin; - ftmp += clkd->r.rates[RATE_STEP] - 1; /* to round up */ - ftmp = div64_ul(ftmp, clkd->r.rates[RATE_STEP]); + ftmp = DIV64_U64_ROUND_UP(ftmp, step); - *rate = ftmp * clkd->r.rates[RATE_STEP] + fmin; + *rate = ftmp * step + fmin; return 0; } diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c index 40ec184eedae..0a192cf2deab 100644 --- a/drivers/firmware/arm_scmi/notify.c +++ b/drivers/firmware/arm_scmi/notify.c @@ -600,9 +600,9 @@ int scmi_notify(const struct scmi_handle *handle, u8 proto_id, u8 evt_id, return -EINVAL; } if (kfifo_avail(&r_evt->proto->equeue.kfifo) < sizeof(eh) + len) { - dev_warn(handle->dev, - "queue full, dropping proto_id:%d evt_id:%d ts:%lld\n", - proto_id, evt_id, ktime_to_ns(ts)); + dev_warn_ratelimited(handle->dev, + "queue full, dropping proto_id:%d evt_id:%d ts:%lld\n", + proto_id, evt_id, ktime_to_ns(ts)); return -ENOMEM; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index aa039e148a5e..8525c45ab209 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -372,19 +372,59 @@ static bool amdgpu_read_disabled_bios(struct amdgpu_device *adev) } #ifdef CONFIG_ACPI +/** + * amdgpu_acpi_vfct_match() - Check if a VFCT entry matches the device + * @adev: AMDGPU device + * @vhdr: VFCT image header to check + * + * VFCT entries contain the PCI bus number as recorded during BIOS POST. + * On systems where the kernel renumbers PCI buses (e.g. pci=realloc or + * resource conflicts), the runtime bus number may differ from the POST + * value. Match by device identity (vendor + device + function) and use + * the bus number as a preference: exact bus match is preferred, but when + * the bus numbers disagree we accept the entry if the device identity + * matches. + * + * Returns: 0 on match, -ENODEV on no match + */ +static int amdgpu_acpi_vfct_match(struct amdgpu_device *adev, + VFCT_IMAGE_HEADER *vhdr) +{ + /* Vendor and device IDs must always match */ + if (vhdr->VendorID != adev->pdev->vendor || + vhdr->DeviceID != adev->pdev->device) + return -ENODEV; + + if (vhdr->PCIDevice != PCI_SLOT(adev->pdev->devfn) || + vhdr->PCIFunction != PCI_FUNC(adev->pdev->devfn)) + return -ENODEV; + + /* Exact bus number match - preferred */ + if (vhdr->PCIBus == adev->pdev->bus->number) + return 0; + + /* Bus mismatch but device identity matches (PCI renumbering case) */ + dev_notice(adev->dev, + "VFCT bus number mismatch: table %u != runtime %u, matching by device identity (vendor 0x%04x device 0x%04x)\n", + vhdr->PCIBus, adev->pdev->bus->number, + adev->pdev->vendor, adev->pdev->device); + return 0; +} + static bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev) { struct acpi_table_header *hdr; acpi_size tbl_size; UEFI_ACPI_VFCT *vfct; unsigned int offset; + bool r = false; if (!ACPI_SUCCESS(acpi_get_table("VFCT", 1, &hdr))) return false; tbl_size = hdr->length; if (tbl_size < sizeof(UEFI_ACPI_VFCT)) { dev_info(adev->dev, "ACPI VFCT table present but broken (too short #1),skipping\n"); - return false; + goto out; } vfct = (UEFI_ACPI_VFCT *)hdr; @@ -397,36 +437,36 @@ static bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev) offset += sizeof(VFCT_IMAGE_HEADER); if (offset > tbl_size) { dev_info(adev->dev, "ACPI VFCT image header truncated,skipping\n"); - return false; + goto out; } offset += vhdr->ImageLength; if (offset > tbl_size) { dev_info(adev->dev, "ACPI VFCT image truncated,skipping\n"); - return false; + goto out; } if (vhdr->ImageLength && - vhdr->PCIBus == adev->pdev->bus->number && - vhdr->PCIDevice == PCI_SLOT(adev->pdev->devfn) && - vhdr->PCIFunction == PCI_FUNC(adev->pdev->devfn) && - vhdr->VendorID == adev->pdev->vendor && - vhdr->DeviceID == adev->pdev->device) { + !amdgpu_acpi_vfct_match(adev, vhdr)) { adev->bios = kmemdup(&vbios->VbiosContent, vhdr->ImageLength, GFP_KERNEL); if (!check_atom_bios(adev, vhdr->ImageLength)) { amdgpu_bios_release(adev); - return false; + goto out; } adev->bios_size = vhdr->ImageLength; - return true; + r = true; + goto out; } } dev_info(adev->dev, "ACPI VFCT table present but broken (too short #2),skipping\n"); - return false; + +out: + acpi_put_table(hdr); + return r; } #else static inline bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index e77db76b48b8..6480a344006d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -234,6 +234,9 @@ amdgpu_devcoredump_print_ibs(struct drm_printer *p, drm_printf(p, "\nIB #%d 0x%llx %d dw\n", i, coredump->ibs[i].gpu_addr, coredump->ibs[i].ib_size_dw); + + for (int j = 0; j < coredump->ibs[i].ib_size_dw; j++) + drm_printf(p, "0xffffffff\n"); } return; } @@ -355,10 +358,14 @@ amdgpu_devcoredump_format(char *buffer, size_t count, struct amdgpu_coredump_inf drm_printf(&p, "kernel: %s\n", init_utsname()->release); drm_printf(&p, "module: " KBUILD_MODNAME "\n"); drm_printf(&p, "time: %ptSp\n", &coredump->reset_time); + drm_printf(&p, "pasid: %u\n", coredump->pasid); + drm_printf(&p, "vmid: %u\n", coredump->vmid); if (coredump->reset_task_info.task.pid) - drm_printf(&p, "process_name: %s PID: %d\n", + drm_printf(&p, "process_name: %s TGID: %d thread: %s PID: %d\n", coredump->reset_task_info.process_name, + coredump->reset_task_info.tgid, + coredump->reset_task_info.task.comm, coredump->reset_task_info.task.pid); /* SOC Information */ @@ -562,6 +569,7 @@ void amdgpu_coredump(struct amdgpu_device *adev, bool skip_vram_check, amdgpu_vm_put_task_info(ti); } coredump->pasid = job->pasid; + coredump->vmid = job->vmid; coredump->num_ibs = job->num_ibs; for (i = 0; i < job->num_ibs; ++i) { coredump->ibs[i].gpu_addr = job->ibs[i].gpu_addr; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.h index 2371e20fc68b..63f27337c09a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.h @@ -63,6 +63,7 @@ struct amdgpu_coredump_info { char *formatted; unsigned int pasid; + unsigned int vmid; int num_ibs; struct amdgpu_coredump_ib_info ibs[] __counted_by(num_ibs); }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 53335ca96b1d..e5f26e5892ba 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1323,6 +1323,15 @@ static bool amdgpu_device_pcie_dynamic_switching_supported(struct amdgpu_device if (c->x86_vendor == X86_VENDOR_INTEL) return false; + + /* + * AMD Ryzen Pinnacle Ridge (Zen+, family 0x17 model 0x08) CPUs don't + * support PCIe dynamic speed switching. + * https://gitlab.freedesktop.org/drm/amd/-/work_items/5436 + */ + if (c->x86_vendor == X86_VENDOR_AMD && c->x86 == 0x17 && + c->x86_model == 0x08) + return false; #endif return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 7b9bb998906d..2860f12915c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -3137,9 +3137,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 5, 3): case IP_VERSION(11, 5, 4): case IP_VERSION(11, 5, 6): + adev->family = AMDGPU_FAMILY_GC_11_5_0; + break; case IP_VERSION(11, 7, 0): case IP_VERSION(11, 7, 1): - adev->family = AMDGPU_FAMILY_GC_11_5_0; + adev->family = AMDGPU_FAMILY_GC_11_5_4; break; case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index f98bfba59a2c..718937777e53 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -276,10 +276,12 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev, goto error_free; } - r = amdgpu_bo_pin(*bo_ptr, domain); - if (r) { - dev_err(adev->dev, "(%d) kernel bo pin failed\n", r); - goto error_unreserve; + if (free) { + r = amdgpu_bo_pin(*bo_ptr, domain); + if (r) { + dev_err(adev->dev, "(%d) kernel bo pin failed\n", r); + goto error_unreserve; + } } r = amdgpu_ttm_alloc_gart(&(*bo_ptr)->tbo); @@ -302,7 +304,8 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev, return 0; error_unpin: - amdgpu_bo_unpin(*bo_ptr); + if (free) + amdgpu_bo_unpin(*bo_ptr); error_unreserve: amdgpu_bo_unreserve(*bo_ptr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 025625e7e800..eb8bbfc7e6d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -2684,12 +2684,22 @@ void amdgpu_sdma_set_buffer_funcs_scheds(struct amdgpu_device *adev, return; } - /* Navi1x's workaround requires us to limit to a single SDMA sched - * for ttm. - */ hub = &adev->vmhub[AMDGPU_GFXHUB(0)]; - adev->mman.num_buffer_funcs_scheds = hub->sdma_invalidation_workaround ? - 1 : n; + + /* + * Allow using multiple SDMA schedulers only on GPUs where + * we are allowed to do concurrent VM flushes. + * This consideration is necessary because all GART windows + * are mapped in VMID 0 (the kernel VMID) so each buffer + * entity would flush VMID 0 concurrently. + * + * Also consider the SDMA invalidation workaround on + * Navi 1x GPUs, which also prevents us from using + * multiple SDMA engines on VMID 0 at the same time. + */ + adev->mman.num_buffer_funcs_scheds = + (adev->vm_manager.concurrent_flush && + !hub->sdma_invalidation_workaround) ? n : 1; } #if defined(CONFIG_DEBUG_FS) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index d854343b3734..572f2949cb64 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -1376,16 +1376,19 @@ void amdgpu_userq_pre_reset(struct amdgpu_device *adev) /* TODO: We probably need a new lock for the queue state */ xa_for_each(&adev->userq_doorbell_xa, queue_id, queue) { - if (queue->state != AMDGPU_USERQ_STATE_MAPPED) - continue; - - userq_funcs = adev->userq_funcs[queue->queue_type]; - userq_funcs->unmap(queue); - /* just mark all queues as hung at this point. - * if unmap succeeds, we could map again - * in amdgpu_userq_post_reset() if vram is not lost + if (queue->state == AMDGPU_USERQ_STATE_MAPPED) { + userq_funcs = adev->userq_funcs[queue->queue_type]; + userq_funcs->unmap(queue); + /* just mark all queues as hung at this point. + * if unmap succeeds, we could map again + * in amdgpu_userq_post_reset() if vram is not lost + */ + queue->state = AMDGPU_USERQ_STATE_HUNG; + } + /* Force-complete any pending fence regardless of queue state so + * that eviction/suspend and queue teardown waiters don't block + * forever on a fence that will never signal after the reset. */ - queue->state = AMDGPU_USERQ_STATE_HUNG; amdgpu_userq_fence_driver_force_completion(queue); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index bb99b7c3a010..f224d33c4bc4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -855,12 +855,10 @@ void amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, job->oa_size); } - if (vm_flush_needed || pasid_mapping_needed || cleaner_shader_needed) { - amdgpu_fence_emit(ring, job->hw_vm_fence, 0); - fence = &job->hw_vm_fence->base; - /* get a ref for the job */ - dma_fence_get(fence); - } + amdgpu_fence_emit(ring, job->hw_vm_fence, 0); + fence = &job->hw_vm_fence->base; + /* get a ref for the job */ + dma_fence_get(fence); if (vm_flush_needed) { mutex_lock(&id_mgr->lock); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 678ec611a4f2..67137679a901 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -3103,6 +3103,7 @@ static void deallocate_hiq_sdma_mqd(struct kfd_node *dev, struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) { struct device_queue_manager *dqm; + int i; pr_debug("Loading device queue manager\n"); @@ -3231,6 +3232,9 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) deallocate_hiq_sdma_mqd(dev, &dqm->hiq_sdma_mqd); out_free: + for (i = 0; i < KFD_MQD_TYPE_MAX; i++) + kfree(dqm->mqd_mgrs[i]); + kfree(dqm); return NULL; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c index 28354a4e5dd5..98a5512b701b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c @@ -23,6 +23,7 @@ */ #include <linux/slab.h> +#include <linux/overflow.h> #include "kfd_priv.h" #include "kfd_topology.h" #include "kfd_svm.h" @@ -235,7 +236,7 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope struct kfd_topology_device *topo_dev; u64 expected_queue_size; struct amdgpu_vm *vm; - u32 total_cwsr_size; + u64 total_cwsr_size; int err; topo_dev = kfd_topology_device_by_id(pdd->dev->id); @@ -308,8 +309,14 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope goto out_err_unreserve; } - total_cwsr_size = (properties->ctx_save_restore_area_size + - topo_dev->node_props.debug_memory_size) * NUM_XCC(pdd->dev->xcc_mask); + total_cwsr_size = (u64)properties->ctx_save_restore_area_size + + topo_dev->node_props.debug_memory_size; + if (check_mul_overflow(total_cwsr_size, + NUM_XCC(pdd->dev->xcc_mask), + &total_cwsr_size)) { + err = -EINVAL; + goto out_err_unreserve; + } total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE); err = kfd_queue_buffer_get(vm, (void *)properties->ctx_save_restore_area_address, @@ -344,7 +351,7 @@ out_err_release: int kfd_queue_release_buffers(struct kfd_process_device *pdd, struct queue_properties *properties) { struct kfd_topology_device *topo_dev; - u32 total_cwsr_size; + u64 total_cwsr_size; kfd_queue_buffer_put(&properties->wptr_bo); kfd_queue_buffer_put(&properties->rptr_bo); @@ -355,8 +362,12 @@ int kfd_queue_release_buffers(struct kfd_process_device *pdd, struct queue_prope topo_dev = kfd_topology_device_by_id(pdd->dev->id); if (!topo_dev) return -EINVAL; - total_cwsr_size = (properties->ctx_save_restore_area_size + - topo_dev->node_props.debug_memory_size) * NUM_XCC(pdd->dev->xcc_mask); + total_cwsr_size = (u64)properties->ctx_save_restore_area_size + + topo_dev->node_props.debug_memory_size; + if (check_mul_overflow(total_cwsr_size, + NUM_XCC(pdd->dev->xcc_mask), + &total_cwsr_size)) + return -EINVAL; total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE); kfd_queue_buffer_svm_put(pdd, properties->ctx_save_restore_area_address, total_cwsr_size); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 18145d78334f..9c564cd5edee 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -580,89 +580,25 @@ static void schedule_dc_vmin_vmax(struct amdgpu_device *adev, queue_work(system_percpu_wq, &offload_work->work); } -static void dm_vupdate_high_irq(void *interrupt_params) -{ - struct common_irq_params *irq_params = interrupt_params; - struct amdgpu_device *adev = irq_params->adev; - struct amdgpu_crtc *acrtc; - struct drm_device *drm_dev; - struct drm_vblank_crtc *vblank; - ktime_t frame_duration_ns, previous_timestamp; - unsigned long flags; - int vrr_active; - - acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VUPDATE); - - if (acrtc) { - vrr_active = amdgpu_dm_crtc_vrr_active_irq(acrtc); - drm_dev = acrtc->base.dev; - vblank = drm_crtc_vblank_crtc(&acrtc->base); - previous_timestamp = atomic64_read(&irq_params->previous_timestamp); - frame_duration_ns = vblank->time - previous_timestamp; - - if (frame_duration_ns > 0) { - trace_amdgpu_refresh_rate_track(acrtc->base.index, - frame_duration_ns, - ktime_divns(NSEC_PER_SEC, frame_duration_ns)); - atomic64_set(&irq_params->previous_timestamp, vblank->time); - } - - drm_dbg_vbl(drm_dev, - "crtc:%d, vupdate-vrr:%d\n", acrtc->crtc_id, - vrr_active); - - /* Core vblank handling is done here after end of front-porch in - * vrr mode, as vblank timestamping will give valid results - * while now done after front-porch. This will also deliver - * page-flip completion events that have been queued to us - * if a pageflip happened inside front-porch. - */ - if (vrr_active && acrtc->dm_irq_params.stream) { - bool replay_en = acrtc->dm_irq_params.stream->link->replay_settings.replay_feature_enabled; - bool psr_en = acrtc->dm_irq_params.stream->link->psr_settings.psr_feature_enabled; - bool fs_active_var_en = acrtc->dm_irq_params.freesync_config.state - == VRR_STATE_ACTIVE_VARIABLE; - - amdgpu_dm_crtc_handle_vblank(acrtc); - - /* BTR processing for pre-DCE12 ASICs */ - if (adev->family < AMDGPU_FAMILY_AI) { - spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); - mod_freesync_handle_v_update( - adev->dm.freesync_module, - acrtc->dm_irq_params.stream, - &acrtc->dm_irq_params.vrr_params); - - if (fs_active_var_en || (!fs_active_var_en && !replay_en && !psr_en)) { - schedule_dc_vmin_vmax(adev, - acrtc->dm_irq_params.stream, - &acrtc->dm_irq_params.vrr_params.adjust); - } - spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); - } - } - } -} - /** - * dm_crtc_high_irq() - Handles CRTC interrupt - * @interrupt_params: used for determining the CRTC instance + * dm_crtc_high_irq_handler() - Common OTG vblank/flip event handling + * @adev: amdgpu device + * @acrtc: the CRTC to service * - * Handles the CRTC/VSYNC interrupt by notfying DRM's VBLANK - * event handler. + * Performs writeback completion, vblank event handling, CRC processing, VRR BTR + * updates and pageflip completion delivery. + * + * On DCN this is driven by VUPDATE_NO_LOCK (the register latch point) from + * dm_vupdate_high_irq(); on DCE it is driven by VLINE0 at the start of vblank + * from dm_crtc_high_irq(). */ -static void dm_crtc_high_irq(void *interrupt_params) +static void dm_crtc_high_irq_handler(struct amdgpu_device *adev, + struct amdgpu_crtc *acrtc) { - struct common_irq_params *irq_params = interrupt_params; - struct amdgpu_device *adev = irq_params->adev; struct drm_writeback_job *job; - struct amdgpu_crtc *acrtc; unsigned long flags; int vrr_active; - - acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK); - if (!acrtc) - return; + bool is_dcn = amdgpu_ip_version(adev, DCE_HWIP, 0) != 0; if (acrtc->wb_conn) { spin_lock_irqsave(&acrtc->wb_conn->job_lock, flags); @@ -699,12 +635,17 @@ static void dm_crtc_high_irq(void *interrupt_params) vrr_active, acrtc->dm_irq_params.active_planes); /** - * Core vblank handling at start of front-porch is only possible - * in non-vrr mode, as only there vblank timestamping will give - * valid results while done in front-porch. Otherwise defer it - * to dm_vupdate_high_irq after end of front-porch. + * Core vblank handling. + * + * On DCN this handler runs at VUPDATE_NO_LOCK, the register latch + * point, which is the correct place to timestamp both VRR and non-VRR + * vblanks. + * + * On DCE this handler runs at the start of front-porch, where only + * non-VRR timestamping is valid; VRR vblank is deferred to + * dm_vupdate_high_irq() after end of front-porch. */ - if (!vrr_active) + if (is_dcn || !vrr_active) amdgpu_dm_crtc_handle_vblank(acrtc); /** @@ -737,18 +678,33 @@ static void dm_crtc_high_irq(void *interrupt_params) } /* - * If there aren't any active_planes then DCH HUBP may be clock-gated. - * In that case, pageflip completion interrupts won't fire and pageflip - * completion events won't get delivered. Prevent this by sending - * pending pageflip events from here if a flip is still pending. + * Deliver pageflip completion events (DCN only). * - * If any planes are enabled, use dm_pflip_high_irq() instead, to - * avoid race conditions between flip programming and completion, - * which could cause too early flip completion events. + * Since GRPH_PFLIP is not used, VUPDATE_NO_LOCK is the flip latch + * point. Deliver any pending pageflip completion event from here, + * once HW has consumed the new address (the OTG no longer reports a + * pending flip). + * + * Also handle the case here where there aren't any active planes and + * DCN HUBP may be clock-gated, so the flip-pending status may be + * undefined. */ - if (adev->family >= AMDGPU_FAMILY_RV && - acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && - acrtc->dm_irq_params.active_planes == 0) { + if (is_dcn && acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && + acrtc->event) { + + if (!dc_get_flip_pending_on_otg(adev->dm.dc, acrtc->otg_inst)) { + drm_crtc_send_vblank_event(&acrtc->base, acrtc->event); + acrtc->event = NULL; + drm_crtc_vblank_put(&acrtc->base); + acrtc->pflip_status = AMDGPU_FLIP_NONE; + } + /* + * If the flip is still pending, leave it armed and + * retry on the next vupdate. + */ + } else if (is_dcn && acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && + acrtc->dm_irq_params.active_planes == 0) { + if (acrtc->event) { drm_crtc_send_vblank_event(&acrtc->base, acrtc->event); acrtc->event = NULL; @@ -760,6 +716,104 @@ static void dm_crtc_high_irq(void *interrupt_params) spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); } +static void dm_vupdate_high_irq(void *interrupt_params) +{ + struct common_irq_params *irq_params = interrupt_params; + struct amdgpu_device *adev = irq_params->adev; + struct amdgpu_crtc *acrtc; + struct drm_device *drm_dev; + struct drm_vblank_crtc *vblank; + ktime_t frame_duration_ns, previous_timestamp; + unsigned long flags; + int vrr_active; + + acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VUPDATE); + if (!acrtc) + return; + + vrr_active = amdgpu_dm_crtc_vrr_active_irq(acrtc); + drm_dev = acrtc->base.dev; + vblank = drm_crtc_vblank_crtc(&acrtc->base); + previous_timestamp = atomic64_read(&irq_params->previous_timestamp); + frame_duration_ns = vblank->time - previous_timestamp; + + if (frame_duration_ns > 0) { + trace_amdgpu_refresh_rate_track(acrtc->base.index, + frame_duration_ns, + ktime_divns(NSEC_PER_SEC, frame_duration_ns)); + atomic64_set(&irq_params->previous_timestamp, vblank->time); + } + + drm_dbg_vbl(drm_dev, + "crtc:%d, vupdate-vrr:%d\n", acrtc->crtc_id, + vrr_active); + + /* + * On DCN, VUPDATE_NO_LOCK is the single OTG interrupt used to deliver + * vblank and pageflip completion events; VSTARTUP and GRPH_PFLIP are + * not used. Run the full handler here. + */ + if (amdgpu_ip_version(adev, DCE_HWIP, 0) != 0) { + dm_crtc_high_irq_handler(adev, acrtc); + return; + } + + /* DCE only below. */ + + /* Core vblank handling is done here after end of front-porch in + * vrr mode, as vblank timestamping will give valid results + * while now done after front-porch. This will also deliver + * page-flip completion events that have been queued to us + * if a pageflip happened inside front-porch. + */ + if (vrr_active && acrtc->dm_irq_params.stream) { + bool replay_en = acrtc->dm_irq_params.stream->link->replay_settings.replay_feature_enabled; + bool psr_en = acrtc->dm_irq_params.stream->link->psr_settings.psr_feature_enabled; + bool fs_active_var_en = acrtc->dm_irq_params.freesync_config.state + == VRR_STATE_ACTIVE_VARIABLE; + + amdgpu_dm_crtc_handle_vblank(acrtc); + + /* BTR processing for pre-DCE12 ASICs */ + if (adev->family < AMDGPU_FAMILY_AI) { + spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); + mod_freesync_handle_v_update( + adev->dm.freesync_module, + acrtc->dm_irq_params.stream, + &acrtc->dm_irq_params.vrr_params); + + if (fs_active_var_en || (!fs_active_var_en && !replay_en && !psr_en)) { + schedule_dc_vmin_vmax(adev, + acrtc->dm_irq_params.stream, + &acrtc->dm_irq_params.vrr_params.adjust); + } + spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); + } + } +} + +/** + * dm_crtc_high_irq() - Handles CRTC interrupt + * @interrupt_params: used for determining the CRTC instance + * + * Handles the CRTC/VSYNC interrupt by notifying DRM's VBLANK event handler. + * + * Used on DCE (VLINE0, set to vblank start). On DCN the equivalent handling is + * driven by VUPDATE_NO_LOCK in dm_vupdate_high_irq(). + */ +static void dm_crtc_high_irq(void *interrupt_params) +{ + struct common_irq_params *irq_params = interrupt_params; + struct amdgpu_device *adev = irq_params->adev; + struct amdgpu_crtc *acrtc; + + acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK); + if (!acrtc) + return; + + dm_crtc_high_irq_handler(adev, acrtc); +} + #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) /** * dm_dcn_vertical_interrupt0_high_irq() - Handles OTG Vertical interrupt0 for @@ -3298,6 +3352,13 @@ static void dm_gpureset_toggle_interrupts(struct amdgpu_device *adev, */ if (!dc_interrupt_set(adev->dm.dc, irq_source, enable)) drm_warn(adev_to_drm(adev), "Failed to %sable vblank interrupt\n", enable ? "en" : "dis"); + + } else if (acrtc && state->stream_status[i].plane_count != 0) { + /* DCN only needs to toggle VUPDATE_NO_LOCK */ + rc = amdgpu_dm_crtc_set_vupdate_irq(&acrtc->base, enable); + if (rc) + drm_warn(adev_to_drm(adev), "Failed to %sable vupdate interrupt\n", + enable ? "en" : "dis"); } } @@ -4069,6 +4130,8 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) caps->ext_caps = &aconnector->dc_link->dpcd_sink_ext_caps; caps->aux_support = false; + panel_backlight_quirk = drm_get_panel_backlight_quirk(aconnector->drm_edid); + if (caps->ext_caps->bits.oled == 1 /* * || @@ -4081,6 +4144,9 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) caps->aux_support = false; else if (amdgpu_backlight == 1) caps->aux_support = true; + else if (!IS_ERR_OR_NULL(panel_backlight_quirk) && + panel_backlight_quirk->force_pwm) + caps->aux_support = false; if (caps->aux_support) aconnector->dc_link->backlight_control_type = BACKLIGHT_CONTROL_AMD_AUX; @@ -4096,8 +4162,6 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) else caps->aux_min_input_signal = 1; - panel_backlight_quirk = - drm_get_panel_backlight_quirk(aconnector->drm_edid); if (!IS_ERR_OR_NULL(panel_backlight_quirk)) { if (panel_backlight_quirk->min_brightness) { caps->min_input_signal = @@ -4863,38 +4927,6 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev) * for acknowledging and handling. */ - /* Use VSTARTUP interrupt */ - for (i = DCN_1_0__SRCID__DC_D1_OTG_VSTARTUP; - i <= DCN_1_0__SRCID__DC_D1_OTG_VSTARTUP + adev->mode_info.num_crtc - 1; - i++) { - r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->crtc_irq); - - if (r) { - drm_err(adev_to_drm(adev), "Failed to add crtc irq id!\n"); - return r; - } - - int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT; - int_params.irq_source = - dc_interrupt_to_irq_source(dc, i, 0); - - if (int_params.irq_source == DC_IRQ_SOURCE_INVALID || - int_params.irq_source < DC_IRQ_SOURCE_VBLANK1 || - int_params.irq_source > DC_IRQ_SOURCE_VBLANK6) { - drm_err(adev_to_drm(adev), "Failed to register vblank irq!\n"); - return -EINVAL; - } - - c_irq_params = &adev->dm.vblank_params[int_params.irq_source - DC_IRQ_SOURCE_VBLANK1]; - - c_irq_params->adev = adev; - c_irq_params->irq_src = int_params.irq_source; - - if (!amdgpu_dm_irq_register_interrupt(adev, &int_params, - dm_crtc_high_irq, c_irq_params)) - return -ENOMEM; - } - /* Use otg vertical line interrupt */ #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) for (i = 0; i <= adev->mode_info.num_crtc - 1; i++) { @@ -4966,37 +4998,6 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev) return -ENOMEM; } - /* Use GRPH_PFLIP interrupt */ - for (i = DCN_1_0__SRCID__HUBP0_FLIP_INTERRUPT; - i <= DCN_1_0__SRCID__HUBP0_FLIP_INTERRUPT + dc->caps.max_otg_num - 1; - i++) { - r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->pageflip_irq); - if (r) { - drm_err(adev_to_drm(adev), "Failed to add page flip irq id!\n"); - return r; - } - - int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT; - int_params.irq_source = - dc_interrupt_to_irq_source(dc, i, 0); - - if (int_params.irq_source == DC_IRQ_SOURCE_INVALID || - int_params.irq_source < DC_IRQ_SOURCE_PFLIP_FIRST || - int_params.irq_source > DC_IRQ_SOURCE_PFLIP_LAST) { - drm_err(adev_to_drm(adev), "Failed to register pflip irq!\n"); - return -EINVAL; - } - - c_irq_params = &adev->dm.pflip_params[int_params.irq_source - DC_IRQ_SOURCE_PFLIP_FIRST]; - - c_irq_params->adev = adev; - c_irq_params->irq_src = int_params.irq_source; - - if (!amdgpu_dm_irq_register_interrupt(adev, &int_params, - dm_pflip_high_irq, c_irq_params)) - return -ENOMEM; - } - /* HPD */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, DCN_1_0__SRCID__DC_HPD1_INT, &adev->hpd_irq); @@ -5563,11 +5564,11 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) caps = &dm->backlight_caps[aconnector->bl_idx]; if (get_brightness_range(caps, &min, &max)) { if (power_supply_is_system_supplied() > 0) - props.brightness = DIV_ROUND_CLOSEST((max - min) * caps->ac_level, 100); + props.brightness = DIV_ROUND_CLOSEST(max * caps->ac_level, 100); else - props.brightness = DIV_ROUND_CLOSEST((max - min) * caps->dc_level, 100); + props.brightness = DIV_ROUND_CLOSEST(max * caps->dc_level, 100); /* min is zero, so max needs to be adjusted */ - props.max_brightness = max - min; + props.max_brightness = max; drm_dbg(drm, "Backlight caps: min: %d, max: %d, ac %d, dc %d\n", min, max, caps->ac_level, caps->dc_level); } else @@ -9674,21 +9675,9 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, if (acrtc_state) { timing = &acrtc_state->stream->timing; - if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= - IP_VERSION(3, 2, 0) && - !(adev->flags & AMD_IS_APU)) { - /* - * DGPUs NV3x and newer that support idle optimizations - * experience intermittent flip-done timeouts on cursor - * updates. Restore 5s offdelay behavior for now. - * - * Discussion on the issue: - * https://lore.kernel.org/amd-gfx/20260217191632.1243826-1-sysdadmin@m1k.cloud/ - */ - config.offdelay_ms = 5000; - config.disable_immediate = false; - } else if (amdgpu_ip_version(adev, DCE_HWIP, 0) < - IP_VERSION(3, 5, 0)) { + if (amdgpu_ip_version(adev, DCE_HWIP, 0) < + IP_VERSION(3, 5, 0) || + !(adev->flags & AMD_IS_APU)) { /* * Older HW and DGPU have issues with instant off; * use a 2 frame offdelay. @@ -9707,14 +9696,22 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, drm_crtc_vblank_on_config(&acrtc->base, &config); - /* Allow RX6xxx, RX7700, RX7800 GPUs to call amdgpu_irq_get.*/ + /* + * Since pflip_high_irq is no longer registered for DCN, grab an + * extra reference to vupdate irq instead to workaround this + * issue: + * https://gitlab.freedesktop.org/drm/amd/-/work_items/3936 + * + * The callbacks to drm_vblank_on/off should really take care of + * this though. + */ switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) { case IP_VERSION(3, 0, 0): case IP_VERSION(3, 0, 2): case IP_VERSION(3, 0, 3): case IP_VERSION(3, 2, 0): - if (amdgpu_irq_get(adev, &adev->pageflip_irq, irq_type)) - drm_err(dev, "DM_IRQ: Cannot get pageflip irq!\n"); + if (amdgpu_irq_get(adev, &adev->vupdate_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot get vupdate irq!\n"); #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) if (amdgpu_irq_get(adev, &adev->vline0_irq, irq_type)) drm_err(dev, "DM_IRQ: Cannot get vline0 irq!\n"); @@ -9732,8 +9729,8 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, if (amdgpu_irq_put(adev, &adev->vline0_irq, irq_type)) drm_err(dev, "DM_IRQ: Cannot put vline0 irq!\n"); #endif - if (amdgpu_irq_put(adev, &adev->pageflip_irq, irq_type)) - drm_err(dev, "DM_IRQ: Cannot put pageflip irq!\n"); + if (amdgpu_irq_put(adev, &adev->vupdate_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot put vupdate irq!\n"); } drm_crtc_vblank_off(&acrtc->base); @@ -9746,6 +9743,10 @@ static void dm_update_pflip_irq_state(struct amdgpu_device *adev, int irq_type = amdgpu_display_crtc_idx_to_irq_type(adev, acrtc->crtc_id); + /* GRPH_PFLIP is not used on DCN; nothing to reapply. */ + if (amdgpu_ip_version(adev, DCE_HWIP, 0) != 0) + return; + /** * This reads the current state for the IRQ and force reapplies * the setting to hardware. @@ -10078,9 +10079,13 @@ static void amdgpu_dm_handle_vrr_transition(struct amdgpu_display_manager *dm, struct dm_crtc_state *old_state, struct dm_crtc_state *new_state) { + struct amdgpu_device *adev = drm_to_adev(new_state->base.crtc->dev); bool old_vrr_active = amdgpu_dm_crtc_vrr_active(old_state); bool new_vrr_active = amdgpu_dm_crtc_vrr_active(new_state); + /* Only DCE gates vupdate on VRR, keep it enabled for DCN */ + bool vrr_gates_vupdate = amdgpu_ip_version(adev, DCE_HWIP, 0) == 0; + if (!old_vrr_active && new_vrr_active) { /* Transition VRR inactive -> active: * While VRR is active, we must not disable vblank irq, as a @@ -10090,7 +10095,8 @@ static void amdgpu_dm_handle_vrr_transition(struct amdgpu_display_manager *dm, * We also need vupdate irq for the actual core vblank handling * at end of vblank. */ - WARN_ON(amdgpu_dm_crtc_set_vupdate_irq(new_state->base.crtc, true) != 0); + if (vrr_gates_vupdate) + WARN_ON(amdgpu_dm_crtc_set_vupdate_irq(new_state->base.crtc, true) != 0); WARN_ON(drm_crtc_vblank_get(new_state->base.crtc) != 0); drm_dbg_driver(new_state->base.crtc->dev, "%s: crtc=%u VRR off->on: Get vblank ref\n", __func__, new_state->base.crtc->base.id); @@ -10106,7 +10112,8 @@ static void amdgpu_dm_handle_vrr_transition(struct amdgpu_display_manager *dm, /* Transition VRR active -> inactive: * Allow vblank irq disable again for fixed refresh rate. */ - WARN_ON(amdgpu_dm_crtc_set_vupdate_irq(new_state->base.crtc, false) != 0); + if (vrr_gates_vupdate) + WARN_ON(amdgpu_dm_crtc_set_vupdate_irq(new_state->base.crtc, false) != 0); drm_crtc_vblank_put(new_state->base.crtc); drm_dbg_driver(new_state->base.crtc->dev, "%s: crtc=%u VRR on->off: Drop vblank ref\n", __func__, new_state->base.crtc->base.id); @@ -10255,6 +10262,28 @@ static void amdgpu_dm_enable_self_refresh(struct amdgpu_display_manager *dm, } } +static void dm_arm_vblank_event(struct amdgpu_crtc *acrtc, + struct dm_crtc_state *acrtc_state, + bool pflip_update, + bool cursor_update) +{ + assert_spin_locked(&acrtc->base.dev->event_lock); + + if (!acrtc->base.state->event || acrtc_state->active_planes == 0) + return; + + if (pflip_update) { + drm_crtc_vblank_get(&acrtc->base); + WARN_ON(acrtc->pflip_status != AMDGPU_FLIP_NONE); + /* Arm flip completion handling and event delivery after programming. */ + prepare_flip_isr(acrtc); + } else if (cursor_update) { + drm_crtc_vblank_get(&acrtc->base); + acrtc->event = acrtc->base.state->event; + acrtc->base.state->event = NULL; + } +} + static void amdgpu_dm_commit_planes(struct drm_atomic_commit *state, struct drm_device *dev, struct amdgpu_display_manager *dm, @@ -10277,6 +10306,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_commit *state, bool vrr_active = amdgpu_dm_crtc_vrr_active(acrtc_state); bool cursor_update = false; bool pflip_present = false; + bool immediate_flip = false; + bool flip_latched_during_prog = false; bool dirty_rects_changed = false; bool updated_planes_and_streams = false; struct { @@ -10441,6 +10472,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_commit *state, acrtc_state->update_type == UPDATE_TYPE_FAST && get_mem_type(old_plane_state->fb) == get_mem_type(fb); + immediate_flip |= bundle->flip_addrs[planes_count].flip_immediate; + timestamp_ns = ktime_get_ns(); bundle->flip_addrs[planes_count].flip_timestamp_in_us = div_u64(timestamp_ns, 1000); bundle->surface_updates[planes_count].flip_addr = &bundle->flip_addrs[planes_count]; @@ -10509,39 +10542,24 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_commit *state, usleep_range(1000, 1100); } - /** - * Prepare the flip event for the pageflip interrupt to handle. - * - * This only works in the case where we've already turned on the - * appropriate hardware blocks (eg. HUBP) so in the transition case - * from 0 -> n planes we have to skip a hardware generated event - * and rely on sending it from software. - */ - if (acrtc_attach->base.state->event && - acrtc_state->active_planes > 0) { - drm_crtc_vblank_get(pcrtc); - - spin_lock_irqsave(&pcrtc->dev->event_lock, flags); - - WARN_ON(acrtc_attach->pflip_status != AMDGPU_FLIP_NONE); - prepare_flip_isr(acrtc_attach); - - spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); - } - if (acrtc_state->stream) { if (acrtc_state->freesync_vrr_info_changed) bundle->stream_update.vrr_infopacket = &acrtc_state->stream->vrr_infopacket; } - } else if (cursor_update && acrtc_state->active_planes > 0) { - spin_lock_irqsave(&pcrtc->dev->event_lock, flags); - if (acrtc_attach->base.state->event) { - drm_crtc_vblank_get(pcrtc); - acrtc_attach->event = acrtc_attach->base.state->event; - acrtc_attach->base.state->event = NULL; + } + + /* + * DCE depends on a combination of GRPH_FLIP, VLINE0, and VUPDATE for + * event delivery. Only GRPH_FLIP handler can send pflip events, and it + * only fires if HW latched to the flip. Maintain legacy behavior by + * arming event before programming. + */ + if (amdgpu_ip_version(dm->adev, DCE_HWIP, 0) == 0) { + scoped_guard(spinlock_irqsave, &pcrtc->dev->event_lock) { + dm_arm_vblank_event(acrtc_attach, acrtc_state, + pflip_present, cursor_update); } - spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); } /* Update the planes if changed or disable if we don't have any. */ @@ -10633,6 +10651,115 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_commit *state, acrtc_state->cursor_mode == DM_CURSOR_NATIVE_MODE) amdgpu_dm_commit_cursors(state); + /* + * DCN specific vblank handling + * ============================ + * + * With the event_lock held, arm the vblank event, and determine whether + * deliver it immediately, or in VUPDATE_NO_LOCK IRQ (i.e. HW latch + * point) handler. Do this *after* programming so that the IRQ handler + * will not deliver the event before HW laches onto the programmed + * values: + * + * Commit thread IRQ handler HW + * ----------------------------------------------------------------- + * arm_vblank_event() + * vupdate() + * vupdate_handler() + * cook_timestamp() + * # prev flip already latched, + * # so flip_latched == true. + * if event_armed && flip_latched: + * send_vblank_event() + * # sent before latch, **BAD!** + * hw_program() + * vupdate() + * **latch** + * + * There's a consequence of arming after: it's possible for HW to latch + * between start of HW programming and acrtc->event/pflip_status arming. + * When this happens, the IRQ handler will send the event on the next + * immediate latch point, even though HW has already latched. This is + * handled by optimistically checking for HW latch after programming, + * and if latched, send the event immediately: + * + * Commit thread IRQ handler HW + * ----------------------------------------------------------------- + * hw_program() + * vupdate() + * **latch** + * vupdate_handler() + * cook_timestamp() + * # event_armed == false + * # **no event sent!** + * arm_vblank_event() + * if flip_latched: + * **send_vblank_event()** + * disarm_vblank_event() + * + * The IRQ handler is expected to cook the timestamp, but we need to + * cook the timestamp before optimistic sending as well. That's because + * the following sequence is possible: + * + * Commit thread IRQ handler HW + * ----------------------------------------------------------------- + * hw_program() + * arm_vblank_event() + * vupdate() + * **latch** + * if flip_latched: + * # Need cook before send! + * **cook_timestamp()** + * send_vblank_event() + * disarm_vblank_event() + * vupdate_handler() + * cook_timestamp() + * # event_armed == false + * # no event sent! + * + * Cooking twice is OK, since DRM scanout accurate timestamps report A) + * the previous vactive start if currently in vactive, or B) the next + * vactive start if currently in vblank (see &get_vblank_counter). 'A)' + * is what we want for the optimistic send, and for 'B)', we'll cook a + * timestamp no later than the next IRQ handler run. + * + * The more correct fix is to wrap programming and arming with the + * event_lock and thus serializing it with the IRQ handler. However, + * there are various sleep-waits within + * update_planes_and_stream_adapter() that makes spin locking illegal. + * And on full updates, it can take 1-2 frame-times to return (see + * commit_planes_for_stream). + * + * On DCE, GRPH_PFLIP IRQ is used and takes care of this. + */ + if (amdgpu_ip_version(dm->adev, DCE_HWIP, 0) != 0) { + spin_lock_irqsave(&pcrtc->dev->event_lock, flags); + + if (updated_planes_and_streams) { + flip_latched_during_prog = + !dc_get_flip_pending_on_otg(dm->dc, acrtc_attach->otg_inst); + } + + dm_arm_vblank_event(acrtc_attach, acrtc_state, + pflip_present, cursor_update); + + /* + * Deliver the event immediately on immediate flip, or on a + * update that has already latched. + */ + if ((immediate_flip || flip_latched_during_prog) && + acrtc_attach->pflip_status == AMDGPU_FLIP_SUBMITTED && + acrtc_attach->event) { + drm_crtc_accurate_vblank_count(&acrtc_attach->base); + drm_crtc_send_vblank_event(&acrtc_attach->base, + acrtc_attach->event); + acrtc_attach->event = NULL; + drm_crtc_vblank_put(&acrtc_attach->base); + acrtc_attach->pflip_status = AMDGPU_FLIP_NONE; + } + spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); + } + cleanup: kfree(bundle); } @@ -12098,6 +12225,7 @@ skip_modeset: /* Release extra reference */ if (new_stream) dc_stream_release(new_stream); + new_stream = NULL; /* * We want to do dc stream updates that do not require a @@ -12814,10 +12942,15 @@ static int dm_crtc_get_cursor_mode(struct amdgpu_device *adev, /* Overlay cursor not supported on HW before DCN * DCN401/420 does not have the cursor-on-scaled-plane or cursor-on-yuv-plane restrictions * as previous DCN generations, so enable native mode on DCN401/420 + * + * Always set native cursor mode when the CRTC is disabled, + * to make sure it doesn't cause atomic commits to fail when + * they are trying to disable the CRTC. */ if (amdgpu_ip_version(adev, DCE_HWIP, 0) == IP_VERSION(4, 0, 1) || amdgpu_ip_version(adev, DCE_HWIP, 0) == IP_VERSION(4, 2, 0) || - amdgpu_ip_version(adev, DCE_HWIP, 0) == IP_VERSION(4, 2, 1)) { + amdgpu_ip_version(adev, DCE_HWIP, 0) == IP_VERSION(4, 2, 1) || + !dm_crtc_state->base.enable) { *cursor_mode = DM_CURSOR_NATIVE_MODE; return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 3dcedaa67ed8..b43cd68cde67 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -274,7 +274,14 @@ static inline int amdgpu_dm_crtc_set_vblank(struct drm_crtc *crtc, bool enable) drm_crtc_vblank_restore(crtc); } - if (dc_supports_vrr(dm->dc->ctx->dce_version)) { + /* + * On DCN, VUPDATE_NO_LOCK is the single OTG interrupt used to deliver + * vblank and pageflip completion events, so enable it whenever vblank + * is enabled. On DCE, vupdate is only needed in VRR mode. + */ + if (amdgpu_ip_version(adev, DCE_HWIP, 0) != 0) { + rc = amdgpu_dm_crtc_set_vupdate_irq(crtc, enable); + } else if (dc_supports_vrr(dm->dc->ctx->dce_version)) { if (enable) { /* vblank irq on -> Only need vupdate irq in vrr mode */ if (amdgpu_dm_crtc_vrr_active(acrtc_state)) @@ -288,36 +295,43 @@ static inline int amdgpu_dm_crtc_set_vblank(struct drm_crtc *crtc, bool enable) if (rc) return rc; - /* crtc vblank or vstartup interrupt */ - if (enable) { - rc = amdgpu_irq_get(adev, &adev->crtc_irq, irq_type); - drm_dbg_vbl(crtc->dev, "Get crtc_irq ret=%d\n", rc); - } else { - rc = amdgpu_irq_put(adev, &adev->crtc_irq, irq_type); - drm_dbg_vbl(crtc->dev, "Put crtc_irq ret=%d\n", rc); - } - - if (rc) - return rc; - /* - * hubp surface flip interrupt - * - * We have no guarantee that the frontend index maps to the same - * backend index - some even map to more than one. - * - * TODO: Use a different interrupt or check DC itself for the mapping. + * VLINE0 (crtc_irq) and GRPH_PFLIP (pageflip_irq) are only used on + * DCE. On DCN, vblank and pageflip completion are delivered from + * VUPDATE_NO_LOCK (enabled above), so don't touch them here. */ - if (enable) { - rc = amdgpu_irq_get(adev, &adev->pageflip_irq, irq_type); - drm_dbg_vbl(crtc->dev, "Get pageflip_irq ret=%d\n", rc); - } else { - rc = amdgpu_irq_put(adev, &adev->pageflip_irq, irq_type); - drm_dbg_vbl(crtc->dev, "Put pageflip_irq ret=%d\n", rc); - } + if (amdgpu_ip_version(adev, DCE_HWIP, 0) == 0) { + /* crtc vblank or vstartup interrupt */ + if (enable) { + rc = amdgpu_irq_get(adev, &adev->crtc_irq, irq_type); + drm_dbg_vbl(crtc->dev, "Get crtc_irq ret=%d\n", rc); + } else { + rc = amdgpu_irq_put(adev, &adev->crtc_irq, irq_type); + drm_dbg_vbl(crtc->dev, "Put crtc_irq ret=%d\n", rc); + } - if (rc) - return rc; + if (rc) + return rc; + + /* + * hubp surface flip interrupt + * + * We have no guarantee that the frontend index maps to the same + * backend index - some even map to more than one. + * + * TODO: Use a different interrupt or check DC itself for the mapping. + */ + if (enable) { + rc = amdgpu_irq_get(adev, &adev->pageflip_irq, irq_type); + drm_dbg_vbl(crtc->dev, "Get pageflip_irq ret=%d\n", rc); + } else { + rc = amdgpu_irq_put(adev, &adev->pageflip_irq, irq_type); + drm_dbg_vbl(crtc->dev, "Put pageflip_irq ret=%d\n", rc); + } + + if (rc) + return rc; + } #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) /* crtc vline0 interrupt, only available on DCN+ */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index c6f94eb71ffa..6be7f6edd0b2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -1201,11 +1201,25 @@ enum dc_edid_status dm_helpers_read_local_edid( continue; edid = drm_edid_raw(drm_edid); // FIXME: Get rid of drm_edid_raw() - if (!edid || - edid->extensions >= sizeof(sink->dc_edid.raw_edid) / EDID_LENGTH) + /* + * Use the length of the EDID property blob populated by + * drm_edid_connector_update() above. It reflects the true number + * of EDID blocks, including any HDMI Forum EDID Extension Override + * Data Block (HF-EEODB) count, which the raw byte 0x7e extension + * count can hide (e.g. HDMI 8K sinks). + */ + if (!edid || !connector->edid_blob_ptr || + connector->edid_blob_ptr->length > sizeof(sink->dc_edid.raw_edid)) return EDID_BAD_INPUT; - sink->dc_edid.length = EDID_LENGTH * (edid->extensions + 1); + /* + * FIXME: amdgpu_dm today does not consider the HF-EEODB, which + * may contain additional mode info for sinks. This is a + * workaround until dc_edid is refactored out from DC into + * amdgpu_dm's ownership, allowing amdgpu_dm to use drm_edid + * directly + */ + sink->dc_edid.length = connector->edid_blob_ptr->length; memmove(sink->dc_edid.raw_edid, (uint8_t *)edid, sink->dc_edid.length); /* We don't need the original edid anymore */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 175106cce5a4..e25b94b65dac 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -6165,6 +6165,51 @@ void dc_interrupt_ack(struct dc *dc, enum dc_irq_source src) dal_irq_service_ack(dc->res_pool->irqs, src); } +/* + * dc_get_flip_pending_on_otg() - Check if a GRPH_FLIP is still pending on OTG + * + * @dc: display core context @otg_inst: OTG instance to query + * + * Reads the HUBP flip-pending status for the pipe(s) bound to @otg_inst, + * returning true if any of them has not yet latched its programmed surface + * address. + * + * Unlike dc_plane_get_status(), this does not take or mutate a dc_plane_state, + * so it is safe to call from interrupt context without racing a concurrent + * commit that may be updating plane state. + * + * Return: true if a flip is still pending on the OTG, false otherwise. + */ +bool dc_get_flip_pending_on_otg(struct dc *dc, int otg_inst) +{ + bool flip_pending = false; + int i; + + if (!dc || !dc->current_state) + return false; + + dc_exit_ips_for_hw_access(dc); + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; + struct hubp *hubp = pipe_ctx->plane_res.hubp; + + if (!pipe_ctx->plane_state || !pipe_ctx->stream_res.tg) + continue; + + if (pipe_ctx->stream_res.tg->inst != otg_inst) + continue; + + if (hubp && hubp->funcs->hubp_is_flip_pending && + hubp->funcs->hubp_is_flip_pending(hubp)) { + flip_pending = true; + break; + } + } + + return flip_pending; +} + void dc_power_down_on_boot(struct dc *dc) { if (dc->ctx->dce_environment != DCE_ENV_VIRTUAL_HW && diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 82d02ebbd829..1dc85f6b6689 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1815,6 +1815,8 @@ struct dc_scratch_space { bool dp_skip_DID2; bool dp_skip_reset_segment; bool dp_skip_fs_144hz; + /* Some DP bridges don't work with RBR and must use HBR. */ + bool dp_skip_rbr; bool dp_mot_reset_segment; /* Some USB4 docks do not handle turning off MST DSC once it has been enabled. */ bool dpia_mst_dsc_always_on; @@ -2881,6 +2883,7 @@ enum dc_irq_source dc_interrupt_to_irq_source( uint32_t ext_id); bool dc_interrupt_set(struct dc *dc, enum dc_irq_source src, bool enable); void dc_interrupt_ack(struct dc *dc, enum dc_irq_source src); +bool dc_get_flip_pending_on_otg(struct dc *dc, int otg_inst); enum dc_irq_source dc_get_hpd_irq_source_at_index( struct dc *dc, uint32_t link_index); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c index 7c293917e6fd..ecb8493ec523 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c @@ -1229,9 +1229,9 @@ static bool get_dp_dto_frequency_100hz( */ modulo_hz = REG_READ(MODULO[inst]); if (modulo_hz) { - temp = div_u64((uint64_t)clock_hz * dp_dto_ref_khz * 10, modulo_hz); - ASSERT(temp / 100 <= 0xFFFFFFFFUL); - *pixel_clk_100hz = (unsigned int)(temp / 100); + temp = clock_hz * dp_dto_ref_khz * 10; + ASSERT(temp <= UINT_MAX * modulo_hz * 100ULL); + *pixel_clk_100hz = div_u64(temp, modulo_hz * 100); } else *pixel_clk_100hz = 0; } else { @@ -1285,13 +1285,12 @@ static bool dcn401_get_dp_dto_frequency_100hz(const struct clock_source *clock_s * - target pix_clk_hz = (DPDTO INTEGER * DPDTO MODULO + DPDTO PHASE) */ temp = (unsigned long long)dp_dto_integer * modulo_hz + phase_hz; - - if (temp / 100 > 0xFFFFFFFFUL) { + if (temp > (UINT_MAX * 100ULL)) { /* pixel rate 100hz should never be this high, if it is, throw an assert and return 0 */ BREAK_TO_DEBUGGER(); *pixel_clk_100hz = 0; } else { - *pixel_clk_100hz = (unsigned int)(temp / 100); + *pixel_clk_100hz = div_u64(temp, 100); } return true; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index 7d8951fecd57..29dbb5e410d8 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -623,7 +623,7 @@ static bool detect_dp(struct dc_link *link, link->dpcd_caps.sink_count.bits.SINK_COUNT = 1; /* NUTMEG requires that we use HBR, doesn't work with RBR. */ if (link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_00001A) - link->preferred_link_setting.link_rate = LINK_RATE_HIGH; + link->wa_flags.dp_skip_rbr = true; } return true; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index 47abb4066709..1cd17a0272bc 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -750,8 +750,10 @@ static bool decide_dp_link_settings(struct dc_link *link, struct dc_link_setting if (req_bw > dp_link_bandwidth_kbps(link, &link->verified_link_cap)) return false; - if (link->preferred_link_setting.link_rate != LINK_RATE_UNKNOWN) - initial_link_setting.link_rate = link->preferred_link_setting.link_rate; + if (link->wa_flags.dp_skip_rbr) { + initial_link_setting.link_rate = LINK_RATE_HIGH; + current_link_setting.link_rate = LINK_RATE_HIGH; + } /* search for the minimum link setting that: * 1. is supported according to the link training result diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c index b92d4f378d60..97ea22af5d2b 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c @@ -992,6 +992,11 @@ struct stream_encoder *dce100_find_first_free_match_stream_enc_for_link( for (i = 0; i < pool->stream_enc_count; i++) { if (!res_ctx->is_stream_enc_acquired[i] && pool->stream_enc[i]) { + /* DP/MST needs a digital encoder; skip analog/no-DP encoders */ + if (dc_is_dp_signal(stream->signal) && + (!pool->stream_enc[i]->funcs || + !pool->stream_enc[i]->funcs->dp_set_stream_attribute)) + continue; /* Store first available for MST second display * in daisy chain use case */ @@ -1014,7 +1019,7 @@ struct stream_encoder *dce100_find_first_free_match_stream_enc_for_link( * required for non DP connectors. */ - if (j >= 0 && link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT) + if (j >= 0 && dc_is_dp_signal(stream->signal)) return pool->stream_enc[j]; return NULL; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c index 7de12b16d7ad..a8241036def2 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c @@ -2142,6 +2142,7 @@ static bool dcn42_resource_construct( dc->config.use_pipe_ctx_sync_logic = true; dc->config.dc_mode_clk_limit_support = false; dc->config.enable_windowed_mpo_odm = true; + dc->config.set_pipe_unlock_order = true; /* Need to ensure DET gets freed before allocating */ /* Use psp mailbox to enable assr */ dc->config.use_assr_psp_message = true; /* dcn42 and afterward always support external panel replay */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.c index 527d17f29f3b..94e166c0a9b0 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.c @@ -22,6 +22,7 @@ #include "dcn35/dcn35_resource.h" #include "dcn321/dcn321_resource.h" #include "dcn401/dcn401_resource.h" +#include "dcn42/dcn42_resource.h" #include "dcn42/dcn42_resource_fpu.h" #include "dcn10/dcn10_ipp.h" @@ -116,6 +117,23 @@ #define regAPG9_APG_DBG_GEN_CONTROL 0x38ae #define regAPG9_APG_DBG_GEN_CONTROL_BASE_IDX 2 +#define regHUBP0_HUBPREQ_DEBUG_DB 0x05f8 +#define regHUBP0_HUBPREQ_DEBUG_DB_BASE_IDX 2 +#define regHUBP0_HUBPREQ_DEBUG 0x05f9 +#define regHUBP0_HUBPREQ_DEBUG_BASE_IDX 2 +#define regHUBP1_HUBPREQ_DEBUG_DB 0x06d4 +#define regHUBP1_HUBPREQ_DEBUG_DB_BASE_IDX 2 +#define regHUBP1_HUBPREQ_DEBUG 0x06d5 +#define regHUBP1_HUBPREQ_DEBUG_BASE_IDX 2 +#define regHUBP2_HUBPREQ_DEBUG_DB 0x07b0 +#define regHUBP2_HUBPREQ_DEBUG_DB_BASE_IDX 2 +#define regHUBP2_HUBPREQ_DEBUG 0x07b1 +#define regHUBP2_HUBPREQ_DEBUG_BASE_IDX 2 +#define regHUBP3_HUBPREQ_DEBUG_DB 0x088c +#define regHUBP3_HUBPREQ_DEBUG_DB_BASE_IDX 2 +#define regHUBP3_HUBPREQ_DEBUG 0x088d +#define regHUBP3_HUBPREQ_DEBUG_BASE_IDX 2 + enum dcn401_clk_src_array_id { DCN401_CLK_SRC_PLL0, DCN401_CLK_SRC_PLL1, @@ -461,7 +479,7 @@ static const struct dcn_optc_mask optc_mask = { OPTC_COMMON_MASK_SH_LIST_DCN42B(_MASK)}; #define hubp_regs_init(id) \ - HUBP_REG_LIST_DCN42B_RI(id) + HUBP_REG_LIST_DCN42_RI(id) static struct dcn_hubp2_registers hubp_regs[4]; @@ -1882,9 +1900,7 @@ static struct resource_funcs dcn42b_res_pool_funcs = { .update_soc_for_wm_a = dcn30_update_soc_for_wm_a, .add_phantom_pipes = dcn32_add_phantom_pipes, .calculate_mall_ways_from_bytes = dcn32_calculate_mall_ways_from_bytes, -#ifdef CONFIG_DRM_AMD_DC_DML21 .prepare_mcache_programming = dcn42b_prepare_mcache_programming, -#endif .build_pipe_pix_clk_params = dcn42b_build_pipe_pix_clk_params, .get_power_profile = dcn401_get_power_profile, .get_vstartup_for_pipe = dcn401_get_vstartup_for_pipe, @@ -2087,6 +2103,7 @@ static bool dcn42b_resource_construct( dc->config.use_pipe_ctx_sync_logic = true; dc->config.dc_mode_clk_limit_support = false; dc->config.enable_windowed_mpo_odm = true; + dc->config.set_pipe_unlock_order = true; /* Need to ensure DET gets freed before allocating */ /* Use psp mailbox to enable assr */ dc->config.use_assr_psp_message = true; /* dcn42 and afterward always support external panel replay */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.h index 2da3e3c8304a..2824a0e1acc9 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.h +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.h @@ -344,7 +344,6 @@ * DCCG_SRII(PHASE, DP_DTO, 3), * DCCG_SRII(MODULO, DP_DTO, 3), * SR(DSCCLK3_DTO_PARAM), - * SR(HDMISTREAMCLK_CNTL), * SR(SYMCLKD_CLOCK_ENABLE), * SR(SYMCLKE_CLOCK_ENABLE) */ @@ -360,6 +359,7 @@ SR(PHYBSYMCLK_CLOCK_CNTL), \ SR(PHYCSYMCLK_CLOCK_CNTL), \ SR(DPSTREAMCLK_CNTL), \ + SR(HDMISTREAMCLK_CNTL), \ SR(SYMCLK32_SE_CNTL), \ SR(SYMCLK32_LE_CNTL), \ DCCG_SRII(PIXEL_RATE_CNTL, OTG, 0), \ @@ -542,120 +542,6 @@ SRI_ARR(DC_ABM1_ACE_OFFSET_SLOPE_DATA, ABM, id), \ SRI_ARR(DC_ABM1_ACE_PWL_CNTL, ABM, id) -/* HUBP */ -/* Not in DCN42B: HUBPREQ_DEBUG_DB and HUBPREQ_DEBUG */ -#define HUBP_REG_LIST_DCN42B_RI(id) \ - SRI_ARR(DCN_DMDATA_VM_CNTL, HUBPREQ, id), \ - SRI_ARR(FLIP_PARAMETERS_3, HUBPREQ, id), \ - SRI_ARR(FLIP_PARAMETERS_4, HUBPREQ, id), \ - SRI_ARR(FLIP_PARAMETERS_5, HUBPREQ, id), \ - SRI_ARR(FLIP_PARAMETERS_6, HUBPREQ, id), \ - SRI_ARR(VBLANK_PARAMETERS_5, HUBPREQ, id), \ - SRI_ARR(VBLANK_PARAMETERS_6, HUBPREQ, id), \ - HUBP_REG_LIST_DCN_VM_RI(id), \ - SRI_ARR(PREFETCH_SETTINGS, HUBPREQ, id), \ - SRI_ARR(PREFETCH_SETTINGS_C, HUBPREQ, id), \ - SRI_ARR(DCN_VM_SYSTEM_APERTURE_LOW_ADDR, HUBPREQ, id), \ - SRI_ARR(DCN_VM_SYSTEM_APERTURE_HIGH_ADDR, HUBPREQ, id), \ - SRI_ARR(CURSOR_SETTINGS, HUBPREQ, id), \ - SRI_ARR(CURSOR_SURFACE_ADDRESS_HIGH, CURSOR0_, id), \ - SRI_ARR(CURSOR_SURFACE_ADDRESS, CURSOR0_, id), \ - SRI_ARR(CURSOR_SIZE, CURSOR0_, id), \ - SRI_ARR(CURSOR_CONTROL, CURSOR0_, id), \ - SRI_ARR(CURSOR_POSITION, CURSOR0_, id), \ - SRI_ARR(CURSOR_HOT_SPOT, CURSOR0_, id), \ - SRI_ARR(CURSOR_DST_OFFSET, CURSOR0_, id), \ - SRI_ARR(DMDATA_ADDRESS_HIGH, CURSOR0_, id), \ - SRI_ARR(DMDATA_ADDRESS_LOW, CURSOR0_, id), \ - SRI_ARR(DMDATA_CNTL, CURSOR0_, id), \ - SRI_ARR(DMDATA_SW_CNTL, CURSOR0_, id), \ - SRI_ARR(DMDATA_QOS_CNTL, CURSOR0_, id), \ - SRI_ARR(DMDATA_SW_DATA, CURSOR0_, id), \ - SRI_ARR(DMDATA_STATUS, CURSOR0_, id), \ - SRI_ARR(FLIP_PARAMETERS_0, HUBPREQ, id), \ - SRI_ARR(FLIP_PARAMETERS_1, HUBPREQ, id), \ - SRI_ARR(FLIP_PARAMETERS_2, HUBPREQ, id), \ - SRI_ARR(DCN_CUR1_TTU_CNTL0, HUBPREQ, id), \ - SRI_ARR(DCN_CUR1_TTU_CNTL1, HUBPREQ, id), \ - SRI_ARR(DCSURF_FLIP_CONTROL2, HUBPREQ, id), \ - SRI_ARR(VMID_SETTINGS_0, HUBPREQ, id), \ - SRI_ARR(DCHUBP_CNTL, HUBP, id), \ - SRI_ARR(DCSURF_ADDR_CONFIG, HUBP, id), \ - SRI_ARR(DCSURF_TILING_CONFIG, HUBP, id), \ - SRI_ARR(DCSURF_SURFACE_PITCH, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_PITCH_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_CONFIG, HUBP, id), \ - SRI_ARR(DCSURF_FLIP_CONTROL, HUBPREQ, id), \ - SRI_ARR(DCSURF_PRI_VIEWPORT_DIMENSION, HUBP, id), \ - SRI_ARR(DCSURF_PRI_VIEWPORT_START, HUBP, id), \ - SRI_ARR(DCSURF_SEC_VIEWPORT_DIMENSION, HUBP, id), \ - SRI_ARR(DCSURF_SEC_VIEWPORT_START, HUBP, id), \ - SRI_ARR(DCSURF_PRI_VIEWPORT_DIMENSION_C, HUBP, id), \ - SRI_ARR(DCSURF_PRI_VIEWPORT_START_C, HUBP, id), \ - SRI_ARR(DCSURF_SEC_VIEWPORT_DIMENSION_C, HUBP, id), \ - SRI_ARR(DCSURF_SEC_VIEWPORT_START_C, HUBP, id), \ - SRI_ARR(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH, HUBPREQ, id), \ - SRI_ARR(DCSURF_PRIMARY_SURFACE_ADDRESS, HUBPREQ, id), \ - SRI_ARR(DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH, HUBPREQ, id), \ - SRI_ARR(DCSURF_SECONDARY_SURFACE_ADDRESS, HUBPREQ, id), \ - SRI_ARR(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH, HUBPREQ, id), \ - SRI_ARR(DCSURF_PRIMARY_META_SURFACE_ADDRESS, HUBPREQ, id), \ - SRI_ARR(DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH, HUBPREQ, id), \ - SRI_ARR(DCSURF_SECONDARY_META_SURFACE_ADDRESS, HUBPREQ, id), \ - SRI_ARR(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_PRIMARY_SURFACE_ADDRESS_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_SECONDARY_SURFACE_ADDRESS_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_PRIMARY_META_SURFACE_ADDRESS_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_SECONDARY_META_SURFACE_ADDRESS_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_INUSE, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_INUSE_HIGH, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_INUSE_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_INUSE_HIGH_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_EARLIEST_INUSE, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_EARLIEST_INUSE_HIGH, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_EARLIEST_INUSE_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_CONTROL, HUBPREQ, id), \ - SRI_ARR(DCSURF_SURFACE_FLIP_INTERRUPT, HUBPREQ, id), \ - SRI_ARR(HUBPRET_CONTROL, HUBPRET, id), \ - SRI_ARR(HUBPRET_READ_LINE_STATUS, HUBPRET, id), \ - SRI_ARR(DCN_EXPANSION_MODE, HUBPREQ, id), \ - SRI_ARR(DCHUBP_REQ_SIZE_CONFIG, HUBP, id), \ - SRI_ARR(DCHUBP_REQ_SIZE_CONFIG_C, HUBP, id), \ - SRI_ARR(BLANK_OFFSET_0, HUBPREQ, id), \ - SRI_ARR(BLANK_OFFSET_1, HUBPREQ, id), \ - SRI_ARR(DST_DIMENSIONS, HUBPREQ, id), \ - SRI_ARR(DST_AFTER_SCALER, HUBPREQ, id), \ - SRI_ARR(VBLANK_PARAMETERS_0, HUBPREQ, id), \ - SRI_ARR(REF_FREQ_TO_PIX_FREQ, HUBPREQ, id), \ - SRI_ARR(VBLANK_PARAMETERS_1, HUBPREQ, id), \ - SRI_ARR(VBLANK_PARAMETERS_3, HUBPREQ, id), \ - SRI_ARR(NOM_PARAMETERS_4, HUBPREQ, id), \ - SRI_ARR(NOM_PARAMETERS_5, HUBPREQ, id), \ - SRI_ARR(PER_LINE_DELIVERY_PRE, HUBPREQ, id), \ - SRI_ARR(PER_LINE_DELIVERY, HUBPREQ, id), \ - SRI_ARR(VBLANK_PARAMETERS_2, HUBPREQ, id), \ - SRI_ARR(VBLANK_PARAMETERS_4, HUBPREQ, id), \ - SRI_ARR(NOM_PARAMETERS_6, HUBPREQ, id), \ - SRI_ARR(NOM_PARAMETERS_7, HUBPREQ, id), \ - SRI_ARR(DCN_TTU_QOS_WM, HUBPREQ, id), \ - SRI_ARR(DCN_GLOBAL_TTU_CNTL, HUBPREQ, id), \ - SRI_ARR(DCN_SURF0_TTU_CNTL0, HUBPREQ, id), \ - SRI_ARR(DCN_SURF0_TTU_CNTL1, HUBPREQ, id), \ - SRI_ARR(DCN_SURF1_TTU_CNTL0, HUBPREQ, id), \ - SRI_ARR(DCN_SURF1_TTU_CNTL1, HUBPREQ, id), \ - SRI_ARR(DCN_CUR0_TTU_CNTL0, HUBPREQ, id), \ - SRI_ARR(DCN_CUR0_TTU_CNTL1, HUBPREQ, id), \ - SRI_ARR(HUBP_CLK_CNTL, HUBP, id), \ - SRI_ARR(HUBPRET_READ_LINE_VALUE, HUBPRET, id), \ - SRI_ARR(DCHUBP_MALL_CONFIG, HUBP, id), \ - SRI_ARR(DCHUBP_VMPG_CONFIG, HUBP, id), \ - SRI_ARR(UCLK_PSTATE_FORCE, HUBPREQ, id), \ - SRI_ARR(HUBP_3DLUT_DLG_PARAM, CURSOR0_, id), \ - HUBP_3DLUT_FL_REG_LIST_DCN401(id) struct dcn42b_resource_pool { struct resource_pool base; }; diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index 8079da7c5335..012227c70600 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -3892,13 +3892,16 @@ static void si_notify_hw_of_powersource(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - /* Check if the platform already manages the AC/DC switch via dedicated GPIO. */ - if (adev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_HARDWAREDC) - return; - - /* The SMU automatically notices DC, but needs to be notified when switching to AC. */ - if (adev->pm.ac_power) + /* + * Check if the platform already manages the AC/DC switch via dedicated GPIO. + * Otherwise SMU automatically notices DC, but needs to be notified of AC. + */ + if (adev->pm.ac_power && + (adev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_HARDWAREDC)) amdgpu_si_send_msg_to_smc(adev, PPSMC_MSG_RunningOnAC); + + /* Recompute clocks with updated max_limits. */ + amdgpu_legacy_dpm_compute_clocks(adev); } static PPSMC_Result si_send_msg_to_smc_with_parameter(struct amdgpu_device *adev, @@ -7689,7 +7692,7 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev, break; } - if (queue_thermal) + if (queue_thermal && amdgpu_dpm) schedule_work(&adev->pm.dpm.thermal.work); return 0; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c index 1d6e30269d56..4d553be56396 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c @@ -106,11 +106,8 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr) hwmgr->od_enabled = false; switch (hwmgr->chip_id) { case CHIP_BONAIRE: - /* R9 M380 in iMac 2015: SMU hangs when enabling MCLK DPM - * R7 260X cards with old MC ucode: MCLK DPM is unstable - */ - if (adev->pdev->subsystem_vendor == 0x106B || - adev->pdev->device == 0x6658) { + /* R9 M380 in iMac 2015: SMU hangs when enabling MCLK DPM */ + if (adev->pdev->subsystem_vendor == 0x106B) { dev_info(adev->dev, "disabling MCLK DPM on quirky ASIC"); adev->pm.pp_feature &= ~PP_MCLK_DPM_MASK; hwmgr->feature_mask &= ~PP_MCLK_DPM_MASK; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 95bf187f02a5..bc82ba2e4c9b 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -5857,15 +5857,19 @@ static int smu7_power_off_asic(struct pp_hwmgr *hwmgr) static void smu7_notify_ac_dc(struct pp_hwmgr *hwmgr) { struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - /* Check if the platform already manages the AC/DC switch via dedicated GPIO. */ - if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + /* + * Check if the platform already manages the AC/DC switch via dedicated GPIO. + * Otherwise SMU automatically notices DC, but needs to be notified of AC. + */ + if (adev->pm.ac_power && + phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_AutomaticDCTransition)) - return; - - /* The SMU automatically notices DC, but needs to be notified when switching to AC. */ - if (adev->pm.ac_power) smum_send_msg_to_smc(hwmgr, PPSMC_MSG_RunningOnAC, NULL); + + /* Recompute clocks with updated max_limits. */ + pp_funcs->pm_compute_clocks(adev->powerplay.pp_handle); } static const struct pp_hwmgr_func smu7_hwmgr_funcs = { diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 762ec3cede96..3969a7670482 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1367,6 +1367,14 @@ static void smu_feature_cap_init(struct smu_context *smu) bitmap_zero(fea_cap->cap_map, SMU_FEATURE_CAP_ID__COUNT); } +static int smu_set_power_dep(struct smu_context *smu, bool enable) +{ + if (!smu->ppt_funcs->set_power_dep) + return 0; + + return smu->ppt_funcs->set_power_dep(smu, enable); +} + static int smu_sw_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; @@ -1428,6 +1436,8 @@ static int smu_sw_init(struct amdgpu_ip_block *ip_block) if (!smu->ppt_funcs->get_fan_control_mode) smu->adev->pm.no_fan = true; + smu_set_power_dep(smu, true); + return 0; } @@ -1450,6 +1460,8 @@ static int smu_sw_fini(struct amdgpu_ip_block *ip_block) smu_fini_microcode(smu); + smu_set_power_dep(smu, false); + return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index d76e0b005308..e3a89e9a9df4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -749,6 +749,9 @@ struct smu_context { bool pm_enabled; bool is_apu; + /* Power dependency link from an integrated xHCI controller to the GPU */ + struct device_link *usb_power_link; + uint32_t smc_driver_if_version; uint32_t smc_fw_if_version; uint32_t smc_fw_version; @@ -1648,12 +1651,19 @@ struct pptable_funcs { int (*ras_send_msg)(struct smu_context *smu, enum smu_message_type msg, uint32_t param, uint32_t *read_arg); - /** * @get_ras_smu_drv: Get RAS smu driver interface * Return: ras_smu_drv * */ int (*get_ras_smu_drv)(struct smu_context *smu, const struct ras_smu_drv **ras_smu_drv); + + /** + * @set_power_dep: Create or destroy a power dependency link + * from an integrated xHCI controller to the GPU so that the GPU is + * resumed before the USB controller during PM resume. @enable is true + * to create the link and false to tear it down. + */ + int (*set_power_dep)(struct smu_context *smu, bool enable); }; typedef enum { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c index 75719c47a41e..3d73f2050bbe 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c @@ -1701,6 +1701,50 @@ static int smu_v14_0_0_restore_user_od_settings(struct smu_context *smu) return 0; } +/* + * Link any xHCI controller sharing the GPU's PCIe root port as a consumer + * of the GPU so the GPU resumes first, avoiding an xHCI resume race. + */ +static int smu_v14_0_0_set_power_dep(struct smu_context *smu, bool enable) +{ + struct amdgpu_device *adev = smu->adev; + struct pci_dev *gpu_pdev = adev->pdev; + struct pci_dev *root_port, *usb_pdev = NULL; + struct device_link *link; + + if (!enable) { + if (smu->usb_power_link) { + device_link_del(smu->usb_power_link); + smu->usb_power_link = NULL; + } + return 0; + } + + root_port = pcie_find_root_port(gpu_pdev); + while ((usb_pdev = pci_get_class(PCI_CLASS_SERIAL_USB_XHCI, usb_pdev))) { + struct pci_dev *usb_root; + + usb_root = pcie_find_root_port(usb_pdev); + if (usb_root != root_port) + continue; + + /* Create device link: USB (consumer) depends on GPU (supplier) */ + link = device_link_add(&usb_pdev->dev, &gpu_pdev->dev, + DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME); + if (link) { + smu->usb_power_link = link; + drm_info(adev_to_drm(adev), "USB controller %s D0 power state depends on %s\n", + pci_name(usb_pdev), pci_name(gpu_pdev)); + /* Only create one link for the first USB controller found */ + break; + } + } + + pci_dev_put(usb_pdev); + + return 0; +} + static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .check_fw_status = smu_v14_0_check_fw_status, .check_fw_version = smu_cmn_check_fw_version, @@ -1734,6 +1778,7 @@ static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .dpm_set_umsch_mm_enable = smu_v14_0_0_set_umsch_mm_enable, .get_dpm_clock_table = smu_v14_0_common_get_dpm_table, .set_mall_enable = smu_v14_0_common_set_mall_enable, + .set_power_dep = smu_v14_0_0_set_power_dep, }; static void smu_v14_0_0_init_msg_ctl(struct smu_context *smu) diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index 958cb605aedd..9a06ff7d2608 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -1146,20 +1146,35 @@ static void __drm_gpusvm_unmap_pages(struct drm_gpusvm *gpusvm, }; bool use_iova = dma_use_iova(&svm_pages->state); - if (use_iova) - dma_iova_destroy(dev, &svm_pages->state, - svm_pages->state_offset, - svm_pages->dma_addr[0].dir, 0); + /* + * IOVA is reserved for the whole range but only the linked + * system pages (state_offset bytes) need unlinking; free the + * entire reservation to avoid leaking the device-page part. + * On the error path state_offset is 0, so just free it. + */ + if (use_iova) { + if (svm_pages->state_offset) + dma_iova_unlink(dev, &svm_pages->state, 0, + svm_pages->state_offset, + svm_pages->dma_addr[0].dir, 0); + dma_iova_free(dev, &svm_pages->state); + } for (i = 0, j = 0; i < npages; j++) { struct drm_pagemap_addr *addr = &svm_pages->dma_addr[j]; - if (!use_iova && addr->proto == DRM_INTERCONNECT_SYSTEM) - dma_unmap_page(dev, - addr->addr, - PAGE_SIZE << addr->order, - addr->dir); - else if (dpagemap && dpagemap->ops->device_unmap) + if (addr->proto == DRM_INTERCONNECT_SYSTEM) { + /* + * Linked IOVA pages were already torn down by + * the dma_iova_unlink()/dma_iova_free() above; + * only the non-IOVA mappings need unmap here. + */ + if (!use_iova) + dma_unmap_page(dev, + addr->addr, + PAGE_SIZE << addr->order, + addr->dir); + } else if (dpagemap && dpagemap->ops->device_unmap) dpagemap->ops->device_unmap(dpagemap, dev, addr); i += 1 << addr->order; @@ -1486,7 +1501,7 @@ map_pages: /* Unlock and restart mapping to allocate memory. */ drm_gpusvm_notifier_unlock(gpusvm); svm_pages->dma_addr = - kvmalloc_objs(*svm_pages->dma_addr, npages); + kvzalloc_objs(*svm_pages->dma_addr, npages); if (!svm_pages->dma_addr) { err = -ENOMEM; goto err_free; @@ -1529,6 +1544,16 @@ map_pages: err = -EAGAIN; goto err_unmap; } + + /* + * Set the dpagemap as soon as the first + * device page is mapped so the err_unmap path + * can device_unmap() the device mappings that + * have already been created. + */ + drm_pagemap_get(dpagemap); + drm_pagemap_put(svm_pages->dpagemap); + svm_pages->dpagemap = dpagemap; } svm_pages->dma_addr[j] = dpagemap->ops->device_map(dpagemap, @@ -1596,12 +1621,8 @@ map_pages: goto err_unmap; } - if (pagemap) { + if (pagemap) flags.has_devmem_pages = true; - drm_pagemap_get(dpagemap); - drm_pagemap_put(svm_pages->dpagemap); - svm_pages->dpagemap = dpagemap; - } /* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */ WRITE_ONCE(svm_pages->flags.__flags, flags.__flags); diff --git a/drivers/gpu/drm/drm_panel_backlight_quirks.c b/drivers/gpu/drm/drm_panel_backlight_quirks.c index f85cb293a3db..e417c7533053 100644 --- a/drivers/gpu/drm/drm_panel_backlight_quirks.c +++ b/drivers/gpu/drm/drm_panel_backlight_quirks.c @@ -20,6 +20,15 @@ struct drm_get_panel_backlight_quirk { }; static const struct drm_get_panel_backlight_quirk drm_panel_min_backlight_quirks[] = { + /* Lenovo Legion 5 15ARH05, AUX backlight non-functional, force PWM */ + { + .dmi_match.field = DMI_SYS_VENDOR, + .dmi_match.value = "LENOVO", + .dmi_match_other.field = DMI_PRODUCT_VERSION, + .dmi_match_other.value = "Lenovo Legion 5 15ARH05", + .ident.panel_id = drm_edid_encode_panel_id('B', 'O', 'E', 0x08df), + .quirk = { .force_pwm = true, }, + }, /* 13 inch matte panel */ { .dmi_match.field = DMI_BOARD_VENDOR, diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index ad4bfff6903d..164b7d61c9a3 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -2126,19 +2126,6 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state) return 0; } - -/* Divide a U16.16 fixed-point value by 2, staying in fixed-point domain */ -static inline u32 fp_16_16_div2(u32 fp) -{ - return fp >> 1; -} - -/* Convert a U16.16 fixed-point value to integer, rounding up */ -static inline int fp_16_16_to_int_ceil(u32 fp) -{ - return DIV_ROUND_UP(fp, 1 << 16); -} - static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state) { struct intel_display *display = to_intel_display(plane_state); @@ -2154,14 +2141,20 @@ static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state) int max_height = intel_plane_max_height(plane, fb, uv_plane, rotation); /* - * LNL+ UV surface start/size = - * ceiling(half of Y plane start/size). Use ceiling division - * unconditionally; it is a no-op for even values. + * UV (chroma) start/size = ceiling(half of the *integer* Y plane + * start/size), i.e. the value the luma surface programs (src >> 16), + * not the raw U16.16. A bigjoiner seam mapped through the scaler can + * give a fractional luma src; ceiling that directly would round the + * chroma one column too far and read past the chroma surface. */ - int x = fp_16_16_to_int_ceil(fp_16_16_div2(plane_state->uapi.src.x1)); - int y = fp_16_16_to_int_ceil(fp_16_16_div2(plane_state->uapi.src.y1)); - int w = fp_16_16_to_int_ceil(fp_16_16_div2(drm_rect_width(&plane_state->uapi.src))); - int h = fp_16_16_to_int_ceil(fp_16_16_div2(drm_rect_height(&plane_state->uapi.src))); + int luma_x = plane_state->uapi.src.x1 >> 16; + int luma_y = plane_state->uapi.src.y1 >> 16; + int luma_w = drm_rect_width(&plane_state->uapi.src) >> 16; + int luma_h = drm_rect_height(&plane_state->uapi.src) >> 16; + int x = DIV_ROUND_UP(luma_x, 2); + int y = DIV_ROUND_UP(luma_y, 2); + int w = DIV_ROUND_UP(luma_x + luma_w, 2) - x; + int h = DIV_ROUND_UP(luma_y + luma_h, 2) - y; u32 offset; /* FIXME not quite sure how/if these apply to the chroma plane */ diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c index 5a3677ea25b0..a4ce21d4c024 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.c +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -3856,7 +3856,7 @@ void skl_wm_plane_disable_noatomic(struct intel_crtc *crtc, return; skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb[plane->id], 0, 0); - skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb[plane->id], 0, 0); + skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb_y[plane->id], 0, 0); crtc_state->wm.skl.plane_min_ddb[plane->id] = 0; crtc_state->wm.skl.plane_interim_ddb[plane->id] = 0; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c index be4bbff1a57c..d5190e11b270 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_user.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c @@ -259,7 +259,7 @@ void intel_engines_driver_register(struct drm_i915_private *i915) p = &prev->rb_right; } - if (IS_ENABLED(CONFIG_DRM_I915_SELFTESTS) && + if (IS_ENABLED(CONFIG_DRM_I915_SELFTEST) && IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) { struct intel_engine_cs *engine; unsigned int isolation; diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c index 33351deeea4f..07eaf71955c4 100644 --- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c @@ -16,9 +16,9 @@ static int cmp_u64(const void *A, const void *B) { const u64 *a = A, *b = B; - if (a < b) + if (*a < *b) return -1; - else if (a > b) + else if (*a > *b) return 1; else return 0; @@ -28,9 +28,9 @@ static int cmp_u32(const void *A, const void *B) { const u32 *a = A, *b = B; - if (a < b) + if (*a < *b) return -1; - else if (a > b) + else if (*a > *b) return 1; else return 0; diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c index 0b25abebb803..9687c59de350 100644 --- a/drivers/gpu/drm/panthor/panthor_device.c +++ b/drivers/gpu/drm/panthor/panthor_device.c @@ -182,7 +182,10 @@ int panthor_device_init(struct panthor_device *ptdev) return ret; #ifdef CONFIG_DEBUG_FS - drmm_mutex_init(&ptdev->base, &ptdev->gems.lock); + ret = drmm_mutex_init(&ptdev->base, &ptdev->gems.lock); + if (ret) + return ret; + INIT_LIST_HEAD(&ptdev->gems.node); #endif diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c index de8e6689a869..90f59d782a80 100644 --- a/drivers/gpu/drm/panthor/panthor_fw.c +++ b/drivers/gpu/drm/panthor/panthor_fw.c @@ -829,6 +829,7 @@ static int panthor_fw_load(struct panthor_device *ptdev) } if (hdr.size > iter.size) { + ret = -EINVAL; drm_err(&ptdev->base, "Firmware image is truncated\n"); goto out; } diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index 4032c6ad45bc..e384cbd0cbf7 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -3764,10 +3764,8 @@ static int tegra_sor_probe(struct platform_device *pdev) sor->num_settings = sor->soc->num_settings; sor->pmc = devm_tegra_pmc_get(&pdev->dev); - if (IS_ERR(sor->pmc)) { - err = PTR_ERR(sor->pmc); - goto put_aux; - } + if (IS_ERR(sor->pmc)) + return PTR_ERR(sor->pmc); np = of_parse_phandle(pdev->dev.of_node, "nvidia,dpaux", 0); if (np) { diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 278bbe7a11ad..46983e7de7a3 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -1051,9 +1051,31 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt, return -EBUSY; #ifdef CONFIG_X86 - /* Anything returned to the system needs to be cached. */ - if (tt->caching != ttm_cached) - set_pages_array_wb(tt->pages, tt->num_pages); + /* Anything returned to the system needs to be cached. Walk allocations + * skipping NULL pages and issue set_pages_array_wb() per contiguous run. + */ + if (tt->caching != ttm_cached) { + pgoff_t run_start = 0, run_count = 0; + + for (i = 0; i < tt->num_pages; i += num_pages) { + page = tt->pages[i]; + if (unlikely(!page || ttm_backup_page_ptr_is_handle(page))) { + if (run_count) { + set_pages_array_wb(&tt->pages[run_start], + run_count); + run_count = 0; + } + num_pages = 1; + continue; + } + num_pages = 1UL << ttm_pool_page_order(pool, page); + if (!run_count) + run_start = i; + run_count += num_pages; + } + if (run_count) + set_pages_array_wb(&tt->pages[run_start], run_count); + } #endif if (tt->dma_address || flags->purge) { @@ -1061,7 +1083,7 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt, unsigned int order; page = tt->pages[i]; - if (unlikely(!page)) { + if (unlikely(!page || ttm_backup_page_ptr_is_handle(page))) { num_pages = 1; continue; } @@ -1104,6 +1126,10 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt, if (unlikely(!page)) continue; + /* Already-handled entry from a previous attempt. */ + if (unlikely(ttm_backup_page_ptr_is_handle(page))) + continue; + ttm_pool_split_for_swap(pool, page); shandle = ttm_backup_backup_page(backup, page, flags->writeback, i, diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c index 435d37d36034..66c3f6f74e9c 100644 --- a/drivers/gpu/drm/virtio/virtgpu_gem.c +++ b/drivers/gpu/drm/virtio/virtgpu_gem.c @@ -139,13 +139,15 @@ void virtio_gpu_gem_object_close(struct drm_gem_object *obj, if (!vgdev->has_virgl_3d) return; - objs = virtio_gpu_array_alloc(1); - if (!objs) - return; - virtio_gpu_array_add_obj(objs, obj); + if (vfpriv->context_created) { + objs = virtio_gpu_array_alloc(1); + if (!objs) + return; + virtio_gpu_array_add_obj(objs, obj); - virtio_gpu_cmd_context_detach_resource(vgdev, vfpriv->ctx_id, - objs); + virtio_gpu_cmd_context_detach_resource(vgdev, vfpriv->ctx_id, + objs); + } virtio_gpu_notify(vgdev); } diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index cfde9f573df6..b4329f28e976 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -49,7 +49,10 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work) virtio_gpu_cmd_get_edids(vgdev); virtio_gpu_cmd_get_display_info(vgdev); virtio_gpu_notify(vgdev); - drm_helper_hpd_irq_event(vgdev->ddev); + wait_event_timeout(vgdev->resp_wq, + !vgdev->display_info_pending, + 5 * HZ); + drm_kms_helper_hotplug_event(vgdev->ddev); } events_clear |= VIRTIO_GPU_EVENT_DISPLAY; } diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index c8b9475a7472..e5e1af8b8e8a 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -840,9 +840,6 @@ static void virtio_gpu_cmd_get_display_info_cb(struct virtio_gpu_device *vgdev, vgdev->display_info_pending = false; spin_unlock(&vgdev->display_info_lock); wake_up(&vgdev->resp_wq); - - if (!drm_helper_hpd_irq_event(vgdev->ddev)) - drm_kms_helper_hotplug_event(vgdev->ddev); } static void virtio_gpu_cmd_get_capset_info_cb(struct virtio_gpu_device *vgdev, diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 4c80bac67622..7ed76349075f 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -1102,6 +1102,21 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, xe_pm_runtime_get_noresume(xe); } + /* + * Attach CCS BBs before submitting the copy job below so a VF + * migration racing the copy sees valid, up to date attach state. + */ + if (IS_VF_CCS_READY(xe) && + ((move_lacks_source && new_mem->mem_type == XE_PL_TT) || + (old_mem_type == XE_PL_SYSTEM && new_mem->mem_type == XE_PL_TT)) && + handle_system_ccs) { + ret = xe_sriov_vf_ccs_attach_bo(bo, new_mem); + if (ret) { + xe_pm_runtime_put(xe); + goto out; + } + } + if (move_lacks_source) { u32 flags = 0; @@ -1139,22 +1154,19 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, ttm_bo_move_null(ttm_bo, new_mem); } - dma_fence_put(fence); - xe_pm_runtime_put(xe); - /* - * CCS meta data is migrated from TT -> SMEM. So, let us detach the - * BBs from BO as it is no longer needed. + * Detach must wait for the copy above to complete: a VF migration + * racing an in-flight copy must still see valid CCS BBs, so don't + * tear them down until the copy fence has signaled. */ if (IS_VF_CCS_READY(xe) && old_mem_type == XE_PL_TT && - new_mem->mem_type == XE_PL_SYSTEM) + new_mem->mem_type == XE_PL_SYSTEM) { + dma_fence_wait(fence, false); xe_sriov_vf_ccs_detach_bo(bo); + } - if (IS_VF_CCS_READY(xe) && - ((move_lacks_source && new_mem->mem_type == XE_PL_TT) || - (old_mem_type == XE_PL_SYSTEM && new_mem->mem_type == XE_PL_TT)) && - handle_system_ccs) - ret = xe_sriov_vf_ccs_attach_bo(bo); + dma_fence_put(fence); + xe_pm_runtime_put(xe); out: if ((!ttm_bo->resource || ttm_bo->resource->mem_type == XE_PL_SYSTEM) && @@ -1349,7 +1361,7 @@ int xe_bo_notifier_prepare_pinned(struct xe_bo *bo) backup = xe_bo_init_locked(xe, NULL, NULL, bo->ttm.base.resv, NULL, xe_bo_size(bo), DRM_XE_GEM_CPU_CACHING_WB, ttm_bo_type_kernel, XE_BO_FLAG_SYSTEM | XE_BO_FLAG_NEEDS_CPU_ACCESS | - XE_BO_FLAG_PINNED, &exec); + XE_BO_FLAG_PINNED, NULL, &exec); if (IS_ERR(backup)) { drm_exec_retry_on_contention(&exec); ret = PTR_ERR(backup); @@ -1490,7 +1502,7 @@ int xe_bo_evict_pinned(struct xe_bo *bo) xe_bo_size(bo), DRM_XE_GEM_CPU_CACHING_WB, ttm_bo_type_kernel, XE_BO_FLAG_SYSTEM | XE_BO_FLAG_NEEDS_CPU_ACCESS | - XE_BO_FLAG_PINNED, &exec); + XE_BO_FLAG_PINNED, NULL, &exec); if (IS_ERR(backup)) { drm_exec_retry_on_contention(&exec); ret = PTR_ERR(backup); @@ -1826,6 +1838,8 @@ static void xe_ttm_bo_destroy(struct ttm_buffer_object *ttm_bo) if (bo->ttm.base.import_attach) drm_prime_gem_destroy(&bo->ttm.base, NULL); + if (bo->dma_buf) + dma_buf_put(bo->dma_buf); drm_gem_object_release(&bo->ttm.base); xe_assert(xe, list_empty(&ttm_bo->base.gpuva.list)); @@ -2283,6 +2297,8 @@ void xe_bo_free(struct xe_bo *bo) * @cpu_caching: The cpu caching used for system memory backing store. * @type: The TTM buffer object type. * @flags: XE_BO_FLAG_ flags. + * @dma_buf: The dma-buf to reference for the BO lifetime (imported BOs), + * or NULL. * @exec: The drm_exec transaction to use for exhaustive eviction. * * Initialize or create an xe buffer object. On failure, any allocated buffer @@ -2294,7 +2310,8 @@ struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, struct xe_tile *tile, struct dma_resv *resv, struct ttm_lru_bulk_move *bulk, size_t size, u16 cpu_caching, enum ttm_bo_type type, - u32 flags, struct drm_exec *exec) + u32 flags, struct dma_buf *dma_buf, + struct drm_exec *exec) { struct ttm_operation_ctx ctx = { .interruptible = true, @@ -2383,6 +2400,17 @@ struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, placement = (type == ttm_bo_type_sg || bo->flags & XE_BO_FLAG_DEFER_BACKING) ? &sys_placement : &bo->placement; + + /* + * For imported BOs, keep the exporter dma-buf alive for the BO + * lifetime. Taken before ttm_bo_init_reserved() to also cover a + * creation failure there. Released in xe_ttm_bo_destroy(). + */ + if (dma_buf) { + get_dma_buf(dma_buf); + bo->dma_buf = dma_buf; + } + err = ttm_bo_init_reserved(&xe->ttm, &bo->ttm, type, placement, alignment, &ctx, NULL, resv, xe_ttm_bo_destroy); @@ -2500,7 +2528,7 @@ __xe_bo_create_locked(struct xe_device *xe, vm && !xe_vm_in_fault_mode(vm) && flags & XE_BO_FLAG_USER ? &vm->lru_bulk_move : NULL, size, - cpu_caching, type, flags, exec); + cpu_caching, type, flags, NULL, exec); if (IS_ERR(bo)) return bo; diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 6340317f7d2e..7ae1d9ac0574 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -118,7 +118,8 @@ struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, struct xe_tile *tile, struct dma_resv *resv, struct ttm_lru_bulk_move *bulk, size_t size, u16 cpu_caching, enum ttm_bo_type type, - u32 flags, struct drm_exec *exec); + u32 flags, struct dma_buf *dma_buf, + struct drm_exec *exec); struct xe_bo *xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, enum ttm_bo_type type, u32 flags, diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index fcc63ae3f455..e45f24301050 100644 --- a/drivers/gpu/drm/xe/xe_bo_types.h +++ b/drivers/gpu/drm/xe/xe_bo_types.h @@ -36,6 +36,8 @@ struct xe_bo { struct xe_bo *backup_obj; /** @parent_obj: Ref to parent bo if this a backup_obj */ struct xe_bo *parent_obj; + /** @dma_buf: Imported dma-buf ref to keep its resv alive. */ + struct dma_buf *dma_buf; /** @flags: flags for this buffer object */ u32 flags; /** @vm: VM this BO is attached to, for extobj this will be NULL */ diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index abe25aedeead..dcb48caa485d 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -426,7 +426,6 @@ static const struct drm_ioctl_desc xe_ioctls_admin_only[] = { static const struct drm_driver admin_only_driver = { .driver_features = - XE_DISPLAY_DRIVER_FEATURES | DRIVER_GEM | DRIVER_RENDER | DRIVER_GEM_GPUVA, .open = xe_file_open, .postclose = xe_file_close, @@ -438,7 +437,6 @@ static const struct drm_driver admin_only_driver = { .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, - XE_DISPLAY_DRIVER_OPS, }; /** @@ -580,7 +578,7 @@ int xe_device_init_early(struct xe_device *xe) WQ_MEM_RECLAIM); xe->ordered_wq = alloc_ordered_workqueue("xe-ordered-wq", 0); xe->unordered_wq = alloc_workqueue("xe-unordered-wq", WQ_PERCPU, 0); - xe->destroy_wq = alloc_workqueue("xe-destroy-wq", WQ_PERCPU, 0); + xe->destroy_wq = alloc_workqueue("xe-destroy-wq", WQ_PERCPU | WQ_MEM_RECLAIM, 0); if (!xe->ordered_wq || !xe->unordered_wq || !xe->preempt_fence_wq || !xe->destroy_wq) { /* diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 32dd2ffbc796..aad10899d9ac 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -355,7 +355,7 @@ struct xe_device { /** @unordered_wq: used to serialize unordered work */ struct workqueue_struct *unordered_wq; - /** @destroy_wq: used to serialize user destroy work, like queue */ + /** @destroy_wq: used to serialize SVM pagemap destroy work */ struct workqueue_struct *destroy_wq; /** @tiles: device tiles */ diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 8a920e58245c..bf0728838ead 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -302,7 +302,7 @@ xe_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) bo = xe_bo_init_locked(xe, NULL, NULL, resv, NULL, dma_buf->size, 0, /* Will require 1way or 2way for vm_bind */ - ttm_bo_type_sg, XE_BO_FLAG_SYSTEM, &exec); + ttm_bo_type_sg, XE_BO_FLAG_SYSTEM, dma_buf, &exec); drm_exec_retry_on_contention(&exec); if (IS_ERR(bo)) { ret = PTR_ERR(bo); diff --git a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h index e5e53b421f29..cda14d954e57 100644 --- a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h @@ -10,6 +10,7 @@ #include <linux/workqueue.h> #include "xe_gpu_scheduler_types.h" +#include "xe_hw_fence_types.h" struct dma_fence; struct xe_exec_queue; @@ -24,6 +25,10 @@ struct xe_guc_exec_queue { struct rcu_head rcu; /** @sched: GPU scheduler for this xe_exec_queue */ struct xe_gpu_scheduler sched; + /** + * @name: Scheduler timeline name, kept with @sched until RCU free. + */ + char name[MAX_FENCE_NAME_LEN]; /** @entity: Scheduler entity for this xe_exec_queue */ struct xe_sched_entity entity; /** diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index f5c3d8a97ec6..1c92b96e4c32 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -10,6 +10,7 @@ #include <linux/circ_buf.h> #include <linux/dma-fence-array.h> +#include <drm/drm_drv.h> #include <drm/drm_managed.h> #include "abi/guc_actions_abi.h" @@ -37,6 +38,7 @@ #include "xe_macros.h" #include "xe_map.h" #include "xe_mocs.h" +#include "xe_module.h" #include "xe_pm.h" #include "xe_ring_ops_types.h" #include "xe_sched_job.h" @@ -232,17 +234,9 @@ static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q) static void guc_submit_sw_fini(struct drm_device *drm, void *arg) { struct xe_guc *guc = arg; - struct xe_device *xe = guc_to_xe(guc); struct xe_gt *gt = guc_to_gt(guc); - int ret; - - ret = wait_event_timeout(guc->submission_state.fini_wq, - xa_empty(&guc->submission_state.exec_queue_lookup), - HZ * 5); - drain_workqueue(xe->destroy_wq); - - xe_gt_assert(gt, ret); + xe_gt_assert(gt, xa_empty(&guc->submission_state.exec_queue_lookup)); xa_destroy(&guc->submission_state.exec_queue_lookup); } @@ -319,8 +313,6 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids) xa_init(&guc->submission_state.exec_queue_lookup); - init_waitqueue_head(&guc->submission_state.fini_wq); - primelockdep(guc); guc->submission_state.initialized = true; @@ -411,9 +403,6 @@ static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, xe_guc_id_mgr_release_locked(&guc->submission_state.idm, q->guc->id, q->width); - if (xa_empty(&guc->submission_state.exec_queue_lookup)) - wake_up(&guc->submission_state.fini_wq); - mutex_unlock(&guc->submission_state.lock); } @@ -1685,6 +1674,7 @@ static void guc_exec_queue_fini(struct xe_exec_queue *q) { struct xe_guc_exec_queue *ge = q->guc; struct xe_guc *guc = exec_queue_to_guc(q); + struct drm_device *drm = &guc_to_xe(guc)->drm; if (xe_exec_queue_is_multi_queue_secondary(q)) { struct xe_exec_queue_group *group = q->multi_queue.group; @@ -1703,36 +1693,52 @@ static void guc_exec_queue_fini(struct xe_exec_queue *q) * (timeline name). */ kfree_rcu(ge, rcu); + + drm_dev_put(drm); } -static void __guc_exec_queue_destroy_async(struct work_struct *w) +static void guc_exec_queue_do_destroy(struct xe_exec_queue *q) { - struct xe_guc_exec_queue *ge = - container_of(w, struct xe_guc_exec_queue, destroy_async); - struct xe_exec_queue *q = ge->q; + struct xe_guc_exec_queue *ge = q->guc; struct xe_guc *guc = exec_queue_to_guc(q); + struct xe_device *xe = guc_to_xe(guc); + struct drm_device *drm = &xe->drm; + + /* + * guc_exec_queue_fini() drops the queue's drm_device ref. + * Keep the device alive until the PM-runtime guard unwinds. + */ + drm_dev_get(drm); + + scoped_guard(xe_pm_runtime, xe) { + trace_xe_exec_queue_destroy(q); - guard(xe_pm_runtime)(guc_to_xe(guc)); - trace_xe_exec_queue_destroy(q); + /* Confirm no work left behind accessing device structures */ + cancel_delayed_work_sync(&ge->sched.base.work_tdr); - /* Confirm no work left behind accessing device structures */ - cancel_delayed_work_sync(&ge->sched.base.work_tdr); + xe_exec_queue_fini(q); + } - xe_exec_queue_fini(q); + drm_dev_put(drm); } -static void guc_exec_queue_destroy_async(struct xe_exec_queue *q) +static void __guc_exec_queue_destroy_async(struct work_struct *w) { - struct xe_guc *guc = exec_queue_to_guc(q); - struct xe_device *xe = guc_to_xe(guc); + struct xe_guc_exec_queue *ge = + container_of(w, struct xe_guc_exec_queue, destroy_async); + + guc_exec_queue_do_destroy(ge->q); +} +static void guc_exec_queue_destroy_async(struct xe_exec_queue *q) +{ INIT_WORK(&q->guc->destroy_async, __guc_exec_queue_destroy_async); /* We must block on kernel engines so slabs are empty on driver unload */ if (q->flags & EXEC_QUEUE_FLAG_PERMANENT || exec_queue_wedged(q)) - __guc_exec_queue_destroy_async(&q->guc->destroy_async); + guc_exec_queue_do_destroy(q); else - queue_work(xe->destroy_wq, &q->guc->destroy_async); + xe_destroy_wq_queue(&q->guc->destroy_async); } static void __guc_exec_queue_destroy(struct xe_guc *guc, struct xe_exec_queue *q) @@ -1927,6 +1933,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q) { struct xe_gpu_scheduler *sched; struct xe_guc *guc = exec_queue_to_guc(q); + struct drm_device *drm = &guc_to_xe(guc)->drm; struct workqueue_struct *submit_wq = NULL; struct xe_guc_exec_queue *ge; long timeout; @@ -1938,6 +1945,8 @@ static int guc_exec_queue_init(struct xe_exec_queue *q) if (!ge) return -ENOMEM; + drm_dev_get(drm); + q->guc = ge; ge->q = q; init_rcu_head(&ge->rcu); @@ -1955,6 +1964,8 @@ static int guc_exec_queue_init(struct xe_exec_queue *q) xe_exec_queue_assign_name(q, q->guc->id); + strscpy(ge->name, q->name, sizeof(ge->name)); + /* * Use primary queue's submit_wq for all secondary queues of a * multi queue group. This serialization avoids any locking around @@ -1969,7 +1980,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q) err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops, submit_wq, xe_lrc_ring_size() / MAX_JOB_SIZE_BYTES, 64, timeout, guc_to_gt(guc)->ordered_wq, NULL, - q->name, gt_to_xe(q->gt)->drm.dev); + ge->name, gt_to_xe(q->gt)->drm.dev); if (err) goto err_release_id; @@ -2014,6 +2025,7 @@ err_release_id: release_guc_id(guc, q); err_free: kfree(ge); + drm_dev_put(drm); return err; } diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h index c7b9642b41ba..31a2acb63ac3 100644 --- a/drivers/gpu/drm/xe/xe_guc_types.h +++ b/drivers/gpu/drm/xe/xe_guc_types.h @@ -100,8 +100,6 @@ struct xe_guc { * even initialized - before that not even the lock is valid */ bool initialized; - /** @submission_state.fini_wq: submit fini wait queue */ - wait_queue_head_t fini_wq; } submission_state; /** @hwconfig: Hardware config state */ diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 9428dd5e7760..7d28290e7d1c 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -1166,6 +1166,8 @@ static int emit_flush_invalidate(u32 *dw, int i, u32 flags) * @tile: Tile whose migration context to be used. * @q : Execution to be used along with migration context. * @src_bo: The buffer object @src is currently bound to. + * @new_mem: The (not yet committed) destination resource @src_bo is being + * moved into; src_bo->ttm.resource is still the old resource. * @read_write : Creates BB commands for CCS read/write. * * Creates batch buffer instructions to copy CCS metadata from CCS pool to @@ -1177,12 +1179,13 @@ static int emit_flush_invalidate(u32 *dw, int i, u32 flags) */ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, struct xe_bo *src_bo, + struct ttm_resource *new_mem, enum xe_sriov_vf_ccs_rw_ctxs read_write) { bool src_is_pltt = read_write == XE_SRIOV_VF_CCS_READ_CTX; bool dst_is_pltt = read_write == XE_SRIOV_VF_CCS_WRITE_CTX; - struct ttm_resource *src = src_bo->ttm.resource; + struct ttm_resource *src = new_mem; struct xe_migrate *m = tile->migrate; struct xe_gt *gt = tile->primary_gt; u32 batch_size, batch_size_allocated; diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h index 965c45889c72..78e5b63f3ebe 100644 --- a/drivers/gpu/drm/xe/xe_migrate.h +++ b/drivers/gpu/drm/xe/xe_migrate.h @@ -138,6 +138,7 @@ struct dma_fence *xe_migrate_resolve(struct xe_migrate *m, int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, struct xe_bo *src_bo, + struct ttm_resource *new_mem, enum xe_sriov_vf_ccs_rw_ctxs read_write); void xe_migrate_ccs_rw_copy_clear(struct xe_bo *src_bo, diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c index 4cb578182912..99347f216ec8 100644 --- a/drivers/gpu/drm/xe/xe_module.c +++ b/drivers/gpu/drm/xe/xe_module.c @@ -7,6 +7,7 @@ #include <linux/init.h> #include <linux/module.h> +#include <linux/workqueue.h> #include <drm/drm_module.h> @@ -91,6 +92,50 @@ static int xe_check_nomodeset(void) return 0; } +static struct workqueue_struct *xe_destroy_wq; + +static int __init xe_destroy_wq_module_init(void) +{ + xe_destroy_wq = alloc_workqueue("xe-guc-destroy-wq", WQ_UNBOUND, 0); + if (!xe_destroy_wq) + return -ENOMEM; + return 0; +} + +static void xe_destroy_wq_module_exit(void) +{ + if (xe_destroy_wq) + destroy_workqueue(xe_destroy_wq); + xe_destroy_wq = NULL; +} + +/** + * xe_destroy_wq_queue() - Queue work on the destroy workqueue + * @work: work item to queue + * + * The destroy workqueue has module lifetime and is used for GuC exec queue + * teardown that can outlive a single xe_device. SVM pagemap destroy uses the + * per-device xe->destroy_wq instead. + * + * Return: %true if @work was queued, %false if it was already pending. + */ +bool xe_destroy_wq_queue(struct work_struct *work) +{ + return queue_work(xe_destroy_wq, work); +} + +/** + * xe_destroy_wq_flush() - Flush the destroy workqueue + * + * Drains all pending destroy work. Called from PCI remove to ensure + * teardown ordering before the device is destroyed. + */ +void xe_destroy_wq_flush(void) +{ + if (xe_destroy_wq) + flush_workqueue(xe_destroy_wq); +} + struct init_funcs { int (*init)(void); void (*exit)(void); @@ -113,6 +158,10 @@ static const struct init_funcs init_funcs[] = { .exit = xe_sched_job_module_exit, }, { + .init = xe_destroy_wq_module_init, + .exit = xe_destroy_wq_module_exit, + }, + { .init = xe_register_pci_driver, .exit = xe_unregister_pci_driver, }, diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h index 79cb9639c0f3..e8e54f701cf3 100644 --- a/drivers/gpu/drm/xe/xe_module.h +++ b/drivers/gpu/drm/xe/xe_module.h @@ -8,6 +8,8 @@ #include <linux/types.h> +struct work_struct; + /* Module modprobe variables */ struct xe_modparam { bool force_execlist; @@ -27,5 +29,8 @@ struct xe_modparam { extern struct xe_modparam xe_modparam; +bool xe_destroy_wq_queue(struct work_struct *work); +void xe_destroy_wq_flush(void); + #endif diff --git a/drivers/gpu/drm/xe/xe_nvm.c b/drivers/gpu/drm/xe/xe_nvm.c index 33487e91f366..1ea67eaeae24 100644 --- a/drivers/gpu/drm/xe/xe_nvm.c +++ b/drivers/gpu/drm/xe/xe_nvm.c @@ -60,35 +60,40 @@ static bool xe_nvm_writable_override(struct xe_device *xe) struct xe_mmio *mmio = xe_root_tile_mmio(xe); bool writable_override; struct xe_reg reg; - u32 test_bit; + u32 test_bit, test_val; switch (xe->info.platform) { case XE_CRESCENTISLAND: reg = PCODE_SCRATCH(0); test_bit = FDO_MODE; + test_val = FDO_MODE; break; case XE_BATTLEMAGE: reg = HECI_FWSTS2(DG2_GSC_HECI2_BASE); test_bit = HECI_FW_STATUS_2_NVM_ACCESS_MODE; + test_val = 0; break; case XE_PVC: reg = HECI_FWSTS2(PVC_GSC_HECI2_BASE); test_bit = HECI_FW_STATUS_2_NVM_ACCESS_MODE; + test_val = 0; break; case XE_DG2: reg = HECI_FWSTS2(DG2_GSC_HECI2_BASE); test_bit = HECI_FW_STATUS_2_NVM_ACCESS_MODE; + test_val = 0; break; case XE_DG1: reg = HECI_FWSTS2(DG1_GSC_HECI2_BASE); test_bit = HECI_FW_STATUS_2_NVM_ACCESS_MODE; + test_val = 0; break; default: drm_err(&xe->drm, "Unknown platform\n"); return true; } - writable_override = !(xe_mmio_read32(mmio, reg) & test_bit); + writable_override = (xe_mmio_read32(mmio, reg) & test_bit) == test_val; if (writable_override) drm_info(&xe->drm, "NVM access overridden by jumper\n"); return writable_override; diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index 3165686e3e04..9cd873708136 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -788,7 +788,8 @@ static int xe_info_init_early(struct xe_device *xe, xe->info.probe_display = IS_ENABLED(CONFIG_DRM_XE_DISPLAY) && xe_modparam.probe_display && - desc->has_display; + desc->has_display && + !xe_device_is_admin_only(xe); xe->info.force_execlist = xe_modparam.force_execlist; xe_assert(xe, desc->max_gt_per_tile > 0); @@ -1048,6 +1049,12 @@ static void xe_pci_remove(struct pci_dev *pdev) return; xe_device_remove(xe); + + /* + * Preserve remove-time flush after moving destroy work to module + * lifetime. + */ + xe_destroy_wq_flush(); xe_pm_fini(xe); } diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index e787c0c27c42..39c9c8f0ea2d 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -2365,8 +2365,11 @@ static void xe_pt_update_ops_init(struct xe_vm_pgtable_update_ops *pt_update_ops) { init_llist_head(&pt_update_ops->deferred); + pt_update_ops->current_op = 0; pt_update_ops->start = ~0x0ull; pt_update_ops->last = 0x0ull; + pt_update_ops->needs_svm_lock = false; + pt_update_ops->needs_invalidation = false; xe_page_reclaim_list_init(&pt_update_ops->prl); } diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c index 09b99fb2608b..6787564629c6 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c @@ -404,6 +404,8 @@ void xe_sriov_vf_ccs_rw_update_bb_addr(struct xe_sriov_vf_ccs_ctx *ctx) /** * xe_sriov_vf_ccs_attach_bo - Insert CCS read write commands in the BO. * @bo: the &buffer object to which batch buffer commands will be added. + * @new_mem: the (not yet committed) destination resource @bo is being moved + * into; bo->ttm.resource is still the old resource at this point. * * This function shall be called only by VF. It inserts the PTEs and copy * command instructions in the BO by calling xe_migrate_ccs_rw_copy() @@ -411,7 +413,7 @@ void xe_sriov_vf_ccs_rw_update_bb_addr(struct xe_sriov_vf_ccs_ctx *ctx) * * Returns: 0 if successful, negative error code on failure. */ -int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo) +int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo, struct ttm_resource *new_mem) { struct xe_device *xe = xe_bo_device(bo); enum xe_sriov_vf_ccs_rw_ctxs ctx_id; @@ -430,7 +432,21 @@ int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo) xe_assert(xe, !bb); ctx = &xe->sriov.vf.ccs.contexts[ctx_id]; - err = xe_migrate_ccs_rw_copy(tile, ctx->mig_q, bo, ctx_id); + err = xe_migrate_ccs_rw_copy(tile, ctx->mig_q, bo, new_mem, ctx_id); + if (err) + goto err_unwind; + } + return 0; + +err_unwind: + /* + * Clean up any contexts already attached. Can't reuse + * xe_sriov_vf_ccs_detach_bo() here as it requires both contexts + * attached before cleaning up either one. + */ + for_each_ccs_rw_ctx(ctx_id) { + if (bo->bb_ccs[ctx_id]) + xe_migrate_ccs_rw_copy_clear(bo, ctx_id); } return err; } diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h index 00e58b36c510..e1034d852104 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h @@ -11,11 +11,12 @@ #include "xe_sriov_vf_ccs_types.h" struct drm_printer; +struct ttm_resource; struct xe_device; struct xe_bo; int xe_sriov_vf_ccs_init(struct xe_device *xe); -int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo); +int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo, struct ttm_resource *new_mem); int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo); int xe_sriov_vf_ccs_register_context(struct xe_device *xe); void xe_sriov_vf_ccs_rebase(struct xe_device *xe); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 080c2fff0e95..32ded13491ca 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -3255,11 +3255,26 @@ static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm, .request_decompress = false, .check_purged = true, }); - if (!err && !xe_vma_has_no_bo(vma)) - err = xe_bo_migrate(xe_vma_bo(vma), - region_to_mem_type[region], - NULL, - exec); + if (!err && !xe_vma_has_no_bo(vma)) { + struct xe_bo *bo = xe_vma_bo(vma); + u32 mem_type; + + if (region == DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC) { + unsigned int i; + + mem_type = XE_PL_TT; + for (i = 0; i < bo->placement.num_placement; i++) { + if (mem_type_is_vram(bo->placements[i].mem_type)) { + mem_type = bo->placements[i].mem_type; + break; + } + } + } else { + mem_type = region_to_mem_type[region]; + } + + err = xe_bo_migrate(bo, mem_type, NULL, exec); + } break; } default: diff --git a/drivers/gpu/drm/xe/xe_wopcm.c b/drivers/gpu/drm/xe/xe_wopcm.c index 900daf1d1b1b..fe65ed246775 100644 --- a/drivers/gpu/drm/xe/xe_wopcm.c +++ b/drivers/gpu/drm/xe/xe_wopcm.c @@ -49,9 +49,9 @@ */ /* Default WOPCM size is 2MB from Gen11, 1MB on previous platforms */ -/* FIXME: Larger size require for 2 tile PVC, do a proper probe sooner or later */ +/* FIXME: Larger size require for some platforms, do a proper probe sooner or later */ #define DGFX_WOPCM_SIZE SZ_4M -/* FIXME: Larger size require for MTL, do a proper probe sooner or later */ +#define LNL_WOPCM_SIZE SZ_8M #define MTL_WOPCM_SIZE SZ_4M #define WOPCM_SIZE SZ_2M @@ -179,9 +179,14 @@ err_out: u32 xe_wopcm_size(struct xe_device *xe) { - return IS_DGFX(xe) ? DGFX_WOPCM_SIZE : - xe->info.platform == XE_METEORLAKE ? MTL_WOPCM_SIZE : - WOPCM_SIZE; + if (xe->info.platform >= XE_LUNARLAKE) + return LNL_WOPCM_SIZE; + else if (IS_DGFX(xe)) + return DGFX_WOPCM_SIZE; + else if (xe->info.platform == XE_METEORLAKE) + return MTL_WOPCM_SIZE; + else + return WOPCM_SIZE; } static u32 max_wopcm_size(struct xe_device *xe) diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index e3884096c2fe..ea3b584990c9 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -1012,10 +1012,10 @@ void host1x_bo_clear_cached_mappings(struct host1x_bo *bo) if (WARN_ON(!cache)) continue; - mutex_lock(&mapping->cache->lock); + mutex_lock(&cache->lock); WARN_ON(kref_read(&mapping->ref) != 1); __host1x_bo_unpin(&mapping->ref); - mutex_unlock(&mapping->cache->lock); + mutex_unlock(&cache->lock); } } EXPORT_SYMBOL(host1x_bo_clear_cached_mappings); diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index 29a23484cbe7..01a022b3ee82 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -1009,7 +1009,7 @@ struct ec_sensors_data { /* sorted list of unique register banks */ u8 banks[ASUS_EC_MAX_BANK + 1]; /* in jiffies */ - unsigned long last_updated; + u64 next_update; struct lock_data lock_data; /* number of board EC sensors */ u8 nr_sensors; @@ -1189,7 +1189,7 @@ static int asus_ec_block_read(const struct device *dev, } for (ireg = 0; ireg < ec->nr_registers; ireg++) { reg_bank = register_bank(ec->registers[ireg]); - if (reg_bank < bank) { + if (reg_bank != bank) { continue; } ec_read(register_index(ec->registers[ireg]), @@ -1278,13 +1278,12 @@ static int get_cached_value_or_update(const struct device *dev, int sensor_index, struct ec_sensors_data *state, s32 *value) { - if (time_after(jiffies, state->last_updated + HZ)) { + if (time_after64(get_jiffies_64(), state->next_update)) { if (update_ec_sensors(dev, state)) { dev_err(dev, "update_ec_sensors() failure\n"); return -EIO; } - - state->last_updated = jiffies; + state->next_update = get_jiffies_64() + HZ; } *value = state->sensors[sensor_index].cached_value; @@ -1402,6 +1401,7 @@ static int asus_ec_probe(struct platform_device *pdev) if (!ec_data) return -ENOMEM; + ec_data->next_update = INITIAL_JIFFIES; dev_set_drvdata(dev, ec_data); ec_data->board_info = pboard_info; @@ -1495,9 +1495,11 @@ static int asus_ec_probe(struct platform_device *pdev) if (!nr_count[type]) continue; - asus_ec_hwmon_add_chan_info(asus_ec_hwmon_chan, dev, - nr_count[type], type, - hwmon_attributes[type]); + status = asus_ec_hwmon_add_chan_info(asus_ec_hwmon_chan, dev, + nr_count[type], type, + hwmon_attributes[type]); + if (status) + return status; *ptr_asus_ec_ci++ = asus_ec_hwmon_chan++; } diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c index b6e508e43fa1..8354a002f4c5 100644 --- a/drivers/hwmon/corsair-cpro.c +++ b/drivers/hwmon/corsair-cpro.c @@ -645,6 +645,7 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) out_hw_close: hid_hw_close(hdev); + hid_device_io_stop(hdev); out_hw_stop: hid_hw_stop(hdev); return ret; diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c index 76f3e1da68d0..ce958cdaef58 100644 --- a/drivers/hwmon/corsair-psu.c +++ b/drivers/hwmon/corsair-psu.c @@ -822,6 +822,7 @@ static int corsairpsu_probe(struct hid_device *hdev, const struct hid_device_id fail_and_close: hid_hw_close(hdev); + hid_device_io_stop(hdev); fail_and_stop: hid_hw_stop(hdev); return ret; diff --git a/drivers/hwmon/gigabyte_waterforce.c b/drivers/hwmon/gigabyte_waterforce.c index 27487e215bdd..4eea05f8b569 100644 --- a/drivers/hwmon/gigabyte_waterforce.c +++ b/drivers/hwmon/gigabyte_waterforce.c @@ -371,13 +371,15 @@ static int waterforce_probe(struct hid_device *hdev, const struct hid_device_id if (IS_ERR(priv->hwmon_dev)) { ret = PTR_ERR(priv->hwmon_dev); hid_err(hdev, "hwmon registration failed with %d\n", ret); - goto fail_and_close; + goto fail_and_io_stop; } waterforce_debugfs_init(priv); return 0; +fail_and_io_stop: + hid_device_io_stop(hdev); fail_and_close: hid_hw_close(hdev); fail_and_stop: diff --git a/drivers/hwmon/nzxt-kraken3.c b/drivers/hwmon/nzxt-kraken3.c index d00409bcab93..05525406c5fb 100644 --- a/drivers/hwmon/nzxt-kraken3.c +++ b/drivers/hwmon/nzxt-kraken3.c @@ -948,7 +948,7 @@ static int kraken3_probe(struct hid_device *hdev, const struct hid_device_id *id ret = kraken3_init_device(hdev); if (ret < 0) { hid_err(hdev, "device init failed with %d\n", ret); - goto fail_and_close; + goto fail_and_stop_io; } ret = kraken3_get_fw_ver(hdev); @@ -960,13 +960,15 @@ static int kraken3_probe(struct hid_device *hdev, const struct hid_device_id *id if (IS_ERR(priv->hwmon_dev)) { ret = PTR_ERR(priv->hwmon_dev); hid_err(hdev, "hwmon registration failed with %d\n", ret); - goto fail_and_close; + goto fail_and_stop_io; } kraken3_debugfs_init(priv, device_name); return 0; +fail_and_stop_io: + hid_device_io_stop(hdev); fail_and_close: hid_hw_close(hdev); fail_and_stop: diff --git a/drivers/hwmon/nzxt-smart2.c b/drivers/hwmon/nzxt-smart2.c index 58ef9fa0184b..e2316c46629d 100644 --- a/drivers/hwmon/nzxt-smart2.c +++ b/drivers/hwmon/nzxt-smart2.c @@ -768,7 +768,7 @@ static int nzxt_smart2_hid_probe(struct hid_device *hdev, out_hw_close: hid_hw_close(hdev); - + hid_device_io_stop(hdev); out_hw_stop: hid_hw_stop(hdev); return ret; diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index e18e80e832fd..175208d712b0 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -1052,32 +1052,49 @@ static int occ_setup_sensor_attrs(struct occ *occ) } /* only need to do this once at startup, as OCC won't change sensors on us */ -static void occ_parse_poll_response(struct occ *occ) +static int occ_parse_poll_response(struct occ *occ) { unsigned int i, old_offset, offset = 0, size = 0; + u16 data_length; struct occ_sensor *sensor; - struct occ_sensors *sensors = &occ->sensors; + struct occ_sensors parsed = {}; + struct occ_sensors *sensors = &parsed; struct occ_response *resp = &occ->resp; struct occ_poll_response *poll = (struct occ_poll_response *)&resp->data[0]; struct occ_poll_response_header *header = &poll->header; struct occ_sensor_data_block *block = &poll->block; + data_length = get_unaligned_be16(&resp->data_length); + if (data_length < sizeof(*header) || data_length > OCC_RESP_DATA_BYTES) { + dev_err(occ->bus_dev, "invalid OCC poll response length %u\n", + data_length); + return -EMSGSIZE; + } + dev_info(occ->bus_dev, "OCC found, code level: %.16s\n", header->occ_code_level); for (i = 0; i < header->num_sensor_data_blocks; ++i) { block = (struct occ_sensor_data_block *)((u8 *)block + offset); + if (size + sizeof(*header) + sizeof(block->header) > + data_length) { + dev_err(occ->bus_dev, + "truncated OCC sensor block header\n"); + return -EMSGSIZE; + } + old_offset = offset; offset = (block->header.num_sensors * block->header.sensor_length) + sizeof(block->header); - size += offset; /* validate all the length/size fields */ - if ((size + sizeof(*header)) >= OCC_RESP_DATA_BYTES) { - dev_warn(occ->bus_dev, "exceeded response buffer\n"); - return; + if (size + sizeof(*header) + offset > data_length) { + dev_err(occ->bus_dev, + "exceeded OCC poll response length\n"); + return -EMSGSIZE; } + size += offset; dev_dbg(occ->bus_dev, " %04x..%04x: %.4s (%d sensors)\n", old_offset, offset - 1, block->header.eye_catcher, @@ -1107,6 +1124,9 @@ static void occ_parse_poll_response(struct occ *occ) dev_dbg(occ->bus_dev, "Max resp size: %u+%zd=%zd\n", size, sizeof(*header), size + sizeof(*header)); + occ->sensors = parsed; + + return 0; } int occ_active(struct occ *occ, bool active) @@ -1138,10 +1158,12 @@ int occ_active(struct occ *occ, bool active) goto unlock; } - occ->active = true; occ->next_update = jiffies + OCC_UPDATE_FREQUENCY; - occ_parse_poll_response(occ); + rc = occ_parse_poll_response(occ); + if (rc) + goto unlock; + occ->active = true; rc = occ_setup_sensor_attrs(occ); if (rc) { dev_err(occ->bus_dev, diff --git a/drivers/hwmon/pmbus/max34440.c b/drivers/hwmon/pmbus/max34440.c index 74876d2207fb..e56057e9273c 100644 --- a/drivers/hwmon/pmbus/max34440.c +++ b/drivers/hwmon/pmbus/max34440.c @@ -88,6 +88,33 @@ static int max34440_read_word_data(struct i2c_client *client, int page, ret = pmbus_read_word_data(client, page, phase, data->iout_oc_warn_limit); break; + case PMBUS_VIN_OV_FAULT_LIMIT: + case PMBUS_VIN_OV_WARN_LIMIT: + case PMBUS_VIN_UV_WARN_LIMIT: + case PMBUS_VIN_UV_FAULT_LIMIT: + case PMBUS_MFR_VIN_MIN: + case PMBUS_MFR_VIN_MAX: + case PMBUS_IIN_OC_WARN_LIMIT: + case PMBUS_IIN_OC_FAULT_LIMIT: + case PMBUS_MFR_IIN_MAX: + case PMBUS_MFR_VOUT_MIN: + case PMBUS_MFR_VOUT_MAX: + case PMBUS_IOUT_UC_FAULT_LIMIT: + case PMBUS_MFR_IOUT_MAX: + case PMBUS_UT_WARN_LIMIT: + case PMBUS_UT_FAULT_LIMIT: + case PMBUS_MFR_MAX_TEMP_1: + /* + * MAX34451/ADPM family do not support VIN/IIN limit registers, + * manufacturer-specific min/max registers, or undercurrent/ + * undertemperature fault limits. Accessing these triggers CML + * error and asserts ALERT. + */ + if (data->id == max34451 || data->id == adpm12160 || + data->id == adpm12200 || data->id == adpm12250) + return -ENXIO; + ret = -ENODATA; + break; case PMBUS_VIRT_READ_VOUT_MIN: ret = pmbus_read_word_data(client, page, phase, MAX34440_MFR_VOUT_MIN); @@ -244,6 +271,51 @@ static int max34440_read_byte_data(struct i2c_client *client, int page, int reg) return ret; } +static int max34451_read_byte_data(struct i2c_client *client, int page, int reg) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + const struct max34440_data *data = to_max34440_data(info); + + switch (reg) { + case PMBUS_STATUS_BYTE: + case PMBUS_STATUS_OTHER: + /* + * MAX34451/ADPM family do not support STATUS_BYTE or + * STATUS_OTHER registers. Accessing them triggers CML + * error and asserts ALERT. + */ + if (data->id == max34451 || data->id == adpm12160 || + data->id == adpm12200 || data->id == adpm12250) + return -ENXIO; + return -ENODATA; + default: + return -ENODATA; + } +} + +static int max34451_write_byte_data(struct i2c_client *client, int page, + int reg, u8 byte) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + const struct max34440_data *data = to_max34440_data(info); + + switch (reg) { + case PMBUS_STATUS_BYTE: + case PMBUS_STATUS_OTHER: + /* + * MAX34451/ADPM family do not support STATUS_BYTE or + * STATUS_OTHER registers. Writing to them triggers CML + * error and asserts ALERT. + */ + if (data->id == max34451 || data->id == adpm12160 || + data->id == adpm12200 || data->id == adpm12250) + return -ENXIO; + return -ENODATA; + default: + return -ENODATA; + } +} + static int max34451_set_supported_funcs(struct i2c_client *client, struct max34440_data *data) { @@ -363,7 +435,9 @@ static struct pmbus_driver_info max34440_info[] = { .func[9] = PMBUS_HAVE_VIN | PMBUS_HAVE_STATUS_INPUT, .func[10] = PMBUS_HAVE_IIN | PMBUS_HAVE_STATUS_INPUT, .func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, + .read_byte_data = max34451_read_byte_data, .read_word_data = max34440_read_word_data, + .write_byte_data = max34451_write_byte_data, .write_word_data = max34440_write_word_data, }, [adpm12200] = { @@ -399,7 +473,9 @@ static struct pmbus_driver_info max34440_info[] = { .func[10] = PMBUS_HAVE_IIN | PMBUS_HAVE_STATUS_INPUT, .func[14] = PMBUS_HAVE_IOUT, .func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, + .read_byte_data = max34451_read_byte_data, .read_word_data = max34440_read_word_data, + .write_byte_data = max34451_write_byte_data, .write_word_data = max34440_write_word_data, }, [adpm12250] = { @@ -433,7 +509,9 @@ static struct pmbus_driver_info max34440_info[] = { .func[10] = PMBUS_HAVE_IIN | PMBUS_HAVE_STATUS_INPUT, .func[14] = PMBUS_HAVE_IOUT, .func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, + .read_byte_data = max34451_read_byte_data, .read_word_data = max34440_read_word_data, + .write_byte_data = max34451_write_byte_data, .write_word_data = max34440_write_word_data, }, [max34440] = { @@ -581,7 +659,9 @@ static struct pmbus_driver_info max34440_info[] = { .func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, .func[19] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, .func[20] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, + .read_byte_data = max34451_read_byte_data, .read_word_data = max34440_read_word_data, + .write_byte_data = max34451_write_byte_data, .write_word_data = max34440_write_word_data, .page_change_delay = MAX34440_PAGE_CHANGE_DELAY, }, diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 28313d0fad37..d5e6e2eca3b3 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1061,11 +1061,28 @@ static inline enum imx_i2c_state i2c_imx_isr_read_continue(struct imx_i2c_struct static inline void i2c_imx_isr_read_block_data_len(struct imx_i2c_struct *i2c_imx) { u8 len = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2DR); + unsigned int temp; if (len == 0 || len > I2C_SMBUS_BLOCK_MAX) { + /* + * SMBus 3.1 6.5.7: support count byte of 0. + * I2C_SMBUS_BLOCK_MAX case should not hold the SDA either. + * So NACK it (TXAK) to not hold the bus. + */ + temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); + temp |= I2CR_TXAK; + imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); + + if (len == 0) { + i2c_imx->msg->buf[i2c_imx->msg_buf_idx++] = 0; + i2c_imx->msg->len = 2; + return; + } + i2c_imx->isr_result = -EPROTO; i2c_imx->state = IMX_I2C_STATE_FAILED; wake_up(&i2c_imx->queue); + return; } i2c_imx->msg->len += len; i2c_imx->msg->buf[i2c_imx->msg_buf_idx++] = len; @@ -1415,6 +1432,7 @@ static int i2c_imx_atomic_read(struct imx_i2c_struct *i2c_imx, int i, result; unsigned int temp; int block_data = msgs->flags & I2C_M_RECV_LEN; + int block_err = 0; result = i2c_imx_prepare_read(i2c_imx, msgs, false); if (result) @@ -1436,8 +1454,20 @@ static int i2c_imx_atomic_read(struct imx_i2c_struct *i2c_imx, */ if ((!i) && block_data) { len = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2DR); - if ((len == 0) || (len > I2C_SMBUS_BLOCK_MAX)) - return -EPROTO; + if ((len == 0) || (len > I2C_SMBUS_BLOCK_MAX)) { + /* + * SMBus 3.1 6.5.7: support count byte of 0. + * I2C_SMBUS_BLOCK_MAX case should not hold the SDA either. + */ + if (len > I2C_SMBUS_BLOCK_MAX) + block_err = -EPROTO; + temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); + temp |= I2CR_TXAK; + imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); + msgs->buf[0] = 0; + msgs->len = 2; + continue; + } dev_dbg(&i2c_imx->adapter.dev, "<%s> read length: 0x%X\n", __func__, len); @@ -1485,7 +1515,7 @@ static int i2c_imx_atomic_read(struct imx_i2c_struct *i2c_imx, "<%s> read byte: B%d=0x%X\n", __func__, i, msgs->buf[i]); } - return 0; + return block_err; } static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs, diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c index 9152cf436bea..51a0c3d80fc9 100644 --- a/drivers/i2c/busses/i2c-k1.c +++ b/drivers/i2c/busses/i2c-k1.c @@ -596,7 +596,7 @@ static irqreturn_t spacemit_i2c_irq_handler(int irq, void *devid) status = readl(i2c->base + SPACEMIT_ISR); if (!status) - return IRQ_HANDLED; + return IRQ_NONE; i2c->status = status; diff --git a/drivers/i2c/busses/i2c-mlxbf.c b/drivers/i2c/busses/i2c-mlxbf.c index 6c1cfe9ec8ac..e33512b25353 100644 --- a/drivers/i2c/busses/i2c-mlxbf.c +++ b/drivers/i2c/busses/i2c-mlxbf.c @@ -1051,8 +1051,10 @@ static int mlxbf_i2c_init_resource(struct platform_device *pdev, tmp_res->io = devm_platform_get_and_ioremap_resource(pdev, type, &tmp_res->params); if (IS_ERR(tmp_res->io)) { + int ret = PTR_ERR(tmp_res->io); + devm_kfree(dev, tmp_res); - return PTR_ERR(tmp_res->io); + return ret; } tmp_res->type = type; diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 126040ca05f1..307925fb78e3 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -1258,7 +1258,7 @@ static int mtk_i2c_transfer(struct i2c_adapter *adap, i2c->auto_restart = i2c->dev_comp->auto_restart; /* checking if we can skip restart and optimize using WRRD mode */ - if (i2c->auto_restart && num == 2) { + if (num == 2) { if (!(msgs[0].flags & I2C_M_RD) && (msgs[1].flags & I2C_M_RD) && msgs[0].addr == msgs[1].addr) { i2c->auto_restart = 0; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 9480d1a51c11..e88d3efb967b 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -5270,7 +5270,7 @@ static int cma_netevent_callback(struct notifier_block *self, list_for_each_entry(current_id, &ips_node->id_list, id_list_entry) { if (!memcmp(current_id->id.route.addr.dev_addr.dst_dev_addr, - neigh->ha, ETH_ALEN)) + neigh->ha, neigh->dev->addr_len)) continue; cma_id_get(current_id); if (!queue_work(cma_wq, ¤t_id->id.net_work)) diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 8d19613179e3..e0b3b36b8b14 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -2031,6 +2031,24 @@ void ib_mark_mad_done(struct ib_mad_send_wr_private *mad_send_wr) change_mad_state(mad_send_wr, IB_MAD_STATE_EARLY_RESP); } +static bool is_kernel_rmpp_data_response(struct ib_mad_agent_private *agent, + struct ib_mad_recv_wc *mad_recv_wc) +{ + const struct ib_mad_hdr *mad_hdr = &mad_recv_wc->recv_buf.mad->mad_hdr; + struct ib_rmpp_mad *rmpp_mad; + + if (!ib_mad_kernel_rmpp_agent(&agent->agent) || + !ib_response_mad(mad_hdr) || + !ib_is_mad_class_rmpp(mad_hdr->mgmt_class)) + return false; + + rmpp_mad = (struct ib_rmpp_mad *)mad_recv_wc->recv_buf.mad; + + return (ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & + IB_MGMT_RMPP_FLAG_ACTIVE) && + rmpp_mad->rmpp_hdr.rmpp_type == IB_MGMT_RMPP_TYPE_DATA; +} + static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv, struct ib_mad_recv_wc *mad_recv_wc) { @@ -2050,6 +2068,18 @@ static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv, } list_add(&mad_recv_wc->recv_buf.list, &mad_recv_wc->rmpp_list); + if (is_kernel_rmpp_data_response(mad_agent_priv, mad_recv_wc)) { + spin_lock_irqsave(&mad_agent_priv->lock, flags); + mad_send_wr = ib_find_send_mad(mad_agent_priv, mad_recv_wc); + spin_unlock_irqrestore(&mad_agent_priv->lock, flags); + + if (!mad_send_wr) { + ib_free_recv_mad(mad_recv_wc); + deref_mad_agent(mad_agent_priv); + return; + } + } + if (ib_mad_kernel_rmpp_agent(&mad_agent_priv->agent)) { mad_recv_wc = ib_process_rmpp_recv_wc(mad_agent_priv, mad_recv_wc); diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 3b613b57e269..86811d31092c 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -2196,13 +2196,13 @@ struct ib_cq *__ib_create_cq(struct ib_device *device, struct ib_cq *cq; int ret; + if (WARN_ON_ONCE(!cq_attr->cqe)) + return ERR_PTR(-EINVAL); + cq = rdma_zalloc_drv_obj(device, ib_cq); if (!cq) return ERR_PTR(-ENOMEM); - if (WARN_ON_ONCE(!cq_attr->cqe)) - return ERR_PTR(-EINVAL); - cq->device = device; cq->comp_handler = comp_handler; cq->event_handler = event_handler; diff --git a/drivers/infiniband/hw/bng_re/bng_dev.c b/drivers/infiniband/hw/bng_re/bng_dev.c index 71a7ca2196ad..311c8bc93160 100644 --- a/drivers/infiniband/hw/bng_re/bng_dev.c +++ b/drivers/infiniband/hw/bng_re/bng_dev.c @@ -113,7 +113,7 @@ static void bng_re_fill_fw_msg(struct bnge_fw_msg *fw_msg, void *msg, } static int bng_re_net_ring_free(struct bng_re_dev *rdev, - u16 fw_ring_id, int type) + u32 fw_ring_id, int type) { struct bnge_auxr_dev *aux_dev = rdev->aux_dev; struct hwrm_ring_free_input req = {}; @@ -123,7 +123,7 @@ static int bng_re_net_ring_free(struct bng_re_dev *rdev, bng_re_init_hwrm_hdr((void *)&req, HWRM_RING_FREE); req.ring_type = type; - req.ring_id = cpu_to_le16(fw_ring_id); + req.ring_id = cpu_to_le32(fw_ring_id); bng_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), BNGE_DFLT_HWRM_CMD_TIMEOUT); rc = bnge_send_msg(aux_dev, &fw_msg); @@ -161,7 +161,7 @@ static int bng_re_net_ring_alloc(struct bng_re_dev *rdev, sizeof(resp), BNGE_DFLT_HWRM_CMD_TIMEOUT); rc = bnge_send_msg(aux_dev, &fw_msg); if (!rc) - *fw_ring_id = le16_to_cpu(resp.ring_id); + *fw_ring_id = (u16)le32_to_cpu(resp.ring_id); return rc; } diff --git a/drivers/infiniband/hw/erdma/erdma_qp.c b/drivers/infiniband/hw/erdma/erdma_qp.c index 25f6c49aec77..e002343832f7 100644 --- a/drivers/infiniband/hw/erdma/erdma_qp.c +++ b/drivers/infiniband/hw/erdma/erdma_qp.c @@ -734,7 +734,7 @@ int erdma_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr *wr = recv_wr; struct erdma_qp *qp = to_eqp(ibqp); unsigned long flags; - int ret; + int ret = 0; spin_lock_irqsave(&qp->lock, flags); diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index 7041a8e9134b..92edec4fa61b 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -836,7 +836,7 @@ static void hns_roce_cleanup_mhop_hem_table(struct hns_roce_dev *hr_dev, mhop.bt_chunk_size; for (i = 0; i < table->num_hem; ++i) { - obj = i * buf_chunk_size / table->obj_size; + obj = (u64)i * buf_chunk_size / table->obj_size; if (table->hem[i]) hns_roce_table_mhop_put(hr_dev, table, obj, 0); } diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index cb54c7c8fcd8..b7388b41ed95 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -633,17 +633,16 @@ static int irdma_setup_umode_qp(struct ib_udata *udata, iwqp->ctx_info.qp_compl_ctx = req.user_compl_ctx; iwqp->user_mode = 1; - if (req.user_wqe_bufs) { - spin_lock_irqsave(&ucontext->qp_reg_mem_list_lock, flags); - iwqp->iwpbl = irdma_get_pbl((unsigned long)req.user_wqe_bufs, - &ucontext->qp_reg_mem_list); - spin_unlock_irqrestore(&ucontext->qp_reg_mem_list_lock, flags); - if (!iwqp->iwpbl) { - ret = -ENODATA; - ibdev_dbg(&iwdev->ibdev, "VERBS: no pbl info\n"); - return ret; - } + spin_lock_irqsave(&ucontext->qp_reg_mem_list_lock, flags); + iwqp->iwpbl = irdma_get_pbl((unsigned long)req.user_wqe_bufs, + &ucontext->qp_reg_mem_list); + spin_unlock_irqrestore(&ucontext->qp_reg_mem_list_lock, flags); + + if (!iwqp->iwpbl) { + ret = -ENODATA; + ibdev_dbg(&iwdev->ibdev, "VERBS: no pbl info\n"); + return ret; } if (!ucontext->use_raw_attrs) { @@ -2802,7 +2801,7 @@ static bool irdma_check_mem_contiguous(u64 *arr, u32 npages, u32 pg_size) u32 pg_idx; for (pg_idx = 0; pg_idx < npages; pg_idx++) { - if ((*arr + (pg_size * pg_idx)) != arr[pg_idx]) + if ((*arr + ((u64)pg_size * pg_idx)) != arr[pg_idx]) return false; } @@ -2835,7 +2834,7 @@ static bool irdma_check_mr_contiguous(struct irdma_pble_alloc *palloc, for (i = 0; i < lvl2->leaf_cnt; i++, leaf++) { arr = leaf->addr; - if ((*start_addr + (i * pg_size * PBLE_PER_PAGE)) != *arr) + if ((*start_addr + ((u64)i * pg_size * PBLE_PER_PAGE)) != *arr) return false; ret = irdma_check_mem_contiguous(arr, leaf->cnt, pg_size); if (!ret) @@ -3791,6 +3790,9 @@ static struct ib_mr *irdma_rereg_user_mr(struct ib_mr *ib_mr, int flags, if (flags & ~(IB_MR_REREG_TRANS | IB_MR_REREG_PD | IB_MR_REREG_ACCESS)) return ERR_PTR(-EOPNOTSUPP); + if (iwmr->type != IRDMA_MEMREG_TYPE_MEM) + return ERR_PTR(-EINVAL); + ret = ib_umem_check_rereg(iwmr->region, flags, new_access); if (ret) return ERR_PTR(ret); diff --git a/drivers/infiniband/hw/mana/wr.c b/drivers/infiniband/hw/mana/wr.c index 1813567d3b16..36a1d506f08f 100644 --- a/drivers/infiniband/hw/mana/wr.c +++ b/drivers/infiniband/hw/mana/wr.c @@ -144,7 +144,7 @@ static int mana_ib_post_send_ud(struct mana_ib_qp *qp, const struct ib_ud_wr *wr int mana_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr) { - int err; + int err = 0; struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp); for (; wr; wr = wr->next) { diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c index 9947feb7fb8a..fca9e1d9d5e9 100644 --- a/drivers/infiniband/hw/mlx5/wr.c +++ b/drivers/infiniband/hw/mlx5/wr.c @@ -840,13 +840,15 @@ out: return err; } -static int handle_reg_mr_integrity(struct mlx5_ib_dev *dev, - struct mlx5_ib_qp *qp, - const struct ib_send_wr *wr, - struct mlx5_wqe_ctrl_seg **ctrl, void **seg, - int *size, void **cur_edge, - unsigned int *idx, int nreq, u8 fence, - u8 next_fence) +static noinline_for_stack int handle_reg_mr_integrity(struct mlx5_ib_dev *dev, + struct mlx5_ib_qp *qp, + const struct ib_send_wr *wr, + struct mlx5_wqe_ctrl_seg **ctrl, + void **seg, + int *size, void **cur_edge, + unsigned int *idx, int nreq, + u8 fence, + u8 next_fence) { struct mlx5_ib_mr *mr; struct mlx5_ib_mr *pi_mr; diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index b74ac85c1b8b..2349c08c32ed 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -318,6 +318,7 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, struct siw_ucontext *uctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); + struct siw_uresp_create_qp uresp = {}; unsigned long flags; int num_sqe, num_rqe, rv = 0; size_t length; @@ -371,11 +372,6 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, spin_lock_init(&qp->rq_lock); spin_lock_init(&qp->orq_lock); - rv = siw_qp_add(sdev, qp); - if (rv) - goto err_atomic; - - /* All queue indices are derived from modulo operations * on a free running 'get' (consumer) and 'put' (producer) * unsigned counter. Having queue sizes at power of two @@ -393,14 +389,14 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, if (qp->sendq == NULL) { rv = -ENOMEM; - goto err_out_xa; + goto err_out; } if (attrs->sq_sig_type != IB_SIGNAL_REQ_WR) { if (attrs->sq_sig_type == IB_SIGNAL_ALL_WR) qp->attrs.flags |= SIW_SIGNAL_ALL_WR; else { rv = -EINVAL; - goto err_out_xa; + goto err_out; } } qp->pd = pd; @@ -426,7 +422,7 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, if (qp->recvq == NULL) { rv = -ENOMEM; - goto err_out_xa; + goto err_out; } qp->attrs.rq_size = num_rqe; } @@ -441,11 +437,8 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, qp->attrs.state = SIW_QP_STATE_IDLE; if (udata) { - struct siw_uresp_create_qp uresp = {}; - uresp.num_sqe = num_sqe; uresp.num_rqe = num_rqe; - uresp.qp_id = qp_id(qp); if (qp->sendq) { length = num_sqe * sizeof(struct siw_sqe); @@ -454,7 +447,7 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, length, &uresp.sq_key); if (!qp->sq_entry) { rv = -ENOMEM; - goto err_out_xa; + goto err_out; } } @@ -466,9 +459,23 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, if (!qp->rq_entry) { uresp.sq_key = SIW_INVAL_UOBJ_KEY; rv = -ENOMEM; - goto err_out_xa; + goto err_out; } } + } + qp->tx_cpu = siw_get_tx_cpu(sdev); + if (qp->tx_cpu < 0) { + rv = -EINVAL; + goto err_out; + } + init_completion(&qp->qp_free); + + rv = siw_qp_add(sdev, qp); + if (rv) + goto err_out_tx; + + if (udata) { + uresp.qp_id = qp_id(qp); if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; @@ -478,22 +485,19 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, if (rv) goto err_out_xa; } - qp->tx_cpu = siw_get_tx_cpu(sdev); - if (qp->tx_cpu < 0) { - rv = -EINVAL; - goto err_out_xa; - } + INIT_LIST_HEAD(&qp->devq); spin_lock_irqsave(&sdev->lock, flags); list_add_tail(&qp->devq, &sdev->qp_list); spin_unlock_irqrestore(&sdev->lock, flags); - init_completion(&qp->qp_free); - return 0; err_out_xa: xa_erase(&sdev->qp_xa, qp_id(qp)); +err_out_tx: + siw_put_tx_cpu(qp->tx_cpu); +err_out: if (uctx) { rdma_user_mmap_entry_remove(qp->sq_entry); rdma_user_mmap_entry_remove(qp->rq_entry); diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index e93bcb5eef70..e7d7b4cb9337 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3864,6 +3864,12 @@ not_found: return 1; found: + if (early_acpihid_map_size == EARLY_MAP_SIZE) { + pr_err("Early ACPI HID map overflow - ignoring ivrs_acpihid%s\n", + str); + return 1; + } + p = acpiid; hid = strsep(&p, ":"); uid = p; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 563f9c2672d5..29dc18d3d22e 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1450,11 +1450,23 @@ static int iommu_completion_wait(struct amd_iommu *iommu) int ret; u64 data; - if (!iommu->need_sync) - return 0; - raw_spin_lock_irqsave(&iommu->lock, flags); + if (!iommu->need_sync) { + /* + * No command has been queued since the last completion-wait. + * A concurrent CPU may have already queued that CWAIT and + * cleared need_sync; need_sync == false only means a covering + * CWAIT is queued, not that all prior commands have completed. + * Wait for the last allocated sequence number so that any + * command queued before this call (possibly on another CPU) + * is guaranteed to have completed before returning. + */ + data = iommu->cmd_sem_val; + raw_spin_unlock_irqrestore(&iommu->lock, flags); + return wait_on_sem(iommu, data); + } + data = get_cmdsem_val(iommu); build_completion_wait(&cmd, iommu, data); @@ -1464,9 +1476,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu) if (ret) return ret; - ret = wait_on_sem(iommu, data); - - return ret; + return wait_on_sem(iommu, data); } static void domain_flush_complete(struct protection_domain *domain) diff --git a/drivers/iommu/amd/nested.c b/drivers/iommu/amd/nested.c index 5b902598e68a..63b53b29e029 100644 --- a/drivers/iommu/amd/nested.c +++ b/drivers/iommu/amd/nested.c @@ -59,7 +59,9 @@ static int validate_gdte_nested(struct iommu_hwpt_amd_guest *gdte) return 0; } -static void *gdom_info_load_or_alloc_locked(struct xarray *xa, unsigned long index) +static void *gdom_info_load_or_alloc_locked(struct xarray *xa, + unsigned long index, + unsigned long *flags) { struct guest_domain_mapping_info *elm, *res; @@ -67,13 +69,13 @@ static void *gdom_info_load_or_alloc_locked(struct xarray *xa, unsigned long ind if (elm) return elm; - xa_unlock(xa); + xa_unlock_irqrestore(xa, *flags); elm = kzalloc_obj(struct guest_domain_mapping_info); - xa_lock(xa); + xa_lock_irqsave(xa, *flags); if (!elm) return ERR_PTR(-ENOMEM); - res = __xa_cmpxchg(xa, index, NULL, elm, GFP_KERNEL); + res = __xa_cmpxchg(xa, index, NULL, elm, GFP_ATOMIC); if (xa_is_err(res)) res = ERR_PTR(xa_err(res)); @@ -95,6 +97,7 @@ amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, const struct iommu_user_data *user_data) { int ret; + unsigned long irqflags; struct nested_domain *ndom; struct guest_domain_mapping_info *gdom_info; struct amd_iommu_viommu *aviommu = container_of(viommu, struct amd_iommu_viommu, core); @@ -136,11 +139,12 @@ amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, * keep track of the gDomID mapping. When the S2 is changed, the INVALIDATE_IOMMU_PAGES * command must be issued for each hDomID in the xarray. */ - xa_lock(&aviommu->gdomid_array); + xa_lock_irqsave(&aviommu->gdomid_array, irqflags); - gdom_info = gdom_info_load_or_alloc_locked(&aviommu->gdomid_array, ndom->gdom_id); + gdom_info = gdom_info_load_or_alloc_locked(&aviommu->gdomid_array, + ndom->gdom_id, &irqflags); if (IS_ERR(gdom_info)) { - xa_unlock(&aviommu->gdomid_array); + xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags); ret = PTR_ERR(gdom_info); goto out_err; } @@ -148,7 +152,7 @@ amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, /* Check if gDomID exist */ if (refcount_inc_not_zero(&gdom_info->users)) { ndom->gdom_info = gdom_info; - xa_unlock(&aviommu->gdomid_array); + xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags); pr_debug("%s: Found gdom_id=%#x, hdom_id=%#x\n", __func__, ndom->gdom_id, gdom_info->hdom_id); @@ -161,7 +165,7 @@ amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, if (gdom_info->hdom_id <= 0) { __xa_cmpxchg(&aviommu->gdomid_array, ndom->gdom_id, gdom_info, NULL, GFP_ATOMIC); - xa_unlock(&aviommu->gdomid_array); + xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags); ret = -ENOSPC; goto out_err_gdom_info; } @@ -169,7 +173,7 @@ amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, ndom->gdom_info = gdom_info; refcount_set(&gdom_info->users, 1); - xa_unlock(&aviommu->gdomid_array); + xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags); pr_debug("%s: Allocate gdom_id=%#x, hdom_id=%#x\n", __func__, ndom->gdom_id, gdom_info->hdom_id); @@ -257,14 +261,15 @@ static int nested_attach_device(struct iommu_domain *dom, struct device *dev, static void nested_domain_free(struct iommu_domain *dom) { + unsigned long irqflags; struct guest_domain_mapping_info *curr; - struct nested_domain *ndom = to_ndomain(dom); + struct nested_domain *ndom __free(kfree) = to_ndomain(dom); struct amd_iommu_viommu *aviommu = ndom->viommu; - xa_lock(&aviommu->gdomid_array); + xa_lock_irqsave(&aviommu->gdomid_array, irqflags); if (!refcount_dec_and_test(&ndom->gdom_info->users)) { - xa_unlock(&aviommu->gdomid_array); + xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags); return; } @@ -275,7 +280,7 @@ static void nested_domain_free(struct iommu_domain *dom) curr = __xa_cmpxchg(&aviommu->gdomid_array, ndom->gdom_id, ndom->gdom_info, NULL, GFP_ATOMIC); - xa_unlock(&aviommu->gdomid_array); + xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags); if (WARN_ON(!curr || xa_err(curr))) return; @@ -285,7 +290,6 @@ static void nested_domain_free(struct iommu_domain *dom) amd_iommu_pdom_id_free(ndom->gdom_info->hdom_id); kfree(curr); - kfree(ndom); } static const struct iommu_domain_ops nested_domain_ops = { diff --git a/drivers/iommu/intel/perf.c b/drivers/iommu/intel/perf.c index 02168f2f20a4..bec98dcbb9ec 100644 --- a/drivers/iommu/intel/perf.c +++ b/drivers/iommu/intel/perf.c @@ -63,7 +63,7 @@ void dmar_latency_disable(struct intel_iommu *iommu, enum latency_type type) return; spin_lock_irqsave(&latency_lock, flags); - memset(&lstat[type], 0, sizeof(*lstat) * DMAR_LATENCY_NUM); + memset(&lstat[type], 0, sizeof(*lstat)); spin_unlock_irqrestore(&latency_lock, flags); } diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index fea10acd4f02..726f7b6d0bff 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -27,7 +27,7 @@ void intel_svm_check(struct intel_iommu *iommu) { - if (!pasid_supported(iommu)) + if (!pasid_supported(iommu) || !ecap_smpwc(iommu->ecap)) return; if (cpu_feature_enabled(X86_FEATURE_GBPAGES) && diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c index a01fe313558e..ce33907bfc24 100644 --- a/drivers/memstick/core/ms_block.c +++ b/drivers/memstick/core/ms_block.c @@ -1338,6 +1338,10 @@ static int msb_ftl_initialize(struct msb_data *msb) return 0; msb->zone_count = msb->block_count / MS_BLOCKS_IN_ZONE; + if (msb->block_count > MS_MAX_ZONES * MS_BLOCKS_IN_ZONE) { + pr_err("Too many blocks: %d\n", msb->block_count); + return -EINVAL; + } msb->logical_block_count = msb->zone_count * 496 - 2; msb->used_blocks_bitmap = bitmap_zalloc(msb->block_count, GFP_KERNEL); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 0274e8d07660..54a923ba4f1e 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2715,7 +2715,6 @@ static void mmc_blk_rpmb_device_release(struct device *dev) { struct mmc_rpmb_data *rpmb = dev_get_drvdata(dev); - rpmb_dev_unregister(rpmb->rdev); mmc_blk_put(rpmb->md); ida_free(&mmc_rpmb_ida, rpmb->id); kfree(rpmb); @@ -2930,8 +2929,8 @@ out_put_device: } static void mmc_blk_remove_rpmb_part(struct mmc_rpmb_data *rpmb) - { + rpmb_dev_unregister(rpmb->rdev); cdev_device_del(&rpmb->chrdev, &rpmb->dev); put_device(&rpmb->dev); } diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index ab38e4c45a8d..4dc16649e61d 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -318,9 +318,9 @@ static void mmc_test_free_mem(struct mmc_test_mem *mem) { if (!mem) return; - while (mem->cnt--) - __free_pages(mem->arr[mem->cnt].page, - mem->arr[mem->cnt].order); + for (unsigned int i = 0; i < mem->cnt; i++) + __free_pages(mem->arr[i].page, + mem->arr[i].order); kfree(mem); } @@ -341,6 +341,7 @@ static struct mmc_test_mem *mmc_test_alloc_mem(unsigned long min_sz, unsigned long page_cnt = 0; unsigned long limit = nr_free_buffer_pages() >> 4; struct mmc_test_mem *mem; + unsigned int idx = 0; if (max_page_cnt > limit) max_page_cnt = limit; @@ -375,23 +376,26 @@ static struct mmc_test_mem *mmc_test_alloc_mem(unsigned long min_sz, goto out_free; break; } - mem->arr[mem->cnt].page = page; - mem->arr[mem->cnt].order = order; - mem->cnt += 1; + mem->arr[idx].page = page; + mem->arr[idx].order = order; + idx += 1; if (max_page_cnt <= (1UL << order)) break; max_page_cnt -= 1UL << order; page_cnt += 1UL << order; - if (mem->cnt >= max_segs) { + if (idx >= mem->cnt) { if (page_cnt < min_page_cnt) goto out_free; break; } } + mem->cnt = idx; + return mem; out_free: + mem->cnt = idx; mmc_test_free_mem(mem); return NULL; } diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 18ecddd6df6f..18f4905c15b9 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -1326,19 +1326,21 @@ static int esdhc_change_pinstate(struct sdhci_host *host, dev_dbg(mmc_dev(host->mmc), "change pinctrl state for uhs %d\n", uhs); - if (IS_ERR(imx_data->pinctrl) || - IS_ERR(imx_data->pins_100mhz) || - IS_ERR(imx_data->pins_200mhz)) + if (IS_ERR(imx_data->pinctrl)) return -EINVAL; switch (uhs) { case MMC_TIMING_UHS_SDR50: case MMC_TIMING_UHS_DDR50: + if (IS_ERR(imx_data->pins_100mhz)) + return -EINVAL; pinctrl = imx_data->pins_100mhz; break; case MMC_TIMING_UHS_SDR104: case MMC_TIMING_MMC_HS200: case MMC_TIMING_MMC_HS400: + if (IS_ERR(imx_data->pins_200mhz)) + return -EINVAL; pinctrl = imx_data->pins_200mhz; break; default: @@ -1349,6 +1351,23 @@ static int esdhc_change_pinstate(struct sdhci_host *host, return pinctrl_select_state(imx_data->pinctrl, pinctrl); } +static void esdhc_set_dll_override(struct sdhci_host *host) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host); + struct esdhc_platform_data *boarddata = &imx_data->boarddata; + u32 v; + + if (!boarddata->delay_line) + return; + + v = boarddata->delay_line << ESDHC_DLL_OVERRIDE_VAL_SHIFT | + (1 << ESDHC_DLL_OVERRIDE_EN_SHIFT); + if (is_imx53_esdhc(imx_data)) + v <<= 1; + writel(v, host->ioaddr + ESDHC_DLL_CTRL); +} + /* * For HS400 eMMC, there is a data_strobe line. This signal is generated * by the device and used for data output and CRC status response output @@ -1404,7 +1423,6 @@ static void esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned timing) u32 m; struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host); - struct esdhc_platform_data *boarddata = &imx_data->boarddata; /* disable ddr mode and disable HS400 mode */ m = readl(host->ioaddr + ESDHC_MIX_CTRL); @@ -1425,15 +1443,7 @@ static void esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned timing) m |= ESDHC_MIX_CTRL_DDREN; writel(m, host->ioaddr + ESDHC_MIX_CTRL); imx_data->is_ddr = 1; - if (boarddata->delay_line) { - u32 v; - v = boarddata->delay_line << - ESDHC_DLL_OVERRIDE_VAL_SHIFT | - (1 << ESDHC_DLL_OVERRIDE_EN_SHIFT); - if (is_imx53_esdhc(imx_data)) - v <<= 1; - writel(v, host->ioaddr + ESDHC_DLL_CTRL); - } + esdhc_set_dll_override(host); break; case MMC_TIMING_MMC_HS400: m |= ESDHC_MIX_CTRL_DDREN | ESDHC_MIX_CTRL_HS400_EN; @@ -2051,7 +2061,9 @@ static int sdhci_esdhc_suspend(struct device *dev) * 2, make sure the pm_runtime_force_resume() in sdhci_esdhc_resume() really * invoke its ->runtime_resume callback (needs_force_resume = 1). */ - pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); + if (ret) + return ret; if ((imx_data->socdata->flags & ESDHC_FLAG_STATE_LOST_IN_LPMODE) && (host->tuning_mode != SDHCI_TUNING_MODE_1)) { @@ -2064,15 +2076,14 @@ static int sdhci_esdhc_suspend(struct device *dev) * to save the tuning delay value just in case the usdhc * lost power during system PM. */ - if (mmc_card_keep_power(host->mmc) && mmc_card_wake_sdio_irq(host->mmc) && - esdhc_is_usdhc(imx_data)) + if (mmc_card_keep_power(host->mmc) && esdhc_is_usdhc(imx_data)) sdhc_esdhc_tuning_save(host); + /* The irqs of imx are not shared. It is safe to disable */ + disable_irq(host->irq); + if (device_may_wakeup(dev)) { - /* The irqs of imx are not shared. It is safe to disable */ - disable_irq(host->irq); - ret = sdhci_enable_irq_wakeups(host); - if (!ret) + if (!sdhci_enable_irq_wakeups(host)) dev_warn(dev, "Failed to enable irq wakeup\n"); } else { /* @@ -2083,12 +2094,12 @@ static int sdhci_esdhc_suspend(struct device *dev) * other function like GPIO function to save power in PM, * which finally block the SDIO wakeup function. */ - ret = pinctrl_pm_select_sleep_state(dev); - if (ret) - return ret; + if (pinctrl_pm_select_sleep_state(dev)) + dev_warn(dev, "Failed to select sleep pinctrl state\n"); } - ret = mmc_gpio_set_cd_wake(host->mmc, true); + if (mmc_gpio_set_cd_wake(host->mmc, true)) + dev_warn(dev, "Failed to enable cd wake\n"); /* * Make sure invoke runtime_suspend to gate off clock. @@ -2096,7 +2107,7 @@ static int sdhci_esdhc_suspend(struct device *dev) */ pm_runtime_force_suspend(dev); - return ret; + return 0; } static int sdhci_esdhc_resume(struct device *dev) @@ -2106,31 +2117,45 @@ static int sdhci_esdhc_resume(struct device *dev) struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host); int ret; - pm_runtime_force_resume(dev); + if (!device_may_wakeup(dev)) { + ret = esdhc_change_pinstate(host, host->timing); + if (ret) + dev_warn(dev, "Failed to restore pinctrl state\n"); + } - ret = mmc_gpio_set_cd_wake(host->mmc, false); + ret = pm_runtime_force_resume(dev); if (ret) return ret; + mmc_gpio_set_cd_wake(host->mmc, false); + /* re-initialize hw state in case it's lost in low power mode */ sdhci_esdhc_imx_hwinit(host); - if (host->irq_wake_enabled) { + if (host->irq_wake_enabled) sdhci_disable_irq_wakeups(host); - enable_irq(host->irq); - } + + enable_irq(host->irq); /* * restore the saved tuning delay value for the device which keep * power during system PM. */ - if (mmc_card_keep_power(host->mmc) && mmc_card_wake_sdio_irq(host->mmc) && - esdhc_is_usdhc(imx_data)) + if (mmc_card_keep_power(host->mmc) && esdhc_is_usdhc(imx_data)) { sdhc_esdhc_tuning_restore(host); + /* + * Restore DLL override for DDR modes. hwinit unconditionally + * clears ESDHC_DLL_CTRL, but the card is still in DDR mode. + */ + if (host->timing == MMC_TIMING_UHS_DDR50 || + host->timing == MMC_TIMING_MMC_DDR52) + esdhc_set_dll_override(host); + } + pm_runtime_put_autosuspend(dev); - return ret; + return 0; } static int sdhci_esdhc_runtime_suspend(struct device *dev) diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c index eef53455b8ee..c688f3eaf468 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -2433,13 +2433,16 @@ static int dwcmshc_probe(struct platform_device *pdev) return err; priv->bus_clk = devm_clk_get(dev, "bus"); - if (!IS_ERR(priv->bus_clk)) - clk_prepare_enable(priv->bus_clk); + if (!IS_ERR(priv->bus_clk)) { + err = clk_prepare_enable(priv->bus_clk); + if (err) + goto err_clk; + } } err = mmc_of_parse(host->mmc); if (err) - goto err_clk; + goto err_bus_clk; sdhci_get_of_property(pdev); @@ -2453,7 +2456,7 @@ static int dwcmshc_probe(struct platform_device *pdev) if (pltfm_data->init) { err = pltfm_data->init(&pdev->dev, host, priv); if (err) - goto err_clk; + goto err_bus_clk; } #ifdef CONFIG_ACPI @@ -2499,9 +2502,10 @@ err_setup_host: err_rpm: pm_runtime_disable(dev); pm_runtime_put_noidle(dev); +err_bus_clk: + clk_disable_unprepare(priv->bus_clk); err_clk: clk_disable_unprepare(pltfm_host->clk); - clk_disable_unprepare(priv->bus_clk); clk_bulk_disable_unprepare(priv->num_other_clks, priv->other_clks); return err; } diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index 6c3cb2f1c9d3..2dae474dcd06 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -1586,7 +1586,7 @@ static int __command_write_data(struct vub300_mmc_host *vub300, return linear_length; } -static void __vub300_command_response(struct vub300_mmc_host *vub300, +static bool __vub300_command_response(struct vub300_mmc_host *vub300, struct mmc_command *cmd, struct mmc_data *data, int data_length) { @@ -1598,17 +1598,11 @@ static void __vub300_command_response(struct vub300_mmc_host *vub300, msecs_to_jiffies(msec_timeout)); if (respretval == 0) { /* TIMED OUT */ /* we don't know which of "out" and "res" if any failed */ - int result; vub300->usb_timed_out = 1; usb_kill_urb(vub300->command_out_urb); usb_kill_urb(vub300->command_res_urb); cmd->error = -ETIMEDOUT; - result = usb_lock_device_for_reset(vub300->udev, - vub300->interface); - if (result == 0) { - result = usb_reset_device(vub300->udev); - usb_unlock_device(vub300->udev); - } + return true; } else if (respretval < 0) { /* we don't know which of "out" and "res" if any failed */ usb_kill_urb(vub300->command_out_urb); @@ -1704,6 +1698,8 @@ static void __vub300_command_response(struct vub300_mmc_host *vub300, } else { cmd->error = -EINVAL; } + + return false; } static void construct_request_response(struct vub300_mmc_host *vub300, @@ -1749,6 +1745,7 @@ static void vub300_cmndwork_thread(struct work_struct *work) struct mmc_request *req = vub300->req; struct mmc_command *cmd = vub300->cmd; struct mmc_data *data = vub300->data; + bool reset_device; int data_length; mutex_lock(&vub300->cmd_mutex); init_completion(&vub300->command_complete); @@ -1771,7 +1768,8 @@ static void vub300_cmndwork_thread(struct work_struct *work) data_length = __command_read_data(vub300, cmd, data); else data_length = __command_write_data(vub300, cmd, data); - __vub300_command_response(vub300, cmd, data, data_length); + reset_device = __vub300_command_response(vub300, cmd, + data, data_length); vub300->req = NULL; vub300->cmd = NULL; vub300->data = NULL; @@ -1779,6 +1777,16 @@ static void vub300_cmndwork_thread(struct work_struct *work) if (cmd->error == -ENOMEDIUM) check_vub300_port_status(vub300); mutex_unlock(&vub300->cmd_mutex); + if (reset_device) { + int result; + + result = usb_lock_device_for_reset(vub300->udev, + vub300->interface); + if (result == 0) { + result = usb_reset_device(vub300->udev); + usb_unlock_device(vub300->udev); + } + } mmc_request_done(vub300->mmc, req); kref_put(&vub300->kref, vub300_delete); return; @@ -2336,12 +2344,16 @@ static int vub300_probe(struct usb_interface *interface, interface_to_InterfaceNumber(interface)); retval = mmc_add_host(mmc); if (retval) - goto err_delete_timer; + goto err_stop_io; return 0; -err_delete_timer: - timer_delete_sync(&vub300->inactivity_timer); +err_stop_io: + vub300->interface = NULL; + kref_put(&vub300->kref, vub300_delete); + + return retval; + err_free_host: mmc_free_host(mmc); /* diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c index cef5f9677d39..66e058df4c32 100644 --- a/drivers/mtd/devices/mchp23k256.c +++ b/drivers/mtd/devices/mchp23k256.c @@ -188,7 +188,7 @@ static int mchp23k256_probe(struct spi_device *spi) data = dev_get_platdata(&spi->dev); - flash->caps = of_device_get_match_data(&spi->dev); + flash->caps = spi_get_device_match_data(spi); if (!flash->caps) flash->caps = &mchp23k256_caps; diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index dce5e67ce3c2..f447902d707e 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -277,6 +277,12 @@ config MTD_PCMCIA_ANONYMOUS If unsure, say N. +config MTD_UCLINUX + bool "Generic uClinux RAM/ROM filesystem support" + depends on (MTD_RAM=y || MTD_ROM=y) && (!MMU || COLDFIRE) + help + Map driver to support image based filesystems for uClinux. + config MTD_PLATRAM tristate "Map driver for platform device RAM (mtd-ram)" select MTD_RAM diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile index fbed278157f6..01745eca1f73 100644 --- a/drivers/mtd/maps/Makefile +++ b/drivers/mtd/maps/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_MTD_SUN_UFLASH) += sun_uflash.o obj-$(CONFIG_MTD_SCx200_DOCFLASH)+= scx200_docflash.o obj-$(CONFIG_MTD_SOLUTIONENGINE)+= solutionengine.o obj-$(CONFIG_MTD_PCI) += pci.o +obj-$(CONFIG_MTD_UCLINUX) += uclinux.o obj-$(CONFIG_MTD_SCB2_FLASH) += scb2_flash.o obj-$(CONFIG_MTD_PLATRAM) += plat-ram.o obj-$(CONFIG_MTD_VMU) += vmu-flash.o diff --git a/drivers/mtd/maps/uclinux.c b/drivers/mtd/maps/uclinux.c new file mode 100644 index 000000000000..de4c46318abb --- /dev/null +++ b/drivers/mtd/maps/uclinux.c @@ -0,0 +1,118 @@ +/****************************************************************************/ + +/* + * uclinux.c -- generic memory mapped MTD driver for uclinux + * + * (C) Copyright 2002, Greg Ungerer (gerg@snapgear.com) + * + * License: GPL + */ + +/****************************************************************************/ + +#include <linux/moduleparam.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/major.h> +#include <linux/mtd/mtd.h> +#include <linux/mtd/map.h> +#include <linux/mtd/partitions.h> +#include <asm/io.h> +#include <asm/sections.h> + +/****************************************************************************/ + +#ifdef CONFIG_MTD_ROM +#define MAP_NAME "rom" +#else +#define MAP_NAME "ram" +#endif + +static struct map_info uclinux_ram_map = { + .name = MAP_NAME, + .size = 0, +}; + +static unsigned long physaddr = -1; +module_param(physaddr, ulong, S_IRUGO); + +static struct mtd_info *uclinux_ram_mtdinfo; + +/****************************************************************************/ + +static const struct mtd_partition uclinux_romfs[] = { + { .name = "ROMfs" } +}; + +#define NUM_PARTITIONS ARRAY_SIZE(uclinux_romfs) + +/****************************************************************************/ + +static int uclinux_point(struct mtd_info *mtd, loff_t from, size_t len, + size_t *retlen, void **virt, resource_size_t *phys) +{ + struct map_info *map = mtd->priv; + *virt = map->virt + from; + if (phys) + *phys = map->phys + from; + *retlen = len; + return(0); +} + +/****************************************************************************/ + +static int __init uclinux_mtd_init(void) +{ + struct mtd_info *mtd; + struct map_info *mapp; + + mapp = &uclinux_ram_map; + + if (physaddr == -1) + mapp->phys = (resource_size_t)__bss_stop; + else + mapp->phys = physaddr; + + if (!mapp->size) + mapp->size = PAGE_ALIGN(ntohl(*((unsigned long *)(mapp->phys + 8)))); + mapp->bankwidth = 4; + + printk("uclinux[mtd]: probe address=0x%x size=0x%x\n", + (int) mapp->phys, (int) mapp->size); + + /* + * The filesystem is guaranteed to be in direct mapped memory. It is + * directly following the kernels own bss region. Following the same + * mechanism used by architectures setting up traditional initrds we + * use phys_to_virt to get the virtual address of its start. + */ + mapp->virt = phys_to_virt(mapp->phys); + + if (mapp->virt == 0) { + printk("uclinux[mtd]: no virtual mapping?\n"); + return(-EIO); + } + + simple_map_init(mapp); + + mtd = do_map_probe("map_" MAP_NAME, mapp); + if (!mtd) { + printk("uclinux[mtd]: failed to find a mapping?\n"); + return(-ENXIO); + } + + mtd->owner = THIS_MODULE; + mtd->_point = uclinux_point; + mtd->priv = mapp; + + uclinux_ram_mtdinfo = mtd; + mtd_device_register(mtd, uclinux_romfs, NUM_PARTITIONS); + + return(0); +} +device_initcall(uclinux_mtd_init); + +/****************************************************************************/ diff --git a/drivers/mtd/mtd_virt_concat.c b/drivers/mtd/mtd_virt_concat.c index 37075ead0f33..da4277ced4d6 100644 --- a/drivers/mtd/mtd_virt_concat.c +++ b/drivers/mtd/mtd_virt_concat.c @@ -75,8 +75,8 @@ void mtd_virt_concat_destroy_joins(void) if (item->concat) { mtd_device_unregister(mtd); kfree(mtd->name); - mtd_concat_destroy(mtd); mtd_virt_concat_put_mtd_devices(item->concat); + mtd_concat_destroy(mtd); } } } @@ -126,8 +126,8 @@ int mtd_virt_concat_destroy(struct mtd_info *mtd) if (concat->mtd.name) { del_mtd_device(&concat->mtd); kfree(concat->mtd.name); - mtd_concat_destroy(&concat->mtd); mtd_virt_concat_put_mtd_devices(item->concat); + mtd_concat_destroy(&concat->mtd); } for (idx = 0; idx < item->count; idx++) @@ -321,8 +321,10 @@ int mtd_virt_concat_create_join(void) if (concat->mtd.name) { ret = memcmp(concat->mtd.name, name, name_sz); - if (ret == 0) + if (ret == 0) { + kfree(name); continue; + } } mtd = mtd_concat_create(concat->subdev, concat->num_subdev, name); if (!mtd) { diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 576537774628..16629382a787 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -105,6 +105,15 @@ static void mtd_release(struct device *dev) device_destroy(&mtd_class, index + 1); } +/* + * No-op device release used in add_mtd_device() error paths. + * Prevents mtd_release() from being called via device_release(), + * which would free the mtd_info that the caller still manages. + */ +static void mtd_dev_release_nop(struct device *dev) +{ +} + static void mtd_device_release(struct kref *kref) { struct mtd_info *mtd = container_of(kref, struct mtd_info, refcnt); @@ -799,10 +808,8 @@ int add_mtd_device(struct mtd_info *mtd) mtd_check_of_node(mtd); of_node_get(mtd_get_of_node(mtd)); error = device_register(&mtd->dev); - if (error) { - put_device(&mtd->dev); + if (error) goto fail_added; - } /* Add the nvmem provider */ error = mtd_nvmem_add(mtd); @@ -840,8 +847,16 @@ int add_mtd_device(struct mtd_info *mtd) return 0; fail_nvmem_add: - device_unregister(&mtd->dev); + device_del(&mtd->dev); fail_added: + /* + * Clear type and set nop release to prevent mtd_release() -> + * release_mtd_partition() -> free_partition() from freeing mtd. + * The caller handles cleanup on failure. + */ + mtd->dev.type = NULL; + mtd->dev.release = mtd_dev_release_nop; + put_device(&mtd->dev); of_node_put(mtd_get_of_node(mtd)); fail_devname: idr_remove(&mtd_idr, i); diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 795a94e6b482..4b41550fd374 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -118,6 +118,9 @@ static struct mtd_info *allocate_partition(struct mtd_info *parent, part->name, parent_size - child->part.offset, child->part.size); /* register to preserve ordering */ + child->part.offset = 0; + child->part.size = 0; + child->erasesize = parent->erasesize; goto out_register; } } @@ -264,6 +267,11 @@ int mtd_add_partition(struct mtd_info *parent, const char *name, if (length <= 0) return -EINVAL; + if (offset < 0 || offset >= (long long)parent_size) + return -EINVAL; + + if ((u64)offset + (u64)length > parent_size) + return -EINVAL; memset(&part, 0, sizeof(part)); part.name = name; part.size = length; diff --git a/drivers/mtd/mtdswap.c b/drivers/mtd/mtdswap.c index 866933fc8426..f33f753f0a9f 100644 --- a/drivers/mtd/mtdswap.c +++ b/drivers/mtd/mtdswap.c @@ -125,6 +125,7 @@ struct mtdswap_dev { char *page_buf; char *oob_buf; + struct dentry *debugfs_stats; }; struct mtdswap_oobdata { @@ -1262,7 +1263,8 @@ static int mtdswap_add_debugfs(struct mtdswap_dev *d) if (IS_ERR_OR_NULL(root)) return -1; - debugfs_create_file("mtdswap_stats", S_IRUSR, root, d, &mtdswap_fops); + d->debugfs_stats = debugfs_create_file("mtdswap_stats", 0400, root, + d, &mtdswap_fops); return 0; } @@ -1463,6 +1465,7 @@ static void mtdswap_remove_dev(struct mtd_blktrans_dev *dev) { struct mtdswap_dev *d = MTDSWAP_MBD_TO_MTDSWAP(dev); + debugfs_remove(d->debugfs_stats); del_mtd_blktrans_dev(dev); mtdswap_cleanup(d); kfree(d); diff --git a/drivers/mtd/nand/ecc-mtk.c b/drivers/mtd/nand/ecc-mtk.c index c75bb8b80cc1..66f0985ef7cd 100644 --- a/drivers/mtd/nand/ecc-mtk.c +++ b/drivers/mtd/nand/ecc-mtk.c @@ -123,8 +123,8 @@ static int mt7622_ecc_regs[] = { [ECC_DECIRQ_STA] = 0x144, }; -static inline void mtk_ecc_wait_idle(struct mtk_ecc *ecc, - enum mtk_ecc_operation op) +static inline int mtk_ecc_wait_idle(struct mtk_ecc *ecc, + enum mtk_ecc_operation op) { struct device *dev = ecc->dev; u32 val; @@ -136,6 +136,8 @@ static inline void mtk_ecc_wait_idle(struct mtk_ecc *ecc, if (ret) dev_warn(dev, "%s NOT idle\n", op == ECC_ENCODE ? "encoder" : "decoder"); + + return ret; } static irqreturn_t mtk_ecc_irq(int irq, void *id) @@ -265,6 +267,7 @@ static struct mtk_ecc *mtk_ecc_get(struct device_node *np) { struct platform_device *pdev; struct mtk_ecc *ecc; + int ret; pdev = of_find_device_by_node(np); if (!pdev) @@ -276,7 +279,12 @@ static struct mtk_ecc *mtk_ecc_get(struct device_node *np) return ERR_PTR(-EPROBE_DEFER); } - clk_prepare_enable(ecc->clk); + ret = clk_prepare_enable(ecc->clk); + if (ret) { + put_device(&pdev->dev); + return ERR_PTR(ret); + } + mtk_ecc_hw_init(ecc); return ecc; @@ -312,7 +320,11 @@ int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config) return ret; } - mtk_ecc_wait_idle(ecc, op); + ret = mtk_ecc_wait_idle(ecc, op); + if (ret) { + mutex_unlock(&ecc->lock); + return ret; + } ret = mtk_ecc_config(ecc, config); if (ret) { @@ -412,7 +424,9 @@ int mtk_ecc_encode(struct mtk_ecc *ecc, struct mtk_ecc_config *config, if (ret) goto timeout; - mtk_ecc_wait_idle(ecc, ECC_ENCODE); + ret = mtk_ecc_wait_idle(ecc, ECC_ENCODE); + if (ret) + goto timeout; /* Program ECC bytes to OOB: per sector oob = FDM + ECC + SPARE */ len = (config->strength * ecc->caps->parity_bits + 7) >> 3; diff --git a/drivers/mtd/nand/onenand/onenand_samsung.c b/drivers/mtd/nand/onenand/onenand_samsung.c index 6d6aa709a21f..b7b7758ce4d8 100644 --- a/drivers/mtd/nand/onenand/onenand_samsung.c +++ b/drivers/mtd/nand/onenand/onenand_samsung.c @@ -554,6 +554,9 @@ static int s5pc110_dma_poll(dma_addr_t dst, dma_addr_t src, size_t count, int di } while (!(status & S5PC110_DMA_TRANS_STATUS_TD) && time_before(jiffies, timeout)); + if (!(status & S5PC110_DMA_TRANS_STATUS_TD)) + return -ETIMEDOUT; + writel(S5PC110_DMA_TRANS_CMD_TDC, base + S5PC110_DMA_TRANS_CMD); return 0; @@ -608,7 +611,9 @@ static int s5pc110_dma_irq(dma_addr_t dst, dma_addr_t src, size_t count, int dir writel(S5PC110_DMA_TRANS_CMD_TR, base + S5PC110_DMA_TRANS_CMD); - wait_for_completion_timeout(&onenand->complete, msecs_to_jiffies(20)); + if (!wait_for_completion_timeout(&onenand->complete, + msecs_to_jiffies(20))) + return -ETIMEDOUT; return 0; } diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig index 64b8b99a3a68..1f4053e531fd 100644 --- a/drivers/mtd/nand/raw/Kconfig +++ b/drivers/mtd/nand/raw/Kconfig @@ -72,6 +72,7 @@ config MTD_NAND_AU1550 config MTD_NAND_NDFC tristate "IBM/MCC 4xx NAND controller" depends on 44x || COMPILE_TEST + depends on OF select MTD_NAND_ECC_SW_HAMMING select MTD_NAND_ECC_SW_HAMMING_SMC help diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c index fad0334f759d..a88ac2cfaccd 100644 --- a/drivers/mtd/nand/raw/fsl_ifc_nand.c +++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c @@ -684,8 +684,15 @@ static int fsl_ifc_read_page(struct nand_chip *chip, uint8_t *buf, return check_erased_page(chip, buf); } - if (ctrl->nand_stat != IFC_NAND_EVTER_STAT_OPC) + if (!ctrl->nand_stat) { mtd->ecc_stats.failed++; + return -ETIMEDOUT; + } + + if (ctrl->nand_stat != IFC_NAND_EVTER_STAT_OPC) { + mtd->ecc_stats.failed++; + return -EIO; + } return nctrl->max_bitflips; } diff --git a/drivers/mtd/nand/raw/ingenic/ingenic_ecc.c b/drivers/mtd/nand/raw/ingenic/ingenic_ecc.c index 525c34c281b6..beb033705cf3 100644 --- a/drivers/mtd/nand/raw/ingenic/ingenic_ecc.c +++ b/drivers/mtd/nand/raw/ingenic/ingenic_ecc.c @@ -67,6 +67,7 @@ static struct ingenic_ecc *ingenic_ecc_get(struct device_node *np) { struct platform_device *pdev; struct ingenic_ecc *ecc; + int ret; pdev = of_find_device_by_node(np); if (!pdev) @@ -78,7 +79,11 @@ static struct ingenic_ecc *ingenic_ecc_get(struct device_node *np) } ecc = platform_get_drvdata(pdev); - clk_prepare_enable(ecc->clk); + ret = clk_prepare_enable(ecc->clk); + if (ret) { + put_device(&pdev->dev); + return ERR_PTR(ret); + } return ecc; } diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c index 19b13ae536d4..8f6a89d9ba83 100644 --- a/drivers/mtd/nand/raw/lpc32xx_mlc.c +++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c @@ -396,6 +396,7 @@ static int lpc32xx_xmit_dma(struct mtd_info *mtd, void *mem, int len, struct lpc32xx_nand_host *host = nand_get_controller_data(chip); struct dma_async_tx_descriptor *desc; int flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT; + unsigned long time_left; int res; sg_init_one(&host->sgl, mem, len); @@ -410,6 +411,7 @@ static int lpc32xx_xmit_dma(struct mtd_info *mtd, void *mem, int len, flags); if (!desc) { dev_err(mtd->dev.parent, "Failed to prepare slave sg\n"); + res = -ENXIO; goto out1; } @@ -420,7 +422,13 @@ static int lpc32xx_xmit_dma(struct mtd_info *mtd, void *mem, int len, dmaengine_submit(desc); dma_async_issue_pending(host->dma_chan); - wait_for_completion_timeout(&host->comp_dma, msecs_to_jiffies(1000)); + time_left = wait_for_completion_timeout(&host->comp_dma, + msecs_to_jiffies(1000)); + if (!time_left) { + dmaengine_terminate_sync(host->dma_chan); + res = -ETIMEDOUT; + goto out1; + } dma_unmap_sg(host->dma_chan->device->dev, &host->sgl, 1, DMA_BIDIRECTIONAL); @@ -428,7 +436,7 @@ static int lpc32xx_xmit_dma(struct mtd_info *mtd, void *mem, int len, out1: dma_unmap_sg(host->dma_chan->device->dev, &host->sgl, 1, DMA_BIDIRECTIONAL); - return -ENXIO; + return res; } static int lpc32xx_read_page(struct nand_chip *chip, uint8_t *buf, diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c index 3ca30e7dce33..10c8080207f4 100644 --- a/drivers/mtd/nand/raw/lpc32xx_slc.c +++ b/drivers/mtd/nand/raw/lpc32xx_slc.c @@ -430,6 +430,7 @@ static int lpc32xx_xmit_dma(struct mtd_info *mtd, dma_addr_t dma, struct dma_async_tx_descriptor *desc; int flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT; int res; + unsigned long time_left; host->dma_slave_config.direction = dir; host->dma_slave_config.src_addr = dma; @@ -467,12 +468,19 @@ static int lpc32xx_xmit_dma(struct mtd_info *mtd, dma_addr_t dma, dmaengine_submit(desc); dma_async_issue_pending(host->dma_chan); - wait_for_completion_timeout(&host->comp, msecs_to_jiffies(1000)); + time_left = wait_for_completion_timeout(&host->comp, + msecs_to_jiffies(1000)); + if (!time_left) { + dmaengine_terminate_sync(host->dma_chan); + res = -ETIMEDOUT; + } else { + res = 0; + } dma_unmap_sg(host->dma_chan->device->dev, &host->sgl, 1, DMA_BIDIRECTIONAL); - return 0; + return res; out1: dma_unmap_sg(host->dma_chan->device->dev, &host->sgl, 1, DMA_BIDIRECTIONAL); diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c index a937ca3eeff5..a48274297d3b 100644 --- a/drivers/mtd/nand/raw/ndfc.c +++ b/drivers/mtd/nand/raw/ndfc.c @@ -188,7 +188,7 @@ static int ndfc_probe(struct platform_device *ofdev) const __be32 *reg; u32 ccr; u32 cs; - int err, len; + int err, len = 0; /* Read the reg property to get the chip select */ reg = of_get_property(ofdev->dev.of_node, "reg", &len); diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index f86786344d52..74bb5ee83b31 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -822,7 +822,7 @@ static int spinand_mtd_regular_page_read(struct mtd_info *mtd, loff_t from, bool disable_ecc = false; bool ecc_failed = false; unsigned int retry_mode = 0; - int ret; + int ret = 0; old_stats = mtd->ecc_stats; diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 951dd10e192b..182a41d59a75 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -1211,7 +1211,7 @@ static netdev_tx_t amt_dev_xmit(struct sk_buff *skb, struct net_device *dev) data = true; } v6 = false; - group.ip4 = iph->daddr; + group.ip4 = ip_hdr(skb)->daddr; #if IS_ENABLED(CONFIG_IPV6) } else if (iph->version == 6) { ip6h = ipv6_hdr(skb); @@ -1235,7 +1235,7 @@ static netdev_tx_t amt_dev_xmit(struct sk_buff *skb, struct net_device *dev) data = true; } v6 = true; - group.ip6 = ip6h->daddr; + group.ip6 = ipv6_hdr(skb)->daddr; #endif } else { dev->stats.tx_errors++; @@ -1278,12 +1278,12 @@ static netdev_tx_t amt_dev_xmit(struct sk_buff *skb, struct net_device *dev) hlist_for_each_entry_rcu(gnode, &tunnel->groups[hash], node) { if (!v6) { - if (gnode->group_addr.ip4 == iph->daddr) + if (gnode->group_addr.ip4 == group.ip4) goto found; #if IS_ENABLED(CONFIG_IPV6) } else { if (ipv6_addr_equal(&gnode->group_addr.ip6, - &ip6h->daddr)) + &group.ip6)) goto found; #endif } @@ -2000,14 +2000,18 @@ static void amt_igmpv3_report_handler(struct amt_dev *amt, struct sk_buff *skb, struct igmpv3_report *ihrv3 = igmpv3_report_hdr(skb); int len = skb_transport_offset(skb) + sizeof(*ihrv3); void *zero_grec = (void *)&igmpv3_zero_grec; - struct iphdr *iph = ip_hdr(skb); struct amt_group_node *gnode; union amt_addr group, host; struct igmpv3_grec *grec; + __be32 saddr; u16 nsrcs; + u16 ngrec; int i; - for (i = 0; i < ntohs(ihrv3->ngrec); i++) { + saddr = ip_hdr(skb)->saddr; + ngrec = ntohs(ihrv3->ngrec); + + for (i = 0; i < ngrec; i++) { len += sizeof(*grec); if (!ip_mc_may_pull(skb, len)) break; @@ -2019,10 +2023,13 @@ static void amt_igmpv3_report_handler(struct amt_dev *amt, struct sk_buff *skb, if (!ip_mc_may_pull(skb, len)) break; + grec = (void *)(skb->data + len - sizeof(*grec) - + nsrcs * sizeof(__be32)); + memset(&group, 0, sizeof(union amt_addr)); group.ip4 = grec->grec_mca; memset(&host, 0, sizeof(union amt_addr)); - host.ip4 = iph->saddr; + host.ip4 = saddr; gnode = amt_lookup_group(tunnel, &group, &host, false); if (!gnode) { gnode = amt_add_group(amt, tunnel, &group, &host, @@ -2162,14 +2169,18 @@ static void amt_mldv2_report_handler(struct amt_dev *amt, struct sk_buff *skb, struct mld2_report *mld2r = (struct mld2_report *)icmp6_hdr(skb); int len = skb_transport_offset(skb) + sizeof(*mld2r); void *zero_grec = (void *)&mldv2_zero_grec; - struct ipv6hdr *ip6h = ipv6_hdr(skb); struct amt_group_node *gnode; union amt_addr group, host; struct mld2_grec *grec; + struct in6_addr saddr; u16 nsrcs; + u16 ngrec; int i; - for (i = 0; i < ntohs(mld2r->mld2r_ngrec); i++) { + saddr = ipv6_hdr(skb)->saddr; + ngrec = ntohs(mld2r->mld2r_ngrec); + + for (i = 0; i < ngrec; i++) { len += sizeof(*grec); if (!ipv6_mc_may_pull(skb, len)) break; @@ -2181,10 +2192,13 @@ static void amt_mldv2_report_handler(struct amt_dev *amt, struct sk_buff *skb, if (!ipv6_mc_may_pull(skb, len)) break; + grec = (void *)(skb->data + len - sizeof(*grec) - + nsrcs * sizeof(struct in6_addr)); + memset(&group, 0, sizeof(union amt_addr)); group.ip6 = grec->grec_mca; memset(&host, 0, sizeof(union amt_addr)); - host.ip6 = ip6h->saddr; + host.ip6 = saddr; gnode = amt_lookup_group(tunnel, &group, &host, true); if (!gnode) { gnode = amt_add_group(amt, tunnel, &group, &host, @@ -2305,7 +2319,9 @@ static bool amt_multicast_data_handler(struct amt_dev *amt, struct sk_buff *skb) skb_push(skb, sizeof(*eth)); skb_reset_mac_header(skb); skb_pull(skb, sizeof(*eth)); - eth = eth_hdr(skb); + + if (skb_cow_head(skb, 0)) + return true; if (!pskb_may_pull(skb, sizeof(*iph))) return true; @@ -2315,6 +2331,7 @@ static bool amt_multicast_data_handler(struct amt_dev *amt, struct sk_buff *skb) if (!ipv4_is_multicast(iph->daddr)) return true; skb->protocol = htons(ETH_P_IP); + eth = eth_hdr(skb); eth->h_proto = htons(ETH_P_IP); ip_eth_mc_map(iph->daddr, eth->h_dest); #if IS_ENABLED(CONFIG_IPV6) @@ -2328,6 +2345,7 @@ static bool amt_multicast_data_handler(struct amt_dev *amt, struct sk_buff *skb) if (!ipv6_addr_is_multicast(&ip6h->daddr)) return true; skb->protocol = htons(ETH_P_IPV6); + eth = eth_hdr(skb); eth->h_proto = htons(ETH_P_IPV6); ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); #endif @@ -2351,10 +2369,12 @@ static bool amt_membership_query_handler(struct amt_dev *amt, struct sk_buff *skb) { struct amt_header_membership_query *amtmq; - struct igmpv3_query *ihv3; struct ethhdr *eth, *oeth; + struct igmpv3_query *ihv3; + u8 h_source[ETH_ALEN]; struct iphdr *iph; int hdr_size, len; + u64 response_mac; hdr_size = sizeof(*amtmq) + sizeof(struct udphdr); if (!pskb_may_pull(skb, hdr_size)) @@ -2367,6 +2387,8 @@ static bool amt_membership_query_handler(struct amt_dev *amt, if (amtmq->nonce != amt->nonce) return true; + response_mac = amtmq->response_mac; + hdr_size -= sizeof(*eth); if (iptunnel_pull_header(skb, hdr_size, htons(ETH_P_TEB), false)) return true; @@ -2376,6 +2398,9 @@ static bool amt_membership_query_handler(struct amt_dev *amt, skb_pull(skb, sizeof(*eth)); skb_reset_network_header(skb); eth = eth_hdr(skb); + ether_addr_copy(h_source, oeth->h_source); + if (skb_cow_head(skb, 0)) + return true; if (!pskb_may_pull(skb, sizeof(*iph))) return true; @@ -2388,6 +2413,7 @@ static bool amt_membership_query_handler(struct amt_dev *amt, sizeof(*ihv3))) return true; + iph = ip_hdr(skb); if (!ipv4_is_multicast(iph->daddr)) return true; @@ -2395,10 +2421,11 @@ static bool amt_membership_query_handler(struct amt_dev *amt, skb_reset_transport_header(skb); skb_push(skb, sizeof(*iph) + AMT_IPHDR_OPTS); WRITE_ONCE(amt->ready4, true); - amt->mac = amtmq->response_mac; + amt->mac = response_mac; amt->req_cnt = 0; amt->qi = ihv3->qqic; skb->protocol = htons(ETH_P_IP); + eth = eth_hdr(skb); eth->h_proto = htons(ETH_P_IP); ip_eth_mc_map(iph->daddr, eth->h_dest); #if IS_ENABLED(CONFIG_IPV6) @@ -2421,10 +2448,11 @@ static bool amt_membership_query_handler(struct amt_dev *amt, skb_reset_transport_header(skb); skb_push(skb, sizeof(*ip6h) + AMT_IP6HDR_OPTS); WRITE_ONCE(amt->ready6, true); - amt->mac = amtmq->response_mac; + amt->mac = response_mac; amt->req_cnt = 0; amt->qi = mld2q->mld2q_qqic; skb->protocol = htons(ETH_P_IPV6); + eth = eth_hdr(skb); eth->h_proto = htons(ETH_P_IPV6); ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); #endif @@ -2432,7 +2460,7 @@ static bool amt_membership_query_handler(struct amt_dev *amt, return true; } - ether_addr_copy(eth->h_source, oeth->h_source); + ether_addr_copy(eth->h_source, h_source); skb->pkt_type = PACKET_MULTICAST; skb->ip_summed = CHECKSUM_NONE; len = skb->len; @@ -2455,8 +2483,11 @@ static bool amt_update_handler(struct amt_dev *amt, struct sk_buff *skb) struct ethhdr *eth; struct iphdr *iph; int len, hdr_size; + u64 response_mac; + __be32 saddr; + __be32 nonce; - iph = ip_hdr(skb); + saddr = ip_hdr(skb)->saddr; hdr_size = sizeof(*amtmu) + sizeof(struct udphdr); if (!pskb_may_pull(skb, hdr_size)) @@ -2466,15 +2497,18 @@ static bool amt_update_handler(struct amt_dev *amt, struct sk_buff *skb) if (amtmu->reserved || amtmu->version) return true; + nonce = amtmu->nonce; + response_mac = amtmu->response_mac; + if (iptunnel_pull_header(skb, hdr_size, skb->protocol, false)) return true; skb_reset_network_header(skb); list_for_each_entry_rcu(tunnel, &amt->tunnel_list, list) { - if (tunnel->ip4 == iph->saddr) { - if ((amtmu->nonce == tunnel->nonce && - amtmu->response_mac == tunnel->mac)) { + if (tunnel->ip4 == saddr) { + if ((nonce == tunnel->nonce && + response_mac == tunnel->mac)) { mod_delayed_work(amt_wq, &tunnel->gc_wq, msecs_to_jiffies(amt_gmi(amt)) * 3); @@ -2492,6 +2526,9 @@ report: if (!pskb_may_pull(skb, sizeof(*iph))) return true; + if (skb_cow_head(skb, 0)) + return true; + iph = ip_hdr(skb); if (iph->version == 4) { if (ip_mc_check_igmp(skb)) { @@ -2508,6 +2545,7 @@ report: eth = eth_hdr(skb); skb->protocol = htons(ETH_P_IP); eth->h_proto = htons(ETH_P_IP); + iph = ip_hdr(skb); ip_eth_mc_map(iph->daddr, eth->h_dest); #if IS_ENABLED(CONFIG_IPV6) } else if (iph->version == 6) { @@ -2527,6 +2565,7 @@ report: eth = eth_hdr(skb); skb->protocol = htons(ETH_P_IPV6); eth->h_proto = htons(ETH_P_IPV6); + ip6h = ipv6_hdr(skb); ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); #endif } else { @@ -2772,7 +2811,7 @@ drop: static int amt_rcv(struct sock *sk, struct sk_buff *skb) { struct amt_dev *amt; - struct iphdr *iph; + __be32 saddr; int type; bool err; @@ -2785,7 +2824,7 @@ static int amt_rcv(struct sock *sk, struct sk_buff *skb) } skb->dev = amt->dev; - iph = ip_hdr(skb); + saddr = ip_hdr(skb)->saddr; type = amt_parse_type(skb); if (type == -1) { err = true; @@ -2795,7 +2834,7 @@ static int amt_rcv(struct sock *sk, struct sk_buff *skb) if (amt->mode == AMT_MODE_GATEWAY) { switch (type) { case AMT_MSG_ADVERTISEMENT: - if (iph->saddr != amt->discovery_ip) { + if (saddr != amt->discovery_ip) { netdev_dbg(amt->dev, "Invalid Relay IP\n"); err = true; goto drop; @@ -2807,7 +2846,7 @@ static int amt_rcv(struct sock *sk, struct sk_buff *skb) } goto out; case AMT_MSG_MULTICAST_DATA: - if (iph->saddr != amt->remote_ip) { + if (saddr != amt->remote_ip) { netdev_dbg(amt->dev, "Invalid Relay IP\n"); err = true; goto drop; @@ -2818,7 +2857,7 @@ static int amt_rcv(struct sock *sk, struct sk_buff *skb) else goto out; case AMT_MSG_MEMBERSHIP_QUERY: - if (iph->saddr != amt->remote_ip) { + if (saddr != amt->remote_ip) { netdev_dbg(amt->dev, "Invalid Relay IP\n"); err = true; goto drop; @@ -2995,9 +3034,15 @@ static int amt_dev_open(struct net_device *dev) amt->event_idx = 0; amt->nr_events = 0; + enable_delayed_work(&amt->discovery_wq); + enable_delayed_work(&amt->req_wq); + err = amt_socket_create(amt); - if (err) + if (err) { + disable_delayed_work(&amt->req_wq); + disable_delayed_work(&amt->discovery_wq); return err; + } amt->req_cnt = 0; amt->remote_ip = 0; @@ -3023,8 +3068,8 @@ static int amt_dev_stop(struct net_device *dev) struct sock *sk; int i; - cancel_delayed_work_sync(&amt->req_wq); - cancel_delayed_work_sync(&amt->discovery_wq); + disable_delayed_work_sync(&amt->req_wq); + disable_delayed_work_sync(&amt->discovery_wq); cancel_delayed_work_sync(&amt->secret_wq); /* shutdown */ @@ -3278,6 +3323,8 @@ static int amt_newlink(struct net_device *dev, INIT_DELAYED_WORK(&amt->req_wq, amt_req_work); INIT_DELAYED_WORK(&amt->secret_wq, amt_secret_work); INIT_WORK(&amt->event_wq, amt_event_work); + disable_delayed_work(&amt->req_wq); + disable_delayed_work(&amt->discovery_wq); INIT_LIST_HEAD(&amt->tunnel_list); return 0; err: diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e044fc733b8c..522eab060f9e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3455,7 +3455,8 @@ static void bond_send_validate(struct bonding *bond, struct slave *slave) { bond_arp_send_all(bond, slave); #if IS_ENABLED(CONFIG_IPV6) - bond_ns_send_all(bond, slave); + if (likely(ipv6_mod_enabled())) + bond_ns_send_all(bond, slave); #endif } diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index e4058708ae68..a8fad6fe5302 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -40,11 +40,8 @@ config CAN_VXCAN When one end receives the packet it appears on its pair and vice versa. The vxcan can be used for cross namespace communication. - In opposite to vcan loopback devices the vxcan only forwards CAN - frames to its pair and does *not* provide a local echo of sent - CAN frames. To disable a potential echo in af_can.c the vxcan driver - announces IFF_ECHO in the interface flags. To have a clean start - in each namespace the CAN GW hop counter is set to zero. + To have a clean start in each namespace the CAN GW hop counter is + set to zero. This driver can also be built as a module. If so, the module will be called vxcan. diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c index 06cb2629f66a..4fd1aefb780f 100644 --- a/drivers/net/can/peak_canfd/peak_canfd.c +++ b/drivers/net/can/peak_canfd/peak_canfd.c @@ -2,7 +2,7 @@ /* Copyright (C) 2007, 2011 Wolfgang Grandegger <wg@grandegger.com> * * Copyright (C) 2016-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> */ #include <linux/can.h> diff --git a/drivers/net/can/peak_canfd/peak_canfd_user.h b/drivers/net/can/peak_canfd/peak_canfd_user.h index 60c6542028cf..dc0ecb566a85 100644 --- a/drivers/net/can/peak_canfd/peak_canfd_user.h +++ b/drivers/net/can/peak_canfd/peak_canfd_user.h @@ -2,7 +2,7 @@ /* CAN driver for PEAK System micro-CAN based adapters * * Copyright (C) 2003-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> */ #ifndef PEAK_CANFD_USER_H #define PEAK_CANFD_USER_H diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index 93558e33bc02..7c749301ea84 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -4,7 +4,7 @@ * Derived from the PCAN project file driver/src/pcan_pci.c: * * Copyright (C) 2001-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> */ #include <linux/kernel.h> @@ -19,7 +19,7 @@ #include "peak_canfd_user.h" -MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>"); +MODULE_AUTHOR("Stéphane Grosjean <s.grosjean@peak-system.fr>"); MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCIe/M.2 FD family cards"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index 4cc4a1581dd1..69c61ccf621d 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -5,7 +5,7 @@ * Derived from the PCAN project file driver/src/pcan_pci.c: * * Copyright (C) 2001-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> */ #include <linux/kernel.h> @@ -22,7 +22,7 @@ #include "sja1000.h" -MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>"); +MODULE_AUTHOR("Stéphane Grosjean <s.grosjean@peak-system.fr>"); MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCI family cards"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c index 42a77d435b39..c3c2aa21da47 100644 --- a/drivers/net/can/sja1000/peak_pcmcia.c +++ b/drivers/net/can/sja1000/peak_pcmcia.c @@ -4,7 +4,7 @@ * Derived from the PCAN project file driver/src/pcan_pccard.c * * Copyright (C) 2006-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> */ #include <linux/kernel.h> #include <linux/module.h> @@ -19,7 +19,7 @@ #include <linux/can/dev.h> #include "sja1000.h" -MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>"); +MODULE_AUTHOR("Stéphane Grosjean <s.grosjean@peak-system.fr>"); MODULE_DESCRIPTION("CAN driver for PEAK-System PCAN-PC Cards"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index d257440fa01f..f41d4a0d140f 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -1390,10 +1390,13 @@ static void esd_usb_disconnect(struct usb_interface *intf) netdev = dev->nets[i]->netdev; netdev_info(netdev, "unregister\n"); unregister_netdev(netdev); - free_candev(netdev); } } unlink_all_urbs(dev); + for (i = 0; i < dev->net_count; i++) { + if (dev->nets[i]) + free_candev(dev->nets[i]->netdev); + } kfree(dev); } } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 9278a1522aae..8fd058c32856 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -4,7 +4,7 @@ * Derived from the PCAN project file driver/src/pcan_usb.c * * Copyright (C) 2003-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> * * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de> */ diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index cf48bb26d46d..c7933d1acc99 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -4,7 +4,7 @@ * Derived from the PCAN project file driver/src/pcan_usb_core.c * * Copyright (C) 2003-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> * * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de> */ @@ -24,7 +24,7 @@ #include "pcan_usb_core.h" -MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>"); +MODULE_AUTHOR("Stéphane Grosjean <s.grosjean@peak-system.fr>"); MODULE_DESCRIPTION("CAN driver for PEAK-System USB adapters"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h index d1c1897d47b9..65999f04f4b7 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h @@ -4,7 +4,7 @@ * Derived from the PCAN project file driver/src/pcan_usb_core.c * * Copyright (C) 2003-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> * * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de> */ diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index eb4f5884ad73..ef9fd693e9bd 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -3,7 +3,7 @@ * CAN driver for PEAK System PCAN-USB FD / PCAN-USB Pro FD adapter * * Copyright (C) 2013-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> */ #include <linux/ethtool.h> #include <linux/module.h> diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 4bfa8d0fbb32..aefcded8e12a 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -4,7 +4,7 @@ * Derived from the PCAN project file driver/src/pcan_usbpro.c * * Copyright (C) 2003-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> */ #include <linux/ethtool.h> #include <linux/module.h> diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h index 162c7546d3a8..d669c9e610c7 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h @@ -4,7 +4,7 @@ * Derived from the PCAN project file driver/src/pcan_usbpro_fw.h * * Copyright (C) 2003-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> */ #ifndef PCAN_USB_PRO_H #define PCAN_USB_PRO_H diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 59001fd4b6f7..79418e682f71 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1686,11 +1686,14 @@ static void airoha_qdma_stop_napi(struct airoha_qdma *qdma) } } -static void airoha_dev_get_hw_stats(struct airoha_gdm_dev *dev) +static void airoha_update_hw_stats(struct airoha_gdm_dev *dev) { struct airoha_gdm_port *port = dev->port; struct airoha_eth *eth = dev->eth; u32 val, i = 0; + u64 data; + + spin_lock(&port->stats_lock); /* Read relevant MIB for GDM with multiple port attached */ if (port->id == AIROHA_GDM3_IDX || port->id == AIROHA_GDM4_IDX) @@ -1701,152 +1704,188 @@ static void airoha_dev_get_hw_stats(struct airoha_gdm_dev *dev) u64_stats_update_begin(&dev->stats.syncp); - /* TX */ + /* TX - 64-bit H+L registers: hw accumulates the total, read directly. + * Use local variable to prevent readers from seeing intermediate values. + * Clamp to prevent regression from torn reads between H and L. + */ val = airoha_fe_rr(eth, REG_FE_GDM_TX_OK_PKT_CNT_H(port->id)); - dev->stats.tx_ok_pkts += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_TX_OK_PKT_CNT_L(port->id)); - dev->stats.tx_ok_pkts += val; + data += val; + dev->stats.tx_ok_pkts = max(data, dev->stats.tx_ok_pkts); val = airoha_fe_rr(eth, REG_FE_GDM_TX_OK_BYTE_CNT_H(port->id)); - dev->stats.tx_ok_bytes += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_TX_OK_BYTE_CNT_L(port->id)); - dev->stats.tx_ok_bytes += val; + data += val; + dev->stats.tx_ok_bytes = max(data, dev->stats.tx_ok_bytes); + /* TX - 32-bit registers: accumulate delta to handle wrap-around. */ val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_DROP_CNT(port->id)); - dev->stats.tx_drops += val; + dev->stats.tx_drops += (u32)(val - dev->stats.mib_prev.tx_drops); + dev->stats.mib_prev.tx_drops = val; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_BC_CNT(port->id)); - dev->stats.tx_broadcast += val; + dev->stats.tx_broadcast += (u32)(val - dev->stats.mib_prev.tx_broadcast); + dev->stats.mib_prev.tx_broadcast = val; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_MC_CNT(port->id)); - dev->stats.tx_multicast += val; + dev->stats.tx_multicast += (u32)(val - dev->stats.mib_prev.tx_multicast); + dev->stats.mib_prev.tx_multicast = val; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_RUNT_CNT(port->id)); - dev->stats.tx_len[i] += val; + dev->stats.mib_prev.tx_runt64 += + (u32)(val - dev->stats.mib_prev.tx_runt); + dev->stats.mib_prev.tx_runt = val; + /* tx_len[0]: RUNT (32-bit, delta) + E64 (64-bit, absolute). */ + data = dev->stats.mib_prev.tx_runt64; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_E64_CNT_H(port->id)); - dev->stats.tx_len[i] += ((u64)val << 32); + data += (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_E64_CNT_L(port->id)); - dev->stats.tx_len[i++] += val; + data += val; + dev->stats.tx_len[i] = max(data, dev->stats.tx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_L64_CNT_H(port->id)); - dev->stats.tx_len[i] += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_L64_CNT_L(port->id)); - dev->stats.tx_len[i++] += val; + data += val; + dev->stats.tx_len[i] = max(data, dev->stats.tx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_L127_CNT_H(port->id)); - dev->stats.tx_len[i] += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_L127_CNT_L(port->id)); - dev->stats.tx_len[i++] += val; + data += val; + dev->stats.tx_len[i] = max(data, dev->stats.tx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_L255_CNT_H(port->id)); - dev->stats.tx_len[i] += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_L255_CNT_L(port->id)); - dev->stats.tx_len[i++] += val; + data += val; + dev->stats.tx_len[i] = max(data, dev->stats.tx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_L511_CNT_H(port->id)); - dev->stats.tx_len[i] += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_L511_CNT_L(port->id)); - dev->stats.tx_len[i++] += val; + data += val; + dev->stats.tx_len[i] = max(data, dev->stats.tx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_L1023_CNT_H(port->id)); - dev->stats.tx_len[i] += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_L1023_CNT_L(port->id)); - dev->stats.tx_len[i++] += val; + data += val; + dev->stats.tx_len[i] = max(data, dev->stats.tx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_TX_ETH_LONG_CNT(port->id)); - dev->stats.tx_len[i++] += val; + dev->stats.tx_len[i++] += (u32)(val - dev->stats.mib_prev.tx_long); + dev->stats.mib_prev.tx_long = val; /* RX */ val = airoha_fe_rr(eth, REG_FE_GDM_RX_OK_PKT_CNT_H(port->id)); - dev->stats.rx_ok_pkts += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_RX_OK_PKT_CNT_L(port->id)); - dev->stats.rx_ok_pkts += val; + data += val; + dev->stats.rx_ok_pkts = max(data, dev->stats.rx_ok_pkts); val = airoha_fe_rr(eth, REG_FE_GDM_RX_OK_BYTE_CNT_H(port->id)); - dev->stats.rx_ok_bytes += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_RX_OK_BYTE_CNT_L(port->id)); - dev->stats.rx_ok_bytes += val; + data += val; + dev->stats.rx_ok_bytes = max(data, dev->stats.rx_ok_bytes); val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_DROP_CNT(port->id)); - dev->stats.rx_drops += val; + dev->stats.rx_drops += (u32)(val - dev->stats.mib_prev.rx_drops); + dev->stats.mib_prev.rx_drops = val; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_BC_CNT(port->id)); - dev->stats.rx_broadcast += val; + dev->stats.rx_broadcast += (u32)(val - dev->stats.mib_prev.rx_broadcast); + dev->stats.mib_prev.rx_broadcast = val; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_MC_CNT(port->id)); - dev->stats.rx_multicast += val; + dev->stats.rx_multicast += (u32)(val - dev->stats.mib_prev.rx_multicast); + dev->stats.mib_prev.rx_multicast = val; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ERROR_DROP_CNT(port->id)); - dev->stats.rx_errors += val; + dev->stats.rx_errors += (u32)(val - dev->stats.mib_prev.rx_errors); + dev->stats.mib_prev.rx_errors = val; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_CRC_ERR_CNT(port->id)); - dev->stats.rx_crc_error += val; + dev->stats.rx_crc_error += (u32)(val - dev->stats.mib_prev.rx_crc_error); + dev->stats.mib_prev.rx_crc_error = val; val = airoha_fe_rr(eth, REG_FE_GDM_RX_OVERFLOW_DROP_CNT(port->id)); - dev->stats.rx_over_errors += val; + dev->stats.rx_over_errors += (u32)(val - dev->stats.mib_prev.rx_over_errors); + dev->stats.mib_prev.rx_over_errors = val; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_FRAG_CNT(port->id)); - dev->stats.rx_fragment += val; + dev->stats.rx_fragment += (u32)(val - dev->stats.mib_prev.rx_fragment); + dev->stats.mib_prev.rx_fragment = val; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_JABBER_CNT(port->id)); - dev->stats.rx_jabber += val; + dev->stats.rx_jabber += (u32)(val - dev->stats.mib_prev.rx_jabber); + dev->stats.mib_prev.rx_jabber = val; i = 0; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_RUNT_CNT(port->id)); - dev->stats.rx_len[i] += val; + dev->stats.mib_prev.rx_runt64 += + (u32)(val - dev->stats.mib_prev.rx_runt); + dev->stats.mib_prev.rx_runt = val; + /* rx_len[0]: RUNT (32-bit, delta) + E64 (64-bit, absolute). */ + data = dev->stats.mib_prev.rx_runt64; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_E64_CNT_H(port->id)); - dev->stats.rx_len[i] += ((u64)val << 32); + data += (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_E64_CNT_L(port->id)); - dev->stats.rx_len[i++] += val; + data += val; + dev->stats.rx_len[i] = max(data, dev->stats.rx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_L64_CNT_H(port->id)); - dev->stats.rx_len[i] += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_L64_CNT_L(port->id)); - dev->stats.rx_len[i++] += val; + data += val; + dev->stats.rx_len[i] = max(data, dev->stats.rx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_L127_CNT_H(port->id)); - dev->stats.rx_len[i] += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_L127_CNT_L(port->id)); - dev->stats.rx_len[i++] += val; + data += val; + dev->stats.rx_len[i] = max(data, dev->stats.rx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_L255_CNT_H(port->id)); - dev->stats.rx_len[i] += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_L255_CNT_L(port->id)); - dev->stats.rx_len[i++] += val; + data += val; + dev->stats.rx_len[i] = max(data, dev->stats.rx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_L511_CNT_H(port->id)); - dev->stats.rx_len[i] += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_L511_CNT_L(port->id)); - dev->stats.rx_len[i++] += val; + data += val; + dev->stats.rx_len[i] = max(data, dev->stats.rx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_L1023_CNT_H(port->id)); - dev->stats.rx_len[i] += ((u64)val << 32); + data = (u64)val << 32; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_L1023_CNT_L(port->id)); - dev->stats.rx_len[i++] += val; + data += val; + dev->stats.rx_len[i] = max(data, dev->stats.rx_len[i]); + i++; val = airoha_fe_rr(eth, REG_FE_GDM_RX_ETH_LONG_CNT(port->id)); - dev->stats.rx_len[i++] += val; + dev->stats.rx_len[i] += (u32)(val - dev->stats.mib_prev.rx_long); + dev->stats.mib_prev.rx_long = val; u64_stats_update_end(&dev->stats.syncp); -} - -static void airoha_update_hw_stats(struct airoha_gdm_dev *dev) -{ - struct airoha_gdm_port *port = dev->port; - int i; - - spin_lock(&port->stats_lock); - - for (i = 0; i < ARRAY_SIZE(port->devs); i++) { - if (port->devs[i]) - airoha_dev_get_hw_stats(port->devs[i]); - } - - /* Reset MIB counters */ - airoha_fe_set(dev->eth, REG_FE_GDM_MIB_CLEAR(port->id), - FE_GDM_MIB_RX_CLEAR_MASK | FE_GDM_MIB_TX_CLEAR_MASK); spin_unlock(&port->stats_lock); } @@ -2504,8 +2543,7 @@ static int airoha_tc_setup_qdisc_ets(struct net_device *dev, if (opt->parent == TC_H_ROOT) return -EINVAL; - channel = TC_H_MAJ(opt->handle) >> 16; - channel = channel % AIROHA_NUM_QOS_CHANNELS; + channel = TC_H_MIN(opt->parent) % AIROHA_NUM_QOS_CHANNELS; switch (opt->command) { case TC_ETS_REPLACE: diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index f6d01a8e8da1..fe934f9ffe8a 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -245,6 +245,33 @@ struct airoha_hw_stats { u64 rx_fragment; u64 rx_jabber; u64 rx_len[7]; + + struct { + /* Previous HW register values for 32-bit counter delta + * tracking. Storing the last seen value and accumulating + * (u32)(curr - prev) into the 64-bit software counter + * handles wrap-around transparently via unsigned arithmetic. + * tx_runt64/rx_runt64 hold the running sum of runt deltas. + * These fields are never reported to userspace. + */ + u32 tx_drops; + u32 tx_broadcast; + u32 tx_multicast; + u32 tx_runt; + u32 tx_long; + u64 tx_runt64; + u32 rx_drops; + u32 rx_broadcast; + u32 rx_multicast; + u32 rx_errors; + u32 rx_crc_error; + u32 rx_over_errors; + u32 rx_fragment; + u32 rx_jabber; + u32 rx_runt; + u32 rx_long; + u64 rx_runt64; + } mib_prev; }; enum { diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c index 870d61fdd9c6..b679bed952de 100644 --- a/drivers/net/ethernet/airoha/airoha_npu.c +++ b/drivers/net/ethernet/airoha/airoha_npu.c @@ -168,7 +168,7 @@ static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id, dma_addr_t dma_addr; int ret; - dma_addr = dma_map_single(npu->dev, p, size, DMA_TO_DEVICE); + dma_addr = dma_map_single(npu->dev, p, size, DMA_BIDIRECTIONAL); ret = dma_mapping_error(npu->dev, dma_addr); if (ret) return ret; @@ -191,7 +191,7 @@ static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id, spin_unlock_bh(&npu->cores[core].lock); - dma_unmap_single(npu->dev, dma_addr, size, DMA_TO_DEVICE); + dma_unmap_single(npu->dev, dma_addr, size, DMA_BIDIRECTIONAL); return ret; } diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index e7c78293002a..f6396925722d 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -1659,6 +1659,7 @@ void airoha_ppe_deinit(struct airoha_eth *eth) npu = rcu_replace_pointer(eth->npu, NULL, lockdep_is_held(&flow_offload_mutex)); if (npu) { + synchronize_rcu(); npu->ops.ppe_deinit(npu); airoha_npu_put(npu); } diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c index 097bb092bdb8..eadb4b604fbe 100644 --- a/drivers/net/ethernet/amd/pds_core/adminq.c +++ b/drivers/net/ethernet/amd/pds_core/adminq.c @@ -18,7 +18,13 @@ static int pdsc_process_notifyq(struct pdsc_qcq *qcq) comp = cq_info->comp; eid = le64_to_cpu(comp->event.eid); while (eid > pdsc->last_eid) { - u16 ecode = le16_to_cpu(comp->event.ecode); + u16 ecode; + + /* Order the payload read after the event id, the field the + * driver uses to detect a new completion. + */ + dma_rmb(); + ecode = le16_to_cpu(comp->event.ecode); switch (ecode) { case PDS_EVENT_LINK_CHANGE: @@ -101,6 +107,10 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq) spin_lock_irqsave(&pdsc->adminq_lock, irqflags); comp = cq->info[cq->tail_idx].comp; while (pdsc_color_match(comp->color, cq->done_color)) { + /* Order the payload reads after the color bit, the field the + * driver uses to detect a new completion. + */ + dma_rmb(); q_info = &q->info[q->tail_idx]; q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c index 73b3481220b1..3acafe10a6d5 100644 --- a/drivers/net/ethernet/amd/pds_core/auxbus.c +++ b/drivers/net/ethernet/amd/pds_core/auxbus.c @@ -177,17 +177,21 @@ void pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf, { struct pds_auxiliary_dev *padev; - if (!*pd_ptr) - return; - mutex_lock(&pf->config_lock); + /* A concurrent del may have already torn this device down and + * cleared it. + */ padev = *pd_ptr; + if (!padev) + goto out_unlock; + pds_client_unregister(pf, padev->client_id); auxiliary_device_delete(&padev->aux_dev); auxiliary_device_uninit(&padev->aux_dev); *pd_ptr = NULL; +out_unlock: mutex_unlock(&pf->config_lock); } @@ -210,6 +214,13 @@ int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf, mutex_lock(&pf->config_lock); + /* Nothing to do if the aux device is already present. This also + * guards against a second add overwriting *pd_ptr and leaking the + * first, symmetric with the check in pdsc_auxbus_dev_del(). + */ + if (*pd_ptr) + goto out_unlock; + mask = BIT_ULL(PDSC_S_FW_DEAD) | BIT_ULL(PDSC_S_STOPPING_DRIVER); if (cf->state & mask) { diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 38a2446571af..04ec2569c61c 100644 --- a/drivers/net/ethernet/amd/pds_core/core.c +++ b/drivers/net/ethernet/amd/pds_core/core.c @@ -110,7 +110,6 @@ static void pdsc_qcq_intr_free(struct pdsc *pdsc, struct pdsc_qcq *qcq) return; pdsc_intr_free(pdsc, qcq->intx); - qcq->intx = PDS_CORE_INTR_INDEX_NOT_ASSIGNED; } static int pdsc_qcq_intr_alloc(struct pdsc *pdsc, struct pdsc_qcq *qcq) @@ -145,6 +144,12 @@ void pdsc_qcq_free(struct pdsc *pdsc, struct pdsc_qcq *qcq) pdsc_qcq_intr_free(pdsc, qcq); + /* Drain any work queued by ISR before it was freed above */ + if (qcq->work.func) + cancel_work_sync(&qcq->work); + + qcq->intx = PDS_CORE_INTR_INDEX_NOT_ASSIGNED; + if (qcq->q_base) dma_free_coherent(dev, qcq->q_size, qcq->q_base, qcq->q_base_pa); @@ -304,8 +309,11 @@ err_out: static void pdsc_core_uninit(struct pdsc *pdsc) { - pdsc_qcq_free(pdsc, &pdsc->notifyqcq); + /* Free adminqcq first: its work accesses notifyqcq, so we must + * disable its IRQ and drain its work before freeing notifyqcq. + */ pdsc_qcq_free(pdsc, &pdsc->adminqcq); + pdsc_qcq_free(pdsc, &pdsc->notifyqcq); if (pdsc->kern_dbpage) { iounmap(pdsc->kern_dbpage); @@ -479,8 +487,6 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing) { if (!pdsc->pdev->is_virtfn) pdsc_devcmd_reset(pdsc); - if (pdsc->adminqcq.work.func) - cancel_work_sync(&pdsc->adminqcq.work); pci_clear_master(pdsc->pdev); @@ -533,6 +539,7 @@ static void pdsc_adminq_wait_and_dec_once_unused(struct pdsc *pdsc) dev_dbg_ratelimited(pdsc->dev, "%s: adminq in use\n", __func__); cpu_relax(); + cond_resched(); } } @@ -606,9 +613,10 @@ void pdsc_pci_reset_thread(struct work_struct *work) struct pdsc *pdsc = container_of(work, struct pdsc, pci_reset_work); struct pci_dev *pdev = pdsc->pdev; - pci_dev_get(pdev); - pci_reset_function(pdev); - pci_dev_put(pdev); + /* Use try variant to avoid deadlock with pdsc_remove(). + * If lock is contended, the watchdog timer will retry. + */ + pci_try_reset_function(pdev); } static void pdsc_check_pci_health(struct pdsc *pdsc) diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index 2ea97e1c5939..8adae7b18898 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -90,6 +90,12 @@ int pdsc_dl_flash_update(struct devlink *dl, { struct pdsc *pdsc = devlink_priv(dl); + if (params->component) { + NL_SET_ERR_MSG_MOD(extack, + "Component update not supported by this device"); + return -EOPNOTSUPP; + } + return pdsc_firmware_update(pdsc, params->fw, extack); } diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index 22db78343eb0..8d94a4d70395 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -238,6 +238,10 @@ static int pdsc_init_pf(struct pdsc *pdsc) /* General workqueue and timer, but don't start timer yet */ snprintf(wq_name, sizeof(wq_name), "%s.%d", PDS_CORE_DRV_NAME, pdsc->uid); pdsc->wq = create_singlethread_workqueue(wq_name); + if (!pdsc->wq) { + err = -ENOMEM; + goto err_out_unmap_bars; + } INIT_WORK(&pdsc->health_work, pdsc_health_thread); INIT_WORK(&pdsc->pci_reset_work, pdsc_pci_reset_thread); timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0); @@ -253,7 +257,7 @@ static int pdsc_init_pf(struct pdsc *pdsc) err = pdsc_setup(pdsc, PDSC_SETUP_INIT); if (err) { mutex_unlock(&pdsc->config_lock); - goto err_out_unmap_bars; + goto err_out_shutdown_timer; } err = pdsc_start(pdsc); @@ -305,13 +309,14 @@ err_out_stop: pdsc_stop(pdsc); err_out_teardown: pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING); -err_out_unmap_bars: +err_out_shutdown_timer: timer_shutdown_sync(&pdsc->wdtimer); if (pdsc->wq) destroy_workqueue(pdsc->wq); mutex_destroy(&pdsc->config_lock); mutex_destroy(&pdsc->devcmd_lock); pci_free_irq_vectors(pdsc->pdev); +err_out_unmap_bars: pdsc_unmap_bars(pdsc); err_out_release_regions: pci_release_regions(pdsc->pdev); @@ -435,8 +440,6 @@ static void pdsc_remove(struct pci_dev *pdev) pdsc_auxbus_dev_del(pdsc, pdsc, &pdsc->padev); timer_shutdown_sync(&pdsc->wdtimer); - if (pdsc->wq) - destroy_workqueue(pdsc->wq); mutex_lock(&pdsc->config_lock); set_bit(PDSC_S_STOPPING_DRIVER, &pdsc->state); @@ -444,6 +447,9 @@ static void pdsc_remove(struct pci_dev *pdev) pdsc_stop(pdsc); pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING); mutex_unlock(&pdsc->config_lock); + + if (pdsc->wq) + destroy_workqueue(pdsc->wq); mutex_destroy(&pdsc->config_lock); mutex_destroy(&pdsc->devcmd_lock); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index fa0df6181207..12770af031eb 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -267,9 +267,14 @@ static void xgbe_an37_set(struct xgbe_prv_data *pdata, bool enable, XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_CTRL1, reg); - reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL); - reg |= XGBE_VEND2_MAC_AUTO_SW; - XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL, reg); + if (pdata->an_mode == XGBE_AN_MODE_CL37_SGMII) { + reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL); + if (enable) + reg |= XGBE_VEND2_MAC_AUTO_SW; + else + reg &= ~XGBE_VEND2_MAC_AUTO_SW; + XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL, reg); + } } static void xgbe_an37_restart(struct xgbe_prv_data *pdata) diff --git a/drivers/net/ethernet/broadcom/bnge/bnge.h b/drivers/net/ethernet/broadcom/bnge/bnge.h index f21cff651fd4..4479ccd071f5 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge.h +++ b/drivers/net/ethernet/broadcom/bnge/bnge.h @@ -36,6 +36,7 @@ struct bnge_pf_info { }; #define INVALID_HW_RING_ID ((u16)-1) +#define INVALID_HW_RING_ID_32BIT (U32_MAX) enum { BNGE_FW_CAP_SHORT_CMD = BIT_ULL(0), diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c index 1c9cfec1b633..651c5e783516 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c @@ -1283,7 +1283,7 @@ int bnge_hwrm_stat_ctx_alloc(struct bnge_net *bn) int hwrm_ring_free_send_msg(struct bnge_net *bn, struct bnge_ring_struct *ring, - u32 ring_type, int cmpl_ring_id) + u32 ring_type, u32 cmpl_ring_id) { struct hwrm_ring_free_input *req; struct bnge_dev *bd = bn->bd; @@ -1295,7 +1295,7 @@ int hwrm_ring_free_send_msg(struct bnge_net *bn, req->cmpl_ring = cpu_to_le16(cmpl_ring_id); req->ring_type = ring_type; - req->ring_id = cpu_to_le16(ring->fw_ring_id); + req->ring_id = cpu_to_le32(ring->fw_ring_id); bnge_hwrm_req_hold(bd, req); rc = bnge_hwrm_req_send(bd, req); @@ -1317,7 +1317,7 @@ int hwrm_ring_alloc_send_msg(struct bnge_net *bn, struct hwrm_ring_alloc_output *resp; struct hwrm_ring_alloc_input *req; struct bnge_dev *bd = bn->bd; - u16 ring_id, flags = 0; + u32 ring_id, flags = 0; int rc; rc = bnge_hwrm_req_init(bd, req, HWRM_RING_ALLOC); @@ -1401,7 +1401,7 @@ int hwrm_ring_alloc_send_msg(struct bnge_net *bn, resp = bnge_hwrm_req_hold(bd, req); rc = bnge_hwrm_req_send(bd, req); - ring_id = le16_to_cpu(resp->ring_id); + ring_id = le32_to_cpu(resp->ring_id); bnge_hwrm_req_drop(bd, req); exit: diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h index 3501de7a89b9..bf452e390d5b 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h +++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h @@ -50,7 +50,7 @@ int bnge_hwrm_cfa_l2_set_rx_mask(struct bnge_dev *bd, void bnge_hwrm_stat_ctx_free(struct bnge_net *bn); int bnge_hwrm_stat_ctx_alloc(struct bnge_net *bn); int hwrm_ring_free_send_msg(struct bnge_net *bn, struct bnge_ring_struct *ring, - u32 ring_type, int cmpl_ring_id); + u32 ring_type, u32 cmpl_ring_id); int hwrm_ring_alloc_send_msg(struct bnge_net *bn, struct bnge_ring_struct *ring, u32 ring_type, u32 map_index); diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c index 70768193004c..6f7ef506d4e1 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c @@ -1327,12 +1327,12 @@ err_free_core: return rc; } -u16 bnge_cp_ring_for_rx(struct bnge_rx_ring_info *rxr) +u32 bnge_cp_ring_for_rx(struct bnge_rx_ring_info *rxr) { return rxr->rx_cpr->ring_struct.fw_ring_id; } -u16 bnge_cp_ring_for_tx(struct bnge_tx_ring_info *txr) +u32 bnge_cp_ring_for_tx(struct bnge_tx_ring_info *txr) { return txr->tx_cpr->ring_struct.fw_ring_id; } @@ -1375,12 +1375,12 @@ static void bnge_init_nq_tree(struct bnge_net *bn) struct bnge_nq_ring_info *nqr = &bn->bnapi[i]->nq_ring; struct bnge_ring_struct *ring = &nqr->ring_struct; - ring->fw_ring_id = INVALID_HW_RING_ID; + ring->fw_ring_id = INVALID_HW_RING_ID_32BIT; for (j = 0; j < nqr->cp_ring_count; j++) { struct bnge_cp_ring_info *cpr = &nqr->cp_ring_arr[j]; ring = &cpr->ring_struct; - ring->fw_ring_id = INVALID_HW_RING_ID; + ring->fw_ring_id = INVALID_HW_RING_ID_32BIT; } } } @@ -1637,7 +1637,7 @@ static void bnge_init_one_rx_ring_rxbd(struct bnge_net *bn, ring = &rxr->rx_ring_struct; bnge_init_rxbd_pages(ring, type); - ring->fw_ring_id = INVALID_HW_RING_ID; + ring->fw_ring_id = INVALID_HW_RING_ID_32BIT; } static void bnge_init_one_agg_ring_rxbd(struct bnge_net *bn, @@ -1647,7 +1647,7 @@ static void bnge_init_one_agg_ring_rxbd(struct bnge_net *bn, u32 type; ring = &rxr->rx_agg_ring_struct; - ring->fw_ring_id = INVALID_HW_RING_ID; + ring->fw_ring_id = INVALID_HW_RING_ID_32BIT; if (bnge_is_agg_reqd(bn->bd)) { type = ((u32)BNGE_RX_PAGE_SIZE << RX_BD_LEN_SHIFT) | RX_BD_TYPE_RX_AGG_BD | RX_BD_FLAGS_SOP; @@ -1708,7 +1708,7 @@ static void bnge_init_tx_rings(struct bnge_net *bn) struct bnge_tx_ring_info *txr = &bn->tx_ring[i]; struct bnge_ring_struct *ring = &txr->tx_ring_struct; - ring->fw_ring_id = INVALID_HW_RING_ID; + ring->fw_ring_id = INVALID_HW_RING_ID_32BIT; netif_queue_set_napi(bn->netdev, i, NETDEV_QUEUE_TYPE_TX, &txr->bnapi->napi); @@ -1867,7 +1867,7 @@ static int bnge_hwrm_rx_agg_ring_alloc(struct bnge_net *bn, ring->fw_ring_id); bnge_db_write(bn->bd, &rxr->rx_agg_db, rxr->rx_agg_prod); bnge_db_write(bn->bd, &rxr->rx_db, rxr->rx_prod); - bn->grp_info[grp_idx].agg_fw_ring_id = ring->fw_ring_id; + bn->grp_info[grp_idx].agg_fw_ring_id = (u16)ring->fw_ring_id; return 0; } @@ -1886,7 +1886,7 @@ static int bnge_hwrm_rx_ring_alloc(struct bnge_net *bn, return rc; bnge_set_db(bn, &rxr->rx_db, type, map_idx, ring->fw_ring_id); - bn->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id; + bn->grp_info[map_idx].rx_fw_ring_id = (u16)ring->fw_ring_id; return 0; } @@ -1916,7 +1916,7 @@ static int bnge_hwrm_ring_alloc(struct bnge_net *bn) bnge_set_db(bn, &nqr->nq_db, type, map_idx, ring->fw_ring_id); bnge_db_nq(bn, &nqr->nq_db, nqr->nq_raw_cons); enable_irq(vector); - bn->grp_info[i].nq_fw_ring_id = ring->fw_ring_id; + bn->grp_info[i].nq_fw_ring_id = (u16)ring->fw_ring_id; if (!i) { rc = bnge_hwrm_set_async_event_cr(bd, ring->fw_ring_id); @@ -1986,15 +1986,13 @@ void bnge_fill_hw_rss_tbl(struct bnge_net *bn, struct bnge_vnic_info *vnic) tbl_size = bnge_get_rxfh_indir_size(bd); for (i = 0; i < tbl_size; i++) { - u16 ring_id, j; + u32 j; j = bd->rss_indir_tbl[i]; rxr = &bn->rx_ring[j]; - ring_id = rxr->rx_ring_struct.fw_ring_id; - *ring_tbl++ = cpu_to_le16(ring_id); - ring_id = bnge_cp_ring_for_rx(rxr); - *ring_tbl++ = cpu_to_le16(ring_id); + *ring_tbl++ = cpu_to_le16(rxr->rx_ring_struct.fw_ring_id); + *ring_tbl++ = cpu_to_le16(bnge_cp_ring_for_rx(rxr)); } } @@ -2285,7 +2283,7 @@ static void bnge_disable_int(struct bnge_net *bn) nqr = &bnapi->nq_ring; ring = &nqr->ring_struct; - if (ring->fw_ring_id != INVALID_HW_RING_ID) + if (ring->fw_ring_id != INVALID_HW_RING_ID_32BIT) bnge_db_nq(bn, &nqr->nq_db, nqr->nq_raw_cons); } } @@ -2401,7 +2399,7 @@ static void bnge_hwrm_rx_ring_free(struct bnge_net *bn, u32 grp_idx = rxr->bnapi->index; u32 cmpl_ring_id; - if (ring->fw_ring_id == INVALID_HW_RING_ID) + if (ring->fw_ring_id == INVALID_HW_RING_ID_32BIT) return; cmpl_ring_id = bnge_cp_ring_for_rx(rxr); @@ -2409,7 +2407,7 @@ static void bnge_hwrm_rx_ring_free(struct bnge_net *bn, RING_FREE_REQ_RING_TYPE_RX, close_path ? cmpl_ring_id : INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; + ring->fw_ring_id = INVALID_HW_RING_ID_32BIT; bn->grp_info[grp_idx].rx_fw_ring_id = INVALID_HW_RING_ID; } @@ -2421,14 +2419,14 @@ static void bnge_hwrm_rx_agg_ring_free(struct bnge_net *bn, u32 grp_idx = rxr->bnapi->index; u32 cmpl_ring_id; - if (ring->fw_ring_id == INVALID_HW_RING_ID) + if (ring->fw_ring_id == INVALID_HW_RING_ID_32BIT) return; cmpl_ring_id = bnge_cp_ring_for_rx(rxr); hwrm_ring_free_send_msg(bn, ring, RING_FREE_REQ_RING_TYPE_RX_AGG, close_path ? cmpl_ring_id : INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; + ring->fw_ring_id = INVALID_HW_RING_ID_32BIT; bn->grp_info[grp_idx].agg_fw_ring_id = INVALID_HW_RING_ID; } @@ -2439,14 +2437,14 @@ static void bnge_hwrm_tx_ring_free(struct bnge_net *bn, struct bnge_ring_struct *ring = &txr->tx_ring_struct; u32 cmpl_ring_id; - if (ring->fw_ring_id == INVALID_HW_RING_ID) + if (ring->fw_ring_id == INVALID_HW_RING_ID_32BIT) return; cmpl_ring_id = close_path ? bnge_cp_ring_for_tx(txr) : INVALID_HW_RING_ID; hwrm_ring_free_send_msg(bn, ring, RING_FREE_REQ_RING_TYPE_TX, cmpl_ring_id); - ring->fw_ring_id = INVALID_HW_RING_ID; + ring->fw_ring_id = INVALID_HW_RING_ID_32BIT; } static void bnge_hwrm_cp_ring_free(struct bnge_net *bn, @@ -2455,12 +2453,12 @@ static void bnge_hwrm_cp_ring_free(struct bnge_net *bn, struct bnge_ring_struct *ring; ring = &cpr->ring_struct; - if (ring->fw_ring_id == INVALID_HW_RING_ID) + if (ring->fw_ring_id == INVALID_HW_RING_ID_32BIT) return; hwrm_ring_free_send_msg(bn, ring, RING_FREE_REQ_RING_TYPE_L2_CMPL, INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; + ring->fw_ring_id = INVALID_HW_RING_ID_32BIT; } static void bnge_hwrm_ring_free(struct bnge_net *bn, bool close_path) @@ -2496,11 +2494,11 @@ static void bnge_hwrm_ring_free(struct bnge_net *bn, bool close_path) bnge_hwrm_cp_ring_free(bn, &nqr->cp_ring_arr[j]); ring = &nqr->ring_struct; - if (ring->fw_ring_id != INVALID_HW_RING_ID) { + if (ring->fw_ring_id != INVALID_HW_RING_ID_32BIT) { hwrm_ring_free_send_msg(bn, ring, RING_FREE_REQ_RING_TYPE_NQ, INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; + ring->fw_ring_id = INVALID_HW_RING_ID_32BIT; bn->grp_info[i].nq_fw_ring_id = INVALID_HW_RING_ID; } } diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h index f4636b5b0cf3..d177919c2e11 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h +++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h @@ -630,8 +630,8 @@ struct bnge_l2_filter { refcount_t refcnt; }; -u16 bnge_cp_ring_for_rx(struct bnge_rx_ring_info *rxr); -u16 bnge_cp_ring_for_tx(struct bnge_tx_ring_info *txr); +u32 bnge_cp_ring_for_rx(struct bnge_rx_ring_info *rxr); +u32 bnge_cp_ring_for_tx(struct bnge_tx_ring_info *txr); void bnge_fill_hw_rss_tbl(struct bnge_net *bn, struct bnge_vnic_info *vnic); int bnge_alloc_rx_data(struct bnge_net *bn, struct bnge_rx_ring_info *rxr, u16 prod, gfp_t gfp); diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_rmem.h b/drivers/net/ethernet/broadcom/bnge/bnge_rmem.h index 341c7f81ed09..bb0c79a1ee60 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_rmem.h +++ b/drivers/net/ethernet/broadcom/bnge/bnge_rmem.h @@ -184,7 +184,7 @@ struct bnge_ctx_mem_info { struct bnge_ring_struct { struct bnge_ring_mem_info ring_mem; - u16 fw_ring_id; + u32 fw_ring_id; union { u16 grp_idx; u16 map_idx; /* Used by NQs */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 5c751933da6a..a515c368bac0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -566,6 +566,18 @@ void bnxt_aux_devices_init(struct bnxt *bp) if (!aux_priv) goto next_auxdev; + edev = kzalloc_obj(*edev); + if (!edev) + goto aux_priv_free; + aux_priv->edev = edev; + bnxt_set_edev_info(edev, bp); + + ulp = kzalloc_obj(*ulp); + if (!ulp) + goto edev_free; + edev->ulp_tbl = ulp; + aux_priv->id = idx; + aux_dev = &aux_priv->aux_dev; aux_dev->id = bp->auxdev_id; aux_dev->name = bnxt_aux_devices[idx].name; @@ -573,37 +585,26 @@ void bnxt_aux_devices_init(struct bnxt *bp) aux_dev->dev.release = bnxt_aux_dev_release; rc = auxiliary_device_init(aux_dev); - if (rc) { - kfree(aux_priv); - goto next_auxdev; - } + if (rc) + goto ulp_free; bp->aux_priv[idx] = aux_priv; /* From this point, all cleanup will happen via the .release * callback & any error unwinding will need to include a call * to auxiliary_device_uninit. */ - edev = kzalloc_obj(*edev); - if (!edev) - goto aux_dev_uninit; - - aux_priv->edev = edev; - bnxt_set_edev_info(edev, bp); - - ulp = kzalloc_obj(*ulp); - if (!ulp) - goto aux_dev_uninit; - - edev->ulp_tbl = ulp; bp->edev[idx] = edev; if (idx == BNXT_AUXDEV_RDMA) bp->ulp_num_msix_want = bnxt_set_dflt_ulp_msix(bp); - aux_priv->id = idx; bnxt_auxdev_set_state(bp, idx, BNXT_ADEV_STATE_INIT); continue; -aux_dev_uninit: - auxiliary_device_uninit(aux_dev); +ulp_free: + kfree(ulp); +edev_free: + kfree(edev); +aux_priv_free: + kfree(aux_priv); next_auxdev: if (idx == BNXT_AUXDEV_RDMA) bp->flags &= ~BNXT_FLAG_ROCE_CAP; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 9335703768a9..764d2a09668f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4732,6 +4732,7 @@ static void dpaa2_eth_disconnect_mac(struct dpaa2_eth_priv *priv) dpaa2_mac_disconnect(mac); dpaa2_mac_close(mac); + put_device(&mac->mc_dev->dev); kfree(mac); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 858ba844ac51..dd4f60031d0c 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1560,6 +1560,7 @@ static void dpaa2_switch_port_disconnect_mac(struct ethsw_port_priv *port_priv) dpaa2_mac_disconnect(mac); dpaa2_mac_close(mac); + put_device(&mac->mc_dev->dev); kfree(mac); } diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index fe35703c509e..b8d70c0ecb6c 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -900,22 +900,28 @@ static void dtsec_mac_config(struct phylink_config *config, unsigned int mode, { struct mac_device *mac_dev = fman_config_to_mac(config); struct dtsec_regs __iomem *regs = mac_dev->fman_mac->regs; - u32 tmp; + u32 ecntrl, maccfg2; + + maccfg2 = ioread32be(®s->maccfg2); + maccfg2 &= ~(MACCFG2_NIBBLE_MODE | MACCFG2_BYTE_MODE); switch (state->interface) { case PHY_INTERFACE_MODE_RMII: - tmp = DTSEC_ECNTRL_RMM; + ecntrl = DTSEC_ECNTRL_RMM; + maccfg2 |= MACCFG2_NIBBLE_MODE; break; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: - tmp = DTSEC_ECNTRL_GMIIM | DTSEC_ECNTRL_RPM; + ecntrl = DTSEC_ECNTRL_GMIIM | DTSEC_ECNTRL_RPM; + maccfg2 |= MACCFG2_BYTE_MODE; break; case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_1000BASEX: case PHY_INTERFACE_MODE_2500BASEX: - tmp = DTSEC_ECNTRL_TBIM | DTSEC_ECNTRL_SGMIIM; + ecntrl = DTSEC_ECNTRL_TBIM | DTSEC_ECNTRL_SGMIIM; + maccfg2 |= MACCFG2_BYTE_MODE; break; default: dev_warn(mac_dev->dev, "cannot configure dTSEC for %s\n", @@ -923,7 +929,8 @@ static void dtsec_mac_config(struct phylink_config *config, unsigned int mode, return; } - iowrite32be(tmp, ®s->ecntrl); + iowrite32be(ecntrl, ®s->ecntrl); + iowrite32be(maccfg2, ®s->maccfg2); } static void dtsec_link_up(struct phylink_config *config, struct phy_device *phy, diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 1d66d3834f7e..c280ff35ee77 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -13,6 +13,7 @@ #include <linux/netdevice.h> #include <linux/net_tstamp.h> #include <linux/pci.h> +#include <linux/timer.h> #include <linux/ptp_clock_kernel.h> #include <linux/u64_stats_sync.h> #include <net/page_pool/helpers.h> @@ -41,6 +42,7 @@ /* Interval to schedule a stats report update, 20000ms. */ #define GVE_STATS_REPORT_TIMER_PERIOD 20000 +#define GVE_RX_NAPI_RESCHED_MS 20 /* msecs */ /* Numbers of NIC tx/rx stats in stats report. */ #define NIC_TX_STATS_REPORT_NUM 0 @@ -341,6 +343,7 @@ struct gve_rx_ring { struct xdp_rxq_info xdp_rxq; struct xsk_buff_pool *xsk_pool; struct page_frag_cache page_cache; /* Page cache to allocate XDP frames */ + struct timer_list starvation_timer; /* for queue starvation recovery */ }; /* A TX desc ring entry */ diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 02cba280d81a..8271f731a91f 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -18,6 +18,16 @@ #include <net/tcp.h> #include <net/xdp_sock_drv.h> +static void gve_rx_starvation_timer(struct timer_list *t) +{ + struct gve_rx_ring *rx = timer_container_of(rx, t, starvation_timer); + struct gve_priv *priv = rx->gve; + struct gve_notify_block *block; + + block = &priv->ntfy_blocks[rx->ntfy_id]; + napi_schedule(&block->napi); +} + static void gve_rx_free_hdr_bufs(struct gve_priv *priv, struct gve_rx_ring *rx) { struct device *hdev = &priv->pdev->dev; @@ -120,6 +130,7 @@ void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx) if (rx->dqo.page_pool) page_pool_disable_direct_recycling(rx->dqo.page_pool); + timer_shutdown_sync(&rx->starvation_timer); gve_remove_napi(priv, ntfy_idx); gve_rx_remove_from_block(priv, idx); gve_rx_reset_ring_dqo(priv, idx); @@ -208,8 +219,10 @@ static int gve_rx_alloc_hdr_bufs(struct gve_priv *priv, struct gve_rx_ring *rx, void gve_rx_start_ring_dqo(struct gve_priv *priv, int idx) { int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); + struct gve_rx_ring *rx = &priv->rx[idx]; gve_rx_add_to_block(priv, idx); + timer_setup(&rx->starvation_timer, gve_rx_starvation_timer, 0); gve_add_napi(priv, ntfy_idx, gve_napi_poll_dqo); } @@ -365,6 +378,7 @@ void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx) struct gve_rx_compl_queue_dqo *complq = &rx->dqo.complq; struct gve_rx_buf_queue_dqo *bufq = &rx->dqo.bufq; struct gve_priv *priv = rx->gve; + u32 num_bufs_avail_to_hw; u32 num_avail_slots; u32 num_full_slots; u32 num_posted = 0; @@ -400,6 +414,26 @@ void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx) } rx->fill_cnt += num_posted; + + /* If the queue has fewer than GVE_RX_BUF_THRESH_DQO descriptors + * visible to the hardware, the hardware is in danger of starving + * and cannot trigger interrupts. + * + * We use a threshold of 32 because a single maximum-sized RSC + * packet can consume up to 19 descriptors in the Rx path. Lower + * thresholds (e.g., 8 or 16) would be unsafe as they could cause + * the device to drop/stall on a maximum-sized RSC packet. + * + * Start the timer to periodically reschedule NAPI and recover. + */ + num_bufs_avail_to_hw = + ((bufq->tail & ~(GVE_RX_BUF_THRESH_DQO - 1)) - + bufq->head) & bufq->mask; + + if (num_bufs_avail_to_hw < GVE_RX_BUF_THRESH_DQO) { + mod_timer(&rx->starvation_timer, + jiffies + msecs_to_jiffies(GVE_RX_NAPI_RESCHED_MS)); + } } static void gve_rx_skb_csum(struct sk_buff *skb, diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 18376bcc718a..fc2c47dcfaab 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -594,7 +594,11 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) skb = build_skb(buf, priv->rx_buf_size); if (unlikely(!skb)) { net_dbg_ratelimited("build_skb failed\n"); - goto refill; + /* Retain the slot; return budget so NAPI retries this + * buffer. Refill would overwrite rx_buf[]/rx_phys[] + * and leak them. + */ + return budget; } dma_unmap_single(priv->dev, priv->rx_phys[priv->rx_head], @@ -622,14 +626,15 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) rx++; } -refill: buf = netdev_alloc_frag(priv->rx_buf_size); if (!buf) goto done; phys = dma_map_single(priv->dev, buf, RX_BUF_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(priv->dev, phys)) + if (dma_mapping_error(priv->dev, phys)) { + skb_free_frag(buf); goto done; + } priv->rx_buf[priv->rx_head] = buf; priv->rx_phys[priv->rx_head] = phys; hip04_set_recv_desc(priv, phys); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h index 52ea97c818b8..d9ab94910a2a 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h @@ -104,8 +104,6 @@ struct hinic_dev { u16 num_rss; u16 rss_limit; struct hinic_rss_type rss_type; - u8 *rss_hkey_user; - s32 *rss_indir_user; struct hinic_intr_coal_info *rx_intr_coalesce; struct hinic_intr_coal_info *tx_intr_coalesce; struct hinic_sriov_info sriov_info; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index a8b129ce1b7e..f75e8563f23a 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -1064,17 +1064,6 @@ static int __set_rss_rxfh(struct net_device *netdev, int err; if (indir) { - if (!nic_dev->rss_indir_user) { - nic_dev->rss_indir_user = - kzalloc(sizeof(u32) * HINIC_RSS_INDIR_SIZE, - GFP_KERNEL); - if (!nic_dev->rss_indir_user) - return -ENOMEM; - } - - memcpy(nic_dev->rss_indir_user, indir, - sizeof(u32) * HINIC_RSS_INDIR_SIZE); - err = hinic_rss_set_indir_tbl(nic_dev, nic_dev->rss_tmpl_idx, indir); if (err) @@ -1082,16 +1071,6 @@ static int __set_rss_rxfh(struct net_device *netdev, } if (key) { - if (!nic_dev->rss_hkey_user) { - nic_dev->rss_hkey_user = - kzalloc(HINIC_RSS_KEY_SIZE * 2, GFP_KERNEL); - - if (!nic_dev->rss_hkey_user) - return -ENOMEM; - } - - memcpy(nic_dev->rss_hkey_user, key, HINIC_RSS_KEY_SIZE); - err = hinic_rss_set_template_tbl(nic_dev, nic_dev->rss_tmpl_idx, key); if (err) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index f72bb1aa4067..fc91b6665f90 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -767,6 +767,9 @@ static inline bool ice_is_txtime_ena(const struct ice_tx_ring *ring) struct ice_vsi *vsi = ring->vsi; struct ice_pf *pf = vsi->back; + if (vsi->type != ICE_VSI_PF) + return false; + return test_bit(ring->q_index, pf->txtime_txqs); } diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index c30e27bbfe6e..b069e6c514fb 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -512,9 +512,6 @@ int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf) struct ice_repr *repr; int err; - if (!ice_is_eswitch_mode_switchdev(pf)) - return 0; - repr = ice_repr_create_vf(vf); if (IS_ERR(repr)) return PTR_ERR(repr); diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 310e8fe2925c..08a17ded0ad5 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -2623,7 +2623,7 @@ int ice_init_lag(struct ice_pf *pf) goto free_lport_res; /* associate recipes to profiles */ - for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) { + for (n = 0; n < ICE_MAX_NUM_PROFILES; n++) { err = ice_aq_get_recipe_to_profile(&pf->hw, n, &recipe_bits, NULL); if (err) diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c index f8e69630fb72..3ede4c1a5a8a 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.c +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -2368,6 +2368,9 @@ int ice_parser_profile_init(struct ice_parser_result *rslt, u16 proto_off = 0; u16 off; + if (rslt->ptype >= ICE_FLOW_PTYPE_MAX) + return -EINVAL; + memset(prof, 0, sizeof(*prof)); set_bit(rslt->ptype, prof->ptypes); if (blk == ICE_BLK_SW) { diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index ec3d89d8d4d3..eaec36ab6ae3 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -346,7 +346,7 @@ static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp) return 0; } - return ice_ptp_extend_32b_ts(pf->ptp.cached_phc_time, + return ice_ptp_extend_32b_ts(READ_ONCE(pf->ptp.cached_phc_time), (in_tstamp >> 8) & mask); } @@ -3037,6 +3037,11 @@ void ice_ptp_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) struct ice_ptp *ptp = &pf->ptp; int err; + if (ptp->state == ICE_PTP_UNINIT) { + dev_dbg(ice_pf_to_dev(pf), "PTP was not initialized, skipping rebuild\n"); + return; + } + if (ptp->state == ICE_PTP_READY) { ice_ptp_prepare_for_reset(pf, reset_type); } else if (ptp->state != ICE_PTP_RESETTING) { diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 7e00e091756d..e04de0215596 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -484,12 +484,14 @@ static int ice_start_vfs(struct ice_pf *pf) goto teardown; } - retval = ice_eswitch_attach_vf(pf, vf); - if (retval) { - dev_err(ice_pf_to_dev(pf), "Failed to attach VF %d to eswitch, error %d", - vf->vf_id, retval); - ice_vf_vsi_release(vf); - goto teardown; + if (ice_is_eswitch_mode_switchdev(pf)) { + retval = ice_eswitch_attach_vf(pf, vf); + if (retval) { + dev_err(ice_pf_to_dev(pf), "Failed to attach VF %d to eswitch, error %d", + vf->vf_id, retval); + ice_vf_vsi_release(vf); + goto teardown; + } } set_bit(ICE_VF_STATE_INIT, vf->vf_states); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 4ca1a0602307..c04c5856dad6 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1654,7 +1654,7 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) ret = ipv6_skip_exthdr(skb, exthdr - skb->data, &l4_proto, &frag_off); if (ret < 0) - return -1; + goto checksum_sw_fb; } /* define outer transport */ @@ -1673,11 +1673,7 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) l4.hdr = skb_inner_network_header(skb); break; default: - if (first->tx_flags & ICE_TX_FLAGS_TSO) - return -1; - - skb_checksum_help(skb); - return 0; + goto checksum_sw_fb; } /* compute outer L3 header size */ @@ -1736,7 +1732,7 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) ipv6_skip_exthdr(skb, exthdr - skb->data, &l4_proto, &frag_off); } else { - return -1; + goto checksum_sw_fb; } /* compute inner L3 header size */ @@ -1789,15 +1785,17 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) break; default: - if (first->tx_flags & ICE_TX_FLAGS_TSO) - return -1; - skb_checksum_help(skb); - return 0; + goto checksum_sw_fb; } off->td_cmd |= cmd; off->td_offset |= offset; return 1; + +checksum_sw_fb: + if (first->tx_flags & ICE_TX_FLAGS_TSO) + return -1; + return skb_checksum_help(skb); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 27e4acb1620f..9052e71e9c99 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -812,7 +812,8 @@ void ice_reset_all_vfs(struct ice_pf *pf) } ice_vf_post_vsi_rebuild(vf); - ice_eswitch_attach_vf(pf, vf); + if (ice_is_eswitch_mode_switchdev(pf)) + ice_eswitch_attach_vf(pf, vf); mutex_unlock(&vf->cfg_lock); } diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index be66f9b2e101..dc5ad784f456 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -3555,7 +3555,6 @@ restart: pci_sriov_set_totalvfs(adapter->pdev, idpf_get_max_vfs(adapter)); num_max_vports = idpf_get_max_vports(adapter); - adapter->max_vports = num_max_vports; adapter->vports = kzalloc_objs(*adapter->vports, num_max_vports); if (!adapter->vports) return -ENOMEM; @@ -3576,6 +3575,12 @@ restart: goto err_netdev_alloc; } + /* Set max_vports only after vports, netdevs and vport_config buffers + * are allocated to make sure max_vport bound loops don't end up + * crashing, following allocation errors on init. + */ + adapter->max_vports = num_max_vports; + /* Start the mailbox task before requesting vectors. This will ensure * vector information response from mailbox is handled */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 5dd0591fed99..99d78fc5a2c4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -272,6 +272,7 @@ exit: if (allocated) { pfvf->flags |= OTX2_FLAG_MCAM_ENTRIES_ALLOC; pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT; + pfvf->flags |= OTX2_FLAG_TC_FLOWER_SUPPORT; } if (allocated != count) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 40162b08014d..0b46ec29e64e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -30,6 +30,7 @@ #define OTX2_UNSUPP_LSE_DEPTH GENMASK(6, 4) #define MCAST_INVALID_GRP (-1U) +#define RATE_MANTISSA_BITS 8 static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst, u32 *burst_exp, u32 *burst_mantissa) @@ -66,28 +67,30 @@ static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst, static void otx2_get_egress_rate_cfg(u64 maxrate, u32 *exp, u32 *mantissa, u32 *div_exp) { - u64 tmp; - /* Rate calculation by hardware * * PIR_ADD = ((256 + mantissa) << exp) / 256 * rate = (2 * PIR_ADD) / ( 1 << div_exp) * The resultant rate is in Mbps. + * + * Use div_exp = 0 and compute exp/mantissa for maxrate / 2; the + * leading factor of two yields the full rate. Rates below 2 Mbps + * are floored to the smallest step (exp = 0, mantissa = 0). */ - /* 2Mbps to 100Gbps can be expressed with div_exp = 0. - * Setting this to '0' will ease the calculation of - * exponent and mantissa. - */ *div_exp = 0; - if (maxrate) { - *exp = ilog2(maxrate) ? ilog2(maxrate) - 1 : 0; - tmp = maxrate - rounddown_pow_of_two(maxrate); - if (maxrate < MAX_RATE_MANTISSA) - *mantissa = tmp * 2; - else - *mantissa = tmp / (1ULL << (*exp - 7)); + maxrate = maxrate / 2; + if (!maxrate) { + /* Rates below 2 Mbps map to the smallest step */ + *exp = 0; + *mantissa = 0; + } else { + *exp = ilog2(maxrate); + /* Clear MSB and derive fractional bits */ + maxrate &= ~BIT(*exp); + *mantissa = (maxrate << RATE_MANTISSA_BITS) >> *exp; + } } else { /* Instead of disabling rate limiting, set all values to max */ *exp = MAX_RATE_EXPONENT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 4b86df6d5b9e..00e706e1ede1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -173,6 +173,13 @@ static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, } memcpy(ets->tc_tsa, priv->dcbx.tc_tsa, sizeof(ets->tc_tsa)); + /* Report 0 for non ETS TSA */ + for (i = 0; i < ets->ets_cap; i++) { + if (ets->tc_tx_bw[i] == MLX5E_MAX_BW_ALLOC && + priv->dcbx.tc_tsa[i] != IEEE_8021QAZ_TSA_ETS) + ets->tc_tx_bw[i] = 0; + } + return err; } @@ -317,6 +324,14 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, } } + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_CB_SHAPER) { + netdev_err(netdev, + "Failed to validate ETS: CB Shaper is not supported\n"); + return -EOPNOTSUPP; + } + } + /* Validate Bandwidth Sum */ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index aa8610cedaa8..c1acb9012d3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -211,11 +211,11 @@ static void mlx5e_disable_async_events(struct mlx5e_priv *priv) static int mlx5e_devcom_event_mpv(int event, void *my_data, void *event_data) { - struct mlx5e_priv *slave_priv = my_data; + struct mlx5e_priv *master_priv = event_data; switch (event) { case MPV_DEVCOM_MASTER_UP: - mlx5_devcom_comp_set_ready(slave_priv->devcom, true); + mlx5_devcom_comp_set_ready(master_priv->devcom, true); break; case MPV_DEVCOM_MASTER_DOWN: /* no need for comp set ready false since we unregister after diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c index ba5cce706ea2..9693c74e9b16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c @@ -71,7 +71,7 @@ int esw_egress_acl_vlan_create(struct mlx5_eswitch *esw, flow_act.action = flow_action; vport->egress.allowed_vlan = mlx5_add_flow_rules(vport->egress.acl, spec, - &flow_act, fwd_dest, 0); + &flow_act, fwd_dest, fwd_dest ? 1 : 0); if (IS_ERR(vport->egress.allowed_vlan)) { err = PTR_ERR(vport->egress.allowed_vlan); esw_warn(esw->dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c index 997be91f0a13..7cedc348790d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c @@ -175,6 +175,7 @@ int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index) if (refcount_dec_and_test(&idx_data->usecount)) { xa_erase(&st->idx_xa, st_index); + kfree(idx_data); /* We leave PCI config space as was before, no mkey will refer to it */ } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index ddbe9ca8971d..9f682f6bdb50 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -314,7 +314,7 @@ static int mlx5_query_module_id(struct mlx5_core_dev *dev, int module_num, return -EIO; } - ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0); + ptr = MLX5_ADDR_OF(mcia_reg, out, dwords); *module_id = ptr[0]; @@ -399,7 +399,7 @@ static int mlx5_query_mcia(struct mlx5_core_dev *dev, return -EIO; } - ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0); + ptr = MLX5_ADDR_OF(mcia_reg, out, dwords); memcpy(data, ptr, size); return size; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c index 6d5833479d12..237300b82b91 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c @@ -96,6 +96,9 @@ static int nfp_cpp_resource_find(struct nfp_cpp *cpp, struct nfp_resource *res) res->mutex = nfp_cpp_mutex_alloc(cpp, NFP_RESOURCE_TBL_TARGET, addr, key); + if (!res->mutex) + return -ENOMEM; + res->cpp_id = NFP_CPP_ID(entry.region.cpp_target, entry.region.cpp_action, entry.region.cpp_token); diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h index 9bd6872474c1..03b12d83f6e9 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase.h +++ b/drivers/net/ethernet/realtek/rtase/rtase.h @@ -192,6 +192,12 @@ enum rtase_sw_flag_content { RTASE_SWF_MSIX_ENABLED = BIT(2), }; +enum rtase_parse_result { + RTASE_PARSE_OK, + RTASE_PARSE_SKIP, + RTASE_PARSE_DROP, +}; + #define RSVD_MASK 0x3FFFC000 struct rtase_tx_desc { @@ -363,4 +369,6 @@ struct rtase_private { #define RTASE_MSS_MASK GENMASK(28, 18) +#define RTASE_MIN_PAD_LEN 47 + #endif /* RTASE_H */ diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c index 255667775f0e..4168ad9e48ea 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase_main.c +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -61,6 +61,7 @@ #include <linux/pci.h> #include <linux/pm_runtime.h> #include <linux/prefetch.h> +#include <linux/ptp_classify.h> #include <linux/rtnetlink.h> #include <linux/tcp.h> #include <asm/irq.h> @@ -1252,6 +1253,199 @@ static u32 rtase_tx_csum(struct sk_buff *skb, const struct net_device *dev) return csum_cmd; } +static enum rtase_parse_result rtase_get_l3_proto(struct sk_buff *skb, + __be16 *proto, + u32 *network_offset) +{ + struct vlan_hdr *vh, _vh; + struct ethhdr *eh, _eh; + u32 offset = ETH_HLEN; + + eh = skb_header_pointer(skb, 0, sizeof(_eh), &_eh); + if (!eh) + return RTASE_PARSE_DROP; + + *proto = eh->h_proto; + + while (eth_type_vlan(*proto)) { + vh = skb_header_pointer(skb, offset, sizeof(_vh), &_vh); + if (!vh) + return RTASE_PARSE_DROP; + + *proto = vh->h_vlan_encapsulated_proto; + offset += VLAN_HLEN; + } + + *network_offset = offset; + + return RTASE_PARSE_OK; +} + +static bool rtase_pad_to_transport_len(struct sk_buff *skb, + u32 transport_offset, + u32 pad_to_len) +{ + u32 trans_data_len; + u32 pad_len; + + trans_data_len = skb->len - transport_offset; + if (trans_data_len >= pad_to_len) + return true; + + if (skb_is_nonlinear(skb)) { + if (skb_linearize(skb)) + return false; + } + + pad_len = pad_to_len - trans_data_len; + if (__skb_put_padto(skb, skb->len + pad_len, false)) + return false; + + return true; +} + +static enum rtase_parse_result rtase_get_transport_offset(struct sk_buff *skb, + u32 *transport_offset, + u8 *transport_proto, + u32 *pad_to_len) +{ + enum rtase_parse_result ret; + struct ipv6hdr *i6h, _i6h; + struct iphdr *ih, _ih; + bool non_first_frag; + __be16 proto; + u32 offset; + u32 no; + + ret = rtase_get_l3_proto(skb, &proto, &no); + if (ret != RTASE_PARSE_OK) + return ret; + + switch (proto) { + case htons(ETH_P_IP): + ih = skb_header_pointer(skb, no, sizeof(_ih), &_ih); + if (!ih) + return RTASE_PARSE_DROP; + + if (ih->ihl < 5) + return RTASE_PARSE_DROP; + + offset = no + ih->ihl * 4; + if (offset > skb->len) + return RTASE_PARSE_DROP; + + non_first_frag = ntohs(ih->frag_off) & IP_OFFSET; + + if (ih->protocol == IPPROTO_TCP) { + if (skb->len - offset < sizeof(struct tcphdr)) { + if (non_first_frag) { + *transport_offset = offset; + *transport_proto = IPPROTO_TCP; + *pad_to_len = sizeof(struct tcphdr); + + return RTASE_PARSE_OK; + } + + return RTASE_PARSE_DROP; + } + + return RTASE_PARSE_SKIP; + } + + if (ih->protocol != IPPROTO_UDP) + return RTASE_PARSE_SKIP; + + *transport_offset = offset; + *transport_proto = IPPROTO_UDP; + + if (skb->len - offset < sizeof(struct udphdr)) { + if (non_first_frag) { + *pad_to_len = sizeof(struct udphdr); + + return RTASE_PARSE_OK; + } + + return RTASE_PARSE_DROP; + } + + return RTASE_PARSE_OK; + + case htons(ETH_P_IPV6): + i6h = skb_header_pointer(skb, no, sizeof(_i6h), &_i6h); + if (!i6h) + return RTASE_PARSE_DROP; + + offset = no + sizeof(*i6h); + + if (i6h->nexthdr == IPPROTO_TCP) { + if (skb->len - offset < sizeof(struct tcphdr)) + return RTASE_PARSE_DROP; + + return RTASE_PARSE_SKIP; + } + + if (i6h->nexthdr != IPPROTO_UDP) + return RTASE_PARSE_SKIP; + + if (skb->len - offset < sizeof(struct udphdr)) + return RTASE_PARSE_DROP; + + *transport_offset = offset; + *transport_proto = IPPROTO_UDP; + + return RTASE_PARSE_OK; + + default: + return RTASE_PARSE_SKIP; + } +} + +static bool rtase_skb_pad(struct sk_buff *skb) +{ + enum rtase_parse_result ret; + u32 transport_offset; + __be16 *dest, _dest; + u32 trans_data_len; + u32 pad_to_len = 0; + u8 transport_proto; + u16 dest_port; + + ret = rtase_get_transport_offset(skb, &transport_offset, + &transport_proto, &pad_to_len); + if (ret == RTASE_PARSE_SKIP) { + return true; + } else if (ret == RTASE_PARSE_DROP) { + netdev_dbg(skb->dev, "drop malformed packet\n"); + return false; + } + + if (pad_to_len && + !rtase_pad_to_transport_len(skb, transport_offset, pad_to_len)) + return false; + + if (transport_proto != IPPROTO_UDP) + return true; + + trans_data_len = skb->len - transport_offset; + if (trans_data_len < offsetof(struct udphdr, len) || + trans_data_len >= RTASE_MIN_PAD_LEN) + return true; + + dest = skb_header_pointer(skb, + transport_offset + + offsetof(struct udphdr, dest), + sizeof(_dest), &_dest); + if (!dest) + return true; + + dest_port = ntohs(*dest); + if (dest_port != PTP_EV_PORT && dest_port != PTP_GEN_PORT) + return true; + + return rtase_pad_to_transport_len(skb, transport_offset, + RTASE_MIN_PAD_LEN); +} + static int rtase_xmit_frags(struct rtase_ring *ring, struct sk_buff *skb, u32 opts1, u32 opts2) { @@ -1365,6 +1559,9 @@ static netdev_tx_t rtase_start_xmit(struct sk_buff *skb, opts2 |= rtase_tx_csum(skb, dev); } + if (!rtase_skb_pad(skb)) + goto err_dma_0; + frags = rtase_xmit_frags(ring, skb, opts1, opts2); if (unlikely(frags < 0)) goto err_dma_0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index b8d467ba6d72..4d207f41a43b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -525,6 +525,32 @@ static int intel_set_reg_access(const struct pmc_serdes_regs *regs, int max_regs return ret; } +/* + * Return true if the SerDes lane rate must change to serve @interface. + * If the current rate cannot be determined, reconfigure as before. + */ +static bool intel_serdes_needs_reconfig(struct stmmac_priv *priv, + struct intel_priv_data *intel_priv, + phy_interface_t interface) +{ + u32 cur_rate, want_rate; + int data; + + if (!intel_priv->mdio_adhoc_addr) + return true; + + data = mdiobus_read(priv->mii, intel_priv->mdio_adhoc_addr, + SERDES_GCR0); + if (data < 0) + return true; + + cur_rate = (data & SERDES_RATE_MASK) >> SERDES_RATE_PCIE_SHIFT; + want_rate = interface == PHY_INTERFACE_MODE_2500BASEX ? + SERDES_RATE_PCIE_GEN2 : SERDES_RATE_PCIE_GEN1; + + return cur_rate != want_rate; +} + static int intel_mac_finish(struct net_device *ndev, void *intel_data, unsigned int mode, @@ -536,6 +562,11 @@ static int intel_mac_finish(struct net_device *ndev, int max_regs = 0; int ret = 0; + if (!intel_serdes_needs_reconfig(priv, intel_priv, interface)) { + priv->plat->phy_interface = interface; + return 0; + } + ret = intel_tsn_lane_is_available(ndev, intel_priv); if (ret < 0) { netdev_info(priv->dev, "No TSN lane available to set the registers.\n"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 829a23bdad01..23ffe1adcd0d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -106,6 +106,17 @@ static void dwmac4_dma_init_channel(struct stmmac_priv *priv, ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan)); } +static void dwmac4_dma_deinit_channel(struct stmmac_priv *priv, + void __iomem *ioaddr, u32 chan) +{ + const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs; + u32 value; + + value = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan)); + value &= ~DMA_CHAN_INTR_DEFAULT_MASK; + writel(value, ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan)); +} + static void dwmac410_dma_init_channel(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, u32 chan) @@ -125,6 +136,17 @@ static void dwmac410_dma_init_channel(struct stmmac_priv *priv, ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan)); } +static void dwmac410_dma_deinit_channel(struct stmmac_priv *priv, + void __iomem *ioaddr, u32 chan) +{ + const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs; + u32 value; + + value = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan)); + value &= ~DMA_CHAN_INTR_DEFAULT_MASK_4_10; + writel(value, ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan)); +} + static void dwmac4_dma_init(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg) { @@ -548,6 +570,7 @@ const struct stmmac_dma_ops dwmac4_dma_ops = { .reset = dwmac4_dma_reset, .init = dwmac4_dma_init, .init_chan = dwmac4_dma_init_channel, + .deinit_chan = dwmac4_dma_deinit_channel, .init_rx_chan = dwmac4_dma_init_rx_chan, .init_tx_chan = dwmac4_dma_init_tx_chan, .axi = dwmac4_dma_axi, @@ -577,6 +600,7 @@ const struct stmmac_dma_ops dwmac410_dma_ops = { .reset = dwmac4_dma_reset, .init = dwmac4_dma_init, .init_chan = dwmac410_dma_init_channel, + .deinit_chan = dwmac410_dma_deinit_channel, .init_rx_chan = dwmac4_dma_init_rx_chan, .init_tx_chan = dwmac4_dma_init_tx_chan, .axi = dwmac4_dma_axi, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index f02b434bbd50..52054f31376d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -1370,36 +1370,40 @@ static int dwxgmac2_config_l4_filter(struct mac_device_info *hw, u32 filter_no, value &= ~XGMAC_L4PEN0; } - value &= ~(XGMAC_L4SPM0 | XGMAC_L4SPIM0); - value &= ~(XGMAC_L4DPM0 | XGMAC_L4DPIM0); if (sa) { value |= XGMAC_L4SPM0; if (inv) value |= XGMAC_L4SPIM0; + else + value &= ~XGMAC_L4SPIM0; } else { value |= XGMAC_L4DPM0; if (inv) value |= XGMAC_L4DPIM0; + else + value &= ~XGMAC_L4DPIM0; } ret = dwxgmac2_filter_write(hw, filter_no, XGMAC_L3L4_CTRL, value); if (ret) return ret; - if (sa) { - value = FIELD_PREP(XGMAC_L4SP0, match); + ret = dwxgmac2_filter_read(hw, filter_no, XGMAC_L4_ADDR, &value); + if (ret) + return ret; - ret = dwxgmac2_filter_write(hw, filter_no, XGMAC_L4_ADDR, value); - if (ret) - return ret; + if (sa) { + value &= ~XGMAC_L4SP0; + value |= FIELD_PREP(XGMAC_L4SP0, match); } else { - value = FIELD_PREP(XGMAC_L4DP0, match); - - ret = dwxgmac2_filter_write(hw, filter_no, XGMAC_L4_ADDR, value); - if (ret) - return ret; + value &= ~XGMAC_L4DP0; + value |= FIELD_PREP(XGMAC_L4DP0, match); } + ret = dwxgmac2_filter_write(hw, filter_no, XGMAC_L4_ADDR, value); + if (ret) + return ret; + if (!en) return dwxgmac2_filter_write(hw, filter_no, XGMAC_L3L4_CTRL, 0); diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index e6317b94fff7..04dafec021b4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -170,6 +170,8 @@ struct stmmac_dma_ops { void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg); void (*init_chan)(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, u32 chan); + void (*deinit_chan)(struct stmmac_priv *priv, void __iomem *ioaddr, + u32 chan); void (*init_rx_chan)(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, dma_addr_t phy, u32 chan); @@ -235,6 +237,8 @@ struct stmmac_dma_ops { stmmac_do_void_callback(__priv, dma, init, __args) #define stmmac_init_chan(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, init_chan, __priv, __args) +#define stmmac_deinit_chan(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, deinit_chan, __priv, __args) #define stmmac_init_rx_chan(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, init_rx_chan, __priv, __args) #define stmmac_init_tx_chan(__priv, __args...) \ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 2a0d7eff88d3..151c77713025 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1083,63 +1083,45 @@ static void stmmac_mac_link_up(struct phylink_config *config, old_ctrl = readl(priv->ioaddr + MAC_CTRL_REG); ctrl = old_ctrl & ~priv->hw->link.speed_mask; - if (interface == PHY_INTERFACE_MODE_USXGMII) { - switch (speed) { - case SPEED_10000: - ctrl |= priv->hw->link.xgmii.speed10000; - break; - case SPEED_5000: - ctrl |= priv->hw->link.xgmii.speed5000; - break; - case SPEED_2500: + switch (speed) { + case SPEED_100000: + ctrl |= priv->hw->link.xlgmii.speed100000; + break; + case SPEED_50000: + ctrl |= priv->hw->link.xlgmii.speed50000; + break; + case SPEED_40000: + ctrl |= priv->hw->link.xlgmii.speed40000; + break; + case SPEED_25000: + ctrl |= priv->hw->link.xlgmii.speed25000; + break; + case SPEED_10000: + ctrl |= priv->hw->link.xgmii.speed10000; + break; + case SPEED_5000: + ctrl |= priv->hw->link.xgmii.speed5000; + break; + case SPEED_2500: + if (interface == PHY_INTERFACE_MODE_USXGMII) ctrl |= priv->hw->link.xgmii.speed2500; - break; - default: - return; - } - } else if (interface == PHY_INTERFACE_MODE_XLGMII) { - switch (speed) { - case SPEED_100000: - ctrl |= priv->hw->link.xlgmii.speed100000; - break; - case SPEED_50000: - ctrl |= priv->hw->link.xlgmii.speed50000; - break; - case SPEED_40000: - ctrl |= priv->hw->link.xlgmii.speed40000; - break; - case SPEED_25000: - ctrl |= priv->hw->link.xlgmii.speed25000; - break; - case SPEED_10000: - ctrl |= priv->hw->link.xgmii.speed10000; - break; - case SPEED_2500: - ctrl |= priv->hw->link.speed2500; - break; - case SPEED_1000: - ctrl |= priv->hw->link.speed1000; - break; - default: - return; - } - } else { - switch (speed) { - case SPEED_2500: + else ctrl |= priv->hw->link.speed2500; - break; - case SPEED_1000: - ctrl |= priv->hw->link.speed1000; - break; - case SPEED_100: - ctrl |= priv->hw->link.speed100; - break; - case SPEED_10: - ctrl |= priv->hw->link.speed10; - break; - default: - return; - } + break; + case SPEED_1000: + ctrl |= priv->hw->link.speed1000; + break; + case SPEED_100: + ctrl |= priv->hw->link.speed100; + break; + case SPEED_10: + ctrl |= priv->hw->link.speed10; + break; + default: + netdev_err(priv->dev, + "unsupported speed %s on %s, leaving the MAC disabled\n", + phy_speed_to_str(speed), phy_modes(interface)); + return; } if (priv->plat->fix_mac_speed) @@ -2560,6 +2542,7 @@ static void stmmac_stop_all_dma(struct stmmac_priv *priv) { u8 rx_channels_count = priv->plat->rx_queues_to_use; u8 tx_channels_count = priv->plat->tx_queues_to_use; + u8 dma_csr_ch = max(rx_channels_count, tx_channels_count); u8 chan; for (chan = 0; chan < rx_channels_count; chan++) @@ -2567,6 +2550,9 @@ static void stmmac_stop_all_dma(struct stmmac_priv *priv) for (chan = 0; chan < tx_channels_count; chan++) stmmac_stop_tx_dma(priv, chan); + + for (chan = 0; chan < dma_csr_ch; chan++) + stmmac_deinit_chan(priv, priv->ioaddr, chan); } /** diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index d78652718599..14cabe76e53e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -446,6 +446,7 @@ static int tc_parse_flow_actions(struct stmmac_priv *priv, } #define ETHER_TYPE_FULL_MASK cpu_to_be16(~0) +#define IP_PROTO_FULL_MASK 0xFF static int tc_add_basic_flow(struct stmmac_priv *priv, struct flow_cls_offload *cls, @@ -461,6 +462,37 @@ static int tc_add_basic_flow(struct stmmac_priv *priv, flow_rule_match_basic(rule, &match); + /* Both network proto and transport proto not present in the key */ + if (!match.mask || !(match.mask->n_proto || match.mask->ip_proto)) { + NL_SET_ERR_MSG_MOD(cls->common.extack, + "filter must specify network or transport protocol"); + return -EOPNOTSUPP; + } + + /* If the proto is present in the key and is not full mask */ + if ((match.mask->n_proto && match.mask->n_proto != ETHER_TYPE_FULL_MASK) || + (match.mask->ip_proto && match.mask->ip_proto != IP_PROTO_FULL_MASK)) { + NL_SET_ERR_MSG_MOD(cls->common.extack, + "only full protocol mask is supported"); + return -EOPNOTSUPP; + } + + /* Network proto is present in the key and is not IPv4 */ + if (match.mask->n_proto && match.key->n_proto != cpu_to_be16(ETH_P_IP)) { + NL_SET_ERR_MSG_MOD(cls->common.extack, + "only IPv4 network protocol is supported"); + return -EOPNOTSUPP; + } + + /* Transport proto is present in the key and is not TCP or UDP */ + if (match.mask->ip_proto && + match.key->ip_proto != IPPROTO_TCP && + match.key->ip_proto != IPPROTO_UDP) { + NL_SET_ERR_MSG_MOD(cls->common.extack, + "only TCP and UDP transport protocols are supported"); + return -EOPNOTSUPP; + } + entry->ip_proto = match.key->ip_proto; return 0; } @@ -598,6 +630,8 @@ static int tc_add_flow(struct stmmac_priv *priv, ret = tc_flow_parsers[i].fn(priv, cls, entry); if (!ret) entry->in_use = true; + else if (ret == -EOPNOTSUPP) + return ret; } if (!entry->in_use) @@ -627,6 +661,7 @@ static int tc_del_flow(struct stmmac_priv *priv, entry->in_use = false; entry->cookie = 0; entry->is_l4 = false; + entry->action = 0; return ret; } diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c index affea1a364ef..26d0cfc58ee2 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c @@ -96,11 +96,13 @@ int txgbe_read_eeprom_hostif(struct wx *wx, dword_len = round_up(length, 4) >> 2; for (i = 0; i < dword_len; i++) { + u32 copy_len = min_t(u32, 4, length - i * 4); + value = rd32a(wx, WX_FW2SW_MBOX, i + offset); le32_to_cpus(&value); - memcpy(data, &value, 4); - data += 4; + memcpy(data, &value, copy_len); + data += copy_len; } return 0; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index 20c5a295c6c2..c277863baf67 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -945,6 +945,7 @@ static void txgbe_remove(struct pci_dev *pdev) netdev = wx->netdev; wx_disable_sriov(wx); unregister_netdev(netdev); + txgbe_fdir_filter_exit(wx); timer_shutdown_sync(&wx->service_timer); cancel_work_sync(&wx->service_task); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 396e1a113cd4..72023ebd0e1b 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -43,8 +43,17 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); #define GENEVE_OPT_GRO_HINT_LEN 1 struct geneve_opt_gro_hint { +#if defined(__LITTLE_ENDIAN_BITFIELD) u8 inner_proto_id:2, - nested_is_v6:1; + nested_is_v6:1, + rsvd:5; +#elif defined(__BIG_ENDIAN_BITFIELD) + u8 rsvd:5, + nested_is_v6:1, + inner_proto_id:2; +#else +#error "Please fix <asm/byteorder.h>" +#endif u8 nested_nh_offset; u8 nested_tp_offset; u8 nested_hdr_len; @@ -577,6 +586,7 @@ static int geneve_post_decap_hint(const struct sock *sk, struct sk_buff *skb, struct iphdr *iph; struct udphdr *uh; __be16 p; + int err; hint_off = geneve_sk_gro_hint_off(sk, *geneveh, &p, &len); if (!hint_off) @@ -601,12 +611,20 @@ static int geneve_post_decap_hint(const struct sock *sk, struct sk_buff *skb, !geneve_opt_gro_hint_validate(skb->data, gro_hint))) return -EINVAL; - ipv6h = (void *)skb->data + gro_hint->nested_nh_offset; - iph = (struct iphdr *)ipv6h; total_len = skb->len - gro_hint->nested_nh_offset; if (total_len >= GRO_LEGACY_MAX_SIZE) return -E2BIG; + err = skb_ensure_writable(skb, gro_hint->nested_tp_offset + sizeof(*uh)); + if (unlikely(err)) + return err; + + *geneveh = geneve_hdr(skb); + gro_hint = geneve_opt_gro_hint(*geneveh, hint_off); + + ipv6h = (void *)skb->data + gro_hint->nested_nh_offset; + iph = (struct iphdr *)ipv6h; + /* * After stripping the outer encap, the packet still carries a * tunnel encapsulation: the nested one. @@ -2376,6 +2394,9 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], struct geneve_config cfg; int err; + if (!rtnl_dev_link_net_capable(dev, geneve->net)) + return -EPERM; + /* If the geneve device is configured for metadata (or externally * controlled, for example, OVS), then nothing can be changed. */ diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index a60ef32b35b8..9a12cc53da00 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -669,8 +669,9 @@ static int gtp1u_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) return -1; /* pull GTP and UDP headers */ - skb_pull_data(skb, - sizeof(struct gtp1_header_long) + sizeof(struct udphdr)); + if (!skb_pull_data(skb, sizeof(struct gtp1_header_long) + + sizeof(struct udphdr))) + return -1; gtp_pkt = skb_push(skb, sizeof(struct gtp1u_packet)); memset(gtp_pkt, 0, sizeof(struct gtp1u_packet)); @@ -826,13 +827,17 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) if (!pskb_may_pull(skb, hdrlen)) return -1; + gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr)); + + if (gtp1->flags & GTP1_F_EXTHDR && + gtp_parse_exthdrs(skb, &hdrlen) < 0) + return -1; + if (gtp_inner_proto(skb, hdrlen, &inner_proto) < 0) { netdev_dbg(gtp->dev, "GTP packet does not encapsulate an IP packet\n"); return -1; } - gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr)); - pctx = gtp1_pdp_find(gtp, ntohl(gtp1->tid), gtp_proto_to_family(inner_proto)); if (!pctx) { @@ -840,10 +845,6 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) return 1; } - if (gtp1->flags & GTP1_F_EXTHDR && - gtp_parse_exthdrs(skb, &hdrlen) < 0) - return -1; - return gtp_rx(pctx, skb, hdrlen, gtp->role, inner_proto); } diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index dd89282f0179..ee0e2eb7dbc6 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3615,19 +3615,22 @@ static int macsec_dev_open(struct net_device *dev) ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { err = -EOPNOTSUPP; - goto clear_allmulti; + goto clear_promisc; } ctx.secy = &macsec->secy; err = macsec_offload(ops->mdo_dev_open, &ctx); if (err) - goto clear_allmulti; + goto clear_promisc; } if (netif_carrier_ok(real_dev)) netif_carrier_on(dev); return 0; +clear_promisc: + if (dev->flags & IFF_PROMISC) + dev_set_promiscuity(real_dev, -1); clear_allmulti: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(real_dev, -1); diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c index 6d2bbae7477b..88d9e36cd4a2 100644 --- a/drivers/net/mctp/mctp-i3c.c +++ b/drivers/net/mctp/mctp-i3c.c @@ -731,18 +731,21 @@ static __init int mctp_i3c_mod_init(void) int rc; rc = i3c_register_notifier(&mctp_i3c_notifier); - if (rc < 0) { - i3c_driver_unregister(&mctp_i3c_driver); + if (rc < 0) return rc; - } i3c_for_each_bus_locked(mctp_i3c_bus_add_new, NULL); rc = i3c_driver_register(&mctp_i3c_driver); if (rc < 0) - return rc; + goto err_unregister_notifier; return 0; + +err_unregister_notifier: + i3c_unregister_notifier(&mctp_i3c_notifier); + mctp_i3c_bus_remove_all(); + return rc; } static __exit void mctp_i3c_mod_exit(void) diff --git a/drivers/net/mctp/mctp-serial.c b/drivers/net/mctp/mctp-serial.c index 26c9a33fd636..a5070ffa9a95 100644 --- a/drivers/net/mctp/mctp-serial.c +++ b/drivers/net/mctp/mctp-serial.c @@ -318,7 +318,7 @@ static void mctp_serial_push_header(struct mctp_serial *dev, u8 c) } else { dev->rxlen = c; dev->rxpos = 0; - dev->rxstate = STATE_DATA; + dev->rxstate = c > 0 ? STATE_DATA : STATE_TRAILER; dev->rxfcs = crc_ccitt_byte(dev->rxfcs, c); } break; diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c index a6b777a9c2d9..9a66d693039a 100644 --- a/drivers/net/ovpn/io.c +++ b/drivers/net/ovpn/io.c @@ -142,7 +142,7 @@ void ovpn_decrypt_post(void *data, int ret) } /* keep track of last received authenticated packet for keepalive */ - WRITE_ONCE(peer->last_recv, ktime_get_real_seconds()); + WRITE_ONCE(peer->last_recv, ktime_get_boottime_seconds()); rcu_read_lock(); sock = rcu_dereference(peer->sock); @@ -294,7 +294,7 @@ void ovpn_encrypt_post(void *data, int ret) ovpn_peer_stats_increment_tx(&peer->link_stats, orig_len); /* keep track of last sent packet for keepalive */ - WRITE_ONCE(peer->last_sent, ktime_get_real_seconds()); + WRITE_ONCE(peer->last_sent, ktime_get_boottime_seconds()); /* skb passed down the stack - don't free it */ skb = NULL; err_unlock: diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index a09d61296425..a21d02ac715e 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -26,11 +26,12 @@ static void unlock_ovpn(struct ovpn_priv *ovpn, struct llist_head *release_list) __releases(&ovpn->lock) { - struct ovpn_peer *peer; + struct ovpn_peer *peer, *next; spin_unlock_bh(&ovpn->lock); - llist_for_each_entry(peer, release_list->first, release_entry) { + llist_for_each_entry_safe(peer, next, release_list->first, + release_entry) { ovpn_socket_release(peer); ovpn_peer_put(peer); } @@ -44,7 +45,7 @@ static void unlock_ovpn(struct ovpn_priv *ovpn, */ void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout) { - time64_t now = ktime_get_real_seconds(); + time64_t now = ktime_get_boottime_seconds(); netdev_dbg(peer->ovpn->dev, "scheduling keepalive for peer %u: interval=%u timeout=%u\n", @@ -1167,7 +1168,6 @@ static void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk, ovpn_sock = rcu_access_pointer(peer->sock); if (!ovpn_sock || ovpn_sock->sk != sk) { spin_unlock_bh(&ovpn->lock); - ovpn_peer_put(peer); return; } } @@ -1285,8 +1285,10 @@ static time64_t ovpn_peer_keepalive_work_single(struct ovpn_peer *peer, netdev_dbg(peer->ovpn->dev, "sending keepalive to peer %u\n", peer->id); - if (schedule_work(&peer->keepalive_work)) - ovpn_peer_hold(peer); + if (WARN_ON(!ovpn_peer_hold(peer))) + return 0; + if (!schedule_work(&peer->keepalive_work)) + ovpn_peer_put(peer); } if (next_run1 < next_run2) @@ -1357,7 +1359,7 @@ void ovpn_peer_keepalive_work(struct work_struct *work) { struct ovpn_priv *ovpn = container_of(work, struct ovpn_priv, keepalive_work.work); - time64_t next_run = 0, now = ktime_get_real_seconds(); + time64_t next_run = 0, now = ktime_get_boottime_seconds(); LLIST_HEAD(release_list); spin_lock_bh(&ovpn->lock); diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c index 433bd07a4f1b..0af14055c39a 100644 --- a/drivers/net/ovpn/tcp.c +++ b/drivers/net/ovpn/tcp.c @@ -151,7 +151,8 @@ err: /* take reference for deferred peer deletion. should never fail */ if (WARN_ON(!ovpn_peer_hold(peer))) goto err_nopeer; - schedule_work(&peer->tcp.defer_del_work); + if (!schedule_work(&peer->tcp.defer_del_work)) + ovpn_peer_put(peer); ovpn_dev_dstats_rx_dropped(peer->ovpn->dev); err_nopeer: kfree_skb(skb); @@ -283,7 +284,8 @@ static void ovpn_tcp_send_sock(struct ovpn_peer *peer, struct sock *sk) * stream therefore we abort the connection */ ovpn_peer_hold(peer); - schedule_work(&peer->tcp.defer_del_work); + if (!schedule_work(&peer->tcp.defer_del_work)) + ovpn_peer_put(peer); /* we bail out immediately and keep tx_in_progress set * to true. This way we prevent more TX attempts diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index e69fa2f0a0e8..0337e2bcc012 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -1058,6 +1058,7 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs, /* Reset link_state */ state->link = false; + state->an_complete = false; state->speed = SPEED_UNKNOWN; state->duplex = DUPLEX_UNKNOWN; state->pause = 0; @@ -1069,6 +1070,8 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs, if (ret < 0) return ret; + state->an_complete = ret & DW_VR_MII_AN_STS_C37_ANCMPLT_INTR; + if (ret & DW_VR_MII_C37_ANSGM_SP_LNKSTS) { int speed_value; @@ -1086,34 +1089,13 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs, state->duplex = DUPLEX_FULL; else state->duplex = DUPLEX_HALF; - } else if (ret == DW_VR_MII_AN_STS_C37_ANCMPLT_INTR) { - int speed, duplex; - - state->link = true; - - speed = xpcs_read(xpcs, MDIO_MMD_VEND2, MII_BMCR); - if (speed < 0) - return speed; - - speed &= BMCR_SPEED100 | BMCR_SPEED1000; - if (speed == BMCR_SPEED1000) - state->speed = SPEED_1000; - else if (speed == BMCR_SPEED100) - state->speed = SPEED_100; - else if (speed == 0) - state->speed = SPEED_10; - - duplex = xpcs_read(xpcs, MDIO_MMD_VEND2, MII_ADVERTISE); - if (duplex < 0) - return duplex; - if (duplex & ADVERTISE_1000XFULL) - state->duplex = DUPLEX_FULL; - else if (duplex & ADVERTISE_1000XHALF) - state->duplex = DUPLEX_HALF; + return 0; + } + /* Clear AN complete status or interrupt */ + if (state->an_complete) xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS, 0); - } return 0; } diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 7a578b5aa2ed..f71cffa88406 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -753,7 +753,7 @@ static int m88e1111_config_inband(struct phy_device *phydev, unsigned int modes) err = phy_modify(phydev, MII_M1111_PHY_EXT_SR, MII_M1111_HWCFG_SERIAL_AN_BYPASS, extsr); if (err < 0) - return extsr; + return err; return phy_modify_paged(phydev, MII_MARVELL_FIBER_PAGE, MII_BMCR, BMCR_ANENABLE, bmcr); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 57c68efa5ff8..cacc4c3a37d2 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -184,6 +184,7 @@ struct channel { struct list_head clist; /* link in list of channels per unit */ spinlock_t upl; /* protects `ppp' and 'bridge' */ struct channel __rcu *bridge; /* "bridged" ppp channel */ + struct rcu_head rcu; /* for RCU-deferred free of the channel */ #ifdef CONFIG_PPP_MULTILINK u8 avail; /* flag used in multilink stuff */ u8 had_frag; /* >= 1 fragments have been sent */ @@ -809,7 +810,9 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case PPPIOCSMRU: if (get_user(val, p)) break; + ppp_recv_lock(ppp); ppp->mru = val; + ppp_recv_unlock(ppp); err = 0; break; @@ -830,7 +833,9 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; case PPPIOCGFLAGS: + ppp_lock(ppp); val = ppp->flags | ppp->xstate | ppp->rstate; + ppp_unlock(ppp); if (put_user(val, p)) break; err = 0; @@ -854,7 +859,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case PPPIOCSDEBUG: if (get_user(val, p)) break; - ppp->debug = val; + WRITE_ONCE(ppp->debug, val); err = 0; break; @@ -865,16 +870,16 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; case PPPIOCGIDLE32: - idle32.xmit_idle = (jiffies - ppp->last_xmit) / HZ; - idle32.recv_idle = (jiffies - ppp->last_recv) / HZ; - if (copy_to_user(argp, &idle32, sizeof(idle32))) + idle32.xmit_idle = max(0L, (long)(jiffies - READ_ONCE(ppp->last_xmit))) / HZ; + idle32.recv_idle = max(0L, (long)(jiffies - READ_ONCE(ppp->last_recv))) / HZ; + if (copy_to_user(argp, &idle32, sizeof(idle32))) break; err = 0; break; case PPPIOCGIDLE64: - idle64.xmit_idle = (jiffies - ppp->last_xmit) / HZ; - idle64.recv_idle = (jiffies - ppp->last_recv) / HZ; + idle64.xmit_idle = max(0L, (long)(jiffies - READ_ONCE(ppp->last_xmit))) / HZ; + idle64.recv_idle = max(0L, (long)(jiffies - READ_ONCE(ppp->last_recv))) / HZ; if (copy_to_user(argp, &idle64, sizeof(idle64))) break; err = 0; @@ -915,7 +920,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (copy_to_user(argp, &npi, sizeof(npi))) break; } else { - ppp->npmode[i] = npi.mode; + WRITE_ONCE(ppp->npmode[i], npi.mode); /* we may be able to transmit more packets now (??) */ netif_wake_queue(ppp->dev); } @@ -1453,7 +1458,7 @@ ppp_start_xmit(struct sk_buff *skb, struct net_device *dev) goto outf; /* Drop, accept or reject the packet */ - switch (ppp->npmode[npi]) { + switch (READ_ONCE(ppp->npmode[npi])) { case NPMODE_PASS: break; case NPMODE_QUEUE: @@ -1481,7 +1486,7 @@ ppp_start_xmit(struct sk_buff *skb, struct net_device *dev) outf: kfree_skb(skb); - ++dev->stats.tx_dropped; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -1531,11 +1536,11 @@ ppp_net_siocdevprivate(struct net_device *dev, struct ifreq *ifr, static void ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64) { - stats64->rx_errors = dev->stats.rx_errors; - stats64->tx_errors = dev->stats.tx_errors; - stats64->rx_dropped = dev->stats.rx_dropped; - stats64->tx_dropped = dev->stats.tx_dropped; - stats64->rx_length_errors = dev->stats.rx_length_errors; + stats64->rx_errors = DEV_STATS_READ(dev, rx_errors); + stats64->tx_errors = DEV_STATS_READ(dev, tx_errors); + stats64->rx_dropped = DEV_STATS_READ(dev, rx_dropped); + stats64->tx_dropped = DEV_STATS_READ(dev, tx_dropped); + stats64->rx_length_errors = DEV_STATS_READ(dev, rx_length_errors); dev_fetch_sw_netstats(stats64, dev->tstats); } @@ -1789,7 +1794,7 @@ ppp_prepare_tx_skb(struct ppp *ppp, struct sk_buff **pskb) *(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_OUTBOUND_TAG); if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { - if (ppp->debug & 1) + if (READ_ONCE(ppp->debug) & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: outbound frame " "not passed\n"); @@ -1799,11 +1804,11 @@ ppp_prepare_tx_skb(struct ppp *ppp, struct sk_buff **pskb) /* if this packet passes the active filter, record the time */ if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) - ppp->last_xmit = jiffies; + WRITE_ONCE(ppp->last_xmit, jiffies); skb_pull(skb, 2); #else /* for data packets, record the time */ - ppp->last_xmit = jiffies; + WRITE_ONCE(ppp->last_xmit, jiffies); #endif /* CONFIG_PPP_FILTER */ } @@ -1888,7 +1893,7 @@ ppp_prepare_tx_skb(struct ppp *ppp, struct sk_buff **pskb) drop: kfree_skb(skb); - ++ppp->dev->stats.tx_errors; + DEV_STATS_INC(ppp->dev, tx_errors); return 1; } @@ -2153,9 +2158,9 @@ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) noskb: spin_unlock(&pch->downl); err_linearize: - if (ppp->debug & 1) + if (READ_ONCE(ppp->debug) & 1) netdev_err(ppp->dev, "PPP: no memory (fragment)\n"); - ++ppp->dev->stats.tx_errors; + DEV_STATS_INC(ppp->dev, tx_errors); ++ppp->nxseq; return 1; /* abandon the frame */ } @@ -2328,7 +2333,7 @@ ppp_input(struct ppp_channel *chan, struct sk_buff *skb) if (!ppp_decompress_proto(skb)) { kfree_skb(skb); if (ppp) { - ++ppp->dev->stats.rx_length_errors; + DEV_STATS_INC(ppp->dev, rx_length_errors); ppp_receive_error(ppp); } goto done; @@ -2390,7 +2395,7 @@ ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) static void ppp_receive_error(struct ppp *ppp) { - ++ppp->dev->stats.rx_errors; + DEV_STATS_INC(ppp->dev, rx_errors); if (ppp->vj) slhc_toss(ppp->vj); } @@ -2501,7 +2506,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) *(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_INBOUND_TAG); if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { - if (ppp->debug & 1) + if (READ_ONCE(ppp->debug) & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: inbound frame " "not passed\n"); @@ -2510,14 +2515,14 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) } if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) - ppp->last_recv = jiffies; + WRITE_ONCE(ppp->last_recv, jiffies); __skb_pull(skb, 2); } else #endif /* CONFIG_PPP_FILTER */ - ppp->last_recv = jiffies; + WRITE_ONCE(ppp->last_recv, jiffies); if ((ppp->dev->flags & IFF_UP) == 0 || - ppp->npmode[npi] != NPMODE_PASS) { + READ_ONCE(ppp->npmode[npi]) != NPMODE_PASS) { kfree_skb(skb); } else { /* chop off protocol */ @@ -2657,7 +2662,7 @@ ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) */ if (seq_before(seq, ppp->nextseq)) { kfree_skb(skb); - ++ppp->dev->stats.rx_dropped; + DEV_STATS_INC(ppp->dev, rx_dropped); ppp_receive_error(ppp); return; } @@ -2693,7 +2698,7 @@ ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) if (pskb_may_pull(skb, 2)) ppp_receive_nonmp_frame(ppp, skb); else { - ++ppp->dev->stats.rx_length_errors; + DEV_STATS_INC(ppp->dev, rx_length_errors); kfree_skb(skb); ppp_receive_error(ppp); } @@ -2770,7 +2775,7 @@ ppp_mp_reconstruct(struct ppp *ppp) seq = seq_before(minseq, PPP_MP_CB(p)->sequence)? minseq + 1: PPP_MP_CB(p)->sequence; - if (ppp->debug & 1) + if (READ_ONCE(ppp->debug) & 1) netdev_printk(KERN_DEBUG, ppp->dev, "lost frag %u..%u\n", oldseq, seq-1); @@ -2799,7 +2804,7 @@ ppp_mp_reconstruct(struct ppp *ppp) if (lost == 0 && (PPP_MP_CB(p)->BEbits & E) && (PPP_MP_CB(head)->BEbits & B)) { if (len > ppp->mrru + 2) { - ++ppp->dev->stats.rx_length_errors; + DEV_STATS_INC(ppp->dev, rx_length_errors); netdev_printk(KERN_DEBUG, ppp->dev, "PPP: reconstructed packet" " is too long (%d)\n", len); @@ -2819,7 +2824,7 @@ ppp_mp_reconstruct(struct ppp *ppp) struct sk_buff *tmp2; skb_queue_reverse_walk_from_safe(list, p, tmp2) { - if (ppp->debug & 1) + if (READ_ONCE(ppp->debug) & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); @@ -2841,7 +2846,7 @@ ppp_mp_reconstruct(struct ppp *ppp) skb_queue_walk_safe(list, p, tmp) { if (p == head) break; - if (ppp->debug & 1) + if (READ_ONCE(ppp->debug) & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); @@ -2849,12 +2854,12 @@ ppp_mp_reconstruct(struct ppp *ppp) kfree_skb(p); } - if (ppp->debug & 1) + if (READ_ONCE(ppp->debug) & 1) netdev_printk(KERN_DEBUG, ppp->dev, " missed pkts %u..%u\n", ppp->nextseq, PPP_MP_CB(head)->sequence-1); - ++ppp->dev->stats.rx_dropped; + DEV_STATS_INC(ppp->dev, rx_dropped); ppp_receive_error(ppp); } @@ -3160,7 +3165,8 @@ ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound) if (!ppp->rc_state) break; if (ppp->rcomp->decomp_init(ppp->rc_state, dp, len, - ppp->file.index, 0, ppp->mru, ppp->debug)) { + ppp->file.index, 0, ppp->mru, + READ_ONCE(ppp->debug))) { ppp->rstate |= SC_DECOMP_RUN; ppp->rstate &= ~(SC_DC_ERROR | SC_DC_FERROR); } @@ -3169,7 +3175,8 @@ ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound) if (!ppp->xc_state) break; if (ppp->xcomp->comp_init(ppp->xc_state, dp, len, - ppp->file.index, 0, ppp->debug)) + ppp->file.index, 0, + READ_ONCE(ppp->debug))) ppp->xstate |= SC_COMP_RUN; } break; @@ -3321,8 +3328,8 @@ ppp_get_stats(struct ppp *ppp, struct ppp_stats *st) st->p.ppp_opackets += tx_packets; st->p.ppp_obytes += tx_bytes; } - st->p.ppp_ierrors = ppp->dev->stats.rx_errors; - st->p.ppp_oerrors = ppp->dev->stats.tx_errors; + st->p.ppp_ierrors = DEV_STATS_READ(ppp->dev, rx_errors); + st->p.ppp_oerrors = DEV_STATS_READ(ppp->dev, tx_errors); if (!vj) return; st->vj.vjs_packets = vj->sls_o_compressed + vj->sls_o_uncompressed; @@ -3562,6 +3569,18 @@ ppp_disconnect_channel(struct channel *pch) return err; } +/* Purge after the grace period: a late ppp_input() may still queue an + * skb on pch->file.rq before the last RCU reader drains. + */ +static void ppp_release_channel_free(struct rcu_head *rcu) +{ + struct channel *pch = container_of(rcu, struct channel, rcu); + + skb_queue_purge(&pch->file.xq); + skb_queue_purge(&pch->file.rq); + kfree(pch); +} + /* * Drop a reference to a ppp channel and free its memory if the refcount reaches * zero. @@ -3581,9 +3600,7 @@ static void ppp_release_channel(struct channel *pch) pr_err("ppp: destroying undead channel %p !\n", pch); return; } - skb_queue_purge(&pch->file.xq); - skb_queue_purge(&pch->file.rq); - kfree(pch); + call_rcu(&pch->rcu, ppp_release_channel_free); } static void __exit ppp_cleanup(void) @@ -3596,6 +3613,7 @@ static void __exit ppp_cleanup(void) device_destroy(&ppp_class, MKDEV(PPP_MAJOR, 0)); class_unregister(&ppp_class); unregister_pernet_device(&ppp_net_ops); + rcu_barrier(); /* wait for RCU callbacks before module unload */ } /* diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 4a018acb5262..6874a1a8edaf 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -825,6 +825,7 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m, dev_hard_header(skb, dev, ETH_P_PPP_SES, po->pppoe_pa.remote, NULL, total_len); + ph = pppoe_hdr(skb); memcpy(ph, &hdr, sizeof(struct pppoe_hdr)); ph->length = htons(total_len); diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 820e1a8fc956..faae711cf793 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -693,6 +693,8 @@ static void slip_receive_buf(struct tty_struct *tty, const u8 *cp, const u8 *fp, if (!sl || sl->magic != SLIP_MAGIC || !netif_running(sl->dev)) return; + spin_lock_bh(&sl->lock); + /* Read the characters out of the buffer */ while (count--) { if (fp && *fp++) { @@ -708,6 +710,8 @@ static void slip_receive_buf(struct tty_struct *tty, const u8 *cp, const u8 *fp, #endif slip_unesc(sl, *cp++); } + + spin_unlock_bh(&sl->lock); } /************************************ diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 40522afc0532..f8df83f9965d 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1530,7 +1530,11 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb, struct ipv6hdr *ipv6; struct tcphdr *tcp; } hdr; - BUG_ON(gdesc->rcd.tcp == 0); + + /* v4/v6/tcp then describe the inner header, which we can't locate. */ + if ((le32_to_cpu(gdesc->dword[0]) & (1UL << VMXNET3_RCD_HDR_INNER_SHIFT)) || + gdesc->rcd.tcp == 0) + return 0; maplen = skb_headlen(skb); if (unlikely(sizeof(struct iphdr) + sizeof(struct tcphdr) > maplen)) @@ -1544,15 +1548,21 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb, hdr.eth = eth_hdr(skb); if (gdesc->rcd.v4) { - BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP) && - hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IP)); + if (hdr.eth->h_proto != htons(ETH_P_IP) && + hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IP)) + return 0; + hdr.ptr += hlen; - BUG_ON(hdr.ipv4->protocol != IPPROTO_TCP); + if (hdr.ipv4->protocol != IPPROTO_TCP) + return 0; + hlen = hdr.ipv4->ihl << 2; hdr.ptr += hdr.ipv4->ihl << 2; } else if (gdesc->rcd.v6) { - BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6) && - hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IPV6)); + if (hdr.eth->h_proto != htons(ETH_P_IPV6) && + hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IPV6)) + return 0; + hdr.ptr += hlen; /* Use an estimated value, since we also need to handle * TSO case. diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 67c367cc5662..d834a4865aec 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -4421,6 +4421,9 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct vxlan_rdst *dst; int err; + if (!rtnl_dev_link_net_capable(dev, vxlan->net)) + return -EPERM; + dst = &vxlan->default_dst; err = vxlan_nl2conf(tb, data, dev, &conf, true, extack); if (err) diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c index 055a4969f593..af7a0d7f95a5 100644 --- a/drivers/net/vxlan/vxlan_mdb.c +++ b/drivers/net/vxlan/vxlan_mdb.c @@ -42,6 +42,7 @@ struct vxlan_mdb_remote { }; #define VXLAN_SGRP_F_DELETE BIT(0) +#define VXLAN_SGRP_F_NEW BIT(1) struct vxlan_mdb_src_entry { struct hlist_node node; @@ -844,6 +845,7 @@ vxlan_mdb_remote_src_add(const struct vxlan_mdb_config *cfg, ent = vxlan_mdb_remote_src_entry_add(remote, &src->addr); if (!ent) return -ENOMEM; + ent->flags |= VXLAN_SGRP_F_NEW; } else if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "Source entry already exists"); return -EEXIST; @@ -853,15 +855,16 @@ vxlan_mdb_remote_src_add(const struct vxlan_mdb_config *cfg, if (err) goto err_src_del; - /* Clear flags in case source entry was marked for deletion as part of - * replace flow. + /* Clear the deletion mark so the entry survives the replace sweep. + * The new mark is retained until the whole operation succeeds. */ - ent->flags = 0; + ent->flags &= ~VXLAN_SGRP_F_DELETE; return 0; err_src_del: - vxlan_mdb_remote_src_entry_del(ent); + if (ent->flags & VXLAN_SGRP_F_NEW) + vxlan_mdb_remote_src_entry_del(ent); return err; } @@ -889,11 +892,19 @@ static int vxlan_mdb_remote_srcs_add(const struct vxlan_mdb_config *cfg, goto err_src_del; } + hlist_for_each_entry(ent, &remote->src_list, node) + ent->flags &= ~VXLAN_SGRP_F_NEW; + return 0; err_src_del: - hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) - vxlan_mdb_remote_src_del(cfg->vxlan, &cfg->group, remote, ent); + hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) { + if (ent->flags & VXLAN_SGRP_F_NEW) + vxlan_mdb_remote_src_del(cfg->vxlan, &cfg->group, remote, + ent); + else + ent->flags &= ~VXLAN_SGRP_F_DELETE; + } return err; } @@ -1069,7 +1080,7 @@ vxlan_mdb_remote_srcs_replace(const struct vxlan_mdb_config *cfg, err = vxlan_mdb_remote_srcs_add(cfg, remote, extack); if (err) - goto err_clear_delete; + return err; hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) { if (ent->flags & VXLAN_SGRP_F_DELETE) @@ -1078,11 +1089,6 @@ vxlan_mdb_remote_srcs_replace(const struct vxlan_mdb_config *cfg, } return 0; - -err_clear_delete: - hlist_for_each_entry(ent, &remote->src_list, node) - ent->flags &= ~VXLAN_SGRP_F_DELETE; - return err; } static int vxlan_mdb_remote_replace(const struct vxlan_mdb_config *cfg, diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index d4da88c77112..065c00c12cc1 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -514,7 +514,8 @@ static void wanxl_pci_remove_one(struct pci_dev *pdev) if (card->irq) free_irq(card->irq, card); - wanxl_reset(card); + if (card->plx) + wanxl_reset(card); for (i = 0; i < RX_QUEUE_LENGTH; i++) if (card->rx_skbs[i]) { diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index faac359aa9ac..b3f1b7186721 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -706,6 +706,7 @@ static int ath10k_htt_rx_pop_paddr32_list(struct ath10k_htt *htt, if (!(__le32_to_cpu(rxd_attention->flags) & RX_ATTENTION_FLAGS_MSDU_DONE)) { ath10k_warn(htt->ar, "tried to pop an incomplete frame, oops!\n"); + __skb_queue_purge(list); return -EIO; } } @@ -770,6 +771,7 @@ static int ath10k_htt_rx_pop_paddr64_list(struct ath10k_htt *htt, if (!(__le32_to_cpu(rxd_attention->flags) & RX_ATTENTION_FLAGS_MSDU_DONE)) { ath10k_warn(htt->ar, "tried to pop an incomplete frame, oops!\n"); + __skb_queue_purge(list); return -EIO; } } diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c index f566d699d074..1e1dea485760 100644 --- a/drivers/net/wireless/ath/ath11k/ahb.c +++ b/drivers/net/wireless/ath/ath11k/ahb.c @@ -996,6 +996,7 @@ static int ath11k_ahb_fw_resources_init(struct ath11k_base *ab) ret = ath11k_ahb_setup_msa_resources(ab); if (ret) { ath11k_err(ab, "failed to setup msa resources\n"); + of_node_put(node); return ret; } diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 9e90d8e3f155..8e2abc7b8383 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -4618,6 +4618,9 @@ static void ath11k_hal_rx_msdu_list_get(struct ath11k *ar, msdu_details = &msdu_link->msdu_link[0]; for (i = 0; i < HAL_RX_NUM_MSDU_DESC; i++) { + if (!i && FIELD_GET(BUFFER_ADDR_INFO0_ADDR, + msdu_details[i].buf_addr_info.info0) == 0) + break; if (FIELD_GET(BUFFER_ADDR_INFO0_ADDR, msdu_details[i].buf_addr_info.info0) == 0) { msdu_desc_info = &msdu_details[i - 1].rx_msdu_info; diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c index 35bb9e7a63a2..a163168f3617 100644 --- a/drivers/net/wireless/ath/ath11k/pci.c +++ b/drivers/net/wireless/ath/ath11k/pci.c @@ -199,6 +199,8 @@ static void ath11k_pci_soc_global_reset(struct ath11k_base *ab) val |= PCIE_SOC_GLOBAL_RESET_V; ath11k_pcic_write32(ab, PCIE_SOC_GLOBAL_RESET, val); + /* Flush the posted write to the device */ + ath11k_pcic_read32(ab, PCIE_SOC_GLOBAL_RESET); /* TODO: exact time to sleep is uncertain */ delay = 10; @@ -208,6 +210,8 @@ static void ath11k_pci_soc_global_reset(struct ath11k_base *ab) val &= ~PCIE_SOC_GLOBAL_RESET_V; ath11k_pcic_write32(ab, PCIE_SOC_GLOBAL_RESET, val); + /* Flush the posted write to the device */ + ath11k_pcic_read32(ab, PCIE_SOC_GLOBAL_RESET); mdelay(delay); diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c index 410a7ee076a0..7dc07339b957 100644 --- a/drivers/net/wireless/ath/ath11k/qmi.c +++ b/drivers/net/wireless/ath/ath11k/qmi.c @@ -3294,9 +3294,14 @@ static void ath11k_qmi_driver_event_work(struct work_struct *work) clear_bit(ATH11K_FLAG_CRASH_FLUSH, &ab->dev_flags); clear_bit(ATH11K_FLAG_RECOVERY, &ab->dev_flags); - ath11k_core_qmi_firmware_ready(ab); - set_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags); - + if (!test_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags)) { + ret = ath11k_core_qmi_firmware_ready(ab); + if (ret) { + set_bit(ATH11K_FLAG_QMI_FAIL, &ab->dev_flags); + break; + } + set_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags); + } break; case ATH11K_QMI_EVENT_COLD_BOOT_CAL_DONE: break; diff --git a/drivers/net/wireless/ath/ath12k/dp_peer.c b/drivers/net/wireless/ath/ath12k/dp_peer.c index 47d009a0d61f..a12073afc307 100644 --- a/drivers/net/wireless/ath/ath12k/dp_peer.c +++ b/drivers/net/wireless/ath/ath12k/dp_peer.c @@ -274,11 +274,14 @@ int ath12k_dp_link_peer_rhash_tbl_init(struct ath12k_dp *dp) void ath12k_dp_link_peer_rhash_tbl_destroy(struct ath12k_dp *dp) { - mutex_lock(&dp->link_peer_rhash_tbl_lock); + guard(mutex)(&dp->link_peer_rhash_tbl_lock); + + if (!dp->rhead_peer_addr) + return; + rhashtable_destroy(dp->rhead_peer_addr); kfree(dp->rhead_peer_addr); dp->rhead_peer_addr = NULL; - mutex_unlock(&dp->link_peer_rhash_tbl_lock); } static int ath12k_dp_link_peer_rhash_insert(struct ath12k_dp *dp, @@ -570,6 +573,8 @@ int ath12k_dp_link_peer_assign(struct ath12k_dp *dp, struct ath12k_dp_hw *dp_hw, peerid_index = ath12k_dp_peer_get_peerid_index(dp, peer->peer_id); rcu_assign_pointer(dp_peer->link_peers[peer->link_id], peer); + WRITE_ONCE(dp_peer->link_peers_map, + READ_ONCE(dp_peer->link_peers_map) | BIT(peer->link_id)); rcu_assign_pointer(dp_hw->dp_peers[peerid_index], dp_peer); @@ -632,6 +637,8 @@ void ath12k_dp_link_peer_unassign(struct ath12k_dp *dp, struct ath12k_dp_hw *dp_ peerid_index = ath12k_dp_peer_get_peerid_index(dp, peer->peer_id); rcu_assign_pointer(dp_peer->link_peers[peer->link_id], NULL); + WRITE_ONCE(dp_peer->link_peers_map, + READ_ONCE(dp_peer->link_peers_map) & ~BIT(peer->link_id)); rcu_assign_pointer(dp_hw->dp_peers[peerid_index], NULL); diff --git a/drivers/net/wireless/ath/ath12k/dp_peer.h b/drivers/net/wireless/ath/ath12k/dp_peer.h index f5067e66f1e1..7c9709bf717b 100644 --- a/drivers/net/wireless/ath/ath12k/dp_peer.h +++ b/drivers/net/wireless/ath/ath12k/dp_peer.h @@ -140,6 +140,7 @@ struct ath12k_dp_peer { /* Info used in MMIC verification of * RX fragments */ struct ieee80211_key_conf *keys[WMI_MAX_KEY_INDEX + 1]; + unsigned long link_peers_map; struct ath12k_dp_link_peer __rcu *link_peers[ATH12K_NUM_MAX_LINKS]; struct ath12k_reoq_buf reoq_bufs[IEEE80211_NUM_TIDS + 1]; struct ath12k_dp_rx_tid rx_tid[IEEE80211_NUM_TIDS + 1]; diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c index 06e74124e57e..8fa0e90b4531 100644 --- a/drivers/net/wireless/ath/ath12k/dp_rx.c +++ b/drivers/net/wireless/ath/ath12k/dp_rx.c @@ -1384,10 +1384,9 @@ void ath12k_dp_rx_deliver_msdu(struct ath12k_pdev_dp *dp_pdev, struct napi_struc pubsta = peer ? peer->sta : NULL; - if (pubsta && pubsta->valid_links) { - status->link_valid = 1; - status->link_id = peer->hw_links[rxcb->hw_link_id]; - } + status->link_valid = 0; + if (pubsta && pubsta->valid_links) + ath12k_hw_set_rx_link_id(dp->hw_params, peer, rxcb, status); ath12k_dbg(dp->ab, ATH12K_DBG_DATA, "rx skb %p len %u peer %pM %d %s sn %u %s%s%s%s%s%s%s%s%s%s rate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i mic-err %i amsdu-more %i\n", diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h index d135b2936378..86fb8b719613 100644 --- a/drivers/net/wireless/ath/ath12k/hw.h +++ b/drivers/net/wireless/ath/ath12k/hw.h @@ -13,6 +13,10 @@ #include "wmi.h" #include "hal.h" +struct ath12k_dp_peer; +struct ath12k_skb_rxcb; +struct ieee80211_rx_status; + /* Target configuration defines */ /* Num VDEVS per radio */ @@ -243,6 +247,9 @@ struct ath12k_hw_ops { bool (*dp_srng_is_tx_comp_ring)(int ring_num); bool (*is_frame_link_agnostic)(struct ath12k_link_vif *arvif, struct ieee80211_mgmt *mgmt); + void (*set_rx_link_id)(struct ath12k_dp_peer *dp_peer, + struct ath12k_skb_rxcb *rxcb, + struct ieee80211_rx_status *status); }; static inline @@ -273,6 +280,15 @@ static inline int ath12k_hw_mac_id_to_srng_id(const struct ath12k_hw_params *hw, return 0; } +static inline void ath12k_hw_set_rx_link_id(const struct ath12k_hw_params *hw, + struct ath12k_dp_peer *dp_peer, + struct ath12k_skb_rxcb *rxcb, + struct ieee80211_rx_status *status) +{ + if (hw->hw_ops->set_rx_link_id) + hw->hw_ops->set_rx_link_id(dp_peer, rxcb, status); +} + struct ath12k_fw_ie { __le32 id; __le32 len; diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index af354bef5c0d..51c4df32e716 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -1238,9 +1238,13 @@ void ath12k_mac_peer_cleanup_all(struct ath12k *ar) /* cleanup dp peer */ spin_lock_bh(&dp_hw->peer_lock); dp_peer = peer->dp_peer; - peerid_index = ath12k_dp_peer_get_peerid_index(dp, peer->peer_id); - rcu_assign_pointer(dp_peer->link_peers[peer->link_id], NULL); - rcu_assign_pointer(dp_hw->dp_peers[peerid_index], NULL); + if (dp_peer) { + peerid_index = ath12k_dp_peer_get_peerid_index(dp, peer->peer_id); + rcu_assign_pointer(dp_peer->link_peers[peer->link_id], NULL); + WRITE_ONCE(dp_peer->link_peers_map, + READ_ONCE(dp_peer->link_peers_map) & ~BIT(peer->link_id)); + rcu_assign_pointer(dp_hw->dp_peers[peerid_index], NULL); + } spin_unlock_bh(&dp_hw->peer_lock); ath12k_dp_link_peer_rhash_delete(dp, peer); diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c index d9a22d6afbb0..fee4129ea405 100644 --- a/drivers/net/wireless/ath/ath12k/pci.c +++ b/drivers/net/wireless/ath/ath12k/pci.c @@ -188,6 +188,8 @@ static void ath12k_pci_soc_global_reset(struct ath12k_base *ab) val |= PCIE_SOC_GLOBAL_RESET_V; ath12k_pci_write32(ab, PCIE_SOC_GLOBAL_RESET, val); + /* Flush the posted write to the device */ + ath12k_pci_read32(ab, PCIE_SOC_GLOBAL_RESET); /* TODO: exact time to sleep is uncertain */ delay = 10; @@ -197,6 +199,8 @@ static void ath12k_pci_soc_global_reset(struct ath12k_base *ab) val &= ~PCIE_SOC_GLOBAL_RESET_V; ath12k_pci_write32(ab, PCIE_SOC_GLOBAL_RESET, val); + /* Flush the posted write to the device */ + ath12k_pci_read32(ab, PCIE_SOC_GLOBAL_RESET); mdelay(delay); diff --git a/drivers/net/wireless/ath/ath12k/peer.c b/drivers/net/wireless/ath/ath12k/peer.c index c222bdaa333c..2681a047d4d5 100644 --- a/drivers/net/wireless/ath/ath12k/peer.c +++ b/drivers/net/wireless/ath/ath12k/peer.c @@ -453,6 +453,9 @@ err_free: void ath12k_link_sta_rhash_tbl_destroy(struct ath12k_base *ab) { + if (!ab->rhead_sta_addr) + return; + rhashtable_destroy(ab->rhead_sta_addr); kfree(ab->rhead_sta_addr); ab->rhead_sta_addr = NULL; diff --git a/drivers/net/wireless/ath/ath12k/wifi7/dp_rx.c b/drivers/net/wireless/ath/ath12k/wifi7/dp_rx.c index cb9dd8cb28b6..95d87dd67872 100644 --- a/drivers/net/wireless/ath/ath12k/wifi7/dp_rx.c +++ b/drivers/net/wireless/ath/ath12k/wifi7/dp_rx.c @@ -5,6 +5,7 @@ */ #include "dp_rx.h" +#include "../dp_peer.h" #include "../dp_tx.h" #include "../peer.h" #include "hal_qcn9274.h" @@ -2315,3 +2316,35 @@ ath12k_wifi7_dp_rxdesc_mpdu_valid(struct ath12k_base *ab, return tlv_tag == HAL_RX_MPDU_START; } + +void +ath12k_wifi7_dp_rx_set_link_id_qcn9274(struct ath12k_dp_peer *dp_peer, + struct ath12k_skb_rxcb *rxcb, + struct ieee80211_rx_status *status) +{ + status->link_valid = 1; + status->link_id = dp_peer->hw_links[rxcb->hw_link_id]; +} + +void +ath12k_wifi7_dp_rx_set_link_id_wcn7850(struct ath12k_dp_peer *dp_peer, + struct ath12k_skb_rxcb *rxcb, + struct ieee80211_rx_status *status) +{ + struct ath12k_dp_link_peer *link_peer; + unsigned long links_map; + int i; + + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), + "ath12k set rx link id called without rcu lock"); + + links_map = READ_ONCE(dp_peer->link_peers_map); + for_each_set_bit(i, &links_map, ATH12K_NUM_MAX_LINKS) { + link_peer = rcu_dereference(dp_peer->link_peers[i]); + if (link_peer && link_peer->peer_id == rxcb->peer_id) { + status->link_valid = 1; + status->link_id = link_peer->link_id; + return; + } + } +} diff --git a/drivers/net/wireless/ath/ath12k/wifi7/dp_rx.h b/drivers/net/wireless/ath/ath12k/wifi7/dp_rx.h index 8aa79faf567f..1d3a4788a2dd 100644 --- a/drivers/net/wireless/ath/ath12k/wifi7/dp_rx.h +++ b/drivers/net/wireless/ath/ath12k/wifi7/dp_rx.h @@ -57,4 +57,10 @@ ath12k_wifi7_dp_rxdesc_mpdu_valid(struct ath12k_base *ab, struct hal_rx_desc *rx_desc); int ath12k_wifi7_dp_rx_tid_delete_handler(struct ath12k_base *ab, struct ath12k_dp_rx_tid_rxq *rx_tid); +void ath12k_wifi7_dp_rx_set_link_id_qcn9274(struct ath12k_dp_peer *dp_peer, + struct ath12k_skb_rxcb *rxcb, + struct ieee80211_rx_status *status); +void ath12k_wifi7_dp_rx_set_link_id_wcn7850(struct ath12k_dp_peer *dp_peer, + struct ath12k_skb_rxcb *rxcb, + struct ieee80211_rx_status *status); #endif diff --git a/drivers/net/wireless/ath/ath12k/wifi7/hw.c b/drivers/net/wireless/ath/ath12k/wifi7/hw.c index 3d59fa452ec0..d9fdd2fc8298 100644 --- a/drivers/net/wireless/ath/ath12k/wifi7/hw.c +++ b/drivers/net/wireless/ath/ath12k/wifi7/hw.c @@ -158,6 +158,7 @@ static const struct ath12k_hw_ops qcn9274_ops = { .get_ring_selector = ath12k_wifi7_hw_get_ring_selector_qcn9274, .dp_srng_is_tx_comp_ring = ath12k_wifi7_dp_srng_is_comp_ring_qcn9274, .is_frame_link_agnostic = ath12k_wifi7_is_frame_link_agnostic_qcn9274, + .set_rx_link_id = ath12k_wifi7_dp_rx_set_link_id_qcn9274, }; static const struct ath12k_hw_ops wcn7850_ops = { @@ -168,6 +169,7 @@ static const struct ath12k_hw_ops wcn7850_ops = { .get_ring_selector = ath12k_wifi7_hw_get_ring_selector_wcn7850, .dp_srng_is_tx_comp_ring = ath12k_wifi7_dp_srng_is_comp_ring_wcn7850, .is_frame_link_agnostic = ath12k_wifi7_is_frame_link_agnostic_wcn7850, + .set_rx_link_id = ath12k_wifi7_dp_rx_set_link_id_wcn7850, }; static const struct ath12k_hw_ops qcc2072_ops = { @@ -178,6 +180,7 @@ static const struct ath12k_hw_ops qcc2072_ops = { .get_ring_selector = ath12k_wifi7_hw_get_ring_selector_wcn7850, .dp_srng_is_tx_comp_ring = ath12k_wifi7_dp_srng_is_comp_ring_wcn7850, .is_frame_link_agnostic = ath12k_wifi7_is_frame_link_agnostic_wcn7850, + .set_rx_link_id = ath12k_wifi7_dp_rx_set_link_id_wcn7850, }; #define ATH12K_TX_RING_MASK_0 0x1 diff --git a/drivers/net/wireless/ath/ath6kl/txrx.c b/drivers/net/wireless/ath/ath6kl/txrx.c index 97fdac7237e2..d81825413906 100644 --- a/drivers/net/wireless/ath/ath6kl/txrx.c +++ b/drivers/net/wireless/ath/ath6kl/txrx.c @@ -1723,13 +1723,15 @@ void aggr_recv_addba_req_evt(struct ath6kl_vif *vif, u8 tid_mux, u16 seq_no, rxtid = &aggr_conn->rx_tid[tid]; - if (win_sz < AGGR_WIN_SZ_MIN || win_sz > AGGR_WIN_SZ_MAX) - ath6kl_dbg(ATH6KL_DBG_WLAN_RX, "%s: win_sz %d, tid %d\n", - __func__, win_sz, tid); - if (rxtid->aggr) aggr_delete_tid_state(aggr_conn, tid); + if (win_sz < AGGR_WIN_SZ_MIN || win_sz > AGGR_WIN_SZ_MAX) { + ath6kl_dbg(ATH6KL_DBG_WLAN_RX, "%s: win_sz %d, tid %d\n", + __func__, win_sz, tid); + return; + } + rxtid->seq_next = seq_no; hold_q_size = TID_WINDOW_SZ(win_sz) * sizeof(struct skb_hold_q); rxtid->hold_q = kzalloc(hold_q_size, GFP_KERNEL); @@ -1828,7 +1830,7 @@ void aggr_reset_state(struct aggr_info_conn *aggr_conn) return; if (aggr_conn->timer_scheduled) { - timer_delete(&aggr_conn->timer); + timer_delete_sync(&aggr_conn->timer); aggr_conn->timer_scheduled = false; } diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c index 72611a2ceb9d..2b0c5038ae04 100644 --- a/drivers/net/wireless/ath/ath6kl/wmi.c +++ b/drivers/net/wireless/ath/ath6kl/wmi.c @@ -484,6 +484,18 @@ static int ath6kl_wmi_tx_complete_event_rx(u8 *datap, int len) evt = (struct wmi_tx_complete_event *) datap; + if (len < sizeof(*evt)) { + ath6kl_dbg(ATH6KL_DBG_WMI, "tx complete: invalid len %d\n", + len); + return -EINVAL; + } + + if (len < sizeof(*evt) + evt->num_msg * sizeof(struct tx_complete_msg_v1)) { + ath6kl_dbg(ATH6KL_DBG_WMI, "tx complete: invalid len %d for %u msgs\n", + len, evt->num_msg); + return -EINVAL; + } + ath6kl_dbg(ATH6KL_DBG_WMI, "comp: %d %d %d\n", evt->num_msg, evt->msg_len, evt->msg_type); @@ -862,6 +874,14 @@ static int ath6kl_wmi_connect_event_rx(struct wmi *wmi, u8 *datap, int len, ev = (struct wmi_connect_event *) datap; + if (len < sizeof(*ev) + ev->beacon_ie_len + + ev->assoc_req_len + ev->assoc_resp_len) { + ath6kl_dbg(ATH6KL_DBG_WMI, + "connect event: IE lengths %u+%u+%u exceed buffer %d\n", + ev->beacon_ie_len, ev->assoc_req_len, + ev->assoc_resp_len, len); + return -EINVAL; + } if (vif->nw_type == AP_NETWORK) { /* AP mode start/STA connected event */ struct net_device *dev = vif->ndev; diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 515267f48d80..47f904e7e652 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -1215,15 +1215,10 @@ static int ath9k_hif_request_firmware(struct hif_device_usb *hif_dev, ret = request_firmware_nowait(THIS_MODULE, true, hif_dev->fw_name, &hif_dev->udev->dev, GFP_KERNEL, hif_dev, ath9k_hif_usb_firmware_cb); - if (ret) { + if (ret) dev_err(&hif_dev->udev->dev, "ath9k_htc: Async request for firmware %s failed\n", hif_dev->fw_name); - return ret; - } - - dev_info(&hif_dev->udev->dev, "ath9k_htc: Firmware %s requested\n", - hif_dev->fw_name); return ret; } diff --git a/drivers/net/wireless/ath/carl9170/rx.c b/drivers/net/wireless/ath/carl9170/rx.c index 6833430130f4..0383d5c9698b 100644 --- a/drivers/net/wireless/ath/carl9170/rx.c +++ b/drivers/net/wireless/ath/carl9170/rx.c @@ -150,7 +150,8 @@ static void carl9170_cmd_callback(struct ar9170 *ar, u32 len, void *buffer) spin_lock(&ar->cmd_lock); if (ar->readbuf) { if (len >= 4) - memcpy(ar->readbuf, buffer + 4, len - 4); + memcpy(ar->readbuf, buffer + 4, + min_t(u32, len - 4, ar->readlen)); ar->readbuf = NULL; } @@ -917,7 +918,9 @@ static void carl9170_rx_stream(struct ar9170 *ar, void *buf, unsigned int len) } } - skb_put_data(ar->rx_failover, tbuf, tlen); + skb_put_data(ar->rx_failover, tbuf, + min_t(unsigned int, tlen, + ar->rx_failover_missing)); ar->rx_failover_missing -= tlen; if (ar->rx_failover_missing <= 0) { diff --git a/drivers/net/wireless/ath/carl9170/tx.c b/drivers/net/wireless/ath/carl9170/tx.c index 59caf1e4b158..06aaf281655b 100644 --- a/drivers/net/wireless/ath/carl9170/tx.c +++ b/drivers/net/wireless/ath/carl9170/tx.c @@ -692,7 +692,7 @@ void carl9170_tx_process_status(struct ar9170 *ar, unsigned int i; for (i = 0; i < cmd->hdr.ext; i++) { - if (WARN_ON(i > ((cmd->hdr.len / 2) + 1))) { + if (WARN_ON(i >= (cmd->hdr.len / 2))) { print_hex_dump_bytes("UU:", DUMP_PREFIX_NONE, (void *) cmd, cmd->hdr.len + 4); break; diff --git a/drivers/net/wireless/atmel/at76c50x-usb.c b/drivers/net/wireless/atmel/at76c50x-usb.c index 32e3e09e7680..d9c2809be4ba 100644 --- a/drivers/net/wireless/atmel/at76c50x-usb.c +++ b/drivers/net/wireless/atmel/at76c50x-usb.c @@ -1521,13 +1521,16 @@ static inline int at76_guess_freq(struct at76_priv *priv) if (ieee80211_is_probe_resp(hdr->frame_control)) { el_off = offsetof(struct ieee80211_mgmt, u.probe_resp.variable); - el = ((struct ieee80211_mgmt *)hdr)->u.probe_resp.variable; } else if (ieee80211_is_beacon(hdr->frame_control)) { el_off = offsetof(struct ieee80211_mgmt, u.beacon.variable); - el = ((struct ieee80211_mgmt *)hdr)->u.beacon.variable; } else { goto exit; } + + if (len < el_off) + goto exit; + + el = priv->rx_skb->data + el_off; len -= el_off; el = cfg80211_find_ie(WLAN_EID_DS_PARAMS, el, len); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index d24b80e492e0..869c4872d399 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -911,6 +911,7 @@ int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev) return ret; } switch (sdiodev->func2->device) { + case SDIO_DEVICE_ID_BROADCOM_43752: case SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373: f2_blksz = SDIO_4373_FUNC2_BLOCKSIZE; break; @@ -1069,6 +1070,7 @@ static int brcmf_ops_sdio_probe(struct sdio_func *func, bus_if = kzalloc_obj(*bus_if); if (!bus_if) return -ENOMEM; + mutex_init(&bus_if->bus_reset_lock); sdiodev = kzalloc_obj(*sdiodev); if (!sdiodev) { kfree(bus_if); @@ -1130,6 +1132,14 @@ static void brcmf_ops_sdio_remove(struct sdio_func *func) if (func->num != 1) return; + /* Drain bus_reset before the shared brcmf_sdiod_remove() + * teardown, which the SDIO reset callback also reaches. The + * data worker can arm bus_reset via brcmf_fw_crashed(); cancel + * it first. + */ + brcmf_sdio_cancel_datawork(sdiodev->bus); + brcmf_bus_cancel_reset_work(bus_if); + /* only proceed with rest of cleanup if func 1 */ brcmf_sdiod_remove(sdiodev); @@ -1204,6 +1214,8 @@ static int brcmf_ops_sdio_suspend(struct device *dev) } else { /* power will be cut so remove device, probe again in resume */ brcmf_sdiod_intr_unregister(sdiodev); + brcmf_sdio_cancel_datawork(sdiodev->bus); + brcmf_bus_cancel_reset_work(bus_if); ret = brcmf_sdiod_remove(sdiodev); if (ret) brcmf_err("Failed to remove device on suspend\n"); @@ -1229,6 +1241,8 @@ static int brcmf_ops_sdio_resume(struct device *dev) ret = brcmf_sdiod_probe(sdiodev); if (ret) brcmf_err("Failed to probe device on resume\n"); + else + brcmf_bus_allow_reset_work(bus_if); } else { if (sdiodev->wowl_enabled && sdiodev->settings->bus.sdio.oob_irq_supported) disable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h index fe31051a9e11..9371c1489948 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/firmware.h> #include <linux/device.h> +#include <linux/mutex.h> #include "debug.h" /* IDs of the 6 default common rings of msgbuf protocol */ @@ -179,6 +180,8 @@ struct brcmf_bus { enum brcmf_fwvendor fwvid; bool always_use_fws_queue; bool wowl_supported; + bool removing; /* device removal in progress; quiesce async work */ + struct mutex bus_reset_lock; const struct brcmf_bus_ops *ops; struct brcmf_bus_msgbuf *msgbuf; @@ -186,6 +189,9 @@ struct brcmf_bus { struct list_head list; }; +void brcmf_bus_cancel_reset_work(struct brcmf_bus *bus_if); +void brcmf_bus_allow_reset_work(struct brcmf_bus *bus_if); + /* * callback wrappers */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 0b55d445895f..89f61710a210 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -2146,7 +2146,7 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme) sme->crypto.akm_suites[0]); return -EINVAL; } - } else if (val & (WPA2_AUTH_PSK | WPA2_AUTH_UNSPECIFIED)) { + } else if (val & (WPA2_AUTH_PSK | WPA2_AUTH_UNSPECIFIED | WPA2_AUTH_1X_SHA256)) { switch (sme->crypto.akm_suites[0]) { case WLAN_AKM_SUITE_8021X: val = WPA2_AUTH_UNSPECIFIED; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index ec170647800d..dad6f4563d14 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -1167,6 +1167,35 @@ static int brcmf_revinfo_read(struct seq_file *s, void *data) return 0; } +/* + * Serialize arming from debugfs reset and brcmf_fw_crashed() against + * teardown. The remove path sets ->removing and drains the work while + * holding bus_reset_lock, so a racing armer is either drained or skips it. + */ +static void brcmf_bus_schedule_reset(struct brcmf_bus *bus_if) +{ + mutex_lock(&bus_if->bus_reset_lock); + if (bus_if->drvr && bus_if->drvr->bus_reset.func && !bus_if->removing) + schedule_work(&bus_if->drvr->bus_reset); + mutex_unlock(&bus_if->bus_reset_lock); +} + +void brcmf_bus_cancel_reset_work(struct brcmf_bus *bus_if) +{ + mutex_lock(&bus_if->bus_reset_lock); + bus_if->removing = true; + if (bus_if->drvr) + cancel_work_sync(&bus_if->drvr->bus_reset); + mutex_unlock(&bus_if->bus_reset_lock); +} + +void brcmf_bus_allow_reset_work(struct brcmf_bus *bus_if) +{ + mutex_lock(&bus_if->bus_reset_lock); + bus_if->removing = false; + mutex_unlock(&bus_if->bus_reset_lock); +} + static void brcmf_core_bus_reset(struct work_struct *work) { struct brcmf_pub *drvr = container_of(work, struct brcmf_pub, @@ -1187,7 +1216,7 @@ static ssize_t bus_reset_write(struct file *file, const char __user *user_buf, if (value != 1) return -EINVAL; - schedule_work(&drvr->bus_reset); + brcmf_bus_schedule_reset(drvr->bus_if); return count; } @@ -1417,14 +1446,23 @@ void brcmf_dev_coredump(struct device *dev) void brcmf_fw_crashed(struct device *dev) { struct brcmf_bus *bus_if = dev_get_drvdata(dev); - struct brcmf_pub *drvr = bus_if->drvr; + struct brcmf_pub *drvr; + + /* May fire before brcmf_attach() wires up drvr, or after removal + * has cleared it; guard the derefs below (and the arming gate in + * brcmf_bus_schedule_reset() already checks drvr/->removing). + */ + if (!bus_if) + return; + drvr = bus_if->drvr; + if (!drvr) + return; bphy_err(drvr, "Firmware has halted or crashed\n"); brcmf_dev_coredump(dev); - if (drvr->bus_reset.func) - schedule_work(&drvr->bus_reset); + brcmf_bus_schedule_reset(bus_if); } void brcmf_detach(struct device *dev) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c index ce09d44fa73c..873754be5174 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c @@ -293,6 +293,12 @@ brcmf_notify_auth_frame_rx(struct brcmf_if *ifp, return -EINVAL; } + if (mgmt_frame_len < offsetof(struct ieee80211_mgmt, u)) { + bphy_err(drvr, "Event %s (%d) frame too small. Ignore\n", + brcmf_fweh_event_name(e->event_code), e->event_code); + return -EINVAL; + } + wdev = &ifp->vif->wdev; WARN_ON(!wdev); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 13662aa4b4ea..55f4d7b970f2 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -1383,16 +1383,20 @@ fail: static void brcmf_pcie_release_scratchbuffers(struct brcmf_pciedev_info *devinfo) { - if (devinfo->shared.scratch) + if (devinfo->shared.scratch) { dma_free_coherent(&devinfo->pdev->dev, BRCMF_DMA_D2H_SCRATCH_BUF_LEN, devinfo->shared.scratch, devinfo->shared.scratch_dmahandle); - if (devinfo->shared.ringupd) + devinfo->shared.scratch = NULL; + } + if (devinfo->shared.ringupd) { dma_free_coherent(&devinfo->pdev->dev, BRCMF_DMA_D2H_RINGUPD_BUF_LEN, devinfo->shared.ringupd, devinfo->shared.ringupd_dmahandle); + devinfo->shared.ringupd = NULL; + } } static int brcmf_pcie_init_scratchbuffers(struct brcmf_pciedev_info *devinfo) @@ -2499,6 +2503,7 @@ brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = -ENOMEM; goto fail; } + mutex_init(&bus->bus_reset_lock); bus->msgbuf = kzalloc_obj(*bus->msgbuf); if (!bus->msgbuf) { ret = -ENOMEM; @@ -2594,6 +2599,11 @@ brcmf_pcie_remove(struct pci_dev *pdev) if (devinfo->ci) brcmf_pcie_intr_disable(devinfo); + if (devinfo->irq_allocated) + synchronize_irq(pdev->irq); + + brcmf_bus_cancel_reset_work(bus); + brcmf_detach(&pdev->dev); brcmf_free(&pdev->dev); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 8fb595733b9c..9f7ed1d293a0 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -4465,6 +4465,7 @@ int brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev) bus->sdiodev = sdiodev; sdiodev->bus = bus; skb_queue_head_init(&bus->glom); + INIT_WORK(&bus->datawork, brcmf_sdio_dataworker); bus->txbound = BRCMF_TXBOUND; bus->rxbound = BRCMF_RXBOUND; bus->txminmax = BRCMF_TXMINMAX; @@ -4479,7 +4480,6 @@ int brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev) goto fail; } brcmf_sdiod_freezer_count(sdiodev); - INIT_WORK(&bus->datawork, brcmf_sdio_dataworker); bus->brcmf_wq = wq; /* attempt to attach to the dongle */ @@ -4560,6 +4560,12 @@ fail: return ret; } +void brcmf_sdio_cancel_datawork(struct brcmf_sdio *bus) +{ + if (bus) + cancel_work_sync(&bus->datawork); +} + /* Detach and free everything */ void brcmf_sdio_remove(struct brcmf_sdio *bus) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h index 80180d5c6c87..b93d153a8963 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h @@ -361,6 +361,7 @@ int brcmf_sdiod_remove(struct brcmf_sdio_dev *sdiodev); int brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev); void brcmf_sdio_remove(struct brcmf_sdio *bus); void brcmf_sdio_isr(struct brcmf_sdio *bus, bool in_isr); +void brcmf_sdio_cancel_datawork(struct brcmf_sdio *bus); void brcmf_sdio_wd_timer(struct brcmf_sdio *bus, bool active); void brcmf_sdio_wowl_config(struct device *dev, bool enabled); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c index 0b52f968b907..b41949a9bdc8 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c @@ -1260,6 +1260,7 @@ static int brcmf_usb_probe_cb(struct brcmf_usbdev_info *devinfo, ret = -ENOMEM; goto fail; } + mutex_init(&bus->bus_reset_lock); bus->dev = dev; bus_pub->bus = bus; @@ -1329,6 +1330,8 @@ brcmf_usb_disconnect_cb(struct brcmf_usbdev_info *devinfo) return; brcmf_dbg(USB, "Enter, bus_pub %p\n", devinfo); + brcmf_bus_cancel_reset_work(devinfo->bus_pub.bus); + brcmf_detach(devinfo->dev); brcmf_free(devinfo->dev); kfree(devinfo->bus_pub.bus); diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c index c11428485dcc..2b8a23865bfb 100644 --- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c @@ -6157,6 +6157,8 @@ static int ipw2100_pci_init_one(struct pci_dev *pci_dev, if (err) { printk(KERN_WARNING DRV_NAME "Error calling pci_enable_device.\n"); + free_libipw(dev, 0); + pci_iounmap(pci_dev, ioaddr); return err; } @@ -6169,16 +6171,14 @@ static int ipw2100_pci_init_one(struct pci_dev *pci_dev, if (err) { printk(KERN_WARNING DRV_NAME "Error calling pci_set_dma_mask.\n"); - pci_disable_device(pci_dev); - return err; + goto fail; } err = pci_request_regions(pci_dev, DRV_NAME); if (err) { printk(KERN_WARNING DRV_NAME "Error calling pci_request_regions.\n"); - pci_disable_device(pci_dev); - return err; + goto fail; } /* We disable the RETRY_TIMEOUT register (0x41) to keep diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_rx.c b/drivers/net/wireless/intel/ipw2x00/libipw_rx.c index b7bc94f7abd8..c8841f9b9ad9 100644 --- a/drivers/net/wireless/intel/ipw2x00/libipw_rx.c +++ b/drivers/net/wireless/intel/ipw2x00/libipw_rx.c @@ -414,7 +414,7 @@ int libipw_rx(struct libipw_device *ieee, struct sk_buff *skb, ieee->host_mc_decrypt : ieee->host_decrypt; if (can_be_decrypted) { - if (skb->len >= hdrlen + 3) { + if (skb->len >= hdrlen + 4) { /* Top two-bits of byte 3 are the key index */ keyidx = skb->data[hdrlen + 3] >> 6; } @@ -660,7 +660,7 @@ int libipw_rx(struct libipw_device *ieee, struct sk_buff *skb, int trimlen = 0; /* Top two-bits of byte 3 are the key index */ - if (skb->len >= hdrlen + 3) + if (skb->len >= hdrlen + 4) keyidx = skb->data[hdrlen + 3] >> 6; /* To strip off any security data which appears before the diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c b/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c index 7a04cb120b1b..6080f5f23e69 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c @@ -15,6 +15,7 @@ .non_shared_ant = ANT_B, \ .vht_mu_mimo_supported = true, \ .uhb_supported = true, \ + .unii9_supported = true, \ .eht_supported = true, \ .uhr_supported = true, \ .num_rbds = IWL_NUM_RBDS_EHT, \ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index bf0f851a9075..430a7642e01a 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -865,6 +865,11 @@ int iwl_acpi_get_wgds_table(struct iwl_fw_runtime *fwrt) min_size, max_size, &tbl_rev); if (!IS_ERR(wifi_pkg)) { + if (tbl_rev < 0 || + tbl_rev >= BITS_PER_BYTE * + sizeof(rev_data[idx].revisions)) + continue; + if (!(BIT(tbl_rev) & rev_data[idx].revisions)) continue; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h index 443a9a416325..0172c0747a47 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h @@ -205,6 +205,7 @@ struct iwl_nvm_get_info_phy { #define IWL_NUM_CHANNELS_V1 51 #define IWL_NUM_CHANNELS_V2 110 +#define IWL_NUM_CHANNELS_V3 115 /** * struct iwl_nvm_get_info_regulatory_v1 - regulatory information @@ -219,12 +220,12 @@ struct iwl_nvm_get_info_regulatory_v1 { } __packed; /* REGULATORY_NVM_GET_INFO_REGULATORY_S_VER_1 */ /** - * struct iwl_nvm_get_info_regulatory - regulatory information + * struct iwl_nvm_get_info_regulatory_v2 - regulatory information * @lar_enabled: is LAR enabled * @n_channels: number of valid channels in the array * @channel_profile: regulatory data of this channel */ -struct iwl_nvm_get_info_regulatory { +struct iwl_nvm_get_info_regulatory_v2 { __le32 lar_enabled; __le32 n_channels; __le32 channel_profile[IWL_NUM_CHANNELS_V2]; @@ -245,6 +246,32 @@ struct iwl_nvm_get_info_rsp_v3 { } __packed; /* REGULATORY_NVM_GET_INFO_RSP_API_S_VER_3 */ /** + * struct iwl_nvm_get_info_rsp_v4 - response to get NVM data + * @general: general NVM data + * @mac_sku: data relating to MAC sku + * @phy_sku: data relating to PHY sku + * @regulatory: regulatory data + */ +struct iwl_nvm_get_info_rsp_v4 { + struct iwl_nvm_get_info_general general; + struct iwl_nvm_get_info_sku mac_sku; + struct iwl_nvm_get_info_phy phy_sku; + struct iwl_nvm_get_info_regulatory_v2 regulatory; +} __packed; /* REGULATORY_NVM_GET_INFO_RSP_API_S_VER_4 */ + +/** + * struct iwl_nvm_get_info_regulatory - regulatory information + * @lar_enabled: is LAR enabled + * @n_channels: number of valid channels in the array + * @channel_profile: regulatory data of this channel + */ +struct iwl_nvm_get_info_regulatory { + __le32 lar_enabled; + __le32 n_channels; + __le32 channel_profile[IWL_NUM_CHANNELS_V3]; +} __packed; /* REGULATORY_NVM_GET_INFO_REGULATORY_S_VER_3 */ + +/** * struct iwl_nvm_get_info_rsp - response to get NVM data * @general: general NVM data * @mac_sku: data relating to MAC sku @@ -256,7 +283,7 @@ struct iwl_nvm_get_info_rsp { struct iwl_nvm_get_info_sku mac_sku; struct iwl_nvm_get_info_phy phy_sku; struct iwl_nvm_get_info_regulatory regulatory; -} __packed; /* REGULATORY_NVM_GET_INFO_RSP_API_S_VER_4 */ +} __packed; /* REGULATORY_NVM_GET_INFO_RSP_API_S_VER_5 */ /** * struct iwl_nvm_access_complete_cmd - NVM_ACCESS commands are completed diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h index 08f4cc3ea1c3..ee78371082b0 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2012-2014, 2018-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2026 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -1319,7 +1319,7 @@ struct iwl_scan_offload_match_info { u8 resume_while_scanning; u8 self_recovery; __le16 reserved; - struct iwl_scan_offload_profile_match matches[]; + struct iwl_scan_offload_profile_match matches[IWL_SCAN_MAX_PROFILES_V2]; } __packed; /* SCAN_OFFLOAD_PROFILES_QUERY_RSP_S_VER_3 and * SCAN_OFFLOAD_MATCH_INFO_NOTIFICATION_S_VER_1 */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c index afff8d51ca95..ec0ff58ab312 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright(c) 2020-2025 Intel Corporation + * Copyright(c) 2020-2026 Intel Corporation */ #include "iwl-drv.h" @@ -12,6 +12,7 @@ #include "fw/api/alive.h" #include "fw/uefi.h" #include "fw/img.h" +#include "fw/dbg.h" #define IWL_PNVM_REDUCED_CAP_BIT BIT(25) @@ -26,6 +27,12 @@ static bool iwl_pnvm_complete_fn(struct iwl_notif_wait_data *notif_wait, struct iwl_trans *trans = (struct iwl_trans *)data; struct iwl_pnvm_init_complete_ntfy *pnvm_ntf = (void *)pkt->data; + if (IWL_FW_CHECK(trans, + iwl_rx_packet_payload_len(pkt) < sizeof(*pnvm_ntf), + "Bad notif len: %d\n", + iwl_rx_packet_payload_len(pkt))) + return true; + IWL_DEBUG_FW(trans, "PNVM complete notification received with status 0x%0x\n", le32_to_cpu(pnvm_ntf->status)); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c index 8d9ff36e30f5..1d6d38ee55b4 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c @@ -389,7 +389,7 @@ bool iwl_add_mcc_to_tas_block_list(u16 *list, u8 *size, u16 mcc) if (*size >= IWL_WTAS_BLACK_LIST_MAX) return false; - list[*size++] = mcc; + list[(*size)++] = mcc; return true; } IWL_EXPORT_SYMBOL(iwl_add_mcc_to_tas_block_list); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/smem.c b/drivers/net/wireless/intel/iwlwifi/fw/smem.c index 344ddde85b18..20ed26a1bb00 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/smem.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/smem.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2021, 2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2021, 2025-2026 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -14,9 +14,17 @@ static void iwl_parse_shared_mem_22000(struct iwl_fw_runtime *fwrt, { struct iwl_shared_mem_cfg *mem_cfg = (void *)pkt->data; int i, lmac; - int lmac_num = le32_to_cpu(mem_cfg->lmac_num); - u8 api_ver = iwl_fw_lookup_notif_ver(fwrt->fw, SYSTEM_GROUP, - SHARED_MEM_CFG_CMD, 0); + int lmac_num; + u8 api_ver; + + if (IWL_FW_CHECK(fwrt, iwl_rx_packet_payload_len(pkt) < + offsetofend(struct iwl_shared_mem_cfg, lmac_smem[1]), + "bad shared mem notification size\n")) + return; + + lmac_num = le32_to_cpu(mem_cfg->lmac_num); + api_ver = iwl_fw_lookup_notif_ver(fwrt->fw, SYSTEM_GROUP, + SHARED_MEM_CFG_CMD, 0); /* Note: notification has 3 entries, but we only expect 2 */ if (IWL_FW_CHECK(fwrt, lmac_num > ARRAY_SIZE(fwrt->smem_cfg.lmac), @@ -30,7 +38,7 @@ static void iwl_parse_shared_mem_22000(struct iwl_fw_runtime *fwrt, if (api_ver >= 4 && !IWL_FW_CHECK(fwrt, iwl_rx_packet_payload_len(pkt) < sizeof(*mem_cfg), - "bad shared mem notification size\n")) { + "bad shared mem notification size (v4)\n")) { fwrt->smem_cfg.rxfifo2_control_size = le32_to_cpu(mem_cfg->rxfifo2_control_size); } @@ -53,6 +61,11 @@ static void iwl_parse_shared_mem(struct iwl_fw_runtime *fwrt, struct iwl_shared_mem_cfg_v2 *mem_cfg = (void *)pkt->data; int i; + if (IWL_FW_CHECK(fwrt, iwl_rx_packet_payload_len(pkt) < + offsetof(struct iwl_shared_mem_cfg_v2, rxfifo_addr), + "bad shared mem notification size\n")) + return; + fwrt->smem_cfg.num_lmacs = 1; fwrt->smem_cfg.num_txfifo_entries = ARRAY_SIZE(mem_cfg->txfifo_size); @@ -67,6 +80,11 @@ static void iwl_parse_shared_mem(struct iwl_fw_runtime *fwrt, /* new API has more data, from rxfifo_addr field and on */ if (fw_has_capa(&fwrt->fw->ucode_capa, IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG)) { + if (IWL_FW_CHECK(fwrt, iwl_rx_packet_payload_len(pkt) < + sizeof(*mem_cfg), + "bad shared mem notification size (extend)\n")) + return; + BUILD_BUG_ON(sizeof(fwrt->smem_cfg.internal_txfifo_size) != sizeof(mem_cfg->internal_txfifo_size)); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c index 2ef0a7a920ad..014f22c42f41 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c @@ -700,7 +700,7 @@ int iwl_uefi_get_ppag_table(struct iwl_fw_runtime *fwrt) return -EINVAL; parse_table: - if (!(BIT(data->revision) & valid_rev)) { + if (data->revision >= 32 || !(BIT(data->revision) & valid_rev)) { ret = -EINVAL; IWL_DEBUG_RADIO(fwrt, "Unsupported UEFI PPAG revision:%d\n", diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 6a3539ad7331..3ac7f000ede4 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -415,6 +415,7 @@ struct iwl_mac_cfg { * @vht_mu_mimo_supported: VHT MU-MIMO support * @nvm_type: see &enum iwl_nvm_type * @uhb_supported: ultra high band channels supported + * @unii9_supported: UNII-9 channels supported * @eht_supported: EHT supported * @uhr_supported: UHR supported * @num_rbds: number of receive buffer descriptors to use @@ -450,6 +451,7 @@ struct iwl_rf_cfg { lp_xtal_workaround:1, vht_mu_mimo_supported:1, uhb_supported:1, + unii9_supported:1, eht_supported:1, uhr_supported:1; u8 valid_tx_ant; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index d021b24d04d6..b1a55909f0d4 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -475,6 +475,7 @@ static int iwl_dbg_tlv_parse_bin(struct iwl_trans *trans, const u8 *data, { const struct iwl_ucode_tlv *tlv; u32 tlv_len; + size_t aligned_tlv_len; while (len >= sizeof(*tlv)) { len -= sizeof(*tlv); @@ -487,8 +488,16 @@ static int iwl_dbg_tlv_parse_bin(struct iwl_trans *trans, const u8 *data, len, tlv_len); return -EINVAL; } - len -= ALIGN(tlv_len, 4); - data += sizeof(*tlv) + ALIGN(tlv_len, 4); + + aligned_tlv_len = ALIGN(tlv_len, 4); + if (len < aligned_tlv_len) { + IWL_ERR(trans, "invalid aligned TLV len: %zd/%zu\n", + len, aligned_tlv_len); + return -EINVAL; + } + + len -= aligned_tlv_len; + data += sizeof(*tlv) + aligned_tlv_len; iwl_dbg_tlv_alloc(trans, tlv, true); } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 842586d4fc5c..7f1515dfc5bf 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -492,7 +492,7 @@ static void set_sec_offset(struct iwl_firmware_pieces *pieces, * Gets uCode section from tlv. */ static int iwl_store_ucode_sec(struct fw_img_parsing *img, - const void *data, int size) + const void *data, size_t size) { struct fw_sec *sec; const struct fw_sec_parsing *sec_parse; @@ -501,6 +501,9 @@ static int iwl_store_ucode_sec(struct fw_img_parsing *img, if (WARN_ON(!img || !data)) return -EINVAL; + if (size < sizeof(sec_parse->offset)) + return -EINVAL; + sec_parse = (const struct fw_sec_parsing *)data; alloc_size = sizeof(*img->sec) * (img->sec_counter + 1); @@ -804,6 +807,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, u32 build, paging_mem_size; int num_of_cpus; bool usniffer_req = false; + size_t aligned_tlv_len; if (len < sizeof(*ucode)) { IWL_ERR(drv, "uCode has invalid length: %zd\n", len); @@ -852,8 +856,16 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, len, tlv_len); return -EINVAL; } - len -= ALIGN(tlv_len, 4); - data += sizeof(*tlv) + ALIGN(tlv_len, 4); + + aligned_tlv_len = ALIGN(tlv_len, 4); + if (len < aligned_tlv_len) { + IWL_ERR(drv, "invalid aligned TLV len: %zd/%zu\n", + len, aligned_tlv_len); + return -EINVAL; + } + + len -= aligned_tlv_len; + data += sizeof(*tlv) + aligned_tlv_len; switch (tlv_type) { case IWL_UCODE_TLV_INST: diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index d47b4ae2f486..bd5353fdde81 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -85,16 +85,7 @@ static const u16 iwl_nvm_channels[] = { 149, 153, 157, 161, 165 }; -static const u16 iwl_ext_nvm_channels[] = { - /* 2.4 GHz */ - 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, - /* 5 GHz */ - 36, 40, 44, 48, 52, 56, 60, 64, 68, 72, 76, 80, 84, 88, 92, - 96, 100, 104, 108, 112, 116, 120, 124, 128, 132, 136, 140, 144, - 149, 153, 157, 161, 165, 169, 173, 177, 181 -}; - -static const u16 iwl_uhb_nvm_channels[] = { +static const u16 iwl_unii9_nvm_channels[] = { /* 2.4 GHz */ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, /* 5 GHz */ @@ -105,12 +96,16 @@ static const u16 iwl_uhb_nvm_channels[] = { 1, 5, 9, 13, 17, 21, 25, 29, 33, 37, 41, 45, 49, 53, 57, 61, 65, 69, 73, 77, 81, 85, 89, 93, 97, 101, 105, 109, 113, 117, 121, 125, 129, 133, 137, 141, 145, 149, 153, 157, 161, 165, 169, 173, 177, 181, 185, - 189, 193, 197, 201, 205, 209, 213, 217, 221, 225, 229, 233 + 189, 193, 197, 201, 205, 209, 213, 217, 221, 225, 229, 233, + + /* UNII-9 */ + 237, 241, 245, 249, 253 }; #define IWL_NVM_NUM_CHANNELS ARRAY_SIZE(iwl_nvm_channels) -#define IWL_NVM_NUM_CHANNELS_EXT ARRAY_SIZE(iwl_ext_nvm_channels) -#define IWL_NVM_NUM_CHANNELS_UHB ARRAY_SIZE(iwl_uhb_nvm_channels) +#define IWL_NVM_NUM_CHANNELS_EXT 51 +#define IWL_NVM_NUM_CHANNELS_UHB 110 +#define IWL_NVM_NUM_CHANNELS_UNII9 ARRAY_SIZE(iwl_unii9_nvm_channels) #define NUM_2GHZ_CHANNELS 14 #define NUM_5GHZ_CHANNELS 37 #define FIRST_2GHZ_HT_MINUS 5 @@ -351,12 +346,15 @@ static int iwl_init_channel_map(struct iwl_trans *trans, int num_of_ch; const u16 *nvm_chan; - if (cfg->uhb_supported) { + if (cfg->unii9_supported) { + num_of_ch = IWL_NVM_NUM_CHANNELS_UNII9; + nvm_chan = iwl_unii9_nvm_channels; + } else if (cfg->uhb_supported) { num_of_ch = IWL_NVM_NUM_CHANNELS_UHB; - nvm_chan = iwl_uhb_nvm_channels; + nvm_chan = iwl_unii9_nvm_channels; } else if (cfg->nvm_type == IWL_NVM_EXT) { num_of_ch = IWL_NVM_NUM_CHANNELS_EXT; - nvm_chan = iwl_ext_nvm_channels; + nvm_chan = iwl_unii9_nvm_channels; } else { num_of_ch = IWL_NVM_NUM_CHANNELS; nvm_chan = iwl_nvm_channels; @@ -1441,7 +1439,9 @@ iwl_parse_mei_nvm_data(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg, u8 rx_chains = fw->valid_rx_ant; u8 tx_chains = fw->valid_rx_ant; - if (cfg->uhb_supported) + if (cfg->unii9_supported) + data = kzalloc_flex(*data, channels, IWL_NVM_NUM_CHANNELS_UNII9); + else if (cfg->uhb_supported) data = kzalloc_flex(*data, channels, IWL_NVM_NUM_CHANNELS_UHB); else data = kzalloc_flex(*data, channels, IWL_NVM_NUM_CHANNELS_EXT); @@ -1506,7 +1506,9 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg, u16 lar_config; const __le16 *ch_section; - if (cfg->uhb_supported) + if (cfg->unii9_supported) + data = kzalloc_flex(*data, channels, IWL_NVM_NUM_CHANNELS_UNII9); + else if (cfg->uhb_supported) data = kzalloc_flex(*data, channels, IWL_NVM_NUM_CHANNELS_UHB); else if (cfg->nvm_type != IWL_NVM_EXT) data = kzalloc_flex(*data, channels, IWL_NVM_NUM_CHANNELS); @@ -1727,12 +1729,15 @@ iwl_parse_nvm_mcc_info(struct iwl_trans *trans, int max_num_ch; struct iwl_reg_capa reg_capa; - if (cfg->uhb_supported) { + if (cfg->unii9_supported) { + max_num_ch = IWL_NVM_NUM_CHANNELS_UNII9; + nvm_chan = iwl_unii9_nvm_channels; + } else if (cfg->uhb_supported) { max_num_ch = IWL_NVM_NUM_CHANNELS_UHB; - nvm_chan = iwl_uhb_nvm_channels; + nvm_chan = iwl_unii9_nvm_channels; } else if (cfg->nvm_type == IWL_NVM_EXT) { max_num_ch = IWL_NVM_NUM_CHANNELS_EXT; - nvm_chan = iwl_ext_nvm_channels; + nvm_chan = iwl_unii9_nvm_channels; } else { max_num_ch = IWL_NVM_NUM_CHANNELS; nvm_chan = iwl_nvm_channels; @@ -2087,13 +2092,26 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans, struct iwl_nvm_get_info_rsp_v3 *rsp_v3; bool v4 = fw_has_api(&fw->ucode_capa, IWL_UCODE_TLV_API_REGULATORY_NVM_INFO); - size_t rsp_size = v4 ? sizeof(*rsp) : sizeof(*rsp_v3); + size_t rsp_size; void *channel_profile; ret = iwl_trans_send_cmd(trans, &hcmd); if (ret) return ERR_PTR(ret); + switch (iwl_fw_lookup_notif_ver(fw, REGULATORY_AND_NVM_GROUP, + NVM_GET_INFO, 0)) { + case 5: + rsp_size = sizeof(struct iwl_nvm_get_info_rsp); + break; + case 4: + rsp_size = sizeof(struct iwl_nvm_get_info_rsp_v4); + break; + default: + rsp_size = sizeof(struct iwl_nvm_get_info_rsp_v3); + break; + } + if (WARN(iwl_rx_packet_payload_len(hcmd.resp_pkt) != rsp_size, "Invalid payload len in NVM response from FW %d", iwl_rx_packet_payload_len(hcmd.resp_pkt))) { @@ -2107,7 +2125,7 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans, if (empty_otp) IWL_INFO(trans, "OTP is empty\n"); - nvm = kzalloc_flex(*nvm, channels, IWL_NUM_CHANNELS_V2); + nvm = kzalloc_flex(*nvm, channels, IWL_NUM_CHANNELS_V3); if (!nvm) { ret = -ENOMEM; goto out; diff --git a/drivers/net/wireless/intel/iwlwifi/mld/agg.c b/drivers/net/wireless/intel/iwlwifi/mld/agg.c index e3627ad0321c..a464ebdec57f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/agg.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/agg.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2024-2025 Intel Corporation + * Copyright (C) 2024-2026 Intel Corporation */ #include "agg.h" #include "sta.h" @@ -222,6 +222,11 @@ iwl_mld_reorder(struct iwl_mld *mld, struct napi_struct *napi, if (baid == IWL_RX_REORDER_DATA_INVALID_BAID) return IWL_MLD_PASS_SKB; + if (IWL_FW_CHECK(mld, baid >= ARRAY_SIZE(mld->fw_id_to_ba), + "Got out-of-range BAID %u in reorder_data=0x%x\n", + baid, reorder)) + return IWL_MLD_PASS_SKB; + /* no sta yet */ if (WARN_ONCE(!sta, "Got valid BAID without a valid station assigned\n")) diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c index 17286b3341c0..9ac17be30400 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c @@ -1708,7 +1708,7 @@ static void iwl_mld_check_he_obss_narrow_bw_ru_iter(struct wiphy *wiphy, elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, ies->data, ies->len); - if (!elem || elem->datalen < 10 || + if (!elem || elem->datalen < 11 || !(elem->data[10] & WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT)) { *tolerated = false; diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mcc.c b/drivers/net/wireless/intel/iwlwifi/mld/mcc.c index 8502129abe49..830c251f43af 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mcc.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mcc.c @@ -18,9 +18,15 @@ static struct iwl_mcc_update_resp_v8 * iwl_mld_copy_mcc_resp(const struct iwl_rx_packet *pkt) { const struct iwl_mcc_update_resp_v8 *mcc_resp_v8 = (const void *)pkt->data; - int n_channels = __le32_to_cpu(mcc_resp_v8->n_channels); struct iwl_mcc_update_resp_v8 *resp_cp; - int notif_len = struct_size(resp_cp, channels, n_channels); + int n_channels; + int notif_len; + + if (iwl_rx_packet_payload_len(pkt) < sizeof(*mcc_resp_v8)) + return ERR_PTR(-EINVAL); + + n_channels = __le32_to_cpu(mcc_resp_v8->n_channels); + notif_len = struct_size(resp_cp, channels, n_channels); if (iwl_rx_packet_payload_len(pkt) != notif_len) return ERR_PTR(-EINVAL); diff --git a/drivers/net/wireless/intel/iwlwifi/mld/thermal.c b/drivers/net/wireless/intel/iwlwifi/mld/thermal.c index f8a8c35066be..e445b1d7d4b0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/thermal.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/thermal.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2024-2025 Intel Corporation + * Copyright (C) 2024-2026 Intel Corporation */ #ifdef CONFIG_THERMAL #include <linux/sort.h> @@ -272,6 +272,7 @@ static void iwl_mld_thermal_zone_register(struct iwl_mld *mld) if (ret) { IWL_DEBUG_TEMP(mld, "Failed to enable thermal zone\n"); thermal_zone_device_unregister(mld->tzone); + mld->tzone = NULL; } } @@ -385,10 +386,8 @@ static void iwl_mld_thermal_zone_unregister(struct iwl_mld *mld) return; IWL_DEBUG_TEMP(mld, "Thermal zone device unregister\n"); - if (mld->tzone) { - thermal_zone_device_unregister(mld->tzone); - mld->tzone = NULL; - } + thermal_zone_device_unregister(mld->tzone); + mld->tzone = NULL; } static void iwl_mld_cooling_device_unregister(struct iwl_mld *mld) diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tx.c b/drivers/net/wireless/intel/iwlwifi/mld/tx.c index 2185dade95f8..2df6643a5aa8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/tx.c @@ -1120,6 +1120,10 @@ void iwl_mld_handle_tx_resp_notif(struct iwl_mld *mld, ssn = le32_to_cpup((__le32 *)agg_status + tx_resp->frame_count) & 0xFFFF; + if (IWL_FW_CHECK(mld, txq_id >= ARRAY_SIZE(mld->fw_id_to_txq), + "Invalid txq id %d\n", txq_id)) + return; + __skb_queue_head_init(&skbs); /* we can free until ssn % q.n_bd not inclusive */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 9a74f60c9185..6b11fa32ea5c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1509,6 +1509,10 @@ static void iwl_mvm_report_wakeup_reasons(struct iwl_mvm *mvm, if (WARN_ON_ONCE(truncated < 0)) truncated = 0; + /* this would be a firmware bug */ + if (WARN_ON_ONCE(pktsize < sizeof(*hdr))) + return; + if (ieee80211_is_data(hdr->frame_control)) { int hdrlen = ieee80211_hdrlen(hdr->frame_control); int ivlen = 0, icvlen = 4; /* also FCS */ @@ -1517,10 +1521,6 @@ static void iwl_mvm_report_wakeup_reasons(struct iwl_mvm *mvm, if (!pkt) goto report; - skb_put_data(pkt, pktdata, hdrlen); - pktdata += hdrlen; - pktsize -= hdrlen; - if (ieee80211_has_protected(hdr->frame_control)) { /* * This is unlocked and using gtk_i(c)vlen, @@ -1539,13 +1539,24 @@ static void iwl_mvm_report_wakeup_reasons(struct iwl_mvm *mvm, /* if truncated, FCS/ICV is (partially) gone */ if (truncated >= icvlen) { - icvlen = 0; truncated -= icvlen; + icvlen = 0; } else { icvlen -= truncated; truncated = 0; } + if (IWL_FW_CHECK(mvm, + pktsize <= hdrlen + ivlen + icvlen, + "pktsize is too small %d\n", + pktsize)) { + kfree_skb(pkt); + return; + } + + skb_put_data(pkt, pktdata, hdrlen); + pktdata += hdrlen; + pktsize -= hdrlen; pktsize -= ivlen + icvlen; pktdata += ivlen; @@ -2123,16 +2134,16 @@ static void iwl_mvm_parse_wowlan_info_notif(struct iwl_mvm *mvm, struct iwl_wowlan_status_data *status, u32 len) { - if (IWL_FW_CHECK(mvm, data->num_mlo_link_keys, - "MLO is not supported, shouldn't receive MLO keys\n")) - return; - if (len < sizeof(*data)) { IWL_ERR(mvm, "Invalid WoWLAN info notification!\n"); status = NULL; return; } + if (IWL_FW_CHECK(mvm, data->num_mlo_link_keys, + "MLO is not supported, shouldn't receive MLO keys\n")) + return; + if (mvm->fast_resume) return; @@ -2448,13 +2459,15 @@ iwl_mvm_netdetect_query_results(struct iwl_mvm *mvm, if (fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_SCAN_OFFLOAD_CHANS)) { - query_len = sizeof(struct iwl_scan_offload_match_info); matches_len = sizeof(struct iwl_scan_offload_profile_match) * max_profiles; + query_len = offsetof(struct iwl_scan_offload_match_info, + matches) + matches_len; } else { - query_len = sizeof(struct iwl_scan_offload_profiles_query_v1); matches_len = sizeof(struct iwl_scan_offload_profile_match_v1) * max_profiles; + query_len = sizeof(struct iwl_scan_offload_profiles_query_v1) + + matches_len; } len = iwl_rx_packet_payload_len(cmd.resp_pkt); @@ -2756,7 +2769,7 @@ static int iwl_mvm_wowlan_store_wake_pkt(struct iwl_mvm *mvm, struct iwl_wowlan_status_data *status, u32 len) { - u32 data_size, packet_len = le32_to_cpu(notif->wake_packet_length); + u32 data_size, packet_len; if (len < sizeof(*notif)) { IWL_ERR(mvm, "Invalid WoWLAN wake packet notification!\n"); @@ -2775,6 +2788,7 @@ static int iwl_mvm_wowlan_store_wake_pkt(struct iwl_mvm *mvm, return -EIO; } + packet_len = le32_to_cpu(notif->wake_packet_length); data_size = len - offsetof(struct iwl_wowlan_wake_pkt_notif, wake_packet); /* data_size got the padding from the notification, remove it. */ @@ -2807,7 +2821,8 @@ static void iwl_mvm_nd_match_info_handler(struct iwl_mvm *mvm, if (IS_ERR_OR_NULL(vif)) return; - if (len < sizeof(struct iwl_scan_offload_match_info) + matches_len) { + if (len < offsetof(struct iwl_scan_offload_match_info, matches) + + matches_len) { IWL_ERR(mvm, "Invalid scan match info notification\n"); return; } @@ -2942,6 +2957,11 @@ static bool iwl_mvm_wait_d3_notif(struct iwl_notif_wait_data *notif_wait, case WIDE_ID(PROT_OFFLOAD_GROUP, D3_END_NOTIFICATION): { struct iwl_d3_end_notif *notif = (void *)pkt->data; + if (len < sizeof(*notif)) { + IWL_ERR(mvm, "Invalid D3 end notification size\n"); + break; + } + d3_data->d3_end_flags = __le32_to_cpu(notif->flags); d3_data->notif_received |= IWL_D3_NOTIF_D3_END_NOTIF; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index 3a14ca5e512a..8d7f60dcd027 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -646,7 +646,8 @@ static void iter(struct ieee80211_hw *hw, WARN_ON(*target->cipher == IWL_LOCATION_CIPHER_INVALID); } -static void +/* The tk buffer is assumed to be exactly TK_11AZ_LEN bytes */ +static int iwl_mvm_ftm_set_secured_ranging(struct iwl_mvm *mvm, struct ieee80211_vif *vif, u8 *bssid, u8 *cipher, u8 *hltk, u8 *tk, u8 *rx_pn, u8 *tx_pn, __le32 *flags) @@ -656,12 +657,12 @@ iwl_mvm_ftm_set_secured_ranging(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); if (mvmvif->ftm_unprotected) - return; + return 0; #endif if (!(le32_to_cpu(*flags) & (IWL_INITIATOR_AP_FLAGS_NON_TB | IWL_INITIATOR_AP_FLAGS_TB))) - return; + return 0; lockdep_assert_held(&mvm->mutex); @@ -679,14 +680,31 @@ iwl_mvm_ftm_set_secured_ranging(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (vif->cfg.assoc && !memcmp(vif->bss_conf.bssid, bssid, ETH_ALEN)) { struct iwl_mvm_ftm_iter_data target; + u32 key_len; target.bssid = bssid; target.cipher = cipher; target.tk = NULL; ieee80211_iter_keys(mvm->hw, vif, iter, &target); - if (!WARN_ON(!target.tk)) - memcpy(tk, target.tk, TK_11AZ_LEN); + if (WARN_ON(!target.tk)) + return -EINVAL; + + switch (*target.cipher) { + case IWL_LOCATION_CIPHER_CCMP_128: + case IWL_LOCATION_CIPHER_GCMP_128: + key_len = WLAN_KEY_LEN_CCMP; + break; + case IWL_LOCATION_CIPHER_GCMP_256: + key_len = WLAN_KEY_LEN_GCMP_256; + break; + default: + WARN_ON(1); + return -EINVAL; + } + + memset(tk, 0, TK_11AZ_LEN); + memcpy(tk, target.tk, key_len); } else { memcpy(tk, entry->tk, sizeof(entry->tk)); } @@ -695,8 +713,10 @@ iwl_mvm_ftm_set_secured_ranging(struct iwl_mvm *mvm, struct ieee80211_vif *vif, memcpy(tx_pn, entry->tx_pn, sizeof(entry->tx_pn)); FTM_SET_FLAG(SECURED); - return; + return 0; } + + return 0; } static int @@ -708,12 +728,11 @@ iwl_mvm_ftm_put_target_v7(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (err) return err; - iwl_mvm_ftm_set_secured_ranging(mvm, vif, target->bssid, - &target->cipher, target->hltk, - target->tk, target->rx_pn, - target->tx_pn, - &target->initiator_ap_flags); - return err; + return iwl_mvm_ftm_set_secured_ranging(mvm, vif, target->bssid, + &target->cipher, target->hltk, + target->tk, target->rx_pn, + target->tx_pn, + &target->initiator_ap_flags); } static int iwl_mvm_ftm_start_v11(struct iwl_mvm *mvm, @@ -881,11 +900,13 @@ iwl_mvm_ftm_put_target_v10(struct iwl_mvm *mvm, struct ieee80211_vif *vif, iwl_mvm_ftm_set_target_flags(mvm, peer, &target->initiator_ap_flags); iwl_mvm_ftm_set_sta(mvm, vif, peer, &target->sta_id, &target->initiator_ap_flags); - iwl_mvm_ftm_set_secured_ranging(mvm, vif, target->bssid, - &target->cipher, target->hltk, - target->tk, target->rx_pn, - target->tx_pn, - &target->initiator_ap_flags); + ret = iwl_mvm_ftm_set_secured_ranging(mvm, vif, target->bssid, + &target->cipher, target->hltk, + target->tk, target->rx_pn, + target->tx_pn, + &target->initiator_ap_flags); + if (ret) + return ret; i2r_max_sts = IWL_MVM_FTM_I2R_MAX_STS > 1 ? 1 : IWL_MVM_FTM_I2R_MAX_STS; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 6e507d6dcdd2..fa523be91d8a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -964,12 +964,22 @@ int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm) return ret; } + if (IWL_FW_CHECK(mvm, + iwl_rx_packet_payload_len(cmd.resp_pkt) != + sizeof(*resp), + "Wrong size for iwl_geo_tx_power_profiles_resp: %d\n", + iwl_rx_packet_payload_len(cmd.resp_pkt))) { + ret = -EIO; + goto out; + } + resp = (void *)cmd.resp_pkt->data; ret = le32_to_cpu(resp->profile_idx); if (WARN_ON(ret > BIOS_GEO_MAX_PROFILE_NUM)) ret = -EIO; +out: iwl_free_resp(&cmd); return ret; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index d6a8624b1ae5..b2c5be22c293 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -1493,49 +1493,54 @@ void iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm, { struct iwl_rx_packet *pkt = rxb_addr(rxb); unsigned int pkt_len = iwl_rx_packet_payload_len(pkt); - struct iwl_extended_beacon_notif *beacon = (void *)pkt->data; - struct iwl_extended_beacon_notif_v5 *beacon_v5 = (void *)pkt->data; struct ieee80211_vif *csa_vif; struct ieee80211_vif *tx_blocked_vif; struct agg_tx_status *agg_status; + u32 beacon_gp2; u16 status; lockdep_assert_held(&mvm->mutex); - mvm->ap_last_beacon_gp2 = le32_to_cpu(beacon->gp2); - if (!iwl_mvm_is_short_beacon_notif_supported(mvm)) { + struct iwl_extended_beacon_notif_v5 *beacon = (void *)pkt->data; struct iwl_tx_resp *beacon_notify_hdr = - &beacon_v5->beacon_notify_hdr; + &beacon->beacon_notify_hdr; - if (unlikely(pkt_len < sizeof(*beacon_v5))) + if (unlikely(pkt_len < sizeof(*beacon))) return; - mvm->ibss_manager = beacon_v5->ibss_mgr_status != 0; + beacon_gp2 = le32_to_cpu(beacon->gp2); + + mvm->ibss_manager = beacon->ibss_mgr_status != 0; agg_status = iwl_mvm_get_agg_status(mvm, beacon_notify_hdr); status = le16_to_cpu(agg_status->status) & TX_STATUS_MSK; IWL_DEBUG_RX(mvm, "beacon status %#x retries:%d tsf:0x%016llX gp2:0x%X rate:%d\n", status, beacon_notify_hdr->failure_frame, le64_to_cpu(beacon->tsf), - mvm->ap_last_beacon_gp2, + beacon_gp2, le32_to_cpu(beacon_notify_hdr->initial_rate)); } else { + const struct iwl_extended_beacon_notif *beacon = + (void *)pkt->data; + if (unlikely(pkt_len < sizeof(*beacon))) return; + beacon_gp2 = le32_to_cpu(beacon->gp2); + mvm->ibss_manager = beacon->ibss_mgr_status != 0; status = le32_to_cpu(beacon->status) & TX_STATUS_MSK; IWL_DEBUG_RX(mvm, "beacon status %#x tsf:0x%016llX gp2:0x%X\n", status, le64_to_cpu(beacon->tsf), - mvm->ap_last_beacon_gp2); + beacon_gp2); } csa_vif = rcu_dereference_protected(mvm->csa_vif, lockdep_is_held(&mvm->mutex)); if (unlikely(csa_vif && csa_vif->bss_conf.csa_active)) - iwl_mvm_csa_count_down(mvm, csa_vif, mvm->ap_last_beacon_gp2, + iwl_mvm_csa_count_down(mvm, csa_vif, beacon_gp2, (status == TX_STATUS_SUCCESS)); tx_blocked_vif = rcu_dereference_protected(mvm->csa_tx_blocked_vif, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 74bd4038fd56..3e73a6195fd9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -625,9 +625,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) hw->wiphy->max_sched_scan_reqs = 1; hw->wiphy->max_sched_scan_ssids = PROBE_OPTION_MAX; hw->wiphy->max_match_sets = iwl_umac_scan_get_max_profiles(mvm->fw); - /* we create the 802.11 header and zero length SSID IE. */ - hw->wiphy->max_sched_scan_ie_len = - SCAN_OFFLOAD_PROBE_REQ_SIZE - 24 - 2; + hw->wiphy->max_sched_scan_ie_len = iwl_mvm_max_scan_ie_len(mvm); hw->wiphy->max_sched_scan_plans = IWL_MAX_SCHED_SCAN_PLANS; hw->wiphy->max_sched_scan_plan_interval = U16_MAX; @@ -3061,7 +3059,6 @@ void iwl_mvm_stop_ap_ibss_common(struct iwl_mvm *mvm, } mvmvif->ap_ibss_active = false; - mvm->ap_last_beacon_gp2 = 0; if (vif->type == NL80211_IFTYPE_AP && !vif->p2p) { iwl_mvm_vif_set_low_latency(mvmvif, false, @@ -3490,7 +3487,7 @@ static void iwl_mvm_check_he_obss_narrow_bw_ru_iter(struct wiphy *wiphy, elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, ies->data, ies->len); - if (!elem || elem->datalen < 10 || + if (!elem || elem->datalen < 11 || !(elem->data[10] & WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT)) { data->tolerated = false; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 683cac56822c..31912f4d0175 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1168,9 +1168,6 @@ struct iwl_mvm { struct ieee80211_vif __rcu *csa_tx_blocked_vif; u8 csa_tx_block_bcn_timeout; - /* system time of last beacon (for AP/GO interface) */ - u32 ap_last_beacon_gp2; - /* indicates that we transmitted the last beacon */ bool ibss_manager; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 953218f1e025..f76e57399c1f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2019, 2021-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2019, 2021-2026 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -416,6 +416,7 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, int ret, resp_ver; u32 status; int resp_len, n_channels; + unsigned int pkt_len; u16 mcc; if (WARN_ON_ONCE(!iwl_mvm_is_lar_supported(mvm))) @@ -431,6 +432,7 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, return ERR_PTR(ret); pkt = cmd.resp_pkt; + pkt_len = iwl_rx_packet_payload_len(pkt); resp_ver = iwl_fw_lookup_notif_ver(mvm->fw, IWL_ALWAYS_LONG_GROUP, MCC_UPDATE_CMD, 0); @@ -439,9 +441,18 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, if (resp_ver >= 8) { struct iwl_mcc_update_resp_v8 *mcc_resp_v8 = (void *)pkt->data; + if (IWL_FW_CHECK(mvm, pkt_len < sizeof(*mcc_resp_v8), + "MCC v8 response too short: %u\n", pkt_len)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } + n_channels = __le32_to_cpu(mcc_resp_v8->n_channels); - if (iwl_rx_packet_payload_len(pkt) != - struct_size(mcc_resp_v8, channels, n_channels)) { + if (IWL_FW_CHECK(mvm, + pkt_len != + struct_size(mcc_resp_v8, channels, n_channels), + "invalid MCC v8 response size: %u (n_channels=%d)\n", + pkt_len, n_channels)) { resp_cp = ERR_PTR(-EINVAL); goto exit; } @@ -464,9 +475,18 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, IWL_UCODE_TLV_CAPA_MCC_UPDATE_11AX_SUPPORT)) { struct iwl_mcc_update_resp_v4 *mcc_resp_v4 = (void *)pkt->data; + if (IWL_FW_CHECK(mvm, pkt_len < sizeof(*mcc_resp_v4), + "MCC v4 response too short: %u\n", pkt_len)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } + n_channels = __le32_to_cpu(mcc_resp_v4->n_channels); - if (iwl_rx_packet_payload_len(pkt) != - struct_size(mcc_resp_v4, channels, n_channels)) { + if (IWL_FW_CHECK(mvm, + pkt_len != + struct_size(mcc_resp_v4, channels, n_channels), + "invalid MCC v4 response size: %u (n_channels=%d)\n", + pkt_len, n_channels)) { resp_cp = ERR_PTR(-EINVAL); goto exit; } @@ -489,9 +509,18 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, } else { struct iwl_mcc_update_resp_v3 *mcc_resp_v3 = (void *)pkt->data; + if (IWL_FW_CHECK(mvm, pkt_len < sizeof(*mcc_resp_v3), + "MCC v3 response too short: %u\n", pkt_len)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } + n_channels = __le32_to_cpu(mcc_resp_v3->n_channels); - if (iwl_rx_packet_payload_len(pkt) != - struct_size(mcc_resp_v3, channels, n_channels)) { + if (IWL_FW_CHECK(mvm, + pkt_len != + struct_size(mcc_resp_v3, channels, n_channels), + "invalid MCC v3 response size: %u (n_channels=%d)\n", + pkt_len, n_channels)) { resp_cp = ERR_PTR(-EINVAL); goto exit; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c b/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c index f39eb48864eb..49dcb1388007 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2021 - 2023, 2025 Intel Corporation + * Copyright (C) 2021 - 2023, 2025-2026 Intel Corporation */ #include "mvm.h" @@ -121,6 +121,8 @@ iwl_mvm_get_crosstimestamp_fw(struct iwl_mvm *mvm, u32 *gp2, u64 *sys_time) *sys_time = (u64)le32_to_cpu(resp->platform_timestamp_hi) << 32 | le32_to_cpu(resp->platform_timestamp_lo); + iwl_free_resp(&cmd); + return ret; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c index 89ac4c6b3e54..e2382be8edd7 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Copyright (C) 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2025 Intel Corporation + * Copyright (C) 2018-2026 Intel Corporation */ #include "rs.h" #include "fw-api.h" @@ -423,9 +423,14 @@ void iwl_mvm_tlc_update_notif(struct iwl_mvm *mvm, struct iwl_lq_sta_rs_fw *lq_sta; u32 flags; + notif = (void *)pkt->data; + if (IWL_FW_CHECK(mvm, notif->sta_id >= mvm->fw->ucode_capa.num_stations, + "Invalid sta id (%d) in TLC notification\n", + notif->sta_id)) + return; + rcu_read_lock(); - notif = (void *)pkt->data; link_sta = rcu_dereference(mvm->fw_id_to_link_sta[notif->sta_id]); sta = rcu_dereference(mvm->fw_id_to_mac_id[notif->sta_id]); if (IS_ERR_OR_NULL(sta) || !link_sta) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c index 269c4b45de80..ab1eb2eb0c3c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c @@ -1227,6 +1227,11 @@ void iwl_mvm_window_status_notif(struct iwl_mvm *mvm, /* get the station */ sta_id = (ratid & BA_WINDOW_STATUS_STA_ID_MSK) >> BA_WINDOW_STATUS_STA_ID_POS; + if (IWL_FW_CHECK(mvm, + sta_id >= mvm->fw->ucode_capa.num_stations, + "Invalid sta id (%d) in BA window status notification\n", + sta_id)) + continue; sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]); if (IS_ERR_OR_NULL(sta)) continue; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 79829f775c89..3831b3c27e0f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2026 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -3144,8 +3144,6 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm, if (ret) return ret; - iwl_mvm_build_scan_probe(mvm, vif, ies, ¶ms); - /* for 6 GHZ band only PSC channels need to be added */ for (i = 0; i < params.n_channels; i++) { struct ieee80211_channel *channel = params.channels[i]; @@ -3179,6 +3177,8 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm, goto out; } + iwl_mvm_build_scan_probe(mvm, vif, ies, ¶ms); + uid = iwl_mvm_build_scan_cmd(mvm, vif, &hcmd, ¶ms, type); if (uid < 0) { ret = uid; @@ -3217,6 +3217,10 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm, mvm->mei_scan_filter.is_mei_limited_scan = false; + if (IWL_FW_CHECK(mvm, uid >= ARRAY_SIZE(mvm->scan_uid_status), + "FW reports out-of-range scan UID %d\n", uid)) + return; + IWL_DEBUG_SCAN(mvm, "Scan completed: uid=%u type=%u, status=%s, EBS=%s\n", uid, mvm->scan_uid_status[uid], diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 1692b6e75f57..93b46c9e2333 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -951,6 +951,11 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, struct ieee80211_vif *vif; struct iwl_mvm_vif *mvmvif; + if (IWL_FW_CHECK(mvm, id >= ARRAY_SIZE(mvm->vif_id_to_mac), + "Invalid mac_link_id (%d) in session protect notif\n", + id)) + return; + rcu_read_lock(); /* note we use link ID == MAC ID */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index dc69c71faa76..d3c2fe830477 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1544,6 +1544,17 @@ static inline u32 iwl_mvm_get_scd_ssn(struct iwl_mvm *mvm, return val & 0xFFF; } +static inline size_t iwl_mvm_tx_resp_min_len(struct iwl_mvm *mvm, + struct iwl_tx_resp *tx_resp) +{ + struct agg_tx_status *agg_status = + iwl_mvm_get_agg_status(mvm, tx_resp); + + /* The aggregate response ends with a trailing SCD SSN __le32 word. */ + return (u8 *)(agg_status + tx_resp->frame_count) - (u8 *)tx_resp + + sizeof(__le32); +} + static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm, struct iwl_rx_packet *pkt) { @@ -1847,6 +1858,9 @@ static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm, int queue = SEQ_TO_QUEUE(sequence); struct ieee80211_sta *sta; + if (WARN_ON_ONCE(iwl_mvm_has_new_tx_api(mvm))) + return; + if (WARN_ON_ONCE(queue < IWL_MVM_DQA_MIN_DATA_QUEUE && (queue != IWL_MVM_DQA_BSS_CLIENT_QUEUE))) return; @@ -1881,6 +1895,26 @@ void iwl_mvm_rx_tx_cmd(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) { struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_tx_resp *tx_resp = (void *)pkt->data; + size_t min_len; + + if (IWL_FW_CHECK(mvm, !tx_resp->frame_count, + "invalid TX_CMD frame_count %u\n", + tx_resp->frame_count)) + return; + + if (IWL_FW_CHECK(mvm, + iwl_mvm_has_new_tx_api(mvm) && + tx_resp->frame_count != 1, + "invalid TX_CMD frame_count %u for new TX API\n", + tx_resp->frame_count)) + return; + + min_len = iwl_mvm_tx_resp_min_len(mvm, tx_resp); + if (IWL_FW_CHECK(mvm, iwl_rx_packet_payload_len(pkt) < min_len, + "invalid TX_CMD len %u (frame_count %u, min %zu)\n", + iwl_rx_packet_payload_len(pkt), tx_resp->frame_count, + min_len)) + return; if (tx_resp->frame_count == 1) iwl_mvm_rx_tx_cmd_single(mvm, pkt); @@ -2100,8 +2134,14 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) if (tid == IWL_MGMT_TID) tid = IWL_MAX_TID_COUNT; + if (IWL_FW_CHECK(mvm, tid >= + ARRAY_SIZE(mvmsta->tid_data), + "invalid TID %d in compressed BA\n", + tid)) + continue; + if (mvmsta) - mvmsta->tid_data[i].lq_color = lq_color; + mvmsta->tid_data[tid].lq_color = lq_color; iwl_mvm_tx_reclaim(mvm, sta_id, tid, (int)(le16_to_cpu(ba_tfd->q_num)), @@ -2121,6 +2161,9 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) ba_notif = (void *)pkt->data; sta_id = ba_notif->sta_id; tid = ba_notif->tid; + if (IWL_FW_CHECK(mvm, tid >= ARRAY_SIZE(mvmsta->tid_data), + "invalid TID %d in BA notif\n", tid)) + return; /* "flow" corresponds to Tx queue */ txq = le16_to_cpu(ba_notif->scd_flow); /* "ssn" is start of block-ack Tx window, corresponds to index diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c index d5eb895144ef..7f886200d693 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Copyright (C) 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2025 Intel Corporation + * Copyright (C) 2018-2026 Intel Corporation */ #include "iwl-trans.h" #include "iwl-fh.h" @@ -99,6 +99,11 @@ int iwl_pcie_init_fw_sec(struct iwl_trans *trans, /* add 2 due to separators */ paging_cnt = iwl_pcie_get_num_sections(fw, lmac_cnt + umac_cnt + 2); + if (WARN_ON(lmac_cnt > ARRAY_SIZE(ctxt_dram->lmac_img) || + umac_cnt > ARRAY_SIZE(ctxt_dram->umac_img) || + paging_cnt > ARRAY_SIZE(ctxt_dram->virtual_img))) + return -EINVAL; + dram->fw = kzalloc_objs(*dram->fw, umac_cnt + lmac_cnt); if (!dram->fw) return -ENOMEM; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/rx.c index fe263cdc2e4f..4631e11f2a96 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/rx.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2003-2014, 2018-2024 Intel Corporation + * Copyright (C) 2003-2014, 2018-2024, 2026 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -1238,11 +1238,16 @@ void iwl_pcie_rx_free(struct iwl_trans *trans) } } kfree(trans_pcie->rx_pool); + trans_pcie->rx_pool = NULL; kfree(trans_pcie->global_table); + trans_pcie->global_table = NULL; kfree(trans_pcie->rxq); + trans_pcie->rxq = NULL; - if (trans_pcie->alloc_page) + if (trans_pcie->alloc_page) { __free_pages(trans_pcie->alloc_page, trans_pcie->rx_page_order); + trans_pcie->alloc_page = NULL; + } } static void iwl_pcie_rx_move_to_allocator(struct iwl_rxq *rxq, diff --git a/drivers/net/wireless/intersil/p54/txrx.c b/drivers/net/wireless/intersil/p54/txrx.c index 1294a1d6528e..9f491334c8d0 100644 --- a/drivers/net/wireless/intersil/p54/txrx.c +++ b/drivers/net/wireless/intersil/p54/txrx.c @@ -499,11 +499,19 @@ static void p54_rx_eeprom_readback(struct p54_common *priv, if (le16_to_cpu(eeprom->v2.len) != priv->eeprom_slice_size) return; + if (eeprom->v2.data + priv->eeprom_slice_size > + skb_tail_pointer(skb)) + return; + memcpy(priv->eeprom, eeprom->v2.data, priv->eeprom_slice_size); } else { if (le16_to_cpu(eeprom->v1.len) != priv->eeprom_slice_size) return; + if (eeprom->v1.data + priv->eeprom_slice_size > + skb_tail_pointer(skb)) + return; + memcpy(priv->eeprom, eeprom->v1.data, priv->eeprom_slice_size); } diff --git a/drivers/net/wireless/marvell/libertas/firmware.c b/drivers/net/wireless/marvell/libertas/firmware.c index f124110944b7..9bf7d4c207b9 100644 --- a/drivers/net/wireless/marvell/libertas/firmware.c +++ b/drivers/net/wireless/marvell/libertas/firmware.c @@ -78,6 +78,7 @@ static void helper_firmware_cb(const struct firmware *firmware, void *context) } else { /* No main firmware needed for this helper --> success! */ lbs_fw_loaded(priv, 0, firmware, NULL); + release_firmware(firmware); } } diff --git a/drivers/net/wireless/marvell/libertas/tx.c b/drivers/net/wireless/marvell/libertas/tx.c index 27304a98787d..13d08022e414 100644 --- a/drivers/net/wireless/marvell/libertas/tx.c +++ b/drivers/net/wireless/marvell/libertas/tx.c @@ -117,6 +117,13 @@ netdev_tx_t lbs_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) if (priv->wdev->iftype == NL80211_IFTYPE_MONITOR) { struct tx_radiotap_hdr *rtap_hdr = (void *)skb->data; + if (skb->len < sizeof(*rtap_hdr) + 4 + ETH_ALEN) { + lbs_deb_tx("tx err: short monitor frame %u\n", skb->len); + dev->stats.tx_dropped++; + dev->stats.tx_errors++; + goto free; + } + /* set txpd fields from the radiotap header */ txpd->tx_control = cpu_to_le32(convert_radiotap_rate_to_mv(rtap_hdr->rate)); diff --git a/drivers/net/wireless/marvell/libertas_tf/main.c b/drivers/net/wireless/marvell/libertas_tf/main.c index fb20fe31cd36..42be6fa22f9c 100644 --- a/drivers/net/wireless/marvell/libertas_tf/main.c +++ b/drivers/net/wireless/marvell/libertas_tf/main.c @@ -174,7 +174,7 @@ static void lbtf_free_adapter(struct lbtf_private *priv) { lbtf_deb_enter(LBTF_DEB_MAIN); lbtf_free_cmd_buffer(priv); - timer_delete(&priv->command_timer); + timer_delete_sync(&priv->command_timer); lbtf_deb_leave(LBTF_DEB_MAIN); } diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index c9daf893472f..abc703441c5d 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -4334,7 +4334,7 @@ mwifiex_cfg80211_authenticate(struct wiphy *wiphy, return -EOPNOTSUPP; } - if (!priv->auth_flag) { + if (!(priv->auth_flag & HOST_MLME_AUTH_PENDING)) { ret = mwifiex_remain_on_chan_cfg(priv, HostCmd_ACT_GEN_SET, req->bss->channel, AUTH_TX_DEFAULT_WAIT_TIME); diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h index e9e896606912..93561116959a 100644 --- a/drivers/net/wireless/marvell/mwifiex/fw.h +++ b/drivers/net/wireless/marvell/mwifiex/fw.h @@ -823,7 +823,7 @@ struct chan_band_param_set { struct mwifiex_ie_types_chan_band_list_param_set { struct mwifiex_ie_types_header header; - struct chan_band_param_set chan_band_param[1]; + struct chan_band_param_set chan_band_param[]; } __packed; struct mwifiex_ie_types_rates_param_set { @@ -886,7 +886,7 @@ struct mwifiex_ie_types_wildcard_ssid_params { #define TSF_DATA_SIZE 8 struct mwifiex_ie_types_tsf_timestamp { struct mwifiex_ie_types_header header; - u8 tsf_data[1]; + u8 tsf_data[]; } __packed; struct mwifiex_cf_param_set { @@ -903,8 +903,8 @@ struct mwifiex_ibss_param_set { struct mwifiex_ie_types_ss_param_set { struct mwifiex_ie_types_header header; union { - struct mwifiex_cf_param_set cf_param_set[1]; - struct mwifiex_ibss_param_set ibss_param_set[1]; + DECLARE_FLEX_ARRAY(struct mwifiex_cf_param_set, cf_param_set); + DECLARE_FLEX_ARRAY(struct mwifiex_ibss_param_set, ibss_param_set); } cf_ibss; } __packed; @@ -922,8 +922,8 @@ struct mwifiex_ds_param_set { struct mwifiex_ie_types_phy_param_set { struct mwifiex_ie_types_header header; union { - struct mwifiex_fh_param_set fh_param_set[1]; - struct mwifiex_ds_param_set ds_param_set[1]; + DECLARE_FLEX_ARRAY(struct mwifiex_fh_param_set, fh_param_set); + DECLARE_FLEX_ARRAY(struct mwifiex_ds_param_set, ds_param_set); } fh_ds; } __packed; @@ -1383,7 +1383,7 @@ struct host_cmd_ds_802_11_snmp_mib { __le16 query_type; __le16 oid; __le16 buf_size; - u8 value[1]; + u8 value[]; } __packed; struct mwifiex_rate_scope { @@ -1551,7 +1551,7 @@ struct mwifiex_scan_cmd_config { * TLV_TYPE_CHANLIST, mwifiex_ie_types_chan_list_param_set * WLAN_EID_SSID, mwifiex_ie_types_ssid_param_set */ - u8 tlv_buf[1]; /* SSID TLV(s) and ChanList TLVs are stored + u8 tlv_buf[]; /* SSID TLV(s) and ChanList TLVs are stored here */ } __packed; @@ -1683,7 +1683,7 @@ struct host_cmd_ds_802_11_bg_scan_query_rsp { struct mwifiex_ietypes_domain_param_set { struct mwifiex_ie_types_header header; u8 country_code[IEEE80211_COUNTRY_STRING_LEN]; - struct ieee80211_country_ie_triplet triplet[1]; + struct ieee80211_country_ie_triplet triplet[]; } __packed; struct host_cmd_ds_802_11d_domain_info { diff --git a/drivers/net/wireless/marvell/mwifiex/join.c b/drivers/net/wireless/marvell/mwifiex/join.c index 5a1a0287c1d5..259140395d35 100644 --- a/drivers/net/wireless/marvell/mwifiex/join.c +++ b/drivers/net/wireless/marvell/mwifiex/join.c @@ -421,15 +421,15 @@ int mwifiex_cmd_802_11_associate(struct mwifiex_private *priv, phy_tlv = (struct mwifiex_ie_types_phy_param_set *) pos; phy_tlv->header.type = cpu_to_le16(WLAN_EID_DS_PARAMS); - phy_tlv->header.len = cpu_to_le16(sizeof(phy_tlv->fh_ds.ds_param_set)); - memcpy(&phy_tlv->fh_ds.ds_param_set, + phy_tlv->header.len = cpu_to_le16(sizeof(*phy_tlv->fh_ds.ds_param_set)); + memcpy(phy_tlv->fh_ds.ds_param_set, &bss_desc->phy_param_set.ds_param_set.current_chan, - sizeof(phy_tlv->fh_ds.ds_param_set)); + sizeof(*phy_tlv->fh_ds.ds_param_set)); pos += sizeof(phy_tlv->header) + le16_to_cpu(phy_tlv->header.len); ss_tlv = (struct mwifiex_ie_types_ss_param_set *) pos; ss_tlv->header.type = cpu_to_le16(WLAN_EID_CF_PARAMS); - ss_tlv->header.len = cpu_to_le16(sizeof(ss_tlv->cf_ibss.cf_param_set)); + ss_tlv->header.len = cpu_to_le16(sizeof(*ss_tlv->cf_ibss.cf_param_set)); pos += sizeof(ss_tlv->header) + le16_to_cpu(ss_tlv->header.len); /* Get the common rates supported between the driver and the BSS Desc */ @@ -736,7 +736,6 @@ int mwifiex_ret_802_11_associate(struct mwifiex_private *priv, /* Send a Media Connected event, according to the Spec */ priv->media_connected = true; - priv->adapter->ps_state = PS_STATE_AWAKE; priv->adapter->pps_uapsd_mode = false; priv->adapter->tx_lock_flag = false; diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c index 623ddde8c8e5..071f7cb305e1 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c @@ -108,7 +108,7 @@ static int mwifiex_cmd_802_11_snmp_mib(struct mwifiex_private *priv, "cmd: SNMP_CMD: cmd_oid = 0x%x\n", cmd_oid); cmd->command = cpu_to_le16(HostCmd_CMD_802_11_SNMP_MIB); cmd->size = cpu_to_le16(sizeof(struct host_cmd_ds_802_11_snmp_mib) - - 1 + S_DS_GEN); + + S_DS_GEN); snmp_mib->oid = cpu_to_le16((u16)cmd_oid); if (cmd_action == HostCmd_ACT_GEN_GET) { diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c index a6550548d3b4..9460d5352b23 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c @@ -196,6 +196,7 @@ static int mwifiex_request_rgpower_table(struct mwifiex_private *priv) struct mwifiex_adapter *adapter = priv->adapter; char rgpower_table_name[30]; char country_code[3]; + int ret; strscpy(country_code, domain_info->country_code, sizeof(country_code)); @@ -214,16 +215,17 @@ static int mwifiex_request_rgpower_table(struct mwifiex_private *priv) adapter->rgpower_data = NULL; } - if ((request_firmware(&adapter->rgpower_data, rgpower_table_name, - adapter->dev))) { + ret = request_firmware_direct(&adapter->rgpower_data, rgpower_table_name, + adapter->dev); + + if (ret) { mwifiex_dbg( adapter, INFO, - "info: %s: failed to request regulatory power table\n", - __func__); - return -EIO; + "info: %s: failed to request regulatory power table: %d\n", + __func__, ret); } - return 0; + return ret; } static int mwifiex_dnld_rgpower_table(struct mwifiex_private *priv) diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c index 845f2a22e071..c71ffe8399e4 100644 --- a/drivers/net/wireless/marvell/mwifiex/tdls.c +++ b/drivers/net/wireless/marvell/mwifiex/tdls.c @@ -215,7 +215,7 @@ mwifiex_tdls_add_ht_oper(struct mwifiex_private *priv, const u8 *mac, /* follow AP's channel bandwidth */ if (ISSUPP_CHANWIDTH40(priv->adapter->hw_dot_11n_dev_cap) && - bss_desc->bcn_ht_cap && + bss_desc->bcn_ht_oper && ISALLOWED_CHANWIDTH40(bss_desc->bcn_ht_oper->ht_param)) ht_oper->ht_param = bss_desc->bcn_ht_oper->ht_param; diff --git a/drivers/net/wireless/marvell/mwifiex/uap_event.c b/drivers/net/wireless/marvell/mwifiex/uap_event.c index 679fdae0f001..ba1bdbbff687 100644 --- a/drivers/net/wireless/marvell/mwifiex/uap_event.c +++ b/drivers/net/wireless/marvell/mwifiex/uap_event.c @@ -123,11 +123,31 @@ int mwifiex_process_uap_event(struct mwifiex_private *priv) len = ETH_ALEN; if (len != -1) { + u16 evt_len = le16_to_cpu(event->len); + sinfo->assoc_req_ies = &event->data[len]; len = (u8 *)sinfo->assoc_req_ies - (u8 *)&event->frame_control; - sinfo->assoc_req_ies_len = - le16_to_cpu(event->len) - (u16)len; + + /* + * event->len is reported by the device firmware + * and is not otherwise validated. Reject a + * length that underflows the header, or that + * would place the association request IEs + * outside the fixed-size event_body[] buffer the + * event was copied into; otherwise the IE walk + * in mwifiex_set_sta_ht_cap() reads past + * event_body and out of the adapter slab object. + */ + if (evt_len < len || + (u8 *)&event->frame_control + evt_len > + adapter->event_body + MAX_EVENT_SIZE) { + mwifiex_dbg(adapter, ERROR, + "invalid STA assoc event length\n"); + kfree(sinfo); + return -1; + } + sinfo->assoc_req_ies_len = evt_len - (u16)len; } } cfg80211_new_sta(priv->netdev->ieee80211_ptr, event->sta_addr, diff --git a/drivers/net/wireless/mediatek/mt76/Kconfig b/drivers/net/wireless/mediatek/mt76/Kconfig index 502303622a53..2ca96e0527c0 100644 --- a/drivers/net/wireless/mediatek/mt76/Kconfig +++ b/drivers/net/wireless/mediatek/mt76/Kconfig @@ -38,8 +38,8 @@ config MT792x_USB select MT76_USB config MT76_NPU - bool - depends on MT76_CORE + tristate + depends on NET_AIROHA_NPU=y || MT76_CORE=NET_AIROHA_NPU source "drivers/net/wireless/mediatek/mt76/mt76x0/Kconfig" source "drivers/net/wireless/mediatek/mt76/mt76x2/Kconfig" diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile index 1d42adfe8030..cacdd2b13d05 100644 --- a/drivers/net/wireless/mediatek/mt76/Makefile +++ b/drivers/net/wireless/mediatek/mt76/Makefile @@ -12,7 +12,11 @@ mt76-y := \ mmio.o util.o trace.o dma.o mac80211.o debugfs.o eeprom.o \ tx.o agg-rx.o mcu.o wed.o scan.o channel.o -mt76-$(CONFIG_MT76_NPU) += npu.o +ifdef CONFIG_MT76_NPU +# CONFIG_MT76_NPU is tristate to simplify dependency tracking, +# but it behaves as a bool symbol here. +mt76-y += npu.o +endif mt76-$(CONFIG_PCI) += pci.o mt76-$(CONFIG_NL80211_TESTMODE) += testmode.o diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index f8c2fe5f2f58..322041859217 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -1189,7 +1189,10 @@ void mt76_dma_cleanup(struct mt76_dev *dev) mt76_for_each_q_rx(dev, i) { struct mt76_queue *q = &dev->q_rx[i]; - netif_napi_del(&dev->napi[i]); + if (!mt76_queue_is_wed_rro(q)) { + napi_disable(&dev->napi[i]); + netif_napi_del(&dev->napi[i]); + } mt76_dma_rx_cleanup(dev, q); page_pool_destroy(q->page_pool); diff --git a/drivers/net/wireless/mediatek/mt76/eeprom.c b/drivers/net/wireless/mediatek/mt76/eeprom.c index b99d7452800f..afdb73661866 100644 --- a/drivers/net/wireless/mediatek/mt76/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/eeprom.c @@ -181,7 +181,7 @@ mt76_eeprom_override(struct mt76_phy *phy) if (err == -EPROBE_DEFER) return err; - if (err) { + if (!is_valid_ether_addr(phy->macaddr)) { eth_random_addr(phy->macaddr); dev_info(dev->dev, "Invalid MAC address, using random address %pM\n", diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 07955555f84d..3822eb8fd88f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -1647,7 +1647,7 @@ int mt76_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *skb, int mt76_testmode_set_state(struct mt76_phy *phy, enum mt76_testmode_state state); int mt76_testmode_alloc_skb(struct mt76_phy *phy, u32 len); -#ifdef CONFIG_MT76_NPU +#if IS_ENABLED(CONFIG_MT76_NPU) void mt76_npu_check_ppe(struct mt76_dev *dev, struct sk_buff *skb, u32 info); int mt76_npu_dma_add_buf(struct mt76_phy *phy, struct mt76_queue *q, @@ -1736,12 +1736,12 @@ static inline int mt76_npu_send_txrx_addr(struct mt76_dev *dev, int ifindex, static inline bool mt76_npu_device_active(struct mt76_dev *dev) { - return !!rcu_access_pointer(dev->mmio.npu); + return mt76_is_mmio(dev) && !!rcu_access_pointer(dev->mmio.npu); } static inline bool mt76_ppe_device_active(struct mt76_dev *dev) { - return !!rcu_access_pointer(dev->mmio.ppe_dev); + return mt76_is_mmio(dev) && !!rcu_access_pointer(dev->mmio.ppe_dev); } static inline int mt76_npu_send_msg(struct airoha_npu *npu, int ifindex, diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index ce0051468501..aad232c5a6fa 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -1601,6 +1601,8 @@ bool mt7615_rx_check(struct mt76_dev *mdev, void *data, int len) switch (type) { case PKT_TYPE_TXRX_NOTIFY: + if (!mt76_is_mmio(mdev)) + return false; mt7615_mac_tx_free(dev, data, len); return false; case PKT_TYPE_TXS: @@ -1634,6 +1636,10 @@ void mt7615_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, dev_kfree_skb(skb); break; case PKT_TYPE_TXRX_NOTIFY: + if (!mt76_is_mmio(mdev)) { + dev_kfree_skb(skb); + break; + } mt7615_mac_tx_free(dev, skb->data, skb->len); dev_kfree_skb(skb); break; diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c index 6596c9e198f4..58b0b15e4fd6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c @@ -1458,6 +1458,8 @@ mt76_connac_mcu_uni_bss_he_tlv(struct mt76_phy *phy, struct ieee80211_vif *vif, struct bss_info_uni_he *he; cap = mt76_connac_get_he_phy_cap(phy, vif); + if (!cap) + return; he = (struct bss_info_uni_he *)tlv; he->he_pe_duration = vif->bss_conf.htc_trig_based_pkt_ext; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index 4a381d351e61..e8fe86f93309 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -595,6 +595,8 @@ mt7915_mcu_bss_he_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, struct tlv *tlv; cap = mt76_connac_get_he_phy_cap(phy->mt76, vif); + if (!cap) + return; tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_HE_BASIC, sizeof(*he)); @@ -1177,13 +1179,12 @@ mt7915_mcu_sta_bfer_vht(struct ieee80211_sta *sta, struct mt7915_phy *phy, } static void -mt7915_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif, - struct mt7915_phy *phy, struct sta_rec_bf *bf) +mt7915_mcu_sta_bfer_he(struct ieee80211_sta *sta, + const struct ieee80211_sta_he_cap *vc, + struct sta_rec_bf *bf) { struct ieee80211_sta_he_cap *pc = &sta->deflink.he_cap; struct ieee80211_he_cap_elem *pe = &pc->he_cap_elem; - const struct ieee80211_sta_he_cap *vc = - mt76_connac_get_he_phy_cap(phy->mt76, vif); const struct ieee80211_he_cap_elem *ve = &vc->he_cap_elem; u16 mcs_map = le16_to_cpu(pc->he_mcs_nss_supp.rx_mcs_80); u8 nss_mcs = mt7915_mcu_get_sta_nss(mcs_map); @@ -1242,6 +1243,7 @@ mt7915_mcu_sta_bfer_tlv(struct mt7915_dev *dev, struct sk_buff *skb, { struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; struct mt7915_phy *phy = mvif->phy; + const struct ieee80211_sta_he_cap *vc = NULL; int tx_ant = hweight8(phy->mt76->chainmask) - 1; struct sta_rec_bf *bf; struct tlv *tlv; @@ -1260,6 +1262,12 @@ mt7915_mcu_sta_bfer_tlv(struct mt7915_dev *dev, struct sk_buff *skb, if (!ebf && !dev->ibf) return; + if (sta->deflink.he_cap.has_he && ebf) { + vc = mt76_connac_get_he_phy_cap(phy->mt76, vif); + if (!vc) + return; + } + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_BF, sizeof(*bf)); bf = (struct sta_rec_bf *)tlv; @@ -1268,7 +1276,7 @@ mt7915_mcu_sta_bfer_tlv(struct mt7915_dev *dev, struct sk_buff *skb, * ht: iBF only, since mac80211 lacks of eBF support */ if (sta->deflink.he_cap.has_he && ebf) - mt7915_mcu_sta_bfer_he(sta, vif, phy, bf); + mt7915_mcu_sta_bfer_he(sta, vc, bf); else if (sta->deflink.vht_cap.vht_supported) mt7915_mcu_sta_bfer_vht(sta, phy, bf, ebf); else if (sta->deflink.ht_cap.ht_supported) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c index 1c2377d0a53d..f7d54472da1b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c @@ -570,8 +570,9 @@ bool mt7921_rx_check(struct mt76_dev *mdev, void *data, int len) switch (type) { case PKT_TYPE_TXRX_NOTIFY: - /* PKT_TYPE_TXRX_NOTIFY can be received only by mmio devices */ - mt7921_mac_tx_free(dev, data, len); /* mmio */ + if (!mt76_is_mmio(mdev)) + return false; + mt7921_mac_tx_free(dev, data, len); return false; case PKT_TYPE_TXS: for (rxd += 2; rxd + 8 <= end; rxd += 8) @@ -600,7 +601,10 @@ void mt7921_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, switch (type) { case PKT_TYPE_TXRX_NOTIFY: - /* PKT_TYPE_TXRX_NOTIFY can be received only by mmio devices */ + if (!mt76_is_mmio(mdev)) { + napi_consume_skb(skb, 1); + break; + } mt7921_mac_tx_free(dev, skb->data, skb->len); napi_consume_skb(skb, 1); break; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index 0641a7131d7c..6b0cd1996ecb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -1203,8 +1203,9 @@ bool mt7925_rx_check(struct mt76_dev *mdev, void *data, int len) switch (type) { case PKT_TYPE_TXRX_NOTIFY: - /* PKT_TYPE_TXRX_NOTIFY can be received only by mmio devices */ - mt7925_mac_tx_free(dev, data, len); /* mmio */ + if (!mt76_is_mmio(mdev)) + return false; + mt7925_mac_tx_free(dev, data, len); return false; case PKT_TYPE_TXS: for (rxd += 4; rxd + 12 <= end; rxd += 12) @@ -1240,7 +1241,10 @@ void mt7925_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, switch (type) { case PKT_TYPE_TXRX_NOTIFY: - /* PKT_TYPE_TXRX_NOTIFY can be received only by mmio devices */ + if (!mt76_is_mmio(mdev)) { + napi_consume_skb(skb, 1); + break; + } mt7925_mac_tx_free(dev, skb->data, skb->len); napi_consume_skb(skb, 1); break; @@ -1284,6 +1288,9 @@ mt7925_vif_connect_iter(void *priv, u8 *mac, for_each_set_bit(i, &valid, IEEE80211_MLD_MAX_NUM_LINKS) { bss_conf = mt792x_vif_to_bss_conf(vif, i); + if (!bss_conf) + continue; + mconf = mt792x_vif_to_link(mvif, i); mt76_connac_mcu_uni_add_dev(&dev->mphy, bss_conf, &mconf->mt76, diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index a9059866b701..2b6cc8e253c0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -1713,6 +1713,9 @@ static void mt7925_sta_set_decap_offload(struct ieee80211_hw *hw, mconf = mt792x_vif_to_link(mvif, i); mlink = mt792x_sta_to_link(msta, i); + if (!mlink) + continue; + if (enabled) set_bit(MT_WCID_FLAG_HDR_TRANS, &mlink->wcid.flags); else diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index e94fa544ff20..cb265a6fc7ad 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -2773,6 +2773,8 @@ mt7925_mcu_bss_he_tlv(struct sk_buff *skb, struct ieee80211_bss_conf *link_conf, struct tlv *tlv; cap = mt76_connac_get_he_phy_cap(phy->mt76, link_conf->vif); + if (!cap) + return; tlv = mt76_connac_mcu_add_tlv(skb, UNI_BSS_INFO_HE_BASIC, sizeof(*he)); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig b/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig index 5503d03bf62c..5742bce12fbb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig +++ b/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig @@ -16,6 +16,6 @@ config MT7996E config MT7996_NPU bool "MT7996 (PCIe) NPU support" depends on MT7996E - depends on NET_AIROHA_NPU=y || MT7996E=NET_AIROHA_NPU + depends on NET_AIROHA_NPU=y || MT76_CORE=NET_AIROHA_NPU select MT76_NPU default n diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index f119f023bcd5..2e83f4b79c87 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -935,6 +935,8 @@ mt7996_mcu_bss_he_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, struct tlv *tlv; cap = mt76_connac_get_he_phy_cap(phy->mt76, vif); + if (!cap) + return; tlv = mt7996_mcu_add_uni_tlv(skb, UNI_BSS_INFO_HE_BASIC, sizeof(*he)); @@ -1855,17 +1857,18 @@ mt7996_mcu_sta_bfer_he(struct ieee80211_link_sta *link_sta, { struct ieee80211_sta_he_cap *pc = &link_sta->he_cap; struct ieee80211_he_cap_elem *pe = &pc->he_cap_elem; - const struct ieee80211_sta_he_cap *vc = - mt76_connac_get_he_phy_cap(phy->mt76, vif); - const struct ieee80211_he_cap_elem *ve = &vc->he_cap_elem; u16 mcs_map = le16_to_cpu(pc->he_mcs_nss_supp.rx_mcs_80); u8 nss_mcs = mt7996_mcu_get_sta_nss(mcs_map); + const struct ieee80211_he_cap_elem *ve; + const struct ieee80211_sta_he_cap *vc; u8 snd_dim, sts; + vc = mt76_connac_get_he_phy_cap(phy->mt76, vif); if (!vc) return; bf->tx_mode = MT_PHY_TYPE_HE_SU; + ve = &vc->he_cap_elem; mt7996_mcu_sta_sounding_rate(bf, phy); @@ -1921,14 +1924,18 @@ mt7996_mcu_sta_bfer_eht(struct ieee80211_link_sta *link_sta, struct ieee80211_sta_eht_cap *pc = &link_sta->eht_cap; struct ieee80211_eht_cap_elem_fixed *pe = &pc->eht_cap_elem; struct ieee80211_eht_mcs_nss_supp *eht_nss = &pc->eht_mcs_nss_supp; - const struct ieee80211_sta_eht_cap *vc = - mt76_connac_get_eht_phy_cap(phy->mt76, vif); - const struct ieee80211_eht_cap_elem_fixed *ve = &vc->eht_cap_elem; u8 nss_mcs = u8_get_bits(eht_nss->bw._80.rx_tx_mcs9_max_nss, IEEE80211_EHT_MCS_NSS_RX) - 1; + const struct ieee80211_eht_cap_elem_fixed *ve; + const struct ieee80211_sta_eht_cap *vc; u8 snd_dim, sts; + vc = mt76_connac_get_eht_phy_cap(phy->mt76, vif); + if (!vc) + return; + bf->tx_mode = MT_PHY_TYPE_EHT_MU; + ve = &vc->eht_cap_elem; mt7996_mcu_sta_sounding_rate(bf, phy); diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c index 009c4770a6f9..60fe5f08964f 100644 --- a/drivers/net/wireless/microchip/wilc1000/hif.c +++ b/drivers/net/wireless/microchip/wilc1000/hif.c @@ -600,6 +600,11 @@ static s32 wilc_parse_assoc_resp_info(u8 *buffer, u32 buffer_len, u16 ies_len; struct wilc_assoc_resp *res = (struct wilc_assoc_resp *)buffer; + if (buffer_len < sizeof(*res)) { + ret_conn_info->status = WLAN_STATUS_UNSPECIFIED_FAILURE; + return -EINVAL; + } + ret_conn_info->status = le16_to_cpu(res->status_code); if (ret_conn_info->status == WLAN_STATUS_SUCCESS) { ies = &buffer[sizeof(*res)]; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c index cac191304bf5..b846fe589c2b 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c @@ -1429,7 +1429,7 @@ static irqreturn_t rt2400pci_interrupt(int irq, void *dev_instance) */ static int rt2400pci_validate_eeprom(struct rt2x00_dev *rt2x00dev) { - struct eeprom_93cx6 eeprom; + struct eeprom_93cx6 eeprom = {}; u32 reg; u16 word; u8 *mac; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c index fc35b60e422c..be9df35acc33 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c @@ -1555,7 +1555,7 @@ static irqreturn_t rt2500pci_interrupt(int irq, void *dev_instance) */ static int rt2500pci_validate_eeprom(struct rt2x00_dev *rt2x00dev) { - struct eeprom_93cx6 eeprom; + struct eeprom_93cx6 eeprom = {}; u32 reg; u16 word; u8 *mac; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800pci.c b/drivers/net/wireless/ralink/rt2x00/rt2800pci.c index 4fa14bb573ad..2596b9fcc7dd 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800pci.c @@ -108,7 +108,7 @@ static void rt2800pci_eepromregister_write(struct eeprom_93cx6 *eeprom) static int rt2800pci_read_eeprom_pci(struct rt2x00_dev *rt2x00dev) { - struct eeprom_93cx6 eeprom; + struct eeprom_93cx6 eeprom = {}; u32 reg; reg = rt2x00mmio_register_read(rt2x00dev, E2PROM_CSR); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c index 82fb230a73bb..4d94b7062f44 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c @@ -1388,7 +1388,7 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev) GFP_KERNEL); if (!rt2x00dev->drv_data) { retval = -ENOMEM; - goto exit; + return retval; } } @@ -1422,7 +1422,7 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev) alloc_ordered_workqueue("%s", 0, wiphy_name(rt2x00dev->hw->wiphy)); if (!rt2x00dev->workqueue) { retval = -ENOMEM; - goto exit; + goto exit_free_drv_data; } INIT_WORK(&rt2x00dev->intf_work, rt2x00lib_intf_scheduled); @@ -1495,6 +1495,14 @@ exit: rt2x00lib_remove_dev(rt2x00dev); return retval; + +exit_free_drv_data: + clear_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags); + + kfree(rt2x00dev->drv_data); + rt2x00dev->drv_data = NULL; + + return retval; } EXPORT_SYMBOL_GPL(rt2x00lib_probe_dev); diff --git a/drivers/net/wireless/ralink/rt2x00/rt61pci.c b/drivers/net/wireless/ralink/rt2x00/rt61pci.c index 79e1fd0a1fbd..d4783658b2c5 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt61pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt61pci.c @@ -2298,7 +2298,7 @@ static irqreturn_t rt61pci_interrupt(int irq, void *dev_instance) */ static int rt61pci_validate_eeprom(struct rt2x00_dev *rt2x00dev) { - struct eeprom_93cx6 eeprom; + struct eeprom_93cx6 eeprom = {}; u32 reg; u16 word; u8 *mac; diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c index a0c36144eb0b..501071104a9f 100644 --- a/drivers/net/wireless/rsi/rsi_91x_hal.c +++ b/drivers/net/wireless/rsi/rsi_91x_hal.c @@ -431,6 +431,7 @@ int rsi_prepare_beacon(struct rsi_common *common, struct sk_buff *skb) struct ieee80211_vif *vif; struct sk_buff *mac_bcn; u8 vap_id = 0, i; + unsigned int tailroom; u16 tim_offset = 0; for (i = 0; i < RSI_MAX_VIFS; i++) { @@ -480,6 +481,13 @@ int rsi_prepare_beacon(struct rsi_common *common, struct sk_buff *skb) if (mac_bcn->data[tim_offset + 2] == 0) bcn_frm->frame_info |= cpu_to_le16(RSI_DATA_DESC_DTIM_BEACON); + tailroom = skb_tailroom(skb); + if (tailroom < FRAME_DESC_SZ || + mac_bcn->len > tailroom - FRAME_DESC_SZ) { + dev_kfree_skb(mac_bcn); + return -EMSGSIZE; + } + memcpy(&skb->data[FRAME_DESC_SZ], mac_bcn->data, mac_bcn->len); skb_put(skb, mac_bcn->len + FRAME_DESC_SZ); diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c index 7f2c1608f2ce..bb167f03367b 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c +++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c @@ -848,8 +848,10 @@ int rsi_hal_load_key(struct rsi_common *common, } else { memcpy(&set_key->key[0][0], data, key_len); } - memcpy(set_key->tx_mic_key, &data[16], 8); - memcpy(set_key->rx_mic_key, &data[24], 8); + if (cipher == WLAN_CIPHER_SUITE_TKIP) { + memcpy(set_key->tx_mic_key, &data[16], 8); + memcpy(set_key->rx_mic_key, &data[24], 8); + } } else { memset(&set_key[FRAME_DESC_SZ], 0, frame_len - FRAME_DESC_SZ); } @@ -1911,6 +1913,12 @@ int rsi_send_bgscan_probe_req(struct rsi_common *common, return -ENOMEM; } + if (probereq_skb->len > MAX_BGSCAN_PROBE_REQ_LEN) { + dev_kfree_skb(probereq_skb); + dev_kfree_skb(skb); + return -EINVAL; + } + memcpy(&skb->data[frame_len], probereq_skb->data, probereq_skb->len); bgscan->probe_req_length = cpu_to_le16(probereq_skb->len); diff --git a/drivers/net/wireless/virtual/mac80211_hwsim_main.c b/drivers/net/wireless/virtual/mac80211_hwsim_main.c index 0dd8a6c85953..75caa97becc8 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim_main.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim_main.c @@ -870,9 +870,9 @@ static const struct nla_policy hwsim_genl_policy[HWSIM_ATTR_MAX + 1] = { [HWSIM_ATTR_FLAGS] = { .type = NLA_U32 }, [HWSIM_ATTR_RX_RATE] = { .type = NLA_U32 }, [HWSIM_ATTR_SIGNAL] = { .type = NLA_U32 }, - [HWSIM_ATTR_TX_INFO] = { .type = NLA_BINARY, - .len = IEEE80211_TX_MAX_RATES * - sizeof(struct hwsim_tx_rate)}, + [HWSIM_ATTR_TX_INFO] = + NLA_POLICY_EXACT_LEN(IEEE80211_TX_MAX_RATES * + sizeof(struct hwsim_tx_rate)), [HWSIM_ATTR_COOKIE] = { .type = NLA_U64 }, [HWSIM_ATTR_CHANNELS] = { .type = NLA_U32 }, [HWSIM_ATTR_RADIO_ID] = { .type = NLA_U32 }, @@ -1324,6 +1324,17 @@ static void mac80211_hwsim_set_tsf(struct ieee80211_hw *hw, } } +static struct ieee80211_rate * +mac80211_hwsim_get_tx_rate(struct ieee80211_hw *hw, + struct ieee80211_tx_info *info) +{ + if (info->control.rates[0].flags & + (IEEE80211_TX_RC_MCS | IEEE80211_TX_RC_VHT_MCS)) + return NULL; + + return ieee80211_get_tx_rate(hw, info); +} + static void mac80211_hwsim_monitor_rx(struct ieee80211_hw *hw, struct sk_buff *tx_skb, struct ieee80211_channel *chan) @@ -1333,7 +1344,7 @@ static void mac80211_hwsim_monitor_rx(struct ieee80211_hw *hw, struct hwsim_radiotap_hdr *hdr; u16 flags, bitrate; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_skb); - struct ieee80211_rate *txrate = ieee80211_get_tx_rate(hw, info); + struct ieee80211_rate *txrate = mac80211_hwsim_get_tx_rate(hw, info); if (!txrate) bitrate = 0; @@ -1603,7 +1614,7 @@ static void mac80211_hwsim_write_tsf(struct mac80211_hwsim_data *data, spin_lock_bh(&data->tsf_offset_lock); - txrate = ieee80211_get_tx_rate(data->hw, info); + txrate = mac80211_hwsim_get_tx_rate(data->hw, info); if (txrate) bitrate = txrate->bitrate; @@ -7289,6 +7300,7 @@ static void hwsim_virtio_rx_work(struct work_struct *work) skb->data = skb->head; skb_reset_tail_pointer(skb); + len = min(len, skb_end_offset(skb)); skb_put(skb, len); hwsim_virtio_handle_cmd(skb); diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 3c9ef826551d..e835779b6f5f 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -1618,6 +1618,8 @@ static DEVICE_ATTR_RW(charge_control_end_threshold); static int asus_wmi_battery_add(struct power_supply *battery, struct acpi_battery_hook *hook) { + int ret, rv; + /* The WMI method does not provide a way to specific a battery, so we * just assume it is the first battery. * Note: On some newer ASUS laptops (Zenbook UM431DA), the primary/first @@ -1635,12 +1637,30 @@ static int asus_wmi_battery_add(struct power_supply *battery, struct acpi_batter /* The charge threshold is only reset when the system is power cycled, * and we can't read the current threshold, however the majority of - * platforms retains it, therefore signal the threshold as unknown - * until user explicitly sets it to a new value. + * platforms retains it. + * + * Setting a negative value would signal the threshold as unknown + * until user explicitly sets it to a new value, however to avoid + * regressing userspace, we initialize it to a value of 100. */ - charge_end_threshold = -1; + charge_end_threshold = 100; + ret = asus_wmi_set_devstate(ASUS_WMI_DEVID_RSOC, charge_end_threshold, &rv); + if (ret) { + pr_err("Failed to reset battery charge threshold\n"); + goto asus_wmi_battery_add_err; + } + + if (rv != 1) { + pr_err("Error in battery charge threshold reset\n"); + ret = -EIO; + goto asus_wmi_battery_add_err; + } return 0; +asus_wmi_battery_add_err: + device_remove_file(&battery->dev, + &dev_attr_charge_control_end_threshold); + return ret; } static int asus_wmi_battery_remove(struct power_supply *battery, struct acpi_battery_hook *hook) diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c index 3ae4557b32b4..5ab2215fdd7f 100644 --- a/drivers/platform/x86/intel/vsec.c +++ b/drivers/platform/x86/intel/vsec.c @@ -103,6 +103,12 @@ static void intel_vsec_remove_aux(void *data) auxiliary_device_uninit(data); } +static void intel_vsec_dev_free(struct intel_vsec_device *intel_vsec_dev) +{ + kfree(intel_vsec_dev->acpi_disc); + kfree(intel_vsec_dev); +} + static void intel_vsec_dev_release(struct device *dev) { struct intel_vsec_device *intel_vsec_dev = dev_to_ivdev(dev); @@ -111,8 +117,7 @@ static void intel_vsec_dev_release(struct device *dev) ida_free(intel_vsec_dev->ida, intel_vsec_dev->auxdev.id); - kfree(intel_vsec_dev->acpi_disc); - kfree(intel_vsec_dev); + intel_vsec_dev_free(intel_vsec_dev); } static const struct vsec_feature_dependency * @@ -218,20 +223,22 @@ int intel_vsec_add_aux(struct device *parent, struct auxiliary_device *auxdev = &intel_vsec_dev->auxdev; int ret, id; - if (!parent) + if (!parent) { + intel_vsec_dev_free(intel_vsec_dev); return -EINVAL; + } ret = xa_alloc(&auxdev_array, &intel_vsec_dev->id, intel_vsec_dev, PMT_XA_LIMIT, GFP_KERNEL); if (ret < 0) { - kfree(intel_vsec_dev); + intel_vsec_dev_free(intel_vsec_dev); return ret; } id = ida_alloc(intel_vsec_dev->ida, GFP_KERNEL); if (id < 0) { xa_erase(&auxdev_array, intel_vsec_dev->id); - kfree(intel_vsec_dev); + intel_vsec_dev_free(intel_vsec_dev); return id; } diff --git a/drivers/pmdomain/imx/imx8m-blk-ctrl.c b/drivers/pmdomain/imx/imx8m-blk-ctrl.c index 19e992d2ee3b..99d100e1d923 100644 --- a/drivers/pmdomain/imx/imx8m-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx8m-blk-ctrl.c @@ -54,6 +54,15 @@ struct imx8m_blk_ctrl_domain_data { * register. */ u32 mipi_phy_rst_mask; + + /* + * VC8000E reset de-assertion edge and AXI clock may have a timing issue. + * Workaround: Set bit2 (vc8000e_clk_en) of BLK_CLK_EN_CSR to 0 to gate off + * both AXI clock and VC8000E clock sent to VC8000E and AXI clock sent to + * VPU_NOC m_v_2 interface during VC8000E power up(VC8000E reset is + * de-asserted by HW) + */ + bool is_errata_err050531; }; #define DOMAIN_MAX_CLKS 4 @@ -108,7 +117,11 @@ static int imx8m_blk_ctrl_power_on(struct generic_pm_domain *genpd) dev_err(bc->dev, "failed to enable clocks\n"); goto bus_put; } - regmap_set_bits(bc->regmap, BLK_CLK_EN, data->clk_mask); + + if (data->is_errata_err050531) + regmap_clear_bits(bc->regmap, BLK_CLK_EN, data->clk_mask); + else + regmap_set_bits(bc->regmap, BLK_CLK_EN, data->clk_mask); /* power up upstream GPC domain */ ret = pm_runtime_get_sync(domain->power_dev); @@ -117,6 +130,9 @@ static int imx8m_blk_ctrl_power_on(struct generic_pm_domain *genpd) goto clk_disable; } + if (data->is_errata_err050531) + regmap_set_bits(bc->regmap, BLK_CLK_EN, data->clk_mask); + /* wait for reset to propagate */ udelay(5); @@ -511,12 +527,38 @@ static const struct imx8m_blk_ctrl_domain_data imx8mp_vpu_blk_ctl_domain_data[] .clk_mask = BIT(2), .path_names = (const char *[]){"vc8000e"}, .num_paths = 1, + .is_errata_err050531 = true, }, }; +static int imx8mp_vpu_power_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct imx8m_blk_ctrl *bc = container_of(nb, struct imx8m_blk_ctrl, + power_nb); + + if (action == GENPD_NOTIFY_ON) { + /* + * On power up we have no software backchannel to the GPC to + * wait for the ADB handshake to happen, so we just delay for a + * bit. On power down the GPC driver waits for the handshake. + */ + + udelay(5); + + /* set "fuse" bits to enable the VPUs */ + regmap_set_bits(bc->regmap, 0x8, 0xffffffff); + regmap_set_bits(bc->regmap, 0xc, 0xffffffff); + regmap_set_bits(bc->regmap, 0x10, 0xffffffff); + regmap_set_bits(bc->regmap, 0x14, 0xffffffff); + } + + return NOTIFY_OK; +} + static const struct imx8m_blk_ctrl_data imx8mp_vpu_blk_ctl_dev_data = { .max_reg = 0x18, - .power_notifier_fn = imx8mm_vpu_power_notifier, + .power_notifier_fn = imx8mp_vpu_power_notifier, .domains = imx8mp_vpu_blk_ctl_domain_data, .num_domains = ARRAY_SIZE(imx8mp_vpu_blk_ctl_domain_data), }; diff --git a/drivers/pmdomain/imx/imx93-blk-ctrl.c b/drivers/pmdomain/imx/imx93-blk-ctrl.c index 1afc78b034fa..243ce939ba68 100644 --- a/drivers/pmdomain/imx/imx93-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx93-blk-ctrl.c @@ -48,6 +48,8 @@ #define PRIO(X) (X) +#define BLK_CTRL_NO_PARENT UINT_MAX + struct imx93_blk_ctrl_domain; struct imx93_blk_ctrl { @@ -68,12 +70,18 @@ struct imx93_blk_ctrl_qos { u32 cfg_prio; }; +struct imx93_blk_ctrl_subdomain_link { + struct generic_pm_domain *parent; + struct generic_pm_domain *subdomain; +}; + struct imx93_blk_ctrl_domain_data { const char *name; const char * const *clk_names; int num_clks; u32 rst_mask; u32 clk_mask; + u32 parent; int num_qos; struct imx93_blk_ctrl_qos qos[DOMAIN_MAX_QOS]; }; @@ -203,6 +211,13 @@ static void imx93_release_pm_genpd(void *data) pm_genpd_remove(genpd); } +static void imx93_release_subdomain(void *data) +{ + struct imx93_blk_ctrl_subdomain_link *link = data; + + pm_genpd_remove_subdomain(link->parent, link->subdomain); +} + static struct lock_class_key blk_ctrl_genpd_lock_class; static int imx93_blk_ctrl_probe(struct platform_device *pdev) @@ -302,6 +317,34 @@ static int imx93_blk_ctrl_probe(struct platform_device *pdev) bc->onecell_data.domains[i] = &domain->genpd; } + for (i = 0; i < bc_data->num_domains; i++) { + struct imx93_blk_ctrl_domain *domain = &bc->domains[i]; + const struct imx93_blk_ctrl_domain_data *data = domain->data; + struct imx93_blk_ctrl_subdomain_link *link; + + if (bc_data->skip_mask & BIT(i) || + data->parent == BLK_CTRL_NO_PARENT) + continue; + + link = devm_kzalloc(dev, sizeof(*link), GFP_KERNEL); + if (!link) + return -ENOMEM; + + link->parent = &bc->domains[data->parent].genpd; + link->subdomain = &domain->genpd; + + ret = pm_genpd_add_subdomain(&bc->domains[data->parent].genpd, + &domain->genpd); + if (ret) + return dev_err_probe(dev, ret, "failed to add subdomain %s\n", + domain->genpd.name); + + ret = devm_add_action_or_reset(dev, imx93_release_subdomain, link); + if (ret) + return dev_err_probe(dev, ret, + "failed to add subdomain release callback\n"); + } + ret = devm_pm_runtime_enable(dev); if (ret) return dev_err_probe(dev, ret, "failed to enable pm-runtime\n"); @@ -326,8 +369,9 @@ static const struct imx93_blk_ctrl_domain_data imx93_media_blk_ctl_domain_data[] .name = "mediablk-mipi-dsi", .clk_names = (const char *[]){ "dsi" }, .num_clks = 1, - .rst_mask = BIT(11) | BIT(12), - .clk_mask = BIT(11) | BIT(12), + .rst_mask = BIT(11), + .clk_mask = BIT(11), + .parent = IMX93_MEDIABLK_PD_MIPI_PHY, }, [IMX93_MEDIABLK_PD_MIPI_CSI] = { .name = "mediablk-mipi-csi", @@ -335,6 +379,7 @@ static const struct imx93_blk_ctrl_domain_data imx93_media_blk_ctl_domain_data[] .num_clks = 2, .rst_mask = BIT(9) | BIT(10), .clk_mask = BIT(9) | BIT(10), + .parent = IMX93_MEDIABLK_PD_MIPI_PHY, }, [IMX93_MEDIABLK_PD_PXP] = { .name = "mediablk-pxp", @@ -342,6 +387,7 @@ static const struct imx93_blk_ctrl_domain_data imx93_media_blk_ctl_domain_data[] .num_clks = 1, .rst_mask = BIT(7) | BIT(8), .clk_mask = BIT(7) | BIT(8), + .parent = BLK_CTRL_NO_PARENT, .num_qos = 2, .qos = { { @@ -363,6 +409,7 @@ static const struct imx93_blk_ctrl_domain_data imx93_media_blk_ctl_domain_data[] .num_clks = 2, .rst_mask = BIT(4) | BIT(5) | BIT(6), .clk_mask = BIT(4) | BIT(5) | BIT(6), + .parent = BLK_CTRL_NO_PARENT, .num_qos = 1, .qos = { { @@ -379,6 +426,7 @@ static const struct imx93_blk_ctrl_domain_data imx93_media_blk_ctl_domain_data[] .num_clks = 1, .rst_mask = BIT(2) | BIT(3), .clk_mask = BIT(2) | BIT(3), + .parent = BLK_CTRL_NO_PARENT, .num_qos = 4, .qos = { { @@ -404,6 +452,14 @@ static const struct imx93_blk_ctrl_domain_data imx93_media_blk_ctl_domain_data[] } } }, + [IMX93_MEDIABLK_PD_MIPI_PHY] = { + .name = "mediablk-mipi-phy", + .clk_names = NULL, + .num_clks = 0, + .rst_mask = BIT(12), + .clk_mask = BIT(12), + .parent = BLK_CTRL_NO_PARENT, + }, }; static const struct regmap_range imx93_media_blk_ctl_yes_ranges[] = { diff --git a/drivers/pmdomain/mediatek/mtk-pm-domains.c b/drivers/pmdomain/mediatek/mtk-pm-domains.c index e1cfd4223473..f0a6339affd7 100644 --- a/drivers/pmdomain/mediatek/mtk-pm-domains.c +++ b/drivers/pmdomain/mediatek/mtk-pm-domains.c @@ -393,9 +393,8 @@ err_infra: return ret; }; -static int scpsys_hwv_power_off(struct generic_pm_domain *genpd) +static int scpsys_hwv_power_off_internal(struct scpsys_domain *pd) { - struct scpsys_domain *pd = container_of(genpd, struct scpsys_domain, genpd); const struct scpsys_hwv_domain_data *hwv = pd->hwv_data; struct scpsys *scpsys = pd->scpsys; u32 val; @@ -464,6 +463,13 @@ err_infra: return ret; }; +static int scpsys_hwv_power_off(struct generic_pm_domain *genpd) +{ + struct scpsys_domain *pd = container_of(genpd, struct scpsys_domain, genpd); + + return scpsys_hwv_power_off_internal(pd); +} + static int scpsys_ctl_pwrseq_on(struct scpsys_domain *pd) { struct scpsys *scpsys = pd->scpsys; @@ -694,9 +700,8 @@ err_reg: return ret; } -static int scpsys_power_off(struct generic_pm_domain *genpd) +static int scpsys_power_off_internal(struct scpsys_domain *pd) { - struct scpsys_domain *pd = container_of(genpd, struct scpsys_domain, genpd); struct scpsys *scpsys = pd->scpsys; bool tmp; int ret; @@ -737,6 +742,13 @@ static int scpsys_power_off(struct generic_pm_domain *genpd) return 0; } +static int scpsys_power_off(struct generic_pm_domain *genpd) +{ + struct scpsys_domain *pd = container_of(genpd, struct scpsys_domain, genpd); + + return scpsys_power_off_internal(pd); +} + static struct generic_pm_domain *scpsys_add_one_domain(struct scpsys *scpsys, struct device_node *node) { @@ -884,7 +896,14 @@ generic_pm_domain *scpsys_add_one_domain(struct scpsys *scpsys, struct device_no * late_init time. */ if (MTK_SCPD_CAPS(pd, MTK_SCPD_KEEP_DEFAULT_OFF)) { - if (scpsys_domain_is_on(pd)) + bool domain_is_on; + + if (scpsys->soc_data->type == SCPSYS_MTCMOS_TYPE_HW_VOTER) + domain_is_on = scpsys_hwv_domain_is_enable_done(pd); + else + domain_is_on = scpsys_domain_is_on(pd); + + if (domain_is_on) dev_warn(scpsys->dev, "%pOF: A default off power domain has been ON\n", node); } else { @@ -973,6 +992,7 @@ err_put_node: static void scpsys_remove_one_domain(struct scpsys_domain *pd) { + struct scpsys *scpsys = pd->scpsys; int ret; /* @@ -984,8 +1004,14 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd) dev_err(pd->scpsys->dev, "failed to remove domain '%s' : %d - state may be inconsistent\n", pd->genpd.name, ret); - if (scpsys_domain_is_on(pd)) - scpsys_power_off(&pd->genpd); + + if (scpsys->soc_data->type == SCPSYS_MTCMOS_TYPE_HW_VOTER) { + if (scpsys_hwv_domain_is_enable_done(pd)) + scpsys_hwv_power_off_internal(pd); + } else { + if (scpsys_domain_is_on(pd)) + scpsys_power_off_internal(pd); + } clk_bulk_put(pd->num_clks, pd->clks); clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks); diff --git a/drivers/ptp/ptp_netc.c b/drivers/ptp/ptp_netc.c index 94e952ee6990..5e381c354d74 100644 --- a/drivers/ptp/ptp_netc.c +++ b/drivers/ptp/ptp_netc.c @@ -779,6 +779,7 @@ static void netc_timer_init(struct netc_timer *priv) netc_timer_wr(priv, NETC_TMR_FIPER_CTRL, fiper_ctrl); netc_timer_wr(priv, NETC_TMR_ECTRL, NETC_TMR_DEFAULT_ETTF_THR); + netc_timer_offset_write(priv, 0); ktime_get_real_ts64(&now); ns = timespec64_to_ns(&now); netc_timer_cnt_write(priv, ns); diff --git a/drivers/ptp/ptp_s390.c b/drivers/ptp/ptp_s390.c index 29618eb9bf44..02d624d89a0a 100644 --- a/drivers/ptp/ptp_s390.c +++ b/drivers/ptp/ptp_s390.c @@ -107,6 +107,9 @@ static __init int ptp_s390_init(void) if (IS_ERR(ptp_stcke_clock)) return PTR_ERR(ptp_stcke_clock); + if (!test_facility(28) || !ptff_query(PTFF_QPT)) + return 0; + ptp_qpt_clock = ptp_clock_register(&ptp_s390_qpt_info, NULL); if (IS_ERR(ptp_qpt_clock)) { ptp_clock_unregister(ptp_stcke_clock); @@ -117,7 +120,8 @@ static __init int ptp_s390_init(void) static __exit void ptp_s390_exit(void) { - ptp_clock_unregister(ptp_qpt_clock); + if (ptp_qpt_clock) + ptp_clock_unregister(ptp_qpt_clock); ptp_clock_unregister(ptp_stcke_clock); } diff --git a/drivers/regulator/ltc3676.c b/drivers/regulator/ltc3676.c index 73d511eb1c1d..768cdce0d4ec 100644 --- a/drivers/regulator/ltc3676.c +++ b/drivers/regulator/ltc3676.c @@ -45,11 +45,11 @@ #define LTC3676_DVBxA_REF_SELECT BIT(5) #define LTC3676_DVBxB_PGOOD_MASK BIT(5) -#define LTC3676_IRQSTAT_PGOOD_TIMEOUT BIT(3) -#define LTC3676_IRQSTAT_UNDERVOLT_WARN BIT(4) -#define LTC3676_IRQSTAT_UNDERVOLT_FAULT BIT(5) -#define LTC3676_IRQSTAT_THERMAL_WARN BIT(6) -#define LTC3676_IRQSTAT_THERMAL_FAULT BIT(7) +#define LTC3676_IRQSTAT_PGOOD_TIMEOUT BIT(2) +#define LTC3676_IRQSTAT_UNDERVOLT_WARN BIT(3) +#define LTC3676_IRQSTAT_UNDERVOLT_FAULT BIT(4) +#define LTC3676_IRQSTAT_THERMAL_WARN BIT(5) +#define LTC3676_IRQSTAT_THERMAL_FAULT BIT(6) enum ltc3676_reg { LTC3676_SW1, diff --git a/drivers/reset/reset-imx7.c b/drivers/reset/reset-imx7.c index dd01fe11c5cb..a3cb8244d76a 100644 --- a/drivers/reset/reset-imx7.c +++ b/drivers/reset/reset-imx7.c @@ -236,6 +236,12 @@ static int imx8mq_reset_set(struct reset_controller_dev *rcdev, case IMX8MQ_RESET_PCIE_CTRL_APPS_EN: case IMX8MQ_RESET_PCIE2_CTRL_APPS_EN: + case IMX8MQ_RESET_MIPI_CSI1_CORE_RESET: + case IMX8MQ_RESET_MIPI_CSI1_PHY_REF_RESET: + case IMX8MQ_RESET_MIPI_CSI1_ESC_RESET: + case IMX8MQ_RESET_MIPI_CSI2_CORE_RESET: + case IMX8MQ_RESET_MIPI_CSI2_PHY_REF_RESET: + case IMX8MQ_RESET_MIPI_CSI2_ESC_RESET: case IMX8MQ_RESET_MIPI_DSI_PCLK_RESET_N: case IMX8MQ_RESET_MIPI_DSI_ESC_RESET_N: case IMX8MQ_RESET_MIPI_DSI_DPI_RESET_N: diff --git a/drivers/reset/reset-sunxi.c b/drivers/reset/reset-sunxi.c index 2544de6576e4..2f6df7707cad 100644 --- a/drivers/reset/reset-sunxi.c +++ b/drivers/reset/reset-sunxi.c @@ -44,7 +44,7 @@ static int sunxi_reset_init(struct device_node *np) data->membase = ioremap(res.start, size); if (!data->membase) { ret = -ENOMEM; - goto err_alloc; + goto err_mem_region; } spin_lock_init(&data->lock); @@ -57,6 +57,8 @@ static int sunxi_reset_init(struct device_node *np) return reset_controller_register(&data->rcdev); +err_mem_region: + release_mem_region(res.start, size); err_alloc: kfree(data); return ret; diff --git a/drivers/reset/spacemit/reset-spacemit-k3.c b/drivers/reset/spacemit/reset-spacemit-k3.c index 9841f5e057b2..2e87f320cf11 100644 --- a/drivers/reset/spacemit/reset-spacemit-k3.c +++ b/drivers/reset/spacemit/reset-spacemit-k3.c @@ -112,7 +112,7 @@ static const struct ccu_reset_data k3_apmu_resets[] = { [RESET_APMU_SDH0] = RESET_DATA(APMU_SDH0_CLK_RES_CTRL, 0, BIT(1)), [RESET_APMU_SDH1] = RESET_DATA(APMU_SDH1_CLK_RES_CTRL, 0, BIT(1)), [RESET_APMU_SDH2] = RESET_DATA(APMU_SDH2_CLK_RES_CTRL, 0, BIT(1)), - [RESET_APMU_USB2_AHB] = RESET_DATA(APMU_USB_CLK_RES_CTRL, 0, BIT(1)), + [RESET_APMU_USB2_AHB] = RESET_DATA(APMU_USB_CLK_RES_CTRL, 0, BIT(0)), [RESET_APMU_USB2_VCC] = RESET_DATA(APMU_USB_CLK_RES_CTRL, 0, BIT(2)), [RESET_APMU_USB2_PHY] = RESET_DATA(APMU_USB_CLK_RES_CTRL, 0, BIT(3)), [RESET_APMU_USB3_A_AHB] = RESET_DATA(APMU_USB_CLK_RES_CTRL, 0, BIT(5)), diff --git a/drivers/scsi/bfa/bfa_fcs_lport.c b/drivers/scsi/bfa/bfa_fcs_lport.c index 2df399c537c1..8c9d423129c0 100644 --- a/drivers/scsi/bfa/bfa_fcs_lport.c +++ b/drivers/scsi/bfa/bfa_fcs_lport.c @@ -2627,7 +2627,7 @@ bfa_fcs_fdmi_get_hbaattr(struct bfa_fcs_lport_fdmi_s *fdmi, } -static void +static noinline_for_stack void bfa_fcs_fdmi_get_portattr(struct bfa_fcs_lport_fdmi_s *fdmi, struct bfa_fcs_fdmi_port_attr_s *port_attr) { diff --git a/drivers/scsi/elx/efct/efct_hw.c b/drivers/scsi/elx/efct/efct_hw.c index 1838032f6486..b79c6a7ea791 100644 --- a/drivers/scsi/elx/efct/efct_hw.c +++ b/drivers/scsi/elx/efct/efct_hw.c @@ -1997,6 +1997,8 @@ efct_hw_io_abort(struct efct_hw *hw, struct efct_hw_io *io_to_abort, wqcb = efct_hw_reqtag_alloc(hw, efct_hw_wq_process_abort, io_to_abort); if (!wqcb) { efc_log_err(hw->os, "can't allocate request tag\n"); + io_to_abort->abort_in_progress = false; + kref_put(&io_to_abort->ref, io_to_abort->release); return -ENOSPC; } diff --git a/drivers/scsi/elx/efct/efct_unsol.c b/drivers/scsi/elx/efct/efct_unsol.c index e6addab66a60..6a871a59c909 100644 --- a/drivers/scsi/elx/efct/efct_unsol.c +++ b/drivers/scsi/elx/efct/efct_unsol.c @@ -385,6 +385,7 @@ efct_dispatch_fcp_cmd(struct efct_node *node, struct efc_hw_sequence *seq) if (cmnd->fc_flags & FCP_CFL_LEN_MASK) { efc_log_err(efct, "Additional CDB not supported\n"); + efct_scsi_io_free(io); return -EIO; } /* diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index e047747d4ecf..46cc8e3c79a2 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -357,6 +357,7 @@ static void scsi_host_dev_release(struct device *dev) /* Wait for functions invoked through call_rcu(&scmd->rcu, ...) */ rcu_barrier(); + cancel_work_sync(&shost->eh_work); if (shost->tmf_work_q) destroy_workqueue(shost->tmf_work_q); if (shost->ehandler) @@ -422,6 +423,7 @@ struct Scsi_Host *scsi_host_alloc(const struct scsi_host_template *sht, int priv INIT_LIST_HEAD(&shost->starved_list); init_waitqueue_head(&shost->host_wait); mutex_init(&shost->scan_mutex); + INIT_WORK(&shost->eh_work, scsi_rcu_eh_wakeup); index = ida_alloc(&host_index_ida, GFP_KERNEL); if (index < 0) { diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index a1b116cd4723..8edad1830abe 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -5017,6 +5017,10 @@ static int hpsa_scsi_ioaccel2_queue_command(struct ctlr_info *h, if (phys_disk->in_reset) { cmd->result = DID_RESET << 16; + atomic_dec(&phys_disk->ioaccel_cmds_out); + scsi_dma_unmap(cmd); + if (use_sg > h->ioaccel_maxsg) + hpsa_unmap_ioaccel2_sg_chain_block(h, cp); return -1; } diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 82af59c913e9..23355f12fbff 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -8189,6 +8189,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) mempool_free(mboxq, phba->mbox_mem_pool); goto out_free_bsmbx; } + mempool_free(mboxq, phba->mbox_mem_pool); /* * 1 for cmd, 1 for rsp, NVME adds an extra one @@ -8311,8 +8312,6 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) goto out_free_sg_dma_buf; } - mempool_free(mboxq, phba->mbox_mem_pool); - /* Verify OAS is supported */ lpfc_sli4_oas_verify(phba); diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 147127fb4db9..453a2232452d 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -73,6 +73,26 @@ void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy) } } +void scsi_rcu_eh_wakeup(struct work_struct *work) +{ + struct Scsi_Host *shost = container_of(work, struct Scsi_Host, eh_work); + unsigned long flags; + unsigned int busy; + + /* + * Ensure any running scsi_dec_host_busy has completed its rcu section + * so changes to host state and host_eh_scheduled are visible to all + * future calls of scsi_dec_host_busy + */ + synchronize_rcu(); + + busy = scsi_host_busy(shost); + + spin_lock_irqsave(shost->host_lock, flags); + scsi_eh_wakeup(shost, busy); + spin_unlock_irqrestore(shost->host_lock, flags); +} + /** * scsi_schedule_eh - schedule EH for SCSI host * @shost: SCSI host to invoke error handling on. @@ -88,7 +108,7 @@ void scsi_schedule_eh(struct Scsi_Host *shost) if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 || scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) { shost->host_eh_scheduled++; - scsi_eh_wakeup(shost, scsi_host_busy(shost)); + queue_work(shost->tmf_work_q, &shost->eh_work); } spin_unlock_irqrestore(shost->host_lock, flags); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 22e2e3223440..daeb3693fe55 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2224,14 +2224,6 @@ struct scsi_device *scsi_device_from_queue(struct request_queue *q) return sdev; } -/* - * pktcdvd should have been integrated into the SCSI layers, but for historical - * reasons like the old IDE driver it isn't. This export allows it to safely - * probe if a given device is a SCSI one and only attach to that. - */ -#ifdef CONFIG_CDROM_PKTCDVD_MODULE -EXPORT_SYMBOL_GPL(scsi_device_from_queue); -#endif /** * scsi_block_requests - Utility function used by low-level drivers to prevent diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index 7a193cc04e5b..3dbf2ca59536 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -91,6 +91,7 @@ extern enum blk_eh_timer_return scsi_timeout(struct request *req); extern int scsi_error_handler(void *host); extern enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *cmd); extern void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy); +extern void scsi_rcu_eh_wakeup(struct work_struct *work); extern void scsi_eh_scmd_add(struct scsi_cmnd *); void scsi_eh_ready_devs(struct Scsi_Host *shost, struct list_head *work_q, @@ -102,6 +103,7 @@ void scsi_eh_done(struct scsi_cmnd *scmd); /* scsi_lib.c */ extern void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd); +extern struct scsi_device *scsi_device_from_queue(struct request_queue *q); extern void scsi_queue_insert(struct scsi_cmnd *cmd, enum scsi_qc_status reason); extern void scsi_io_completion(struct scsi_cmnd *, unsigned int); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 74cd4e8a61c2..5408f002e6c0 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -863,10 +863,9 @@ sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo) if (val >= SG_MAX_QUEUE) break; rinfo[val].req_state = srp->done + 1; - rinfo[val].problem = - srp->header.masked_status & - srp->header.host_status & - srp->header.driver_status; + rinfo[val].problem = srp->header.masked_status || + srp->header.host_status || + srp->header.driver_status; if (srp->done) rinfo[val].duration = srp->header.duration; diff --git a/drivers/soc/tegra/fuse/tegra-apbmisc.c b/drivers/soc/tegra/fuse/tegra-apbmisc.c index 5b0e9dae231f..6af69ccaa295 100644 --- a/drivers/soc/tegra/fuse/tegra-apbmisc.c +++ b/drivers/soc/tegra/fuse/tegra-apbmisc.c @@ -116,7 +116,7 @@ bool tegra_is_silicon(void) u32 tegra_read_straps(void) { - WARN(!chipid, "Tegra ABP MISC not yet available\n"); + WARN(!apbmisc_base, "Tegra ABP MISC not yet available\n"); return strapping; } diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index aaba1a3ad577..ecb0be394696 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -382,12 +382,16 @@ static irqreturn_t cqspi_irq_handler(int this_irq, void *dev) /* Clear interrupt */ writel(irq_status, cqspi->iobase + CQSPI_REG_IRQSTATUS); - if (cqspi->use_dma_read && ddata && ddata->get_dma_status) - irq_status = ddata->get_dma_status(cqspi); - else if (cqspi->slow_sram) + if (cqspi->use_dma_read && ddata && ddata->get_dma_status) { + if (ddata->get_dma_status(cqspi)) { + complete(&cqspi->transfer_complete); + return IRQ_HANDLED; + } + } else if (cqspi->slow_sram) { irq_status &= CQSPI_IRQ_MASK_RD_SLOW_SRAM | CQSPI_IRQ_MASK_WR; - else + } else { irq_status &= CQSPI_IRQ_MASK_RD | CQSPI_IRQ_MASK_WR; + } if (irq_status) complete(&cqspi->transfer_complete); diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c index bd70a7ed8067..f7d848fec9ab 100644 --- a/drivers/spi/spi-dw-dma.c +++ b/drivers/spi/spi-dw-dma.c @@ -282,7 +282,8 @@ static int dw_spi_dma_wait(struct dw_spi *dws, unsigned int len, u32 speed) static inline bool dw_spi_dma_tx_busy(struct dw_spi *dws) { - return !(dw_readl(dws, DW_SPI_SR) & DW_SPI_SR_TF_EMPT); + return (dw_readl(dws, DW_SPI_SR) & + (DW_SPI_SR_BUSY | DW_SPI_SR_TF_EMPT)) != DW_SPI_SR_TF_EMPT; } static int dw_spi_dma_wait_tx_done(struct dw_spi *dws, diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c index 87c5d26a5089..2853b95b2c59 100644 --- a/drivers/target/target_core_fabric_lib.c +++ b/drivers/target/target_core_fabric_lib.c @@ -290,13 +290,24 @@ static void sbp_parse_pr_out_transport_id(char *buf, char *i_str) static bool iscsi_parse_pr_out_transport_id( struct se_portal_group *se_tpg, char *buf, + u32 buf_len, u32 *out_tid_len, char **port_nexus_ptr, char *i_str) { char *p; + u32 tid_len; int i; - u8 format_code = (buf[0] & 0xc0); + u8 format_code; + + /* + * The 4-byte iSCSI TransportID header (FORMAT CODE + 2-byte ADDITIONAL + * LENGTH) must be present before any of it can be parsed. + */ + if (buf_len < 4) + return false; + + format_code = buf[0] & 0xc0; /* * Check for FORMAT CODE 00b or 01b from spc4r17, section 7.5.4.6: * @@ -316,15 +327,17 @@ static bool iscsi_parse_pr_out_transport_id( return false; } /* - * If the caller wants the TransportID Length, we set that value for the - * entire iSCSI Tarnsport ID now. + * Reconstruct the self-described TransportID length from the ADDITIONAL + * LENGTH field plus the 4-byte header. Reject it if it is below the + * spc4r17 section 7.5.4.6 minimum (ADDITIONAL LENGTH shall be at least + * 20) or if it runs past the bytes actually received, so that every + * access below stays inside the TransportID. */ - if (out_tid_len) { - /* The shift works thanks to integer promotion rules */ - *out_tid_len = get_unaligned_be16(&buf[2]); - /* Add four bytes for iSCSI Transport ID header */ - *out_tid_len += 4; - } + tid_len = get_unaligned_be16(&buf[2]) + 4; + if (tid_len < 24 || tid_len > buf_len) + return false; + if (out_tid_len) + *out_tid_len = tid_len; /* * Check for ',i,0x' separator between iSCSI Name and iSCSI Initiator @@ -332,16 +345,32 @@ static bool iscsi_parse_pr_out_transport_id( * format. */ if (format_code == 0x40) { - p = strstr(&buf[4], ",i,0x"); + p = strnstr(&buf[4], ",i,0x", tid_len - 4); if (!p) { - pr_err("Unable to locate \",i,0x\" separator" - " for Initiator port identifier: %s\n", - &buf[4]); + pr_err("Unable to locate \",i,0x\" separator in iSCSI TransportID\n"); + return false; + } + /* + * The iSCSI name runs from &buf[4] up to the separator; reject it + * if it cannot fit in i_str[TRANSPORT_IQN_LEN]. + */ + if (p - &buf[4] >= TRANSPORT_IQN_LEN) { + pr_err("iSCSI Initiator port name too long in TransportID\n"); return false; } *p = '\0'; /* Terminate iSCSI Name */ p += 5; /* Skip over ",i,0x" separator */ + /* + * The ISID must follow the separator. A ",i,0x" sitting at the + * very end of the TransportID leaves no ISID and would point the + * port nexus at buf + tid_len, i.e. past the descriptor, which + * the registration code then reads as the ISID string. + */ + if (p >= buf + tid_len) { + pr_err("Missing ISID in iSCSI Initiator port TransportID\n"); + return false; + } *port_nexus_ptr = p; /* * Go ahead and do the lower case conversion of the received @@ -349,7 +378,7 @@ static bool iscsi_parse_pr_out_transport_id( * for comparison against the running iSCSI session's ISID from * iscsi_target.c:lio_sess_get_initiator_sid() */ - for (i = 0; i < 12; i++) { + for (i = 0; i < 12 && p < buf + tid_len; i++) { /* * The first ISCSI INITIATOR SESSION ID field byte * containing an ASCII null character terminates the @@ -367,10 +396,22 @@ static bool iscsi_parse_pr_out_transport_id( *p = tolower(*p); p++; } - } else + strscpy(i_str, &buf[4], TRANSPORT_IQN_LEN); + } else { *port_nexus_ptr = NULL; - - strscpy(i_str, &buf[4], TRANSPORT_IQN_LEN); + /* + * FORMAT CODE 00b: the name occupies buf[4..tid_len-1]. The + * declared length tid_len - 4 must fit in i_str[TRANSPORT_IQN_LEN]. + * (For 01b the same tid_len bound would be over-restrictive: the + * descriptor also carries the separator and ISID, so a legal + * <=223-byte name gives tid_len up to 244.) + */ + if (tid_len - 4 >= TRANSPORT_IQN_LEN) { + pr_err("iSCSI Initiator port name too long in TransportID\n"); + return false; + } + strscpy(i_str, &buf[4], tid_len - 4); + } return true; } @@ -420,8 +461,16 @@ int target_get_pr_transport_id(struct se_node_acl *nacl, } bool target_parse_pr_out_transport_id(struct se_portal_group *tpg, - char *buf, u32 *out_tid_len, char **port_nexus_ptr, char *i_str) + char *buf, u32 buf_len, u32 *out_tid_len, + char **port_nexus_ptr, char *i_str) { + /* + * The fixed-length SAS/SRP/FCP/SBP TransportIDs are 24 bytes; the iSCSI + * format is variable and bounds itself against buf_len below. + */ + if (tpg->proto_id != SCSI_PROTOCOL_ISCSI && buf_len < 24) + return false; + switch (tpg->proto_id) { case SCSI_PROTOCOL_SAS: /* @@ -440,8 +489,8 @@ bool target_parse_pr_out_transport_id(struct se_portal_group *tpg, sbp_parse_pr_out_transport_id(buf, i_str); break; case SCSI_PROTOCOL_ISCSI: - return iscsi_parse_pr_out_transport_id(tpg, buf, out_tid_len, - port_nexus_ptr, i_str); + return iscsi_parse_pr_out_transport_id(tpg, buf, buf_len, + out_tid_len, port_nexus_ptr, i_str); default: pr_err("Unknown proto_id: 0x%02x\n", tpg->proto_id); return false; diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h index 763e6d26e187..f0886ea29034 100644 --- a/drivers/target/target_core_internal.h +++ b/drivers/target/target_core_internal.h @@ -104,7 +104,8 @@ int target_get_pr_transport_id(struct se_node_acl *nacl, struct t10_pr_registration *pr_reg, int *format_code, unsigned char *buf); bool target_parse_pr_out_transport_id(struct se_portal_group *tpg, - char *buf, u32 *out_tid_len, char **port_nexus_ptr, char *i_str); + char *buf, u32 buf_len, u32 *out_tid_len, + char **port_nexus_ptr, char *i_str); /* target_core_hba.c */ struct se_hba *core_alloc_hba(const char *, u32, u32); diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 11790f2c5d80..1a77b4bb62b0 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -1573,7 +1573,7 @@ core_scsi3_decode_spec_i_port( iport_ptr = NULL; tid_found = target_parse_pr_out_transport_id(tmp_tpg, - ptr, &tid_len, &iport_ptr, i_str); + ptr, tpdl, &tid_len, &iport_ptr, i_str); if (!tid_found) continue; /* @@ -3285,7 +3285,7 @@ core_scsi3_emulate_pro_register_and_move(struct se_cmd *cmd, u64 res_key, goto out; } tid_found = target_parse_pr_out_transport_id(dest_se_tpg, - &buf[24], &tmp_tid_len, &iport_ptr, initiator_str); + &buf[24], tid_len, &tmp_tid_len, &iport_ptr, initiator_str); if (!tid_found) { pr_err("SPC-3 PR REGISTER_AND_MOVE: Unable to locate" " initiator_str from Transport ID\n"); @@ -3293,9 +3293,6 @@ core_scsi3_emulate_pro_register_and_move(struct se_cmd *cmd, u64 res_key, goto out; } - transport_kunmap_data_sg(cmd); - buf = NULL; - pr_debug("SPC-3 PR [%s] Extracted initiator %s identifier: %s" " %s\n", dest_tf_ops->fabric_name, (iport_ptr != NULL) ? "port" : "device", initiator_str, (iport_ptr != NULL) ? @@ -3532,6 +3529,11 @@ after_iport_check: core_scsi3_update_and_write_aptpl(cmd->se_dev, aptpl); core_scsi3_put_pr_reg(dest_pr_reg); + /* + * iport_ptr aliases the PR-OUT parameter list mapped above, so the + * buffer is unmapped only here on success (and at out: on error). + */ + transport_kunmap_data_sg(cmd); return 0; out: if (buf) diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c index 4e71ed679a76..4266a0cb7e3b 100644 --- a/drivers/usb/atm/ueagle-atm.c +++ b/drivers/usb/atm/ueagle-atm.c @@ -2549,6 +2549,7 @@ static struct usbatm_driver uea_usbatm_driver = { static int uea_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *usb = interface_to_usbdev(intf); + bool single_iface = usb->config->desc.bNumInterfaces == 1; int ret; uea_dbg(usb, "ADSL device found with vid (%#X) pid (%#X) Rev (%#X): %s\n", @@ -2557,6 +2558,22 @@ static int uea_probe(struct usb_interface *intf, const struct usb_device_id *id) le16_to_cpu(usb->descriptor.bcdDevice), chip_name[UEA_CHIP_VERSION(id)]); + /* + * uea_probe() decides between the pre-firmware and post-firmware case + * from the USB id and stores a different object as interface data in + * each case: a struct completion for a pre-firmware device, a struct + * usbatm_data for a post-firmware one. uea_disconnect() instead tells + * the two apart by the number of interfaces (a pre-firmware device + * exposes a single interface, ADI930 has 2 and eagle has 3). A crafted + * device advertising a pre-firmware id together with a multi-interface + * descriptor (or the other way around) makes the two disagree, so that + * usbatm_usb_disconnect() treats the small completion object as a + * struct usbatm_data and reads out of bounds. Reject such inconsistent + * descriptors so both paths make the same decision. + */ + if (UEA_IS_PREFIRM(id) != single_iface) + return -ENODEV; + usb_reset_device(usb); if (UEA_IS_PREFIRM(id)) { diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 77b59f49bddb..3e72b9c6af0c 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -731,10 +731,12 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, goto err; } - gso = buf + pad - sock_hlen; - - if (!sock_hlen) + if (!sock_hlen) { memset(buf, 0, pad); + gso = buf; + } else { + gso = buf + pad - sock_hlen; + } if ((gso->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && vhost16_to_cpu(vq, gso->csum_start) + diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 088b3a0e6ce6..581ac799d974 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -1017,10 +1017,6 @@ static int virtballoon_probe(struct virtio_device *vdev) unsigned int capacity; capacity = virtqueue_get_vring_size(vb->reporting_vq); - if (capacity < PAGE_REPORTING_CAPACITY) { - err = -ENOSPC; - goto out_unregister_oom; - } vb->pr_dev_info.order = PAGE_REPORTING_ORDER_UNSPECIFIED; @@ -1041,6 +1037,7 @@ static int virtballoon_probe(struct virtio_device *vdev) vb->pr_dev_info.order = 5; #endif + vb->pr_dev_info.capacity = capacity; err = page_reporting_register(&vb->pr_dev_info); if (err) goto out_unregister_oom; diff --git a/drivers/watchdog/airoha_wdt.c b/drivers/watchdog/airoha_wdt.c index dc8ca11c14d8..4bd333189b87 100644 --- a/drivers/watchdog/airoha_wdt.c +++ b/drivers/watchdog/airoha_wdt.c @@ -147,6 +147,9 @@ static int airoha_wdt_probe(struct platform_device *pdev) /* Watchdog ticks at half the bus rate */ airoha_wdt->wdt_freq = clk_get_rate(bus_clk) / 2; + if (!airoha_wdt->wdt_freq) + return dev_err_probe(dev, -EINVAL, + "invalid clock frequency\n"); /* Initialize struct watchdog device */ wdog_dev = &airoha_wdt->wdog_dev; diff --git a/drivers/watchdog/ni903x_wdt.c b/drivers/watchdog/ni903x_wdt.c index 8b1b9baa914e..c72a9ee9cb8e 100644 --- a/drivers/watchdog/ni903x_wdt.c +++ b/drivers/watchdog/ni903x_wdt.c @@ -183,9 +183,14 @@ static int ni903x_acpi_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct watchdog_device *wdd; struct ni903x_wdt *wdt; + acpi_handle handle; acpi_status status; int ret; + handle = ACPI_HANDLE(dev); + if (!handle) + return -ENODEV; + wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL); if (!wdt) return -ENOMEM; @@ -193,7 +198,7 @@ static int ni903x_acpi_probe(struct platform_device *pdev) platform_set_drvdata(pdev, wdt); wdt->dev = dev; - status = acpi_walk_resources(ACPI_HANDLE(dev), METHOD_NAME__CRS, + status = acpi_walk_resources(handle, METHOD_NAME__CRS, ni903x_resources, wdt); if (ACPI_FAILURE(status) || wdt->io_base == 0) { dev_err(dev, "failed to get resources\n"); diff --git a/drivers/watchdog/s32g_wdt.c b/drivers/watchdog/s32g_wdt.c index ad55063060af..6422a694fc65 100644 --- a/drivers/watchdog/s32g_wdt.c +++ b/drivers/watchdog/s32g_wdt.c @@ -56,8 +56,7 @@ MODULE_PARM_DESC(early_enable, static const struct watchdog_info s32g_wdt_info = { .identity = "s32g watchdog", - .options = WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE | - WDIOC_GETTIMEOUT | WDIOC_GETTIMELEFT, + .options = WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE, }; static struct s32g_wdt_device *wdd_to_s32g_wdt(struct watchdog_device *wdd) diff --git a/drivers/watchdog/watchdog_pretimeout.c b/drivers/watchdog/watchdog_pretimeout.c index 19eb2ed2c7cb..02e09b9e396d 100644 --- a/drivers/watchdog/watchdog_pretimeout.c +++ b/drivers/watchdog/watchdog_pretimeout.c @@ -167,6 +167,8 @@ void watchdog_unregister_governor(struct watchdog_governor *gov) } spin_lock_irq(&pretimeout_lock); + if (default_gov == gov) + default_gov = NULL; list_for_each_entry(p, &pretimeout_list, entry) if (p->wdd->gov == gov) p->wdd->gov = default_gov; diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index e33f95c91b09..c7036e0e41bd 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -611,6 +611,25 @@ static void scsiback_disconnect(struct vscsibk_info *info) xenbus_unmap_ring_vfree(info->dev, info->ring.sring); } +/* + * Send the error response for a request that did not reach the target core + * and return its tag. Free the tag before the response drops the v2p + * reference that keeps the session alive, and snapshot what the response + * needs since returning the tag can let the slot be reused. + */ +static void scsiback_resp_and_free(struct vscsibk_pend *pending_req, + int32_t result) +{ + struct vscsibk_info *info = pending_req->info; + struct v2p_entry *v2p = pending_req->v2p; + struct se_session *se_sess = v2p->tpg->tpg_nexus->tvn_se_sess; + u16 rqid = pending_req->rqid; + + target_free_tag(se_sess, &pending_req->se_cmd); + scsiback_send_response(info, NULL, result, 0, rqid); + kref_put(&v2p->kref, scsiback_free_translation_entry); +} + static void scsiback_device_action(struct vscsibk_pend *pending_req, enum tcm_tmreq_table act, int tag) { @@ -639,7 +658,7 @@ static void scsiback_device_action(struct vscsibk_pend *pending_req, return; err: - scsiback_do_resp_with_sense(NULL, err, 0, pending_req); + scsiback_resp_and_free(pending_req, err); } /* @@ -792,9 +811,8 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info, case VSCSIIF_ACT_SCSI_CDB: if (scsiback_gnttab_data_map(&ring_req, pending_req)) { scsiback_fast_flush_area(pending_req); - scsiback_do_resp_with_sense(NULL, - DID_ERROR << 16, 0, pending_req); - transport_generic_free_cmd(&pending_req->se_cmd, 0); + scsiback_resp_and_free(pending_req, + DID_ERROR << 16); } else { scsiback_cmd_exec(pending_req); } @@ -808,9 +826,7 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info, break; default: pr_err_ratelimited("invalid request\n"); - scsiback_do_resp_with_sense(NULL, DID_ERROR << 16, 0, - pending_req); - transport_generic_free_cmd(&pending_req->se_cmd, 0); + scsiback_resp_and_free(pending_req, DID_ERROR << 16); break; } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 23c3eeb58dc1..1be632c742bd 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -3054,7 +3054,10 @@ void btrfs_backref_free_node(struct btrfs_backref_cache *cache, if (node) { ASSERT(list_empty(&node->list)); ASSERT(list_empty(&node->lower)); - ASSERT(node->eb == NULL, "node->eb->start=%llu", node->eb->start); + ASSERT(node->eb == NULL, "node->eb->start=%llu level=%d owner=%llu", + node->eb ? node->eb->start : 0, + node->eb ? btrfs_header_level(node->eb) : 0, + node->eb ? btrfs_header_owner(node->eb) : 0); cache->nr_nodes--; btrfs_put_root(node->root); kfree(node); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index d5d81f9546c3..7fdc6c3fd066 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -476,6 +476,8 @@ static inline bool btrfs_inode_can_compress(const struct btrfs_inode *inode) if (inode->flags & BTRFS_INODE_NODATACOW || inode->flags & BTRFS_INODE_NODATASUM) return false; + if (btrfs_is_data_reloc_root(inode->root)) + return false; return true; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 7d604524e83c..de5785117a47 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2004,7 +2004,7 @@ static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *e btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, - -eb->len, + -(s64)eb->len, fs_info->dirty_metadata_batch); ret = true; } else { @@ -3774,7 +3774,7 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans, return; buffer_tree_clear_mark(eb, PAGECACHE_TAG_DIRTY); - percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, -eb->len, + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, -(s64)eb->len, fs_info->dirty_metadata_batch); for (int i = 0; i < num_extent_folios(eb); i++) { diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index fce9c5cc0122..6ad7b39ae358 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -866,13 +866,13 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, goto next; } - flags = em->flags; /* * In case we split the extent map, we want to preserve the * EXTENT_FLAG_LOGGING flag on our extent map, but we don't want * it on the new extent maps. */ - em->flags &= ~(EXTENT_FLAG_PINNED | EXTENT_FLAG_LOGGING); + flags = em->flags & ~EXTENT_FLAG_LOGGING; + em->flags &= ~EXTENT_FLAG_PINNED; modified = !list_empty(&em->list); /* diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 9f6454e9db81..cf50fd623f41 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -358,6 +358,7 @@ int btrfs_lookup_bio_sums(struct btrfs_bio *bbio) const unsigned int nblocks = orig_len >> fs_info->sectorsize_bits; int ret = 0; u32 bio_offset = 0; + bool using_commit_root = false; if ((inode->flags & BTRFS_INODE_NODATASUM) || test_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state)) @@ -431,6 +432,7 @@ int btrfs_lookup_bio_sums(struct btrfs_bio *bbio) * from across transactions. */ if (bbio->csum_search_commit_root) { + using_commit_root = true; path->search_commit_root = true; path->skip_locking = true; down_read(&fs_info->commit_root_sem); @@ -463,6 +465,28 @@ int btrfs_lookup_bio_sums(struct btrfs_bio *bbio) * assume this is the case. */ if (count == 0) { + /* + * If an extent is relocated in the current transaction + * then relocation writes a new csum without updating + * the extent map generation. Until the next commit, we + * will see a hole in that case, so we need to fallback + * to searching the transaction csum root. + * + * Note that a commit root lookup of a referenced extent can + * only miss, not return a stale csum. A freed extent's csum + * is deleted in the same transaction and its bytenr is not + * reusable until that transaction has committed and the + * extent is unpinned. + */ + if (using_commit_root) { + up_read(&fs_info->commit_root_sem); + using_commit_root = false; + path->search_commit_root = false; + path->skip_locking = false; + btrfs_release_path(path); + continue; + } + memset(csum_dst, 0, csum_size); count = 1; @@ -481,7 +505,7 @@ int btrfs_lookup_bio_sums(struct btrfs_bio *bbio) bio_offset += count * sectorsize; } - if (bbio->csum_search_commit_root) + if (using_commit_root) up_read(&fs_info->commit_root_sem); return ret; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 6009b1477232..e2af75a205ea 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -551,6 +551,9 @@ static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index) u32 crc = ~(u32)0; unsigned offset = 0; + if (index >= io_ctl->num_pages) + return -EIO; + if (index == 0) offset = sizeof(u32) * io_ctl->num_pages; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 272598f6ae77..b446c3014b24 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8068,7 +8068,8 @@ static int btrfs_getattr(struct mnt_idmap *idmap, stat->result_mask |= STATX_SUBVOL; spin_lock(&BTRFS_I(inode)->lock); - delalloc_bytes = BTRFS_I(inode)->new_delalloc_bytes; + delalloc_bytes = S_ISREG(inode->i_mode) ? + BTRFS_I(inode)->new_delalloc_bytes : 0; inode_bytes = inode_get_bytes(inode); spin_unlock(&BTRFS_I(inode)->lock); stat->blocks = (ALIGN(inode_bytes, blocksize) + diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 9d47d16394fc..68b33f365fda 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -289,6 +289,7 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, int ret; const char *comp = NULL; u32 inode_flags; + bool prop_set = false; if (btrfs_root_readonly(root)) return -EROFS; @@ -401,16 +402,15 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, if (comp) { ret = btrfs_set_prop(trans, inode, "btrfs.compression", comp, strlen(comp), 0); - if (unlikely(ret)) { - btrfs_abort_transaction(trans, ret); + if (ret) goto out_end_trans; - } + prop_set = true; } else { ret = btrfs_set_prop(trans, inode, "btrfs.compression", NULL, 0, 0); - if (unlikely(ret && ret != -ENODATA)) { - btrfs_abort_transaction(trans, ret); + prop_set = (ret == 0); + /* If ret == -ENODATA ignore and proceed to update inode item. */ + if (ret && ret != -ENODATA) goto out_end_trans; - } } update_flags: @@ -420,6 +420,12 @@ update_flags: inode_inc_iversion(&inode->vfs_inode); inode_set_ctime_current(&inode->vfs_inode); ret = btrfs_update_inode(trans, inode); + /* + * If we set a property or deleted one, we must abort if we fail to + * update the inode, to avoid persisting an inconsistent state. + */ + if (unlikely(ret && prop_set)) + btrfs_abort_transaction(trans, ret); out_end_trans: btrfs_end_transaction(trans); @@ -2042,6 +2048,7 @@ static int _btrfs_ioctl_get_subvol_info(struct inode *inode, ret = -ENOENT; goto out; } + ret = 0; } out: diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index 6e4aa22853ab..1531adb117d1 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -552,17 +552,26 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in, size_t max_segment_len = workspace_buf_length(fs_info); int ret; - if (unlikely(srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)) + if (unlikely(srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)) { + btrfs_err(fs_info, "invalid lzo header length, has %zu expect (%u, %zu)", + srclen, LZO_LEN, max_segment_len + LZO_LEN * 2); return -EUCLEAN; + } in_len = get_unaligned_le32(data_in); - if (unlikely(in_len != srclen)) + if (unlikely(in_len != srclen)) { + btrfs_err(fs_info, "invalid lzo header length, has %zu expect %zu", + in_len, srclen); return -EUCLEAN; + } data_in += LZO_LEN; in_len = get_unaligned_le32(data_in); - if (unlikely(in_len != srclen - LZO_LEN * 2)) + if (unlikely(in_len != srclen - LZO_LEN * 2)) { + btrfs_err(fs_info, "invalid lzo segment length, has %zu expect %zu", + in_len, srclen - LZO_LEN * 2); return -EUCLEAN; + } data_in += LZO_LEN; out_len = sectorsize; diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 87e60a2d4bd8..53e726119ca7 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -449,9 +449,9 @@ void btrfs_print_leaf(const struct extent_buffer *l) nr = btrfs_header_nritems(l); btrfs_info(fs_info, - "leaf %llu gen %llu total ptrs %d free space %d owner %llu", + "leaf %llu gen %llu total ptrs %d free space %d owner %lld", btrfs_header_bytenr(l), btrfs_header_generation(l), nr, - btrfs_leaf_free_space(l), btrfs_header_owner(l)); + btrfs_leaf_free_space(l), (s64)btrfs_header_owner(l)); print_eb_refs_lock(l); for (i = 0 ; i < nr ; i++) { char key_buf[KEY_TYPE_BUF_SIZE]; @@ -600,10 +600,10 @@ void btrfs_print_tree(const struct extent_buffer *c, bool follow) return; } btrfs_info(fs_info, - "node %llu level %d gen %llu total ptrs %d free spc %u owner %llu", + "node %llu level %d gen %llu total ptrs %d free spc %u owner %lld", btrfs_header_bytenr(c), level, btrfs_header_generation(c), nr, (u32)BTRFS_NODEPTRS_PER_BLOCK(fs_info) - nr, - btrfs_header_owner(c)); + (s64)btrfs_header_owner(c)); print_eb_refs_lock(c); for (i = 0; i < nr; i++) { btrfs_node_key_to_cpu(c, &key, i); diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index adc956432d2f..bb77d46376d4 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -127,14 +127,24 @@ int btrfs_set_prop(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, return ret; } + ret = handler->validate(inode, value, value_len); + if (ret) + return ret; ret = btrfs_setxattr(trans, &inode->vfs_inode, handler->xattr_name, value, value_len, flags); if (ret) return ret; ret = handler->apply(inode, value, value_len); - if (ret) { - btrfs_setxattr(trans, &inode->vfs_inode, handler->xattr_name, NULL, - 0, flags); + /* We validated before, so it should not fail here. */ + ASSERT(ret == 0); + if (unlikely(ret)) { + int ret2; + + /* Try to delete xattr, if not possible abort transaction. */ + ret2 = btrfs_setxattr(trans, &inode->vfs_inode, handler->xattr_name, + NULL, 0, flags); + if (unlikely(ret2)) + btrfs_abort_transaction(trans, ret2); return ret; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index fb85bc8b345c..fc5c14b5adad 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -588,6 +588,7 @@ static int __add_reloc_root(struct btrfs_root *root, struct reloc_control *rc) btrfs_err(fs_info, "Duplicate root found for start=%llu while inserting into relocation tree", node->bytenr); + kfree(node); return -EEXIST; } @@ -719,21 +720,19 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans, ret = btrfs_insert_root(trans, fs_info->tree_root, &root_key, root_item); - if (ret) - goto abort; + if (unlikely(ret)) { + btrfs_abort_transaction(trans, ret); + return ERR_PTR(ret); + } reloc_root = btrfs_read_tree_root(fs_info->tree_root, &root_key); if (IS_ERR(reloc_root)) { - ret = PTR_ERR(reloc_root); - goto abort; + btrfs_abort_transaction(trans, PTR_ERR(reloc_root)); + return ERR_CAST(reloc_root); } set_bit(BTRFS_ROOT_SHAREABLE, &reloc_root->state); btrfs_set_root_last_trans(reloc_root, trans->transid); return reloc_root; - -abort: - btrfs_abort_transaction(trans, ret); - return ERR_PTR(ret); } /* @@ -892,6 +891,13 @@ static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr, leaf = path->nodes[0]; fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + if (unlikely(btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE)) { + btrfs_print_leaf(leaf); + btrfs_err(fs_info, + "unexpected inline file extent item for data reloc inode %llu key offset %llu", + btrfs_ino(BTRFS_I(reloc_inode)), bytenr); + return -EUCLEAN; + } /* * The cluster-boundary key searched above is always written by @@ -1520,6 +1526,17 @@ static int insert_dirty_subvol(struct btrfs_trans_handle *trans, return 0; } +static void clear_reloc_root(struct btrfs_root *root) +{ + root->reloc_root = NULL; + /* + * Need barrier to ensure clear_bit() only happens after + * root->reloc_root = NULL. Pairs with have_reloc_root(). + */ + smp_wmb(); + clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state); +} + static int clean_dirty_subvols(struct reloc_control *rc) { struct btrfs_root *root; @@ -1534,13 +1551,7 @@ static int clean_dirty_subvols(struct reloc_control *rc) struct btrfs_root *reloc_root = root->reloc_root; list_del_init(&root->reloc_dirty_list); - root->reloc_root = NULL; - /* - * Need barrier to ensure clear_bit() only happens after - * root->reloc_root = NULL. Pairs with have_reloc_root. - */ - smp_wmb(); - clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state); + clear_reloc_root(root); if (reloc_root) { /* * btrfs_drop_snapshot drops our ref we hold for @@ -1912,24 +1923,43 @@ again: * corruption, e.g. bad reloc tree key offset. */ ret = -EINVAL; + btrfs_put_root(root); goto out; } ret = merge_reloc_root(rc, root); - btrfs_put_root(root); if (ret) { - if (list_empty(&reloc_root->root_list)) + /* + * Clear the reloc root since below we will call + * free_reloc_roots(), otherwise we leave + * root->reloc_root pointing to a freed reloc + * root and trigger a use-after-free during + * unmount or elsewhere. + */ + clear_reloc_root(root); + btrfs_put_root(root); + /* + * We are adding the reloc_root to the local + * reloc_roots list, so we add a ref for this + * list which will be dropped below by the call + * to free_reloc_roots(). + */ + if (list_empty(&reloc_root->root_list)) { list_add_tail(&reloc_root->root_list, &reloc_roots); + btrfs_grab_root(reloc_root); + } + /* Now drop the ref for root->reloc_root. */ + btrfs_put_root(reloc_root); goto out; } + btrfs_put_root(root); } else { if (!IS_ERR(root)) { if (root->reloc_root == reloc_root) { - root->reloc_root = NULL; + clear_reloc_root(root); + /* Drop the ref for root->reloc_root. */ btrfs_put_root(reloc_root); } - clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, - &root->state); btrfs_put_root(root); } diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index 56060acac2e9..2a9397be8116 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -359,6 +359,23 @@ void btrfs_subpage_set_dirty(const struct btrfs_fs_info *fs_info, folio_mark_dirty(folio); } +static void folio_clear_tags(struct folio *folio) +{ + struct address_space *mapping = folio_mapping(folio); + XA_STATE(xas, &mapping->i_pages, folio->index); + unsigned long flags; + + ASSERT(folio_test_locked(folio)); + ASSERT(mapping); + ASSERT(mapping_use_writeback_tags(mapping)); + + xas_lock_irqsave(&xas, flags); + xas_load(&xas); + xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); + xas_unlock_irqrestore(&xas, flags); +} + /* * Extra clear_and_test function for subpage dirty bitmap. * @@ -403,7 +420,6 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info, unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, writeback, start, len); unsigned long flags; - bool keep_write; spin_lock_irqsave(&bfs->lock, flags); bitmap_set(bfs->bitmaps, start_bit, len >> fs_info->sectorsize_bits); @@ -413,10 +429,14 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info, * folio. Doing so can cause WB_SYNC_ALL writepages() to overlook it, * assume writeback is complete, and exit too early — violating sync * ordering guarantees. + * + * Instead we manually clear the DIRTY and TOWRITE tags after the folio + * is no longer dirty. */ - keep_write = folio_test_dirty(folio); if (!folio_test_writeback(folio)) - __folio_start_writeback(folio, keep_write); + __folio_start_writeback(folio, true); + if (!folio_test_dirty(folio)) + folio_clear_tags(folio); spin_unlock_irqrestore(&bfs->lock, flags); } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index cb3e676a81cc..0ce91396b517 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1923,6 +1923,12 @@ static int check_inode_ref(struct extent_buffer *leaf, iref = (struct btrfs_inode_ref *)ptr; namelen = btrfs_inode_ref_name_len(leaf, iref); + if (unlikely(namelen == 0 || namelen > BTRFS_NAME_LEN)) { + inode_ref_err(leaf, slot, + "invalid inode ref name length, has %u expect [1, %u]", + namelen, BTRFS_NAME_LEN); + return -EUCLEAN; + } if (unlikely(ptr + sizeof(*iref) + namelen > end)) { inode_ref_err(leaf, slot, "inode ref overflow, ptr %lu end %lu namelen %u", diff --git a/fs/erofs/ishare.c b/fs/erofs/ishare.c index 0868c12fc15b..a1a20a5ba548 100644 --- a/fs/erofs/ishare.c +++ b/fs/erofs/ishare.c @@ -12,12 +12,6 @@ static struct vfsmount *erofs_ishare_mnt; -static inline bool erofs_is_ishare_inode(struct inode *inode) -{ - /* assumed FS_ONDEMAND is excluded with FS_PAGE_CACHE_SHARE feature */ - return inode->i_sb->s_type == &erofs_anon_fs_type; -} - static int erofs_ishare_iget5_eq(struct inode *inode, void *data) { struct erofs_inode_fingerprint *fp1 = &EROFS_I(inode)->fingerprint; @@ -179,7 +173,7 @@ struct inode *erofs_real_inode(struct inode *inode, bool *need_iput) struct inode *realinode; *need_iput = false; - if (!erofs_is_ishare_inode(inode)) + if (inode->i_sb != erofs_ishare_mnt->mnt_sb) return inode; vi_share = EROFS_I(inode); diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 86fa5c6a0c70..9d8f862f309f 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -595,17 +595,6 @@ static const struct export_operations erofs_export_ops = { .get_parent = erofs_get_parent, }; -static void erofs_set_sysfs_name(struct super_block *sb) -{ - struct erofs_sb_info *sbi = EROFS_SB(sb); - - if (erofs_is_fileio_mode(sbi)) - super_set_sysfs_name_generic(sb, "%s", - bdi_dev_name(sb->s_bdi)); - else - super_set_sysfs_name_id(sb); -} - static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; @@ -657,12 +646,14 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) err = super_setup_bdi(sb); if (err) return err; + + snprintf(sb->s_id, sizeof(sb->s_id), + "%u:%u", MAJOR(sb->s_dev), MINOR(sb->s_dev)); } else { if (!sb_set_blocksize(sb, PAGE_SIZE)) { errorfc(fc, "failed to set initial blksize"); return -EINVAL; } - sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dif0.dax_part_off, NULL, NULL); } @@ -740,7 +731,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; - erofs_set_sysfs_name(sb); + super_set_sysfs_name_id(sb); err = erofs_register_sysfs(sb); if (err) return err; @@ -1038,7 +1029,7 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) ",user_xattr" : ",nouser_xattr"); if (IS_ENABLED(CONFIG_EROFS_FS_POSIX_ACL)) seq_puts(seq, test_opt(opt, POSIX_ACL) ? ",acl" : ",noacl"); - if (IS_ENABLED(CONFIG_EROFS_FS_ZIP)) + if (IS_ENABLED(CONFIG_EROFS_FS_ZIP) && sbi->available_compr_algs) seq_printf(seq, ",cache_strategy=%s", erofs_param_cache_strategy[opt->cache_strategy].name); if (test_opt(opt, DAX_ALWAYS)) diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index bab521613552..5811556a7b71 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -732,7 +732,8 @@ static int z_erofs_map_sanity_check(struct inode *inode, map->m_algorithmformat, EROFS_I(inode)->nid); return -EFSCORRUPTED; } - if (EROFS_MAP_FULL(map->m_flags) && map->m_llen < map->m_plen) { + if (EROFS_MAP_FULL(map->m_flags) && map->m_llen < map->m_plen && + map->m_la + map->m_llen < inode->i_size) { erofs_err(inode->i_sb, "too much compressed data @ la %llu of nid %llu", map->m_la, EROFS_I(inode)->nid); return -EFSCORRUPTED; diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 99ed9228a677..2772675bd35a 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -249,13 +249,13 @@ static inline unsigned char fat_checksum(const __u8 *name) return s; } -static inline sector_t fat_clus_to_blknr(struct msdos_sb_info *sbi, int clus) +static inline sector_t fat_clus_to_blknr(const struct msdos_sb_info *sbi, int clus) { return ((sector_t)clus - FAT_START_ENT) * sbi->sec_per_clus + sbi->data_start; } -static inline void fat_get_blknr_offset(struct msdos_sb_info *sbi, +static inline void fat_get_blknr_offset(const struct msdos_sb_info *sbi, loff_t i_pos, sector_t *blknr, int *offset) { *blknr = i_pos >> sbi->dir_per_block_bits; diff --git a/fs/fat/fat_test.c b/fs/fat/fat_test.c index 4eeed9dca549..9583ce66dca3 100644 --- a/fs/fat/fat_test.c +++ b/fs/fat/fat_test.c @@ -22,7 +22,7 @@ static void fat_checksum_test(struct kunit *test) static void fat_clus_to_blknr_test(struct kunit *test) { - struct msdos_sb_info sbi = { + static const struct msdos_sb_info sbi = { .sec_per_clus = 4, .data_start = 100, }; @@ -34,7 +34,7 @@ static void fat_clus_to_blknr_test(struct kunit *test) static void fat_get_blknr_offset_test(struct kunit *test) { - struct msdos_sb_info sbi = { + static const struct msdos_sb_info sbi = { .dir_per_block = 16, .dir_per_block_bits = 4, }; diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 4836887f11ef..386a881b520f 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -901,7 +901,8 @@ static __be32 nlmsvc_proc_granted_msg(struct svc_rqst *rqstp) if (argp->xdrgen.cookie.len > NLM_MAXCOOKIELEN) return rpc_garbage_args; - host = nlm3svc_lookup_host(rqstp, argp->xdrgen.alock.caller_name, false); + host = nlmsvc_lookup_host(rqstp, argp->xdrgen.alock.caller_name.data, + argp->xdrgen.alock.caller_name.len); if (!host) return rpc_system_err; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index d0486f4a47ba..fa92e31d19d6 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -2340,14 +2340,15 @@ int nfsd_nl_unlock_filesystem_doit(struct sk_buff *skb, if (error) return error; - nfsd4_cancel_copy_by_sb(net, path.dentry->d_sb); error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb); mutex_lock(&nfsd_mutex); - if (nn->nfsd_serv) + if (nn->nfsd_serv) { + nfsd4_cancel_copy_by_sb(net, path.dentry->d_sb); nfsd4_revoke_states(nn, path.dentry->d_sb); - else + } else { error = -EINVAL; + } mutex_unlock(&nfsd_mutex); path_put(&path); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 4df6ca03a8de..1788d93a2522 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -440,6 +440,7 @@ cifs_alloc_inode(struct super_block *sb) return NULL; cifs_inode->cifsAttrs = ATTR_ARCHIVE; /* default */ cifs_inode->time = 0; + cifs_inode->time_last_write = 0; /* * Until the file is open and we have gotten oplock info back from the * server, can not assume caching of file data or metadata. @@ -1490,9 +1491,13 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, } } - /* force revalidate of size and timestamps of target file now - that target is updated on the server */ - CIFS_I(target_inode)->time = 0; + /* + * On success, duplicate_extents already updated the target inode attrs + * or marked them stale if the refresh failed. On failure, mark attrs + * stale because EOF may have changed before the clone failed. + */ + if (rc) + CIFS_I(target_inode)->time = 0; unlock: /* although unlocking in the reverse order from locking is not strictly necessary here it is a little cleaner to be consistent */ diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 08e94633a9c1..79e4e84f8985 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1566,6 +1566,7 @@ struct cifsInodeInfo { spinlock_t writers_lock; unsigned int writers; /* Number of writers on this inode */ unsigned long time; /* jiffies of last update of inode */ + unsigned long time_last_write; /* jiffies of last writable close or truncate */ u64 uniqueid; /* server inode number */ u64 createtime; /* creation time on server */ __u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for this inode */ diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 968740e7c9c3..b279a44be729 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1423,11 +1423,21 @@ void smb2_deferred_work_close(struct work_struct *work) { struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, deferred.work); + struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry)); - spin_lock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); + spin_lock(&cinode->deferred_lock); cifs_del_deferred_close(cfile); cfile->deferred_close_scheduled = false; - spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); + spin_unlock(&cinode->deferred_lock); + /* + * Refresh time_last_write immediately before the actual server close + * so the protection window is anchored to the real close time, not + * the earlier userspace close time stored by cifs_close(). + */ + if (OPEN_FMODE(cfile->f_flags) & FMODE_WRITE) { + /* Pairs with smp_load_acquire() in is_size_safe_to_change(). */ + smp_store_release(&cinode->time_last_write, jiffies); + } _cifsFileInfo_put(cfile, true, false); } @@ -1457,6 +1467,10 @@ int cifs_close(struct inode *inode, struct file *file) if (file->private_data != NULL) { cfile = file->private_data; file->private_data = NULL; + if (file->f_mode & FMODE_WRITE) { + /* Pairs with smp_load_acquire() in is_size_safe_to_change(). */ + smp_store_release(&cinode->time_last_write, jiffies); + } dclose = kmalloc_obj(struct cifs_deferred_close); if ((cfile->status_file_deleted == false) && (smb2_can_defer_close(inode, dclose))) { @@ -3225,13 +3239,26 @@ static int is_inode_writable(struct cifsInodeInfo *cifs_inode) bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file, bool from_readdir) { + struct cifs_sb_info *cifs_sb; + unsigned long tlw; + if (!cifsInode) return true; + cifs_sb = CIFS_SB(cifsInode); + if (is_inode_writable(cifsInode) || ((cifsInode->oplock & CIFS_CACHE_RW_FLG) != 0 && from_readdir)) { /* This inode is open for write at least once */ - struct cifs_sb_info *cifs_sb = CIFS_SB(cifsInode); + + /* + * Readdir data is unreliable when we have writable handles or + * an exclusive lease -- never allow it to change i_size, even + * on direct-IO mounts where the server's directory metadata + * can still lag behind the actual file state. + */ + if (from_readdir) + return false; if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_DIRECT_IO) { /* since no page cache to corrupt on directio @@ -3243,8 +3270,40 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file, return true; return false; - } else - return true; + } + + /* + * No writable handles open. Check whether we are within the attribute + * cache validity window of a recent local modification. + * + * For the close() path: cifs_close() calls smp_store_release() on + * time_last_write before _cifsFileInfo_put() removes the handle under + * open_file_lock. That spin_unlock() is a store-release that pairs + * with the spin_lock() (load-acquire) in is_inode_writable() above, + * so if is_inode_writable() returned false the smp_load_acquire() + * below is guaranteed to observe any time_last_write update from a + * concurrent close(). + * + * For the setattr/truncate paths: those callers use smp_store_release() + * directly; the smp_load_acquire() below pairs with that store. There + * is no shared lock between setattr and readdir, so this relies on + * acquire-release semantics alone. The store propagation latency on + * weakly-ordered architectures (nanoseconds) is negligible relative to + * the acregmax window (seconds) and the readdir RPC round-trip + * (milliseconds), making this a sound design choice in practice. + * + * time_last_write == 0 means the inode has never been written locally; + * skip the window check to avoid false positives near boot time when + * jiffies is still close to INITIAL_JIFFIES on 32-bit systems. + */ + if (from_readdir) { + /* Pairs with smp_store_release() at close and truncate sites. */ + tlw = smp_load_acquire(&cifsInode->time_last_write); + if (tlw && time_before(jiffies, tlw + cifs_sb->ctx->acregmax)) + return false; + } + + return true; } void cifs_oplock_break(struct work_struct *work) diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index deed04dd9b91..b2806371bfde 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -237,6 +237,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, if (is_size_safe_to_change(cifs_i, fattr->cf_eof, from_readdir)) { i_size_write(inode, fattr->cf_eof); inode->i_blocks = CIFS_INO_BLOCKS(fattr->cf_bytes); + } else if (from_readdir && i_size_read(inode) != fattr->cf_eof) { + cifs_i->time = 0; } if (S_ISLNK(fattr->cf_mode) && fattr->cf_symlink_target) { @@ -3277,6 +3279,8 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) if ((attrs->ia_valid & ATTR_SIZE) && attrs->ia_size != i_size_read(inode)) { + /* Pairs with smp_load_acquire() in is_size_safe_to_change(). */ + smp_store_release(&cifsInode->time_last_write, jiffies); truncate_setsize(inode, attrs->ia_size); netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true); fscache_resize_cookie(cifs_inode_cookie(inode), attrs->ia_size); @@ -3478,6 +3482,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if ((attrs->ia_valid & ATTR_SIZE) && attrs->ia_size != i_size_read(inode)) { + /* Pairs with smp_load_acquire() in is_size_safe_to_change(). */ + smp_store_release(&cifsInode->time_last_write, jiffies); truncate_setsize(inode, attrs->ia_size); netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true); fscache_resize_cookie(cifs_inode_cookie(inode), attrs->ia_size); diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index e4bac2a0b85d..6edebc0807ea 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -497,7 +497,7 @@ cifs_del_deferred_close(struct cifsFileInfo *cfile) void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) { - struct cifsFileInfo *cfile = NULL; + struct cifsFileInfo *cfile = NULL, *failed_cfile = NULL; struct file_list *tmp_list, *tmp_next_list; LIST_HEAD(file_head); @@ -514,8 +514,10 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) tmp_list = kmalloc_obj(struct file_list, GFP_ATOMIC); - if (tmp_list == NULL) + if (tmp_list == NULL) { + failed_cfile = cfile; break; + } tmp_list->cfile = cfile; list_add_tail(&tmp_list->list, &file_head); } @@ -523,8 +525,24 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) } spin_unlock(&cifs_inode->open_file_lock); + if (failed_cfile) { + if (OPEN_FMODE(failed_cfile->f_flags) & FMODE_WRITE) { + /* Pairs with smp_load_acquire() in is_size_safe_to_change(). */ + smp_store_release(&CIFS_I(d_inode(failed_cfile->dentry))->time_last_write, + jiffies); + } + _cifsFileInfo_put(failed_cfile, false, false); + } + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { - _cifsFileInfo_put(tmp_list->cfile, false, false); + struct cifsFileInfo *cfile = tmp_list->cfile; + + if (OPEN_FMODE(cfile->f_flags) & FMODE_WRITE) { + /* Pairs with smp_load_acquire() in is_size_safe_to_change(). */ + smp_store_release(&CIFS_I(d_inode(cfile->dentry))->time_last_write, + jiffies); + } + _cifsFileInfo_put(cfile, false, false); list_del(&tmp_list->list); kfree(tmp_list); } @@ -533,7 +551,7 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) void cifs_close_all_deferred_files(struct cifs_tcon *tcon) { - struct cifsFileInfo *cfile; + struct cifsFileInfo *cfile, *failed_cfile = NULL; struct file_list *tmp_list, *tmp_next_list; LIST_HEAD(file_head); @@ -547,8 +565,10 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) tmp_list = kmalloc_obj(struct file_list, GFP_ATOMIC); - if (tmp_list == NULL) + if (tmp_list == NULL) { + failed_cfile = cfile; break; + } tmp_list->cfile = cfile; list_add_tail(&tmp_list->list, &file_head); } @@ -556,8 +576,24 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) } spin_unlock(&tcon->open_file_lock); + if (failed_cfile) { + if (OPEN_FMODE(failed_cfile->f_flags) & FMODE_WRITE) { + /* Pairs with smp_load_acquire() in is_size_safe_to_change(). */ + smp_store_release(&CIFS_I(d_inode(failed_cfile->dentry))->time_last_write, + jiffies); + } + _cifsFileInfo_put(failed_cfile, true, false); + } + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { - _cifsFileInfo_put(tmp_list->cfile, true, false); + struct cifsFileInfo *cfile = tmp_list->cfile; + + if (OPEN_FMODE(cfile->f_flags) & FMODE_WRITE) { + /* Pairs with smp_load_acquire() in is_size_safe_to_change(). */ + smp_store_release(&CIFS_I(d_inode(cfile->dentry))->time_last_write, + jiffies); + } + _cifsFileInfo_put(cfile, true, false); list_del(&tmp_list->list); kfree(tmp_list); } @@ -604,7 +640,7 @@ void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, struct dentry *dentry) { struct file_list *tmp_list, *tmp_next_list; - struct cifsFileInfo *cfile; + struct cifsFileInfo *cfile, *failed_cfile = NULL; LIST_HEAD(file_head); spin_lock(&tcon->open_file_lock); @@ -617,16 +653,34 @@ void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); tmp_list = kmalloc_obj(struct file_list, GFP_ATOMIC); - if (tmp_list == NULL) + if (tmp_list == NULL) { + failed_cfile = cfile; break; + } tmp_list->cfile = cfile; list_add_tail(&tmp_list->list, &file_head); } } spin_unlock(&tcon->open_file_lock); + if (failed_cfile) { + if (OPEN_FMODE(failed_cfile->f_flags) & FMODE_WRITE) { + /* Pairs with smp_load_acquire() in is_size_safe_to_change(). */ + smp_store_release(&CIFS_I(d_inode(failed_cfile->dentry))->time_last_write, + jiffies); + } + _cifsFileInfo_put(failed_cfile, true, false); + } + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { - _cifsFileInfo_put(tmp_list->cfile, true, false); + struct cifsFileInfo *cfile = tmp_list->cfile; + + if (OPEN_FMODE(cfile->f_flags) & FMODE_WRITE) { + /* Pairs with smp_load_acquire() in is_size_safe_to_change(). */ + smp_store_release(&CIFS_I(d_inode(cfile->dentry))->time_last_write, + jiffies); + } + _cifsFileInfo_put(cfile, true, false); list_del(&tmp_list->list); kfree(tmp_list); } @@ -682,6 +736,8 @@ parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, int i, rc = 0; char *data_end; struct dfs_referral_level_3 *ref; + unsigned int path_consumed; + size_t search_name_len; if (rsp_size < sizeof(*rsp)) { cifs_dbg(VFS | ONCE, @@ -728,6 +784,7 @@ parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, rc = -ENOMEM; goto parse_DFS_referrals_exit; } + search_name_len = strlen(searchName); /* collect necessary data from referrals */ for (i = 0; i < *num_of_nodes; i++) { @@ -736,21 +793,34 @@ parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, struct dfs_info3_param *node = (*target_nodes)+i; node->flags = le32_to_cpu(rsp->DFSFlags); + path_consumed = le16_to_cpu(rsp->PathConsumed); if (is_unicode) { - __le16 *tmp = kmalloc(strlen(searchName)*2 + 2, - GFP_KERNEL); - if (tmp == NULL) { + size_t search_name_utf16_len = search_name_len * 2 + 2; + __le16 *tmp; + + if (path_consumed > search_name_utf16_len) { + rc = -EINVAL; + goto parse_DFS_referrals_exit; + } + + tmp = kmalloc(search_name_utf16_len, GFP_KERNEL); + if (!tmp) { rc = -ENOMEM; goto parse_DFS_referrals_exit; } - cifsConvertToUTF16((__le16 *) tmp, searchName, + cifsConvertToUTF16((__le16 *)tmp, searchName, PATH_MAX, nls_codepage, remap); - node->path_consumed = cifs_utf16_bytes(tmp, - le16_to_cpu(rsp->PathConsumed), - nls_codepage); + node->path_consumed = cifs_utf16_bytes(tmp, path_consumed, + nls_codepage); kfree(tmp); - } else - node->path_consumed = le16_to_cpu(rsp->PathConsumed); + } else { + if (path_consumed > search_name_len) { + rc = -EINVAL; + goto parse_DFS_referrals_exit; + } + + node->path_consumed = path_consumed; + } node->server_type = le16_to_cpu(ref->ServerType); node->ref_flag = le16_to_cpu(ref->ReferralEntryFlags); diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index ee5996e6d7d8..32a75afca8f5 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -952,7 +952,7 @@ static bool cifs_dir_emit(struct dir_context *ctx, static int cifs_filldir(char *find_entry, struct file *file, struct dir_context *ctx, char *scratch_buf, unsigned int max_len, - struct cached_fid *cfid) + char *end_of_smb, struct cached_fid *cfid) { struct cifsFileInfo *file_info = file->private_data; struct super_block *sb = file_inode(file)->i_sb; @@ -974,6 +974,11 @@ static int cifs_filldir(char *find_entry, struct file *file, return -EINVAL; } + if (de.name + de.namelen > end_of_smb) { + cifs_dbg(VFS, "search entry name extends past end of SMB\n"); + return -EINVAL; + } + /* skip . and .. since we added them first */ if (cifs_entry_is_dot(&de, file_info->srch_inf.unicode)) return 0; @@ -1194,7 +1199,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) */ *tmp_buf = 0; rc = cifs_filldir(current_entry, file, ctx, - tmp_buf, max_len, cfid); + tmp_buf, max_len, end_of_smb, cfid); if (rc) { if (rc > 0) rc = 0; diff --git a/fs/smb/client/smb1maperror.c b/fs/smb/client/smb1maperror.c index 74530088d17d..ab3d09613c91 100644 --- a/fs/smb/client/smb1maperror.c +++ b/fs/smb/client/smb1maperror.c @@ -10,6 +10,9 @@ */ #include <linux/bsearch.h> + +#include <kunit/visibility.h> + #include "cifsproto.h" #include "smb1proto.h" #include "smberr.h" @@ -239,48 +242,45 @@ int __init smb1_init_maperror(void) } #if IS_ENABLED(CONFIG_SMB1_KUNIT_TESTS) -#define EXPORT_SYMBOL_FOR_SMB_TEST(sym) \ - EXPORT_SYMBOL_FOR_MODULES(sym, "smb1maperror_test") - const struct ntstatus_to_dos_err * search_ntstatus_to_dos_map_test(__u32 ntstatus) { return search_ntstatus_to_dos_map(ntstatus); } -EXPORT_SYMBOL_FOR_SMB_TEST(search_ntstatus_to_dos_map_test); +EXPORT_SYMBOL_IF_KUNIT(search_ntstatus_to_dos_map_test); const struct ntstatus_to_dos_err * ntstatus_to_dos_map_test = ntstatus_to_dos_map; -EXPORT_SYMBOL_FOR_SMB_TEST(ntstatus_to_dos_map_test); +EXPORT_SYMBOL_IF_KUNIT(ntstatus_to_dos_map_test); unsigned int ntstatus_to_dos_num = ARRAY_SIZE(ntstatus_to_dos_map); -EXPORT_SYMBOL_FOR_SMB_TEST(ntstatus_to_dos_num); +EXPORT_SYMBOL_IF_KUNIT(ntstatus_to_dos_num); const struct smb_to_posix_error * search_mapping_table_ERRDOS_test(__u16 smb_err) { return search_mapping_table_ERRDOS(smb_err); } -EXPORT_SYMBOL_FOR_SMB_TEST(search_mapping_table_ERRDOS_test); +EXPORT_SYMBOL_IF_KUNIT(search_mapping_table_ERRDOS_test); const struct smb_to_posix_error * mapping_table_ERRDOS_test = mapping_table_ERRDOS; -EXPORT_SYMBOL_FOR_SMB_TEST(mapping_table_ERRDOS_test); +EXPORT_SYMBOL_IF_KUNIT(mapping_table_ERRDOS_test); unsigned int mapping_table_ERRDOS_num = ARRAY_SIZE(mapping_table_ERRDOS); -EXPORT_SYMBOL_FOR_SMB_TEST(mapping_table_ERRDOS_num); +EXPORT_SYMBOL_IF_KUNIT(mapping_table_ERRDOS_num); const struct smb_to_posix_error * search_mapping_table_ERRSRV_test(__u16 smb_err) { return search_mapping_table_ERRSRV(smb_err); } -EXPORT_SYMBOL_FOR_SMB_TEST(search_mapping_table_ERRSRV_test); +EXPORT_SYMBOL_IF_KUNIT(search_mapping_table_ERRSRV_test); const struct smb_to_posix_error * mapping_table_ERRSRV_test = mapping_table_ERRSRV; -EXPORT_SYMBOL_FOR_SMB_TEST(mapping_table_ERRSRV_test); +EXPORT_SYMBOL_IF_KUNIT(mapping_table_ERRSRV_test); unsigned int mapping_table_ERRSRV_num = ARRAY_SIZE(mapping_table_ERRSRV); -EXPORT_SYMBOL_FOR_SMB_TEST(mapping_table_ERRSRV_num); +EXPORT_SYMBOL_IF_KUNIT(mapping_table_ERRSRV_num); #endif diff --git a/fs/smb/client/smb1maperror_test.c b/fs/smb/client/smb1maperror_test.c index 2caaf11228ef..903c46f71291 100644 --- a/fs/smb/client/smb1maperror_test.c +++ b/fs/smb/client/smb1maperror_test.c @@ -75,3 +75,4 @@ kunit_test_suite(maperror_suite); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("KUnit tests of SMB1 maperror"); +MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index 5ef919bce52d..f35b6488d810 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -30,6 +30,19 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) u8 *end = (u8 *)err + iov->iov_len; u32 len; + /* + * Per [MS-SMB2] section 2.2.2, a STATUS_STOPPED_ON_SYMLINK response has to + * carry a Symbolic Link Error Response, so ByteCount cannot be zero. Some + * servers (e.g. the macOS built-in SMB server) violate this and return an + * empty error response, with both ErrorContextCount and ByteCount set to + * zero, i.e. without the symlink target. Detect this and return -ENODATA + * so that callers can tell "server did not send the target" apart from a + * malformed response, and retrieve the target with FSCTL_GET_REPARSE_POINT + * instead. + */ + if (!err->ErrorContextCount && !le32_to_cpu(err->ByteCount)) + return ERR_PTR(-ENODATA); + if (err->ErrorContextCount) { struct smb2_error_context_rsp *p; @@ -199,6 +212,14 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, rc = smb2_parse_symlink_response(oparms->cifs_sb, &err_iov, oparms->path, &data->symlink_target); + /* + * If smb2_parse_symlink_response returned -ENODATA then the + * symlink_target was not sent. Treat this as if the SMB2_open() + * failed with STATUS_IO_REPARSE_TAG_NOT_HANDLED status, which is + * indicated by the -EIO errno. + */ + if (rc == -ENODATA) + rc = -EIO; if (!rc) { memset(&data->fi, 0, sizeof(data->fi)); oparms->create_options |= OPEN_REPARSE_POINT; diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 6c9c229b91f6..213bc298cdf2 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -792,9 +792,19 @@ static int parse_create_response(struct cifs_open_info_data *data, rc = smb2_parse_symlink_response(cifs_sb, iov, full_path, &data->symlink_target); - if (rc) + if (rc != 0 && rc != -ENODATA) return rc; - tag = IO_REPARSE_TAG_SYMLINK; + /* + * -ENODATA means that the response was parsed but did not contain + * the symlink target at all (see symlink_data()). Treat it like + * STATUS_IO_REPARSE_TAG_NOT_HANDLED, which does not contain it + * either: leave the tag unset and clear rc, so that the caller + * retrieves the target with SMB2_OP_GET_REPARSE. + */ + if (rc == -ENODATA) + rc = 0; + else + tag = IO_REPARSE_TAG_SYMLINK; reparse_point = true; break; case STATUS_SUCCESS: @@ -987,7 +997,14 @@ int smb2_query_path_info(const unsigned int xid, rc = -EOPNOTSUPP; } - if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) { + /* + * If the symlink was already parsed in create response then it is needed to fix + * its type now (after the second call with OPEN_REPARSE_POINT which filled the + * data->fi.Attributes). If the symlink was not parsed in create response then + * the data->symlink_target was not filled yet and then the type will be fixed + * later after data->symlink_target is filled. + */ + if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc && data->symlink_target) { bool directory = le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY; rc = smb2_fix_symlink_target_type(&data->symlink_target, directory, cifs_sb); } diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c index 9ed21f7b618c..d86f2460d0e5 100644 --- a/fs/smb/client/smb2maperror.c +++ b/fs/smb/client/smb2maperror.c @@ -8,6 +8,9 @@ * */ #include <linux/errno.h> + +#include <kunit/visibility.h> + #include "cifsproto.h" #include "cifs_debug.h" #include "smb2proto.h" @@ -109,18 +112,15 @@ int __init smb2_init_maperror(void) } #if IS_ENABLED(CONFIG_SMB_KUNIT_TESTS) -#define EXPORT_SYMBOL_FOR_SMB_TEST(sym) \ - EXPORT_SYMBOL_FOR_MODULES(sym, "smb2maperror_test") - const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status) { return smb2_get_err_map(smb2_status); } -EXPORT_SYMBOL_FOR_SMB_TEST(smb2_get_err_map_test); +EXPORT_SYMBOL_IF_KUNIT(smb2_get_err_map_test); const struct status_to_posix_error *smb2_error_map_table_test = smb2_error_map_table; -EXPORT_SYMBOL_FOR_SMB_TEST(smb2_error_map_table_test); +EXPORT_SYMBOL_IF_KUNIT(smb2_error_map_table_test); unsigned int smb2_error_map_num = ARRAY_SIZE(smb2_error_map_table); -EXPORT_SYMBOL_FOR_SMB_TEST(smb2_error_map_num); +EXPORT_SYMBOL_IF_KUNIT(smb2_error_map_num); #endif diff --git a/fs/smb/client/smb2maperror_test.c b/fs/smb/client/smb2maperror_test.c index 0f8a44a5ed3c..44dc5e899cad 100644 --- a/fs/smb/client/smb2maperror_test.c +++ b/fs/smb/client/smb2maperror_test.c @@ -47,3 +47,4 @@ kunit_test_suite(maperror_suite); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("KUnit tests of SMB2 maperror"); +MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 6270b33147d2..9068175e57cd 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -19,7 +19,8 @@ #include "nterr.h" #include "cached_dir.h" -static unsigned int __smb2_calc_size(void *buf, bool *have_data); +static unsigned int __smb2_calc_size(void *buf, bool *have_data, + bool *data_area_overlap); static int check_smb2_hdr(struct smb2_hdr *shdr, __u64 mid) @@ -148,6 +149,7 @@ smb2_check_message(char *buf, unsigned int pdu_len, unsigned int len, __u32 calc_len; /* calculated length */ __u64 mid; bool have_data; + bool data_area_overlap; /* If server is a channel, select the primary channel */ pserver = SERVER_IS_CHAN(server) ? server->primary_server : server; @@ -232,7 +234,12 @@ smb2_check_message(char *buf, unsigned int pdu_len, unsigned int len, } have_data = false; - calc_len = __smb2_calc_size(buf, &have_data); + data_area_overlap = false; + calc_len = __smb2_calc_size(buf, &have_data, &data_area_overlap); + + /* Reject responses whose data area overlaps the fixed area. */ + if (data_area_overlap) + return 1; /* For SMB2_IOCTL, OutputOffset and OutputLength are optional, so might * be 0, and not a real miscalculation */ @@ -416,14 +423,15 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) } /* - * Calculate the size of the SMB message based on the fixed header - * portion, the number of word parameters and the data portion of the message. - * If have_data is non-NULL, it is set to true when a non-empty data area was - * found (data_length > 0), allowing callers to distinguish the implied bcc[0] - * case (no data area) from an overreported data length. + * Calculate the size of the SMB message based on the fixed header, fixed + * parameter area, and variable data area. + * + * If have_data is not NULL, it is set when a non-empty data area is found. + * If data_area_overlap is not NULL, it is set when the data area overlaps + * the fixed area. */ static unsigned int -__smb2_calc_size(void *buf, bool *have_data) +__smb2_calc_size(void *buf, bool *have_data, bool *data_area_overlap) { struct smb2_pdu *pdu = buf; struct smb2_hdr *shdr = &pdu->hdr; @@ -432,6 +440,11 @@ __smb2_calc_size(void *buf, bool *have_data) /* Structure Size has already been checked to make sure it is 64 */ int len = le16_to_cpu(shdr->StructureSize); + if (have_data) + *have_data = false; + if (data_area_overlap) + *data_area_overlap = false; + /* * StructureSize2, ie length of fixed parameter area has already * been checked to make sure it is the correct length. @@ -454,7 +467,10 @@ __smb2_calc_size(void *buf, bool *have_data) if (offset + 1 < len) { cifs_dbg(VFS, "data area offset %d overlaps SMB2 header %d\n", offset + 1, len); + if (data_area_overlap) + *data_area_overlap = true; data_length = 0; + goto calc_size_exit; } else { len = offset + data_length; } @@ -469,7 +485,7 @@ calc_size_exit: unsigned int smb2_calc_size(void *buf) { - return __smb2_calc_size(buf, NULL); + return __smb2_calc_size(buf, NULL, NULL); } /* Note: caller must free return buffer */ diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 6bce44b171e4..cbd51a08e97e 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2193,10 +2193,14 @@ smb2_duplicate_extents(const unsigned int xid, u64 len, u64 dest_off) { int rc; + int qrc; unsigned int ret_data_len; struct inode *inode; + struct smb2_file_all_info file_inf; struct duplicate_extents_to_file dup_ext_buf; + struct timespec64 ts; struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink); + u64 asize; /* server fileays advertise duplicate extent support with this flag */ if ((le32_to_cpu(tcon->fsAttrInfo.Attributes) & @@ -2232,6 +2236,32 @@ smb2_duplicate_extents(const unsigned int xid, if (ret_data_len > 0) cifs_dbg(FYI, "Non-zero response length in duplicate extents\n"); + if (rc == 0) { + qrc = SMB2_query_info(xid, tcon, trgtfile->fid.persistent_fid, + trgtfile->fid.volatile_fid, &file_inf); + spin_lock(&inode->i_lock); + if (qrc == 0) { + asize = le64_to_cpu(file_inf.AllocationSize); + CIFS_I(inode)->time = jiffies; + if (file_inf.LastWriteTime) { + ts = cifs_NTtimeToUnix(file_inf.LastWriteTime); + inode_set_mtime_to_ts(inode, ts); + } + if (file_inf.ChangeTime) { + ts = cifs_NTtimeToUnix(file_inf.ChangeTime); + inode_set_ctime_to_ts(inode, ts); + } + if (file_inf.LastAccessTime) { + ts = cifs_NTtimeToUnix(file_inf.LastAccessTime); + inode_set_atime_to_ts(inode, ts); + } + inode->i_blocks = CIFS_INO_BLOCKS(asize); + } else { + CIFS_I(inode)->time = 0; /* force reval */ + } + spin_unlock(&inode->i_lock); + } + duplicate_extents_out: if (rc) trace_smb3_clone_err(xid, srcfile->fid.volatile_fid, @@ -3490,6 +3520,15 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, filemap_invalidate_lock(inode->i_mapping); /* + * Flush dirty data first, otherwise a dirty folio spanning the punched + * range may be written back after the ioctl and refill the hole. + */ + rc = filemap_write_and_wait_range(inode->i_mapping, offset, + offset + len - 1); + if (rc < 0) + goto unlock; + + /* * We implement the punch hole through ioctl, so we need remove the page * caches first, otherwise the data may be inconsistent with the server. */ @@ -3543,7 +3582,7 @@ static int smb3_simple_fallocate_write_range(unsigned int xid, char *buf) { struct cifs_io_parms io_parms = {0}; - int nbytes; + unsigned int nbytes; int rc = 0; struct kvec iov[2]; @@ -3564,9 +3603,10 @@ static int smb3_simple_fallocate_write_range(unsigned int xid, rc = SMB2_write(xid, &io_parms, &nbytes, iov, 1); if (rc) break; + if (!nbytes) + return -EIO; if (nbytes > len) return -EINVAL; - buf += nbytes; off += nbytes; len -= nbytes; } @@ -3579,11 +3619,25 @@ static int smb3_simple_fallocate_range(unsigned int xid, loff_t off, loff_t len) { struct file_allocated_range_buffer in_data, *out_data = NULL, *tmp_data; + struct inode *inode = d_inode(cfile->dentry); u32 out_data_len; char *buf = NULL; + u64 range_start, range_len, range_end; loff_t l; int rc; + buf = kvzalloc(min_t(loff_t, len, SMB2_MAX_BUFFER_SIZE), GFP_KERNEL); + if (!buf) { + rc = -ENOMEM; + goto out; + } + + if (off >= i_size_read(inode)) { + rc = smb3_simple_fallocate_write_range(xid, tcon, cfile, + off, len, buf); + goto out; + } + in_data.file_offset = cpu_to_le64(off); in_data.length = cpu_to_le64(len); rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, @@ -3595,12 +3649,6 @@ static int smb3_simple_fallocate_range(unsigned int xid, if (rc) goto out; - buf = kzalloc(1024 * 1024, GFP_KERNEL); - if (buf == NULL) { - rc = -ENOMEM; - goto out; - } - tmp_data = out_data; while (len) { /* @@ -3617,13 +3665,21 @@ static int smb3_simple_fallocate_range(unsigned int xid, goto out; } - if (off < le64_to_cpu(tmp_data->file_offset)) { + range_start = le64_to_cpu(tmp_data->file_offset); + range_len = le64_to_cpu(tmp_data->length); + if (check_add_overflow(range_start, range_len, &range_end) || + range_end > S64_MAX) { + rc = -EINVAL; + goto out; + } + + if (off < range_start) { /* * We are at a hole. Write until the end of the region * or until the next allocated data, * whichever comes next. */ - l = le64_to_cpu(tmp_data->file_offset) - off; + l = range_start - off; if (len < l) l = len; rc = smb3_simple_fallocate_write_range(xid, tcon, @@ -3640,11 +3696,13 @@ static int smb3_simple_fallocate_range(unsigned int xid, * until the end of the data or the end of the region * we are supposed to fallocate, whichever comes first. */ - l = le64_to_cpu(tmp_data->length); - if (len < l) - l = len; - off += l; - len -= l; + if (off < range_end) { + l = range_end - off; + if (len < l) + l = len; + off += l; + len -= l; + } tmp_data = &tmp_data[1]; out_data_len -= sizeof(struct file_allocated_range_buffer); @@ -3652,7 +3710,7 @@ static int smb3_simple_fallocate_range(unsigned int xid, out: kfree(out_data); - kfree(buf); + kvfree(buf); return rc; } @@ -3665,18 +3723,22 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, struct cifsFileInfo *cfile = file->private_data; long rc = -EOPNOTSUPP; unsigned int xid; - loff_t new_eof; + loff_t old_eof, new_eof; + struct smb2_file_all_info file_inf; + u64 asize; + int qrc; xid = get_xid(); inode = d_inode(cfile->dentry); cifsi = CIFS_I(inode); + old_eof = i_size_read(inode); trace_smb3_falloc_enter(xid, cfile->fid.persistent_fid, tcon->tid, tcon->ses->Suid, off, len); /* if file not oplocked can't be sure whether asking to extend size */ if (!CIFS_CACHE_READ(cifsi)) - if (keep_size == false) { + if (!keep_size) { trace_smb3_falloc_err(xid, cfile->fid.persistent_fid, tcon->tid, tcon->ses->Suid, off, len, rc); free_xid(xid); @@ -3686,21 +3748,98 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, /* * Extending the file */ - if ((keep_size == false) && i_size_read(inode) < off + len) { + if (!keep_size && old_eof < off + len) { rc = inode_newsize_ok(inode, off + len); if (rc) goto out; + /* + * A small range at or beyond EOF can be allocated by writing + * zeroes. For off > old_eof, this preserves the intervening + * hole instead of allocating from offset 0. + */ + if (off > old_eof || + (off == old_eof && old_eof != 0 && + (cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE))) { + if (len > 1024 * 1024) { + rc = -EOPNOTSUPP; + goto out; + } + + rc = smb3_simple_fallocate_range(xid, tcon, cfile, + off, len); + if (rc) { + spin_lock(&inode->i_lock); + cifsi->time = 0; + spin_unlock(&inode->i_lock); + goto out; + } + + new_eof = off + len; + netfs_resize_file(&cifsi->netfs, new_eof, true); + cifs_setsize(inode, new_eof); + + qrc = SMB2_query_info(xid, tcon, + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, &file_inf); + spin_lock(&inode->i_lock); + if (qrc == 0) { + asize = le64_to_cpu(file_inf.AllocationSize); + inode->i_blocks = CIFS_INO_BLOCKS(asize); + } else { + cifsi->time = 0; + } + spin_unlock(&inode->i_lock); + goto out; + } + if (cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE) smb2_set_sparse(xid, tcon, cfile, inode, false); new_eof = off + len; + + qrc = SMB2_query_info(xid, tcon, + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, &file_inf); + if (qrc == 0) + asize = le64_to_cpu(file_inf.AllocationSize); + + /* + * FILE_ALLOCATION_INFORMATION can only describe allocation up to + * new_eof. Some servers may accept it without allocating blocks, + * so refresh AllocationSize before updating i_blocks. + */ + if (off == 0 || off == old_eof) { + if (qrc || asize < new_eof) { + rc = SMB2_set_allocation(xid, tcon, + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + cfile->pid, new_eof); + if (rc) + goto out; + } + } + rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_eof); - if (rc == 0) { - netfs_resize_file(&cifsi->netfs, new_eof, true); - cifs_setsize(inode, new_eof); + if (rc) + goto out; + + netfs_resize_file(&cifsi->netfs, new_eof, true); + cifs_setsize(inode, new_eof); + + qrc = SMB2_query_info(xid, tcon, + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, &file_inf); + spin_lock(&inode->i_lock); + if (qrc == 0) { + asize = le64_to_cpu(file_inf.AllocationSize); + if (asize >= new_eof) + inode->i_blocks = CIFS_INO_BLOCKS(asize); + } else { + cifsi->time = 0; } + spin_unlock(&inode->i_lock); goto out; } diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 8f83ab377db1..4ce165e40657 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -5950,6 +5950,25 @@ SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, } int +SMB2_set_allocation(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid, u32 pid, + loff_t allocation_size) +{ + struct smb2_file_alloc_info info; + void *data; + unsigned int size; + + info.AllocationSize = cpu_to_le64(allocation_size); + + data = &info; + size = sizeof(struct smb2_file_alloc_info); + + return send_set_info(xid, tcon, persistent_fid, volatile_fid, + pid, FILE_ALLOCATION_INFORMATION, SMB2_O_INFO_FILE, + 0, 1, &data, &size); +} + +int SMB2_set_acl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, struct smb_ntsd *pnntsd, int pacllen, int aclflag) diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index e01effe45ae2..2e9f70096825 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -204,6 +204,9 @@ void SMB2_query_directory_free(struct smb_rqst *rqst); int SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 pid, loff_t new_eof); +int SMB2_set_allocation(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid, u32 pid, + loff_t allocation_size); int SMB2_set_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 pid, u8 info_class, u8 info_type, diff --git a/fs/smb/common/fscc.h b/fs/smb/common/fscc.h index 859849a42fec..941db5a95564 100644 --- a/fs/smb/common/fscc.h +++ b/fs/smb/common/fscc.h @@ -283,6 +283,11 @@ struct smb2_file_eof_info { /* encoding of request for level 10 */ __le64 EndOfFile; /* new end of file value */ } __packed; /* level 20 Set */ +/* See MS-FSCC 2.4.4 */ +struct smb2_file_alloc_info { /* encoding of request for level 19 */ + __le64 AllocationSize; +} __packed; + /* See MS-FSCC 2.4.15 */ typedef struct { __le32 NextEntryOffset; diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index d6331184ebfc..f99c86284ba3 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -457,22 +457,19 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn) { struct ksmbd_session *sess; unsigned long id; + struct hlist_node *tmp; + int bkt; down_write(&sessions_table_lock); - if (conn->binding) { - int bkt; - struct hlist_node *tmp; - - hash_for_each_safe(sessions_table, bkt, tmp, sess, hlist) { - if (!ksmbd_chann_del(conn, sess) && - xa_empty(&sess->ksmbd_chann_list)) { - hash_del(&sess->hlist); - down_write(&conn->session_lock); - xa_erase(&conn->sessions, sess->id); - up_write(&conn->session_lock); - if (atomic_dec_and_test(&sess->refcnt)) - ksmbd_session_destroy(sess); - } + hash_for_each_safe(sessions_table, bkt, tmp, sess, hlist) { + if (!ksmbd_chann_del(conn, sess) && + xa_empty(&sess->ksmbd_chann_list)) { + hash_del(&sess->hlist); + down_write(&conn->session_lock); + xa_erase(&conn->sessions, sess->id); + up_write(&conn->session_lock); + if (atomic_dec_and_test(&sess->refcnt)) + ksmbd_session_destroy(sess); } } diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index 8893a9aaede7..4637a8c8436d 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -19,7 +19,7 @@ struct ksmbd_file_table; struct channel { - char sess_key[SMB2_NTLMV2_SESSKEY_SIZE]; + char sess_key[CIFS_KEY_SIZE]; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; struct ksmbd_conn *conn; }; diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 3c55ae5d6a11..79787099afdc 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -875,6 +875,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) out: ksmbd_free_work_struct(work); ksmbd_conn_r_count_dec(conn); + ksmbd_conn_put(conn); } /** @@ -910,7 +911,7 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo) br_info->open_trunc = opinfo->open_trunc; work->request_buf = (char *)br_info; - work->conn = conn; + work->conn = ksmbd_conn_get(conn); work->sess = opinfo->sess; ksmbd_conn_r_count_inc(conn); @@ -985,6 +986,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk) out: ksmbd_free_work_struct(work); ksmbd_conn_r_count_dec(conn); + ksmbd_conn_put(conn); } /** @@ -1034,7 +1036,7 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo, bool wait_ack, memcpy(br_info->lease_key, lease->lease_key, SMB2_LEASE_KEY_SIZE); work->request_buf = (char *)br_info; - work->conn = conn; + work->conn = ksmbd_conn_get(conn); work->sess = opinfo->sess; ksmbd_conn_r_count_inc(conn); diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index c0c4edd092c2..9f3629c86291 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -407,6 +407,11 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) return 1; } + if (len < __SMB2_HEADER_STRUCTURE_SIZE + sizeof(__le16)) { + ksmbd_debug(SMB, "Message is too small for StructureSize2\n"); + return 1; + } + if (smb2_req_struct_sizes[command] != pdu->StructureSize2) { if (!(command == SMB2_OPLOCK_BREAK_HE && (le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_20 || diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index b73167785e87..bec692bca1ca 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1689,7 +1689,7 @@ static int ntlm_authenticate(struct ksmbd_work *work, struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; struct ksmbd_user *user; - char channel_key[SMB2_NTLMV2_SESSKEY_SIZE] = {}; + char channel_key[CIFS_KEY_SIZE] = {}; char *auth_key = conn->binding ? channel_key : sess->sess_key; u64 prev_id; bool binding = conn->binding; @@ -1826,7 +1826,7 @@ static int krb5_authenticate(struct ksmbd_work *work, struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; char *in_blob, *out_blob; - char channel_key[SMB2_NTLMV2_SESSKEY_SIZE] = {}; + char channel_key[CIFS_KEY_SIZE] = {}; char *auth_key = conn->binding ? channel_key : sess->sess_key; u64 prev_sess_id; bool binding = conn->binding; @@ -6597,9 +6597,8 @@ static int smb2_rename(struct ksmbd_work *work, pr_err("failed to store stream name in xattr: %d\n", rc); rc = -EINVAL; - goto out; } - + kfree(xattr_stream_name); goto out; } @@ -6781,6 +6780,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, */ loff_t alloc_blks; + u64 alloc_size; struct inode *inode; struct kstat stat; int rc; @@ -6796,7 +6796,19 @@ static int set_file_allocation_info(struct ksmbd_work *work, if (rc) return rc; - alloc_blks = (le64_to_cpu(file_alloc_info->AllocationSize) + 511) >> 9; + /* + * AllocationSize is fully client-controlled (the caller only + * validates the fixed 8-byte buffer length). Reject values that + * would overflow the "round up to 512-byte blocks" conversion + * below instead of silently wrapping it to a tiny block count, + * which would truncate the file to a size the client never + * asked for. + */ + alloc_size = le64_to_cpu(file_alloc_info->AllocationSize); + if (alloc_size > MAX_LFS_FILESIZE - 511) + return -EINVAL; + + alloc_blks = (alloc_size + 511) >> 9; inode = file_inode(fp->filp); if (alloc_blks > stat.blocks) { @@ -7433,6 +7445,15 @@ int smb2_read(struct ksmbd_work *work) goto out; } + /* + * ksmbd_vfs_read() fills only nbytes; the [nbytes, ALIGN(nbytes, 8)) + * tail of the un-zeroed buffer is transmitted as compound-response + * alignment padding, leaking uninitialized kernel memory to the + * client. Zero just that tail. + */ + if (nbytes & 7) + memset(aux_payload_buf + nbytes, 0, ALIGN(nbytes, 8) - nbytes); + if ((nbytes == 0 && length != 0) || nbytes < mincount) { kvfree(aux_payload_buf); rsp->hdr.Status = STATUS_END_OF_FILE; @@ -9787,22 +9808,21 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work) } if (le16_to_cpu(rsp->Command) == SMB2_SESSION_SETUP_HE && sess) { - __u8 *hash_value; + ksmbd_conn_lock(conn); if (conn->binding) { struct preauth_session *preauth_sess; preauth_sess = ksmbd_preauth_session_lookup(conn, sess->id); - if (!preauth_sess) - return; - hash_value = preauth_sess->Preauth_HashValue; - } else { - hash_value = sess->Preauth_HashValue; - if (!hash_value) - return; + if (preauth_sess) + ksmbd_gen_preauth_integrity_hash(conn, + work->response_buf, + preauth_sess->Preauth_HashValue); + } else if (sess->Preauth_HashValue) { + ksmbd_gen_preauth_integrity_hash(conn, work->response_buf, + sess->Preauth_HashValue); } - ksmbd_gen_preauth_integrity_hash(conn, work->response_buf, - hash_value); + ksmbd_conn_unlock(conn); } } diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index c2512dbcdec8..aa06c8c905f1 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -212,10 +212,6 @@ struct smb2_file_ea_info { __le32 EASize; } __packed; -struct smb2_file_alloc_info { - __le64 AllocationSize; -} __packed; - struct smb2_file_disposition_info { __u8 DeletePending; } __packed; diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index c6909716b041..89501e8bd2f8 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -878,7 +878,7 @@ xfs_defer_add_barrier( if (dfp) return; - xfs_defer_alloc(&tp->t_dfops, &xfs_barrier_defer_type); + dfp = xfs_defer_alloc(&tp->t_dfops, &xfs_barrier_defer_type); trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL); } diff --git a/fs/xfs/scrub/cow_repair.c b/fs/xfs/scrub/cow_repair.c index 0075b6d5a1b5..8dd9c0266e21 100644 --- a/fs/xfs/scrub/cow_repair.c +++ b/fs/xfs/scrub/cow_repair.c @@ -29,6 +29,7 @@ #include "xfs_rtalloc.h" #include "xfs_rtbitmap.h" #include "xfs_rtgroup.h" +#include "xfs_bmap_util.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -80,12 +81,6 @@ struct xrep_cow { unsigned int next_bno; }; -/* CoW staging extent. */ -struct xrep_cow_extent { - xfs_fsblock_t fsbno; - xfs_extlen_t len; -}; - /* * Mark the part of the file range that corresponds to the given physical * space. Caller must ensure that the physical range is within xc->irec. @@ -231,6 +226,29 @@ xrep_cow_mark_missing_staging_rmap( } /* + * Trim the start and end of the current mapping by up to 1/4 of the length + * and mark that as "bad" to test the cow fork repair mechanism. + */ +static inline int +xrep_cow_debug_replacement( + struct xrep_cow *xc) +{ + xfs_fsblock_t fsbno = xc->irec.br_startblock; + xfs_extlen_t len = xc->irec.br_blockcount; + uint32_t trim; + + /* get_random_u32_below requires a nonzero argument */ + trim = len > 4 ? get_random_u32_below(len / 4) : 0; + len -= trim; + + trim = len > 4 ? get_random_u32_below(len / 4) : 0; + fsbno += trim; + len -= trim; + + return xrep_cow_mark_file_range(xc, fsbno, len); +} + +/* * Find any part of the CoW fork mapping that isn't a single-owner CoW staging * extent and mark the corresponding part of the file range in the bitmap. */ @@ -299,8 +317,9 @@ xrep_cow_find_bad( * If userspace is forcing us to rebuild the CoW fork or someone turned * on the debugging knob, replace everything in the CoW fork. */ - if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) || - XFS_TEST_ERROR(sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR)) + if (XFS_TEST_ERROR(sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR)) + error = xrep_cow_debug_replacement(xc); + else if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) error = xrep_cow_mark_file_range(xc, xc->irec.br_startblock, xc->irec.br_blockcount); @@ -381,8 +400,9 @@ xrep_cow_find_bad_rt( * turned on the debugging knob, replace everything in the * CoW fork and then scan for staging extents in the refcountbt. */ - if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) || - XFS_TEST_ERROR(sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR)) + if (XFS_TEST_ERROR(sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR)) + error = xrep_cow_debug_replacement(xc); + else if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) error = xrep_cow_mark_file_range(xc, xc->irec.br_startblock, xc->irec.br_blockcount); @@ -401,22 +421,21 @@ out_rtg: STATIC int xrep_cow_alloc( struct xfs_scrub *sc, - xfs_extlen_t maxlen, - struct xrep_cow_extent *repl) + struct xfs_bmbt_irec *del) { struct xfs_alloc_arg args = { .tp = sc->tp, .mp = sc->mp, .oinfo = XFS_RMAP_OINFO_SKIP_UPDATE, .minlen = 1, - .maxlen = maxlen, + .maxlen = del->br_blockcount, .prod = 1, .resv = XFS_AG_RESV_NONE, .datatype = XFS_ALLOC_USERDATA, }; int error; - error = xfs_trans_reserve_more(sc->tp, maxlen, 0); + error = xfs_trans_reserve_more(sc->tp, del->br_blockcount, 0); if (error) return error; @@ -428,8 +447,8 @@ xrep_cow_alloc( xfs_refcount_alloc_cow_extent(sc->tp, false, args.fsbno, args.len); - repl->fsbno = args.fsbno; - repl->len = args.len; + del->br_startblock = args.fsbno; + del->br_blockcount = args.len; return 0; } @@ -440,10 +459,12 @@ xrep_cow_alloc( STATIC int xrep_cow_alloc_rt( struct xfs_scrub *sc, - xfs_extlen_t maxlen, - struct xrep_cow_extent *repl) + struct xfs_bmbt_irec *del) { - xfs_rtxlen_t maxrtx = xfs_rtb_to_rtx(sc->mp, maxlen); + xfs_fsblock_t fsbno; + xfs_rtxlen_t maxrtx = + min(U32_MAX, xfs_blen_to_rtbxlen(sc->mp, del->br_blockcount)); + xfs_extlen_t len; int error; error = xfs_trans_reserve_more(sc->tp, 0, maxrtx); @@ -451,11 +472,14 @@ xrep_cow_alloc_rt( return error; error = xfs_rtallocate_rtgs(sc->tp, NULLRTBLOCK, 1, maxrtx, 1, false, - false, &repl->fsbno, &repl->len); + false, &fsbno, &len); if (error) return error; - xfs_refcount_alloc_cow_extent(sc->tp, true, repl->fsbno, repl->len); + xfs_refcount_alloc_cow_extent(sc->tp, true, fsbno, len); + + del->br_startblock = fsbno; + del->br_blockcount = len; return 0; } @@ -469,19 +493,19 @@ static inline int xrep_cow_find_mapping( struct xrep_cow *xc, struct xfs_iext_cursor *icur, - xfs_fileoff_t startoff, - struct xfs_bmbt_irec *got) + xfs_fileoff_t badoff, + xfs_extlen_t badlen, + struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *rep) { struct xfs_inode *ip = xc->sc->ip; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); - if (!xfs_iext_lookup_extent(ip, ifp, startoff, icur, got)) + if (!xfs_iext_lookup_extent(ip, ifp, badoff, icur, got)) goto bad; + memcpy(rep, got, sizeof(*rep)); - if (got->br_startoff > startoff) - goto bad; - - if (got->br_blockcount == 0) + if (got->br_startoff > badoff) goto bad; if (isnullstartblock(got->br_startblock)) @@ -490,56 +514,28 @@ xrep_cow_find_mapping( if (xfs_bmap_is_written_extent(got)) goto bad; - return 0; -bad: - ASSERT(0); - return -EFSCORRUPTED; -} - -#define REPLACE_LEFT_SIDE (1U << 0) -#define REPLACE_RIGHT_SIDE (1U << 1) + if (got->br_startoff < badoff) { + const int64_t delta = badoff - got->br_startoff; -/* - * Given a CoW fork mapping @got and a replacement mapping @repl, remap the - * beginning of @got with the space described by @rep. - */ -static inline void -xrep_cow_replace_mapping( - struct xfs_inode *ip, - struct xfs_iext_cursor *icur, - const struct xfs_bmbt_irec *got, - const struct xrep_cow_extent *repl) -{ - struct xfs_bmbt_irec new = *got; /* struct copy */ - - ASSERT(repl->len > 0); - ASSERT(!isnullstartblock(got->br_startblock)); + rep->br_blockcount -= delta; + rep->br_startoff += delta; + rep->br_startblock += delta; + } - trace_xrep_cow_replace_mapping(ip, got, repl->fsbno, repl->len); + if (got->br_startoff + got->br_blockcount > badoff + badlen) { + const int64_t delta = (got->br_startoff + got->br_blockcount) - + (badoff + badlen); - if (got->br_blockcount == repl->len) { - /* - * The new extent is a complete replacement for the existing - * extent. Update the COW fork record. - */ - new.br_startblock = repl->fsbno; - xfs_iext_update_extent(ip, BMAP_COWFORK, icur, &new); - return; + rep->br_blockcount -= delta; } - /* - * The new extent can replace the beginning of the COW fork record. - * Move the left side of @got upwards, then insert the new record. - */ - new.br_startoff += repl->len; - new.br_startblock += repl->len; - new.br_blockcount -= repl->len; - xfs_iext_update_extent(ip, BMAP_COWFORK, icur, &new); + if (got->br_blockcount == 0) + goto bad; - new.br_startoff = got->br_startoff; - new.br_startblock = repl->fsbno; - new.br_blockcount = repl->len; - xfs_iext_insert(ip, icur, &new, BMAP_COWFORK); + return 0; +bad: + ASSERT(0); + return -EFSCORRUPTED; } /* @@ -553,33 +549,30 @@ xrep_cow_replace_range( xfs_extlen_t *blockcount) { struct xfs_iext_cursor icur; - struct xrep_cow_extent repl; - struct xfs_bmbt_irec got; + struct xfs_bmbt_irec got, rep; struct xfs_scrub *sc = xc->sc; - xfs_fileoff_t nextoff; - xfs_extlen_t alloc_len; + xfs_fsblock_t old_fsbno; int error; /* - * Put the existing CoW fork mapping in @got. If @got ends before - * @rep, truncate @rep so we only replace one extent mapping at a time. + * Put the existing CoW fork mapping in @got, and put in @rep the + * contents of @got trimmed to @startoff/@blockcount. We only want + * to replace the bad region, and only one mapping at a time. */ - error = xrep_cow_find_mapping(xc, &icur, startoff, &got); + error = xrep_cow_find_mapping(xc, &icur, startoff, *blockcount, &got, + &rep); if (error) return error; - nextoff = min(startoff + *blockcount, - got.br_startoff + got.br_blockcount); + old_fsbno = rep.br_startblock; /* * Allocate a replacement extent. If we don't fill all the blocks, * shorten the quantity that will be deleted in this step. */ - alloc_len = min_t(xfs_fileoff_t, XFS_MAX_BMBT_EXTLEN, - nextoff - startoff); if (XFS_IS_REALTIME_INODE(sc->ip)) - error = xrep_cow_alloc_rt(sc, alloc_len, &repl); + error = xrep_cow_alloc_rt(sc, &rep); else - error = xrep_cow_alloc(sc, alloc_len, &repl); + error = xrep_cow_alloc(sc, &rep); if (error) return error; @@ -587,7 +580,7 @@ xrep_cow_replace_range( * Replace the old mapping with the new one, and commit the metadata * changes made so far. */ - xrep_cow_replace_mapping(sc->ip, &icur, &got, &repl); + xfs_bmap_replace_cow_mapping(sc->ip, &icur, &got, &rep); xfs_inode_set_cowblocks_tag(sc->ip); error = xfs_defer_finish(&sc->tp); @@ -596,15 +589,15 @@ xrep_cow_replace_range( /* Note the old CoW staging extents; we'll reap them all later. */ if (XFS_IS_REALTIME_INODE(sc->ip)) - error = xrtb_bitmap_set(&xc->old_cowfork_rtblocks, - got.br_startblock, repl.len); + error = xrtb_bitmap_set(&xc->old_cowfork_rtblocks, old_fsbno, + rep.br_blockcount); else - error = xfsb_bitmap_set(&xc->old_cowfork_fsblocks, - got.br_startblock, repl.len); + error = xfsb_bitmap_set(&xc->old_cowfork_fsblocks, old_fsbno, + rep.br_blockcount); if (error) return error; - *blockcount = repl.len; + *blockcount = rep.br_blockcount; return 0; } diff --git a/fs/xfs/scrub/dirtree.c b/fs/xfs/scrub/dirtree.c index c6a210f7508f..b2cf6e5439d9 100644 --- a/fs/xfs/scrub/dirtree.c +++ b/fs/xfs/scrub/dirtree.c @@ -383,6 +383,14 @@ xchk_dirpath_step_up( goto out_scanlock; } + /* The handle encoded in the parent pointer must match. */ + if (VFS_I(dp)->i_generation != be32_to_cpu(dl->pptr_rec.p_gen)) { + trace_xchk_dirpath_badgen(dl->sc, dp, path->path_nr, + path->nr_steps, &dl->xname, &dl->pptr_rec); + error = -EFSCORRUPTED; + goto out_scanlock; + } + /* We've reached the root directory; the path is ok. */ if (parent_ino == dl->root_ino) { xchk_dirpath_set_outcome(dl, path, XCHK_DIRPATH_OK); @@ -411,14 +419,6 @@ xchk_dirpath_step_up( goto out_scanlock; } - /* The handle encoded in the parent pointer must match. */ - if (VFS_I(dp)->i_generation != be32_to_cpu(dl->pptr_rec.p_gen)) { - trace_xchk_dirpath_badgen(dl->sc, dp, path->path_nr, - path->nr_steps, &dl->xname, &dl->pptr_rec); - error = -EFSCORRUPTED; - goto out_scanlock; - } - /* Parent pointer must point up to a directory. */ if (!S_ISDIR(VFS_I(dp)->i_mode)) { trace_xchk_dirpath_nondir_parent(dl->sc, dp, path->path_nr, diff --git a/fs/xfs/scrub/dqiterate.c b/fs/xfs/scrub/dqiterate.c index 10950e4bd4c3..079dc4e691a0 100644 --- a/fs/xfs/scrub/dqiterate.c +++ b/fs/xfs/scrub/dqiterate.c @@ -205,7 +205,7 @@ xchk_dquot_iter( if (error) return error; - cursor->id = dq->q_id + 1; + cursor->id = (uint64_t)dq->q_id + 1; *dqpp = dq; return 1; } diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index 493dcf5cc6c1..3ec41c198351 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -921,7 +921,7 @@ xrep_dinode_bad_bmbt_fork( if (nrecs == 0 || xfs_bmdr_space_calc(nrecs) > dfork_size) return true; - if (level == 0 || level >= XFS_BM_MAXLEVELS(sc->mp, whichfork)) + if (level == 0 || level > XFS_BM_MAXLEVELS(sc->mp, whichfork)) return true; dmxr = xfs_bmdr_maxrecs(dfork_size, 0); @@ -1757,7 +1757,7 @@ xrep_clamp_timestamp( struct xfs_inode *ip, struct timespec64 *ts) { - ts->tv_nsec = clamp_t(long, ts->tv_nsec, 0, NSEC_PER_SEC); + ts->tv_nsec = clamp_t(long, ts->tv_nsec, 0, NSEC_PER_SEC - 1); *ts = timestamp_truncate(*ts, VFS_I(ip)); } diff --git a/fs/xfs/scrub/rgsuper.c b/fs/xfs/scrub/rgsuper.c index 482f899a518a..2bd2c0351b35 100644 --- a/fs/xfs/scrub/rgsuper.c +++ b/fs/xfs/scrub/rgsuper.c @@ -23,6 +23,8 @@ int xchk_setup_rgsuperblock( struct xfs_scrub *sc) { + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); return xchk_trans_alloc(sc, 0); } @@ -43,6 +45,7 @@ xchk_rgsuperblock( struct xfs_scrub *sc) { xfs_rgnumber_t rgno = sc->sm->sm_agno; + unsigned int flags; int error; /* @@ -63,7 +66,12 @@ xchk_rgsuperblock( if (!xchk_xref_process_error(sc, 0, 0, &error)) return error; - error = xchk_rtgroup_lock(sc, &sc->sr, XFS_RTGLOCK_BITMAP_SHARED); + if (xfs_has_rtrmapbt(sc->mp)) + flags = XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP; + else + flags = XFS_RTGLOCK_BITMAP_SHARED; + + error = xchk_rtgroup_lock(sc, &sc->sr, flags); if (error) return error; @@ -80,9 +88,13 @@ int xrep_rgsuperblock( struct xfs_scrub *sc) { + struct xfs_buf *sb_bp; + ASSERT(rtg_rgno(sc->sr.rtg) == 0); + sb_bp = xfs_trans_getsb(sc->tp); xfs_log_sb(sc->tp); + xfs_log_rtsb(sc->tp, sb_bp); return 0; } #endif /* CONFIG_XFS_ONLINE_REPAIR */ diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c index de3f22f310f7..52c24d3d4be6 100644 --- a/fs/xfs/scrub/rtbitmap.c +++ b/fs/xfs/scrub/rtbitmap.c @@ -258,7 +258,7 @@ xchk_rtbitmap( * the last free extent we saw and the last possible extent in the rt * group. */ - last_rgbno = rtg->rtg_extents * mp->m_sb.sb_rextsize - 1; + last_rgbno = rtg->rtg_extents * mp->m_sb.sb_rextsize; if (rtb->next_free_rgbno < last_rgbno) xchk_xref_has_rt_owner(sc, rtb->next_free_rgbno, last_rgbno - rtb->next_free_rgbno); diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c index 0d10ce2910c2..4e7c540c8d23 100644 --- a/fs/xfs/scrub/rtrefcount.c +++ b/fs/xfs/scrub/rtrefcount.c @@ -607,7 +607,7 @@ xchk_xref_is_rt_cow_staging( /* CoW lookup returned a shared extent record? */ if (rc.rc_domain != XFS_REFC_DOMAIN_COW) - xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); /* Must be at least as long as what was passed in */ if (rc.rc_blockcount < len) diff --git a/fs/xfs/scrub/rtrmap.c b/fs/xfs/scrub/rtrmap.c index 043be93c7148..564d19a97a2f 100644 --- a/fs/xfs/scrub/rtrmap.c +++ b/fs/xfs/scrub/rtrmap.c @@ -87,6 +87,9 @@ xchk_rtrmapbt_is_shareable( return false; if (irec->rm_flags & XFS_RMAP_UNWRITTEN) return false; + if (irec->rm_owner == XFS_RMAP_OWN_COW || + irec->rm_owner == XFS_RMAP_OWN_FS) + return false; return true; } @@ -146,6 +149,9 @@ xchk_rtrmap_mergeable( return false; if (r1->rm_flags != r2->rm_flags) return false; + if (r1->rm_owner == XFS_RMAP_OWN_COW || + r1->rm_owner == XFS_RMAP_OWN_FS) + return true; return r1->rm_offset + r1->rm_blockcount == r2->rm_offset; } @@ -209,7 +215,7 @@ xchk_rtrmapbt_xref( xfs_rgbno_to_rtb(sc->sr.rtg, irec->rm_startblock), irec->rm_blockcount); if (irec->rm_owner == XFS_RMAP_OWN_COW) - xchk_xref_is_cow_staging(sc, irec->rm_startblock, + xchk_xref_is_rt_cow_staging(sc, irec->rm_startblock, irec->rm_blockcount); else xchk_rtrmapbt_xref_rtrefc(sc, irec); diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index a3f1abc91390..6d7d3523b71f 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -11,7 +11,7 @@ struct xfs_scrub; struct xchk_relax { unsigned long next_resched; unsigned int resched_nr; - bool interruptible; + bool killable; }; /* Yield to the scheduler at most 10x per second. */ @@ -21,7 +21,7 @@ struct xchk_relax { (struct xchk_relax){ \ .next_resched = XCHK_RELAX_NEXT, \ .resched_nr = 0, \ - .interruptible = true, \ + .killable = true, \ } /* @@ -45,7 +45,7 @@ static inline int xchk_maybe_relax(struct xchk_relax *widget) widget->next_resched = XCHK_RELAX_NEXT; } - if (widget->interruptible && fatal_signal_pending(current)) + if (widget->killable && fatal_signal_pending(current)) return -EINTR; return 0; diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 1b7d9e07a27d..d5d39d82749e 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -2671,41 +2671,6 @@ TRACE_EVENT(xrep_cow_mark_file_range, __entry->blockcount) ); -TRACE_EVENT(xrep_cow_replace_mapping, - TP_PROTO(struct xfs_inode *ip, const struct xfs_bmbt_irec *irec, - xfs_fsblock_t new_startblock, xfs_extlen_t new_blockcount), - TP_ARGS(ip, irec, new_startblock, new_blockcount), - TP_STRUCT__entry( - __field(dev_t, dev) - __field(xfs_ino_t, ino) - __field(xfs_fsblock_t, startblock) - __field(xfs_fileoff_t, startoff) - __field(xfs_filblks_t, blockcount) - __field(xfs_exntst_t, state) - __field(xfs_fsblock_t, new_startblock) - __field(xfs_extlen_t, new_blockcount) - ), - TP_fast_assign( - __entry->dev = ip->i_mount->m_super->s_dev; - __entry->ino = I_INO(ip); - __entry->startoff = irec->br_startoff; - __entry->startblock = irec->br_startblock; - __entry->blockcount = irec->br_blockcount; - __entry->state = irec->br_state; - __entry->new_startblock = new_startblock; - __entry->new_blockcount = new_blockcount; - ), - TP_printk("dev %d:%d ino 0x%llx startoff 0x%llx startblock 0x%llx fsbcount 0x%llx state 0x%x new_startblock 0x%llx new_fsbcount 0x%x", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->ino, - __entry->startoff, - __entry->startblock, - __entry->blockcount, - __entry->state, - __entry->new_startblock, - __entry->new_blockcount) -); - TRACE_EVENT(xrep_cow_free_staging, TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t blockcount), diff --git a/fs/xfs/scrub/xfarray.c b/fs/xfs/scrub/xfarray.c index c7c4a71b6fa7..2ce24bfe4c0f 100644 --- a/fs/xfs/scrub/xfarray.c +++ b/fs/xfs/scrub/xfarray.c @@ -487,8 +487,7 @@ xfarray_sortinfo_alloc( xfarray_sortinfo_lo(si)[0] = 0; xfarray_sortinfo_hi(si)[0] = array->nr - 1; si->relax = INIT_XCHK_RELAX; - if (flags & XFARRAY_SORT_KILLABLE) - si->relax.interruptible = false; + si->relax.killable = !!(flags & XFARRAY_SORT_KILLABLE); trace_xfarray_sort(si, nr_bytes); *infop = si; diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 3b9f262f8e91..c88b9ade7389 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1744,3 +1744,92 @@ out_trans_cancel: xfs_trans_cancel(tp); goto out_unlock_ilock; } + +/* + * Given a CoW fork mapping @got and a replacement mapping @rep, map the space + * described by @rep into the cow fork, pushing aside @got as necessary. @icur + * must point to iext tree leaf containing @got. + */ +void +xfs_bmap_replace_cow_mapping( + struct xfs_inode *ip, + struct xfs_iext_cursor *icur, + struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *rep) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); + xfs_fileoff_t rep_endoff = + rep->br_startoff + rep->br_blockcount; + xfs_fileoff_t got_endoff = + got->br_startoff + got->br_blockcount; + uint32_t state = BMAP_COWFORK; + + ASSERT(rep->br_blockcount > 0); + ASSERT(!isnullstartblock(got->br_startblock)); + ASSERT(got->br_startoff <= rep->br_startoff); + ASSERT(got_endoff >= rep_endoff); + + trace_xfs_bmap_replace_cow_mapping(ip, got, rep); + + if (got->br_startoff == rep->br_startoff) + state |= BMAP_LEFT_FILLING; + if (got_endoff == rep_endoff) + state |= BMAP_RIGHT_FILLING; + + switch (state & (BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING)) { + case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING: + /* + * Replacement matches the whole mapping, update the record. + */ + xfs_iext_update_extent(ip, state, icur, rep); + break; + case BMAP_LEFT_FILLING: + /* + * Replace the first part of the mapping: Update the cursor + * position with the new mapping, then add a record with the + * tail of the old mapping. + */ + got->br_startoff = rep_endoff; + got->br_blockcount -= rep->br_blockcount; + got->br_startblock += rep->br_blockcount; + + xfs_iext_update_extent(ip, state, icur, rep); + xfs_iext_next(ifp, icur); + xfs_iext_insert(ip, icur, got, state); + break; + case BMAP_RIGHT_FILLING: + /* + * Replacing the last part of the mapping. Shorten the current + * mapping then add a record with the new mapping. + */ + got->br_blockcount -= rep->br_blockcount; + + xfs_iext_update_extent(ip, state, icur, got); + xfs_iext_next(ifp, icur); + xfs_iext_insert(ip, icur, rep, state); + break; + case 0: + /* + * Replacing the middle of the extent. Shorten the current + * mapping, add a new record with the new mapping, and add a + * second new record with the tail of the old mapping. + */ + got->br_blockcount = rep->br_startoff - got->br_startoff; + + struct xfs_bmbt_irec new = { + .br_startoff = rep_endoff, + .br_blockcount = got_endoff - rep_endoff, + .br_state = got->br_state, + .br_startblock = got->br_startblock + + rep->br_blockcount + + got->br_blockcount, + }; + + xfs_iext_update_extent(ip, state, icur, got); + xfs_iext_next(ifp, icur); + xfs_iext_insert(ip, icur, rep, state); + xfs_iext_next(ifp, icur); + xfs_iext_insert(ip, icur, &new, state); + break; + } +} diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index c477b3361630..eaaf094154b9 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -81,4 +81,8 @@ int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip, int xfs_flush_unmap_range(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t len); +void xfs_bmap_replace_cow_mapping(struct xfs_inode *ip, + struct xfs_iext_cursor *icur, struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *rep); + #endif /* __XFS_BMAP_UTIL_H__ */ diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index edc368938f30..639f875a8fb2 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -1710,7 +1710,7 @@ xlog_cil_push_background( static void xlog_cil_push_now( struct xlog *log, - xfs_lsn_t push_seq, + xfs_csn_t push_seq, bool async) { struct xfs_cil *cil = log->l_cilp; diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 5f984bf5698a..fdb011e6ef60 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1907,18 +1907,20 @@ xlog_recover_reorder_trans( list_for_each_entry_safe(item, n, &sort_list, ri_list) { enum xlog_recover_reorder fate = XLOG_REORDER_ITEM_LIST; + /* a committed item with no regions has a NULL ri_buf[0] */ + if (!item->ri_cnt || !item->ri_buf) { + xfs_warn(log->l_mp, + "%s: committed log item has no regions", + __func__); + error = -EFSCORRUPTED; + break; + } + item->ri_ops = xlog_find_item_ops(item); if (!item->ri_ops) { xfs_warn(log->l_mp, "%s: unrecognized type of log operation (%d)", __func__, ITEM_TYPE(item)); - ASSERT(0); - /* - * return the remaining items back to the transaction - * item list so they can be freed in caller. - */ - if (!list_empty(&sort_list)) - list_splice_init(&sort_list, &trans->r_itemq); error = -EFSCORRUPTED; break; } @@ -1946,7 +1948,15 @@ xlog_recover_reorder_trans( } } - ASSERT(list_empty(&sort_list)); + /* + * Return the remaining items back to the transaction item list so they + * can be freed in caller. This should only happen when we encounter + * an error. + */ + if (!list_empty(&sort_list)) { + ASSERT(error); + list_splice_init(&sort_list, &trans->r_itemq); + } if (!list_empty(&buffer_list)) list_splice(&buffer_list, &trans->r_itemq); if (!list_empty(&item_list)) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index a5c188b78138..480136136635 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -440,6 +440,7 @@ xfs_reflink_fill_cow_hole( struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; xfs_filblks_t resaligned; + unsigned int seq_before = READ_ONCE(ip->i_df.if_seq); unsigned int dblocks = 0, rblocks = 0; int nimaps; int error; @@ -465,6 +466,22 @@ xfs_reflink_fill_cow_hole( *lockmode = XFS_ILOCK_EXCL; + /* + * The data fork mapping may have changed while we dropped the ILOCK + * (a racing O_DIRECT writer under IOLOCK_SHARED can complete a full + * CoW cycle including xfs_reflink_end_cow(), which remaps this offset + * and drops the refcount of the old shared block). Re-read it so the + * shared-status recheck below and the caller's in-place iomap both + * operate on the current mapping rather than a stale physical block. + */ + if (seq_before != READ_ONCE(ip->i_df.if_seq)) { + nimaps = 1; + error = xfs_bmapi_read(ip, imap->br_startoff, + imap->br_blockcount, imap, &nimaps, 0); + if (error) + goto out_trans_cancel; + } + error = xfs_find_trim_cow_extent(ip, imap, cmap, shared, &found); if (error || !*shared) goto out_trans_cancel; @@ -511,6 +528,8 @@ xfs_reflink_fill_delalloc( bool found; do { + unsigned int seq_before = READ_ONCE(ip->i_df.if_seq); + xfs_iunlock(ip, *lockmode); *lockmode = 0; @@ -521,6 +540,23 @@ xfs_reflink_fill_delalloc( *lockmode = XFS_ILOCK_EXCL; + /* + * The data fork mapping may have changed while we dropped the + * ILOCK (a racing O_DIRECT writer under IOLOCK_SHARED can + * complete a full CoW cycle including xfs_reflink_end_cow(), + * which remaps this offset and drops the refcount of the old + * shared block). Re-read it so the shared-status recheck + * below and the caller's in-place iomap both operate on the + * current mapping rather than a stale physical block. + */ + if (seq_before != READ_ONCE(ip->i_df.if_seq)) { + nimaps = 1; + error = xfs_bmapi_read(ip, imap->br_startoff, + imap->br_blockcount, imap, &nimaps, 0); + if (error) + goto out_trans_cancel; + } + error = xfs_find_trim_cow_extent(ip, imap, cmap, shared, &found); if (error || !*shared) diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index 676777064c2d..b62712187324 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -781,6 +781,23 @@ static const struct kobj_type xfs_zoned_ktype = { }; int +xfs_zoned_sysfs_init(struct xfs_mount *mp) +{ + if (!IS_ENABLED(CONFIG_XFS_RT) || !xfs_has_zoned(mp)) + return 0; + + return xfs_sysfs_init(&mp->m_zoned_kobj, &xfs_zoned_ktype, + &mp->m_kobj, "zoned"); +} + +void +xfs_zoned_sysfs_del(struct xfs_mount *mp) +{ + if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(mp)) + xfs_sysfs_del(&mp->m_zoned_kobj); +} + +int xfs_mount_sysfs_init( struct xfs_mount *mp) { @@ -820,14 +837,6 @@ xfs_mount_sysfs_init( if (error) goto out_remove_error_dir; - if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(mp)) { - /* .../xfs/<dev>/zoned/ */ - error = xfs_sysfs_init(&mp->m_zoned_kobj, &xfs_zoned_ktype, - &mp->m_kobj, "zoned"); - if (error) - goto out_remove_error_dir; - } - return 0; out_remove_error_dir: @@ -846,9 +855,6 @@ xfs_mount_sysfs_del( struct xfs_error_cfg *cfg; int i, j; - if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(mp)) - xfs_sysfs_del(&mp->m_zoned_kobj); - for (i = 0; i < XFS_ERR_CLASS_MAX; i++) { for (j = 0; j < XFS_ERR_ERRNO_MAX; j++) { cfg = &mp->m_error_cfg[i][j]; diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h index 1622fe80ad3e..25e5f8fae2f3 100644 --- a/fs/xfs/xfs_sysfs.h +++ b/fs/xfs/xfs_sysfs.h @@ -53,6 +53,8 @@ xfs_sysfs_del( } int xfs_mount_sysfs_init(struct xfs_mount *mp); +int xfs_zoned_sysfs_init(struct xfs_mount *mp); +void xfs_zoned_sysfs_del(struct xfs_mount *mp); void xfs_mount_sysfs_del(struct xfs_mount *mp); #endif /* __XFS_SYSFS_H__ */ diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index d478693674f9..aeb89ac53bf1 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -6439,6 +6439,47 @@ TRACE_EVENT(xfs_verify_media_error, __entry->error) ); +TRACE_EVENT(xfs_bmap_replace_cow_mapping, + TP_PROTO(struct xfs_inode *ip, const struct xfs_bmbt_irec *got, + const struct xfs_bmbt_irec *rep), + TP_ARGS(ip, got, rep), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_ino_t, ino) + __field(xfs_fsblock_t, startblock) + __field(xfs_fileoff_t, startoff) + __field(xfs_filblks_t, blockcount) + __field(xfs_exntst_t, state) + __field(xfs_fileoff_t, new_startoff) + __field(xfs_fsblock_t, new_startblock) + __field(xfs_extlen_t, new_blockcount) + __field(xfs_exntst_t, new_state) + ), + TP_fast_assign( + __entry->dev = ip->i_mount->m_super->s_dev; + __entry->ino = I_INO(ip); + __entry->startoff = got->br_startoff; + __entry->startblock = got->br_startblock; + __entry->blockcount = got->br_blockcount; + __entry->state = got->br_state; + __entry->new_startoff = rep->br_startoff; + __entry->new_startblock = rep->br_startblock; + __entry->new_blockcount = rep->br_blockcount; + __entry->new_state = rep->br_state; + ), + TP_printk("dev %d:%d ino 0x%llx startoff 0x%llx startblock 0x%llx fsbcount 0x%llx state 0x%x new_startoff 0x%llx new_startblock 0x%llx new_fsbcount 0x%x new_state 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->startoff, + __entry->startblock, + __entry->blockcount, + __entry->state, + __entry->new_startoff, + __entry->new_startblock, + __entry->new_blockcount, + __entry->new_state) +); + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 08d8b34f467e..7d13fa7ab30a 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -21,6 +21,7 @@ #include "xfs_rtbitmap.h" #include "xfs_rtrmap_btree.h" #include "xfs_zone_alloc.h" +#include "xfs_sysfs.h" #include "xfs_zone_priv.h" #include "xfs_zones.h" #include "xfs_trace.h" @@ -1420,11 +1421,17 @@ xfs_mount_zones( if (error) goto out_free_zone_info; + error = xfs_zoned_sysfs_init(mp); + if (error) + goto out_zone_gc_unmount; + xfs_info(mp, "%u zones of %u blocks (%u max open zones)", mp->m_sb.sb_rgcount, iz.zone_capacity, mp->m_max_open_zones); trace_xfs_zones_mount(mp); return 0; +out_zone_gc_unmount: + xfs_zone_gc_unmount(mp); out_free_zone_info: xfs_free_zone_info(mp->m_zone_info); return error; @@ -1434,6 +1441,7 @@ void xfs_unmount_zones( struct xfs_mount *mp) { + xfs_zoned_sysfs_del(mp); xfs_zone_gc_unmount(mp); xfs_free_zone_info(mp->m_zone_info); } diff --git a/include/drm/drm_utils.h b/include/drm/drm_utils.h index 6a46f755daba..7e077484c5bb 100644 --- a/include/drm/drm_utils.h +++ b/include/drm/drm_utils.h @@ -19,6 +19,7 @@ int drm_get_panel_orientation_quirk(int width, int height); struct drm_panel_backlight_quirk { u16 min_brightness; u32 brightness_mask; + bool force_pwm; }; const struct drm_panel_backlight_quirk * diff --git a/include/dt-bindings/power/fsl,imx93-power.h b/include/dt-bindings/power/fsl,imx93-power.h index 17f9f015bf7d..071221fe5c57 100644 --- a/include/dt-bindings/power/fsl,imx93-power.h +++ b/include/dt-bindings/power/fsl,imx93-power.h @@ -11,5 +11,6 @@ #define IMX93_MEDIABLK_PD_PXP 2 #define IMX93_MEDIABLK_PD_LCDIF 3 #define IMX93_MEDIABLK_PD_ISI 4 +#define IMX93_MEDIABLK_PD_MIPI_PHY 5 #endif diff --git a/include/dt-bindings/reset/altr,rst-mgr-s10.h b/include/dt-bindings/reset/altr,rst-mgr-s10.h index 04c4d0c6fd34..c2505b9eb63e 100644 --- a/include/dt-bindings/reset/altr,rst-mgr-s10.h +++ b/include/dt-bindings/reset/altr,rst-mgr-s10.h @@ -22,7 +22,7 @@ #define USB0_RESET 35 #define USB1_RESET 36 #define NAND_RESET 37 -/* 38 is empty */ +#define COMBOPHY_RESET 38 #define SDMMC_RESET 39 #define EMAC0_OCP_RESET 40 #define EMAC1_OCP_RESET 41 diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 068ba2e77c5d..6ed9f82e639f 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -134,6 +134,8 @@ static inline bool mem_alloc_profiling_enabled(void) &mem_alloc_profiling_key); } +bool mem_alloc_profiling_permanently_disabled(void); + static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) { struct alloc_tag_counters v = { 0, 0 }; @@ -239,6 +241,7 @@ static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag) #define DEFINE_ALLOC_TAG(_alloc_tag) static inline bool mem_alloc_profiling_enabled(void) { return false; } +static inline bool mem_alloc_profiling_permanently_disabled(void) { return true; } static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) {} static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 17eca3dfc59e..e71d83ee0aef 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -421,6 +421,13 @@ struct ffa_mem_region { #define FFA_EMAD_HAS_IMPDEF_FIELD(version) ((version) >= FFA_VERSION_1_2) #define FFA_MEM_REGION_HAS_EP_MEM_OFFSET(version) ((version) > FFA_VERSION_1_0) +/* The layout changed from FFA_VERSION_1_0 and the region includes an + * ep_mem_offset. + */ +#define FFA_MEM_REGION_SZ(version) (!FFA_MEM_REGION_HAS_EP_MEM_OFFSET((version)) ?\ + offsetof(struct ffa_mem_region, ep_mem_offset) :\ + sizeof(struct ffa_mem_region)) + static inline u32 ffa_emad_size_get(u32 ffa_version) { u32 sz; @@ -445,7 +452,7 @@ ffa_mem_desc_offset(struct ffa_mem_region *buf, int count, u32 ffa_version) if (!FFA_MEM_REGION_HAS_EP_MEM_OFFSET(ffa_version)) offset += offsetof(struct ffa_mem_region, ep_mem_offset); else - offset += sizeof(struct ffa_mem_region); + offset += buf->ep_mem_offset; return offset; } diff --git a/include/linux/bnge/hsi.h b/include/linux/bnge/hsi.h index 8ea13d5407ee..1f7bd96415a5 100644 --- a/include/linux/bnge/hsi.h +++ b/include/linux/bnge/hsi.h @@ -8317,8 +8317,7 @@ struct hwrm_ring_alloc_output { __le16 req_type; __le16 seq_id; __le16 resp_len; - __le16 ring_id; - __le16 logical_ring_id; + __le32 ring_id; u8 push_buffer_index; #define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PING_BUFFER 0x0UL #define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER 0x1UL @@ -8345,10 +8344,10 @@ struct hwrm_ring_free_input { u8 flags; #define RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID 0x1UL #define RING_FREE_REQ_FLAGS_LAST RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID - __le16 ring_id; + __le16 unused_1; __le32 prod_idx; __le32 opaque; - __le32 unused_1; + __le32 ring_id; }; /* hwrm_ring_free_output (size:128b/16B) */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 240401d9b25b..c09b7994de4e 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -578,6 +578,7 @@ const char *btf_str_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); u32 *btf_kfunc_flags(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); +int btf_kfunc_check_flag(const struct btf *btf, u32 kfunc_btf_id, u32 flag); bool btf_kfunc_is_allowed(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); diff --git a/include/linux/can/dev/peak_canfd.h b/include/linux/can/dev/peak_canfd.h index d3788a3d0942..056e0efa649f 100644 --- a/include/linux/can/dev/peak_canfd.h +++ b/include/linux/can/dev/peak_canfd.h @@ -3,7 +3,7 @@ * CAN driver for PEAK System micro-CAN based adapters * * Copyright (C) 2003-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> */ #ifndef PUCAN_H #define PUCAN_H diff --git a/include/linux/damon.h b/include/linux/damon.h index 02ac34537df9..cfbbf8ba28f6 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * DAMON api - * - * Author: SeongJae Park <sj@kernel.org> */ #ifndef _DAMON_H_ diff --git a/include/linux/ieee80211-eht.h b/include/linux/ieee80211-eht.h index 18f9c662cf4c..c109722b1969 100644 --- a/include/linux/ieee80211-eht.h +++ b/include/linux/ieee80211-eht.h @@ -857,7 +857,7 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) const struct ieee80211_multi_link_elem *mle = (const void *)data; u8 fixed = sizeof(*mle); u8 common = 0; - bool check_common_len = false; + u8 common_len; u16 control; if (!data || len < fixed) @@ -868,7 +868,6 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { case IEEE80211_ML_CONTROL_TYPE_BASIC: common += sizeof(struct ieee80211_mle_basic_common_info); - check_common_len = true; if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) common += 1; if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) @@ -888,9 +887,9 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) common += sizeof(struct ieee80211_mle_preq_common_info); if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID) common += 1; - check_common_len = true; break; case IEEE80211_ML_CONTROL_TYPE_RECONF: + common += 1; if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) common += ETH_ALEN; if (control & IEEE80211_MLC_RECONF_PRES_EML_CAPA) @@ -902,7 +901,6 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) break; case IEEE80211_ML_CONTROL_TYPE_TDLS: common += sizeof(struct ieee80211_mle_tdls_common_info); - check_common_len = true; break; case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: common = ETH_ALEN + 1; @@ -915,11 +913,9 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) if (len < fixed + common) return false; - if (!check_common_len) - return true; + common_len = mle->variable[0]; - /* if present, common length is the first octet there */ - return mle->variable[0] >= common; + return common_len >= common && common_len <= len - fixed; } /** diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 695c86ee6d7a..8f18a508320d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -12215,18 +12215,7 @@ struct mlx5_ifc_mcia_reg_bits { u8 reserved_at_60[0x20]; - u8 dword_0[0x20]; - u8 dword_1[0x20]; - u8 dword_2[0x20]; - u8 dword_3[0x20]; - u8 dword_4[0x20]; - u8 dword_5[0x20]; - u8 dword_6[0x20]; - u8 dword_7[0x20]; - u8 dword_8[0x20]; - u8 dword_9[0x20]; - u8 dword_10[0x20]; - u8 dword_11[0x20]; + u8 dwords[0x400]; }; struct mlx5_ifc_dcbx_param_bits { diff --git a/include/linux/page_reporting.h b/include/linux/page_reporting.h index 9d4ca5c218a0..272b1274efdc 100644 --- a/include/linux/page_reporting.h +++ b/include/linux/page_reporting.h @@ -5,7 +5,6 @@ #include <linux/mmzone.h> #include <linux/scatterlist.h> -/* This value should always be a power of 2, see page_reporting_cycle() */ #define PAGE_REPORTING_CAPACITY 32 #define PAGE_REPORTING_ORDER_UNSPECIFIED -1 @@ -22,6 +21,9 @@ struct page_reporting_dev_info { /* Minimal order of page reporting */ unsigned int order; + + /* Max pages per report batch; 0 (default) means PAGE_REPORTING_CAPACITY */ + unsigned int capacity; }; /* Tear-down and bring-up for page reporting devices */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index a8553401b1c9..d5e35f24738d 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -551,20 +551,6 @@ static inline void psock_progs_drop(struct sk_psock_progs *progs) psock_set_prog(&progs->skb_verdict, NULL); } -/* for tcp only, sk is locked */ -static inline ssize_t sk_psock_msg_inq(struct sock *sk) -{ - struct sk_psock *psock; - ssize_t inq = 0; - - psock = sk_psock_get(sk); - if (likely(psock)) { - inq = sk_psock_get_msg_len_nolock(psock); - sk_psock_put(sk, psock); - } - return inq; -} - /* for udp only, sk is not locked */ static inline ssize_t sk_msg_first_len(struct sock *sk) { diff --git a/include/linux/slab.h b/include/linux/slab.h index 51f03f18c9a7..32c9f8ed7ae2 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -58,10 +58,13 @@ enum _slab_flag_bits { #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, +#ifdef CONFIG_SLAB_OBJ_EXT _SLAB_NO_OBJ_EXT, -#if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) +#ifdef CONFIG_64BIT _SLAB_OBJ_EXT_IN_OBJ, #endif +#endif + _SLAB_NO_SHEAVES, _SLAB_FLAGS_LAST_BIT }; @@ -239,8 +242,14 @@ enum _slab_flag_bits { #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ -/* Slab created using create_boot_cache */ +/* Slab caches without obj_exts array */ +#ifdef CONFIG_SLAB_OBJ_EXT #define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) +#else +#define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED +#endif + +#define SLAB_NO_SHEAVES __SLAB_FLAG_BIT(_SLAB_NO_SHEAVES) #if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) #define SLAB_OBJ_EXT_IN_OBJ __SLAB_FLAG_BIT(_SLAB_OBJ_EXT_IN_OBJ) @@ -505,8 +514,12 @@ typedef struct { unsigned long v; } kmalloc_token_t; extern unsigned long random_kmalloc_seed; #define __kmalloc_token(...) ((kmalloc_token_t){ .v = _CODE_LOCATION_ }) #elif defined(CONFIG_KMALLOC_PARTITION_TYPED) +#ifdef __CHECKER__ +#define __kmalloc_token(...) ((kmalloc_token_t){ .v = 0 }) +#else /* !__CHECKER__ */ #define __kmalloc_token(...) ((kmalloc_token_t){ .v = __builtin_infer_alloc_token(__VA_ARGS__) }) -#endif +#endif /* __CHECKER__ */ +#endif /* CONFIG_KMALLOC_PARTITION_TYPED */ #define DECL_TOKEN_PARAM(_token) , kmalloc_token_t (_token) #define _PASS_TOKEN_PARAM(_token) , (_token) #define PASS_TOKEN_PARAM(_token) (_token) @@ -700,6 +713,9 @@ enum kmalloc_cache_type { #ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, #endif +#ifndef CONFIG_SLAB_OBJ_EXT + KMALLOC_NO_OBJ_EXT = KMALLOC_NORMAL, +#endif KMALLOC_PARTITION_START = KMALLOC_NORMAL, KMALLOC_PARTITION_END = KMALLOC_PARTITION_START + KMALLOC_PARTITION_CACHES_NR, #ifdef CONFIG_SLUB_TINY @@ -713,6 +729,9 @@ enum kmalloc_cache_type { #ifdef CONFIG_MEMCG KMALLOC_CGROUP, #endif +#ifdef CONFIG_SLAB_OBJ_EXT + KMALLOC_NO_OBJ_EXT, +#endif NR_KMALLOC_TYPES }; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 4ca09298e11a..e7133ff87fbf 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -2430,6 +2430,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent); void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, u8 *name, u8 name_len); +u8 hci_to_mgmt_reason(u8 err); void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 reason, bool mgmt_connected); diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h index feb6b3ae5e69..102c278e3584 100644 --- a/include/net/bluetooth/rfcomm.h +++ b/include/net/bluetooth/rfcomm.h @@ -226,6 +226,9 @@ int rfcomm_send_rpn(struct rfcomm_session *s, int cr, u8 dlci, u8 bit_rate, u8 data_bits, u8 stop_bits, u8 parity, u8 flow_ctrl_settings, u8 xon_char, u8 xoff_char, u16 param_mask); +int rfcomm_dlc_send_rpn(struct rfcomm_dlc *d, u8 bit_rate, u8 data_bits, + u8 stop_bits, u8 parity, u8 flow_ctrl_settings, + u8 xon_char, u8 xoff_char, u16 param_mask); /* ---- RFCOMM DLCs (channels) ---- */ struct rfcomm_dlc *rfcomm_dlc_alloc(gfp_t prio); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8188ad200de5..f5abf1db7558 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7228,7 +7228,7 @@ struct wireless_dev { enum ieee80211_bss_type conn_bss_type; u32 conn_owner_nlportid; - struct work_struct disconnect_wk; + struct wiphy_work disconnect_wk; u8 disconnect_bssid[ETH_ALEN]; struct list_head event_list; @@ -7265,7 +7265,7 @@ struct wireless_dev { struct list_head pmsr_list; spinlock_t pmsr_lock; - struct work_struct pmsr_free_wk; + struct wiphy_work pmsr_free_wk; unsigned long unprot_beacon_reported; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 3bd08d7f39c1..5f5cb36439fe 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -156,8 +156,20 @@ static inline int tcf_classify(struct sk_buff *skb, { return TC_ACT_UNSPEC; } - #endif +static inline int tcf_classify_qdisc(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ + int ret = tcf_classify(skb, NULL, tp, res, compat_mode); + + /* TC_ACT_REDIRECT from qdisc filter chains is not supported. + * Use BPF via tcx or mirred redirect instead. + */ + if (unlikely(ret == TC_ACT_REDIRECT)) + ret = TC_ACT_SHOT; + return ret; +} static inline unsigned long __cls_set_class(unsigned long *clp, unsigned long cl) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index affee44bd38e..cccc662561aa 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -312,7 +312,8 @@ struct sctp_cookie { __u8 auth_random[sizeof(struct sctp_paramhdr) + SCTP_AUTH_RANDOM_LENGTH]; - __u8 auth_hmacs[SCTP_AUTH_NUM_HMACS * sizeof(__u16) + 2]; + __u8 auth_hmacs[sizeof(struct sctp_paramhdr) + + SCTP_AUTH_NUM_HMACS * sizeof(__u16)]; __u8 auth_chunks[sizeof(struct sctp_paramhdr) + SCTP_AUTH_MAX_CHUNKS]; /* This is a shim for my peer's INIT packet, followed by diff --git a/include/net/tcp.h b/include/net/tcp.h index 6d376ea4d1c0..2c5b889530b5 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1974,6 +1974,8 @@ static inline void tcp_fast_path_check(struct sock *sk) bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, int mib_idx, u32 *last_oow_ack_time); +void tcp_reqsk_send_challenge_ack(struct sock *sk, struct sk_buff *skb, + struct request_sock *req); static inline void tcp_mib_init(struct net *net) { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 519a0156a05c..a6d69aaa6cd2 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -162,6 +162,8 @@ struct xfrm_dev_offload { */ struct net_device *real_dev; unsigned long offload_handle; + /* Snapshot the attached device index for dump paths. */ + int ifindex; u8 dir : 2; u8 type : 2; u8 flags : 2; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 029f5115b2ea..8694eeadd753 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -408,7 +408,6 @@ void scsi_attach_vpd(struct scsi_device *sdev); void scsi_cdl_check(struct scsi_device *sdev); int scsi_cdl_enable(struct scsi_device *sdev, bool enable); -extern struct scsi_device *scsi_device_from_queue(struct request_queue *q); extern int __must_check scsi_device_get(struct scsi_device *); extern void scsi_device_put(struct scsi_device *); extern struct scsi_device *scsi_device_lookup(struct Scsi_Host *, diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 7e2011830ba4..f6b286fa59f2 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -750,6 +750,9 @@ struct Scsi_Host { */ struct device *dma_dev; + /* Used for an rcu-synchronizing eh wakeup */ + struct work_struct eh_work; + /* Delay for runtime autosuspend */ int rpm_autosuspend_delay; diff --git a/include/soc/tegra/pmc.h b/include/soc/tegra/pmc.h index 4bcbf19d75ac..53f6d02889db 100644 --- a/include/soc/tegra/pmc.h +++ b/include/soc/tegra/pmc.h @@ -210,7 +210,6 @@ tegra_pmc_io_pad_power_disable(struct tegra_pmc *pmc, enum tegra_io_pad id) bool tegra_pmc_cpu_is_powered(unsigned int cpuid); int tegra_pmc_cpu_power_on(unsigned int cpuid); int tegra_pmc_cpu_remove_clamping(unsigned int cpuid); -bool tegra_pmc_core_domain_state_synced(void); #if defined(CONFIG_SOC_TEGRA_PMC) && defined(CONFIG_PM_SLEEP) enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void); @@ -230,6 +229,10 @@ static inline void tegra_pmc_enter_suspend_mode(enum tegra_suspend_mode mode) { } #endif +#endif + +#if defined(CONFIG_ARM) && defined(CONFIG_SOC_TEGRA_PMC) +bool tegra_pmc_core_domain_state_synced(void); #else /* needed for COMPILE_TEST */ static inline bool tegra_pmc_core_domain_state_synced(void) diff --git a/include/trace/events/memory-failure.h b/include/trace/events/memory-failure.h index aa57cc8f896b..7a8ee5d1a44e 100644 --- a/include/trace/events/memory-failure.h +++ b/include/trace/events/memory-failure.h @@ -1,6 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM -#define TRACE_SYSTEM memory_failure +/* + * For historical versions, memory_failure_event is in ras subsystem, + * some user programs depend on it. + */ +#define TRACE_SYSTEM ras #define TRACE_INCLUDE_FILE memory-failure #if !defined(_TRACE_MEMORY_FAILURE_H) || defined(TRACE_HEADER_MULTI_READ) diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 9b576603b3f1..0a13baf3d8d1 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -598,7 +598,7 @@ struct btrfs_ioctl_search_args_v2 { __u64 buf_size; /* in - size of buffer * out - on EOVERFLOW: needed size * to store item */ - __u64 buf[]; /* out - found items */ + __u8 buf[]; /* out - found items */ }; /* With a @src_length of zero, the range from @src_offset->EOF is cloned! */ diff --git a/io_uring/bpf-ops.c b/io_uring/bpf-ops.c index 5a50f0675fe5..cf2bd068e331 100644 --- a/io_uring/bpf-ops.c +++ b/io_uring/bpf-ops.c @@ -168,6 +168,8 @@ static int io_install_bpf(struct io_ring_ctx *ctx, struct io_uring_bpf_ops *ops) if (ctx->bpf_ops) return -EBUSY; + if (ops->priv) + return -EBUSY; if (WARN_ON_ONCE(!ops->loop_step)) return -EINVAL; diff --git a/io_uring/fs.c b/io_uring/fs.c index d0580c754bf8..26ea841a22e7 100644 --- a/io_uring/fs.c +++ b/io_uring/fs.c @@ -110,7 +110,8 @@ int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) const char __user *fname; int err; - if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in) + if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in || + sqe->addr3 || sqe->__pad2[0]) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index b6b969b55e12..de0129bceaba 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -328,8 +328,8 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, buf = io_ring_head_to_buf(br, ++head, bl->mask); } while (--nr_iovs); - if (arg->mode & KBUF_MODE_FREE) - kfree(arg->iovs); + if (arg->iovs != org_iovs && (arg->mode & KBUF_MODE_FREE)) + kfree(org_iovs); if (head == tail) req->flags |= REQ_F_BL_EMPTY; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 64572f85edc8..c4673a54c4ba 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -9114,6 +9114,35 @@ u32 *btf_kfunc_flags(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_p return btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id); } +/* + * Check a single KF_* @flag on a kfunc across all of its hook sets. + * Returns: + * * 1 if @flag is set + * * 0 if @flag is not set + * * -EINVAL if @flag is set inconsistently across the sets + * * -ENOENT if kfunc_btf_id is not a registered kfunc + */ +int btf_kfunc_check_flag(const struct btf *btf, u32 kfunc_btf_id, u32 flag) +{ + enum btf_kfunc_hook hook; + int res = -ENOENT; + bool is_set; + u32 *flags; + + for (hook = 0; hook < BTF_KFUNC_HOOK_MAX; hook++) { + flags = btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id); + if (!flags) + continue; + is_set = *flags & flag; + if (res < 0) + res = is_set; + else if (res != is_set) + return -EINVAL; + } + + return res; +} + u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6515d4d3c003..99444eae917e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2584,24 +2584,25 @@ static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset) #define KF_IMPL_SUFFIX "_impl" -static const struct btf_type *find_kfunc_impl_proto(struct bpf_verifier_env *env, +static const struct btf_type *find_kfunc_impl_proto(struct bpf_verifier_log *log, struct btf *btf, const char *func_name) { - char *buf = env->tmp_str_buf; const struct btf_type *func; + char buf[KSYM_NAME_LEN]; s32 impl_id; int len; - len = snprintf(buf, TMP_STR_BUF_LEN, "%s%s", func_name, KF_IMPL_SUFFIX); - if (len < 0 || len >= TMP_STR_BUF_LEN) { - verbose(env, "function name %s%s is too long\n", func_name, KF_IMPL_SUFFIX); + len = snprintf(buf, sizeof(buf), "%s%s", func_name, KF_IMPL_SUFFIX); + if (len < 0 || len >= sizeof(buf)) { + bpf_log(log, "function name %s%s is too long\n", + func_name, KF_IMPL_SUFFIX); return NULL; } impl_id = btf_find_by_name_kind(btf, buf, BTF_KIND_FUNC); if (impl_id <= 0) { - verbose(env, "cannot find function %s in BTF\n", buf); + bpf_log(log, "cannot find function %s in BTF\n", buf); return NULL; } @@ -2653,7 +2654,7 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env, * can be found through the counterpart _impl kfunc. */ if (kfunc_flags && (*kfunc_flags & KF_IMPLICIT_ARGS)) - func_proto = find_kfunc_impl_proto(env, btf, func_name); + func_proto = find_kfunc_impl_proto(&env->log, btf, func_name); else func_proto = btf_type_by_id(btf, func->type); @@ -5326,14 +5327,11 @@ static int check_max_stack_depth(struct bpf_verifier_env *env) static int __check_buffer_access(struct bpf_verifier_env *env, const char *buf_info, const struct bpf_reg_state *reg, - argno_t argno, int off, int size) + argno_t argno, int off, int size, + u32 *access_end) { - if (off < 0) { - verbose(env, - "%s invalid %s buffer access: off=%d, size=%d\n", - reg_arg_name(env, argno), buf_info, off, size); - return -EACCES; - } + s64 start; + if (!tnum_is_const(reg->var_off)) { char tn_buf[48]; @@ -5344,6 +5342,15 @@ static int __check_buffer_access(struct bpf_verifier_env *env, return -EACCES; } + start = (s64)reg->var_off.value + off; + if (start < 0) { + verbose(env, + "%s invalid negative %s buffer offset: off=%d, var_off=%lld\n", + reg_arg_name(env, argno), buf_info, off, (s64)reg->var_off.value); + return -EACCES; + } + + *access_end = start + size; return 0; } @@ -5351,14 +5358,14 @@ static int check_tp_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, argno_t argno, int off, int size) { + u32 access_end; int err; - err = __check_buffer_access(env, "tracepoint", reg, argno, off, size); + err = __check_buffer_access(env, "tracepoint", reg, argno, off, size, &access_end); if (err) return err; - env->prog->aux->max_tp_access = max(reg->var_off.value + off + size, - env->prog->aux->max_tp_access); + env->prog->aux->max_tp_access = max(access_end, env->prog->aux->max_tp_access); return 0; } @@ -5370,13 +5377,14 @@ static int check_buffer_access(struct bpf_verifier_env *env, u32 *max_access) { const char *buf_info = type_is_rdonly_mem(reg->type) ? "rdonly" : "rdwr"; + u32 access_end; int err; - err = __check_buffer_access(env, buf_info, reg, argno, off, size); + err = __check_buffer_access(env, buf_info, reg, argno, off, size, &access_end); if (err) return err; - *max_access = max(reg->var_off.value + off + size, *max_access); + *max_access = max(access_end, *max_access); return 0; } @@ -18873,6 +18881,47 @@ static int btf_id_allow_sleepable(u32 btf_id, unsigned long addr, const struct b return -EINVAL; } +/* + * Resolve the prototype describing a trace target's real ABI. A + * KF_IMPLICIT_ARGS kfunc has its injected args stripped from the public + * prototype, so use the _impl prototype; other targets use their own. + */ +static const struct btf_type * +btf_attach_func_proto(struct bpf_verifier_log *log, struct btf *btf, u32 func_id) +{ + const struct btf_type *func; + struct module *mod = NULL; + const char *name; + int implicit; + + func = btf_type_by_id(btf, func_id); + if (!func || !btf_type_is_func(func)) + return NULL; + name = btf_name_by_offset(btf, func->name_off); + + /* + * btf_kfunc_check_flag() reads kfunc_set_tab, which for a module is + * stable only once it is live; hold a module ref across the read to + * exclude a concurrent module load. + */ + if (btf_is_module(btf)) { + mod = btf_try_get_module(btf); + if (!mod) + return NULL; + } + implicit = btf_kfunc_check_flag(btf, func_id, KF_IMPLICIT_ARGS); + module_put(mod); + + if (implicit == -EINVAL) { + bpf_log(log, "kfunc %s has inconsistent KF_IMPLICIT_ARGS\n", name); + return NULL; + } + if (implicit > 0) + return find_kfunc_impl_proto(log, btf, name); + + return btf_type_by_id(btf, func->type); +} + int bpf_check_attach_target(struct bpf_verifier_log *log, const struct bpf_prog *prog, const struct bpf_prog *tgt_prog, @@ -19121,8 +19170,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, if (prog_extension && btf_check_type_match(log, prog, btf, t)) return -EINVAL; - t = btf_type_by_id(btf, t->type); - if (!btf_type_is_func_proto(t)) + t = btf_attach_func_proto(log, btf, btf_id); + if (!t || !btf_type_is_func_proto(t)) return -EINVAL; if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) && @@ -19405,10 +19454,8 @@ int bpf_check_attach_btf_id_multi(struct btf *btf, struct bpf_prog *prog, u32 bt tname = btf_name_by_offset(btf, t->name_off); if (!tname) return -EINVAL; - if (!btf_type_is_func(t)) - return -EINVAL; - t = btf_type_by_id(btf, t->type); - if (!btf_type_is_func_proto(t)) + t = btf_attach_func_proto(NULL, btf, btf_id); + if (!t || !btf_type_is_func_proto(t)) return -EINVAL; err = btf_distill_func_proto(NULL, btf, t, tname, &tgt_info->fmodel); if (err < 0) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 591e3aa487fc..45944b3e31ca 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2653,7 +2653,12 @@ void cpuset_update_tasks_nodemask(struct cpuset *cs) migrate = is_memory_migrate(cs); - mpol_rebind_mm(mm, &cs->mems_allowed); + /* + * For v1 we can have empty effective_mems, but we cannot + * attach any tasks (see cpuset_can_attach_check()). For v2, + * effective_mems is guaranteed to not be empty. + */ + mpol_rebind_mm(mm, &cs->effective_mems); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); else diff --git a/kernel/liveupdate/luo_session.c b/kernel/liveupdate/luo_session.c index b79b2a488974..f38b5b18f3f8 100644 --- a/kernel/liveupdate/luo_session.c +++ b/kernel/liveupdate/luo_session.c @@ -378,7 +378,7 @@ static const struct luo_ioctl_op luo_session_ioctl_ops[] = { IOCTL_OP(LIVEUPDATE_SESSION_RETRIEVE_FD, luo_session_retrieve_fd, struct liveupdate_session_retrieve_fd, token, LUO_IOCTL_INCOMING), IOCTL_OP(LIVEUPDATE_SESSION_GET_NAME, luo_session_get_name, - struct liveupdate_session_retrieve_fd, token, LUO_IOCTL_ALL), + struct liveupdate_session_get_name, name, LUO_IOCTL_ALL), }; static bool luo_ioctl_type_valid(struct luo_session *session, diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 691d53fe0f64..e3fa7b2fac9d 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -479,6 +479,18 @@ static bool rq_is_open(struct rq *rq, u64 enq_flags) */ DEFINE_PER_CPU(struct rq *, scx_locked_rq_state); +static void switch_rq_lock(struct rq *from, struct rq *to) +{ + bool tracked = scx_locked_rq() == from; + + if (tracked) + update_locked_rq(NULL); + raw_spin_rq_unlock(from); + raw_spin_rq_lock(to); + if (tracked) + update_locked_rq(to); +} + /* * Flipped on enable per sch->is_cid_type. Declared in internal.h so * subsystem inlines can read it. @@ -2274,8 +2286,7 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, deactivate_task(src_rq, p, 0); set_task_cpu(p, cpu_of(dst_rq)); - raw_spin_rq_unlock(src_rq); - raw_spin_rq_lock(dst_rq); + switch_rq_lock(src_rq, dst_rq); /* * We want to pass scx-specific enq_flags but activate_task() will @@ -2307,6 +2318,7 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, * no to the BPF scheduler initiated migrations while offline. * * The caller must ensure that @p and @rq are on different CPUs. + * If enforce == true, caller must hold @p's rq lock. */ static bool task_can_run_on_remote_rq(struct scx_sched *sch, struct task_struct *p, struct rq *rq, @@ -2314,6 +2326,14 @@ static bool task_can_run_on_remote_rq(struct scx_sched *sch, { s32 cpu = cpu_of(rq); + /* + * To prevent races with @p still running on its old CPU while switching + * out, make sure we're holding @p's rq lock so as not to risk + * erroneously killing the BPF scheduler. + */ + if (enforce) + lockdep_assert_rq_held(task_rq(p)); + WARN_ON_ONCE(task_cpu(p) == cpu); /* @@ -2581,13 +2601,6 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq, return; } - if (src_rq != dst_rq && - unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) { - dispatch_enqueue(sch, rq, find_global_dsq(sch, task_cpu(p)), p, - enq_flags | SCX_ENQ_CLEAR_OPSS | SCX_ENQ_GDSQ_FALLBACK); - return; - } - /* * @p is on a possibly remote @src_rq which we need to lock to move the * task. If dequeue is in progress, it'd be locking @src_rq and waiting @@ -2606,14 +2619,14 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq, /* switch to @src_rq lock */ if (locked_rq != src_rq) { - raw_spin_rq_unlock(locked_rq); + switch_rq_lock(locked_rq, src_rq); locked_rq = src_rq; - raw_spin_rq_lock(src_rq); } /* task_rq couldn't have changed if we're still the holding cpu */ if (likely(p->scx.holding_cpu == raw_smp_processor_id()) && !WARN_ON_ONCE(src_rq != task_rq(p))) { + bool fallback = false; /* * If @p is staying on the same rq, there's no need to go * through the full deactivate/activate cycle. Optimize by @@ -2623,6 +2636,11 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq, p->scx.holding_cpu = -1; dispatch_enqueue(sch, dst_rq, &dst_rq->scx.local_dsq, p, enq_flags); + } else if (unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) { + p->scx.holding_cpu = -1; + fallback = true; + dispatch_enqueue(sch, src_rq, find_global_dsq(sch, task_cpu(p)), + p, enq_flags | SCX_ENQ_GDSQ_FALLBACK); } else { move_remote_task_to_local_dsq(p, enq_flags, src_rq, dst_rq); @@ -2631,15 +2649,13 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq, } /* if the destination CPU is idle, wake it up */ - if (sched_class_above(p->sched_class, dst_rq->curr->sched_class)) + if (!fallback && sched_class_above(p->sched_class, dst_rq->curr->sched_class)) resched_curr(dst_rq); } /* switch back to @rq lock */ - if (locked_rq != rq) { - raw_spin_rq_unlock(locked_rq); - raw_spin_rq_lock(rq); - } + if (locked_rq != rq) + switch_rq_lock(locked_rq, rq); } /** @@ -2970,24 +2986,38 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) /* * @p is getting newly scheduled or got kicked after someone updated its - * slice. Refresh whether tick can be stopped. See scx_can_stop_tick(). + * slice. Update SCX_RQ_CAN_STOP_TICK to reflect whether the tick can be + * stopped. See scx_can_stop_tick(). + * + * Moreover, refresh the load_avgs just when transitioning in and out of + * nohz. In the future, we might want to add a mechanism to update + * load_avgs periodically on tick-stopped CPUs. */ - if ((p->scx.slice == SCX_SLICE_INF) != - (bool)(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) { - if (p->scx.slice == SCX_SLICE_INF) + if (p->scx.slice == SCX_SLICE_INF) { + if (!(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) { + /* + * Bypass mode always assigns finite slices, so @p + * can't have an infinite slice while bypassing. + * Therefore, sched_update_tick_dependency() can safely + * evaluate the outgoing task. + */ rq->scx.flags |= SCX_RQ_CAN_STOP_TICK; - else - rq->scx.flags &= ~SCX_RQ_CAN_STOP_TICK; + sched_update_tick_dependency(rq); - sched_update_tick_dependency(rq); + update_other_load_avgs(rq); + } + } else { + if (rq->scx.flags & SCX_RQ_CAN_STOP_TICK) { + rq->scx.flags &= ~SCX_RQ_CAN_STOP_TICK; + update_other_load_avgs(rq); + } /* - * For now, let's refresh the load_avgs just when transitioning - * in and out of nohz. In the future, we might want to add a - * mechanism which calls the following periodically on - * tick-stopped CPUs. + * @rq still references the outgoing scheduling context. A finite + * slice is sufficient by itself to require the tick. */ - update_other_load_avgs(rq); + if (tick_nohz_full_cpu(cpu_of(rq))) + tick_nohz_dep_set_cpu(cpu_of(rq), TICK_DEP_BIT_SCHED); } } @@ -3082,9 +3112,14 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, * sched_class, %SCX_OPS_ENQ_LAST must be set. Tell * ops.enqueue() that @p is the only one available for this cpu, * which should trigger an explicit follow-up scheduling event. + * + * Core scheduling can force this CPU idle while @p stays + * runnable. @p's cookie then won't match the core's, so skip + * the warning in that case. */ if (next && sched_class_above(&ext_sched_class, next->sched_class)) { - WARN_ON_ONCE(!(sch->ops.flags & SCX_OPS_ENQ_LAST)); + WARN_ON_ONCE(sched_cpu_cookie_match(rq, p) && + !(sch->ops.flags & SCX_OPS_ENQ_LAST)); do_enqueue_task(rq, p, SCX_ENQ_LAST, -1); } else { do_enqueue_task(rq, p, 0, -1); @@ -3648,6 +3683,13 @@ static void scx_disable_task(struct scx_sched *sch, struct task_struct *p) scx_set_task_state(p, SCX_TASK_READY); /* + * Reset the SCX-managed fields when @p leaves the BPF scheduler's + * control, after ops.disable() has observed their final values. + */ + p->scx.dsq_vtime = 0; + p->scx.slice = 0; + + /* * Verify the task is not in BPF scheduler's custody. If flag * transitions are consistent, the flag should always be clear * here. @@ -3925,6 +3967,17 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p, if (task_dead_and_done(p)) return; + /* + * When switching sched_class away from SCX, reweight_task_scx() + * is called _after_ scx_disable_task(). Skip calling ops.set_weight() + * since the BPF scheduler may have already forgotten the task in + * ops.disable(). + * p->scx.weight will be recalculated in scx_enable_task() if the task + * ever returns to SCX class. + */ + if (scx_get_task_state(p) != SCX_TASK_ENABLED) + return; + p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight)); if (SCX_HAS_OP(sch, set_weight)) SCX_CALL_OP_TASK(sch, set_weight, rq, p, p->scx.weight); @@ -4301,6 +4354,15 @@ bool scx_can_stop_tick(struct rq *rq) if (p->sched_class != &ext_sched_class) return true; + /* + * @rq->curr may still reference an outgoing EXT task after it has been + * dequeued. If no EXT tasks are accounted on @rq, ignore its stale + * slice state. If another task is dispatched from a DSQ, + * set_next_task_scx() will update the dependency for the incoming task. + */ + if (!rq->scx.nr_running) + return true; + if (scx_bypassing(sch, cpu_of(rq))) return false; @@ -4901,6 +4963,8 @@ static void scx_sched_free_rcu_work(struct work_struct *work) cgroup_put(sch_cgroup(sch)); if (sch->sub_kset) kobject_put(&sch->sub_kset->kobj); + if (scx_parent(sch)) + kobject_put(&scx_parent(sch)->kobj); #endif /* CONFIG_EXT_SUB_SCHED */ for_each_possible_cpu(cpu) { @@ -5672,7 +5736,7 @@ static void free_kick_syncs(void) int cpu; for_each_possible_cpu(cpu) { - struct scx_kick_syncs **ksyncs = per_cpu_ptr(&scx_kick_syncs, cpu); + struct scx_kick_syncs __rcu **ksyncs = per_cpu_ptr(&scx_kick_syncs, cpu); struct scx_kick_syncs *to_free; to_free = rcu_replace_pointer(*ksyncs, NULL, true); @@ -6653,7 +6717,7 @@ static int alloc_kick_syncs(void) * can exceed percpu allocator limits on large machines. */ for_each_possible_cpu(cpu) { - struct scx_kick_syncs **ksyncs = per_cpu_ptr(&scx_kick_syncs, cpu); + struct scx_kick_syncs __rcu **ksyncs = per_cpu_ptr(&scx_kick_syncs, cpu); struct scx_kick_syncs *new_ksyncs; WARN_ON_ONCE(rcu_access_pointer(*ksyncs)); @@ -6825,11 +6889,6 @@ static struct scx_sched *scx_alloc_and_add_sched(struct scx_enable_cmd *cmd, sch->ops = *cmd->ops; } - rcu_assign_pointer(ops->priv, sch); - - sch->kobj.kset = scx_kset; - INIT_LIST_HEAD(&sch->all); - #ifdef CONFIG_EXT_SUB_SCHED char *buf = kzalloc(PATH_MAX, GFP_KERNEL); if (!buf) { @@ -6847,13 +6906,32 @@ static struct scx_sched *scx_alloc_and_add_sched(struct scx_enable_cmd *cmd, sch->cgrp = cgrp; INIT_LIST_HEAD(&sch->children); INIT_LIST_HEAD(&sch->sibling); +#endif /* CONFIG_EXT_SUB_SCHED */ - if (parent) + /* + * Publishing makes @sch visible to scx_prog_sched() readers. Failure + * paths after this point must free @sch through kobject_put() whose + * release path defers the actual freeing by an RCU grace period. + */ + rcu_assign_pointer(ops->priv, sch); + + sch->kobj.kset = scx_kset; + INIT_LIST_HEAD(&sch->all); + +#ifdef CONFIG_EXT_SUB_SCHED + if (parent) { + /* + * Pin @parent for @sch's lifetime. The kobject hierarchy pins + * it only via @parent->sub_kset, which is dropped during + * disable. Released in scx_sched_free_rcu_work(). + */ + kobject_get(&parent->kobj); ret = kobject_init_and_add(&sch->kobj, &scx_ktype, &parent->sub_kset->kobj, "sub-%llu", cgroup_id(cgrp)); - else + } else { ret = kobject_init_and_add(&sch->kobj, &scx_ktype, NULL, "root"); + } if (ret < 0) { RCU_INIT_POINTER(ops->priv, NULL); @@ -6895,7 +6973,6 @@ static struct scx_sched *scx_alloc_and_add_sched(struct scx_enable_cmd *cmd, #ifdef CONFIG_EXT_SUB_SCHED err_free_lb_resched: - RCU_INIT_POINTER(ops->priv, NULL); free_cpumask_var(sch->bypass_lb_resched_cpumask); #endif err_free_lb_cpumask: @@ -6988,7 +7065,7 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops) * run past the BPF allocation. Skip for cid-form. */ if (!sch->is_cid_type && (ops->cpu_acquire || ops->cpu_release)) - pr_warn("ops->cpu_acquire/release() are deprecated, use sched_switch TP instead\n"); + pr_warn_ratelimited("ops->cpu_acquire/release() are deprecated, use sched_switch TP instead\n"); /* * Sub-scheduler support is tied to the cid-form struct_ops. A sub-sched @@ -7686,6 +7763,12 @@ err_unlock_and_disable: percpu_up_write(&scx_fork_rwsem); err_disable: mutex_unlock(&scx_enable_mutex); + /* + * Some enable failures only return an errno (e.g. -ENOMEM from an + * allocation) without calling scx_error(). Record it so + * scx_flush_disable_work() runs the disable and ops.exit() fires. + */ + scx_error(sch, "scx_sub_enable() failed (%d)", ret); scx_flush_disable_work(sch); cmd->ret = 0; } @@ -7806,7 +7889,7 @@ static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log, off + size <= offsetofend(struct task_struct, scx.slice)) || (off >= offsetof(struct task_struct, scx.dsq_vtime) && off + size <= offsetofend(struct task_struct, scx.dsq_vtime))) { - pr_warn("sched_ext: Writing directly to p->scx.slice/dsq_vtime is deprecated, use scx_bpf_task_set_slice/dsq_vtime()"); + pr_warn_ratelimited("sched_ext: Writing directly to p->scx.slice/dsq_vtime is deprecated, use scx_bpf_task_set_slice/dsq_vtime()\n"); return SCALAR_VALUE; } @@ -8796,10 +8879,8 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, in_balance = this_rq->scx.flags & SCX_RQ_IN_BALANCE; if (in_balance) { - if (this_rq != src_rq) { - raw_spin_rq_unlock(this_rq); - raw_spin_rq_lock(src_rq); - } + if (this_rq != src_rq) + switch_rq_lock(this_rq, src_rq); } else { raw_spin_rq_lock(src_rq); } @@ -8831,10 +8912,8 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, dispatched = true; out: if (in_balance) { - if (this_rq != locked_rq) { - raw_spin_rq_unlock(locked_rq); - raw_spin_rq_lock(this_rq); - } + if (this_rq != locked_rq) + switch_rq_lock(locked_rq, this_rq); } else { raw_spin_rq_unlock_irqrestore(locked_rq, flags); } diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h index 145272cb4d8a..673059fa9d72 100644 --- a/kernel/sched/ext/internal.h +++ b/kernel/sched/ext/internal.h @@ -1469,21 +1469,24 @@ static const char *scx_enable_state_str[] = { * The sched_ext core uses a "lock dancing" protocol coordinated by * p->scx.holding_cpu. When moving a task to a different rq: * - * 1. Verify task can be moved (CPU affinity, migration_disabled, etc.) - * 2. Set p->scx.holding_cpu to the current CPU - * 3. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING + * 1. Set p->scx.holding_cpu to the current CPU + * 2. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING * is set, so clearing DISPATCHING first prevents the circular wait * (safe to lock the rq we need) - * 4. Unlock the current CPU's rq - * 5. Lock src_rq (where the task currently lives) - * 6. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the + * 3. Unlock the current CPU's rq + * 4. Lock src_rq (where the task currently lives) + * 5. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the * race (dequeue clears holding_cpu to -1 when it takes the task), in * this case migration is aborted - * 7. If src_rq == dst_rq: clear holding_cpu and enqueue directly + * 6. If src_rq == dst_rq: clear holding_cpu and enqueue directly * into dst_rq's local DSQ (no lock swap needed) - * 8. Otherwise: call move_remote_task_to_local_dsq(), which releases - * src_rq, locks dst_rq, and performs the deactivate/activate - * migration cycle (dst_rq is held on return) + * 7. Otherwise, verify under src_rq lock that the task can be moved to dst_rq + * (CPU affinity, migration_disabled, etc.). If not, clear holding_cpu, + * leave the task on src_rq, and enqueue it on the fallback DSQ. + * 8. Otherwise (i.e. if the task can be moved to dst_rq), call + * move_remote_task_to_local_dsq(), which releases src_rq, locks dst_rq, + * and performs the deactivate/activate migration cycle + * (dst_rq is held on return) * 9. Unlock dst_rq and re-lock the current CPU's rq to restore * the lock state expected by the caller * diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 50518b071414..bcd97cb24ac9 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -172,7 +172,8 @@ static bool eprobe_dyn_event_match(const char *system, const char *event, if (!slash) return false; - if (strncmp(ep->event_system, argv[0], slash - argv[0])) + if (strncmp(ep->event_system, argv[0], slash - argv[0]) || + ep->event_system[slash - argv[0]] != '\0') return false; if (strcmp(ep->event_name, slash + 1)) return false; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index d17cfee77d9c..506e6037e163 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -188,7 +188,7 @@ void __trace_probe_log_err(int offset, int err_type) lockdep_assert_held(&dyn_event_ops_mutex); - if (!trace_probe_log.argv) + if (!trace_probe_log.argv || !trace_probe_log.argc) return; /* Recalculate the length and allocate buffer */ @@ -2013,7 +2013,7 @@ int traceprobe_update_arg(struct probe_arg *arg) } /* When len=0, we just calculate the needed length */ -#define LEN_OR_ZERO (len ? len - pos : 0) +#define LEN_OR_ZERO (len > pos ? len - pos : 0) static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, enum probe_print_type ptype) { @@ -2338,16 +2338,17 @@ int trace_probe_compare_arg_type(struct trace_probe *a, struct trace_probe *b) bool trace_probe_match_command_args(struct trace_probe *tp, int argc, const char **argv) { - char buf[MAX_ARGSTR_LEN + 1]; int i; if (tp->nr_args < argc) return false; for (i = 0; i < argc; i++) { - snprintf(buf, sizeof(buf), "%s=%s", - tp->args[i].name, tp->args[i].comm); - if (strcmp(buf, argv[i])) + int len = strlen(tp->args[i].name); + + if (strncmp(argv[i], tp->args[i].name, len) || + argv[i][len] != '=' || + strcmp(argv[i] + len + 1, tp->args[i].comm)) return false; } return true; diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index d9be1cf5187d..e5b218176c5a 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -26,6 +26,15 @@ static bool mem_profiling_support = true; static bool mem_profiling_support; #endif +/* + * Memory allocation profiling is permanently disabled and cannot be enabled. + * Must be called after setup_early_mem_profiling(). + */ +bool mem_alloc_profiling_permanently_disabled(void) +{ + return !mem_profiling_support; +} + static struct codetag_type *alloc_tag_cttype; #ifdef CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU diff --git a/lib/bug.c b/lib/bug.c index 292420f45811..7c1c2c27f58e 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -219,14 +219,12 @@ static enum bug_trap_type __report_bug(struct bug_entry *bug, unsigned long buga no_cut = bug->flags & BUGFLAG_NO_CUT_HERE; has_args = bug->flags & BUGFLAG_ARGS; -#ifdef CONFIG_KUNIT /* * Before the once logic so suppressed warnings do not consume * the single-fire budget of WARN_ON_ONCE(). */ if (warning && kunit_is_suppressed_warning(true)) return BUG_TRAP_TYPE_WARN; -#endif disable_trace_on_warning(); diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index 591c1c2a7fb3..83d4c95e079e 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -8,8 +8,7 @@ config CRYPTO_LIB_UTILS config CRYPTO_LIB_AES tristate - # Select dependencies of modes that are part of libaes. - select CRYPTO_LIB_UTILS if CRYPTO_LIB_AES_CBC_MACS + select CRYPTO_LIB_UTILS config CRYPTO_LIB_AES_ARCH bool diff --git a/lib/crypto/md5.c b/lib/crypto/md5.c index 6bf130cfbbf9..3d2b017a0525 100644 --- a/lib/crypto/md5.c +++ b/lib/crypto/md5.c @@ -298,19 +298,5 @@ void hmac_md5_usingrawkey(const u8 *raw_key, size_t raw_key_len, } EXPORT_SYMBOL_GPL(hmac_md5_usingrawkey); -#ifdef md5_mod_init_arch -static int __init md5_mod_init(void) -{ - md5_mod_init_arch(); - return 0; -} -subsys_initcall(md5_mod_init); - -static void __exit md5_mod_exit(void) -{ -} -module_exit(md5_mod_exit); -#endif - MODULE_DESCRIPTION("MD5 and HMAC-MD5 library functions"); MODULE_LICENSE("GPL"); diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 40cfb38ac919..d459bef245f4 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -878,6 +878,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter) iter->walker.tbl = rht_dereference_rcu(ht->tbl, ht); iter->slot = 0; iter->skip = 0; + iter->p = NULL; return -EAGAIN; } diff --git a/mm/damon/core.c b/mm/damon/core.c index 7e4b9affc5b0..cff932b3317d 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Data Access Monitor - * - * Author: SeongJae Park <sj@kernel.org> */ #define pr_fmt(fmt) "damon: " fmt @@ -356,8 +354,21 @@ int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, { struct damon_region *r, *next; unsigned int i; + unsigned long last_end; int err; + for (i = 0; i < nr_ranges; i++) { + unsigned long start, end; + + start = ALIGN_DOWN(ranges[i].start, min_region_sz); + end = ALIGN(ranges[i].end, min_region_sz); + if (start >= end) + return -EINVAL; + if (i > 0 && last_end > start) + return -EINVAL; + last_end = end; + } + /* Remove regions which are not in the new ranges */ damon_for_each_region_safe(r, next, t) { for (i = 0; i < nr_ranges; i++) { diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 8298c6001fd0..32f41491b726 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON-based LRU-lists Sorting - * - * Author: SeongJae Park <sj@kernel.org> */ #define pr_fmt(fmt) "damon-lru-sort: " fmt diff --git a/mm/damon/modules-common.c b/mm/damon/modules-common.c index 86d58f8c4f63..f87fa46a95a0 100644 --- a/mm/damon/modules-common.c +++ b/mm/damon/modules-common.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Common Code for DAMON Modules - * - * Author: SeongJae Park <sj@kernel.org> */ #include <linux/damon.h> diff --git a/mm/damon/modules-common.h b/mm/damon/modules-common.h index f103ad556368..6fd45490e45b 100644 --- a/mm/damon/modules-common.h +++ b/mm/damon/modules-common.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Common Code for DAMON Modules - * - * Author: SeongJae Park <sj@kernel.org> */ #include <linux/moduleparam.h> diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c index d1842e2b00ef..6bdd1cfd3863 100644 --- a/mm/damon/ops-common.c +++ b/mm/damon/ops-common.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Common Code for Data Access Monitoring - * - * Author: SeongJae Park <sj@kernel.org> */ #include <linux/migrate.h> diff --git a/mm/damon/ops-common.h b/mm/damon/ops-common.h index 5efa5b5970de..38d295488fa1 100644 --- a/mm/damon/ops-common.h +++ b/mm/damon/ops-common.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Common Code for Data Access Monitoring - * - * Author: SeongJae Park <sj@kernel.org> */ #include <linux/damon.h> diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index d0598f5f2688..5c2da45f988c 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON Code for The Physical Address Space - * - * Author: SeongJae Park <sj@kernel.org> */ #define pr_fmt(fmt) "damon-pa: " fmt diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index ce4499cf4b8b..11b70d0a9a6f 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON-based page reclamation - * - * Author: SeongJae Park <sj@kernel.org> */ #define pr_fmt(fmt) "damon-reclaim: " fmt diff --git a/mm/damon/sysfs-common.c b/mm/damon/sysfs-common.c index bdc6ae2639e4..c59d7bf7a73a 100644 --- a/mm/damon/sysfs-common.c +++ b/mm/damon/sysfs-common.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Common Code for DAMON Sysfs Interface - * - * Author: SeongJae Park <sj@kernel.org> */ #include <linux/slab.h> diff --git a/mm/damon/sysfs-common.h b/mm/damon/sysfs-common.h index 3079306966a9..733764716e8d 100644 --- a/mm/damon/sysfs-common.h +++ b/mm/damon/sysfs-common.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Common Code for DAMON Sysfs Interface - * - * Author: SeongJae Park <sj@kernel.org> */ #include <linux/damon.h> diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 0134111c3c1f..3cbeccd436e4 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON sysfs Interface - * - * Copyright (c) 2022 SeongJae Park <sj@kernel.org> */ #include <linux/slab.h> diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 2e95e3bac774..a9e187158067 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON sysfs Interface - * - * Copyright (c) 2022 SeongJae Park <sj@kernel.org> */ #include <linux/pid.h> diff --git a/mm/damon/tests/core-kunit.h b/mm/damon/tests/core-kunit.h index 1cfb8c176b87..fcf7c7fadb5f 100644 --- a/mm/damon/tests/core-kunit.h +++ b/mm/damon/tests/core-kunit.h @@ -1,10 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Data Access Monitor Unit Tests - * - * Copyright 2019 Amazon.com, Inc. or its affiliates. All rights reserved. - * - * Author: SeongJae Park <sj@kernel.org> */ #ifdef CONFIG_DAMON_KUNIT_TEST diff --git a/mm/damon/tests/sysfs-kunit.h b/mm/damon/tests/sysfs-kunit.h index f9ec5e795b34..138a4b8d14e7 100644 --- a/mm/damon/tests/sysfs-kunit.h +++ b/mm/damon/tests/sysfs-kunit.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Data Access Monitor Unit Tests - * - * Author: SeongJae Park <sj@kernel.org> */ #ifdef CONFIG_DAMON_SYSFS_KUNIT_TEST diff --git a/mm/damon/tests/vaddr-kunit.h b/mm/damon/tests/vaddr-kunit.h index 563fbc7e3f44..61f844336ffb 100644 --- a/mm/damon/tests/vaddr-kunit.h +++ b/mm/damon/tests/vaddr-kunit.h @@ -1,10 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Data Access Monitor Unit Tests - * - * Copyright 2019 Amazon.com, Inc. or its affiliates. All rights reserved. - * - * Author: SeongJae Park <sj@kernel.org> */ #ifdef CONFIG_DAMON_VADDR_KUNIT_TEST diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index d27147603564..e73ec1ce016e 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON Code for Virtual Address Spaces - * - * Author: SeongJae Park <sj@kernel.org> */ #define pr_fmt(fmt) "damon-va: " fmt diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2bccb0a53a0a..b5d1e9d4463d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3587,10 +3587,6 @@ static void __split_folio_to_order(struct folio *folio, int old_order, (1L << PG_dropbehind) | LRU_GEN_MASK | LRU_REFS_MASK)); - if (handle_hwpoison && - page_range_has_hwpoisoned(new_head, new_nr_pages)) - folio_set_has_hwpoisoned(new_folio); - new_folio->mapping = folio->mapping; new_folio->index = folio->index + i; @@ -3612,6 +3608,14 @@ static void __split_folio_to_order(struct folio *folio, int old_order, folio_set_large_rmappable(new_folio); } + /* + * PG_has_hwpoisoned is on the 2nd page, so set it after + * the compound head is prepped. + */ + if (handle_hwpoison && + page_range_has_hwpoisoned(new_head, new_nr_pages)) + folio_set_has_hwpoisoned(new_folio); + if (folio_test_young(folio)) folio_set_young(new_folio); if (folio_test_idle(folio)) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 7c7ba17ce7af..e196f53f9b46 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -687,7 +687,7 @@ static struct kmemleak_object *__alloc_object(gfp_t gfp) atomic_set(&object->use_count, 1); object->excess_ref = 0; object->count = 0; /* white color initially */ - object->checksum = 0; + object->checksum = ~0; object->del_state = 0; /* task information */ @@ -981,7 +981,7 @@ static void reset_checksum(unsigned long ptr) } raw_spin_lock_irqsave(&object->lock, flags); - object->checksum = 0; + object->checksum = ~0; raw_spin_unlock_irqrestore(&object->lock, flags); put_object(object); } @@ -1410,7 +1410,8 @@ static bool update_checksum(struct kmemleak_object *object) for_each_possible_cpu(cpu) { void *ptr = per_cpu_ptr((void __percpu *)object->pointer, cpu); - object->checksum ^= crc32(0, kasan_reset_tag((void *)ptr), object->size); + object->checksum = crc32(object->checksum, + kasan_reset_tag((void *)ptr), object->size); } } else { object->checksum = crc32(0, kasan_reset_tag((void *)object->pointer), object->size); diff --git a/mm/page_reporting.c b/mm/page_reporting.c index 7418f2e500bb..942e84b6908a 100644 --- a/mm/page_reporting.c +++ b/mm/page_reporting.c @@ -173,11 +173,8 @@ page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone, * any pages that may have already been present from the previous * list processed. This should result in us reporting all pages on * an idle system in about 30 seconds. - * - * The division here should be cheap since PAGE_REPORTING_CAPACITY - * should always be a power of 2. */ - budget = DIV_ROUND_UP(area->nr_free, PAGE_REPORTING_CAPACITY * 16); + budget = DIV_ROUND_UP(area->nr_free, prdev->capacity * 16); /* loop through free list adding unreported pages to sg list */ list_for_each_entry_safe(page, next, list, lru) { @@ -222,10 +219,10 @@ page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone, spin_unlock_irq(&zone->lock); /* begin processing pages in local list */ - err = prdev->report(prdev, sgl, PAGE_REPORTING_CAPACITY); + err = prdev->report(prdev, sgl, prdev->capacity); /* reset offset since the full list was reported */ - *offset = PAGE_REPORTING_CAPACITY; + *offset = prdev->capacity; /* update budget to reflect call to report function */ budget--; @@ -234,7 +231,7 @@ page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone, spin_lock_irq(&zone->lock); /* flush reported pages from the sg list */ - page_reporting_drain(prdev, sgl, PAGE_REPORTING_CAPACITY, !err); + page_reporting_drain(prdev, sgl, prdev->capacity, !err); /* * Reset next to first entry, the old next isn't valid @@ -260,13 +257,13 @@ static int page_reporting_process_zone(struct page_reporting_dev_info *prdev, struct scatterlist *sgl, struct zone *zone) { - unsigned int order, mt, leftover, offset = PAGE_REPORTING_CAPACITY; + unsigned int order, mt, leftover, offset = prdev->capacity; unsigned long watermark; int err = 0; /* Generate minimum watermark to be able to guarantee progress */ watermark = low_wmark_pages(zone) + - (PAGE_REPORTING_CAPACITY << page_reporting_order); + (prdev->capacity << page_reporting_order); /* * Cancel request if insufficient free memory or if we failed @@ -290,7 +287,7 @@ page_reporting_process_zone(struct page_reporting_dev_info *prdev, } /* report the leftover pages before going idle */ - leftover = PAGE_REPORTING_CAPACITY - offset; + leftover = prdev->capacity - offset; if (leftover) { sgl = &sgl[offset]; err = prdev->report(prdev, sgl, leftover); @@ -322,11 +319,11 @@ static void page_reporting_process(struct work_struct *work) atomic_set(&prdev->state, state); /* allocate scatterlist to store pages being reported on */ - sgl = kmalloc_objs(*sgl, PAGE_REPORTING_CAPACITY); + sgl = kmalloc_objs(*sgl, prdev->capacity); if (!sgl) goto err_out; - sg_init_table(sgl, PAGE_REPORTING_CAPACITY); + sg_init_table(sgl, prdev->capacity); for_each_zone(zone) { err = page_reporting_process_zone(prdev, sgl, zone); @@ -377,6 +374,9 @@ int page_reporting_register(struct page_reporting_dev_info *prdev) page_reporting_order = pageblock_order; } + if (!prdev->capacity || prdev->capacity > PAGE_REPORTING_CAPACITY) + prdev->capacity = PAGE_REPORTING_CAPACITY; + /* initialize state and work structures */ atomic_set(&prdev->state, PAGE_REPORTING_IDLE); INIT_DELAYED_WORK(&prdev->work, &page_reporting_process); diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 2ccbabfb2cc1..bac2eb5de63d 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -243,21 +243,31 @@ restart: */ pmde = pmdp_get_lockless(pvmw->pmd); - if (pmd_trans_huge(pmde) || pmd_is_migration_entry(pmde)) { + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + (pmd_trans_huge(pmde) || pmd_is_migration_entry(pmde) || + pmd_is_device_private_entry(pmde))) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); pmde = *pvmw->pmd; - if (!pmd_present(pmde)) { + if (pmd_is_migration_entry(pmde)) { softleaf_t entry; - if (!thp_migration_supported() || - !(pvmw->flags & PVMW_MIGRATION)) + if (!(pvmw->flags & PVMW_MIGRATION)) return not_found(pvmw); entry = softleaf_from_pmd(pmde); + if (!check_pmd(softleaf_to_pfn(entry), pvmw)) + return not_found(pvmw); + return true; + } else if (pmd_is_device_private_entry(pmde)) { + softleaf_t entry; - if (!softleaf_is_migration(entry) || - !check_pmd(softleaf_to_pfn(entry), pvmw)) + if (pvmw->flags & PVMW_MIGRATION) + return not_found(pvmw); + entry = softleaf_from_pmd(pmde); + if (!check_pmd(softleaf_to_pfn(entry), pvmw)) return not_found(pvmw); return true; + } else if (!pmd_present(pmde)) { + return not_found(pvmw); } if (likely(pmd_trans_huge(pmde))) { if (pvmw->flags & PVMW_MIGRATION) @@ -266,17 +276,10 @@ restart: return not_found(pvmw); return true; } - /* THP pmd was split under us: handle on pte level */ + /* THP/device-private pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } else if (!pmd_present(pmde)) { - const softleaf_t entry = softleaf_from_pmd(pmde); - - if (softleaf_is_device_private(entry)) { - pvmw->ptl = pmd_lock(mm, pvmw->pmd); - return true; - } - if ((pvmw->flags & PVMW_SYNC) && thp_vma_suitable_order(vma, pvmw->address, PMD_ORDER) && diff --git a/mm/slab.h b/mm/slab.h index 281a65233795..f5e336b6b6b0 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -22,6 +22,7 @@ #define SLAB_ALLOC_NOLOCK 0x01 /* a kmalloc_nolock() allocation */ #define SLAB_ALLOC_NEW_SLAB 0x02 /* a flag for alloc_slab_obj_exts() */ #define SLAB_ALLOC_NO_RECURSE 0x04 /* prevent kmalloc() recursion */ +#define SLAB_ALLOC_NO_OBJ_EXT 0x08 /* prevent obj_exts array allocation */ static inline bool alloc_flags_allow_spinning(const unsigned int alloc_flags) { @@ -386,12 +387,17 @@ static inline unsigned int size_index_elem(unsigned int bytes) * KMALLOC_MAX_CACHE_SIZE and the caller must check that. */ static inline struct kmem_cache * -kmalloc_slab(size_t size, kmem_buckets *b, gfp_t flags, kmalloc_token_t token) +kmalloc_slab(size_t size, kmem_buckets *b, gfp_t flags, kmalloc_token_t token, + unsigned int alloc_flags) { unsigned int index; + enum kmalloc_cache_type type = kmalloc_type(flags, token); + + if (alloc_flags & SLAB_ALLOC_NO_OBJ_EXT) + type = KMALLOC_NO_OBJ_EXT; if (!b) - b = &kmalloc_caches[kmalloc_type(flags, token)]; + b = &kmalloc_caches[type]; if (size <= 192) index = kmalloc_size_index[size_index_elem(size)]; else @@ -426,7 +432,8 @@ static inline bool is_kmalloc_normal(struct kmem_cache *s) { if (!is_kmalloc_cache(s)) return false; - return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT)); + + return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT|SLAB_NO_OBJ_EXT)); } bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj); @@ -529,6 +536,25 @@ static inline void metadata_access_disable(void) kasan_enable_current(); } +/* + * Return true if KMALLOC_NORMAL caches may need obj_exts arrays. + * + * Memory allocation profiling requires obj_exts for all caches. + * Memcg usually doesn't need them for normal kmalloc caches, but kmalloc types + * with a priority higher than KMALLOC_CGROUP can be aliased with KMALLOC_NORMAL. + */ +static inline bool need_kmalloc_no_objext(void) +{ + if (!mem_alloc_profiling_permanently_disabled()) + return true; + + if (!mem_cgroup_kmem_disabled() && + (KMALLOC_NORMAL == KMALLOC_RECLAIM)) + return true; + + return false; +} + #ifdef CONFIG_SLAB_OBJ_EXT /* diff --git a/mm/slab_common.c b/mm/slab_common.c index b6426d7ceec9..03ecac12cd86 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -783,11 +783,15 @@ u8 kmalloc_size_index[24] __ro_after_init = { size_t kmalloc_size_roundup(size_t size) { if (size && size <= KMALLOC_MAX_CACHE_SIZE) { + struct kmem_cache *s; + /* * The flags don't matter since size_index is common to all. * Neither does the caller for just getting ->object_size. */ - return kmalloc_slab(size, NULL, GFP_KERNEL, __kmalloc_token(0))->object_size; + s = kmalloc_slab(size, NULL, GFP_KERNEL, __kmalloc_token(0), + SLAB_ALLOC_DEFAULT); + return s->object_size; } /* Above the smaller buckets, size is a multiple of page size. */ @@ -843,6 +847,12 @@ EXPORT_SYMBOL(kmalloc_size_roundup); #define KMALLOC_PARTITION_NAME(N, sz) #endif +#ifdef CONFIG_SLAB_OBJ_EXT +#define KMALLOC_NO_OBJ_EXT_NAME(sz) .name[KMALLOC_NO_OBJ_EXT] = "kmalloc-no-objext-" #sz, +#else +#define KMALLOC_NO_OBJ_EXT_NAME(sz) +#endif + #define INIT_KMALLOC_INFO(__size, __short_size) \ { \ .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ @@ -850,6 +860,7 @@ EXPORT_SYMBOL(kmalloc_size_roundup); KMALLOC_CGROUP_NAME(__short_size) \ KMALLOC_DMA_NAME(__short_size) \ KMALLOC_PARTITION_NAME(KMALLOC_PARTITION_CACHES_NR, __short_size) \ + KMALLOC_NO_OBJ_EXT_NAME(__short_size) \ .size = __size, \ } @@ -957,6 +968,12 @@ new_kmalloc_cache(int idx, enum kmalloc_cache_type type) return; } flags |= SLAB_ACCOUNT; + } else if (IS_ENABLED(CONFIG_SLAB_OBJ_EXT) && type == KMALLOC_NO_OBJ_EXT) { + if (!need_kmalloc_no_objext()) { + kmalloc_caches[type][idx] = kmalloc_caches[KMALLOC_NORMAL][idx]; + return; + } + flags |= SLAB_NO_OBJ_EXT | SLAB_NO_MERGE; } else if (IS_ENABLED(CONFIG_ZONE_DMA) && (type == KMALLOC_DMA)) { flags |= SLAB_CACHE_DMA; } diff --git a/mm/slub.c b/mm/slub.c index 9ec774dc7009..0337e60db5ac 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2123,42 +2123,6 @@ static inline void init_slab_obj_exts(struct slab *slab) slab->obj_exts = 0; } -/* - * Calculate the allocation size for slabobj_ext array. - * - * When memory allocation profiling is enabled, the obj_exts array - * could be allocated from the same slab cache it's being allocated for. - * This would prevent the slab from ever being freed because it would - * always contain at least one allocated object (its own obj_exts array). - * - * To avoid this, increase the allocation size when we detect the array - * may come from the same cache, forcing it to use a different cache. - */ -static inline size_t obj_exts_alloc_size(struct kmem_cache *s, - struct slab *slab, gfp_t gfp) -{ - size_t sz = sizeof(struct slabobj_ext) * slab->objects; - struct kmem_cache *obj_exts_cache; - - if (sz > KMALLOC_MAX_CACHE_SIZE) - return sz; - - if (!is_kmalloc_normal(s)) - return sz; - - obj_exts_cache = kmalloc_slab(sz, NULL, gfp, __kmalloc_token(0)); - /* - * We can't simply compare s with obj_exts_cache, because partitioned kmalloc - * caches have multiple caches per size, selected by caller address or type. - * Since caller address or type may differ between kmalloc_slab() and actual - * allocation, bump size when sizes are equal. - */ - if (s->object_size == obj_exts_cache->object_size) - return obj_exts_cache->object_size + 1; - - return sz; -} - int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, gfp_t gfp, unsigned int alloc_flags) { @@ -2168,14 +2132,18 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, unsigned long new_exts; unsigned long old_exts; struct slabobj_ext *vec; - size_t sz; + size_t sz = sizeof(struct slabobj_ext) * slab->objects; gfp &= ~OBJCGS_CLEAR_MASK; - /* Prevent recursive extension vector allocation */ - alloc_flags |= SLAB_ALLOC_NO_RECURSE; - alloc_flags &= ~SLAB_ALLOC_NEW_SLAB; + /* + * In most cases, obj_exts arrays are allocated from normal kmalloc. + * However, normal kmalloc caches must allocate them from + * KMALLOC_NO_OBJ_EXT caches to prevent recursion. + */ + if (is_kmalloc_normal(s)) + alloc_flags |= SLAB_ALLOC_NO_OBJ_EXT; - sz = obj_exts_alloc_size(s, slab, gfp); + alloc_flags &= ~SLAB_ALLOC_NEW_SLAB; /* This will use kmalloc_nolock() if alloc_flags say so */ vec = kmalloc_flags(sz, gfp | __GFP_ZERO, alloc_flags, slab_nid(slab)); @@ -2193,8 +2161,21 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, return -ENOMEM; } - VM_WARN_ON_ONCE(virt_to_slab(vec) != NULL && - virt_to_slab(vec)->slab_cache == s); + if (IS_ENABLED(CONFIG_DEBUG_VM)) { + struct kmem_cache *exts_cache; + struct slab *exts_slab; + + exts_slab = virt_to_slab(vec); + if (exts_slab) { + /* + * The vector must be allocated from either normal or + * KMALLOC_NO_OBJ_EXT kmalloc caches to avoid cycles. + */ + exts_cache = exts_slab->slab_cache; + WARN_ON_ONCE(!is_kmalloc_normal(exts_cache) && + !(exts_cache->flags & SLAB_NO_OBJ_EXT)); + } + } new_exts = (unsigned long)vec; #ifdef CONFIG_MEMCG @@ -2217,7 +2198,6 @@ retry: * assign slabobj_exts in parallel. In this case the existing * objcg vector should be reused. */ - mark_obj_codetag_empty(vec); if (unlikely(!allow_spin)) kfree_nolock(vec); else @@ -2253,14 +2233,6 @@ static inline void free_slab_obj_exts(struct slab *slab, bool allow_spin) return; } - /* - * obj_exts was created with SLAB_ALLOC_NO_RECURSE flag, therefore its - * corresponding extension will be NULL. alloc_tag_sub() will throw a - * warning if slab has extensions but the extension of an object is - * NULL, therefore replace NULL with CODETAG_EMPTY to indicate that - * the extension for obj_exts is expected to be NULL. - */ - mark_obj_codetag_empty(obj_exts); if (allow_spin) kfree(obj_exts); else @@ -5356,7 +5328,7 @@ void *__do_kmalloc_node(kmem_buckets *b, gfp_t flags, int node, if (unlikely(!size)) return ZERO_SIZE_PTR; - s = kmalloc_slab(size, b, flags, token); + s = kmalloc_slab(size, b, flags, token, ac->alloc_flags); ret = slab_alloc_node(s, flags, node, ac); ret = kasan_kmalloc(s, ret, size, flags); @@ -5419,7 +5391,9 @@ static void *__kmalloc_nolock_noprof(DECL_TOKEN_PARAMS(size, token), gfp_t gfp_f retry: if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) return NULL; - s = kmalloc_slab(size, NULL, gfp_flags, PASS_TOKEN_PARAM(token)); + + s = kmalloc_slab(size, NULL, gfp_flags, PASS_TOKEN_PARAM(token), + ac->alloc_flags); if (!(s->flags & __CMPXCHG_DOUBLE) && !kmem_cache_debug(s)) /* @@ -6217,7 +6191,6 @@ static void free_to_pcs_bulk(struct kmem_cache *s, size_t size, void **p) void *remote_objects[PCS_BATCH_MAX]; unsigned int remote_nr = 0; -next_remote_batch: while (i < size) { struct slab *slab = virt_to_slab(p[i]); @@ -6232,8 +6205,11 @@ next_remote_batch: if (unlikely(!can_free_to_pcs(slab))) { remote_objects[remote_nr] = p[i]; p[i] = p[--size]; - if (++remote_nr >= PCS_BATCH_MAX) - goto flush_remote; + if (++remote_nr >= PCS_BATCH_MAX) { + __kmem_cache_free_bulk(s, remote_nr, &remote_objects[0]); + stat_add(s, FREE_SLOWPATH, remote_nr); + remote_nr = 0; + } continue; } @@ -6317,10 +6293,6 @@ flush_remote: if (remote_nr) { __kmem_cache_free_bulk(s, remote_nr, &remote_objects[0]); stat_add(s, FREE_SLOWPATH, remote_nr); - if (i < size) { - remote_nr = 0; - goto next_remote_batch; - } } } @@ -7801,12 +7773,12 @@ static unsigned int calculate_sheaf_capacity(struct kmem_cache *s, return 0; /* - * Bootstrap caches can't have sheaves for now (SLAB_NO_OBJ_EXT). + * Bootstrap caches can't have sheaves for now (SLAB_NO_SHEAVES). * SLAB_NOLEAKTRACE caches (e.g., kmemleak's object_cache) must not * have sheaves to avoid recursion when sheaf allocation triggers * kmemleak tracking. */ - if (s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE)) + if (s->flags & (SLAB_NO_SHEAVES | SLAB_NOLEAKTRACE)) return 0; /* @@ -7981,10 +7953,10 @@ static int calculate_sizes(struct kmem_cache_args *args, struct kmem_cache *s) s->allocflags |= __GFP_RECLAIMABLE; /* - * For KMALLOC_NORMAL caches we enable sheaves later by - * bootstrap_kmalloc_sheaves() to avoid recursion + * For kmalloc caches we enable sheaves later by + * bootstrap_kmalloc_sheaves() to avoid recursion. */ - if (!is_kmalloc_normal(s)) + if (!is_kmalloc_cache(s)) s->sheaf_capacity = calculate_sheaf_capacity(s, args); /* @@ -8499,6 +8471,8 @@ static void __init bootstrap_cache_sheaves(struct kmem_cache *s) bool failed = false; int node, cpu; + VM_WARN_ON_ONCE(cache_has_sheaves(s)); + capacity = calculate_sheaf_capacity(s, &empty_args); /* capacity can be 0 due to debugging or SLUB_TINY */ @@ -8548,10 +8522,13 @@ static void __init bootstrap_kmalloc_sheaves(void) { enum kmalloc_cache_type type; - for (type = KMALLOC_NORMAL; type <= KMALLOC_PARTITION_END; type++) { + for (type = KMALLOC_NORMAL; type < NR_KMALLOC_TYPES; type++) { for (int idx = 0; idx < KMALLOC_SHIFT_HIGH + 1; idx++) { - if (kmalloc_caches[type][idx]) - bootstrap_cache_sheaves(kmalloc_caches[type][idx]); + struct kmem_cache *s = kmalloc_caches[type][idx]; + + /* Do not bootstrap twice when caches are aliased */ + if (s && !cache_has_sheaves(s)) + bootstrap_cache_sheaves(s); } } } @@ -8583,7 +8560,8 @@ void __init kmem_cache_init(void) create_boot_cache(kmem_cache_node, "kmem_cache_node", sizeof(struct kmem_cache_node), - SLAB_HWCACHE_ALIGN | SLAB_NO_OBJ_EXT, 0, 0); + SLAB_HWCACHE_ALIGN | SLAB_NO_SHEAVES | SLAB_NO_OBJ_EXT, + 0, 0); hotplug_node_notifier(slab_memory_callback, SLAB_CALLBACK_PRI); @@ -8593,7 +8571,8 @@ void __init kmem_cache_init(void) create_boot_cache(kmem_cache, "kmem_cache", offsetof(struct kmem_cache, per_node) + nr_node_ids * sizeof(struct kmem_cache_per_node_ptrs), - SLAB_HWCACHE_ALIGN | SLAB_NO_OBJ_EXT, 0, 0); + SLAB_HWCACHE_ALIGN | SLAB_NO_SHEAVES | SLAB_NO_OBJ_EXT, + 0, 0); kmem_cache = bootstrap(&boot_kmem_cache); kmem_cache_node = bootstrap(&boot_kmem_cache_node); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 99e2be39671b..ebd3ac997f64 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -564,6 +564,8 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn, if (r < 0) return NULL; + flush_cache_vmap(start, end); + return pfn_to_page(pfn); } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 246af12bf801..c3adedaaf7d5 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -2111,7 +2111,10 @@ static bool vma_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags, { const struct vm_uffd_ops *ops = vma_uffd_ops(vma); - if (vma->vm_flags & VM_DROPPABLE) + if (vma->vm_flags & (VM_DROPPABLE | VM_SHADOW_STACK)) + return false; + + if (!is_vm_hugetlb_page(vma) && (vma->vm_flags & VM_SPECIAL)) return false; vm_flags &= __VM_UFFD_FLAGS; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index b6d963ce26d0..741d658e9630 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2763,7 +2763,7 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) } mgmt_device_disconnected(hdev, &conn->dst, conn->type, conn->dst_type, - cp->reason, mgmt_conn); + hci_to_mgmt_reason(cp->reason), mgmt_conn); hci_disconn_cfm(conn, cp->reason); @@ -3381,22 +3381,6 @@ unlock: hci_dev_unlock(hdev); } -static u8 hci_to_mgmt_reason(u8 err) -{ - switch (err) { - case HCI_ERROR_CONNECTION_TIMEOUT: - return MGMT_DEV_DISCONN_TIMEOUT; - case HCI_ERROR_REMOTE_USER_TERM: - case HCI_ERROR_REMOTE_LOW_RESOURCES: - case HCI_ERROR_REMOTE_POWER_OFF: - return MGMT_DEV_DISCONN_REMOTE; - case HCI_ERROR_LOCAL_HOST_TERM: - return MGMT_DEV_DISCONN_LOCAL_HOST; - default: - return MGMT_DEV_DISCONN_UNKNOWN; - } -} - static void hci_disconn_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index c896d4edd013..c0b1fc293b49 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -929,12 +929,16 @@ int hci_update_eir_sync(struct hci_dev *hdev) memset(&cp, 0, sizeof(cp)); + hci_dev_lock(hdev); eir_create(hdev, cp.data); - if (memcmp(cp.data, hdev->eir, sizeof(cp.data)) == 0) + if (memcmp(cp.data, hdev->eir, sizeof(cp.data)) == 0) { + hci_dev_unlock(hdev); return 0; + } memcpy(hdev->eir, cp.data, sizeof(cp.data)); + hci_dev_unlock(hdev); return __hci_cmd_sync_status(hdev, HCI_OP_WRITE_EIR, sizeof(cp), &cp, HCI_CMD_TIMEOUT); @@ -966,6 +970,7 @@ int hci_update_class_sync(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_SERVICE_CACHE)) return 0; + hci_dev_lock(hdev); cod[0] = hdev->minor_class; cod[1] = hdev->major_class; cod[2] = get_service_classes(hdev); @@ -973,8 +978,12 @@ int hci_update_class_sync(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE)) cod[1] |= 0x20; - if (memcmp(cod, hdev->dev_class, 3) == 0) + if (memcmp(cod, hdev->dev_class, 3) == 0) { + hci_dev_unlock(hdev); return 0; + } + + hci_dev_unlock(hdev); return __hci_cmd_sync_status(hdev, HCI_OP_WRITE_CLASS_OF_DEV, sizeof(cod), cod, HCI_CMD_TIMEOUT); @@ -1054,14 +1063,19 @@ static int hci_set_random_addr_sync(struct hci_dev *hdev, bdaddr_t *rpa) * In this kind of scenario skip the update and let the random * address be updated at the next cycle. */ + rcu_read_lock(); + if (bacmp(&hdev->random_addr, BDADDR_ANY) && (hci_dev_test_flag(hdev, HCI_LE_ADV) || hci_lookup_le_connect(hdev))) { bt_dev_dbg(hdev, "Deferring random address update"); hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); + rcu_read_unlock(); return 0; } + rcu_read_unlock(); + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_RANDOM_ADDR, 6, rpa, HCI_CMD_TIMEOUT); } @@ -2647,12 +2661,17 @@ static int hci_pause_addr_resolution(struct hci_dev *hdev) /* Cannot disable addr resolution if scanning is enabled or * when initiating an LE connection. */ + rcu_read_lock(); + if (hci_dev_test_flag(hdev, HCI_LE_SCAN) || hci_lookup_le_connect(hdev)) { + rcu_read_unlock(); bt_dev_err(hdev, "Command not allowed when scan/LE connect"); return -EPERM; } + rcu_read_unlock(); + /* Cannot disable addr resolution if advertising is enabled. */ err = hci_pause_advertising_sync(hdev); if (err) { @@ -2790,6 +2809,8 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) { struct hci_conn *conn; + rcu_read_lock(); + conn = hci_conn_hash_lookup_create_pa_sync(hdev); if (conn) { struct conn_params pa; @@ -2799,6 +2820,8 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) bacpy(&pa.addr, &conn->dst); pa.addr_type = conn->dst_type; + rcu_read_unlock(); + /* Clear first since there could be addresses left * behind. */ @@ -2808,6 +2831,8 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) err = hci_le_add_accept_list_sync(hdev, &pa, &num_entries); goto done; + } else { + rcu_read_unlock(); } } @@ -2818,10 +2843,13 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) * the controller. */ list_for_each_entry_safe(b, t, &hdev->le_accept_list, list) { - if (hci_conn_hash_lookup_le(hdev, &b->bdaddr, b->bdaddr_type)) + rcu_read_lock(); + + if (hci_conn_hash_lookup_le(hdev, &b->bdaddr, b->bdaddr_type)) { + rcu_read_unlock(); continue; + } - /* Pointers not dereferenced, no locks needed */ pend_conn = hci_pend_le_action_lookup(&hdev->pend_le_conns, &b->bdaddr, b->bdaddr_type); @@ -2829,6 +2857,8 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) &b->bdaddr, b->bdaddr_type); + rcu_read_unlock(); + /* If the device is not likely to connect or report, * remove it from the acceptlist. */ @@ -2955,6 +2985,8 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, if (sent) { struct hci_conn *conn; + rcu_read_lock(); + conn = hci_conn_hash_lookup_ba(hdev, PA_LINK, &sent->bdaddr); if (conn) { @@ -2979,8 +3011,12 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, phy++; } + rcu_read_unlock(); + if (num_phy) goto done; + } else { + rcu_read_unlock(); } } } @@ -3231,12 +3267,16 @@ int hci_update_passive_scan_sync(struct hci_dev *hdev) /* If there is at least one pending LE connection, we should * keep the background scan running. */ + bool exists; /* If controller is connecting, we should not start scanning * since some controllers are not able to scan and connect at * the same time. */ - if (hci_lookup_le_connect(hdev)) + rcu_read_lock(); + exists = hci_lookup_le_connect(hdev); + rcu_read_unlock(); + if (exists) return 0; bt_dev_dbg(hdev, "start background scanning"); @@ -3454,6 +3494,7 @@ int hci_write_fast_connectable_sync(struct hci_dev *hdev, bool enable) } static bool disconnected_accept_list_entries(struct hci_dev *hdev) + __must_hold(&hdev->lock) { struct bdaddr_list *b; @@ -3494,12 +3535,16 @@ int hci_update_scan_sync(struct hci_dev *hdev) if (hdev->scanning_paused) return 0; + hci_dev_lock(hdev); + if (hci_dev_test_flag(hdev, HCI_CONNECTABLE) || disconnected_accept_list_entries(hdev)) scan = SCAN_PAGE; else scan = SCAN_DISABLED; + hci_dev_unlock(hdev); + if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) scan |= SCAN_INQUIRY; @@ -6665,6 +6710,8 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) if (!hci_dev_test_flag(hdev, HCI_LE_SIMULTANEOUS_ROLES)) hci_pause_advertising_sync(hdev); + hci_dev_lock(hdev); + params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); if (params) { conn->le_conn_min_interval = params->conn_min_interval; @@ -6678,6 +6725,8 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) conn->le_supv_timeout = hdev->le_supv_timeout; } + hci_dev_unlock(hdev); + /* If controller is scanning, we stop it since some controllers are * not able to scan and connect at the same time. Also set the * HCI_LE_SCAN_INTERRUPTED flag so that the command complete @@ -7235,13 +7284,13 @@ unlock: } static int hci_le_past_params_sync(struct hci_dev *hdev, struct hci_conn *conn, - struct hci_conn *acl, struct bt_iso_qos *qos) + u16 acl_handle, struct bt_iso_qos *qos) { struct hci_cp_le_past_params cp; int err; memset(&cp, 0, sizeof(cp)); - cp.handle = cpu_to_le16(acl->handle); + cp.handle = cpu_to_le16(acl_handle); /* An HCI_LE_Periodic_Advertising_Sync_Transfer_Received event is sent * to the Host. HCI_LE_Periodic_Advertising_Report events will be * enabled with duplicate filtering enabled. @@ -7306,16 +7355,28 @@ static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data) * 2. Check if that HCI_CONN_FLAG_PAST has been set which indicates that * user really intended to use PAST. */ + hci_dev_lock(hdev); + le = hci_conn_hash_lookup_le(hdev, &conn->dst, conn->dst_type); if (le) { struct hci_conn_params *params; + hci_conn_flags_t flags = 0; + u16 le_handle = le->handle; params = hci_conn_params_lookup(hdev, &le->dst, le->dst_type); - if (params && params->flags & HCI_CONN_FLAG_PAST) { - err = hci_le_past_params_sync(hdev, conn, le, qos); + if (params) + flags = params->flags; + + hci_dev_unlock(hdev); + + if (flags & HCI_CONN_FLAG_PAST) { + err = hci_le_past_params_sync(hdev, conn, le_handle, + qos); if (!err) goto done; } + } else { + hci_dev_unlock(hdev); } /* SID has not been set listen for HCI_EV_LE_EXT_ADV_REPORT to update diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 733a4b70e10c..1db10e0f617f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3091,6 +3091,8 @@ static int unpair_device_sync(struct hci_dev *hdev, void *data) struct mgmt_cp_unpair_device *cp = cmd->param; struct hci_conn *conn; + hci_dev_lock(hdev); + if (cp->addr.type == BDADDR_BREDR) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->addr.bdaddr); @@ -3098,6 +3100,11 @@ static int unpair_device_sync(struct hci_dev *hdev, void *data) conn = hci_conn_hash_lookup_le(hdev, &cp->addr.bdaddr, le_addr_type(cp->addr.type)); + if (conn) + hci_conn_get(conn); + + hci_dev_unlock(hdev); + if (!conn) return 0; @@ -3105,6 +3112,7 @@ static int unpair_device_sync(struct hci_dev *hdev, void *data) * will clean up the connection no matter the error. */ hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); + hci_conn_put(conn); return 0; } @@ -3252,6 +3260,8 @@ static int disconnect_sync(struct hci_dev *hdev, void *data) struct mgmt_cp_disconnect *cp = cmd->param; struct hci_conn *conn; + hci_dev_lock(hdev); + if (cp->addr.type == BDADDR_BREDR) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->addr.bdaddr); @@ -3259,6 +3269,11 @@ static int disconnect_sync(struct hci_dev *hdev, void *data) conn = hci_conn_hash_lookup_le(hdev, &cp->addr.bdaddr, le_addr_type(cp->addr.type)); + if (conn) + hci_conn_get(conn); + + hci_dev_unlock(hdev); + if (!conn) return -ENOTCONN; @@ -3266,6 +3281,7 @@ static int disconnect_sync(struct hci_dev *hdev, void *data) * will clean up the connection no matter the error. */ hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); + hci_conn_put(conn); return 0; } @@ -7388,6 +7404,9 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err) rp.max_tx_power = HCI_TX_POWER_INVALID; } + if (conn) + hci_conn_put(conn); + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, MGMT_OP_GET_CONN_INFO, status, &rp, sizeof(rp)); @@ -7402,6 +7421,8 @@ static int get_conn_info_sync(struct hci_dev *hdev, void *data) int err; __le16 handle; + hci_dev_lock(hdev); + /* Make sure we are still connected */ if (cp->addr.type == BDADDR_BREDR) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, @@ -7409,12 +7430,16 @@ static int get_conn_info_sync(struct hci_dev *hdev, void *data) else conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->addr.bdaddr); - if (!conn || conn->state != BT_CONNECTED) + if (!conn || conn->state != BT_CONNECTED) { + hci_dev_unlock(hdev); return MGMT_STATUS_NOT_CONNECTED; + } - cmd->user_data = conn; + cmd->user_data = hci_conn_get(conn); handle = cpu_to_le16(conn->handle); + hci_dev_unlock(hdev); + /* Refresh RSSI each time */ err = hci_read_rssi_sync(hdev, handle); @@ -7548,6 +7573,9 @@ static void get_clock_info_complete(struct hci_dev *hdev, void *data, int err) } complete: + if (conn) + hci_conn_put(conn); + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, status, &rp, sizeof(rp)); @@ -7564,15 +7592,21 @@ static int get_clock_info_sync(struct hci_dev *hdev, void *data) memset(&hci_cp, 0, sizeof(hci_cp)); hci_read_clock_sync(hdev, &hci_cp); + hci_dev_lock(hdev); + /* Make sure connection still exists */ conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->addr.bdaddr); - if (!conn || conn->state != BT_CONNECTED) + if (!conn || conn->state != BT_CONNECTED) { + hci_dev_unlock(hdev); return MGMT_STATUS_NOT_CONNECTED; + } - cmd->user_data = conn; + cmd->user_data = hci_conn_get(conn); hci_cp.handle = cpu_to_le16(conn->handle); hci_cp.which = 0x01; /* Piconet clock */ + hci_dev_unlock(hdev); + return hci_read_clock_sync(hdev, &hci_cp); } @@ -7937,14 +7971,36 @@ unlock: static int conn_update_sync(struct hci_dev *hdev, void *data) { - struct hci_conn_params *params = data; - struct hci_conn *conn; + struct hci_conn *conn = data; + struct hci_conn_params *params; + struct hci_conn_params local = {}; - conn = hci_conn_hash_lookup_le(hdev, ¶ms->addr, params->addr_type); - if (!conn) - return -ECANCELED; + hci_dev_lock(hdev); + + if (!hci_conn_valid(hdev, conn) || conn->role != HCI_ROLE_MASTER) + goto cancel; + + params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); + if (!params) + goto cancel; + + local.conn_min_interval = params->conn_min_interval; + local.conn_max_interval = params->conn_max_interval; + local.conn_latency = params->conn_latency; + local.supervision_timeout = params->supervision_timeout; + + hci_dev_unlock(hdev); + + return hci_le_conn_update_sync(hdev, conn, &local); - return hci_le_conn_update_sync(hdev, conn, params); +cancel: + hci_dev_unlock(hdev); + return -ECANCELED; +} + +static void conn_update_sync_destroy(struct hci_dev *hdev, void *data, int err) +{ + hci_conn_put(data); } static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, @@ -8054,9 +8110,13 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, (conn->le_conn_min_interval != min || conn->le_conn_max_interval != max || conn->le_conn_latency != latency || - conn->le_supv_timeout != timeout)) - hci_cmd_sync_queue(hdev, conn_update_sync, - hci_param, NULL); + conn->le_supv_timeout != timeout)) { + hci_conn_get(conn); + if (hci_cmd_sync_queue(hdev, conn_update_sync, + conn, + conn_update_sync_destroy) < 0) + hci_conn_put(conn); + } } } @@ -9848,6 +9908,22 @@ bool mgmt_powering_down(struct hci_dev *hdev) return false; } +u8 hci_to_mgmt_reason(u8 err) +{ + switch (err) { + case HCI_ERROR_CONNECTION_TIMEOUT: + return MGMT_DEV_DISCONN_TIMEOUT; + case HCI_ERROR_REMOTE_USER_TERM: + case HCI_ERROR_REMOTE_LOW_RESOURCES: + case HCI_ERROR_REMOTE_POWER_OFF: + return MGMT_DEV_DISCONN_REMOTE; + case HCI_ERROR_LOCAL_HOST_TERM: + return MGMT_DEV_DISCONN_LOCAL_HOST; + default: + return MGMT_DEV_DISCONN_UNKNOWN; + } +} + void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 reason, bool mgmt_connected) @@ -9909,7 +9985,8 @@ void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn, u8 status) if (test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) { mgmt_device_disconnected(hdev, &conn->dst, conn->type, - conn->dst_type, status, true); + conn->dst_type, + hci_to_mgmt_reason(status), true); return; } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index ebeae17b71d1..75f7512dec54 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1028,6 +1028,23 @@ int rfcomm_send_rpn(struct rfcomm_session *s, int cr, u8 dlci, return rfcomm_send_frame(s, buf, ptr - buf); } +int rfcomm_dlc_send_rpn(struct rfcomm_dlc *d, u8 bit_rate, u8 data_bits, + u8 stop_bits, u8 parity, u8 flow_ctrl_settings, + u8 xon_char, u8 xoff_char, u16 param_mask) +{ + int err = -ENOTCONN; + + rfcomm_lock(); + if (d->session) + err = rfcomm_send_rpn(d->session, 1, d->dlci, bit_rate, + data_bits, stop_bits, parity, + flow_ctrl_settings, xon_char, xoff_char, + param_mask); + rfcomm_unlock(); + + return err; +} + static int rfcomm_send_rls(struct rfcomm_session *s, int cr, u8 dlci, u8 status) { struct rfcomm_hdr *hdr; diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 4b9a699ec59b..b2c1060394e6 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -858,7 +858,7 @@ static void rfcomm_tty_set_termios(struct tty_struct *tty, BT_DBG("tty %p termios %p", tty, old); - if (!dev || !dev->dlc || !dev->dlc->session) + if (!dev || !dev->dlc) return; /* Handle turning off CRTSCTS */ @@ -979,9 +979,8 @@ static void rfcomm_tty_set_termios(struct tty_struct *tty, } if (changes) - rfcomm_send_rpn(dev->dlc->session, 1, dev->dlc->dlci, baud, - data_bits, stop_bits, parity, - RFCOMM_RPN_FLOW_NONE, x_on, x_off, changes); + rfcomm_dlc_send_rpn(dev->dlc, baud, data_bits, stop_bits, parity, + RFCOMM_RPN_FLOW_NONE, x_on, x_off, changes); } static void rfcomm_tty_throttle(struct tty_struct *tty) diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c index 71a12da30004..a713668ea34f 100644 --- a/net/bridge/br_netlink_tunnel.c +++ b/net/bridge/br_netlink_tunnel.c @@ -271,7 +271,8 @@ static void __vlan_tunnel_handle_range(const struct net_bridge_port *p, if (!*v_start) goto out_init; - if (v && curr_change && br_vlan_can_enter_range(v, *v_end)) { + if (v && curr_change && + br_vlan_can_enter_range(v, *v_end, br_get_pvid(vg))) { *v_end = v; return; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d55ea9516e3e..d3880f31edc4 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1627,7 +1627,8 @@ void br_vlan_notify(const struct net_bridge *br, u16 vid, u16 vid_range, int cmd); bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, - const struct net_bridge_vlan *range_end); + const struct net_bridge_vlan *range_end, + u16 pvid); void br_vlan_fill_forward_path_pvid(struct net_bridge *br, struct net_device_path_ctx *ctx, @@ -1874,7 +1875,8 @@ static inline void br_vlan_notify(const struct net_bridge *br, } static inline bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, - const struct net_bridge_vlan *range_end) + const struct net_bridge_vlan *range_end, + u16 pvid) { return true; } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 5560afcaaca3..31c1b2cf75d9 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1982,9 +1982,11 @@ out_kfree: /* check if v_curr can enter a range ending in range_end */ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, - const struct net_bridge_vlan *range_end) + const struct net_bridge_vlan *range_end, + u16 pvid) { - return v_curr->vid - range_end->vid == 1 && + return v_curr->vid != pvid && range_end->vid != pvid && + v_curr->vid - range_end->vid == 1 && range_end->flags == v_curr->flags && br_vlan_opts_eq_range(v_curr, range_end); } @@ -2066,8 +2068,8 @@ static int br_vlan_dump_dev(const struct net_device *dev, idx += range_end->vid - range_start->vid + 1; range_start = v; - } else if (dump_stats || v->vid == pvid || - !br_vlan_can_enter_range(v, range_end)) { + } else if (dump_stats || + !br_vlan_can_enter_range(v, range_end, pvid)) { u16 vlan_flags = br_vlan_flags(range_start, pvid); if (!br_vlan_fill_vids(skb, range_start->vid, diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index fcc200c3e3da..cb0f556ff40d 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -350,8 +350,7 @@ int br_vlan_process_options(const struct net_bridge *br, continue; } - if (v->vid == pvid || - !br_vlan_can_enter_range(v, curr_end)) { + if (!br_vlan_can_enter_range(v, curr_end, pvid)) { br_vlan_notify(br, p, curr_start->vid, curr_end->vid, RTM_NEWVLAN); curr_start = v; diff --git a/net/can/bcm.c b/net/can/bcm.c index a4bef2c48a55..3d637a1e0ac1 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -58,6 +58,7 @@ #include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> +#include <linux/workqueue.h> #include <linux/spinlock.h> #include <net/can.h> #include <net/sock.h> @@ -92,6 +93,8 @@ MODULE_ALIAS("can-proto-2"); #define BCM_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex) +static struct workqueue_struct *bcm_wq; + /* * easy access to the first 64 bit of can(fd)_frame payload. cp->data is * 64 bit aligned so the offset has to be multiples of 8 which is ensured @@ -105,14 +108,16 @@ static inline u64 get_u64(const struct canfd_frame *cp, int offset) struct bcm_op { struct list_head list; struct rcu_head rcu; + struct work_struct work; int ifindex; canid_t can_id; u32 flags; - unsigned long frames_abs, frames_filtered; + atomic_long_t frames_abs, frames_filtered; struct bcm_timeval ival1, ival2; struct hrtimer timer, thrtimer; ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg; int rx_ifindex; + int if_detected; /* first received ifindex in ANYDEV rx_op mode */ int cfsiz; u32 count; u32 nframes; @@ -124,7 +129,9 @@ struct bcm_op { struct canfd_frame last_sframe; struct sock *sk; struct net_device *rx_reg_dev; - spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */ + netdevice_tracker rx_reg_dev_tracker; + spinlock_t bcm_tx_lock; /* protect tx data and timer updates */ + spinlock_t bcm_rx_update_lock; /* protect filter/timer data updates */ }; struct bcm_sock { @@ -224,10 +231,13 @@ static int bcm_proc_show(struct seq_file *m, void *v) list_for_each_entry_rcu(op, &bo->rx_ops, list) { - unsigned long reduction; + long reduction, frames_filtered, frames_abs; + + frames_filtered = atomic_long_read(&op->frames_filtered); + frames_abs = atomic_long_read(&op->frames_abs); /* print only active entries & prevent division by zero */ - if (!op->frames_abs) + if (!frames_abs) continue; seq_printf(m, "rx_op: %03X %-5s ", op->can_id, @@ -249,15 +259,15 @@ static int bcm_proc_show(struct seq_file *m, void *v) (long long)ktime_to_us(op->kt_ival2)); seq_printf(m, "# recv %ld (%ld) => reduction: ", - op->frames_filtered, op->frames_abs); + frames_filtered, frames_abs); - reduction = 100 - (op->frames_filtered * 100) / op->frames_abs; + reduction = 100 - (frames_filtered * 100) / frames_abs; seq_printf(m, "%s%ld%%\n", (reduction == 100) ? "near " : "", reduction); } - list_for_each_entry(op, &bo->tx_ops, list) { + list_for_each_entry_rcu(op, &bo->tx_ops, list) { seq_printf(m, "tx_op: %03X %s ", op->can_id, bcm_proc_getifname(net, ifname, op->ifindex)); @@ -275,7 +285,8 @@ static int bcm_proc_show(struct seq_file *m, void *v) seq_printf(m, "t2=%lld ", (long long)ktime_to_us(op->kt_ival2)); - seq_printf(m, "# sent %ld\n", op->frames_abs); + seq_printf(m, "# sent %ld\n", + atomic_long_read(&op->frames_abs)); } seq_putc(m, '\n'); @@ -285,26 +296,50 @@ static int bcm_proc_show(struct seq_file *m, void *v) } #endif /* CONFIG_PROC_FS */ +static void bcm_update_rx_stats(struct bcm_op *op) +{ + /* prevent overflow of the reduction% calculation in bcm_proc_show() */ + if (atomic_long_inc_return(&op->frames_abs) > LONG_MAX / 100) { + atomic_long_set(&op->frames_filtered, 0); + atomic_long_set(&op->frames_abs, 0); + } +} + +static void bcm_update_tx_stats(struct bcm_op *op) +{ + /* tx_op has no reduction% calculation - use the full range and + * just keep the displayed counter non-negative on overflow + */ + if (atomic_long_inc_return(&op->frames_abs) == LONG_MAX) + atomic_long_set(&op->frames_abs, 0); +} + /* * bcm_can_tx - send the (next) CAN frame to the appropriate CAN interface * of the given bcm tx op */ -static void bcm_can_tx(struct bcm_op *op) +static void bcm_can_tx(struct bcm_op *op, struct canfd_frame *cf) { struct sk_buff *skb; struct can_skb_ext *csx; struct net_device *dev; - struct canfd_frame *cf; + struct canfd_frame cframe; + bool cyclic = !cf; + unsigned int idx = 0; int err; /* no target device? => exit */ if (!op->ifindex) return; - /* read currframe under lock protection */ - spin_lock_bh(&op->bcm_tx_lock); - cf = op->frames + op->cfsiz * op->currframe; - spin_unlock_bh(&op->bcm_tx_lock); + if (cyclic) { + /* read currframe under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + idx = op->currframe; + memcpy(&cframe, op->frames + op->cfsiz * idx, op->cfsiz); + cf = &cframe; + spin_unlock_bh(&op->bcm_tx_lock); + } dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (!dev) { @@ -335,16 +370,22 @@ static void bcm_can_tx(struct bcm_op *op) spin_lock_bh(&op->bcm_tx_lock); if (!err) - op->frames_abs++; + bcm_update_tx_stats(op); - op->currframe++; + /* only advance the cyclic sequence if nothing reset currframe while + * we were sending - a concurrent TX_RESET_MULTI_IDX means this + * frame's bookkeeping belongs to a sequence that no longer exists + */ + if (!cyclic || op->currframe == idx) { + op->currframe++; - /* reached last frame? */ - if (op->currframe >= op->nframes) - op->currframe = 0; + /* reached last frame? */ + if (op->currframe >= op->nframes) + op->currframe = 0; - if (op->count > 0) - op->count--; + if (op->count > 0) + op->count--; + } spin_unlock_bh(&op->bcm_tx_lock); out: @@ -433,12 +474,18 @@ static bool bcm_tx_set_expiry(struct bcm_op *op, struct hrtimer *hrt) { ktime_t ival; + spin_lock_bh(&op->bcm_tx_lock); + if (op->kt_ival1 && op->count) ival = op->kt_ival1; - else if (op->kt_ival2) + else if (op->kt_ival2) { ival = op->kt_ival2; - else + } else { + spin_unlock_bh(&op->bcm_tx_lock); return false; + } + + spin_unlock_bh(&op->bcm_tx_lock); hrtimer_set_expires(hrt, ktime_add(ktime_get(), ival)); return true; @@ -455,26 +502,48 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; + bool tx_ival1, tx_ival2; + + /* snapshot kt_ival1/kt_ival2/count under lock to avoid torn + * ktime_t reads racing with concurrent bcm_tx_setup() updates + */ + spin_lock_bh(&op->bcm_tx_lock); + tx_ival1 = op->kt_ival1 && (op->count > 0); + tx_ival2 = !!op->kt_ival2; + spin_unlock_bh(&op->bcm_tx_lock); + + if (tx_ival1) { + u32 flags, count; + struct bcm_timeval ival1, ival2; - if (op->kt_ival1 && (op->count > 0)) { - bcm_can_tx(op); - if (!op->count && (op->flags & TX_COUNTEVT)) { + bcm_can_tx(op, NULL); + /* snapshot variables under lock to avoid torn reads racing + * with concurrent bcm_tx_setup() updates + */ + spin_lock_bh(&op->bcm_tx_lock); + flags = op->flags; + count = op->count; + ival1 = op->ival1; + ival2 = op->ival2; + spin_unlock_bh(&op->bcm_tx_lock); + + if (!count && (flags & TX_COUNTEVT)) { /* create notification to user */ memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; - msg_head.flags = op->flags; - msg_head.count = op->count; - msg_head.ival1 = op->ival1; - msg_head.ival2 = op->ival2; + msg_head.flags = flags; + msg_head.count = count; + msg_head.ival1 = ival1; + msg_head.ival2 = ival2; msg_head.can_id = op->can_id; msg_head.nframes = 0; bcm_send_to_user(op, &msg_head, NULL, 0); } - } else if (op->kt_ival2) { - bcm_can_tx(op); + } else if (tx_ival2) { + bcm_can_tx(op, NULL); } return bcm_tx_set_expiry(op, &op->timer) ? @@ -488,12 +557,9 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) { struct bcm_msg_head head; - /* update statistics */ - op->frames_filtered++; - - /* prevent statistics overflow */ - if (op->frames_filtered > ULONG_MAX/100) - op->frames_filtered = op->frames_abs = 0; + /* update statistics (frames_filtered <= frames_abs) */ + if (atomic_long_read(&op->frames_abs)) + atomic_long_inc(&op->frames_filtered); /* this element is not throttled anymore */ data->flags &= ~RX_THR; @@ -618,6 +684,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; + spin_lock_bh(&op->bcm_rx_update_lock); + /* if user wants to be informed, when cyclic CAN-Messages come back */ if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) { /* clear received CAN frames to indicate 'nothing received' */ @@ -634,6 +702,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) msg_head.can_id = op->can_id; msg_head.nframes = 0; + spin_unlock_bh(&op->bcm_rx_update_lock); + bcm_send_to_user(op, &msg_head, NULL, 0); return HRTIMER_NORESTART; @@ -682,15 +752,26 @@ static int bcm_rx_thr_flush(struct bcm_op *op) static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, thrtimer); + enum hrtimer_restart ret; + + spin_lock_bh(&op->bcm_rx_update_lock); - if (bcm_rx_thr_flush(op)) { + /* kt_ival2 may have been concurrently cleared by bcm_rx_setup() + * before it cancels this timer - never forward with a zero + * interval in that case. + */ + if (bcm_rx_thr_flush(op) && op->kt_ival2) { hrtimer_forward_now(hrtimer, op->kt_ival2); - return HRTIMER_RESTART; + ret = HRTIMER_RESTART; } else { /* rearm throttle handling */ op->kt_lastmsg = 0; - return HRTIMER_NORESTART; + ret = HRTIMER_NORESTART; } + + spin_unlock_bh(&op->bcm_rx_update_lock); + + return ret; } /* @@ -700,8 +781,10 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) { struct bcm_op *op = (struct bcm_op *)data; const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data; + struct canfd_frame rtrframe; unsigned int i; unsigned char traffic_flags; + bool rtr_frame; if (op->can_id != rxframe->can_id) return; @@ -715,22 +798,59 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) return; } + /* An ANYDEV op with an active RX timeout and/or throttle timer + * tracks a single source interface: claim the first interface that + * delivers a matching frame and reject frames from any other one, + * before hrtimer_cancel() below can touch op->timer - this avoids + * racing bcm_rx_timeout_handler() across concurrent interfaces. + * RX_RTR_FRAME ops are excluded, as kt_ival1/kt_ival2 may briefly + * hold a stale value from an earlier non-RTR configuration. + */ + if (!op->ifindex) { + spin_lock_bh(&op->bcm_rx_update_lock); + + if (!(op->flags & RX_RTR_FRAME) && + (op->kt_ival1 || op->kt_ival2)) { + /* don't claim to vanishing interface */ + if (!op->if_detected && + READ_ONCE(skb->dev->reg_state) == NETREG_REGISTERED) + op->if_detected = skb->dev->ifindex; + + if (op->if_detected != skb->dev->ifindex) { + spin_unlock_bh(&op->bcm_rx_update_lock); + return; + } + } + + spin_unlock_bh(&op->bcm_rx_update_lock); + } + /* disable timeout */ hrtimer_cancel(&op->timer); - /* save rx timestamp */ - op->rx_stamp = skb->tstamp; - /* save originator for recvfrom() */ - op->rx_ifindex = skb->dev->ifindex; - /* update statistics */ - op->frames_abs++; + /* op->flags/op->frames may be updated concurrently by bcm_rx_setup() */ + spin_lock_bh(&op->bcm_rx_update_lock); + + rtr_frame = op->flags & RX_RTR_FRAME; + if (rtr_frame) { + bcm_update_rx_stats(op); + /* snapshot RTR content under lock */ + memcpy(&rtrframe, op->frames, op->cfsiz); + spin_unlock_bh(&op->bcm_rx_update_lock); - if (op->flags & RX_RTR_FRAME) { /* send reply for RTR-request (placed in op->frames[0]) */ - bcm_can_tx(op); + bcm_can_tx(op, &rtrframe); return; } + /* update statistics in the same critical section as bcm_rx_changed() + * below: frames_filtered must never be checked/incremented against a + * frames_abs snapshot from a concurrent bcm_rx_handler() call on + * another CPU for the same (wildcard) op, or frames_filtered can end + * up larger than frames_abs. + */ + bcm_update_rx_stats(op); + /* compute flags to distinguish between own/local/remote CAN traffic */ traffic_flags = 0; if (skb->sk) { @@ -739,6 +859,13 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) traffic_flags |= RX_OWN; } + /* save rx timestamp and originator for recvfrom() under lock: an + * ANYDEV op without an active timer can still run concurrently on + * different CPUs, so content and meta data must be bundled here. + */ + op->rx_stamp = skb->tstamp; + op->rx_ifindex = skb->dev->ifindex; + if (op->flags & RX_FILTER_ID) { /* the easiest case */ bcm_rx_update_and_send(op, op->last_frames, rxframe, @@ -774,6 +901,8 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) rx_starttimer: bcm_rx_starttimer(op); + + spin_unlock_bh(&op->bcm_rx_update_lock); } /* @@ -793,9 +922,12 @@ static struct bcm_op *bcm_find_op(struct list_head *ops, return NULL; } -static void bcm_free_op_rcu(struct rcu_head *rcu_head) +static void bcm_free_op_work(struct work_struct *work) { - struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu); + struct bcm_op *op = container_of(work, struct bcm_op, work); + + hrtimer_cancel(&op->timer); + hrtimer_cancel(&op->thrtimer); if ((op->frames) && (op->frames != &op->sframe)) kfree(op->frames); @@ -803,9 +935,23 @@ static void bcm_free_op_rcu(struct rcu_head *rcu_head) if ((op->last_frames) && (op->last_frames != &op->last_sframe)) kfree(op->last_frames); + /* the last possible access to op->timer/op->thrtimer has now + * happened above via hrtimer_cancel() - op->sk is no longer + * needed by any pending timer callback, so drop our reference + */ + sock_put(op->sk); + kfree(op); } +static void bcm_free_op_rcu(struct rcu_head *rcu_head) +{ + struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu); + + INIT_WORK(&op->work, bcm_free_op_work); + queue_work(bcm_wq, &op->work); +} + static void bcm_remove_op(struct bcm_op *op) { hrtimer_cancel(&op->timer); @@ -822,6 +968,7 @@ static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op) /* mark as removed subscription */ op->rx_reg_dev = NULL; + netdev_put(dev, &op->rx_reg_dev_tracker); } else printk(KERN_ERR "can-bcm: bcm_rx_unreg: registered device " "mismatch %p %p\n", op->rx_reg_dev, dev); @@ -852,17 +999,14 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, * Only remove subscriptions that had not * been removed due to NETDEV_UNREGISTER * in bcm_notifier() + * + * op->rx_reg_dev is a tracked reference taken + * when the subscription was registered, so it + * stays valid here even if a concurrent + * NETDEV_UNREGISTER already unlisted the dev. */ - if (op->rx_reg_dev) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(op->sk), - op->ifindex); - if (dev) { - bcm_rx_unreg(dev, op); - dev_put(dev); - } - } + if (op->rx_reg_dev) + bcm_rx_unreg(op->rx_reg_dev, op); } else can_rx_unregister(sock_net(op->sk), NULL, op->can_id, @@ -930,6 +1074,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; struct canfd_frame *cf; + bool add_op_to_list = false; unsigned int i; int err; @@ -948,6 +1093,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* check the given can_id */ op = bcm_find_op(&bo->tx_ops, msg_head, ifindex); if (op) { + void *new_frames; + /* update existing BCM operation */ /* @@ -958,11 +1105,23 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (msg_head->nframes > op->nframes) return -E2BIG; - /* update CAN frames content */ + /* get new CAN frames content into a staging buffer before + * locking: validate and normalize the frames there so that + * bcm_can_tx() / bcm_tx_timeout_handler() never observe a + * partially updated or unvalidated frame in op->frames + */ + new_frames = kmalloc(msg_head->nframes * op->cfsiz, GFP_KERNEL); + if (!new_frames) + return -ENOMEM; + for (i = 0; i < msg_head->nframes; i++) { - cf = op->frames + op->cfsiz * i; + cf = new_frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); + if (err < 0) { + kfree(new_frames); + return err; + } if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) @@ -972,36 +1131,38 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, err = -EINVAL; } - if (err < 0) + if (err < 0) { + kfree(new_frames); return err; + } if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ cf->can_id = msg_head->can_id; } } + + spin_lock_bh(&op->bcm_tx_lock); + + /* update CAN frames content */ + memcpy(op->frames, new_frames, msg_head->nframes * op->cfsiz); + op->flags = msg_head->flags; - /* only lock for unlikely count/nframes/currframe changes */ if (op->nframes != msg_head->nframes || - op->flags & TX_RESET_MULTI_IDX || - op->flags & SETTIMER) { - - spin_lock_bh(&op->bcm_tx_lock); + op->flags & TX_RESET_MULTI_IDX) { + /* potentially update changed nframes */ + op->nframes = msg_head->nframes; + /* restart multiple frame transmission */ + op->currframe = 0; + } - if (op->nframes != msg_head->nframes || - op->flags & TX_RESET_MULTI_IDX) { - /* potentially update changed nframes */ - op->nframes = msg_head->nframes; - /* restart multiple frame transmission */ - op->currframe = 0; - } + if (op->flags & SETTIMER) + op->count = msg_head->count; - if (op->flags & SETTIMER) - op->count = msg_head->count; + spin_unlock_bh(&op->bcm_tx_lock); - spin_unlock_bh(&op->bcm_tx_lock); - } + kfree(new_frames); } else { /* insert new BCM operation for the given can_id */ @@ -1060,6 +1221,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* bcm_can_tx / bcm_tx_timeout_handler needs this */ op->sk = sk; + sock_hold(sk); op->ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ @@ -1070,17 +1232,18 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, hrtimer_setup(&op->thrtimer, hrtimer_dummy_timeout, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); - /* add this bcm_op to the list of the tx_ops */ - list_add(&op->list, &bo->tx_ops); + add_op_to_list = true; } /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */ if (op->flags & SETTIMER) { /* set timer values */ + spin_lock_bh(&op->bcm_tx_lock); op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); + spin_unlock_bh(&op->bcm_tx_lock); /* disable an active timer due to zero values? */ if (!op->kt_ival1 && !op->kt_ival2) @@ -1093,8 +1256,12 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->flags |= TX_ANNOUNCE; } + /* add this bcm_op to the list of the tx_ops? */ + if (add_op_to_list) + list_add_rcu(&op->list, &bo->tx_ops); + if (op->flags & TX_ANNOUNCE) - bcm_can_tx(op); + bcm_can_tx(op, NULL); if (op->flags & STARTTIMER) bcm_tx_start_timer(op); @@ -1108,6 +1275,39 @@ free_op: return err; } +static int bcm_rx_setup_rtr_check(struct bcm_msg_head *msg_head, + struct bcm_op *op, void *new_frames) +{ + struct canfd_frame *frame0 = new_frames; + + if (!(msg_head->flags & RX_RTR_FRAME)) + return 0; + + /* this frame is sent out as-is by bcm_can_tx() whenever a matching + * remote request is received, so validate its length the same way + * bcm_tx_setup() validates TX_SETUP frames before installing it + */ + if (msg_head->flags & CAN_FD_FRAME) { + if (frame0->len > 64) + return -EINVAL; + } else { + if (frame0->len > 8) + return -EINVAL; + } + + /* funny feature in RX(!)_SETUP only for RTR-mode: + * copy can_id into frame BUT without RTR-flag to + * prevent a full-load-loopback-test ... ;-] + * normalize this on the staged buffer, before it is + * ever installed into op->frames. + */ + if ((msg_head->flags & TX_CP_CAN_ID) || + frame0->can_id == op->can_id) + frame0->can_id = op->can_id & ~CAN_RTR_FLAG; + + return 0; +} + /* * bcm_rx_setup - create or update a bcm rx op (for bcm_sendmsg) */ @@ -1117,6 +1317,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; int do_rx_register; + int new_op = 0; int err = 0; if ((msg_head->flags & RX_FILTER_ID) || (!(msg_head->nframes))) { @@ -1142,6 +1343,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* check the given can_id */ op = bcm_find_op(&bo->rx_ops, msg_head, ifindex); if (op) { + void *new_frames = NULL; + /* update existing BCM operation */ /* @@ -1153,21 +1356,62 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, return -E2BIG; if (msg_head->nframes) { - /* update CAN frames content */ - err = memcpy_from_msg(op->frames, msg, + /* get new CAN frames content before locking */ + new_frames = kmalloc(msg_head->nframes * op->cfsiz, + GFP_KERNEL); + if (!new_frames) + return -ENOMEM; + + err = memcpy_from_msg(new_frames, msg, msg_head->nframes * op->cfsiz); - if (err < 0) + if (err < 0) { + kfree(new_frames); return err; + } - /* clear last_frames to indicate 'nothing received' */ - memset(op->last_frames, 0, msg_head->nframes * op->cfsiz); + err = bcm_rx_setup_rtr_check(msg_head, op, new_frames); + if (err < 0) { + kfree(new_frames); + return err; + } } + spin_lock_bh(&op->bcm_rx_update_lock); op->nframes = msg_head->nframes; op->flags = msg_head->flags; - /* Only an update -> do not call can_rx_register() */ - do_rx_register = 0; + if (msg_head->nframes) { + /* update CAN frames content */ + memcpy(op->frames, new_frames, + msg_head->nframes * op->cfsiz); + + /* clear last_frames to indicate 'nothing received' */ + memset(op->last_frames, 0, + msg_head->nframes * op->cfsiz); + } + + if (msg_head->flags & SETTIMER) { + op->ival1 = msg_head->ival1; + op->ival2 = msg_head->ival2; + op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); + op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); + op->kt_lastmsg = 0; + op->if_detected = 0; /* reclaim ifindex in ANYDEV mode */ + } + spin_unlock_bh(&op->bcm_rx_update_lock); + + /* free temporary frames / kfree(NULL) is safe */ + kfree(new_frames); + + /* Don't register a new CAN filter for the rx_op update unless + * a concurrent NETDEV_UNREGISTER notifier already tore down + * the previous registration. In this case the receiver needs + * to be re-registered here so that this update doesn't + * silently stop delivering frames for the given ifindex. + * Ops with ifindex = 0 (all CAN interfaces) never carry a + * tracked rx_reg_dev and stay registered as-is. + */ + do_rx_register = (ifindex && !op->rx_reg_dev) ? 1 : 0; } else { /* insert new BCM operation for the given can_id */ @@ -1176,6 +1420,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, return -ENOMEM; spin_lock_init(&op->bcm_tx_lock); + spin_lock_init(&op->bcm_rx_update_lock); op->can_id = msg_head->can_id; op->nframes = msg_head->nframes; op->cfsiz = CFSIZ(msg_head->flags); @@ -1209,18 +1454,17 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (msg_head->nframes) { err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz); - if (err < 0) { - if (op->frames != &op->sframe) - kfree(op->frames); - if (op->last_frames != &op->last_sframe) - kfree(op->last_frames); - kfree(op); - return err; - } + if (err < 0) + goto free_op; + + err = bcm_rx_setup_rtr_check(msg_head, op, op->frames); + if (err < 0) + goto free_op; } /* bcm_can_tx / bcm_tx_timeout_handler needs this */ op->sk = sk; + sock_hold(sk); op->ifindex = ifindex; /* ifindex for timeout events w/o previous frame reception */ @@ -1232,40 +1476,31 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, hrtimer_setup(&op->thrtimer, bcm_rx_thr_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); - /* add this bcm_op to the list of the rx_ops */ - list_add(&op->list, &bo->rx_ops); - /* call can_rx_register() */ do_rx_register = 1; + new_op = 1; } /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */ /* check flags */ if (op->flags & RX_RTR_FRAME) { - struct canfd_frame *frame0 = op->frames; - /* no timers in RTR-mode */ hrtimer_cancel(&op->thrtimer); hrtimer_cancel(&op->timer); - - /* - * funny feature in RX(!)_SETUP only for RTR-mode: - * copy can_id into frame BUT without RTR-flag to - * prevent a full-load-loopback-test ... ;-] - */ - if ((op->flags & TX_CP_CAN_ID) || - (frame0->can_id == op->can_id)) - frame0->can_id = op->can_id & ~CAN_RTR_FLAG; - } else { if (op->flags & SETTIMER) { - /* set timer value */ - op->ival1 = msg_head->ival1; - op->ival2 = msg_head->ival2; - op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); - op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); + /* set timers (locked) for newly created op */ + if (new_op) { + spin_lock_bh(&op->bcm_rx_update_lock); + op->ival1 = msg_head->ival1; + op->ival2 = msg_head->ival2; + op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); + op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); + op->kt_lastmsg = 0; + spin_unlock_bh(&op->bcm_rx_update_lock); + } /* disable an active timer due to zero value? */ if (!op->kt_ival1) @@ -1275,9 +1510,11 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, * In any case cancel the throttle timer, flush * potentially blocked msgs and reset throttle handling */ - op->kt_lastmsg = 0; hrtimer_cancel(&op->thrtimer); + + spin_lock_bh(&op->bcm_rx_update_lock); bcm_rx_thr_flush(op); + spin_unlock_bh(&op->bcm_rx_update_lock); } if ((op->flags & STARTTIMER) && op->kt_ival1) @@ -1285,7 +1522,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, HRTIMER_MODE_REL_SOFT); } - /* now we can register for can_ids, if we added a new bcm_op */ + /* now we can register for can_ids, if we added a new bcm_op + * or need to re-register after a NETDEV_UNREGISTER tore down + * the previous registration of an existing op + */ if (do_rx_register) { if (ifindex) { struct net_device *dev; @@ -1298,23 +1538,62 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_rx_handler, op, "bcm", sk); - op->rx_reg_dev = dev; + /* keep a tracked reference so that a later + * unregister can safely reach the device even + * if a concurrent NETDEV_UNREGISTER has + * already unlisted it by ifindex + */ + if (!err) { + op->rx_reg_dev = dev; + netdev_hold(dev, + &op->rx_reg_dev_tracker, + GFP_KERNEL); + } dev_put(dev); + } else { + /* the requested device is gone - do not + * silently succeed without registering + */ + err = -ENODEV; } - } else + } else { err = can_rx_register(sock_net(sk), NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); + } + if (err) { - /* this bcm rx op is broken -> remove it */ - list_del_rcu(&op->list); - bcm_remove_op(op); + /* newly created bcm rx op is broken -> remove it */ + if (new_op) { + bcm_remove_op(op); + return err; + } + + /* an existing op just stays unregistered. + * Cancel op->timer and (defensively) op->thrtimer. + * Other settings can't be reached until the next + * successful RX_SETUP. + */ + hrtimer_cancel(&op->timer); + hrtimer_cancel(&op->thrtimer); return err; } + + /* add a new bcm_op to the list of the rx_ops */ + if (new_op) + list_add_rcu(&op->list, &bo->rx_ops); } return msg_head->nframes * op->cfsiz + MHSIZ; + +free_op: + if (op->frames != &op->sframe) + kfree(op->frames); + if (op->last_frames != &op->last_sframe) + kfree(op->last_frames); + kfree(op); + return err; } /* @@ -1373,12 +1652,13 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); - int ifindex = bo->ifindex; /* default ifindex for this bcm_op */ + int ifindex; struct bcm_msg_head msg_head; int cfsiz; int ret; /* read bytes or error codes as return value */ - if (!bo->bound) + /* Lockless fast-path check for bound socket */ + if (!READ_ONCE(bo->bound)) return -ENOTCONN; /* check for valid message length from userspace */ @@ -1394,17 +1674,38 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if ((size - MHSIZ) % cfsiz) return -EINVAL; + lock_sock(sk); + + /* Re-validate under the socket lock: a concurrent bcm_notify() + * may have unbound this socket (device removal) after the + * lockless fast-path check above. bo->ifindex is only ever + * mutated under lock_sock(), so reading it here - instead of + * before taking the lock - guarantees it can't be observed + * torn against bo->bound. + */ + if (!bo->bound) { + ret = -ENOTCONN; + goto out_release; + } + + /* default ifindex for this bcm_op */ + ifindex = bo->ifindex; + /* check for alternative ifindex for this bcm_op */ if (!ifindex && msg->msg_name) { /* no bound device as default => check msg_name */ DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); - if (msg->msg_namelen < BCM_MIN_NAMELEN) - return -EINVAL; + if (msg->msg_namelen < BCM_MIN_NAMELEN) { + ret = -EINVAL; + goto out_release; + } - if (addr->can_family != AF_CAN) - return -EINVAL; + if (addr->can_family != AF_CAN) { + ret = -EINVAL; + goto out_release; + } /* ifindex from sendto() */ ifindex = addr->can_ifindex; @@ -1413,20 +1714,21 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) struct net_device *dev; dev = dev_get_by_index(sock_net(sk), ifindex); - if (!dev) - return -ENODEV; + if (!dev) { + ret = -ENODEV; + goto out_release; + } if (dev->type != ARPHRD_CAN) { dev_put(dev); - return -ENODEV; + ret = -ENODEV; + goto out_release; } dev_put(dev); } } - lock_sock(sk); - switch (msg_head.opcode) { case TX_SETUP: @@ -1476,6 +1778,7 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) break; } +out_release: release_sock(sk); return ret; @@ -1499,11 +1802,30 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); - /* remove device specific receive entries */ - list_for_each_entry(op, &bo->rx_ops, list) + /* rx_ops: remove device specific receive entries */ + list_for_each_entry(op, &bo->rx_ops, list) { if (op->rx_reg_dev == dev) bcm_rx_unreg(dev, op); + /* release an ANYDEV op's claim (see bcm_rx_handler()) + * on this now confirmed-gone interface. + */ + if (!op->ifindex) { + spin_lock_bh(&op->bcm_rx_update_lock); + if (op->if_detected == dev->ifindex) + op->if_detected = 0; + spin_unlock_bh(&op->bcm_rx_update_lock); + } + } + + /* tx_ops: stop device specific cyclic transmissions on the + * vanishing ifindex. Cancelling the timer is enough to stop + * cyclic bcm_can_tx() calls as there is no re-arming. + */ + list_for_each_entry(op, &bo->tx_ops, list) + if (op->ifindex == dev->ifindex) + hrtimer_cancel(&op->timer); + /* remove device reference, if this is our bound device */ if (bo->bound && bo->ifindex == dev->ifindex) { #if IS_ENABLED(CONFIG_PROC_FS) @@ -1512,7 +1834,12 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, bo->bcm_proc_read = NULL; } #endif - bo->bound = 0; + /* Paired with the lockless fast-path check in + * bcm_sendmsg(); bo->ifindex itself is only ever + * accessed under lock_sock() so it needs no + * annotation. + */ + WRITE_ONCE(bo->bound, 0); bo->ifindex = 0; notify_enodev = 1; } @@ -1616,8 +1943,10 @@ static int bcm_release(struct socket *sock) remove_proc_entry(bo->procname, net->can.bcmproc_dir); #endif /* CONFIG_PROC_FS */ - list_for_each_entry_safe(op, next, &bo->tx_ops, list) + list_for_each_entry_safe(op, next, &bo->tx_ops, list) { + list_del_rcu(&op->list); bcm_remove_op(op); + } list_for_each_entry_safe(op, next, &bo->rx_ops, list) { /* @@ -1629,16 +1958,14 @@ static int bcm_release(struct socket *sock) * Only remove subscriptions that had not * been removed due to NETDEV_UNREGISTER * in bcm_notifier() + * + * op->rx_reg_dev is a tracked reference taken + * when the subscription was registered, so it + * stays valid here even if a concurrent + * NETDEV_UNREGISTER already unlisted the device. */ - if (op->rx_reg_dev) { - struct net_device *dev; - - dev = dev_get_by_index(net, op->ifindex); - if (dev) { - bcm_rx_unreg(dev, op); - dev_put(dev); - } - } + if (op->rx_reg_dev) + bcm_rx_unreg(op->rx_reg_dev, op); } else can_rx_unregister(net, NULL, op->can_id, REGMASK(op->can_id), @@ -1648,12 +1975,14 @@ static int bcm_release(struct socket *sock) synchronize_rcu(); - list_for_each_entry_safe(op, next, &bo->rx_ops, list) + list_for_each_entry_safe(op, next, &bo->rx_ops, list) { + list_del_rcu(&op->list); bcm_remove_op(op); + } /* remove device reference */ if (bo->bound) { - bo->bound = 0; + WRITE_ONCE(bo->bound, 0); bo->ifindex = 0; } @@ -1723,7 +2052,10 @@ static int bcm_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int } #endif /* CONFIG_PROC_FS */ - bo->bound = 1; + /* bo->ifindex above is fully assigned before this point; pairs + * with the lockless fast-path check in bcm_sendmsg() + */ + WRITE_ONCE(bo->bound, 1); fail: release_sock(sk); @@ -1839,11 +2171,15 @@ static int __init bcm_module_init(void) { int err; + bcm_wq = alloc_workqueue("can-bcm-wq", WQ_UNBOUND, 0); + if (!bcm_wq) + return -ENOMEM; + pr_info("can: broadcast manager protocol\n"); err = register_pernet_subsys(&canbcm_pernet_ops); if (err) - return err; + goto register_pernet_failed; err = register_netdevice_notifier(&canbcm_notifier); if (err) @@ -1861,6 +2197,8 @@ register_proto_failed: unregister_netdevice_notifier(&canbcm_notifier); register_notifier_failed: unregister_pernet_subsys(&canbcm_pernet_ops); +register_pernet_failed: + destroy_workqueue(bcm_wq); return err; } @@ -1869,6 +2207,8 @@ static void __exit bcm_module_exit(void) can_proto_unregister(&bcm_can_proto); unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); + rcu_barrier(); + destroy_workqueue(bcm_wq); } module_init(bcm_module_init); diff --git a/net/can/isotp.c b/net/can/isotp.c index c48b4a818297..54becaf6898f 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -152,11 +152,13 @@ struct isotp_sock { struct sock sk; int bound; int ifindex; + struct net_device *dev; + netdevice_tracker dev_tracker; canid_t txid; canid_t rxid; ktime_t tx_gap; ktime_t lastrxcf_tstamp; - struct hrtimer rxtimer, txtimer, txfrtimer; + struct hrtimer rxtimer, txtimer, txfrtimer, echotimer; struct can_isotp_options opt; struct can_isotp_fc_options rxfc, txfc; struct can_isotp_ll_options ll; @@ -164,6 +166,7 @@ struct isotp_sock { u32 force_tx_stmin; u32 force_rx_stmin; u32 cfecho; /* consecutive frame echo tag */ + u32 tx_gen; /* generation, bumped per new tx transfer */ struct tpcon rx, tx; struct list_head notifier; wait_queue_head_t wait; @@ -376,6 +379,15 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) hrtimer_cancel(&so->txtimer); + /* isotp_tx_timeout() may have given up on this job while + * hrtimer_cancel() above waited for it to finish; so->rx_lock + * (held by our caller isotp_rcv()) rules out a concurrent claim, + * so a plain recheck is enough here. + */ + if (so->tx.state != ISOTP_WAIT_FC && + so->tx.state != ISOTP_WAIT_FIRST_FC) + return 1; + if ((cf->len < ae + FC_CONTENT_SZ) || ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, ae + FC_CONTENT_SZ, so->opt.rxpad_content))) { @@ -422,7 +434,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) so->tx.bs = 0; so->tx.state = ISOTP_SENDING; /* send CF frame and enable echo timeout handling */ - hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); break; @@ -575,6 +587,14 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, hrtimer_cancel(&so->rxtimer); + /* isotp_rx_timer_handler() may have raced us for so->rx.state + * while hrtimer_cancel() above waited for it to finish, already + * reporting ETIMEDOUT and resetting the reception; don't process + * this CF into a reassembly that has already been given up on. + */ + if (so->rx.state != ISOTP_WAIT_DATA) + return 1; + /* CFs are never longer than the FF */ if (cf->len > so->rx.ll_dl) return 1; @@ -870,20 +890,36 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) struct canfd_frame *cf = (struct canfd_frame *)skb->data; /* only handle my own local echo CF/SF skb's (no FF!) */ - if (skb->sk != sk || so->cfecho != *(u32 *)cf->data) + if (skb->sk != sk) return; + /* unlike isotp_rcv_fc()/isotp_rcv_cf(), not already under so->rx_lock + * (no isotp_rcv() caller here), so take it ourselves + */ + spin_lock(&so->rx_lock); + + /* so->cfecho may since belong to a new transfer; recheck under lock */ + if (so->cfecho != *(u32 *)cf->data) + goto out_unlock; + /* cancel local echo timeout */ - hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->echotimer); /* local echo skb with consecutive frame has been consumed */ so->cfecho = 0; + /* claiming a transfer also takes so->rx_lock, so a plain recheck + * is enough: so->tx.state can't have flipped to ISOTP_SENDING for + * a new claim while we're still in here + */ + if (so->tx.state != ISOTP_SENDING) + goto out_unlock; + if (so->tx.idx >= so->tx.len) { /* we are done */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); - return; + goto out_unlock; } if (so->txfc.bs && so->tx.bs >= so->txfc.bs) { @@ -891,53 +927,83 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) so->tx.state = ISOTP_WAIT_FC; hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); - return; + goto out_unlock; } /* no gap between data frames needed => use burst mode */ if (!so->tx_gap) { /* enable echo timeout handling */ - hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); - return; + goto out_unlock; } /* start timer to send next consecutive frame with correct delay */ hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); + +out_unlock: + spin_unlock(&so->rx_lock); } -static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) +/* shared by so->txtimer's and so->echotimer's callbacks. Both timers get + * cancelled under so->rx_lock elsewhere, so this must stay lock-free to + * avoid deadlocking with that; uses so->tx_gen instead to avoid tainting + * a new transfer with an error from the one that just timed out. + */ +static enum hrtimer_restart isotp_tx_timeout(struct isotp_sock *so) { - struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, - txtimer); struct sock *sk = &so->sk; + u32 gen = READ_ONCE(so->tx_gen); + u32 old_state = READ_ONCE(so->tx.state); /* don't handle timeouts in IDLE or SHUTDOWN state */ - if (so->tx.state == ISOTP_IDLE || so->tx.state == ISOTP_SHUTDOWN) + if (old_state == ISOTP_IDLE || old_state == ISOTP_SHUTDOWN) + return HRTIMER_NORESTART; + + /* only claim the timeout if the state is still unchanged */ + if (cmpxchg(&so->tx.state, old_state, ISOTP_IDLE) != old_state) return HRTIMER_NORESTART; /* we did not get any flow control or echo frame in time */ - /* report 'communication error on send' */ - sk->sk_err = ECOMM; - if (!sock_flag(sk, SOCK_DEAD)) - sk_error_report(sk); + if (READ_ONCE(so->tx_gen) == gen) { + /* report 'communication error on send' */ + sk->sk_err = ECOMM; + if (!sock_flag(sk, SOCK_DEAD)) + sk_error_report(sk); + } - /* reset tx state */ - so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return HRTIMER_NORESTART; } +/* so->txtimer: fires when a Flow Control frame does not arrive in time */ +static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) +{ + struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, + txtimer); + + return isotp_tx_timeout(so); +} + +/* so->echotimer: fires when a sent CF/SF's local echo does not arrive */ +static enum hrtimer_restart isotp_echo_timer_handler(struct hrtimer *hrtimer) +{ + struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, + echotimer); + + return isotp_tx_timeout(so); +} + static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txfrtimer); /* start echo timeout handling and cover below protocol error */ - hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); /* cfecho should be consumed by isotp_rcv_echo() here */ @@ -958,13 +1024,24 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; s64 hrtimer_sec = ISOTP_ECHO_TIMEOUT; + struct hrtimer *tx_hrt = &so->echotimer; + u32 new_state = ISOTP_SENDING; int off; int err; if (!so->bound || so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; - while (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) { + /* claim the socket under so->rx_lock: this serializes the claim + * with the RX path and with sendmsg()'s own error paths below, so + * none of them can ever see a transfer mid-claim + */ + for (;;) { + spin_lock_bh(&so->rx_lock); + if (READ_ONCE(so->tx.state) == ISOTP_IDLE) + break; + spin_unlock_bh(&so->rx_lock); + /* we do not support multiple buffers - for now */ if (msg->msg_flags & MSG_DONTWAIT) return -EAGAIN; @@ -973,9 +1050,29 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) return -EADDRNOTAVAIL; /* wait for complete transmission of current pdu */ - err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + err = wait_event_interruptible(so->wait, + so->tx.state == ISOTP_IDLE); if (err) - goto err_event_drop; + return err; + } + + /* new transfer: bump so->tx_gen and drain the old one's timers, + * still under the so->rx_lock we just claimed the socket with + */ + WRITE_ONCE(so->tx.state, ISOTP_SENDING); + WRITE_ONCE(so->tx_gen, READ_ONCE(so->tx_gen) + 1); + hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->echotimer); + hrtimer_cancel(&so->txfrtimer); + so->cfecho = 0; + spin_unlock_bh(&so->rx_lock); + + /* so->bound is only checked once above - a wakeup may have + * unbound/rebound the socket meanwhile, so re-validate it + */ + if (!so->bound) { + err = -EADDRNOTAVAIL; + goto err_out_drop; } /* PDU size > default => try max_pdu_size */ @@ -1086,18 +1183,33 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) so->cfecho = *(u32 *)cf->data; } else { /* standard flow control check */ - so->tx.state = ISOTP_WAIT_FIRST_FC; + new_state = ISOTP_WAIT_FIRST_FC; /* start timeout for FC */ hrtimer_sec = ISOTP_FC_TIMEOUT; + tx_hrt = &so->txtimer; /* no CF echo tag for isotp_rcv_echo() (FF-mode) */ so->cfecho = 0; } } - hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), + spin_lock_bh(&so->rx_lock); + if (so->tx.state == ISOTP_SHUTDOWN) { + /* isotp_release() has since taken over and already drained + * our timers - don't send into a socket that's going away + */ + spin_unlock_bh(&so->rx_lock); + kfree_skb(skb); + dev_put(dev); + wake_up_interruptible(&so->wait); + return -EADDRNOTAVAIL; + } + /* WAIT_FIRST_FC for standard FF, else stays ISOTP_SENDING */ + so->tx.state = new_state; + hrtimer_start(tx_hrt, ktime_set(hrtimer_sec, 0), HRTIMER_MODE_REL_SOFT); + spin_unlock_bh(&so->rx_lock); /* send the first or only CAN frame */ cf->flags = so->ll.tx_flags; @@ -1110,13 +1222,10 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); + spin_lock_bh(&so->rx_lock); /* no transmission -> no timeout monitoring */ - hrtimer_cancel(&so->txtimer); - - /* reset consecutive frame echo tag */ - so->cfecho = 0; - - goto err_out_drop; + hrtimer_cancel(tx_hrt); + goto err_out_drop_locked; } if (wait_tx_done) { @@ -1132,14 +1241,21 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) return size; +err_out_drop: + /* claimed but nothing sent yet - no timer to cancel */ + spin_lock_bh(&so->rx_lock); + goto err_out_drop_locked; err_event_drop: - /* got signal: force tx state machine to be idle */ - so->tx.state = ISOTP_IDLE; + /* interrupted waiting on our own transfer - drain its timers */ + spin_lock_bh(&so->rx_lock); hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); -err_out_drop: - /* drop this PDU and unlock a potential wait queue */ + hrtimer_cancel(&so->echotimer); +err_out_drop_locked: + /* release the claim; so->rx_lock still held from above */ + so->cfecho = 0; so->tx.state = ISOTP_IDLE; + spin_unlock_bh(&so->rx_lock); wake_up_interruptible(&so->wait); return err; @@ -1201,13 +1317,20 @@ static int isotp_release(struct socket *sock) so = isotp_sk(sk); net = sock_net(sk); - /* wait for complete transmission of current pdu */ - while (wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0 && - cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SHUTDOWN) != ISOTP_IDLE) + /* best-effort: wait for a running pdu to finish, but don't block on + * it forever - give up after the first signal + */ + while (so->tx.state != ISOTP_IDLE && + wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0) ; - /* force state machines to be idle also when a signal occurred */ + /* claim the socket under so->rx_lock like sendmsg() does, so its + * claim can't race the forced ISOTP_SHUTDOWN below; force it + * unconditionally, even when a signal cut the wait above short + */ + spin_lock_bh(&so->rx_lock); so->tx.state = ISOTP_SHUTDOWN; + spin_unlock_bh(&so->rx_lock); so->rx.state = ISOTP_IDLE; spin_lock(&isotp_notifier_lock); @@ -1219,36 +1342,43 @@ static int isotp_release(struct socket *sock) list_del(&so->notifier); spin_unlock(&isotp_notifier_lock); + rtnl_lock(); lock_sock(sk); - /* remove current filters & unregister */ - if (so->bound) { - if (so->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(net, so->ifindex); - if (dev) { - if (isotp_register_rxid(so)) - can_rx_unregister(net, dev, so->rxid, - SINGLE_MASK(so->rxid), - isotp_rcv, sk); + /* remove current filters & unregister + * tracked reference so->dev is taken at bind() time with rtnl_lock + */ + if (so->bound && so->dev) { + if (isotp_register_rxid(so)) + can_rx_unregister(net, so->dev, so->rxid, + SINGLE_MASK(so->rxid), + isotp_rcv, sk); - can_rx_unregister(net, dev, so->txid, - SINGLE_MASK(so->txid), - isotp_rcv_echo, sk); - dev_put(dev); - synchronize_rcu(); - } - } + can_rx_unregister(net, so->dev, so->txid, + SINGLE_MASK(so->txid), + isotp_rcv_echo, sk); + netdev_put(so->dev, &so->dev_tracker); } + so->ifindex = 0; + so->bound = 0; + so->dev = NULL; + + rtnl_unlock(); + + /* Always wait for a grace period before touching the timers below. + * A concurrent NETDEV_UNREGISTER may have already unregistered our + * filters and cleared so->bound in isotp_notify() without waiting + * for in-flight isotp_rcv() callers to finish, so this call must not + * be skipped just because so->bound is already 0 here. + */ + synchronize_rcu(); + hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->echotimer); hrtimer_cancel(&so->rxtimer); - so->ifindex = 0; - so->bound = 0; - sock_orphan(sk); sock->sk = NULL; @@ -1303,6 +1433,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l if (!addr->can_ifindex) return -ENODEV; + rtnl_lock(); lock_sock(sk); if (so->bound) { @@ -1310,6 +1441,17 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l goto out; } + /* A transmission or reception that outlived a previous binding + * (unbound by NETDEV_UNREGISTER) may still be draining; the FC/echo + * and RX watchdog timers bound how long this takes. Checked together + * with so->bound in the same lock_sock() section above, so there is + * no window in which a concurrent isotp_notify() could be missed. + */ + if (so->tx.state != ISOTP_IDLE || so->rx.state != ISOTP_IDLE) { + err = -EAGAIN; + goto out; + } + /* ensure different CAN IDs when the rx_id is to be registered */ if (isotp_register_rxid(so) && rx_id == tx_id) { err = -EADDRNOTAVAIL; @@ -1322,14 +1464,12 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l goto out; } if (dev->type != ARPHRD_CAN) { - dev_put(dev); err = -ENODEV; - goto out; + goto out_put_dev; } if (READ_ONCE(dev->mtu) < so->ll.mtu) { - dev_put(dev); err = -EINVAL; - goto out; + goto out_put_dev; } if (!(dev->flags & IFF_UP)) notify_enetdown = 1; @@ -1347,16 +1487,25 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), isotp_rcv_echo, sk, "isotpe", sk); - dev_put(dev); - /* switch to new settings */ so->ifindex = ifindex; so->rxid = rx_id; so->txid = tx_id; so->bound = 1; + /* bind() ok -> hold a reference for so->dev so that isotp_release() + * can safely reach the device later, even if a concurrent + * NETDEV_UNREGISTER has already unlisted it by ifindex. + */ + so->dev = dev; + netdev_hold(so->dev, &so->dev_tracker, GFP_KERNEL); + +out_put_dev: + /* remove potential reference from dev_get_by_index() */ + dev_put(dev); out: release_sock(sk); + rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; @@ -1559,7 +1708,7 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, if (!net_eq(dev_net(dev), sock_net(sk))) return; - if (so->ifindex != dev->ifindex) + if (so->dev != dev) return; switch (msg) { @@ -1575,10 +1724,12 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, can_rx_unregister(dev_net(dev), dev, so->txid, SINGLE_MASK(so->txid), isotp_rcv_echo, sk); + netdev_put(so->dev, &so->dev_tracker); } so->ifindex = 0; so->bound = 0; + so->dev = NULL; release_sock(sk); sk->sk_err = ENODEV; @@ -1638,6 +1789,7 @@ static int isotp_init(struct sock *sk) so->ifindex = 0; so->bound = 0; + so->dev = NULL; so->opt.flags = CAN_ISOTP_DEFAULT_FLAGS; so->opt.ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS; @@ -1664,10 +1816,14 @@ static int isotp_init(struct sock *sk) so->rx.buflen = ARRAY_SIZE(so->rx.sbuf); so->tx.buflen = ARRAY_SIZE(so->tx.sbuf); - hrtimer_setup(&so->rxtimer, isotp_rx_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); - hrtimer_setup(&so->txtimer, isotp_tx_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); - hrtimer_setup(&so->txfrtimer, isotp_txfr_timer_handler, CLOCK_MONOTONIC, - HRTIMER_MODE_REL_SOFT); + hrtimer_setup(&so->rxtimer, isotp_rx_timer_handler, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + hrtimer_setup(&so->txtimer, isotp_tx_timer_handler, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + hrtimer_setup(&so->echotimer, isotp_echo_timer_handler, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + hrtimer_setup(&so->txfrtimer, isotp_txfr_timer_handler, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); init_waitqueue_head(&so->wait); spin_lock_init(&so->rx_lock); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index df93d57907da..8a31cb23bc76 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -351,6 +351,18 @@ static void j1939_session_skb_drop_old(struct j1939_session *session) } } +static bool j1939_address_is_local(struct j1939_priv *priv, u8 addr) +{ + bool local = false; + + read_lock_bh(&priv->lock); + if (j1939_address_is_unicast(addr) && priv->ents[addr].nusers) + local = true; + read_unlock_bh(&priv->lock); + + return local; +} + void j1939_session_skb_queue(struct j1939_session *session, struct sk_buff *skb) { @@ -359,8 +371,7 @@ void j1939_session_skb_queue(struct j1939_session *session, j1939_ac_fixup(priv, skb); - if (j1939_address_is_unicast(skcb->addr.da) && - priv->ents[skcb->addr.da].nusers) + if (j1939_address_is_local(priv, skcb->addr.da)) skcb->flags |= J1939_ECU_LOCAL_DST; skcb->flags |= J1939_ECU_LOCAL_SRC; @@ -2038,8 +2049,7 @@ struct j1939_session *j1939_tp_send(struct j1939_priv *priv, return ERR_PTR(ret); /* fix DST flags, it may be used there soon */ - if (j1939_address_is_unicast(skcb->addr.da) && - priv->ents[skcb->addr.da].nusers) + if (j1939_address_is_local(priv, skcb->addr.da)) skcb->flags |= J1939_ECU_LOCAL_DST; /* src is always local, I'm sending ... */ diff --git a/net/can/raw.c b/net/can/raw.c index a26942e78e68..82d9c0499c95 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -562,8 +562,8 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr, return RAW_MIN_NAMELEN; } -static int raw_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int optlen) +static int raw_setsockopt_locked(struct socket *sock, int optname, + sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); @@ -575,9 +575,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, int flag; int err = 0; - if (level != SOL_CAN_RAW) - return -EINVAL; - switch (optname) { case CAN_RAW_FILTER: if (optlen % sizeof(struct can_filter) != 0) @@ -598,17 +595,11 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; } - rtnl_lock(); - lock_sock(sk); - dev = ro->dev; - if (ro->bound && dev) { - if (dev->reg_state != NETREG_REGISTERED) { - if (count > 1) - kfree(filter); - err = -ENODEV; - goto out_fil; - } + if (ro->bound && dev && dev->reg_state != NETREG_REGISTERED) { + if (count > 1) + kfree(filter); + return -ENODEV; } if (ro->bound) { @@ -622,7 +613,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (err) { if (count > 1) kfree(filter); - goto out_fil; + return err; } /* remove old filter registrations */ @@ -642,11 +633,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, } ro->filter = filter; ro->count = count; - - out_fil: - release_sock(sk); - rtnl_unlock(); - break; case CAN_RAW_ERR_FILTER: @@ -658,16 +644,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, err_mask &= CAN_ERR_MASK; - rtnl_lock(); - lock_sock(sk); - dev = ro->dev; - if (ro->bound && dev) { - if (dev->reg_state != NETREG_REGISTERED) { - err = -ENODEV; - goto out_err; - } - } + if (ro->bound && dev && dev->reg_state != NETREG_REGISTERED) + return -ENODEV; /* remove current error mask */ if (ro->bound) { @@ -676,7 +655,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, err_mask); if (err) - goto out_err; + return err; /* remove old err_mask registration */ raw_disable_errfilter(sock_net(sk), dev, sk, @@ -685,11 +664,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, /* link new err_mask to the socket */ ro->err_mask = err_mask; - - out_err: - release_sock(sk); - rtnl_unlock(); - break; case CAN_RAW_LOOPBACK: @@ -769,6 +743,26 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return err; } +static int raw_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + int err; + + if (level != SOL_CAN_RAW) + return -EINVAL; + + rtnl_lock(); + lock_sock(sk); + + err = raw_setsockopt_locked(sock, optname, optval, optlen); + + release_sock(sk); + rtnl_unlock(); + + return err; +} + static int raw_getsockopt(struct socket *sock, int level, int optname, sockopt_t *opt) { diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index ecd659f79fd4..1d295a8769fa 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -158,8 +158,6 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) struct bpf_local_storage_elem *selem; int ret = 0; - RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); - rcu_read_lock_dont_migrate(); sk_storage = rcu_dereference(sk->sk_bpf_storage); diff --git a/net/core/dev.c b/net/core/dev.c index 4b3d5cfdf6e0..5933c5dab09e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4018,6 +4018,9 @@ out_free: return NULL; } +/* Returns the skb on success, NULL if dropped, or ERR_PTR(-EINPROGRESS) + * if stolen by async xfrm crypto (delivered via xfrm_dev_resume()). + */ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again) { netdev_features_t features; @@ -4089,7 +4092,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d skb->prev = skb; skb = validate_xmit_skb(skb, dev, again); - if (!skb) + if (IS_ERR_OR_NULL(skb)) continue; if (!head) @@ -4860,8 +4863,11 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) goto recursion_alert; skb = validate_xmit_skb(skb, dev, &again); - if (!skb) + if (IS_ERR_OR_NULL(skb)) { + if (PTR_ERR(skb) == -EINPROGRESS) + rc = NET_XMIT_SUCCESS; goto out; + } HARD_TX_LOCK(dev, txq, cpu); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 2bf3cab5e557..abaf108ac4db 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -530,10 +530,10 @@ static void net_dm_packet_trace_kfree_skb_hit(void *ignore, return; unlock_free: - spin_unlock_irqrestore(&data->drop_queue.lock, flags); u64_stats_update_begin(&data->stats.syncp); u64_stats_inc(&data->stats.dropped); u64_stats_update_end(&data->stats.syncp); + spin_unlock_irqrestore(&data->drop_queue.lock, flags); consume_skb(nskb); } @@ -566,13 +566,13 @@ static size_t net_dm_packet_report_size(size_t payload_len) /* NET_DM_ATTR_ORIGIN */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_PC */ - nla_total_size(sizeof(u64)) + + nla_total_size_64bit(sizeof(u64)) + /* NET_DM_ATTR_SYMBOL */ nla_total_size(NET_DM_MAX_SYMBOL_LEN + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + /* NET_DM_ATTR_TIMESTAMP */ - nla_total_size(sizeof(u64)) + + nla_total_size_64bit(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ @@ -671,9 +671,7 @@ static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) goto nla_put_failure; - attr = skb_put(msg, nla_total_size(payload_len)); - attr->nla_type = NET_DM_ATTR_PAYLOAD; - attr->nla_len = nla_attr_size(payload_len); + attr = __nla_reserve(msg, NET_DM_ATTR_PAYLOAD, payload_len); if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) goto nla_put_failure; @@ -768,7 +766,7 @@ net_dm_hw_packet_report_size(size_t payload_len, /* NET_DM_ATTR_FLOW_ACTION_COOKIE */ net_dm_flow_action_cookie_size(hw_metadata) + /* NET_DM_ATTR_TIMESTAMP */ - nla_total_size(sizeof(u64)) + + nla_total_size_64bit(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ @@ -831,9 +829,7 @@ static int net_dm_hw_packet_report_fill(struct sk_buff *msg, if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) goto nla_put_failure; - attr = skb_put(msg, nla_total_size(payload_len)); - attr->nla_type = NET_DM_ATTR_PAYLOAD; - attr->nla_len = nla_attr_size(payload_len); + attr = __nla_reserve(msg, NET_DM_ATTR_PAYLOAD, payload_len); if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) goto nla_put_failure; @@ -1001,10 +997,10 @@ net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink, return; unlock_free: - spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); u64_stats_update_begin(&hw_data->stats.syncp); u64_stats_inc(&hw_data->stats.dropped); u64_stats_update_end(&hw_data->stats.syncp); + spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); net_dm_hw_metadata_free(n_hw_metadata); free: consume_skb(nskb); diff --git a/net/core/filter.c b/net/core/filter.c index b446aa8be5c3..11bb0d236822 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2552,11 +2552,13 @@ out_drop: BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { - struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); + struct bpf_redirect_info *ri; - if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) + if (unlikely(!bpf_net_ctx_get() || + (flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))) return TC_ACT_SHOT; + ri = bpf_net_ctx_get_ri(); ri->flags = flags; ri->tgt_index = ifindex; @@ -2573,11 +2575,12 @@ static const struct bpf_func_proto bpf_redirect_proto = { BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) { - struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); + struct bpf_redirect_info *ri; - if (unlikely(flags)) + if (unlikely(!bpf_net_ctx_get() || flags)) return TC_ACT_SHOT; + ri = bpf_net_ctx_get_ri(); ri->flags = BPF_F_PEER; ri->tgt_index = ifindex; @@ -2595,11 +2598,13 @@ static const struct bpf_func_proto bpf_redirect_peer_proto = { BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params, int, plen, u64, flags) { - struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); + struct bpf_redirect_info *ri; - if (unlikely((plen && plen < sizeof(*params)) || flags)) + if (unlikely((plen && plen < sizeof(*params)) || + !bpf_net_ctx_get() || flags)) return TC_ACT_SHOT; + ri = bpf_net_ctx_get_ri(); ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0); ri->tgt_index = ifindex; diff --git a/net/core/gro.c b/net/core/gro.c index 35f2f708f010..29b4d02bf519 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -229,7 +229,9 @@ done: int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) { - if (unlikely(p->len + skb->len >= 65536)) + /* make sure to check flush flag and to not merge */ + if (unlikely(p->len + skb->len >= 65536 || + NAPI_GRO_CB(skb)->flush)) return -E2BIG; if (!pskb_may_pull(skb, skb_gro_offset(skb))) { diff --git a/net/core/sock.c b/net/core/sock.c index 8a59bfaa8096..ffa73594c13c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2492,6 +2492,9 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority, sock_copy(newsk, sk); newsk->sk_prot_creator = prot; +#ifdef CONFIG_BPF_SYSCALL + RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); +#endif /* SANITY */ if (likely(newsk->sk_net_refcnt)) { @@ -2544,6 +2547,11 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority, cgroup_sk_clone(&newsk->sk_cgrp_data); + RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); + + if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) + net_enable_timestamp(); + rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) @@ -2566,8 +2574,6 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority, goto free; } - RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); - if (bpf_sk_storage_clone(sk, newsk)) goto free; @@ -2595,9 +2601,6 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority, if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); - - if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) - net_enable_timestamp(); out: return newsk; free: diff --git a/net/core/sock_map.c b/net/core/sock_map.c index c60ba6d292f9..9efbd8ca7db8 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -542,6 +542,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); + if (sk_is_udp(sk)) + return sk_hashed(sk); if (sk_is_stream_unix(sk)) return (1 << READ_ONCE(sk->sk_state)) & TCPF_ESTABLISHED; if (sk_is_vsock(sk) && diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index d9af9e65f72f..01c73b4b50dd 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -242,6 +242,8 @@ void hsr_del_port(struct hsr_port *port) netdev_rx_handler_unregister(port->dev); if (!port->hsr->fwd_offloaded) dev_set_promiscuity(port->dev, -1); + if (port->type == HSR_PT_SLAVE_A || port->type == HSR_PT_SLAVE_B) + vlan_vids_del_by_dev(port->dev, master->dev); netdev_upper_dev_unlink(port->dev, master->dev); if (hsr->prot_version == PRP_V1 && port->type == HSR_PT_SLAVE_B) { diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 1614593b6d72..7d25519a6cdd 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -63,12 +63,12 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int } /* Update addresses before rehashing */ - inet->inet_daddr = fl4->daddr; + WRITE_ONCE(inet->inet_daddr, fl4->daddr); inet->inet_dport = usin->sin_port; if (!inet->inet_saddr) inet->inet_saddr = fl4->saddr; if (!inet->inet_rcv_saddr) { - inet->inet_rcv_saddr = fl4->saddr; + WRITE_ONCE(inet->inet_rcv_saddr, fl4->saddr); if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e11dc86ceda0..6badad29593b 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1385,7 +1385,7 @@ succeeded: out_remove_new_fa: fib_remove_alias(t, tp, l, new_fa); out_free_new_fa: - kmem_cache_free(fn_alias_kmem, new_fa); + alias_free_mem_rcu(new_fa); out: fib_release_info(fi); err: diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 23e921d313b3..0caedfc7ca92 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -548,11 +548,23 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, if (IS_ERR(rt2)) err = PTR_ERR(rt2); } else { - struct flowi4 fl4_2 = {}; + struct flowi4 fl4_2 = fl4_dec; unsigned long orefdst; - fl4_2.daddr = fl4_dec.saddr; - rt2 = ip_route_output_key(net, &fl4_2); + swap(fl4_2.daddr, fl4_2.saddr); + switch (fl4_2.flowi4_proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_SCTP: + case IPPROTO_DCCP: + swap(fl4_2.fl4_sport, fl4_2.fl4_dport); + break; + } + + fl4_2.flowi4_oif = l3mdev_master_ifindex(route_lookup_dev); + fl4_2.flowi4_flags |= FLOWI_FLAG_ANYSRC; + + rt2 = __ip_route_output_key(net, &fl4_2); if (IS_ERR(rt2)) { err = PTR_ERR(rt2); goto relookup_failed; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 3efdfb4ffa21..0ba1e94e9012 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1018,6 +1018,8 @@ static void __gre_tunnel_init(struct net_device *dev) dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; + dev->lltx = true; + /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ @@ -1029,8 +1031,6 @@ static void __gre_tunnel_init(struct net_device *dev) dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; - - dev->lltx = true; } static int ipgre_tunnel_init(struct net_device *dev) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 6205bd57aa85..44fe75004cac 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1788,8 +1788,8 @@ static bool nh_res_bucket_migrate(struct nh_res_table *res_table, bool notify_nl, bool force) { struct nh_res_bucket *bucket = &res_table->nh_buckets[bucket_index]; + struct netlink_ext_ack extack = {}; struct nh_grp_entry *new_nhge; - struct netlink_ext_ack extack; int err; new_nhge = list_first_entry_or_null(&res_table->uw_nh_entries, diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index e9fbab6ad914..7f74d8b95a37 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -118,13 +118,21 @@ bool raw_v4_match(struct net *net, const struct sock *sk, unsigned short num, __be32 raddr, __be32 laddr, int dif, int sdif) { const struct inet_sock *inet = inet_sk(sk); + __be32 daddr, rcv_saddr; - if (net_eq(sock_net(sk), net) && inet->inet_num == num && - !(inet->inet_daddr && inet->inet_daddr != raddr) && - !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) && - raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) - return true; - return false; + if (!net_eq(sock_net(sk), net) || inet->inet_num != num) + return false; + + daddr = READ_ONCE(inet->inet_daddr); + if (daddr && daddr != raddr) + return false; + + rcv_saddr = READ_ONCE(inet->inet_rcv_saddr); + if (rcv_saddr && rcv_saddr != laddr) + return false; + + return raw_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), + dif, sdif); } EXPORT_SYMBOL_GPL(raw_v4_match); @@ -722,7 +730,8 @@ static int raw_bind(struct sock *sk, struct sockaddr_unsized *uaddr, chk_addr_ret)) goto out; - inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; + inet->inet_saddr = addr->sin_addr.s_addr; + WRITE_ONCE(inet->inet_rcv_saddr, addr->sin_addr.s_addr); if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ sk_dst_reset(sk); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index cc0bd73f36b6..8e905b50dead 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -334,6 +334,7 @@ unlock: static int tcp_bpf_ioctl(struct sock *sk, int cmd, int *karg) { + struct sk_psock *psock; bool slow; if (cmd != SIOCINQ) @@ -344,7 +345,21 @@ static int tcp_bpf_ioctl(struct sock *sk, int cmd, int *karg) return -EINVAL; slow = lock_sock_fast(sk); - *karg = sk_psock_msg_inq(sk); + psock = sk_psock_get(sk); + if (unlikely(!psock)) { + unlock_sock_fast(sk, slow); + return tcp_ioctl(sk, cmd, karg); + } + *karg = sk_psock_get_msg_len_nolock(psock); + /* Without a verdict program, ingress data is never diverted to + * ingress_msg: it stays in sk_receive_queue and is read through + * the fallback to tcp_recvmsg(), so account for it like + * tcp_ioctl() does. + */ + if (!READ_ONCE(psock->progs.stream_verdict) && + !READ_ONCE(psock->progs.skb_verdict)) + *karg += tcp_inq(sk); + sk_psock_put(sk, psock); unlock_sock_fast(sk, slow); return 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 61045a8886e4..daff93d51342 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4038,24 +4038,17 @@ static void tcp_send_ack_reflect_ect(struct sock *sk, bool accecn_reflector) __tcp_send_ack(sk, tp->rcv_nxt, flags); } -/* RFC 5961 7 [ACK Throttling] */ -static void tcp_send_challenge_ack(struct sock *sk, bool accecn_reflector) +/* Consume one slot from the per-netns RFC 5961 challenge ACK quota. + * Returns true if a challenge ACK may be sent. + */ +static bool tcp_challenge_ack_allowed(struct net *net) { - struct tcp_sock *tp = tcp_sk(sk); - struct net *net = sock_net(sk); u32 count, now, ack_limit; - /* First check our per-socket dupack rate limit. */ - if (__tcp_oow_rate_limited(net, - LINUX_MIB_TCPACKSKIPPEDCHALLENGE, - &tp->last_oow_ack_time)) - return; - ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit); if (ack_limit == INT_MAX) - goto send_ack; + return true; - /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != READ_ONCE(net->ipv4.tcp_challenge_timestamp)) { u32 half = (ack_limit + 1) >> 1; @@ -4067,12 +4060,49 @@ static void tcp_send_challenge_ack(struct sock *sk, bool accecn_reflector) count = READ_ONCE(net->ipv4.tcp_challenge_count); if (count > 0) { WRITE_ONCE(net->ipv4.tcp_challenge_count, count - 1); -send_ack: + return true; + } + return false; +} + +/* RFC 5961 7 [ACK Throttling] */ +static void tcp_send_challenge_ack(struct sock *sk, bool accecn_reflector) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); + + /* First check our per-socket dupack rate limit. */ + if (__tcp_oow_rate_limited(net, + LINUX_MIB_TCPACKSKIPPEDCHALLENGE, + &tp->last_oow_ack_time)) + return; + + /* Then check the per-netns RFC 5961 rate limit. */ + if (tcp_challenge_ack_allowed(net)) { NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack_reflect_ect(sk, accecn_reflector); } } +/* Send a challenge ACK from a SYN-RECEIVED request socket. Uses + * __tcp_oow_rate_limited() directly so that an RST carrying payload + * cannot bypass the per-request rate limit. + */ +void tcp_reqsk_send_challenge_ack(struct sock *sk, struct sk_buff *skb, + struct request_sock *req) +{ + struct net *net = sock_net(sk); + + if (__tcp_oow_rate_limited(net, LINUX_MIB_TCPACKSKIPPEDCHALLENGE, + &tcp_rsk(req)->last_oow_ack_time)) + return; + + if (tcp_challenge_ack_allowed(net)) { + NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK); + req->rsk_ops->send_ack(sk, skb, req); + } +} + static void tcp_store_ts_recent(struct tcp_sock *tp) { tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 209ef7522508..b8887cdd66c5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -971,6 +971,9 @@ static void tcp_v4_send_ack(const struct sock *sk, key->rcv_next); arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key); rep.th.doff = arg.iov[0].iov_len / 4; + memset((u8 *)&rep.opt[offset] + tcp_ao_maclen(key->ao_key), + TCPOPT_NOP, tcp_ao_len_aligned(key->ao_key) - + tcp_ao_len(key->ao_key)); tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset], key->ao_key, key->traffic_key, @@ -2318,8 +2321,10 @@ do_time_wait: } drop_reason = psp_twsk_rx_policy_check(inet_twsk(sk), skb); - if (drop_reason) - break; + if (drop_reason) { + inet_twsk_put(inet_twsk(sk)); + goto discard_it; + } } /* to ACK */ fallthrough; @@ -3141,8 +3146,11 @@ static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) bpf_iter_tcp_put_batch(iter); err = bpf_iter_tcp_realloc_batch(iter, expected * 3 / 2, GFP_USER); - if (err) + if (err) { + iter->cur_sk = 0; + iter->end_sk = 0; return ERR_PTR(err); + } sk = bpf_iter_tcp_resume(seq); if (!sk) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ddc4b17a826b..6ab3e3a0b431 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -833,7 +833,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * elsewhere and is checked directly against the child socket rather * than req because user data may have been sent out. */ - if ((flg & TCP_FLAG_ACK) && !fastopen && + if ((flg & TCP_FLAG_ACK) && !(flg & TCP_FLAG_RST) && !fastopen && (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1)) return sk; @@ -872,6 +872,16 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, flg &= ~TCP_FLAG_SYN; } + /* RFC 5961 section 3.2, as clarified by RFC 9293 section + * 3.10.7.4, requires a challenge ACK for a non-exact + * in-window RST in SYN-RECEIVED. + */ + if ((flg & TCP_FLAG_RST) && + TCP_SKB_CB(skb)->seq != tcp_rsk(req)->rcv_nxt) { + tcp_reqsk_send_challenge_ack(sk, skb, req); + return NULL; + } + /* RFC793: "second check the RST bit" and * "fourth, check the SYN bit" */ diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c index e71571455c8a..b78179bfc4c7 100644 --- a/net/ipv6/ila/ila_common.c +++ b/net/ipv6/ila/ila_common.c @@ -85,6 +85,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb, struct tcphdr *th = (struct tcphdr *) (skb_network_header(skb) + nhoff); + ip6h = ipv6_hdr(skb); diff = get_csum_diff(ip6h, p); inet_proto_csum_replace_by_diff(&th->check, skb, diff, true, true); @@ -96,6 +97,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb, (skb_network_header(skb) + nhoff); if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { + ip6h = ipv6_hdr(skb); diff = get_csum_diff(ip6h, p); inet_proto_csum_replace_by_diff(&uh->check, skb, diff, true, true); @@ -110,6 +112,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb, struct icmp6hdr *ih = (struct icmp6hdr *) (skb_network_header(skb) + nhoff); + ip6h = ipv6_hdr(skb); diff = get_csum_diff(ip6h, p); inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb, diff, true, true); @@ -127,6 +130,15 @@ void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p, switch (p->csum_mode) { case ILA_CSUM_ADJUST_TRANSPORT: ila_csum_adjust_transport(skb, p); + /* + * ila_csum_adjust_transport() calls pskb_may_pull(), which can + * reallocate the skb head and leave ip6h (and the iaddr derived + * from it) dangling; reload both before the write below. The + * other csum modes do not pull, so their cached pointers stay + * valid. + */ + ip6h = ipv6_hdr(skb); + iaddr = ila_a2i(&ip6h->daddr); break; case ILA_CSUM_NEUTRAL_MAP: if (sir2ila) { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 7c09a269b352..b843116e9b70 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1455,6 +1455,8 @@ static void ip6gre_tnl_init_features(struct net_device *dev) dev->features |= GRE6_FEATURES; dev->hw_features |= GRE6_FEATURES; + dev->lltx = true; + /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ @@ -1466,8 +1468,6 @@ static void ip6gre_tnl_init_features(struct net_device *dev) dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; - - dev->lltx = true; } static int ip6gre_tunnel_init_common(struct net_device *dev) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 6d80f85e55fa..a7025ec87035 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -120,7 +120,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, ktime_t tstamp = skb->tstamp; struct ip6_frag_state state; u8 *prevhdr, nexthdr = 0; - unsigned int mtu, hlen; + unsigned int mtu, hlen, nexthdr_offset; int hroom, err = 0; __be32 frag_id; @@ -129,6 +129,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, goto blackhole; hlen = err; nexthdr = *prevhdr; + nexthdr_offset = prevhdr - skb_network_header(skb); mtu = skb->dev->mtu; if (frag_max_size > mtu || @@ -147,6 +148,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, (err = skb_checksum_help(skb))) goto blackhole; + prevhdr = skb_network_header(skb) + nexthdr_offset; hroom = LL_RESERVED_SPACE(skb->dev); if (skb_has_frag_list(skb)) { unsigned int first_len = skb_pagelen(skb); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 3cc58698cbbd..b88d364e78aa 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -349,7 +349,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; if (!raw_v6_match(net, sk, nexthdr, &ip6h->saddr, &ip6h->daddr, - inet6_iif(skb), inet6_iif(skb))) + inet6_iif(skb), inet6_sdif(skb))) continue; rawv6_err(sk, skb, type, code, inner_offset, info); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a1301334da48..fc42d67e5822 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4022,7 +4022,7 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) struct fib6_node *fn; /* prefer to send a single notification with all hops */ - skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); + skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC); if (skb) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; @@ -4078,7 +4078,7 @@ out_put: if (skb) { rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, - info->nlh, gfp_any()); + info->nlh, GFP_ATOMIC); } return err; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ebe161d72fbd..9e9155b1b3aa 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -923,6 +923,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 (tcp_ao_len(key->ao_key) << 16) | (key->ao_key->sndid << 8) | (key->rcv_next)); + memset((u8 *)topt + tcp_ao_maclen(key->ao_key), TCPOPT_NOP, + tcp_ao_len_aligned(key->ao_key) - tcp_ao_len(key->ao_key)); tcp_ao_hash_hdr(AF_INET6, (char *)topt, key->ao_key, key->traffic_key, @@ -1977,8 +1979,10 @@ do_time_wait: } drop_reason = psp_twsk_rx_policy_check(inet_twsk(sk), skb); - if (drop_reason) - break; + if (drop_reason) { + inet_twsk_put(inet_twsk(sk)); + goto discard_it; + } } /* to ACK */ fallthrough; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 125ea9a5b8a0..3b749475f6ed 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -88,6 +88,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt6.rt6i_idev = in6_dev_get(dev); if (!xdst->u.rt6.rt6i_idev) { netdev_put(dev, &xdst->u.dst.dev_tracker); + xdst->u.dst.dev = NULL; return -ENODEV; } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index fed240b453bd..ea047bab65e7 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -337,6 +337,7 @@ static void iucv_sever_path(struct sock *sk, int with_user_data) unsigned char user_data[16]; struct iucv_sock *iucv = iucv_sk(sk); struct iucv_path *path = iucv->path; + struct sock_msg_q *p, *n; /* Whoever resets the path pointer, must sever and free it. */ if (xchg(&iucv->path, NULL)) { @@ -348,6 +349,19 @@ static void iucv_sever_path(struct sock *sk, int with_user_data) } else pr_iucv->path_sever(path, NULL); iucv_path_free(path); + + /* + * Message notifications queued on message_q still reference + * the now freed path; drop them, otherwise a later recvmsg() + * would pass the freed iucv_path to message_receive() via + * iucv_process_message_q(). + */ + spin_lock_bh(&iucv->message_q.lock); + list_for_each_entry_safe(p, n, &iucv->message_q.list, list) { + list_del(&p->list); + kfree(p); + } + spin_unlock_bh(&iucv->message_q.lock); } } @@ -1872,7 +1886,8 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb) afiucv_swap_src_dest(skb); trans_hdr->flags = AF_IUCV_FLAG_SYN | AF_IUCV_FLAG_FIN; err = dev_queue_xmit(skb); - iucv_sock_kill(nsk); + if (nsk) + iucv_sock_kill(nsk); bh_unlock_sock(sk); goto out; } @@ -2089,6 +2104,8 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, } } } + if (sk) + sock_hold(sk); read_unlock(&iucv_sk_list.lock); if (!iucv) sk = NULL; @@ -2138,6 +2155,8 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, kfree_skb(skb); } + if (sk) + sock_put(sk); return err; } diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index e8f427375c68..260460d50f54 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -767,7 +767,6 @@ static struct sock *llc_create_incoming_sock(struct sock *sk, newllc->dev = dev; dev_hold(dev); llc_sap_add_socket(llc->sap, newsk); - llc_sap_hold(llc->sap); out: return newsk; } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 3b58af59f7e4..43f142624d33 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1146,9 +1146,6 @@ static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata, fd->max_interval = params->max_interval; old = sdata_dereference(link->u.ap.fils_discovery, sdata); - if (old) - kfree_rcu(old, rcu_head); - if (params->tmpl && params->tmpl_len) { new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL); if (!new) @@ -1160,6 +1157,9 @@ static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata, RCU_INIT_POINTER(link->u.ap.fils_discovery, NULL); } + if (old) + kfree_rcu(old, rcu_head); + *changed |= BSS_CHANGED_FILS_DISCOVERY; return 0; } @@ -1179,8 +1179,6 @@ ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata, link_conf->unsol_bcast_probe_resp_interval = params->interval; old = sdata_dereference(link->u.ap.unsol_bcast_probe_resp, sdata); - if (old) - kfree_rcu(old, rcu_head); if (params->tmpl && params->tmpl_len) { new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL); @@ -1193,6 +1191,9 @@ ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata, RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL); } + if (old) + kfree_rcu(old, rcu_head); + *changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP; return 0; } @@ -2610,6 +2611,9 @@ static int sta_apply_parameters(struct ieee80211_local *local, memcpy(&sta->deflink.pub->supp_rates, &nmi_sta->deflink.pub->supp_rates, sizeof(sta->deflink.pub->supp_rates)); + + sta->deflink.pub->agg = nmi_sta->deflink.pub->agg; + __ieee80211_sta_recalc_aggregates(sta, 0); } /* set the STA state after all sta info from usermode has been set */ diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index d0fd6054f182..882f91abbb66 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -668,7 +668,9 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata) ifibss->state = IEEE80211_IBSS_MLME_SEARCH; - sta_info_flush(sdata, -1); + netif_carrier_off(sdata->dev); + if (!sta_info_flush(sdata, -1)) + synchronize_net(); spin_lock_bh(&ifibss->incomplete_lock); while (!list_empty(&ifibss->incomplete_stations)) { @@ -682,8 +684,6 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata) } spin_unlock_bh(&ifibss->incomplete_lock); - netif_carrier_off(sdata->dev); - sdata->vif.cfg.ibss_joined = false; sdata->vif.cfg.ibss_creator = false; sdata->vif.bss_conf.enable_beacon = false; @@ -710,7 +710,6 @@ static void ieee80211_csa_connection_drop_work(struct wiphy *wiphy, u.ibss.csa_connection_drop_work); ieee80211_ibss_disconnect(sdata); - synchronize_rcu(); skb_queue_purge(&sdata->skb_queue); /* trigger a scan to find another IBSS network to join */ @@ -1029,8 +1028,8 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata, u32 changed = IEEE80211_RC_SUPP_RATES_CHANGED; u8 rx_nss = sta->sta.deflink.rx_nss; - /* Force rx_nss recalculation */ - sta->sta.deflink.rx_nss = 0; + ieee80211_sta_init_nss_bw_capa(&sta->deflink, + &sdata->deflink.conf->chanreq.oper); rate_control_rate_init(&sta->deflink); if (sta->sta.deflink.rx_nss != rx_nss) changed |= IEEE80211_RC_NSS_CHANGED; @@ -1797,8 +1796,6 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) memset(&ifibss->ht_capa, 0, sizeof(ifibss->ht_capa)); memset(&ifibss->ht_capa_mask, 0, sizeof(ifibss->ht_capa_mask)); - synchronize_rcu(); - skb_queue_purge(&sdata->skb_queue); timer_delete_sync(&sdata->u.ibss.timer); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 086272c3ec08..43460a705a6b 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -588,6 +588,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do WARN_ON(!list_empty(&sdata->u.ap.vlans)); } else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { /* remove all packets in parent bc_buf pointing to this dev */ + __skb_queue_head_init(&freeq); ps = &sdata->bss->ps; spin_lock_irqsave(&ps->bc_buf.lock, flags); @@ -595,10 +596,15 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do if (skb->dev == sdata->dev) { __skb_unlink(skb, &ps->bc_buf); local->total_ps_buffered--; - ieee80211_free_txskb(&local->hw, skb); + __skb_queue_tail(&freeq, skb); } } spin_unlock_irqrestore(&ps->bc_buf.lock, flags); + + skb_queue_walk_safe(&freeq, skb, tmp) { + __skb_unlink(skb, &freeq); + ieee80211_free_txskb(&local->hw, skb); + } } if (going_down) diff --git a/net/mac80211/link.c b/net/mac80211/link.c index d0535268962c..dc68144dc363 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -399,6 +399,10 @@ static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata, memcpy(sdata->link, old_data, sizeof(old_data)); memcpy(sdata->vif.link_conf, old, sizeof(old)); ieee80211_set_vif_links_bitmaps(sdata, old_links, dormant_links); + for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { + ieee80211_link_debugfs_remove(&links[link_id]->data); + ieee80211_link_stop(&links[link_id]->data); + } /* and free (only) the newly allocated links */ memset(to_free, 0, sizeof(links)); goto free; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 90d295cc364f..eb1eaaf34612 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1602,7 +1602,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) sband = kmemdup(sband, sizeof(*sband), GFP_KERNEL); if (!sband) { result = -ENOMEM; - goto fail_rate; + goto fail_band; } wiphy_dbg(hw->wiphy, "copying sband (band %d) due to VHT EXT NSS BW flag\n", @@ -1678,6 +1678,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) #endif wiphy_unregister(local->hw.wiphy); fail_wiphy_register: + fail_band: rtnl_lock(); rate_control_deinitialize(local); ieee80211_remove_interfaces(local); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 9e92337bb6f9..fa773f3b0541 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5641,13 +5641,15 @@ static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - u16 reason_code = le16_to_cpu(mgmt->u.deauth.reason_code); + u16 reason_code; lockdep_assert_wiphy(sdata->local->hw.wiphy); - if (len < 24 + 2) + if (len < offsetofend(struct ieee80211_mgmt, u.deauth.reason_code)) return; + reason_code = le16_to_cpu(mgmt->u.deauth.reason_code); + if (!ether_addr_equal(mgmt->bssid, mgmt->sa)) { ieee80211_tdls_handle_disconnect(sdata, mgmt->sa, reason_code); return; @@ -7138,7 +7140,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data; - u16 capab_info, status_code, aid; + u16 capab_info, status_code, aid = 0; struct ieee80211_elems_parse_params parse_params = { .bss = NULL, .link_id = -1, @@ -7217,8 +7219,10 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, if (elems->aid_resp) aid = le16_to_cpu(elems->aid_resp->aid); - else + else if (!assoc_data->s1g) aid = le16_to_cpu(mgmt->u.assoc_resp.aid); + else if (status_code == WLAN_STATUS_SUCCESS) + goto abandon_assoc; /* * The 5 MSB of the AID field are reserved for a non-S1G STA. For diff --git a/net/mac80211/nan.c b/net/mac80211/nan.c index 1800bb96dd29..19e08661be43 100644 --- a/net/mac80211/nan.c +++ b/net/mac80211/nan.c @@ -253,9 +253,12 @@ int ieee80211_nan_set_local_sched(struct ieee80211_sub_if_data *sdata, { struct ieee80211_nan_channel *sched_idx_to_chan[IEEE80211_NAN_MAX_CHANNELS] = {}; struct ieee80211_nan_sched_cfg *sched_cfg = &sdata->vif.cfg.nan_sched; - struct ieee80211_nan_sched_cfg backup_sched; + struct ieee80211_nan_sched_cfg *backup_sched __free(kfree) = kmalloc_obj(*backup_sched); int ret; + if (!backup_sched) + return -ENOMEM; + if (sched->n_channels > IEEE80211_NAN_MAX_CHANNELS) return -EOPNOTSUPP; @@ -275,13 +278,13 @@ int ieee80211_nan_set_local_sched(struct ieee80211_sub_if_data *sdata, bitmap_zero(sdata->u.nan.removed_channels, IEEE80211_NAN_MAX_CHANNELS); - memcpy(backup_sched.schedule, sched_cfg->schedule, - sizeof(backup_sched.schedule)); - memcpy(backup_sched.channels, sched_cfg->channels, - sizeof(backup_sched.channels)); - memcpy(backup_sched.avail_blob, sched_cfg->avail_blob, - sizeof(backup_sched.avail_blob)); - backup_sched.avail_blob_len = sched_cfg->avail_blob_len; + memcpy(backup_sched->schedule, sched_cfg->schedule, + sizeof(backup_sched->schedule)); + memcpy(backup_sched->channels, sched_cfg->channels, + sizeof(backup_sched->channels)); + memcpy(backup_sched->avail_blob, sched_cfg->avail_blob, + sizeof(backup_sched->avail_blob)); + backup_sched->avail_blob_len = sched_cfg->avail_blob_len; memcpy(sched_cfg->avail_blob, sched->nan_avail_blob, sched->nan_avail_blob_len); @@ -380,17 +383,17 @@ err: if (!chan_def->chan) continue; - if (!cfg80211_chandef_identical(&backup_sched.channels[i].chanreq.oper, + if (!cfg80211_chandef_identical(&backup_sched->channels[i].chanreq.oper, chan_def)) ieee80211_nan_remove_channel(sdata, &sched_cfg->channels[i]); } /* Re-add all backed up channels */ - for (int i = 0; i < ARRAY_SIZE(backup_sched.channels); i++) { + for (int i = 0; i < ARRAY_SIZE(backup_sched->channels); i++) { struct ieee80211_nan_channel *chan = &sched_cfg->channels[i]; - *chan = backup_sched.channels[i]; + *chan = backup_sched->channels[i]; /* * For deferred update, no channels were removed and the channel @@ -421,11 +424,11 @@ err: } } - memcpy(sched_cfg->schedule, backup_sched.schedule, - sizeof(backup_sched.schedule)); - memcpy(sched_cfg->avail_blob, backup_sched.avail_blob, - sizeof(backup_sched.avail_blob)); - sched_cfg->avail_blob_len = backup_sched.avail_blob_len; + memcpy(sched_cfg->schedule, backup_sched->schedule, + sizeof(backup_sched->schedule)); + memcpy(sched_cfg->avail_blob, backup_sched->avail_blob, + sizeof(backup_sched->avail_blob)); + sched_cfg->avail_blob_len = backup_sched->avail_blob_len; sched_cfg->deferred = false; bitmap_zero(sdata->u.nan.removed_channels, IEEE80211_NAN_MAX_CHANNELS); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fb9a3574afe9..5e26be8e27d8 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1526,6 +1526,9 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx) if (status->flag & RX_FLAG_DUP_VALIDATED) return RX_CONTINUE; + if (ieee80211_is_ext(hdr->frame_control)) + return RX_CONTINUE; + /* * Drop duplicate 802.11 retransmissions * (IEEE 802.11-2012: 9.3.2.10 "Duplicate detection and recovery") @@ -1714,6 +1717,8 @@ static void sta_ps_start(struct sta_info *sta) else clear_bit(tid, &sta->txq_buffered_tids); } + + sta_info_recalc_tim(sta); } static void sta_ps_end(struct sta_info *sta) @@ -4510,12 +4515,16 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); u8 *bssid = ieee80211_get_bssid(hdr, skb->len, sdata->vif.type); - bool multicast = is_multicast_ether_addr(hdr->addr1) || - ieee80211_is_s1g_beacon(hdr->frame_control); + bool multicast; static const u8 nan_network_id[ETH_ALEN] __aligned(2) = { 0x51, 0x6F, 0x9A, 0x01, 0x00, 0x00 }; + if (ieee80211_is_s1g_beacon(hdr->frame_control)) + return sdata->vif.type == NL80211_IFTYPE_STATION && bssid; + + multicast = is_multicast_ether_addr(hdr->addr1); + switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: if (!bssid && !sdata->u.mgd.use_4addr) @@ -5212,6 +5221,11 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, hdr = (struct ieee80211_hdr *)rx->skb->data; } + if (ieee80211_is_s1g_beacon(hdr->frame_control)) { + ieee80211_invoke_rx_handlers(rx); + return true; + } + /* Store a copy of the pre-translated link addresses for SW crypto */ if (unlikely(is_unicast_ether_addr(hdr->addr1) && !ieee80211_is_data(hdr->frame_control))) @@ -5301,6 +5315,13 @@ static bool ieee80211_rx_for_interface(struct ieee80211_rx_data *rx, struct sta_info *sta; int link_id = -1; + if (ieee80211_is_s1g_beacon(hdr->frame_control)) { + if (!ieee80211_rx_data_set_sta(rx, NULL, -1)) + return false; + + return ieee80211_prepare_and_rx_handle(rx, skb, consume); + } + /* * Look up link station first, in case there's a * chance that they might have a link address that @@ -5376,6 +5397,17 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, err = -ENOBUFS; else err = skb_linearize(skb); + } else if (ieee80211_is_s1g_beacon(fc)) { + size_t s1g_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_beacon.variable) + + ieee80211_s1g_optional_len(fc); + + if (skb->len < s1g_hdr_len) + err = -ENOBUFS; + else + err = skb_linearize(skb); + } else if (ieee80211_is_ext(fc)) { + err = -EINVAL; } else { err = !pskb_may_pull(skb, ieee80211_hdrlen(fc)); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 02b587ff8504..22eba0e6e54c 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -355,6 +355,15 @@ static void sta_info_free_link(struct link_sta_info *link_sta) free_percpu(link_sta->pcpu_rx_stats); } +static void sta_link_free_rcu(struct rcu_head *head) +{ + struct sta_link_alloc *alloc = + container_of(head, struct sta_link_alloc, rcu_head); + + sta_info_free_link(&alloc->info); + kfree(alloc); +} + static void sta_accumulate_removed_link_stats(struct sta_info *sta, int link_id) { struct link_sta_info *link_sta = wiphy_dereference(sta->local->hw.wiphy, @@ -439,10 +448,8 @@ static void sta_remove_link(struct sta_info *sta, unsigned int link_id, RCU_INIT_POINTER(sta->link[link_id], NULL); RCU_INIT_POINTER(sta->sta.link[link_id], NULL); - if (alloc) { - sta_info_free_link(&alloc->info); - kfree_rcu(alloc, rcu_head); - } + if (alloc) + call_rcu(&alloc->rcu_head, sta_link_free_rcu); ieee80211_sta_recalc_aggregates(&sta->sta); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index c13b209fad47..91b14112e24f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2607,6 +2607,18 @@ static u16 ieee80211_store_ack_skb(struct ieee80211_local *local, return info_id; } +static void ieee80211_remove_ack_skb(struct ieee80211_local *local, u16 info_id) +{ + struct sk_buff *ack_skb; + unsigned long flags; + + spin_lock_irqsave(&local->ack_status_lock, flags); + ack_skb = idr_remove(&local->ack_status_frames, info_id); + spin_unlock_irqrestore(&local->ack_status_lock, flags); + + kfree_skb(ack_skb); +} + /** * ieee80211_build_hdr - build 802.11 header in the given frame * @sdata: virtual interface to build the header for @@ -2982,7 +2994,8 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) { ieee80211_free_txskb(&local->hw, skb); skb = NULL; - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto free; } } @@ -3050,6 +3063,8 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, return skb; free: + if (info_id) + ieee80211_remove_ack_skb(local, info_id); kfree_skb(skb); return ERR_PTR(ret); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index f6d4ae4127c8..59f73dabe6e0 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -73,6 +73,9 @@ u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, if (ieee80211_is_s1g_beacon(fc)) { struct ieee80211_ext *ext = (void *) hdr; + if (len < offsetofend(struct ieee80211_ext, u.s1g_beacon.sa)) + return NULL; + return ext->u.s1g_beacon.sa; } diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 5e7cc11fab3a..85452ef9a58c 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -891,6 +891,11 @@ llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec, data = skb_mac_header(skb) + skb->mac_len; datalen = skb_tail_pointer(skb) - data; + if (datalen < authlen) { + kfree_sensitive(req); + return -EBADMSG; + } + sg_init_one(&sg, skb_mac_header(skb), assoclen + datalen); if (!(hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC)) { diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 300d4584533e..65089826ff59 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -179,6 +179,7 @@ void mac802154_scan_worker(struct work_struct *work) enum nl802154_scan_types scan_req_type; struct ieee802154_sub_if_data *sdata; unsigned int scan_duration = 0; + netdevice_tracker dev_tracker; struct wpan_phy *wpan_phy; u8 scan_req_duration; u8 page, channel; @@ -209,6 +210,14 @@ void mac802154_scan_worker(struct work_struct *work) return; } + /* + * sdata->dev is dereferenced below after rcu_read_unlock() and outside + * the rtnl, and a concurrent DEL_INTERFACE / PHY teardown can free it + * asynchronously from netdev_run_todo(). Pin it with a reference taken + * while the RCU read lock is still held, and drop it at every exit. + */ + netdev_hold(sdata->dev, &dev_tracker, GFP_ATOMIC); + wpan_phy = scan_req->wpan_phy; scan_req_type = scan_req->type; scan_req_duration = scan_req->duration; @@ -262,12 +271,14 @@ void mac802154_scan_worker(struct work_struct *work) "Scan page %u channel %u for %ums\n", page, channel, jiffies_to_msecs(scan_duration)); queue_delayed_work(local->mac_wq, &local->scan_work, scan_duration); + netdev_put(sdata->dev, &dev_tracker); return; end_scan: rtnl_lock(); mac802154_scan_cleanup_locked(local, sdata, false); rtnl_unlock(); + netdev_put(sdata->dev, &dev_tracker); } int mac802154_trigger_scan_locked(struct ieee802154_sub_if_data *sdata, diff --git a/net/mctp/device.c b/net/mctp/device.c index 2c84df674669..822120e860c8 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -536,7 +536,9 @@ int __init mctp_device_init(void) { int err; - register_netdevice_notifier(&mctp_dev_nb); + err = register_netdevice_notifier(&mctp_dev_nb); + if (err) + return err; err = rtnl_af_register(&mctp_af_ops); if (err) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index ca504d9626cf..4406c304b639 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -922,8 +922,7 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg, struct nlattr *nla_via, *nla_newdst; int remaining = cfg->rc_mp_len; int err = 0; - - rt->rt_nhn = 0; + u8 nhs = 0; change_nexthops(rt) { int attrlen; @@ -959,12 +958,15 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg, rt->rt_nhn_alive--; rtnh = rtnh_next(rtnh, &remaining); - rt->rt_nhn++; + nhs++; } endfor_nexthops(rt); + rt->rt_nhn = nhs; + return 0; errout: + rt->rt_nhn = nhs; return err; } @@ -2186,6 +2188,9 @@ static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, int ifindex; if (i == RTA_OIF) { + if (!tb[i]) + continue; + ifindex = nla_get_u32(tb[i]); filter->dev = dev_get_by_index_rcu(net, ifindex); if (!filter->dev) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index dff3fd5d3b55..c664023d37ba 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -157,17 +157,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr++; flags = (*ptr++) & MPTCP_DSS_FLAG_MASK; - mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0; mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0; mp_opt->use_map = (flags & MPTCP_DSS_HAS_MAP) != 0; mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0; mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK); - pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d\n", - mp_opt->data_fin, mp_opt->dsn64, - mp_opt->use_map, mp_opt->ack64, - mp_opt->use_ack); - expected_opsize = TCPOLEN_MPTCP_DSS_BASE; if (mp_opt->use_ack) { @@ -178,12 +172,18 @@ static void mptcp_parse_option(const struct sk_buff *skb, } if (mp_opt->use_map) { + mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0; if (mp_opt->dsn64) expected_opsize += TCPOLEN_MPTCP_DSS_MAP64; else expected_opsize += TCPOLEN_MPTCP_DSS_MAP32; } + pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d\n", + mp_opt->data_fin, mp_opt->dsn64, + mp_opt->use_map, mp_opt->ack64, + mp_opt->use_ack); + /* Always parse any csum presence combination, we will enforce * RFC 8684 Section 3.3.0 checks later in subflow_data_ready */ @@ -571,10 +571,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, bool ret = false; /* Zero `use_ack` and `use_map` flags with one shot. */ - BUILD_BUG_ON(sizeof_field(struct mptcp_ext, flags) != sizeof(u16)); - BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct mptcp_ext, flags), - sizeof(u16))); - *(u16 *)&opts->ext_copy.flags = 0; + memset(&opts->ext_copy.flags, 0, sizeof(opts->ext_copy.flags)); opts->csum_reqd = READ_ONCE(msk->csum_enabled); mpext = skb ? mptcp_get_ext(skb) : NULL; diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index d100867e9202..945aa5afc2dd 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -132,12 +132,15 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, __be16 msk_sport = ((struct inet_sock *) inet_sk((struct sock *)msk))->inet_sport; struct mptcp_pm_addr_entry *entry; + int id; spin_lock_bh(&msk->pm.lock); entry = mptcp_userspace_pm_lookup_addr(msk, &skc->addr); + id = entry ? entry->addr.id : -1; spin_unlock_bh(&msk->pm.lock); - if (entry) - return entry->addr.id; + + if (id != -1) + return id; if (skc->addr.port == msk_sport) skc->addr.port = 0; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index cb9515f505aa..ca644ec53eed 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2545,6 +2545,22 @@ static void __mptcp_subflow_disconnect(struct sock *ssk, } } +static void mptcp_cleanup_ssk_backlog(struct sock *sk, struct sock *ssk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + struct sk_buff *skb; + + mptcp_data_lock(sk); + list_for_each_entry(skb, &msk->backlog_list, list) { + if (skb->sk != ssk) + continue; + + atomic_sub(skb->truesize, &skb->sk->sk_rmem_alloc); + skb->sk = NULL; + } + mptcp_data_unlock(sk); +} + /* subflow sockets can be either outgoing (connect) or incoming * (accept). * @@ -2568,6 +2584,9 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); subflow->closing = 1; + if (flags & MPTCP_CF_PUSH) + mptcp_cleanup_ssk_backlog(sk, ssk); + /* Borrow the fwd allocated page left-over; fwd memory for the subflow * could be negative at this point, but will be reach zero soon - when * the data allocated using such fragment will be freed. @@ -2659,9 +2678,6 @@ out: void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { - struct mptcp_sock *msk = mptcp_sk(sk); - struct sk_buff *skb; - /* The first subflow can already be closed or disconnected */ if (subflow->close_event_done || READ_ONCE(subflow->local_id) < 0) return; @@ -2671,17 +2687,6 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (sk->sk_state == TCP_ESTABLISHED) mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL); - /* Remove any reference from the backlog to this ssk; backlog skbs consume - * space in the msk receive queue, no need to touch sk->sk_rmem_alloc - */ - list_for_each_entry(skb, &msk->backlog_list, list) { - if (skb->sk != ssk) - continue; - - atomic_sub(skb->truesize, &skb->sk->sk_rmem_alloc); - skb->sk = NULL; - } - /* subflow aborted before reaching the fully_established status * attempt the creation of the next subflow */ @@ -3907,6 +3912,7 @@ bool mptcp_finish_join(struct sock *ssk) mptcp_data_unlock(parent); if (!ret) { + mptcp_pm_close_subflow(msk); err_prohibited: subflow->reset_reason = MPTCP_RST_EPROHIBIT; return false; diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index d54d7da58334..b0e00be85cb1 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -361,14 +361,13 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, struct ip_vs_iphdr *ipvsh) { int diff; - const unsigned int tcp_offset = ip_hdrlen(skb); struct tcphdr *th; __u32 seq; - if (skb_ensure_writable(skb, tcp_offset + sizeof(*th))) + if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th))) return 0; - th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset); + th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len); /* * Remember seq number in case this pkt gets resized @@ -438,14 +437,13 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, struct ip_vs_iphdr *ipvsh) { int diff; - const unsigned int tcp_offset = ip_hdrlen(skb); struct tcphdr *th; __u32 seq; - if (skb_ensure_writable(skb, tcp_offset + sizeof(*th))) + if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th))) return 0; - th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset); + th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len); /* * Remember seq number in case this pkt gets resized diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 35cbe821c259..bafab93451d0 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1219,8 +1219,7 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, snet.in6 = ciph.saddr.in6; offset = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, offset, sizeof(struct ipv6hdr), - hooknum); + pp, offset, ipvsh->len, hooknum); } #endif diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index ce542ed4b013..9fef4335da13 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -736,13 +736,11 @@ int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { - struct iphdr *iph = ip_hdr(skb); - - if (__ip_vs_get_out_rt(cp->ipvs, cp->af, skb, NULL, iph->daddr, + if (__ip_vs_get_out_rt(cp->ipvs, cp->af, skb, NULL, ip_hdr(skb)->daddr, IP_VS_RT_MODE_NON_LOCAL, NULL, ipvsh) < 0) goto tx_error; - ip_send_check(iph); + ip_send_check(ip_hdr(skb)); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 91582069f6d2..e9ea6d9466e7 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -211,8 +211,8 @@ check_connections: /* Not found, but might be about to be confirmed */ if (PTR_ERR(found) == -EAGAIN) { if (nf_ct_tuple_equal(&conn->tuple, &tuple) && - nf_ct_zone_id(&conn->zone, conn->zone.dir) == - nf_ct_zone_id(zone, zone->dir)) + nf_ct_zone_id(&conn->zone, IP_CT_DIR_ORIGINAL) == + nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL)) goto out_put; /* already exists */ } else { collect++; @@ -223,7 +223,7 @@ check_connections: found_ct = nf_ct_tuplehash_to_ctrack(found); if (nf_ct_tuple_equal(&conn->tuple, &tuple) && - nf_ct_zone_equal(found_ct, zone, zone->dir)) { + nf_ct_zone_equal(found_ct, zone, IP_CT_DIR_ORIGINAL)) { /* * We should not see tuples twice unless someone hooks * this into a table without "-p tcp --syn". diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 9df159448b89..cc8d8e85169f 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -77,7 +77,7 @@ next: hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode, &evicted_list); - if (time_after(stop, jiffies)) { + if (time_after(jiffies, stop)) { ret = STATE_RESTART; break; } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 2a829b5e8240..b66e65439341 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -127,18 +127,18 @@ static int flow_offload_fill_route(struct flow_offload *flow, switch (route->tuple[dir].xmit_type) { case FLOW_OFFLOAD_XMIT_DIRECT: - if (flow_tuple->tun_num) { + if (route->tuple[!dir].in.num_tuns) { flow_tuple->dst_cache = dst; flow_tuple->dst_cookie = flow_offload_dst_cookie(flow_tuple); + } else { + dst_release(dst); } memcpy(flow_tuple->out.h_dest, route->tuple[dir].out.h_dest, ETH_ALEN); memcpy(flow_tuple->out.h_source, route->tuple[dir].out.h_source, ETH_ALEN); flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; - if (!flow_tuple->tun_num) - dst_release(dst); break; case FLOW_OFFLOAD_XMIT_XFRM: case FLOW_OFFLOAD_XMIT_NEIGH: diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c index b4f7bbc3f3ca..51c7f7ce88d9 100644 --- a/net/netfilter/xt_nat.c +++ b/net/netfilter/xt_nat.c @@ -26,6 +26,15 @@ static int xt_nat_checkentry_v0(const struct xt_tgchk_param *par) static int xt_nat_checkentry(const struct xt_tgchk_param *par) { + switch (par->family) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + case NFPROTO_INET: + break; + default: + return -EINVAL; + } + return nf_ct_netns_get(par->net, par->family); } diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index dd98f758176c..a388881c68d4 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -130,11 +130,6 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) if (X(physoutdev)) return -ENAMETOOLONG; } - - if (X(in_mask)) - return -ENAMETOOLONG; - if (X(out_mask)) - return -ENAMETOOLONG; #undef X if (!brnf_probed) { diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 140388a18ae0..513fca6a8e8a 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -837,12 +837,8 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, u16 mru = OVS_CB(skb)->mru; u32 cutlen = OVS_CB(skb)->cutlen; - if (unlikely(cutlen > 0)) { - if (skb->len - cutlen > ovs_mac_header_len(key)) - pskb_trim(skb, skb->len - cutlen); - else - pskb_trim(skb, ovs_mac_header_len(key)); - } + if (unlikely(cutlen < skb->len)) + pskb_trim(skb, max(cutlen, ovs_mac_header_len(key))); if (likely(!mru || (skb->len <= mru + vport->dev->hard_header_len))) { @@ -1234,7 +1230,7 @@ static void execute_psample(struct datapath *dp, struct sk_buff *skb, psample_group.net = ovs_dp_get_net(dp); md.in_ifindex = OVS_CB(skb)->input_vport->dev->ifindex; - md.trunc_size = skb->len - OVS_CB(skb)->cutlen; + md.trunc_size = min(skb->len, OVS_CB(skb)->cutlen); md.rate_as_probability = 1; rate = OVS_CB(skb)->probability ? OVS_CB(skb)->probability : U32_MAX; @@ -1284,22 +1280,21 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, clone = skb_clone(skb, GFP_ATOMIC); if (clone) do_output(dp, clone, port, key); - OVS_CB(skb)->cutlen = 0; + OVS_CB(skb)->cutlen = U32_MAX; break; } case OVS_ACTION_ATTR_TRUNC: { struct ovs_action_trunc *trunc = nla_data(a); - if (skb->len > trunc->max_len) - OVS_CB(skb)->cutlen = skb->len - trunc->max_len; + OVS_CB(skb)->cutlen = trunc->max_len; break; } case OVS_ACTION_ATTR_USERSPACE: output_userspace(dp, skb, key, a, attr, len, OVS_CB(skb)->cutlen); - OVS_CB(skb)->cutlen = 0; + OVS_CB(skb)->cutlen = U32_MAX; if (nla_is_last(a, rem)) { consume_skb(skb); return 0; @@ -1453,7 +1448,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_PSAMPLE: execute_psample(dp, skb, a); - OVS_CB(skb)->cutlen = 0; + OVS_CB(skb)->cutlen = U32_MAX; if (nla_is_last(a, rem)) { consume_skb(skb); return 0; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index f0164817d9b7..eaf332b156d7 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -276,7 +276,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) upcall.portid = ovs_vport_find_upcall_portid(p, skb); upcall.mru = OVS_CB(skb)->mru; - error = ovs_dp_upcall(dp, skb, key, &upcall, 0); + error = ovs_dp_upcall(dp, skb, key, &upcall, U32_MAX); switch (error) { case 0: case -EAGAIN: @@ -457,7 +457,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, struct sk_buff *nskb = NULL; struct sk_buff *user_skb = NULL; /* to be queued to userspace */ struct nlattr *nla; - size_t len; + size_t msg_size; + size_t skb_len; unsigned int hlen; int err, dp_ifindex; u64 hash; @@ -478,7 +479,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, skb = nskb; } - if (nla_attr_size(skb->len) > USHRT_MAX) { + skb_len = min(skb->len, cutlen); + if (nla_attr_size(skb_len) > USHRT_MAX) { err = -EFBIG; goto out; } @@ -493,13 +495,13 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, * padding logic. Only perform zerocopy if padding is not required. */ if (dp->user_features & OVS_DP_F_UNALIGNED) - hlen = skb_zerocopy_headlen(skb); + hlen = min(skb_zerocopy_headlen(skb), cutlen); else - hlen = skb->len; + hlen = skb_len; - len = upcall_msg_size(upcall_info, hlen - cutlen, - OVS_CB(skb)->acts_origlen); - user_skb = genlmsg_new(len, GFP_ATOMIC); + msg_size = upcall_msg_size(upcall_info, hlen, + OVS_CB(skb)->acts_origlen); + user_skb = genlmsg_new(msg_size, GFP_ATOMIC); if (!user_skb) { err = -ENOMEM; goto out; @@ -560,7 +562,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, } /* Add OVS_PACKET_ATTR_LEN when packet is truncated */ - if (cutlen > 0 && + if (skb_len < skb->len && nla_put_u32(user_skb, OVS_PACKET_ATTR_LEN, skb->len)) { err = -ENOBUFS; goto out; @@ -585,9 +587,9 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, err = -ENOBUFS; goto out; } - nla->nla_len = nla_attr_size(skb->len - cutlen); + nla->nla_len = nla_attr_size(skb_len); - err = skb_zerocopy(user_skb, skb, skb->len - cutlen, hlen); + err = skb_zerocopy(user_skb, skb, skb_len, hlen); if (err) goto out; @@ -644,6 +646,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) packet->ignore_df = 1; } OVS_CB(packet)->mru = mru; + OVS_CB(packet)->cutlen = U32_MAX; if (a[OVS_PACKET_ATTR_HASH]) { hash = nla_get_u64(a[OVS_PACKET_ATTR_HASH]); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index db0c3e69d66c..696640e88fa7 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -118,7 +118,7 @@ struct datapath { * @mru: The maximum received fragement size; 0 if the packet is not * fragmented. * @acts_origlen: The netlink size of the flow actions applied to this skb. - * @cutlen: The number of bytes from the packet end to be removed. + * @cutlen: The number of bytes in the packet to preserve on output. * @probability: The sampling probability that was applied to this skb; 0 means * no sampling has occurred; U32_MAX means 100% probability. * @upcall_pid: Netlink socket PID to use for sending this packet to userspace; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 13052408a132..d8079dee700e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2496,13 +2496,56 @@ static inline int add_nested_action_start(struct sw_flow_actions **sfa, return used; } -static inline void add_nested_action_end(struct sw_flow_actions *sfa, - int st_offset) +static inline int add_nested_action_end(struct sw_flow_actions *sfa, + int st_offset) { - struct nlattr *a = (struct nlattr *) ((unsigned char *)sfa->actions + - st_offset); + struct nlattr *a; + u32 attr_len; + + if (WARN_ON_ONCE(st_offset < 0 || + (u32)st_offset > sfa->actions_len)) + return -EINVAL; + + attr_len = sfa->actions_len - (u32)st_offset; + if (WARN_ON_ONCE(attr_len < NLA_HDRLEN)) + return -EINVAL; - a->nla_len = sfa->actions_len - st_offset; + if (attr_len > U16_MAX) + return -EMSGSIZE; + + a = (struct nlattr *)((u8 *)sfa->actions + st_offset); + a->nla_len = attr_len; + return 0; +} + +/* Free the generated action-list tail at @start and truncate it. + * If @nested, @start points to its containing nlattr header. + */ +static void ovs_nla_trim(struct sw_flow_actions *sfa, int start, bool nested) +{ + const struct nlattr *actions; + u32 len; + + if (start < 0) + return; + + if (WARN_ON_ONCE((u32)start > sfa->actions_len)) + return; + + actions = (const struct nlattr *)((u8 *)sfa->actions + start); + len = sfa->actions_len - (u32)start; + + if (nested) { + if (len < NLA_HDRLEN) + goto out; + + actions = (const struct nlattr *)((u8 *)actions + NLA_HDRLEN); + len -= NLA_HDRLEN; + } + + ovs_nla_free_nested_actions(actions, len); +out: + sfa->actions_len = start; } static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, @@ -2522,6 +2565,7 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; const struct nlattr *a; + int actions_start; int rem, start, err; struct sample_arg arg; @@ -2565,18 +2609,27 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_ARG, &arg, sizeof(arg), log); if (err) - return err; + goto err; + actions_start = (*sfa)->actions_len; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth + 1); if (err) - return err; + goto err_free; - add_nested_action_end(*sfa, start); + err = add_nested_action_end(*sfa, start); + if (err) + goto err_free; return 0; + +err_free: + ovs_nla_trim(*sfa, actions_start, false); +err: + (*sfa)->actions_len = start; + return err; } static int validate_and_copy_dec_ttl(struct net *net, @@ -2624,18 +2677,31 @@ static int validate_and_copy_dec_ttl(struct net *net, return start; action_start = add_nested_action_start(sfa, OVS_DEC_TTL_ATTR_ACTION, log); - if (action_start < 0) - return action_start; + if (action_start < 0) { + err = action_start; + goto err; + } err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth + 1); if (err) - return err; + goto err_free; + + err = add_nested_action_end(*sfa, action_start); + if (err) + goto err_free; - add_nested_action_end(*sfa, action_start); - add_nested_action_end(*sfa, start); + err = add_nested_action_end(*sfa, start); + if (err) + goto err_free; return 0; + +err_free: + ovs_nla_trim(*sfa, action_start, true); +err: + (*sfa)->actions_len = start; + return err; } static int validate_and_copy_clone(struct net *net, @@ -2646,6 +2712,7 @@ static int validate_and_copy_clone(struct net *net, u32 mpls_label_count, bool log, bool last, u32 depth) { + int actions_start; int start, err; u32 exec; @@ -2661,17 +2728,26 @@ static int validate_and_copy_clone(struct net *net, err = ovs_nla_add_action(sfa, OVS_CLONE_ATTR_EXEC, &exec, sizeof(exec), log); if (err) - return err; + goto err; + actions_start = (*sfa)->actions_len; err = __ovs_nla_copy_actions(net, attr, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth + 1); if (err) - return err; + goto err_free; - add_nested_action_end(*sfa, start); + err = add_nested_action_end(*sfa, start); + if (err) + goto err_free; return 0; + +err_free: + ovs_nla_trim(*sfa, actions_start, false); +err: + (*sfa)->actions_len = start; + return err; } void ovs_match_init(struct sw_flow_match *match, @@ -2763,20 +2839,20 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, tun_dst = metadata_dst_alloc(key.tun_opts_len, METADATA_IP_TUNNEL, GFP_KERNEL); - if (!tun_dst) - return -ENOMEM; + if (!tun_dst) { + err = -ENOMEM; + goto err; + } err = dst_cache_init(&tun_dst->u.tun_info.dst_cache, GFP_KERNEL); - if (err) { - dst_release((struct dst_entry *)tun_dst); - return err; - } + if (err) + goto err_free_tun_dst; a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL, sizeof(*ovs_tun), log); if (IS_ERR(a)) { - dst_release((struct dst_entry *)tun_dst); - return PTR_ERR(a); + err = PTR_ERR(a); + goto err_free_tun_dst; } ovs_tun = nla_data(a); @@ -2797,8 +2873,16 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, ip_tunnel_info_opts_set(tun_info, TUN_METADATA_OPTS(&key, key.tun_opts_len), key.tun_opts_len, dst_opt_type); - add_nested_action_end(*sfa, start); + err = add_nested_action_end(*sfa, start); + if (WARN_ON_ONCE(err)) + goto err_free_tun_dst; + + return 0; +err_free_tun_dst: + dst_release((struct dst_entry *)tun_dst); +err: + (*sfa)->actions_len = start; return err; } @@ -2971,7 +3055,7 @@ static int validate_set(const struct nlattr *a, /* Convert non-masked non-tunnel set actions to masked set actions. */ if (!masked && key_type != OVS_KEY_ATTR_TUNNEL) { - int start, len = key_len * 2; + int err, start, len = key_len * 2; struct nlattr *at; *skip_copy = true; @@ -2983,8 +3067,11 @@ static int validate_set(const struct nlattr *a, return start; at = __add_action(sfa, key_type, NULL, len, log); - if (IS_ERR(at)) - return PTR_ERR(at); + if (IS_ERR(at)) { + err = PTR_ERR(at); + (*sfa)->actions_len = start; + return err; + } memcpy(nla_data(at), nla_data(ovs_key), key_len); /* Key. */ memset(nla_data(at) + key_len, 0xff, key_len); /* Mask. */ @@ -2994,7 +3081,11 @@ static int validate_set(const struct nlattr *a, mask->ipv6_label &= htonl(0x000FFFFF); } - add_nested_action_end(*sfa, start); + err = add_nested_action_end(*sfa, start); + if (WARN_ON_ONCE(err)) { + (*sfa)->actions_len = start; + return err; + } } return 0; @@ -3040,7 +3131,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, const struct nlattr *acts_if_greater, *acts_if_lesser_eq; struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1]; struct check_pkt_len_arg arg; - int nested_acts_start; + int greater_acts_start = -1; + int lesser_acts_start = -1; int start, err; err = nla_parse_deprecated_strict(a, OVS_CHECK_PKT_LEN_ATTR_MAX, @@ -3075,37 +3167,58 @@ static int validate_and_copy_check_pkt_len(struct net *net, err = ovs_nla_add_action(sfa, OVS_CHECK_PKT_LEN_ATTR_ARG, &arg, sizeof(arg), log); if (err) - return err; + goto err_free; - nested_acts_start = add_nested_action_start(sfa, - OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL, log); - if (nested_acts_start < 0) - return nested_acts_start; + lesser_acts_start = + add_nested_action_start(sfa, + OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL, + log); + if (lesser_acts_start < 0) { + err = lesser_acts_start; + goto err_free; + } err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth + 1); if (err) - return err; + goto err_free; - add_nested_action_end(*sfa, nested_acts_start); + err = add_nested_action_end(*sfa, lesser_acts_start); + if (err) + goto err_free; - nested_acts_start = add_nested_action_start(sfa, - OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER, log); - if (nested_acts_start < 0) - return nested_acts_start; + greater_acts_start = + add_nested_action_start(sfa, + OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER, + log); + if (greater_acts_start < 0) { + err = greater_acts_start; + goto err_free; + } err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth + 1); if (err) - return err; + goto err_free; + + err = add_nested_action_end(*sfa, greater_acts_start); + if (err) + goto err_free; - add_nested_action_end(*sfa, nested_acts_start); - add_nested_action_end(*sfa, start); + err = add_nested_action_end(*sfa, start); + if (err) + goto err_free; return 0; + +err_free: + ovs_nla_trim(*sfa, greater_acts_start, true); + ovs_nla_trim(*sfa, lesser_acts_start, true); + ovs_nla_trim(*sfa, start, false); + return err; } static int validate_psample(const struct nlattr *attr) diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 56b2e2d1a749..12741485c939 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -502,7 +502,7 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb, OVS_CB(skb)->input_vport = vport; OVS_CB(skb)->mru = 0; - OVS_CB(skb)->cutlen = 0; + OVS_CB(skb)->cutlen = U32_MAX; OVS_CB(skb)->probability = 0; OVS_CB(skb)->upcall_pid = 0; if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8e6f3a734ba0..e75d2932475a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4561,7 +4561,11 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, spin_lock(&po->bind_lock); WRITE_ONCE(po->num, num); - if (was_running) + /* + * NETDEV_UNREGISTER may have invalidated the binding while bind_lock + * was dropped above. Do not re-add a fanout hook to a dead device. + */ + if (was_running && READ_ONCE(po->ifindex) != -1) register_prot_hook(sk); spin_unlock(&po->bind_lock); diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 706927139393..31b29e3ca7bc 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -55,6 +55,8 @@ static unsigned char *pep_get_sb(struct sk_buff *skb, u8 *ptype, u8 *plen, ph = skb_header_pointer(skb, 0, 2, &h); if (ph == NULL || ph->sb_len < 2 || !pskb_may_pull(skb, ph->sb_len)) return NULL; + /* pskb_may_pull() may have reallocated the head; refetch ph. */ + ph = skb_header_pointer(skb, 0, 2, &h); ph->sb_len -= 2; *ptype = ph->sb_type; *plen = ph->sb_len; diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index ad44831d6745..1272d49cd038 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -350,16 +350,34 @@ static struct pernet_operations phonet_net_ops = { /* Initialize Phonet devices list */ int __init phonet_device_init(void) { - int err = register_pernet_subsys(&phonet_net_ops); + int err; + + err = register_pernet_subsys(&phonet_net_ops); if (err) return err; - proc_create_net("pnresource", 0, init_net.proc_net, &pn_res_seq_ops, - sizeof(struct seq_net_private)); - register_netdevice_notifier(&phonet_device_notifier); + if (!proc_create_net("pnresource", 0, init_net.proc_net, + &pn_res_seq_ops, sizeof(struct seq_net_private))) { + err = -ENOMEM; + goto err_pernet; + } + + err = register_netdevice_notifier(&phonet_device_notifier); + if (err) + goto err_proc; + err = phonet_netlink_register(); if (err) - phonet_device_exit(); + goto err_notifier; + + return 0; + +err_notifier: + unregister_netdevice_notifier(&phonet_device_notifier); +err_proc: + remove_proc_entry("pnresource", init_net.proc_net); +err_pernet: + unregister_pernet_subsys(&phonet_net_ops); return err; } @@ -367,8 +385,8 @@ void phonet_device_exit(void) { rtnl_unregister_all(PF_PHONET); unregister_netdevice_notifier(&phonet_device_notifier); - unregister_pernet_subsys(&phonet_net_ops); remove_proc_entry("pnresource", init_net.proc_net); + unregister_pernet_subsys(&phonet_net_ops); } int phonet_route_add(struct net_device *dev, u8 daddr) diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index d02ef9a74c3c..a30fa56e6aa3 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -1263,6 +1263,14 @@ static int qrtr_create(struct net *net, struct socket *sock, if (sock->type != SOCK_DGRAM) return -EPROTOTYPE; + /* QRTR keeps its port and node state in module-global variables that + * are not partitioned per network namespace, and the in-kernel name + * service only operates in init_net. Confine the family to init_net so + * a socket in another namespace cannot reach the global control plane. + */ + if (!net_eq(net, &init_net)) + return -EAFNOSUPPORT; + sk = sk_alloc(net, AF_QIPCRTR, GFP_KERNEL, &qrtr_proto, kern); if (!sk) return -ENOMEM; diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index b3f9bbcf9ab9..e5b2adb161d9 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -76,11 +76,11 @@ struct qrtr_node { * requirements. If the requirement changes in the future, these values can be * increased. */ -#define QRTR_NS_MAX_NODES 64 +#define QRTR_NS_MAX_NODES 512 #define QRTR_NS_MAX_SERVERS 256 #define QRTR_NS_MAX_LOOKUPS 64 -static u8 node_count; +static u16 node_count; static struct qrtr_node *node_get(unsigned int node_id) { diff --git a/net/rds/ib.c b/net/rds/ib.c index 39f87272e071..8f9cf491984f 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -429,6 +429,10 @@ static int rds_ib_laddr_check_cm(struct net *net, const struct in6_addr *addr, sa = (struct sockaddr *)&sin; } else { #if IS_ENABLED(CONFIG_IPV6) + if (!ipv6_mod_enabled()) { + ret = -EADDRNOTAVAIL; + goto out; + } memset(&sin6, 0, sizeof(sin6)); sin6.sin6_family = AF_INET6; sin6.sin6_addr = *addr; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 5667f0173b47..d46146887ba4 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -810,6 +810,10 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, dp = event->param.conn.private_data; if (isv6) { #if IS_ENABLED(CONFIG_IPV6) + if (!ipv6_mod_enabled()) { + err = -EOPNOTSUPP; + goto out; + } dp_cmn = &dp->ricp_v6.dp_cmn; saddr6 = &dp->ricp_v6.dp_saddr; daddr6 = &dp->ricp_v6.dp_daddr; diff --git a/net/rds/recv.c b/net/rds/recv.c index 4b3f9e4a8bfd..cf3884d87931 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -399,6 +399,21 @@ void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr, goto out; } + /* + * rds_find_bound() uses a global (netns-agnostic) hash table. + * An RDS connection created in netns A can match a socket bound + * in the init netns, delivering inc cross-netns with inc->i_conn + * pointing into netns A. When cleanup_net() then frees that conn, + * any subsequent dereference of inc->i_conn is a use-after-free. + * Drop the inc if the receiving socket lives in a different netns. + */ + if (!net_eq(sock_net(rds_rs_to_sk(rs)), rds_conn_net(conn))) { + rds_stats_inc(s_recv_drop_no_sock); + rds_sock_put(rs); + rs = NULL; + goto out; + } + /* Process extension headers */ rds_recv_incoming_exthdrs(inc, rs); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index a1de114d5e2e..5de35d556f29 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -366,9 +366,11 @@ int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, rcu_read_unlock(); } #if IS_ENABLED(CONFIG_IPV6) - ret = ipv6_chk_addr(net, addr, dev, 0); - if (ret) - return 0; + if (ipv6_mod_enabled()) { + ret = ipv6_chk_addr(net, addr, dev, 0); + if (ret) + return 0; + } #endif return -EADDRNOTAVAIL; } @@ -655,13 +657,13 @@ static void __net_exit rds_tcp_exit_net(struct net *net) { struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); - rds_tcp_kill_sock(net); - if (rtn->rds_tcp_sysctl) unregister_net_sysctl_table(rtn->rds_tcp_sysctl); if (net != &init_net) kfree(rtn->ctl_table); + + rds_tcp_kill_sock(net); } static struct pernet_operations rds_tcp_net_ops = { diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ce946b0a03e2..865f05fe37ab 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1285,9 +1285,11 @@ int rxrpc_io_thread(void *data); void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb); static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local) { - if (!local->io_thread) + struct task_struct *io_thread = READ_ONCE(local->io_thread); + + if (!io_thread) return; - wake_up_process(READ_ONCE(local->io_thread)); + wake_up_process(io_thread); } static inline bool rxrpc_protocol_error(struct sk_buff *skb, enum rxrpc_abort_reason why) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 876b30c5709e..b14807761d82 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -342,14 +342,20 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_TTL] = { .type = NLA_U8 }, }; -static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) +static void tunnel_key_release_params_rcu(struct rcu_head *head) { - if (!p) - return; + struct tcf_tunnel_key_params *p = container_of(head, typeof(*p), rcu); + if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) dst_release(&p->tcft_enc_metadata->dst); + kfree(p); +} - kfree_rcu(p, rcu); +static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) +{ + if (!p) + return; + call_rcu(&p->rcu, tunnel_key_release_params_rcu); } static int tunnel_key_init(struct net *net, struct nlattr *nla, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ffeea6db8337..fee4524adc98 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -4045,7 +4045,7 @@ struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, stru fl = rcu_dereference_bh(qe->filter_chain); - switch (tcf_classify(skb, NULL, fl, &cl_res, false)) { + switch (tcf_classify_qdisc(skb, fl, &cl_res, false)) { case TC_ACT_SHOT: qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); @@ -4057,10 +4057,6 @@ struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, stru __qdisc_drop(skb, to_free); *ret = __NET_XMIT_STOLEN; return NULL; - case TC_ACT_REDIRECT: - skb_do_redirect(skb); - *ret = __NET_XMIT_STOLEN; - return NULL; case TC_ACT_CONSUMED: *ret = __NET_XMIT_STOLEN; return NULL; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 8a3236456db4..668bcd60d183 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -415,12 +415,13 @@ static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) } static struct qdisc_rate_table *qdisc_rtab_list; +static DEFINE_SPINLOCK(qdisc_rtab_lock); struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab, struct netlink_ext_ack *extack) { - struct qdisc_rate_table *rtab; + struct qdisc_rate_table *rtab, *new_rtab; if (tab == NULL || r->rate == 0 || r->cell_log == 0 || r->cell_log >= 32 || @@ -429,15 +430,20 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, return NULL; } + new_rtab = kmalloc_obj(*new_rtab); + + spin_lock(&qdisc_rtab_lock); for (rtab = qdisc_rtab_list; rtab; rtab = rtab->next) { if (!memcmp(&rtab->rate, r, sizeof(struct tc_ratespec)) && !memcmp(&rtab->data, nla_data(tab), TC_RTAB_SIZE)) { rtab->refcnt++; + spin_unlock(&qdisc_rtab_lock); + kfree(new_rtab); return rtab; } } - rtab = kmalloc_obj(*rtab); + rtab = new_rtab; if (rtab) { rtab->rate = *r; rtab->refcnt = 1; @@ -449,6 +455,7 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, } else { NL_SET_ERR_MSG(extack, "Failed to allocate new qdisc rate table"); } + spin_unlock(&qdisc_rtab_lock); return rtab; } EXPORT_SYMBOL(qdisc_get_rtab); @@ -457,18 +464,25 @@ void qdisc_put_rtab(struct qdisc_rate_table *tab) { struct qdisc_rate_table *rtab, **rtabp; - if (!tab || --tab->refcnt) + if (!tab) return; + spin_lock(&qdisc_rtab_lock); + if (--tab->refcnt) { + spin_unlock(&qdisc_rtab_lock); + return; + } + for (rtabp = &qdisc_rtab_list; (rtab = *rtabp) != NULL; rtabp = &rtab->next) { if (rtab == tab) { *rtabp = rtab->next; - kfree(rtab); - return; + break; } } + spin_unlock(&qdisc_rtab_lock); + kfree(tab); } EXPORT_SYMBOL(qdisc_put_rtab); diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index f78f8e950776..505f63fecf64 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1727,7 +1727,7 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, goto hash; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tcf_classify(skb, NULL, filter, &res, false); + result = tcf_classify_qdisc(skb, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 020657f959b5..91b1ef824afa 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -312,7 +312,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tcf_classify(skb, NULL, fl, &res, false); + result = tcf_classify_qdisc(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c index 27088760eff4..4f678d4ff10e 100644 --- a/net/sched/sch_dualpi2.c +++ b/net/sched/sch_dualpi2.c @@ -364,7 +364,7 @@ static int dualpi2_skb_classify(struct dualpi2_sched_data *q, if (!fl) return NET_XMIT_SUCCESS; - result = tcf_classify(skb, NULL, fl, &res, false); + result = tcf_classify_qdisc(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index cb8cf437ce87..25fcf4079fec 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -391,7 +391,7 @@ static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { fl = rcu_dereference_bh(q->filter_list); - err = tcf_classify(skb, NULL, fl, &res, false); + err = tcf_classify_qdisc(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index cafd1f943d99..6cce86ba383c 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -91,7 +91,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, return fq_codel_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tcf_classify(skb, NULL, filter, &res, false); + result = tcf_classify_qdisc(skb, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 72f48fa4010b..069e1facd413 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -96,7 +96,7 @@ static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch, return fq_pie_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tcf_classify(skb, NULL, filter, &res, false); + result = tcf_classify_qdisc(skb, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 7e537295b8b6..e87f5021a199 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1143,7 +1143,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; head = &q->root; tcf = rcu_dereference_bh(q->root.filter_list); - while (tcf && (result = tcf_classify(skb, NULL, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify_qdisc(skb, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 908b9ba9ba2e..fdac0dc8f35a 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -243,7 +243,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - while (tcf && (result = tcf_classify(skb, NULL, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify_qdisc(skb, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index a467dd122369..66df30939aa5 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -36,7 +36,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) int err; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - err = tcf_classify(skb, NULL, fl, &res, false); + err = tcf_classify_qdisc(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index e4dd56a89072..79437c587e7e 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -39,7 +39,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { fl = rcu_dereference_bh(q->filter_list); - err = tcf_classify(skb, NULL, fl, &res, false); + err = tcf_classify_qdisc(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index cb56787e1d25..6f3b7273cb16 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -709,7 +709,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tcf_classify(skb, NULL, fl, &res, false); + result = tcf_classify_qdisc(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index b1d465094276..ed39869199c0 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -260,7 +260,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, struct tcf_result res; int result; - result = tcf_classify(skb, NULL, fl, &res, false); + result = tcf_classify_qdisc(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 758b88f21865..77675f9a4c46 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -171,7 +171,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return sfq_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tcf_classify(skb, NULL, fl, &res, false); + result = tcf_classify_qdisc(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sctp/auth.c b/net/sctp/auth.c index be9782760f50..c901d373af80 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -672,7 +672,7 @@ int sctp_auth_ep_add_chunkid(struct sctp_endpoint *ep, __u8 chunk_id) /* Check if we can add this chunk to the array */ param_len = ntohs(p->param_hdr.length); nchunks = param_len - sizeof(struct sctp_paramhdr); - if (nchunks == SCTP_NUM_CHUNK_TYPES) + if (nchunks == SCTP_AUTH_MAX_CHUNKS) return -EINVAL; p->chunks[nchunks] = chunk_id; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index cf335494bffe..27c26e12f95d 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1383,10 +1383,6 @@ static int __net_init sctp_defaults_init(struct net *net) net->sctp.l3mdev_accept = 1; #endif - status = sctp_sysctl_net_register(net); - if (status) - goto err_sysctl_register; - /* Allocate and initialise sctp mibs. */ status = init_sctp_mibs(net); if (status) @@ -1420,8 +1416,6 @@ err_init_proc: cleanup_sctp_mibs(net); #endif err_init_mibs: - sctp_sysctl_net_unregister(net); -err_sysctl_register: return status; } @@ -1436,7 +1430,6 @@ static void __net_exit sctp_defaults_exit(struct net *net) net->sctp.proc_net_sctp = NULL; #endif cleanup_sctp_mibs(net); - sctp_sysctl_net_unregister(net); } static struct pernet_operations sctp_defaults_ops = { @@ -1450,16 +1443,28 @@ static int __net_init sctp_ctrlsock_init(struct net *net) /* Initialize the control inode/socket for handling OOTB packets. */ status = sctp_ctl_sock_init(net); - if (status) + if (status) { pr_err("Failed to initialize the SCTP control sock\n"); + return status; + } + + status = sctp_sysctl_net_register(net); + if (status) { + inet_ctl_sock_destroy(net->sctp.ctl_sock); + net->sctp.ctl_sock = NULL; + } return status; } static void __net_exit sctp_ctrlsock_exit(struct net *net) { + sctp_sysctl_net_unregister(net); + sctp_udp_sock_stop(net); + /* Free the control endpoint. */ inet_ctl_sock_destroy(net->sctp.ctl_sock); + net->sctp.ctl_sock = NULL; } static struct pernet_operations sctp_ctrlsock_ops = { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 8adac9e0cd66..c02809264075 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3153,6 +3153,12 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, if (!peer) return SCTP_ERROR_DNS_FAILED; + /* Don't free asconf->transport; a later wildcard DEL-IP + * parameter reuses it. + */ + if (peer == asconf->transport) + return SCTP_ERROR_REQ_REFUSED; + sctp_assoc_rm_peer(asoc, peer); break; case SCTP_PARAM_SET_PRIMARY: diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index d23d935e128e..708fa07d5fff 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -74,7 +74,8 @@ static enum sctp_disposition sctp_sf_do_5_2_6_stale( const struct sctp_association *asoc, const union sctp_subtype type, void *arg, - struct sctp_cmd_seq *commands); + struct sctp_cmd_seq *commands, + struct sctp_errhdr *err); static enum sctp_disposition sctp_sf_shut_8_4_5( struct net *net, const struct sctp_endpoint *ep, @@ -642,7 +643,7 @@ static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk, struct sctp_chunk auth; if (!chunk->auth_chunk) - return true; + return !sctp_auth_recv_cid(chunk->chunk_hdr->type, asoc); /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo * is supposed to be authenticated and we have to do delayed @@ -2529,9 +2530,15 @@ enum sctp_disposition sctp_sf_cookie_echoed_err( * errors. */ sctp_walk_errors(err, chunk->chunk_hdr) { - if (SCTP_ERROR_STALE_COOKIE == err->cause) - return sctp_sf_do_5_2_6_stale(net, ep, asoc, type, - arg, commands); + if (err->cause != SCTP_ERROR_STALE_COOKIE) + continue; + /* The staleness is only meaningful if the cause is long + * enough to hold it; a shorter one is malformed. + */ + if (ntohs(err->length) < sizeof(*err) + sizeof(__be32)) + break; + return sctp_sf_do_5_2_6_stale(net, ep, asoc, type, + arg, commands, err); } /* It is possible to have malformed error causes, and that @@ -2573,13 +2580,13 @@ static enum sctp_disposition sctp_sf_do_5_2_6_stale( const struct sctp_association *asoc, const union sctp_subtype type, void *arg, - struct sctp_cmd_seq *commands) + struct sctp_cmd_seq *commands, + struct sctp_errhdr *err) { int attempts = asoc->init_err_counter + 1; - struct sctp_chunk *chunk = arg, *reply; struct sctp_cookie_preserve_param bht; struct sctp_bind_addr *bp; - struct sctp_errhdr *err; + struct sctp_chunk *reply; u32 stale; if (attempts > asoc->max_init_attempts) { @@ -2590,8 +2597,6 @@ static enum sctp_disposition sctp_sf_do_5_2_6_stale( return SCTP_DISPOSITION_DELETE_TCB; } - err = (struct sctp_errhdr *)(chunk->skb->data); - /* When calculating the time extension, an implementation * SHOULD use the RTT information measured based on the * previous COOKIE ECHO / ERROR exchange, and should add no diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 5c2fdedea088..34ffe6c945a4 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -308,7 +308,8 @@ int sctp_send_reset_streams(struct sctp_association *asoc, goto out; param_len += str_nums * sizeof(__u16) + - sizeof(struct sctp_strreset_inreq); + (out ? sizeof(struct sctp_strreset_inreq) + : sizeof(struct sctp_strreset_outreq)); } if (param_len > SCTP_MAX_CHUNK_LEN - @@ -639,6 +640,9 @@ struct sctp_chunk *sctp_process_strreset_inreq( nums = (ntohs(param.p->length) - sizeof(*inreq)) / sizeof(__u16); str_p = inreq->list_of_streams; + if (nums * sizeof(__u16) + sizeof(struct sctp_strreset_outreq) > + SCTP_MAX_CHUNK_LEN - sizeof(struct sctp_reconf_chunk)) + goto out; for (i = 0; i < nums; i++) { if (ntohs(str_p[i]) >= stream->outcnt) { result = SCTP_STRRESET_ERR_WRONG_SSN; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 15e7db9a3ab2..fca840484ebf 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -615,11 +615,16 @@ int sctp_sysctl_net_register(struct net *net) void sctp_sysctl_net_unregister(struct net *net) { + struct ctl_table_header *header = net->sctp.sysctl_header; const struct ctl_table *table; - table = net->sctp.sysctl_header->ctl_table_arg; - unregister_net_sysctl_table(net->sctp.sysctl_header); + if (!header) + return; + + table = header->ctl_table_arg; + unregister_net_sysctl_table(header); kfree(table); + net->sctp.sysctl_header = NULL; } static struct ctl_table_header *sctp_sysctl_header; diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 8336a9664703..1307dd1a9613 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -113,12 +113,16 @@ const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = { }; /* Properties valid for media, bearer and link */ +static const struct netlink_range_validation tipc_nl_mtu_range = { + .max = U16_MAX, +}; + const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { [TIPC_NLA_PROP_UNSPEC] = { .type = NLA_UNSPEC }, [TIPC_NLA_PROP_PRIO] = { .type = NLA_U32 }, [TIPC_NLA_PROP_TOL] = { .type = NLA_U32 }, [TIPC_NLA_PROP_WIN] = { .type = NLA_U32 }, - [TIPC_NLA_PROP_MTU] = { .type = NLA_U32 }, + [TIPC_NLA_PROP_MTU] = NLA_POLICY_FULL_RANGE(NLA_U32, &tipc_nl_mtu_range), [TIPC_NLA_PROP_BROADCAST] = { .type = NLA_U32 }, [TIPC_NLA_PROP_BROADCAST_RATIO] = { .type = NLA_U32 } }; diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 2a786c56c8c5..d9a4f94ea2d4 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -221,6 +221,10 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, int rem; len = (*cmd->dumpit)(buf, &cb); + if (len < 0) { + err = len; + goto err_out; + } nlmsg_for_each_msg(nlmsg, nlmsg_hdr(buf), len, rem) { err = nlmsg_parse_deprecated(nlmsg, GENL_HDRLEN, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e564341e0216..185c24003b82 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -502,6 +502,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, tipc_set_sk_state(sk, TIPC_OPEN); if (tipc_sk_insert(tsk)) { sk_free(sk); + sock->sk = NULL; pr_warn("Socket create failed; port number exhausted\n"); return -EINVAL; } @@ -1935,7 +1936,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, if (likely(!err)) { int offset = skb_cb->bytes_read; - copy = min_t(int, dlen - offset, buflen); + copy = min_t(size_t, dlen - offset, buflen); rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy); if (unlikely(rc)) goto exit; @@ -2067,7 +2068,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Copy data if msg ok, otherwise return error/partial data */ if (likely(!err)) { offset = skb_cb->bytes_read; - copy = min_t(int, dlen - offset, buflen - copied); + copy = min_t(size_t, dlen - offset, buflen - copied); rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy); if (unlikely(rc)) break; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 62ae7f5b5840..230645cc01c9 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -94,6 +94,8 @@ struct udp_replicast { * @ifindex: local address scope * @work: used to schedule deferred work on a bearer * @rcast: associated udp_replicast container + * @rcast_lock: serialize updates to @rcast.list against concurrent updaters + * @disabled: bearer is being torn down; reject further @rcast.list additions */ struct udp_bearer { struct tipc_bearer __rcu *bearer; @@ -101,6 +103,8 @@ struct udp_bearer { u32 ifindex; struct work_struct work; struct udp_replicast rcast; + spinlock_t rcast_lock; + bool disabled; }; static int tipc_udp_is_mcast_addr(struct udp_media_addr *addr) @@ -278,26 +282,6 @@ out: return err; } -static bool tipc_udp_is_known_peer(struct tipc_bearer *b, - struct udp_media_addr *addr) -{ - struct udp_replicast *rcast, *tmp; - struct udp_bearer *ub; - - ub = rcu_dereference_rtnl(b->media_ptr); - if (!ub) { - pr_err_ratelimited("UDP bearer instance not found\n"); - return false; - } - - list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { - if (!memcmp(&rcast->addr, addr, sizeof(struct udp_media_addr))) - return true; - } - - return false; -} - static int tipc_udp_rcast_add(struct tipc_bearer *b, struct udp_media_addr *addr) { @@ -308,16 +292,34 @@ static int tipc_udp_rcast_add(struct tipc_bearer *b, if (!ub) return -ENODEV; + spin_lock_bh(&ub->rcast_lock); + if (ub->disabled) { + spin_unlock_bh(&ub->rcast_lock); + return 0; + } + list_for_each_entry(rcast, &ub->rcast.list, list) { + if (!memcmp(&rcast->addr, addr, sizeof(*addr))) { + spin_unlock_bh(&ub->rcast_lock); + return 0; + } + } + rcast = kmalloc_obj(*rcast, GFP_ATOMIC); - if (!rcast) + if (!rcast) { + spin_unlock_bh(&ub->rcast_lock); return -ENOMEM; + } if (dst_cache_init(&rcast->dst_cache, GFP_ATOMIC)) { + spin_unlock_bh(&ub->rcast_lock); kfree(rcast); return -ENOMEM; } memcpy(&rcast->addr, addr, sizeof(struct udp_media_addr)); + list_add_rcu(&rcast->list, &ub->rcast.list); + b->bcast_addr.broadcast = TIPC_REPLICAST_SUPPORT; + spin_unlock_bh(&ub->rcast_lock); if (ntohs(addr->proto) == ETH_P_IP) pr_info("New replicast peer: %pI4\n", &rcast->addr.ipv4); @@ -325,8 +327,6 @@ static int tipc_udp_rcast_add(struct tipc_bearer *b, else if (ntohs(addr->proto) == ETH_P_IPV6) pr_info("New replicast peer: %pI6\n", &rcast->addr.ipv6); #endif - b->bcast_addr.broadcast = TIPC_REPLICAST_SUPPORT; - list_add_rcu(&rcast->list, &ub->rcast.list); return 0; } @@ -361,9 +361,6 @@ static int tipc_udp_rcast_disc(struct tipc_bearer *b, struct sk_buff *skb) return 0; } - if (likely(tipc_udp_is_known_peer(b, &src))) - return 0; - return tipc_udp_rcast_add(b, &src); } @@ -644,9 +641,6 @@ int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr) return -EINVAL; } - if (tipc_udp_is_known_peer(b, &addr)) - return 0; - return tipc_udp_rcast_add(b, &addr); } @@ -679,6 +673,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, return -ENOMEM; INIT_LIST_HEAD(&ub->rcast.list); + spin_lock_init(&ub->rcast_lock); if (!attrs[TIPC_NLA_BEARER_UDP_OPTS]) goto err; @@ -819,10 +814,13 @@ static void cleanup_bearer(struct work_struct *work) struct udp_replicast *rcast, *tmp; struct tipc_net *tn; + spin_lock_bh(&ub->rcast_lock); list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { list_del_rcu(&rcast->list); call_rcu_hurry(&rcast->rcu, rcast_free_rcu); } + ub->disabled = true; + spin_unlock_bh(&ub->rcast_lock); tn = tipc_net(sock_net(ub->sk)); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 741aef09bfd3..37bb06a8e8f5 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -595,13 +595,15 @@ void tls_device_splice_eof(struct socket *sock) struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter iter = {}; - if (!tls_is_partially_sent_record(tls_ctx)) + if (!tls_is_partially_sent_record(tls_ctx) && + !tls_is_pending_open_record(tls_ctx)) return; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); - if (tls_is_partially_sent_record(tls_ctx)) { + if (tls_is_partially_sent_record(tls_ctx) || + tls_is_pending_open_record(tls_ctx)) { iov_iter_bvec(&iter, ITER_SOURCE, NULL, 0, 0); tls_push_data(sk, &iter, 0, 0, TLS_RECORD_TYPE_DATA); } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 09475007165b..8becad81279c 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -26,6 +26,13 @@ /* Threshold for detecting small packets to copy */ #define GOOD_COPY_LEN 128 +/* Max payload that can be collapsed into a single linear skb, using the same + * allocation threshold as virtio_vsock_alloc_skb() to avoid adding pressure + * on the page allocator. + */ +#define MAX_COLLAPSE_LEN \ + SKB_MAX_ORDER(VIRTIO_VSOCK_SKB_HEADROOM, PAGE_ALLOC_COSTLY_ORDER) + static void virtio_transport_cancel_close_work(struct vsock_sock *vsk, bool cancel_timeout); static s64 virtio_transport_has_space(struct virtio_vsock_sock *vvs); @@ -420,6 +427,145 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, return ret; } +static bool virtio_transport_can_collapse(struct sk_buff *skb) +{ + /* skbs that are partially consumed, mark a SEQPACKET message boundary, + * or are already large enough should not be collapsed: they either + * need special accounting, carry protocol state, or already have a + * good data-to-overhead ratio. + */ + if (VIRTIO_VSOCK_SKB_CB(skb)->offset) + return false; + if (le32_to_cpu(virtio_vsock_hdr(skb)->flags) & VIRTIO_VSOCK_SEQ_EOM) + return false; + if (skb->len >= MAX_COLLAPSE_LEN) + return false; + return true; +} + +/* Iterate through the packets in the queue starting from the current skb to + * count the number of bytes we can collapse. + */ +static unsigned int +virtio_transport_collapse_size(struct sk_buff *skb, struct sk_buff_head *queue) +{ + unsigned int target = skb->len - VIRTIO_VSOCK_SKB_CB(skb)->offset; + + while ((skb = skb_peek_next(skb, queue)) && + virtio_transport_can_collapse(skb)) { + unsigned int len = skb->len - VIRTIO_VSOCK_SKB_CB(skb)->offset; + + if (len > MAX_COLLAPSE_LEN - target) + return target; + + target += len; + } + + return target; +} + +/* Called under lock_sock to compact the receive queue by merging small skbs. + * @min_to_free: minimum number of skbs to eliminate from the queue. May free + * more to fill each collapsed skb to capacity. + */ +static void +virtio_transport_collapse_rx_queue(struct virtio_vsock_sock *vvs, + u32 min_to_free) +{ + struct sk_buff *skb, *next_skb, *new_skb = NULL; + struct sk_buff_head new_queue; + u32 saved = 0; + + __skb_queue_head_init(&new_queue); + + skb_queue_walk_safe(&vvs->rx_queue, skb, next_skb) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); + u32 src_off = VIRTIO_VSOCK_SKB_CB(skb)->offset; + u32 src_len = skb->len - src_off; + bool keep; + + keep = !virtio_transport_can_collapse(skb); + if (keep) { + /* Finalize pending collapsed skb to preserve packet + * ordering. + */ + if (new_skb) { + __skb_queue_tail(&new_queue, new_skb); + new_skb = NULL; + saved--; + } + goto next; + } + + /* Finalize if this packet won't fit in the remaining tailroom, + * so we can allocate a right-sized new_skb. + */ + if (new_skb && src_len > skb_tailroom(new_skb)) { + __skb_queue_tail(&new_queue, new_skb); + new_skb = NULL; + saved--; + } + + if (!new_skb) { + unsigned int alloc_size; + + /* Check after finalizing to opportunistically fill + * each collapsed skb to capacity, merging more skbs + * than strictly required. + */ + if (saved >= min_to_free) + break; + + alloc_size = virtio_transport_collapse_size(skb, &vvs->rx_queue); + + /* Only this skb's data is eligible, nothing to merge + * with. Keep as-is. + */ + if (alloc_size <= src_len) { + keep = true; + goto next; + } + + new_skb = virtio_vsock_alloc_linear_skb(alloc_size + + VIRTIO_VSOCK_SKB_HEADROOM, GFP_KERNEL); + if (!new_skb) + break; + + memcpy(virtio_vsock_hdr(new_skb), hdr, + sizeof(struct virtio_vsock_hdr)); + virtio_vsock_hdr(new_skb)->len = 0; + } + + /* Cannot fail since src_off/src_len are within bounds, but if + * it does, discard new_skb to avoid queuing corrupted data. + */ + if (WARN_ON_ONCE(skb_copy_bits(skb, src_off, + skb_put(new_skb, src_len), + src_len))) { + kfree_skb(new_skb); + new_skb = NULL; + break; + } + + le32_add_cpu(&virtio_vsock_hdr(new_skb)->len, src_len); + virtio_vsock_hdr(new_skb)->flags |= hdr->flags; + +next: + __skb_unlink(skb, &vvs->rx_queue); + if (keep) { + __skb_queue_tail(&new_queue, skb); + } else { + consume_skb(skb); + saved++; + } + } + + if (new_skb) + __skb_queue_tail(&new_queue, new_skb); + + skb_queue_splice(&new_queue, &vvs->rx_queue); +} + static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, u32 len) { @@ -1354,12 +1500,29 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, { struct virtio_vsock_sock *vvs = vsk->trans; bool can_enqueue, free_pkt = false; + u32 len, queue_max, queue_len; struct virtio_vsock_hdr *hdr; - u32 len; hdr = virtio_vsock_hdr(skb); len = le32_to_cpu(hdr->len); + /* virtio_transport_inc_rx_pkt() rejects packets when the per-skb + * overhead (skb_queue_len * SKB_TRUESIZE(0)) exceeds buf_alloc. + * Proactively collapse the queue before that happens. + * No rx_lock needed: lock_sock is held by caller, preventing + * concurrent enqueue or dequeue. + */ + queue_max = vvs->buf_alloc / SKB_TRUESIZE(0); + queue_len = skb_queue_len(&vvs->rx_queue); + if (queue_len >= queue_max) { + /* Walking a large queue may take a significant amount of time + * and cache misses, causing traffic burstiness. Limit the + * collapse to freeing room for this packet and the next one. + * It may free more to fill each collapsed skb to capacity. + */ + virtio_transport_collapse_rx_queue(vvs, queue_len + 2 - queue_max); + } + spin_lock_bh(&vvs->rx_lock); can_enqueue = virtio_transport_inc_rx_pkt(vvs, len); diff --git a/net/wireless/core.c b/net/wireless/core.c index 3dcf63b04c41..610238d723ff 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1335,6 +1335,7 @@ void wiphy_unregister(struct wiphy *wiphy) /* this has nothing to do now but make sure it's gone */ cancel_work_sync(&rdev->wiphy_work); + cancel_work_sync(&rdev->sched_scan_res_wk); cancel_work_sync(&rdev->rfkill_block); cancel_work_sync(&rdev->conn_work); flush_work(&rdev->event_work); @@ -1424,6 +1425,7 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, list_del_rcu(&wdev->list); synchronize_net(); rdev->devlist_generation++; + wiphy_work_cancel(wdev->wiphy, &wdev->disconnect_wk); cfg80211_mlme_purge_registrations(wdev); @@ -1613,7 +1615,7 @@ void cfg80211_init_wdev(struct wireless_dev *wdev) INIT_LIST_HEAD(&wdev->mgmt_registrations); INIT_LIST_HEAD(&wdev->pmsr_list); spin_lock_init(&wdev->pmsr_lock); - INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk); + wiphy_work_init(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk); #ifdef CONFIG_CFG80211_WEXT wdev->wext.default_key = -1; @@ -1637,7 +1639,7 @@ void cfg80211_init_wdev(struct wireless_dev *wdev) wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr) wdev->netdev->priv_flags |= IFF_DONT_BRIDGE; - INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk); + wiphy_work_init(&wdev->disconnect_wk, cfg80211_autodisconnect_wk); } void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, @@ -1743,11 +1745,11 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, break; case NETDEV_GOING_DOWN: cfg80211_leave(rdev, wdev, -1); - scoped_guard(wiphy, &rdev->wiphy) + scoped_guard(wiphy, &rdev->wiphy) { cfg80211_remove_links(wdev); - /* since we just did cfg80211_leave() nothing to do there */ - cancel_work_sync(&wdev->disconnect_wk); - cancel_work_sync(&wdev->pmsr_free_wk); + /* since we just did cfg80211_leave() nothing to do there */ + wiphy_work_cancel(wdev->wiphy, &wdev->disconnect_wk); + } break; case NETDEV_DOWN: wiphy_lock(&rdev->wiphy); diff --git a/net/wireless/core.h b/net/wireless/core.h index df47ed6208a5..ac6ce9f967ec 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -428,7 +428,7 @@ void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *peer_addr, const u8 *td_bitmap, u8 td_bitmap_len); int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); -void cfg80211_autodisconnect_wk(struct work_struct *work); +void cfg80211_autodisconnect_wk(struct wiphy *wiphy, struct wiphy_work *work); /* SME implementation */ void cfg80211_conn_work(struct work_struct *work); @@ -586,7 +586,7 @@ cfg80211_get_6ghz_power_type(const u8 *elems, size_t elems_len, void cfg80211_release_pmsr(struct wireless_dev *wdev, u32 portid); void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev); -void cfg80211_pmsr_free_wk(struct work_struct *work); +void cfg80211_pmsr_free_wk(struct wiphy *wiphy, struct wiphy_work *work); void cfg80211_remove_link(struct wireless_dev *wdev, unsigned int link_id); void cfg80211_remove_links(struct wireless_dev *wdev); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 2a2c173058ba..7824b7ac2770 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -32,15 +32,11 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, .timeout_reason = NL80211_TIMEOUT_UNSPECIFIED, .req_ie = data->req_ies, .req_ie_len = data->req_ies_len, - .resp_ie = mgmt->u.assoc_resp.variable, - .resp_ie_len = data->len - - offsetof(struct ieee80211_mgmt, - u.assoc_resp.variable), - .status = le16_to_cpu(mgmt->u.assoc_resp.status_code), .ap_mld_addr = data->ap_mld_addr, .assoc_encrypted = data->assoc_encrypted, }; unsigned int link_id; + bool is_s1g = false; for (link_id = 0; link_id < ARRAY_SIZE(data->links); link_id++) { cr.links[link_id].status = data->links[link_id].status; @@ -61,16 +57,32 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, if (cr.links[link_id].bss->channel->band == NL80211_BAND_S1GHZ) { WARN_ON(link_id); - cr.resp_ie = (u8 *)&mgmt->u.s1g_assoc_resp.variable; - cr.resp_ie_len = data->len - - offsetof(struct ieee80211_mgmt, - u.s1g_assoc_resp.variable); + is_s1g = true; } if (cr.ap_mld_addr) cr.valid_links |= BIT(link_id); } + if (is_s1g) { + if (data->len < offsetof(struct ieee80211_mgmt, + u.s1g_assoc_resp.variable)) + goto free_bss; + cr.resp_ie = (u8 *)&mgmt->u.s1g_assoc_resp.variable; + cr.resp_ie_len = data->len - + offsetof(struct ieee80211_mgmt, + u.s1g_assoc_resp.variable); + } else { + if (data->len < offsetof(struct ieee80211_mgmt, + u.assoc_resp.variable)) + goto free_bss; + cr.resp_ie = mgmt->u.assoc_resp.variable; + cr.resp_ie_len = data->len - + offsetof(struct ieee80211_mgmt, + u.assoc_resp.variable); + } + cr.status = le16_to_cpu(mgmt->u.assoc_resp.status_code); + trace_cfg80211_send_rx_assoc(dev, data); /* @@ -79,22 +91,24 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, * and got a reject -- we only try again with an assoc * frame instead of reassoc. */ - if (cfg80211_sme_rx_assoc_resp(wdev, cr.status)) { - for (link_id = 0; link_id < ARRAY_SIZE(data->links); link_id++) { - struct cfg80211_bss *bss = data->links[link_id].bss; - - if (!bss) - continue; - - cfg80211_unhold_bss(bss_from_pub(bss)); - cfg80211_put_bss(wiphy, bss); - } - return; - } + if (cfg80211_sme_rx_assoc_resp(wdev, cr.status)) + goto free_bss; nl80211_send_rx_assoc(rdev, dev, data); /* update current_bss etc., consumes the bss reference */ __cfg80211_connect_result(dev, &cr, cr.status == WLAN_STATUS_SUCCESS); + return; + +free_bss: + for (link_id = 0; link_id < ARRAY_SIZE(data->links); link_id++) { + struct cfg80211_bss *bss = data->links[link_id].bss; + + if (!bss) + continue; + + cfg80211_unhold_bss(bss_from_pub(bss)); + cfg80211_put_bss(wiphy, bss); + } } EXPORT_SYMBOL(cfg80211_rx_assoc_resp); @@ -151,19 +165,35 @@ void cfg80211_rx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct ieee80211_mgmt *mgmt = (void *)buf; + __le16 fc; lockdep_assert_wiphy(wdev->wiphy); - trace_cfg80211_rx_mlme_mgmt(dev, buf, len); + if (len < sizeof(fc)) + return; + + fc = mgmt->frame_control; - if (WARN_ON(len < 2)) + if (ieee80211_is_auth(fc)) { + if (len < offsetofend(struct ieee80211_mgmt, u.auth.status_code)) + return; + } else if (ieee80211_is_deauth(fc)) { + if (len < offsetofend(struct ieee80211_mgmt, u.deauth.reason_code)) + return; + } else if (ieee80211_is_disassoc(fc)) { + if (len < offsetofend(struct ieee80211_mgmt, u.disassoc.reason_code)) + return; + } else { return; + } + + trace_cfg80211_rx_mlme_mgmt(dev, buf, len); - if (ieee80211_is_auth(mgmt->frame_control)) + if (ieee80211_is_auth(fc)) cfg80211_process_auth(wdev, buf, len); - else if (ieee80211_is_deauth(mgmt->frame_control)) + else if (ieee80211_is_deauth(fc)) cfg80211_process_deauth(wdev, buf, len, false); - else if (ieee80211_is_disassoc(mgmt->frame_control)) + else cfg80211_process_disassoc(wdev, buf, len, false); } EXPORT_SYMBOL(cfg80211_rx_mlme_mgmt); @@ -216,15 +246,28 @@ void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len, { struct wireless_dev *wdev = dev->ieee80211_ptr; struct ieee80211_mgmt *mgmt = (void *)buf; + __le16 fc; lockdep_assert_wiphy(wdev->wiphy); - trace_cfg80211_tx_mlme_mgmt(dev, buf, len, reconnect); + if (len < sizeof(fc)) + return; - if (WARN_ON(len < 2)) + fc = mgmt->frame_control; + + if (ieee80211_is_deauth(fc)) { + if (len < offsetofend(struct ieee80211_mgmt, u.deauth.reason_code)) + return; + } else if (ieee80211_is_disassoc(fc)) { + if (len < offsetofend(struct ieee80211_mgmt, u.disassoc.reason_code)) + return; + } else { return; + } + + trace_cfg80211_tx_mlme_mgmt(dev, buf, len, reconnect); - if (ieee80211_is_deauth(mgmt->frame_control)) + if (ieee80211_is_deauth(fc)) cfg80211_process_deauth(wdev, buf, len, reconnect); else cfg80211_process_disassoc(wdev, buf, len, reconnect); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 53b4b3f76697..5adcb6bd0fc5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -461,7 +461,9 @@ nl80211_ftm_responder_policy[NL80211_FTM_RESP_ATTR_MAX + 1] = { static const struct nla_policy nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_REQ_ATTR_ASAP] = { .type = NLA_FLAG }, - [NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE] = { .type = NLA_U32 }, + [NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE] = + NLA_POLICY_RANGE(NLA_U32, NL80211_PREAMBLE_LEGACY, + NL80211_PREAMBLE_HE), [NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP] = NLA_POLICY_MAX(NLA_U8, 15), [NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD] = { .type = NLA_U16 }, @@ -630,7 +632,7 @@ nl80211_mbssid_config_policy[NL80211_MBSSID_CONFIG_ATTR_MAX + 1] = { [NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX] = { .type = NLA_U32 }, [NL80211_MBSSID_CONFIG_ATTR_EMA] = { .type = NLA_FLAG }, [NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID] = - NLA_POLICY_MAX(NLA_U8, IEEE80211_MLD_MAX_NUM_LINKS), + NLA_POLICY_RANGE(NLA_U8, 0, IEEE80211_MLD_MAX_NUM_LINKS - 1), }; static const struct nla_policy @@ -6510,7 +6512,8 @@ static int nl80211_parse_mbssid_config(struct wiphy *wiphy, } static struct cfg80211_mbssid_elems * -nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) +nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs, + struct netlink_ext_ack *extack) { struct nlattr *nl_elems; struct cfg80211_mbssid_elems *elems; @@ -6521,6 +6524,12 @@ nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) return ERR_PTR(-EINVAL); nla_for_each_nested(nl_elems, attrs, rem_elems) { + int ret; + + ret = validate_ie_attr(nl_elems, extack); + if (ret) + return ERR_PTR(ret); + if (num_elems >= 255) return ERR_PTR(-EINVAL); num_elems++; @@ -6787,7 +6796,8 @@ static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, if (attrs[NL80211_ATTR_MBSSID_ELEMS]) { struct cfg80211_mbssid_elems *mbssid = nl80211_parse_mbssid_elems(&rdev->wiphy, - attrs[NL80211_ATTR_MBSSID_ELEMS]); + attrs[NL80211_ATTR_MBSSID_ELEMS], + extack); if (IS_ERR(mbssid)) return PTR_ERR(mbssid); @@ -6803,8 +6813,10 @@ static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, if (IS_ERR(rnr)) return PTR_ERR(rnr); - if (rnr && rnr->cnt < bcn->mbssid_ies->cnt) + if (rnr && rnr->cnt < bcn->mbssid_ies->cnt) { + kfree(rnr); return -EINVAL; + } bcn->rnr_ies = rnr; } @@ -22942,7 +22954,8 @@ static int nl80211_netlink_notify(struct notifier_block * nb, wdev->nl_owner_dead = true; schedule_work(&rdev->destroy_work); } else if (wdev->conn_owner_nlportid == notify->portid) { - schedule_work(&wdev->disconnect_wk); + wiphy_work_queue(wdev->wiphy, + &wdev->disconnect_wk); } cfg80211_release_pmsr(wdev, notify->portid); diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index c8447448f3a5..d1e2fae5bc0e 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -125,6 +125,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI], "FTM: LCI request not supported"); + return -EOPNOTSUPP; } out->ftm.request_civicloc = @@ -133,6 +134,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC], "FTM: civic location request not supported"); + return -EOPNOTSUPP; } out->ftm.trigger_based = @@ -261,8 +263,9 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, "FTM: nominal time is required for PD NTB ranging"); return -EINVAL; } - out->ftm.nominal_time = - nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NOMINAL_TIME]); + if (tb[NL80211_PMSR_FTM_REQ_ATTR_NOMINAL_TIME]) + out->ftm.nominal_time = + nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NOMINAL_TIME]); if (tb[NL80211_PMSR_FTM_REQ_ATTR_MIN_TIME_BETWEEN_MEASUREMENTS]) out->ftm.min_time_between_measurements = @@ -310,6 +313,7 @@ static int pmsr_parse_peer(struct cfg80211_registered_device *rdev, { struct nlattr *tb[NL80211_PMSR_PEER_ATTR_MAX + 1]; struct nlattr *req[NL80211_PMSR_REQ_ATTR_MAX + 1]; + bool have_measurement_type = false; struct nlattr *treq; int err, rem; @@ -376,6 +380,14 @@ static int pmsr_parse_peer(struct cfg80211_registered_device *rdev, } nla_for_each_nested(treq, req[NL80211_PMSR_REQ_ATTR_DATA], rem) { + if (have_measurement_type) { + NL_SET_ERR_MSG_ATTR(info->extack, treq, + "multiple measurement types in request data"); + return -EINVAL; + } + + have_measurement_type = true; + switch (nla_type(treq)) { case NL80211_PMSR_TYPE_FTM: err = pmsr_parse_ftm(rdev, treq, out, info); @@ -385,10 +397,16 @@ static int pmsr_parse_peer(struct cfg80211_registered_device *rdev, "unsupported measurement type"); err = -EINVAL; } + if (err) + return err; } - if (err) - return err; + if (!have_measurement_type) { + NL_SET_ERR_MSG_ATTR(info->extack, + req[NL80211_PMSR_REQ_ATTR_DATA], + "missing measurement type in request data"); + return -EINVAL; + } return 0; } @@ -427,6 +445,11 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) } } + if (!count) { + NL_SET_ERR_MSG_ATTR(info->extack, peers, "No peers specified"); + return -EINVAL; + } + req = kzalloc_flex(*req, peers, count); if (!req) return -ENOMEM; @@ -807,13 +830,11 @@ static void cfg80211_pmsr_process_abort(struct wireless_dev *wdev) } } -void cfg80211_pmsr_free_wk(struct work_struct *work) +void cfg80211_pmsr_free_wk(struct wiphy *wiphy, struct wiphy_work *work) { struct wireless_dev *wdev = container_of(work, struct wireless_dev, pmsr_free_wk); - guard(wiphy)(wdev->wiphy); - cfg80211_pmsr_process_abort(wdev); } @@ -829,7 +850,7 @@ void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) } spin_unlock_bh(&wdev->pmsr_lock); - cancel_work_sync(&wdev->pmsr_free_wk); + wiphy_work_cancel(wdev->wiphy, &wdev->pmsr_free_wk); if (found) cfg80211_pmsr_process_abort(wdev); @@ -844,7 +865,7 @@ void cfg80211_release_pmsr(struct wireless_dev *wdev, u32 portid) list_for_each_entry(req, &wdev->pmsr_list, list) { if (req->nl_portid == portid) { req->nl_portid = 0; - schedule_work(&wdev->pmsr_free_wk); + wiphy_work_queue(wdev->wiphy, &wdev->pmsr_free_wk); } } spin_unlock_bh(&wdev->pmsr_lock); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 05b7dc6b766c..071083cc3367 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -205,7 +205,7 @@ bool cfg80211_is_element_inherited(const struct element *elem, return true; if (elem->id == WLAN_EID_EXTENSION) { - if (!ext_id_len) + if (!ext_id_len || !elem->datalen) return true; loop_len = ext_id_len; list = &non_inherit_elem->data[3 + id_len]; @@ -326,8 +326,11 @@ cfg80211_gen_new_ie(const u8 *ie, size_t ielen, /* For ML probe response, match the MLE in the frame body with * MLD id being 'bssid_index' */ - if (parent->id == WLAN_EID_EXTENSION && parent->datalen > 1 && + if (parent->id == WLAN_EID_EXTENSION && parent->data[0] == WLAN_EID_EXT_EHT_MULTI_LINK && + ieee80211_mle_type_ok(parent->data + 1, + IEEE80211_ML_CONTROL_TYPE_BASIC, + parent->datalen - 1) && bssid_index == ieee80211_mle_get_mld_id(parent->data + 1)) { if (!cfg80211_copy_elem_with_frags(parent, ie, ielen, @@ -3311,14 +3314,15 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, bssid = ext->u.s1g_beacon.sa; capability = le16_to_cpu(compat->compat_info); beacon_interval = le16_to_cpu(compat->beacon_int); + tsf = le32_to_cpu(ext->u.s1g_beacon.timestamp); + tsf |= (u64)le32_to_cpu(compat->tsf_completion) << 32; } else { bssid = mgmt->bssid; beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int); capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); + tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp); } - tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp); - if (ieee80211_is_probe_resp(mgmt->frame_control)) ftype = CFG80211_BSS_FTYPE_PRESP; else if (ext) @@ -3612,8 +3616,10 @@ int cfg80211_wext_siwscan(struct net_device *dev, /* translate "Scan for SSID" request */ if (wreq) { if (wrqu->data.flags & IW_SCAN_THIS_ESSID) { - if (wreq->essid_len > IEEE80211_MAX_SSID_LEN) - return -EINVAL; + if (wreq->essid_len > IEEE80211_MAX_SSID_LEN) { + err = -EINVAL; + goto out; + } memcpy(creq->req.ssids[0].ssid, wreq->essid, wreq->essid_len); creq->req.ssids[0].ssid_len = wreq->essid_len; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index b451df3096dd..2a719b5c487e 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1578,13 +1578,11 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, * Used to clean up after the connection / connection attempt owner socket * disconnects */ -void cfg80211_autodisconnect_wk(struct work_struct *work) +void cfg80211_autodisconnect_wk(struct wiphy *wiphy, struct wiphy_work *work) { struct wireless_dev *wdev = container_of(work, struct wireless_dev, disconnect_wk); - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - - guard(wiphy)(wdev->wiphy); + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); if (wdev->conn_owner_nlportid) { switch (wdev->iftype) { diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index c31d2af5dd22..8aae9273b7c1 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1768,15 +1768,19 @@ void x25_kill_by_neigh(struct x25_neigh *nb) { struct sock *s; +again: write_lock_bh(&x25_list_lock); sk_for_each(s, &x25_list) { if (x25_sk(s)->neighbour == nb) { + sock_hold(s); write_unlock_bh(&x25_list_lock); lock_sock(s); - x25_disconnect(s, ENETUNREACH, 0, 0); + if (x25_sk(s)->neighbour == nb) + x25_disconnect(s, ENETUNREACH, 0, 0); release_sock(s); - write_lock_bh(&x25_list_lock); + sock_put(s); + goto again; } } write_unlock_bh(&x25_list_lock); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 630f3dd31cc5..f153bf695b9d 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -182,7 +182,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur err = x->type_offload->xmit(x, skb, esp_features); if (err) { if (err == -EINPROGRESS) - return NULL; + return ERR_PTR(-EINPROGRESS); XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); kfree_skb(skb); @@ -224,7 +224,15 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur pskb = skb2; } - return skb; + /* skb_gso_segment() set skb->prev to the last segment, but async + * crypto may have stolen it above without updating ->prev. Repoint + * it at the last retained segment so validate_xmit_skb_list() does + * not chain onto a segment now owned by the crypto engine. + */ + if (skb) + skb->prev = pskb; + + return skb ? skb : ERR_PTR(-EINPROGRESS); } EXPORT_SYMBOL_GPL(validate_xmit_xfrm); @@ -313,6 +321,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, } xso->dev = dev; + xso->ifindex = dev->ifindex; netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC); if (xuo->flags & XFRM_OFFLOAD_INBOUND) diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c index ad810d1f97c0..597aedeac26e 100644 --- a/net/xfrm/xfrm_iptfs.c +++ b/net/xfrm/xfrm_iptfs.c @@ -480,6 +480,7 @@ static int iptfs_skb_add_frags(struct sk_buff *skb, } __skb_frag_ref(tofrag); shinfo->nr_frags++; + shinfo->flags |= SKBFL_SHARED_FRAG; /* see if we are done */ fraglen = tofrag->len; diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c index 458931062a04..eb1b6f67739e 100644 --- a/net/xfrm/xfrm_nat_keepalive.c +++ b/net/xfrm/xfrm_nat_keepalive.c @@ -55,8 +55,10 @@ static int nat_keepalive_send_ipv4(struct sk_buff *skb, ka->encap_sport, sock_net_uid(net, NULL)); rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) + if (IS_ERR(rt)) { + kfree_skb(skb); return PTR_ERR(rt); + } skb_dst_set(skb, &rt->dst); @@ -101,6 +103,7 @@ static int nat_keepalive_send_ipv6(struct sk_buff *skb, dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); if (IS_ERR(dst)) { local_unlock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock); + kfree_skb(skb); return PTR_ERR(dst); } @@ -118,7 +121,6 @@ static void nat_keepalive_send(struct nat_keepalive *ka) sizeof(struct ipv6hdr)) + sizeof(struct udphdr); const u8 nat_ka_payload = 0xFF; - int err = -EAFNOSUPPORT; struct sk_buff *skb; struct udphdr *uh; @@ -140,16 +142,17 @@ static void nat_keepalive_send(struct nat_keepalive *ka) switch (ka->family) { case AF_INET: - err = nat_keepalive_send_ipv4(skb, ka); + nat_keepalive_send_ipv4(skb, ka); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: - err = nat_keepalive_send_ipv6(skb, ka, uh); + nat_keepalive_send_ipv6(skb, ka, uh); break; #endif - } - if (err) + default: kfree_skb(skb); + break; + } } struct nat_keepalive_work_ctx { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7ef861a0e823..932a313b9460 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1329,8 +1329,8 @@ static void xfrm_hash_rebuild(struct work_struct *work) } } - if (policy->selector.prefixlen_d < dbits || - policy->selector.prefixlen_s < sbits) + if (policy->selector.prefixlen_d >= dbits && + policy->selector.prefixlen_s >= sbits) continue; bin = xfrm_policy_inexact_alloc_bin(policy, dir); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index c58cd024e3c6..36a4f6793ede 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1547,6 +1547,7 @@ found: xso->type = XFRM_DEV_OFFLOAD_PACKET; xso->dir = xdo->dir; xso->dev = dev; + xso->ifindex = dev->ifindex; xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ; netdev_hold(dev, &xso->dev_tracker, GFP_ATOMIC); error = dev->xfrmdev_ops->xdo_dev_state_add(dev, x, @@ -2071,8 +2072,11 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig, x->mode_cbs = orig->mode_cbs; if (x->mode_cbs && x->mode_cbs->clone_state) { - if (x->mode_cbs->clone_state(x, orig)) + if (x->mode_cbs->clone_state(x, orig)) { + if (!x->mode_data) + x->mode_cbs = NULL; goto error; + } } x->props.reqid = m->new_reqid; @@ -3010,7 +3014,7 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) if (sockptr_is_null(optval) && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); - __sk_dst_reset(sk); + sk_dst_reset(sk); return 0; } @@ -3050,7 +3054,7 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) if (err >= 0) { xfrm_sk_policy_insert(sk, err, pol); xfrm_pol_put(pol); - __sk_dst_reset(sk); + sk_dst_reset(sk); err = 0; } @@ -3291,6 +3295,8 @@ int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) if (x->mode_cbs->init_state) err = x->mode_cbs->init_state(x); module_put(x->mode_cbs->owner); + if (err && !x->mode_data) + x->mode_cbs = NULL; } error: return err; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 6384795ee6b2..d6db63304ba6 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1201,17 +1201,26 @@ static int copy_sec_ctx(struct xfrm_sec_ctx *s, struct sk_buff *skb) return 0; } -static void xso_to_xuo(const struct xfrm_dev_offload *xso, - struct xfrm_user_offload *xuo) +static void xso_to_xuo_ifindex(const struct xfrm_dev_offload *xso, int ifindex, + struct xfrm_user_offload *xuo) { - xuo->ifindex = xso->dev->ifindex; + xuo->ifindex = ifindex; if (xso->dir == XFRM_DEV_OFFLOAD_IN) xuo->flags = XFRM_OFFLOAD_INBOUND; if (xso->type == XFRM_DEV_OFFLOAD_PACKET) xuo->flags |= XFRM_OFFLOAD_PACKET; } -static int copy_user_offload(struct xfrm_dev_offload *xso, struct sk_buff *skb) +#ifdef CONFIG_XFRM_MIGRATE +static void xso_to_xuo(const struct xfrm_dev_offload *xso, + struct xfrm_user_offload *xuo) +{ + xso_to_xuo_ifindex(xso, xso->dev->ifindex, xuo); +} +#endif + +static int copy_user_offload_ifindex(const struct xfrm_dev_offload *xso, + int ifindex, struct sk_buff *skb) { struct xfrm_user_offload *xuo; struct nlattr *attr; @@ -1222,11 +1231,22 @@ static int copy_user_offload(struct xfrm_dev_offload *xso, struct sk_buff *skb) xuo = nla_data(attr); memset(xuo, 0, sizeof(*xuo)); - xso_to_xuo(xso, xuo); + xso_to_xuo_ifindex(xso, ifindex, xuo); return 0; } +static int copy_user_offload(struct xfrm_dev_offload *xso, struct sk_buff *skb) +{ + return copy_user_offload_ifindex(xso, xso->dev->ifindex, skb); +} + +static int copy_user_state_offload(const struct xfrm_dev_offload *xso, + struct sk_buff *skb) +{ + return copy_user_offload_ifindex(xso, READ_ONCE(xso->ifindex), skb); +} + static bool xfrm_redact(void) { return IS_ENABLED(CONFIG_SECURITY) && @@ -1433,8 +1453,8 @@ static int copy_to_user_state_extra(struct xfrm_state *x, &x->replay); if (ret) goto out; - if(x->xso.dev) - ret = copy_user_offload(&x->xso, skb); + if (READ_ONCE(x->xso.dev)) + ret = copy_user_state_offload(&x->xso, skb); if (ret) goto out; if (x->if_id) { @@ -2104,13 +2124,12 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, switch (ut[i].mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: + case XFRM_MODE_IPTFS: if (ut[i].optional && dir == XFRM_POLICY_OUT) { NL_SET_ERR_MSG(extack, "Mode in optional template not allowed in outbound policy"); return -EINVAL; } break; - case XFRM_MODE_IPTFS: - break; default: if (ut[i].family != prev_family) { NL_SET_ERR_MSG(extack, "Mode in template doesn't support a family change"); @@ -4046,8 +4065,8 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) l += nla_total_size(sizeof(*x->coaddr)); if (x->props.extra_flags) l += nla_total_size(sizeof(x->props.extra_flags)); - if (x->xso.dev) - l += nla_total_size(sizeof(struct xfrm_user_offload)); + if (READ_ONCE(x->xso.dev)) + l += nla_total_size(sizeof(struct xfrm_user_offload)); if (x->props.smark.v | x->props.smark.m) { l += nla_total_size(sizeof(x->props.smark.v)); l += nla_total_size(sizeof(x->props.smark.m)); diff --git a/security/landlock/net.c b/security/landlock/net.c index cbff59ec3aba..46c17116fcf4 100644 --- a/security/landlock/net.c +++ b/security/landlock/net.c @@ -351,6 +351,14 @@ static int hook_socket_sendmsg(struct socket *const sock, access_mask_t access_request; int ret = 0; + if ((msg->msg_flags & MSG_FASTOPEN) && address && sk_is_tcp(sock->sk)) { + ret = current_check_access_socket( + sock, address, addrlen, LANDLOCK_ACCESS_NET_CONNECT_TCP, + true); + if (ret != 0) + return ret; + } + if (sk_is_udp(sock->sk)) access_request = LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP; else diff --git a/security/landlock/ruleset.h b/security/landlock/ruleset.h index 61f3c253d5c9..0437adf17428 100644 --- a/security/landlock/ruleset.h +++ b/security/landlock/ruleset.h @@ -35,8 +35,8 @@ struct landlock_layer { */ struct { /** - * @quiet: Suppresses denial logs for the object covered by this - * rule in this domain. For filesystem rules, this inherits + * @flags.quiet: Suppresses denial logs for the object covered by + * this rule in this domain. For filesystem rules, this inherits * down the file hierarchy. */ u8 quiet : 1; diff --git a/security/landlock/task.c b/security/landlock/task.c index 7ddf211f75c3..360d226d0f51 100644 --- a/security/landlock/task.c +++ b/security/landlock/task.c @@ -95,8 +95,7 @@ static int hook_ptrace_access_check(struct task_struct *const child, if (!parent_subject) return 0; - scoped_guard(rcu) - { + scoped_guard(rcu) { const struct landlock_ruleset *const child_dom = landlock_get_task_domain(child); err = domain_ptrace(parent_subject->domain, child_dom); @@ -370,8 +369,7 @@ static int hook_task_kill(struct task_struct *const p, if (!subject) return 0; - scoped_guard(rcu) - { + scoped_guard(rcu) { is_scoped = domain_is_scoped(subject->domain, landlock_get_task_domain(p), signal_scope.scope); @@ -422,8 +420,7 @@ static int hook_file_send_sigiotask(struct task_struct *tsk, if (task_tgid(tsk) == landlock_file(fown->file)->fown_tg) return 0; - scoped_guard(rcu) - { + scoped_guard(rcu) { is_scoped = domain_is_scoped(subject->domain, landlock_get_task_domain(tsk), signal_scope.scope); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 70a3388c047d..8d6945edae7a 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3969,9 +3969,9 @@ static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd, static int default_noexec __ro_after_init; -static int __file_map_prot_check(const struct cred *cred, - const struct file *file, unsigned long prot, - bool shared, bool bf_user_file) +static int __file_map_prot_check(const struct file *file, unsigned long prot, + bool shared, bool mounter_check, + bool bf_user_file) { struct inode *inode = NULL; bool prot_exec = prot & PROT_EXEC; @@ -3984,10 +3984,10 @@ static int __file_map_prot_check(const struct cred *cred, inode = file_inode(file); } - if (default_noexec && prot_exec && + if (!mounter_check && default_noexec && prot_exec && (!file || IS_PRIVATE(inode) || (!shared && prot_write))) { int rc; - u32 sid = cred_sid(cred); + u32 sid = current_sid(); /* * We are making executable an anonymous mapping or a private @@ -4000,6 +4000,8 @@ static int __file_map_prot_check(const struct cred *cred, } if (file) { + const struct cred *cred = mounter_check ? + file->f_cred : current_cred(); /* "read" always possible, "write" only if shared */ u32 av = FILE__READ; if (shared && prot_write) @@ -4013,11 +4015,11 @@ static int __file_map_prot_check(const struct cred *cred, return 0; } -static inline int file_map_prot_check(const struct cred *cred, - const struct file *file, - unsigned long prot, bool shared) +static inline int file_map_prot_check(const struct file *file, + unsigned long prot, bool shared, + bool mounter_check) { - return __file_map_prot_check(cred, file, prot, shared, false); + return __file_map_prot_check(file, prot, shared, mounter_check, false); } static int selinux_mmap_addr(unsigned long addr) @@ -4033,12 +4035,14 @@ static int selinux_mmap_addr(unsigned long addr) return rc; } -static int selinux_mmap_file_common(const struct cred *cred, struct file *file, - unsigned long prot, bool shared) +static int selinux_mmap_file_common(struct file *file, unsigned long prot, + bool shared, bool mounter_check) { if (file) { int rc; struct common_audit_data ad; + const struct cred *cred = mounter_check ? + file->f_cred : current_cred(); ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; @@ -4047,15 +4051,16 @@ static int selinux_mmap_file_common(const struct cred *cred, struct file *file, return rc; } - return file_map_prot_check(cred, file, prot, shared); + return file_map_prot_check(file, prot, shared, mounter_check); } static int selinux_mmap_file(struct file *file, unsigned long reqprot __always_unused, unsigned long prot, unsigned long flags) { - return selinux_mmap_file_common(current_cred(), file, prot, - (flags & MAP_TYPE) == MAP_SHARED); + return selinux_mmap_file_common(file, prot, + (flags & MAP_TYPE) == MAP_SHARED, + false); } /** @@ -4087,8 +4092,9 @@ static int selinux_mmap_backing_file(struct vm_area_struct *vma, if (vma->vm_flags & VM_EXEC) prot |= PROT_EXEC; - return selinux_mmap_file_common(backing_file->f_cred, backing_file, - prot, vma->vm_flags & VM_SHARED); + return selinux_mmap_file_common(backing_file, prot, + vma->vm_flags & VM_SHARED, + true); } static int selinux_file_mprotect(struct vm_area_struct *vma, @@ -4149,11 +4155,11 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, } } - rc = __file_map_prot_check(cred, file, prot, shared, backing_file); + rc = __file_map_prot_check(file, prot, shared, false, backing_file); if (rc) return rc; if (backing_file) { - rc = file_map_prot_check(file->f_cred, file, prot, shared); + rc = file_map_prot_check(file, prot, shared, true); if (rc) return rc; } diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c index 4cd7211ccf48..419288eec4bb 100644 --- a/sound/core/seq/seq_timer.c +++ b/sound/core/seq/seq_timer.c @@ -61,12 +61,23 @@ struct snd_seq_timer *snd_seq_timer_new(void) void snd_seq_timer_delete(struct snd_seq_timer **tmr) { struct snd_seq_timer *t = *tmr; - *tmr = NULL; + struct snd_timer_instance *ti; if (t == NULL) { pr_debug("ALSA: seq: snd_seq_timer_delete() called with NULL timer\n"); return; } + + scoped_guard(spinlock_irq, &t->lock) { + ti = t->timeri; + t->timeri = NULL; + } + if (ti) { + snd_timer_close(ti); + snd_timer_instance_free(ti); + } + + *tmr = NULL; t->running = 0; /* reset time */ diff --git a/sound/core/timer.c b/sound/core/timer.c index 51c6ac4df9f4..07ef127b29e1 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -489,10 +489,20 @@ static void snd_timer_close_locked(struct snd_timer_instance *timeri, snd_timer_stop(timeri); if (timer) { + struct snd_timer_instance *slave; + bool busy; + timer->num_instances--; - /* wait, until the active callback is finished */ + /* unqueue then drain the slaves' callbacks before remove_slave_links() severs them */ spin_lock_irq(&timer->lock); - while (timeri->flags & SNDRV_TIMER_IFLG_CALLBACK) { + list_for_each_entry(slave, &timeri->slave_list_head, open_list) + list_del_init(&slave->ack_list); + for (;;) { + busy = timeri->flags & SNDRV_TIMER_IFLG_CALLBACK; + list_for_each_entry(slave, &timeri->slave_list_head, open_list) + busy |= slave->flags & SNDRV_TIMER_IFLG_CALLBACK; + if (!busy) + break; spin_unlock_irq(&timer->lock); udelay(10); spin_lock_irq(&timer->lock); @@ -927,12 +937,15 @@ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left) ack_list_head = &timer->ack_list_head; else ack_list_head = &timer->sack_list_head; - if (list_empty(&ti->ack_list)) + /* don't requeue an instance whose callback is still running */ + if (list_empty(&ti->ack_list) && + !(ti->flags & SNDRV_TIMER_IFLG_CALLBACK)) list_add_tail(&ti->ack_list, ack_list_head); list_for_each_entry(ts, &ti->slave_active_head, active_list) { ts->pticks = ti->pticks; ts->resolution = resolution; - if (list_empty(&ts->ack_list)) + if (list_empty(&ts->ack_list) && + !(ts->flags & SNDRV_TIMER_IFLG_CALLBACK)) list_add_tail(&ts->ack_list, ack_list_head); } } diff --git a/sound/firewire/bebob/bebob.h b/sound/firewire/bebob/bebob.h index 4d73ecb30d79..41e019b9e24e 100644 --- a/sound/firewire/bebob/bebob.h +++ b/sound/firewire/bebob/bebob.h @@ -13,7 +13,6 @@ #include <linux/firewire.h> #include <linux/firewire-constants.h> #include <linux/module.h> -#include <linux/mod_devicetable.h> #include <linux/delay.h> #include <linux/slab.h> #include <linux/sched/signal.h> diff --git a/sound/firewire/dice/dice.h b/sound/firewire/dice/dice.h index 7744ea6a0791..5abae26d2bba 100644 --- a/sound/firewire/dice/dice.h +++ b/sound/firewire/dice/dice.h @@ -17,7 +17,6 @@ #include <linux/firewire-constants.h> #include <linux/jiffies.h> #include <linux/module.h> -#include <linux/mod_devicetable.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/spinlock.h> diff --git a/sound/firewire/digi00x/digi00x.h b/sound/firewire/digi00x/digi00x.h index 82b647d383c5..60d17a6fddd1 100644 --- a/sound/firewire/digi00x/digi00x.h +++ b/sound/firewire/digi00x/digi00x.h @@ -12,7 +12,6 @@ #include <linux/device.h> #include <linux/firewire.h> #include <linux/module.h> -#include <linux/mod_devicetable.h> #include <linux/delay.h> #include <linux/slab.h> #include <linux/sched/signal.h> diff --git a/sound/firewire/fireface/ff.h b/sound/firewire/fireface/ff.h index 7e42f5778a8a..c9c35c67db27 100644 --- a/sound/firewire/fireface/ff.h +++ b/sound/firewire/fireface/ff.h @@ -12,7 +12,6 @@ #include <linux/firewire.h> #include <linux/firewire-constants.h> #include <linux/module.h> -#include <linux/mod_devicetable.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/compat.h> diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h index c8d5879efe28..a8aadf754e72 100644 --- a/sound/firewire/fireworks/fireworks.h +++ b/sound/firewire/fireworks/fireworks.h @@ -13,7 +13,6 @@ #include <linux/firewire.h> #include <linux/firewire-constants.h> #include <linux/module.h> -#include <linux/mod_devicetable.h> #include <linux/delay.h> #include <linux/slab.h> #include <linux/sched/signal.h> diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h index c66be0a89ccf..7333a76b50aa 100644 --- a/sound/firewire/motu/motu.h +++ b/sound/firewire/motu/motu.h @@ -12,7 +12,6 @@ #include <linux/firewire.h> #include <linux/firewire-constants.h> #include <linux/module.h> -#include <linux/mod_devicetable.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/compat.h> diff --git a/sound/firewire/oxfw/oxfw.h b/sound/firewire/oxfw/oxfw.h index 39ea9a6dde33..aeb83e1595b7 100644 --- a/sound/firewire/oxfw/oxfw.h +++ b/sound/firewire/oxfw/oxfw.h @@ -9,7 +9,6 @@ #include <linux/firewire.h> #include <linux/firewire-constants.h> #include <linux/module.h> -#include <linux/mod_devicetable.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/compat.h> diff --git a/sound/firewire/tascam/tascam.h b/sound/firewire/tascam/tascam.h index d07ffcb27be6..9c42c9b48f21 100644 --- a/sound/firewire/tascam/tascam.h +++ b/sound/firewire/tascam/tascam.h @@ -12,7 +12,6 @@ #include <linux/firewire.h> #include <linux/firewire-constants.h> #include <linux/module.h> -#include <linux/mod_devicetable.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/compat.h> diff --git a/sound/hda/codecs/conexant.c b/sound/hda/codecs/conexant.c index 3d92262763f6..40da2832ba66 100644 --- a/sound/hda/codecs/conexant.c +++ b/sound/hda/codecs/conexant.c @@ -162,9 +162,6 @@ static void cx_fixup_headset_recog(struct hda_codec *codec) { unsigned int mic_present; - /* fix some headset type recognize fail issue, such as EDIFIER headset */ - /* set micbias output current comparator threshold from 66% to 55%. */ - snd_hda_codec_write(codec, 0x1c, 0, 0x320, 0x010); /* set OFF voltage for DFET from -1.2V to -0.8V, set headset micbias register * value adjustment trim from 2.2K ohms to 2.0K ohms. */ diff --git a/sound/hda/codecs/hdmi/hdmi.c b/sound/hda/codecs/hdmi/hdmi.c index 1f4d646724ed..a4a2f2f0540c 100644 --- a/sound/hda/codecs/hdmi/hdmi.c +++ b/sound/hda/codecs/hdmi/hdmi.c @@ -1688,6 +1688,9 @@ int snd_hda_hdmi_generic_pcm_prepare(struct hda_pcm_stream *hinfo, per_pin->channels = substream->runtime->channels; per_pin->setup = true; + if (spec->ops.prepare) + spec->ops.prepare(codec, per_pin); + if (get_wcaps(codec, cvt_nid) & AC_WCAP_STRIPE) { stripe = snd_hdac_get_stream_stripe_ctl(&codec->bus->core, substream); diff --git a/sound/hda/codecs/hdmi/hdmi_local.h b/sound/hda/codecs/hdmi/hdmi_local.h index 548241ad3fa9..dce9a335cff2 100644 --- a/sound/hda/codecs/hdmi/hdmi_local.h +++ b/sound/hda/codecs/hdmi/hdmi_local.h @@ -74,6 +74,15 @@ struct hdmi_ops { hda_nid_t pin_nid, int dev_id, u32 stream_tag, int format); + /* + * Optional hook invoked at the beginning of the PCM prepare + * sequence, before the audio infoframe and stream format are + * (re)programmed. Used to disable keep-alive / silent stream so + * that the format change is not done while keep-alive is active. + */ + void (*prepare)(struct hda_codec *codec, + struct hdmi_spec_per_pin *per_pin); + void (*pin_cvt_fixup)(struct hda_codec *codec, struct hdmi_spec_per_pin *per_pin, hda_nid_t cvt_nid); diff --git a/sound/hda/codecs/hdmi/intelhdmi.c b/sound/hda/codecs/hdmi/intelhdmi.c index 6a7882544ab7..73141046d502 100644 --- a/sound/hda/codecs/hdmi/intelhdmi.c +++ b/sound/hda/codecs/hdmi/intelhdmi.c @@ -418,6 +418,28 @@ static void intel_not_share_assigned_cvt_nid(struct hda_codec *codec, intel_not_share_assigned_cvt(codec, pin_nid, dev_id, mux_idx); } +/* + * prepare ops override for HSW+ + * + * Disable keep-alive before the converter format and audio infoframe are + * reprogrammed by the PCM prepare sequence. Changing the audio format (e.g. + * the channel count when switching to multichannel PCM) while a keep-alive + * stream is active is not safe, so release keep-alive here, early in the + * sequence. It is re-enabled once the new stream has been set up, in + * i915_hsw_setup_stream(). + */ +static void i915_hsw_prepare(struct hda_codec *codec, + struct hdmi_spec_per_pin *per_pin) +{ + struct hdmi_spec *spec = codec->spec; + + if (spec->silent_stream_type == SILENT_STREAM_KAE && per_pin->silent_stream) { + silent_stream_set_kae(codec, per_pin, false); + /* wait for pending transfers in codec to clear */ + usleep_range(100, 200); + } +} + /* setup_stream ops override for HSW+ */ static int i915_hsw_setup_stream(struct hda_codec *codec, hda_nid_t cvt_nid, hda_nid_t pin_nid, int dev_id, u32 stream_tag, @@ -435,15 +457,16 @@ static int i915_hsw_setup_stream(struct hda_codec *codec, hda_nid_t cvt_nid, haswell_verify_D0(codec, cvt_nid, pin_nid); - if (spec->silent_stream_type == SILENT_STREAM_KAE && per_pin && per_pin->silent_stream) { - silent_stream_set_kae(codec, per_pin, false); - /* wait for pending transfers in codec to clear */ - usleep_range(100, 200); - } - res = snd_hda_hdmi_setup_stream(codec, cvt_nid, pin_nid, dev_id, stream_tag, format); + /* + * Keep-alive was disabled in i915_hsw_prepare(), re-enable it now. + * The pin lookup above resolves to the same per_pin that prepare + * used (pin_nid comes from that per_pin), so this stays balanced; a + * NULL per_pin only occurs on a lookup failure that also implies no + * active keep-alive stream to restore. + */ if (spec->silent_stream_type == SILENT_STREAM_KAE && per_pin && per_pin->silent_stream) { usleep_range(100, 200); silent_stream_set_kae(codec, per_pin, true); @@ -607,6 +630,7 @@ static int intel_hsw_common_init(struct hda_codec *codec, hda_nid_t vendor_nid, codec->depop_delay = 0; codec->auto_runtime_pm = 1; + spec->ops.prepare = i915_hsw_prepare; spec->ops.setup_stream = i915_hsw_setup_stream; spec->ops.pin_cvt_fixup = i915_pin_cvt_fixup; spec->ops.silent_stream = i915_set_silent_stream; diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index f7700713dc62..379e1458f4ac 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -3773,6 +3773,15 @@ static void alc245_hp_spk_mute_led_update(void *private_data, int enabled) alc_update_coef_idx(codec, 0x0b, 0x0c, val); } +static void alc245_hp_spk_mute_led_update_inverted(void *private_data, int enabled) +{ + struct hda_codec *codec = private_data; + unsigned int val; + + val = enabled ? 0x04 : 0x08; /* inverted: 0x04 led off, 0x08 led on */ + alc_update_coef_idx(codec, 0x0b, 0x0c, val); +} + /* JD2: mute led GPIO3: micmute led */ static void alc245_tas2781_i2c_hp_fixup_muteled(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -3801,6 +3810,33 @@ static void alc245_tas2781_i2c_hp_fixup_muteled(struct hda_codec *codec, alc245_fixup_hp_mute_led_coefbit(codec, fix, action); alc285_fixup_hp_coef_micmute_led(codec, fix, action); } + +/* Same as alc245_tas2781_i2c_hp_fixup_muteled(), but with inverted speaker + * mute LED polarity. The HP ZBook 8 G2a 14/16 (0x103c:0x8f94, 0x103c:0x8f95) + * are speaker-only models without an HP pin, so the LED is driven directly + * through the vmaster_mute hook. + */ +static void alc245_tas2781_i2c_hp_fixup_muteled_inverted(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + static const hda_nid_t conn[] = { 0x02 }; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + spec->gen.vmaster_mute.hook = alc245_hp_spk_mute_led_update_inverted; + spec->gen.vmaster_mute_led = 1; + spec->gen.auto_mute_via_amp = 1; + snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn); + break; + case HDA_FIXUP_ACT_INIT: + alc245_hp_spk_mute_led_update_inverted(codec, !spec->gen.master_mute); + break; + } + + tas2781_fixup_txnw_i2c(codec, fix, action); + alc285_fixup_hp_coef_micmute_led(codec, fix, action); +} /* * Clear COEF 0x0d (PCBEEP passthrough) bit 0x40 where BIOS sets it wrongly * at PM resume @@ -3903,6 +3939,7 @@ enum { ALC269_FIXUP_DMIC_THINKPAD_ACPI, ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13, ALC269VC_FIXUP_INFINIX_Y4_MAX, + ALC269VC_FIXUP_LUNNEN_GROUND_14, ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO, ALC255_FIXUP_ACER_MIC_NO_PRESENCE, ALC255_FIXUP_ASUS_MIC_NO_PRESENCE, @@ -3942,6 +3979,7 @@ enum { ALC275_FIXUP_DELL_XPS, ALC293_FIXUP_LENOVO_SPK_NOISE, ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, + ALC233_FIXUP_WUJIE_SPEAKERS, ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED, ALC255_FIXUP_DELL_SPK_NOISE, ALC225_FIXUP_DISABLE_MIC_VREF, @@ -3982,6 +4020,7 @@ enum { ALC256_FIXUP_HUAWEI_MACH_WX9_PINS, ALC298_FIXUP_HUAWEI_MBX_STEREO, ALC295_FIXUP_HP_X360, + ALC295_FIXUP_HP_PAVILION_X360, ALC221_FIXUP_HP_HEADSET_MIC, ALC285_FIXUP_LENOVO_HEADPHONE_NOISE, ALC295_FIXUP_HP_AUTO_MUTE, @@ -4117,6 +4156,9 @@ enum { ALC236_FIXUP_DELL_DUAL_CODECS, ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI, ALC287_FIXUP_TAS2781_I2C, + ALC287_FIXUP_ASUS_ALLY_X, + ALC287_FIXUP_ASUS_ALLY_X_SPEAKER, + ALC287_FIXUP_ASUS_ALLY_X_I2C, ALC295_FIXUP_DELL_TAS2781_I2C, ALC245_FIXUP_TAS2781_SPI_2, ALC287_FIXUP_TXNW2781_I2C, @@ -4159,6 +4201,7 @@ enum { ALC256_FIXUP_VAIO_RPL_MIC_NO_PRESENCE, ALC245_FIXUP_HP_TAS2781_SPI_MUTE_LED, ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED, + ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED_INVERTED, ALC288_FIXUP_SURFACE_SWAP_DACS, ALC236_FIXUP_HP_MUTE_LED_MICMUTE_GPIO, ALC233_FIXUP_LENOVO_GPIO2_MIC_HOTKEY, @@ -4169,6 +4212,7 @@ enum { ALC256_FIXUP_HONOR_MRB_XXX_M1020_AUDIO, ALC245_FIXUP_HP_ENVY_X360_15_FH0XXX, ALC287_FIXUP_ACER_MICMUTE_LED, + ALC236_FIXUP_DELL_HP_POP_NOISE, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -4206,6 +4250,13 @@ static void alc287_fixup_lenovo_yoga_book_9i(struct hda_codec *codec, } static const struct hda_fixup alc269_fixups[] = { + [ALC233_FIXUP_WUJIE_SPEAKERS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1b, 0x90170150 }, /* internal speaker */ + { } + }, + }, [ALC269_FIXUP_GPIO2] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_gpio2, @@ -4358,6 +4409,13 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST }, + [ALC269VC_FIXUP_LUNNEN_GROUND_14] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1b, 0x90170150 }, /* internal speaker */ + { } + }, + }, [ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -5294,6 +5352,19 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HP_MUTE_LED_MIC3 }, + [ALC295_FIXUP_HP_PAVILION_X360] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* force amp gain and processing state */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x07 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x7770 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x0d }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x3000 }, + {} + }, + .chained = true, + .chain_id = ALC295_FIXUP_HP_X360 + }, [ALC221_FIXUP_HP_HEADSET_MIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -6476,6 +6547,27 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC285_FIXUP_THINKPAD_HEADSET_JACK, }, + [ALC287_FIXUP_ASUS_ALLY_X] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, /* headset mic */ + { } + }, + .chained = true, + .chain_id = ALC287_FIXUP_ASUS_ALLY_X_SPEAKER, + }, + [ALC287_FIXUP_ASUS_ALLY_X_SPEAKER] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC287_FIXUP_ASUS_ALLY_X_I2C, + }, + [ALC287_FIXUP_ASUS_ALLY_X_I2C] = { + .type = HDA_FIXUP_FUNC, + .v.func = tas2781_fixup_tias_i2c, + .chained = true, + .chain_id = ALC225_FIXUP_HEADSET_JACK, + }, [ALC245_FIXUP_TAS2781_SPI_2] = { .type = HDA_FIXUP_FUNC, .v.func = tas2781_fixup_spi, @@ -6701,6 +6793,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc245_tas2781_i2c_hp_fixup_muteled, }, + [ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED_INVERTED] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc245_tas2781_i2c_hp_fixup_muteled_inverted, + }, [ALC288_FIXUP_SURFACE_SWAP_DACS] = { .type = HDA_FIXUP_FUNC, .v.func = alc288_fixup_surface_swap_dacs, @@ -6755,6 +6851,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC2XX_FIXUP_HEADSET_MIC, }, + [ALC236_FIXUP_DELL_HP_POP_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_invalidate_dacs, + }, }; static const struct hda_quirk alc269_fixup_tbl[] = { @@ -6895,6 +6995,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c28, "Dell Inspiron 16 Plus 7630", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x0c4d, "Dell", ALC287_FIXUP_CS35L41_I2C_4), + SND_PCI_QUIRK(0x1028, 0x0c90, "Alienware x16 R2", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x0c94, "Dell Polaris 3 metal", ALC295_FIXUP_DELL_TAS2781_I2C), SND_PCI_QUIRK(0x1028, 0x0c96, "Dell Polaris 2in1", ALC295_FIXUP_DELL_TAS2781_I2C), SND_PCI_QUIRK(0x1028, 0x0cbd, "Dell Oasis 13 CS MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2), @@ -6906,6 +7007,12 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0cc3, "Dell Oasis 14 Low Weight MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2), SND_PCI_QUIRK(0x1028, 0x0cc4, "Dell Oasis 16 MTL-H/U", ALC289_FIXUP_DELL_CS35L41_SPI_2), SND_PCI_QUIRK(0x1028, 0x0cc5, "Dell Oasis 14", ALC289_FIXUP_RTK_AMP_DUAL_SPK), + SND_PCI_QUIRK(0x1028, 0x0d56, "Dell Pro Tower QCT1255", ALC236_FIXUP_DELL_HP_POP_NOISE), + SND_PCI_QUIRK(0x1028, 0x0d58, "Dell Pro Micro QCM1255", ALC236_FIXUP_DELL_HP_POP_NOISE), + SND_PCI_QUIRK(0x1028, 0x0d5a, "Dell Pro Slim QCS1255", ALC236_FIXUP_DELL_HP_POP_NOISE), + SND_PCI_QUIRK(0x1028, 0x0e6b, "Dell Pro Tower QCT1255", ALC236_FIXUP_DELL_HP_POP_NOISE), + SND_PCI_QUIRK(0x1028, 0x0e6c, "Dell Pro Slim QCS1255", ALC236_FIXUP_DELL_HP_POP_NOISE), + SND_PCI_QUIRK(0x1028, 0x0e6d, "Dell Pro Micro QCM1255", ALC236_FIXUP_DELL_HP_POP_NOISE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -6978,6 +7085,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x82c0, "HP G3 mini premium", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x841c, "HP Pavilion 15-CK0xx", ALC269_FIXUP_HP_MUTE_LED_MIC3), + HDA_CODEC_QUIRK(0x103c, 0x8486, "HP Pavilion x360", ALC295_FIXUP_HP_PAVILION_X360), SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x84a6, "HP 250 G7 Notebook PC", ALC269_FIXUP_HP_LINE1_MIC1_LED), SND_PCI_QUIRK(0x103c, 0x84ae, "HP 15-db0403ng", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), @@ -6992,6 +7100,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x856a, "HP Pavilion 15-cs1xxx", ALC295_FIXUP_HP_PAVILION_MUTE_LED_1B), SND_PCI_QUIRK(0x103c, 0x85c6, "HP Pavilion x360 Convertible 14-dy1xxx", ALC295_FIXUP_HP_MUTE_LED_COEFBIT11), SND_PCI_QUIRK(0x103c, 0x85de, "HP Envy x360 13-ar0xxx", ALC285_FIXUP_HP_ENVY_X360), + SND_PCI_QUIRK(0x103c, 0x85f0, "HP Laptop 15-dw0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8603, "HP Omen 17-cb0xxx", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x860c, "HP ZBook 17 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT), @@ -7121,6 +7230,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8a36, "HP Pavilion Plus 14-eh0xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a3d, "HP Victus 15-fb0xxx (MB 8A3D)", ALC245_FIXUP_HP_MUTE_LED_V2_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a4f, "HP Victus 15-fa0xxx (MB 8A4F)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), + SND_PCI_QUIRK(0x103c, 0x8a50, "HP Victus 15-fa0xxx (MB 8A50)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a6e, "HP EDNA 360", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x103c, 0x8a74, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a75, "HP ProBook 450 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -7131,6 +7241,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ab8, "HP EliteBook 830 G8 Notebook PC (MB 8AB8)", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ab9, "HP EliteBook 840 G8 (MB 8AB8)", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -7268,7 +7379,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8da8, "HP 16 Piston OmniBook X", ALC245_FIXUP_HP_ENVY_X360_15_FH0XXX), SND_PCI_QUIRK(0x103c, 0x8dc9, "HP Laptop 15-fc0xxx", ALC236_FIXUP_HP_DMIC), SND_PCI_QUIRK(0x103c, 0x8dd4, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS), - SND_PCI_QUIRK(0x103c, 0x8dd7, "HP Laptop 15-fd0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), + SND_PCI_QUIRK(0x103c, 0x8dd7, "HP Laptop 15-fd0xxx", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_GPIO), SND_PCI_QUIRK(0x103c, 0x8de8, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2), SND_PCI_QUIRK(0x103c, 0x8de9, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2), SND_PCI_QUIRK(0x103c, 0x8dec, "HP EliteBook 640 G12", ALC236_FIXUP_HP_GPIO_LED), @@ -7341,6 +7452,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8f42, "HP ZBook 8 G2a 14W", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8f57, "HP Trekker G7JC", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8f62, "HP ZBook 8 G2a 16W", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x8f94, "HP ZBook 8 G2a 14", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED_INVERTED), + SND_PCI_QUIRK(0x103c, 0x8f95, "HP ZBook 8 G2a 16", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED_INVERTED), SND_PCI_QUIRK(0x1043, 0x1024, "ASUS Zephyrus G14 2025", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1032, "ASUS VivoBook X513EA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1034, "ASUS GU605C", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), @@ -7460,7 +7573,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e83, "ASUS GA605W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1e93, "ASUS ExpertBook B9403CVAR", ALC294_FIXUP_ASUS_HPE), - SND_PCI_QUIRK(0x1043, 0x1eb3, "ASUS Ally RCLA72", ALC287_FIXUP_TAS2781_I2C), + SND_PCI_QUIRK(0x1043, 0x1eb3, "ASUS Ally RC72LA", ALC287_FIXUP_ASUS_ALLY_X), SND_PCI_QUIRK(0x1043, 0x1ed3, "ASUS HN7306W", ALC287_FIXUP_CS35L41_I2C_2), HDA_CODEC_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2), @@ -7547,6 +7660,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc1a6, "Samsung Galaxy Book Pro 360 (NP930QBD)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_AMP), + HDA_CODEC_QUIRK(0x144d, 0xc824, "Samsung ELECTRONICS (750XBE/730XBE)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc832, "Samsung Galaxy Book Flex Alpha (NP730QCJ)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc876, "Samsung 730QED (NP730QED-KA2US)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), @@ -7766,6 +7880,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { HDA_CODEC_QUIRK(0x17aa, 0x386e, "Legion Y9000X 2022 IAH7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x386e, "Yoga Pro 7 14ARP8", ALC285_FIXUP_SPEAKER2_TO_DAC1), HDA_CODEC_QUIRK(0x17aa, 0x38a8, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), /* this must match before PCI SSID 17aa:386f below */ + HDA_CODEC_QUIRK(0x17aa, 0x38a7, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), /* this must match before PCI SSID 17aa:386f below */ SND_PCI_QUIRK(0x17aa, 0x386f, "Legion Pro 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C), SND_PCI_QUIRK(0x17aa, 0x3874, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2), @@ -7885,6 +8000,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x300f, "TongFang X6AR5xxY", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x3019, "TongFang X6FR5xxY", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x3031, "TongFang X6AR55xU", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d05, 0x3034, "TongFang X6xx45xU", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), @@ -7910,11 +8026,13 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x2782, 0x1705, "MEDION E15433", ALC269VC_FIXUP_INFINIX_Y4_MAX), SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x2782, 0x4900, "MEDION E15443", ALC233_FIXUP_MEDION_MTL_SPK), + SND_PCI_QUIRK(0x2782, 0xa212, "Lunnen Ground 14", ALC269VC_FIXUP_LUNNEN_GROUND_14), SND_PCI_QUIRK(0x7017, 0x2014, "Star Labs StarFighter", ALC233_FIXUP_STARLABS_STARFIGHTER), SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), SND_PCI_QUIRK(0x8086, 0x3038, "Intel NUC 13", ALC295_FIXUP_CHROME_BOOK), + SND_PCI_QUIRK(0xc011, 0x1d05, "MECHREVO WUJIE Series", ALC233_FIXUP_WUJIE_SPEAKERS), SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), @@ -7922,6 +8040,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0xf111, 0x000c, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x000f, "Framework Laptop 13 Pro PTL", ALC295_FIXUP_FRAMEWORK_LAPTOP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0xf111, 0x010f, "Framework Laptop 13 PTL", ALC295_FIXUP_FRAMEWORK_LAPTOP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0xf111, 0x0010, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_LIMIT_INT_MIC_BOOST), #if 0 /* Below is a quirk table taken from the old code. diff --git a/sound/hda/codecs/side-codecs/Kconfig b/sound/hda/codecs/side-codecs/Kconfig index 2a2e8804bf9e..1cfd83e251e4 100644 --- a/sound/hda/codecs/side-codecs/Kconfig +++ b/sound/hda/codecs/side-codecs/Kconfig @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only config SND_HDA_CIRRUS_SCODEC - tristate + tristate "Cirrus side-codec library" if KUNIT config SND_HDA_CIRRUS_SCODEC_KUNIT_TEST tristate "KUnit test for Cirrus side-codec library" if !KUNIT_ALL_TESTS diff --git a/sound/hda/codecs/side-codecs/cs35l41_hda.c b/sound/hda/codecs/side-codecs/cs35l41_hda.c index 64a5bd895fd1..237059ef22f5 100644 --- a/sound/hda/codecs/side-codecs/cs35l41_hda.c +++ b/sound/hda/codecs/side-codecs/cs35l41_hda.c @@ -1434,10 +1434,19 @@ static int cs35l41_get_acpi_mute_state(struct cs35l41_hda *cs35l41, acpi_handle guid_parse(CS35L41_UUID, &guid); if (cs35l41_dsm_supported(handle, CS35L41_DSM_GET_MUTE)) { - ret = acpi_evaluate_dsm(handle, &guid, 0, CS35L41_DSM_GET_MUTE, NULL); + ret = acpi_evaluate_dsm_typed(handle, &guid, 0, + CS35L41_DSM_GET_MUTE, NULL, + ACPI_TYPE_BUFFER); + if (!ret) return -EINVAL; + if (!ret->buffer.length || !ret->buffer.pointer) { + ACPI_FREE(ret); + return -EINVAL; + } + mute = *ret->buffer.pointer; + ACPI_FREE(ret); dev_dbg(cs35l41->dev, "CS35L41_DSM_GET_MUTE: %d\n", mute); } diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.c b/sound/hda/codecs/side-codecs/cs35l56_hda.c index a0ea08eb96a9..78c2cf387a00 100644 --- a/sound/hda/codecs/side-codecs/cs35l56_hda.c +++ b/sound/hda/codecs/side-codecs/cs35l56_hda.c @@ -512,20 +512,6 @@ static void cs35l56_hda_request_firmware_files(struct cs35l56_hda *cs35l56, NULL, "bin"); return; } - - /* - * Check for system-specific bin files without wmfw before - * falling back to generic firmware - */ - if (amp_name) - cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename, - base_name, system_name, amp_name, "bin"); - if (!*coeff_firmware) - cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename, - base_name, system_name, NULL, "bin"); - - if (*coeff_firmware) - return; } ret = cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename, @@ -616,13 +602,15 @@ static void cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56) &wmfw_firmware, &wmfw_filename, &coeff_firmware, &coeff_filename); - /* - * If the BIOS didn't patch the firmware a bin file is mandatory to - * enable the ASP· - */ - if (!coeff_firmware && firmware_missing) { - dev_err(cs35l56->base.dev, ".bin file required but not found\n"); - goto err_fw_release; + /* If the BIOS didn't patch the firmware a wmfw and bin file are mandatory */ + if (firmware_missing) { + if (!wmfw_firmware) { + dev_err(cs35l56->base.dev, ".%s file required but not found\n", "wmfw"); + goto err_fw_release; + } else if (!coeff_firmware) { + dev_err(cs35l56->base.dev, ".%s file required but not found\n", "bin"); + goto err_fw_release; + } } mutex_lock(&cs35l56->base.irq_lock); diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c index 69a22fdfeedb..624db967f17b 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c @@ -354,6 +354,7 @@ static int tas2563_save_calibration(struct tas2781_hda *h) if (ret < 0 || ret >= sizeof(var8) - 1) { dev_err(p->dev, "%s: Read %s failed\n", __func__, var8); + cd->total_sz = 0; return -EINVAL; } /* @@ -371,6 +372,7 @@ static int tas2563_save_calibration(struct tas2781_hda *h) dev_warn(p->dev, "Dev %d: Caldat[%d] read failed %ld\n", i, j, status); + cd->total_sz = 0; return -EINVAL; } bedata = cpu_to_be32(*(uint32_t *)&data[offset]); @@ -382,6 +384,7 @@ static int tas2563_save_calibration(struct tas2781_hda *h) if (cd->total_sz != offset) { dev_err(p->dev, "%s: tot_size(%lu) and offset(%u) mismatch\n", __func__, cd->total_sz, offset); + cd->total_sz = 0; return -EINVAL; } diff --git a/sound/hda/core/regmap.c b/sound/hda/core/regmap.c index e7b866fc52c1..d6eb17aa9e08 100644 --- a/sound/hda/core/regmap.c +++ b/sound/hda/core/regmap.c @@ -214,7 +214,7 @@ static int hda_reg_read_coef(struct hdac_device *codec, unsigned int reg, err = snd_hdac_exec_verb(codec, verb, 0, NULL); if (err < 0) return err; - verb = (reg & ~0xfffff) | (AC_VERB_GET_COEF_INDEX << 8); + verb = (reg & ~0xfffff) | (AC_VERB_GET_PROC_COEF << 8); return snd_hdac_exec_verb(codec, verb, 0, val); } @@ -232,7 +232,7 @@ static int hda_reg_write_coef(struct hdac_device *codec, unsigned int reg, err = snd_hdac_exec_verb(codec, verb, 0, NULL); if (err < 0) return err; - verb = (reg & ~0xfffff) | (AC_VERB_GET_COEF_INDEX << 8) | + verb = (reg & ~0xfffff) | (AC_VERB_SET_PROC_COEF << 8) | (val & 0xffff); return snd_hdac_exec_verb(codec, verb, 0, NULL); } diff --git a/sound/soc/amd/acp-config.c b/sound/soc/amd/acp-config.c index 0d977f4f758d..051946562725 100644 --- a/sound/soc/amd/acp-config.c +++ b/sound/soc/amd/acp-config.c @@ -44,6 +44,18 @@ static const struct dmi_system_id acp70_acpi_flag_override_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "83W5"), }, }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC"), + DMI_MATCH(DMI_PRODUCT_NAME, "TUF Gaming A14 FA401EA"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Vivobook 18 M1807GA"), + }, + }, {} }; diff --git a/sound/soc/amd/acp/Kconfig b/sound/soc/amd/acp/Kconfig index 977e4f2a7a70..a04c301df4d6 100644 --- a/sound/soc/amd/acp/Kconfig +++ b/sound/soc/amd/acp/Kconfig @@ -15,13 +15,17 @@ config SND_SOC_AMD_ACP_COMMON config SND_SOC_ACPI_AMD_MATCH tristate - select SND_SOC_ACPI_AMD_SDCA_QUIRKS if SND_SOC_SDCA select SND_SOC_ACPI if ACPI config SND_SOC_ACPI_AMD_SDCA_QUIRKS - tristate - depends on ACPI + bool "AMD ACPI SDCA quirks" + depends on SND_SOC_ACPI_AMD_MATCH depends on SND_SOC_SDCA + depends on SND_SOC_ACPI_AMD_MATCH = m || SND_SOC_SDCA = y + default y + help + Enable SDCA quirk support for AMD ACPI match tables. + This is compiled into the snd-soc-acpi-amd-match module. if SND_SOC_AMD_ACP_COMMON diff --git a/sound/soc/amd/acp/Makefile b/sound/soc/amd/acp/Makefile index 81d23aded348..ab5f9dc871a6 100644 --- a/sound/soc/amd/acp/Makefile +++ b/sound/soc/amd/acp/Makefile @@ -24,10 +24,10 @@ snd-acp-mach-y := acp-mach-common.o snd-acp-legacy-mach-y := acp-legacy-mach.o acp3x-es83xx/acp3x-es83xx.o snd-acp-sof-mach-y := acp-sof-mach.o snd-soc-acpi-amd-match-y := amd-acp63-acpi-match.o amd-acp70-acpi-match.o +snd-soc-acpi-amd-match-$(CONFIG_SND_SOC_ACPI_AMD_SDCA_QUIRKS) += soc-acpi-amd-sdca-quirks.o snd-acp-sdw-mach-y := acp-sdw-mach-common.o snd-acp-sdw-sof-mach-y += acp-sdw-sof-mach.o snd-acp-sdw-legacy-mach-y += acp-sdw-legacy-mach.o -snd-soc-acpi-amd-sdca-quirks-y += soc-acpi-amd-sdca-quirks.o obj-$(CONFIG_SND_SOC_AMD_ACP_PCM) += snd-acp-pcm.o obj-$(CONFIG_SND_SOC_AMD_ACP_I2S) += snd-acp-i2s.o @@ -41,7 +41,6 @@ obj-$(CONFIG_SND_AMD_ASOC_REMBRANDT) += snd-acp-rembrandt.o obj-$(CONFIG_SND_AMD_ASOC_ACP63) += snd-acp63.o obj-$(CONFIG_SND_AMD_ASOC_ACP70) += snd-acp70.o -obj-$(CONFIG_SND_SOC_ACPI_AMD_SDCA_QUIRKS) += snd-soc-acpi-amd-sdca-quirks.o obj-$(CONFIG_SND_AMD_SOUNDWIRE_ACPI) += snd-amd-sdw-acpi.o obj-$(CONFIG_SND_SOC_AMD_MACH_COMMON) += snd-acp-mach.o obj-$(CONFIG_SND_SOC_AMD_LEGACY_MACH) += snd-acp-legacy-mach.o diff --git a/sound/soc/amd/acp/amd-acp70-acpi-match.c b/sound/soc/amd/acp/amd-acp70-acpi-match.c index 18f2918d4ada..ccd01152c87d 100644 --- a/sound/soc/amd/acp/amd-acp70-acpi-match.c +++ b/sound/soc/amd/acp/amd-acp70-acpi-match.c @@ -553,6 +553,46 @@ static const struct snd_soc_acpi_link_adr acp70_rt722_l0_rt1320_l1[] = { {} }; +static const struct snd_soc_acpi_adr_device tas2783_2_adr[] = { + { + /* left */ + .adr = 0x00003c0102000001ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "tas2783-1", + }, + { + /* right */ + .adr = 0x00003d0102000001ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "tas2783-2", + }, + { + /* left */ + .adr = 0x0000390102000001ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "tas2783-3", + }, + { + /* right */ + .adr = 0x00003a0102000001ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "tas2783-4", + }, +}; + +static const struct snd_soc_acpi_link_adr acp70_tas2783_2[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(tas2783_2_adr), + .adr_d = tas2783_2_adr, + }, + {} +}; + static const struct snd_soc_acpi_adr_device rt1320_0_single_adr[] = { { .adr = 0x000030025D132001ull, @@ -660,6 +700,11 @@ static const struct snd_soc_acpi_link_adr acp70_rt721_only[] = { struct snd_soc_acpi_mach snd_soc_acpi_amd_acp70_sdw_machines[] = { { + .link_mask = BIT(0), + .links = acp70_tas2783_2, + .drv_name = "amd_sdw", + }, + { .link_mask = BIT(0) | BIT(1), .links = acp70_rt1320_l0_rt722_l1, .drv_name = "amd_sdw", @@ -775,5 +820,5 @@ MODULE_DESCRIPTION("AMD ACP7.0 & ACP7.1 tables and support for ACPI enumeration" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Vijendar.Mukunda@amd.com"); #if IS_ENABLED(CONFIG_SND_SOC_ACPI_AMD_SDCA_QUIRKS) -MODULE_IMPORT_NS("SND_SOC_ACPI_AMD_SDCA_QUIRKS"); +MODULE_IMPORT_NS("SND_SOC_SDCA"); #endif diff --git a/sound/soc/amd/acp/soc-acpi-amd-sdca-quirks.c b/sound/soc/amd/acp/soc-acpi-amd-sdca-quirks.c index 63bf9e3c0ae1..9248b6d09e76 100644 --- a/sound/soc/amd/acp/soc-acpi-amd-sdca-quirks.c +++ b/sound/soc/amd/acp/soc-acpi-amd-sdca-quirks.c @@ -35,8 +35,4 @@ bool snd_soc_acpi_amd_sdca_is_device_rt712_vb(void *arg) return false; } -EXPORT_SYMBOL_NS(snd_soc_acpi_amd_sdca_is_device_rt712_vb, "SND_SOC_ACPI_AMD_SDCA_QUIRKS"); -MODULE_DESCRIPTION("ASoC ACPI AMD SDCA quirks"); -MODULE_LICENSE("GPL"); -MODULE_IMPORT_NS("SND_SOC_SDCA"); diff --git a/sound/soc/amd/ps/pci-ps.c b/sound/soc/amd/ps/pci-ps.c index 4ecda224157b..729f9aaba69e 100644 --- a/sound/soc/amd/ps/pci-ps.c +++ b/sound/soc/amd/ps/pci-ps.c @@ -248,7 +248,7 @@ static irqreturn_t acp63_irq_handler(int irq, void *dev_id) if (sdw_dma_irq_flag) return IRQ_WAKE_THREAD; - if (irq_flag | wake_irq_flag) + if (irq_flag || wake_irq_flag) return IRQ_HANDLED; else return IRQ_NONE; @@ -602,7 +602,7 @@ static int snd_acp63_probe(struct pci_dev *pci, return -ENODEV; } - ret = pci_request_regions(pci, "AMD ACP6.2 audio"); + ret = pci_request_regions(pci, "AMD ACP6.3 audio"); if (ret < 0) { dev_err(&pci->dev, "pci_request_regions failed\n"); goto disable_pci; @@ -693,8 +693,37 @@ static int snd_acp_runtime_resume(struct device *dev) return acp_hw_runtime_resume(dev); } +static void acp_disable_msi_on_resume(struct pci_dev *pdev) +{ + u16 control; + + if (!pdev->msi_cap) + return; + + pci_read_config_word(pdev, pdev->msi_cap + PCI_MSI_FLAGS, &control); + if (control & PCI_MSI_FLAGS_ENABLE) { + dev_warn(&pdev->dev, + "ACP: MSI unexpectedly enabled after resume (flags=0x%04x), disabling\n", + control); + control &= ~PCI_MSI_FLAGS_ENABLE; + pci_write_config_word(pdev, pdev->msi_cap + PCI_MSI_FLAGS, control); + } +} + static int snd_acp_resume(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); + + /* + * BIOS/firmware may re-enable MSI in PCI config space during + * system resume even though this driver only uses legacy INTx + * interrupts. If MSI is left enabled with stale address/data + * registers, the device will write interrupts to a bogus address + * causing IOMMU IO_PAGE_FAULT and interrupt delivery failure. + * Explicitly clear the MSI Enable bit before reinitializing + * the ACP hardware. + */ + acp_disable_msi_on_resume(pdev); return acp_hw_resume(dev); } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index d6df7de70b27..af1dce9c9b8a 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -525,6 +525,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vector A16 HX A8WIG"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), DMI_MATCH(DMI_PRODUCT_NAME, "Raider A18 HX A9WJG"), } }, diff --git a/sound/soc/codecs/bt-sco.c b/sound/soc/codecs/bt-sco.c index 3afcef2dfa35..c0bf45b76cb8 100644 --- a/sound/soc/codecs/bt-sco.c +++ b/sound/soc/codecs/bt-sco.c @@ -17,11 +17,17 @@ static const struct snd_soc_dapm_widget bt_sco_widgets[] = { SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("BT_SCO_TX", "Capture", 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("BT_SCO_RX_WB", "WB Playback", 0, + SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("BT_SCO_TX_WB", "WB Capture", 0, + SND_SOC_NOPM, 0, 0), }; static const struct snd_soc_dapm_route bt_sco_routes[] = { { "BT_SCO_TX", NULL, "RX" }, { "TX", NULL, "BT_SCO_RX" }, + { "BT_SCO_TX_WB", NULL, "RX" }, + { "TX", NULL, "BT_SCO_RX_WB" }, }; static struct snd_soc_dai_driver bt_sco_dai[] = { @@ -45,14 +51,14 @@ static struct snd_soc_dai_driver bt_sco_dai[] = { { .name = "bt-sco-pcm-wb", .playback = { - .stream_name = "Playback", + .stream_name = "WB Playback", .channels_min = 1, .channels_max = 1, .rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000, .formats = SNDRV_PCM_FMTBIT_S16_LE, }, .capture = { - .stream_name = "Capture", + .stream_name = "WB Capture", .channels_min = 1, .channels_max = 1, .rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000, diff --git a/sound/soc/codecs/cs35l56-i2c.c b/sound/soc/codecs/cs35l56-i2c.c index 0f64ab628b03..4f6ddf1c5a3f 100644 --- a/sound/soc/codecs/cs35l56-i2c.c +++ b/sound/soc/codecs/cs35l56-i2c.c @@ -55,9 +55,7 @@ static int cs35l56_i2c_probe(struct i2c_client *client) if (ret != 0) return ret; - ret = cs35l56_init(cs35l56); - if (ret == 0) - ret = cs35l56_irq_request(&cs35l56->base, client->irq); + ret = cs35l56_irq_request(&cs35l56->base, client->irq); if (ret < 0) cs35l56_remove(cs35l56); diff --git a/sound/soc/codecs/cs35l56-spi.c b/sound/soc/codecs/cs35l56-spi.c index 9bc9b7c98390..b1eb924a5b6c 100644 --- a/sound/soc/codecs/cs35l56-spi.c +++ b/sound/soc/codecs/cs35l56-spi.c @@ -44,9 +44,7 @@ static int cs35l56_spi_probe(struct spi_device *spi) if (ret != 0) return ret; - ret = cs35l56_init(cs35l56); - if (ret == 0) - ret = cs35l56_irq_request(&cs35l56->base, spi->irq); + ret = cs35l56_irq_request(&cs35l56->base, spi->irq); if (ret < 0) cs35l56_remove(cs35l56); diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 570a68829ccd..063ef7a70de0 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -2008,6 +2008,16 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56) goto err; } + /* + * On SoundWire the cs35l56_init() cannot be run until after the + * device has been enumerated by the SoundWire core. + */ + if (!cs35l56->sdw_peripheral) { + ret = cs35l56_init(cs35l56); + if (ret) + goto err_remove_wm_adsp; + } + ret = snd_soc_register_component(cs35l56->base.dev, &soc_component_dev_cs35l56, cs35l56_dai, ARRAY_SIZE(cs35l56_dai)); @@ -2022,6 +2032,11 @@ err_remove_wm_adsp: wm_adsp2_remove(&cs35l56->dsp); err: + if (pm_runtime_enabled(cs35l56->base.dev)) { + pm_runtime_dont_use_autosuspend(cs35l56->base.dev); + pm_runtime_disable(cs35l56->base.dev); + } + gpiod_set_value_cansleep(cs35l56->base.reset_gpio, 0); regulator_bulk_disable(ARRAY_SIZE(cs35l56->supplies), cs35l56->supplies); @@ -2108,7 +2123,7 @@ post_soft_reset: return dev_err_probe(cs35l56->base.dev, ret, "Failed to write ASP1_CONTROL3\n"); cs35l56->base.init_done = true; - complete(&cs35l56->init_completion); + complete_all(&cs35l56->init_completion); return 0; } diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c index 934666295ee3..dbf45cabfffe 100644 --- a/sound/soc/codecs/cs42l43-jack.c +++ b/sound/soc/codecs/cs42l43-jack.c @@ -310,6 +310,7 @@ irqreturn_t cs42l43_bias_detect_clamp(int irq, void *data) #define CS42L43_JACK_ABSENT 0x0 #define CS42L43_JACK_OPTICAL (SND_JACK_MECHANICAL | SND_JACK_AVOUT) +#define CS42L43_JACK_MICROPHONE (SND_JACK_MECHANICAL | SND_JACK_MICROPHONE) #define CS42L43_JACK_HEADPHONE (SND_JACK_MECHANICAL | SND_JACK_HEADPHONE) #define CS42L43_JACK_HEADSET (SND_JACK_MECHANICAL | SND_JACK_HEADSET) #define CS42L43_JACK_LINEOUT (SND_JACK_MECHANICAL | SND_JACK_LINEOUT) @@ -871,7 +872,7 @@ static const struct cs42l43_jack_override_mode { .hsdet_mode = CS42L43_JACK_3_POLE_SWITCHES, .mic_ctrl = (0x3 << CS42L43_JACK_STEREO_CONFIG_SHIFT) | CS42L43_HS1_BIAS_EN_MASK | CS42L43_HS2_BIAS_EN_MASK, - .report = CS42L43_JACK_LINEIN, + .report = CS42L43_JACK_MICROPHONE, }, [CS42L43_JACK_RAW_OPTICAL] = { .hsdet_mode = CS42L43_JACK_3_POLE_SWITCHES, diff --git a/sound/soc/codecs/fs210x.c b/sound/soc/codecs/fs210x.c index 5f381fe063e8..d794ff918b6f 100644 --- a/sound/soc/codecs/fs210x.c +++ b/sound/soc/codecs/fs210x.c @@ -607,6 +607,7 @@ tag_power_down: regcache_cache_bypass(fs210x->regmap, false); if (!ret) { + regcache_cache_only(fs210x->regmap, false); regcache_mark_dirty(fs210x->regmap); regcache_sync(fs210x->regmap); fs210x->is_inited = true; diff --git a/sound/soc/codecs/rt712-sdca.c b/sound/soc/codecs/rt712-sdca.c index 4796fce084ff..d6353af07380 100644 --- a/sound/soc/codecs/rt712-sdca.c +++ b/sound/soc/codecs/rt712-sdca.c @@ -1843,6 +1843,15 @@ static void rt712_sdca_vb_io_init(struct rt712_sdca_priv *rt712) } } +static void rt712_sdca_reset(struct rt712_sdca_priv *rt712) +{ + rt712_sdca_index_update_bits(rt712, RT712_VENDOR_REG, + RT712_PARA_VERB_CTL, RT712_HIDDEN_REG_SW_RESET, + RT712_HIDDEN_REG_SW_RESET); + rt712_sdca_index_update_bits(rt712, RT712_VENDOR_HDA_CTL, + RT712_HDA_LEGACY_RESET_CTL, 0x1, 0x1); +} + int rt712_sdca_io_init(struct device *dev, struct sdw_slave *slave) { struct rt712_sdca_priv *rt712 = dev_get_drvdata(dev); @@ -1870,6 +1879,8 @@ int rt712_sdca_io_init(struct device *dev, struct sdw_slave *slave) pm_runtime_get_noresume(&slave->dev); + rt712_sdca_reset(rt712); + rt712_sdca_index_read(rt712, RT712_VENDOR_REG, RT712_JD_PRODUCT_NUM, &val); rt712->hw_id = (val & 0xf000) >> 12; rt712->version_id = (val & 0x0f00) >> 8; diff --git a/sound/soc/codecs/tas2562.c b/sound/soc/codecs/tas2562.c index 2f7cfc2be970..e1d62f30418a 100644 --- a/sound/soc/codecs/tas2562.c +++ b/sound/soc/codecs/tas2562.c @@ -675,11 +675,12 @@ static int tas2562_parse_dt(struct tas2562_data *tas2562) if (tas2562->sdz_gpio == NULL) { tas2562->sdz_gpio = devm_gpiod_get_optional(dev, "shut-down", GPIOD_OUT_HIGH); - if (IS_ERR(tas2562->sdz_gpio)) + if (IS_ERR(tas2562->sdz_gpio)) { if (PTR_ERR(tas2562->sdz_gpio) == -EPROBE_DEFER) return -EPROBE_DEFER; - tas2562->sdz_gpio = NULL; + tas2562->sdz_gpio = NULL; + } } if (tas2562->model_id == TAS2110) diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c index bd16d5326a23..dcbeb9618195 100644 --- a/sound/soc/codecs/tas2781-fmwlib.c +++ b/sound/soc/codecs/tas2781-fmwlib.c @@ -12,6 +12,7 @@ #include <linux/i2c.h> #include <linux/init.h> #include <linux/interrupt.h> +#include <linux/limits.h> #include <linux/module.h> #include <linux/of.h> #include <linux/of_irq.h> @@ -1100,13 +1101,42 @@ static int tasdevice_load_block_kernel( return 0; } +static int tasdevice_fw_strnlen(const struct firmware *fmw, int offset) +{ + const u8 *start; + const u8 *nul; + size_t remaining; + size_t len; + + if (offset < 0 || offset >= fmw->size) + return -EINVAL; + + start = fmw->data + offset; + remaining = fmw->size - offset; + nul = memchr(start, '\0', remaining); + if (!nul) + return -EINVAL; + + len = nul - start; + if (len > INT_MAX) + return -EOVERFLOW; + + return len; +} + static int fw_parse_variable_hdr(struct tasdevice_priv *tas_priv, struct tasdevice_dspfw_hdr *fw_hdr, const struct firmware *fmw, int offset) { const unsigned char *buf = fmw->data; - int len = strlen((char *)&buf[offset]); + int len; + len = tasdevice_fw_strnlen(fmw, offset); + if (len < 0) { + dev_err(tas_priv->dev, "%s: Description error\n", __func__); + offset = len; + goto out; + } len++; if (offset + len + 8 > fmw->size) { @@ -1238,7 +1268,12 @@ static int fw_parse_data(struct tasdevice_fw *tas_fmw, memcpy(img_data->name, &data[offset], 64); offset += 64; - n = strlen((char *)&data[offset]); + n = tasdevice_fw_strnlen(fmw, offset); + if (n < 0) { + dev_err(tas_fmw->dev, "%s: Description error\n", __func__); + offset = n; + goto out; + } n++; if (offset + n + 2 > fmw->size) { dev_err(tas_fmw->dev, "%s: Description error\n", __func__); @@ -1309,7 +1344,12 @@ static int fw_parse_program_data(struct tasdevice_priv *tas_priv, } offset += 64; - n = strlen((char *)&buf[offset]); + n = tasdevice_fw_strnlen(fmw, offset); + if (n < 0) { + dev_err(tas_priv->dev, "Description err\n"); + offset = n; + goto out; + } /* skip '\0' and 5 unused bytes */ n += 6; if (offset + n > fmw->size) { @@ -1372,7 +1412,12 @@ static int fw_parse_configuration_data( memcpy(config->name, &data[offset], 64); offset += 64; - n = strlen((char *)&data[offset]); + n = tasdevice_fw_strnlen(fmw, offset); + if (n < 0) { + dev_err(tas_priv->dev, "Description err\n"); + offset = n; + goto out; + } n += 15; if (offset + n > fmw->size) { dev_err(tas_priv->dev, "Description err\n"); @@ -2134,7 +2179,8 @@ static int fw_parse_calibration_data(struct tasdevice_priv *tas_priv, { struct tasdevice_calibration *calibration; unsigned char *data = (unsigned char *)fmw->data; - unsigned int i, n; + unsigned int i; + int n; if (offset + 2 > fmw->size) { dev_err(tas_priv->dev, "%s: Calibrations error\n", __func__); @@ -2166,7 +2212,12 @@ static int fw_parse_calibration_data(struct tasdevice_priv *tas_priv, calibration = &(tas_fmw->calibrations[i]); offset += 64; - n = strlen((char *)&data[offset]); + n = tasdevice_fw_strnlen(fmw, offset); + if (n < 0) { + dev_err(tas_priv->dev, "Description err\n"); + offset = n; + goto out; + } /* skip '\0' and 2 unused bytes */ n += 3; if (offset + n > fmw->size) { diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 9661602b53c5..d232c8f53061 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -808,6 +808,8 @@ static int fsl_sai_hw_free(struct snd_pcm_substream *substream, struct fsl_sai *sai = snd_soc_dai_get_drvdata(cpu_dai); bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; unsigned int ofs = sai->soc_data->reg_offset; + int adir = tx ? RX : TX; + int dir = tx ? TX : RX; /* Clear xMR to avoid channel swap with mclk_with_tere enabled case */ regmap_write(sai->regmap, FSL_SAI_xMR(tx), 0); @@ -815,10 +817,29 @@ static int fsl_sai_hw_free(struct snd_pcm_substream *substream, regmap_update_bits(sai->regmap, FSL_SAI_xCR3(tx, ofs), FSL_SAI_CR3_TRCE_MASK, 0); - if (!sai->is_consumer_mode[tx] && - sai->mclk_streams & BIT(substream->stream)) { - clk_disable_unprepare(sai->mclk_clk[sai->mclk_id[tx]]); - sai->mclk_streams &= ~BIT(substream->stream); + if (!sai->is_consumer_mode[tx]) { + bool adir_active = !!(sai->mclk_streams & BIT(!substream->stream)); + /* + * If opposite stream provides clocks for synchronous mode and + * it is inactive, Clear BYP and BCI + */ + if (fsl_sai_dir_is_synced(sai, adir) && !adir_active) + regmap_update_bits(sai->regmap, FSL_SAI_xCR2(!tx, ofs), + FSL_SAI_CR2_BCI | FSL_SAI_CR2_BYP, 0); + /* + * Clear BYP and BCI of current stream if either of: + * 1. current stream doesn't provide clocks for synchronous mode + * 2. current stream provides clocks for synchronous mode but no + * more stream is active. + */ + if (!fsl_sai_dir_is_synced(sai, dir) || !adir_active) + regmap_update_bits(sai->regmap, FSL_SAI_xCR2(tx, ofs), + FSL_SAI_CR2_BCI | FSL_SAI_CR2_BYP, 0); + + if (sai->mclk_streams & BIT(substream->stream)) { + clk_disable_unprepare(sai->mclk_clk[sai->mclk_id[tx]]); + sai->mclk_streams &= ~BIT(substream->stream); + } } return 0; diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c index a4518fefad69..43438af1e1c6 100644 --- a/sound/soc/fsl/imx-card.c +++ b/sound/soc/fsl/imx-card.c @@ -496,11 +496,15 @@ static void imx_aif_shutdown(struct snd_pcm_substream *substream) struct snd_soc_dai *codec_dai; int i; - for_each_rtd_cpu_dais(rtd, i, cpu_dai) - snd_soc_dai_set_sysclk(cpu_dai, 0, 0, SND_SOC_CLOCK_OUT); + for_each_rtd_cpu_dais(rtd, i, cpu_dai) { + if (!snd_soc_dai_active(cpu_dai)) + snd_soc_dai_set_sysclk(cpu_dai, 0, 0, SND_SOC_CLOCK_OUT); + } - for_each_rtd_codec_dais(rtd, i, codec_dai) - snd_soc_dai_set_sysclk(codec_dai, 0, 0, SND_SOC_CLOCK_IN); + for_each_rtd_codec_dais(rtd, i, codec_dai) { + if (!snd_soc_dai_active(codec_dai)) + snd_soc_dai_set_sysclk(codec_dai, 0, 0, SND_SOC_CLOCK_IN); + } } static const struct snd_soc_ops imx_aif_ops = { diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index d43daf9b025d..c527d575d1ed 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -849,12 +849,15 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { }; static const struct snd_pci_quirk sof_sdw_ssid_quirk_table[] = { + SND_PCI_QUIRK(0x1028, 0x0e53, "Dell XPS WCL", SOC_SDW_SIDECAR_AMPS), + SND_PCI_QUIRK(0x1028, 0x0e54, "Dell XPS PTL", SOC_SDW_SIDECAR_AMPS), SND_PCI_QUIRK(0x1043, 0x1e13, "ASUS Zenbook S14", SOC_SDW_CODEC_MIC), SND_PCI_QUIRK(0x1043, 0x1f43, "ASUS Zenbook S16", SOC_SDW_CODEC_MIC), SND_PCI_QUIRK(0x17aa, 0x2347, "Lenovo P16", SOC_SDW_CODEC_MIC), SND_PCI_QUIRK(0x17aa, 0x2348, "Lenovo P16", SOC_SDW_CODEC_MIC), SND_PCI_QUIRK(0x17aa, 0x2349, "Lenovo P1", SOC_SDW_CODEC_MIC), SND_PCI_QUIRK(0x17aa, 0x3821, "Lenovo 0x3821", SOC_SDW_SIDECAR_AMPS), + SND_PCI_QUIRK(0x17aa, 0x383c, "Lenovo 0x383c", SOC_SDW_SIDECAR_AMPS), {} }; diff --git a/sound/soc/meson/aiu-fifo-spdif.c b/sound/soc/meson/aiu-fifo-spdif.c index e0e00ec026dc..a9861c5d6637 100644 --- a/sound/soc/meson/aiu-fifo-spdif.c +++ b/sound/soc/meson/aiu-fifo-spdif.c @@ -24,6 +24,7 @@ #define AIU_MEM_IEC958_CONTROL_MODE_16BIT BIT(7) #define AIU_MEM_IEC958_CONTROL_MODE_LINEAR BIT(8) #define AIU_MEM_IEC958_BUF_CNTL_INIT BIT(0) +#define AIU_RST_SOFT_958_FAST BIT(2) #define AIU_FIFO_SPDIF_BLOCK 8 @@ -68,11 +69,15 @@ static int fifo_spdif_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + snd_soc_component_write(component, AIU_RST_SOFT, + AIU_RST_SOFT_958_FAST); fifo_spdif_dcu_enable(component, true); break; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: case SNDRV_PCM_TRIGGER_STOP: + snd_soc_component_write(component, AIU_RST_SOFT, + AIU_RST_SOFT_958_FAST); fifo_spdif_dcu_enable(component, false); break; default: diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c index 7925aa3f63ba..98b15a527e37 100644 --- a/sound/soc/qcom/sc8280xp.c +++ b/sound/soc/qcom/sc8280xp.c @@ -164,6 +164,7 @@ static int sc8280xp_platform_probe(struct platform_device *pdev) } static const struct of_device_id snd_sc8280xp_dt_match[] = { + {.compatible = "qcom,eliza-sndcard", "eliza"}, {.compatible = "qcom,kaanapali-sndcard", "kaanapali"}, {.compatible = "qcom,qcm6490-idp-sndcard", "qcm6490"}, {.compatible = "qcom,qcs615-sndcard", "qcs615"}, diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c index f4e22af594fa..93f511fb6190 100644 --- a/sound/soc/sunxi/sun4i-codec.c +++ b/sound/soc/sunxi/sun4i-codec.c @@ -2237,6 +2237,7 @@ static const struct sun4i_codec_quirks sun50i_h616_codec_quirks = { .reg_dac_fifoc = REG_FIELD(SUN50I_H616_CODEC_DAC_FIFOC, 0, 31), .reg_dac_txdata = SUN8I_H3_CODEC_DAC_TXDATA, .has_reset = true, + .playback_only = true, .dma_max_burst = SUN4I_DMA_MAX_BURST, }; diff --git a/sound/usb/caiaq/device.c b/sound/usb/caiaq/device.c index b20aae0caf60..a16e59248480 100644 --- a/sound/usb/caiaq/device.c +++ b/sound/usb/caiaq/device.c @@ -134,14 +134,22 @@ static void usb_ep1_command_reply_dispatch (struct urb* urb) struct device *dev = &urb->dev->dev; struct snd_usb_caiaqdev *cdev = urb->context; unsigned char *buf = urb->transfer_buffer; + unsigned int payload_len; + unsigned int copy_len; if (urb->status || !cdev) { dev_warn(dev, "received EP1 urb->status = %i\n", urb->status); return; } + if (urb->actual_length < 1) + return; + + payload_len = urb->actual_length - 1; switch(buf[0]) { case EP1_CMD_GET_DEVICE_INFO: + if (payload_len < sizeof(struct caiaq_device_spec)) + break; memcpy(&cdev->spec, buf+1, sizeof(struct caiaq_device_spec)); cdev->spec.fw_version = le16_to_cpu(cdev->spec.fw_version); dev_dbg(dev, "device spec (firmware %d): audio: %d in, %d out, " @@ -157,18 +165,21 @@ static void usb_ep1_command_reply_dispatch (struct urb* urb) wake_up(&cdev->ep1_wait_queue); break; case EP1_CMD_AUDIO_PARAMS: + if (payload_len < 1) + break; cdev->audio_parm_answer = buf[1]; wake_up(&cdev->ep1_wait_queue); break; case EP1_CMD_MIDI_READ: + if (urb->actual_length < 3 || urb->actual_length - 3 < buf[2]) + break; snd_usb_caiaq_midi_handle_input(cdev, buf[1], buf + 3, buf[2]); break; case EP1_CMD_READ_IO: if (cdev->chip.usb_id == USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_AUDIO8DJ)) { - if (urb->actual_length > sizeof(cdev->control_state)) - urb->actual_length = sizeof(cdev->control_state); - memcpy(cdev->control_state, buf + 1, urb->actual_length); + copy_len = min_t(unsigned int, payload_len, sizeof(cdev->control_state)); + memcpy(cdev->control_state, buf + 1, copy_len); wake_up(&cdev->ep1_wait_queue); break; } diff --git a/sound/usb/caiaq/input.c b/sound/usb/caiaq/input.c index eabbf41fdfb2..8d924330c54c 100644 --- a/sound/usb/caiaq/input.c +++ b/sound/usb/caiaq/input.c @@ -203,6 +203,8 @@ static void snd_caiaq_input_read_analog(struct snd_usb_caiaqdev *cdev, switch (cdev->chip.usb_id) { case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_RIGKONTROL2): + if (len < 6) + return; snd_caiaq_input_report_abs(cdev, ABS_X, buf, 2); snd_caiaq_input_report_abs(cdev, ABS_Y, buf, 0); snd_caiaq_input_report_abs(cdev, ABS_Z, buf, 1); @@ -210,11 +212,15 @@ static void snd_caiaq_input_read_analog(struct snd_usb_caiaqdev *cdev, case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_RIGKONTROL3): case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_KORECONTROLLER): case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_KORECONTROLLER2): + if (len < 6) + return; snd_caiaq_input_report_abs(cdev, ABS_X, buf, 0); snd_caiaq_input_report_abs(cdev, ABS_Y, buf, 1); snd_caiaq_input_report_abs(cdev, ABS_Z, buf, 2); break; case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_TRAKTORKONTROLX1): + if (len < 16) + return; snd_caiaq_input_report_abs(cdev, ABS_HAT0X, buf, 4); snd_caiaq_input_report_abs(cdev, ABS_HAT0Y, buf, 2); snd_caiaq_input_report_abs(cdev, ABS_HAT1X, buf, 6); diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index b4c855c25eef..703c118f9d4e 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1473,8 +1473,8 @@ sticky: if (!cval->cmask) { snd_usb_set_cur_mix_value(cval, 0, 0, cval->max); } else { + idx = 0; for (i = 0; i < MAX_CHANNELS; i++) { - idx = 0; if (cval->cmask & BIT(i)) { snd_usb_set_cur_mix_value(cval, i + 1, idx, cval->max); idx++; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 1cb588691e16..0de7c9d94259 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2210,6 +2210,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x03f0, 0x654a, /* HP 320 FHD Webcam */ QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIC_RES_16), + DEVICE_FLG(0x040b, 0x0897, /* Weltrend Semiconductor, sold as Redragon H510-PRO Wireless headset */ + QUIRK_FLAG_MIXER_GET_CUR_BROKEN), DEVICE_FLG(0x041e, 0x3000, /* Creative SB Extigy */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x041e, 0x4080, /* Creative Live Cam VF0610 */ @@ -2344,6 +2346,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */ QUIRK_FLAG_FIXED_RATE), + DEVICE_FLG(0x0ecb, 0x2125, /* JBL Quantum650 Wireless */ + QUIRK_FLAG_FIXED_RATE), DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */ QUIRK_FLAG_FIXED_RATE), DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */ @@ -2461,6 +2465,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_DSD_RAW), DEVICE_FLG(0x2708, 0x0002, /* Audient iD14 */ QUIRK_FLAG_IGNORE_CTL_ERROR), + DEVICE_FLG(0x2772, 0x0502, /* Musical Fidelity M6s DAC */ + 0), /* for avoiding QUIRK_FLAG_DSD_RAW with vendor match */ DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x2a70, 0x1881, /* OnePlus Technology (Shenzhen) Co., Ltd. BE02T */ @@ -2483,6 +2489,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_MIXER_GET_CUR_BROKEN), DEVICE_FLG(0x2fc6, 0xf06b, /* MOONDROP Moonriver2 Ti */ QUIRK_FLAG_CTL_MSG_DELAY), + DEVICE_FLG(0x2fc6, 0xf0b5, /* iBasso DC-Elite */ + QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x2fc6, 0xf0b7, /* iBasso DC07 Pro */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ diff --git a/tools/sched_ext/include/scx/cid.bpf.h b/tools/sched_ext/include/scx/cid.bpf.h index db247e42fb45..6b0b4e41b288 100644 --- a/tools/sched_ext/include/scx/cid.bpf.h +++ b/tools/sched_ext/include/scx/cid.bpf.h @@ -391,7 +391,9 @@ static __always_inline bool cmask_equal(const struct scx_cmask __arena *a, if (a->base != b->base || a->nr_cids != b->nr_cids) return false; - nr_words = CMASK_NR_WORDS(a->nr_cids); + if (a->nr_cids == 0) + return true; + nr_words = (a->base + a->nr_cids - 1) / 64 - a->base / 64 + 1; bpf_for(i, 0, CMASK_MAX_WORDS) { if (i >= nr_words) @@ -402,36 +404,6 @@ static __always_inline bool cmask_equal(const struct scx_cmask __arena *a, return true; } -/* - * True iff every bit set in @a is also set in @b over the intersection of - * their ranges. Bits of @a outside @b's range fail the test. - */ -static __always_inline bool cmask_subset(const struct scx_cmask __arena *a, - const struct scx_cmask __arena *b) -{ - u32 a_end = a->base + a->nr_cids; - u32 b_end = b->base + b->nr_cids; - u32 a_wbase = a->base / 64; - u32 b_wbase = b->base / 64; - u32 nr_words, i; - - /* any bit of @a outside @b's range is a subset violation */ - if (a->base < b->base || a_end > b_end) - return false; - - nr_words = CMASK_NR_WORDS(a->nr_cids); - bpf_for(i, 0, CMASK_MAX_WORDS) { - u32 wi_b; - - if (i >= nr_words) - break; - wi_b = a_wbase + i - b_wbase; - if (a->bits[i] & ~b->bits[wi_b]) - return false; - } - return true; -} - /** * cmask_next_set - find the first set bit at or after @cid * @m: cmask to search @@ -489,15 +461,65 @@ static __always_inline u32 cmask_first_set(const struct scx_cmask __arena *m) (cid) = cmask_next_set((m), (cid) + 1)) /* + * True iff every bit set in @a is also set in @b. Matches the kernel-side + * scx_cmask_subset(): ranges don't need to nest, and set bits of @a outside + * @b's range fail the test. + */ +static __always_inline bool cmask_subset(const struct scx_cmask __arena *a, + const struct scx_cmask __arena *b) +{ + u32 a_end = a->base + a->nr_cids; + u32 b_end = b->base + b->nr_cids; + u32 a_wbase = a->base / 64; + u32 b_wbase = b->base / 64; + u32 lo = a->base > b->base ? a->base : b->base; + u32 hi = a_end < b_end ? a_end : b_end; + u32 lo_word, hi_word, i; + + /* set bits of @a outside @b's range can't be in @b */ + if (a->base < b->base && + cmask_next_set(a, a->base) < (b->base < a_end ? b->base : a_end)) + return false; + if (a_end > b_end && + cmask_next_set(a, a->base > b_end ? a->base : b_end) < a_end) + return false; + + if (lo >= hi) + return true; + + /* + * Walk the words the range intersection spans. Plain word tests + * suffice: the scans above guarantee @a has no set bit outside @b's + * range and padding bits are kept clear by all cmask helpers. + */ + lo_word = lo / 64; + hi_word = (hi - 1) / 64; + + bpf_for(i, 0, CMASK_MAX_WORDS) { + u32 w = lo_word + i; + + if (w > hi_word) + break; + if (a->bits[w - a_wbase] & ~b->bits[w - b_wbase]) + return false; + } + return true; +} + +/* * Population count over [base, base + nr_cids). Padding bits in the head/tail * words are guaranteed zero by the mutating helpers, so a flat popcount over - * all words is correct. + * the words the range spans is correct. */ static __always_inline u32 cmask_weight(const struct scx_cmask __arena *m) { - u32 nr_words = CMASK_NR_WORDS(m->nr_cids), i; + u32 nr_words, i; u32 count = 0; + if (!m->nr_cids) + return 0; + nr_words = (m->base + m->nr_cids - 1) / 64 - m->base / 64 + 1; + bpf_for(i, 0, CMASK_MAX_WORDS) { if (i >= nr_words) break; diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index d4f845c32804..a329f901c5ed 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -84,6 +84,7 @@ static void find_controls(void) if (err < 0) { ksft_print_msg("Failed to get hctl for card %d: %s\n", card, snd_strerror(err)); + free(card_data); goto next_card; } @@ -339,9 +340,9 @@ static bool ctl_value_index_valid(struct ctl_data *ctl, } if (int64_val > snd_ctl_elem_info_get_max64(ctl->info)) { - ksft_print_msg("%s.%d value %lld more than maximum %ld\n", + ksft_print_msg("%s.%d value %lld more than maximum %lld\n", ctl->name, index, int64_val, - snd_ctl_elem_info_get_max(ctl->info)); + snd_ctl_elem_info_get_max64(ctl->info)); return false; } diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index adb25146e88c..ea7044f30adc 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -82,6 +82,7 @@ CONFIG_NET_SCH_BPF=y CONFIG_NET_SCH_FQ=y CONFIG_NET_SCH_INGRESS=y CONFIG_NET_SCH_HTB=y +CONFIG_NET_SCH_RED=y CONFIG_NET_SCHED=y CONFIG_NETDEVSIM=y CONFIG_NETFILTER=y diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_implicit_args_tracing.c b/tools/testing/selftests/bpf/prog_tests/kfunc_implicit_args_tracing.c new file mode 100644 index 000000000000..61cc5aaba025 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_implicit_args_tracing.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include "kfunc_implicit_args_tracing.skel.h" + +void test_kfunc_implicit_args_tracing(void) +{ + struct kfunc_implicit_args_tracing *skel; + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, fd; + + skel = kfunc_implicit_args_tracing__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + err = kfunc_implicit_args_tracing__attach(skel); + if (!ASSERT_OK(err, "attach")) + goto cleanup; + + fd = bpf_program__fd(skel->progs.trigger_implicit_arg); + err = bpf_prog_test_run_opts(fd, &topts); + if (!ASSERT_OK(err, "test_run")) + goto cleanup; + + ASSERT_EQ(topts.retval, 5, "kfunc_retval"); + ASSERT_EQ(skel->bss->fentry_arg_cnt, 2, "fentry_arg_cnt"); + ASSERT_NEQ(skel->bss->fentry_aux_arg, 0, "fentry_aux_arg"); + ASSERT_EQ(skel->bss->fentry_result, 1, "fentry_result"); + ASSERT_EQ(skel->bss->fexit_arg_cnt, 2, "fexit_arg_cnt"); + ASSERT_NEQ(skel->bss->fexit_aux_arg, 0, "fexit_aux_arg"); + ASSERT_EQ(skel->bss->fexit_result, 1, "fexit_result"); + +cleanup: + kfunc_implicit_args_tracing__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_bad_access.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_bad_access.c new file mode 100644 index 000000000000..b8538fc4fc3f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_bad_access.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "test_kmods/bpf_testmod.h" +#include "bpf_util.h" + +static void check_attach_reject(const struct bpf_insn *program, size_t prog_len) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts); + char error[4096]; + int bpf_fd, tp_fd; + + opts.log_level = 2; + opts.log_buf = error; + opts.log_size = sizeof(error); + + bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2", + program, prog_len, &opts); + if (!ASSERT_GE(bpf_fd, 0, "prog_load")) + return; + + tp_fd = bpf_raw_tracepoint_open("bpf_testmod_test_writable_bare_tp", bpf_fd); + ASSERT_EQ(tp_fd, -EINVAL, "bpf_raw_tracepoint_open"); + if (tp_fd >= 0) + close(tp_fd); + + close(bpf_fd); +} + +void test_raw_tp_writable_reject_bad_access(void) +{ + const struct bpf_insn program[] = { + /* r6 is our tp buffer */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + /* one byte beyond the end of the writable context */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, + sizeof(struct bpf_testmod_test_writable_ctx)), + BPF_EXIT_INSN(), + }; + + const struct bpf_insn negative_var_off_program[] = { + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + /* make var_off negative, but keep the effective access offset non-negative */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + /* one byte beyond the end of the writable context */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, + sizeof(struct bpf_testmod_test_writable_ctx) + 8), + BPF_EXIT_INSN(), + }; + + if (test__start_subtest("past_end")) + check_attach_reject(program, ARRAY_SIZE(program)); + + if (test__start_subtest("negative_var_off_past_end")) + check_attach_reject(negative_var_off_program, + ARRAY_SIZE(negative_var_off_program)); +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c deleted file mode 100644 index 216b0dfac0fe..000000000000 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <test_progs.h> -#include <linux/nbd.h> -#include "bpf_util.h" - -void test_raw_tp_writable_reject_nbd_invalid(void) -{ - __u32 duration = 0; - char error[4096]; - int bpf_fd = -1, tp_fd = -1; - - const struct bpf_insn program[] = { - /* r6 is our tp buffer */ - BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), - /* one byte beyond the end of the nbd_request struct */ - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, - sizeof(struct nbd_request)), - BPF_EXIT_INSN(), - }; - - LIBBPF_OPTS(bpf_prog_load_opts, opts, - .log_level = 2, - .log_buf = error, - .log_size = sizeof(error), - ); - - bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2", - program, ARRAY_SIZE(program), - &opts); - if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable load", - "failed: %d errno %d\n", bpf_fd, errno)) - return; - - tp_fd = bpf_raw_tracepoint_open("nbd_send_request", bpf_fd); - if (CHECK(tp_fd >= 0, "bpf_raw_tracepoint_writable open", - "erroneously succeeded\n")) - goto out_bpffd; - - close(tp_fd); -out_bpffd: - close(bpf_fd); -} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index cb3229711f93..e5fc038d747b 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -853,7 +853,7 @@ static void test_sockmap_many_socket(void) return; } - udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0); + udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK); if (udp < 0) { close(dgram); close(tcp); @@ -922,7 +922,7 @@ static void test_sockmap_many_maps(void) return; } - udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0); + udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK); if (udp < 0) { close(dgram); close(tcp); @@ -993,7 +993,7 @@ static void test_sockmap_same_sock(void) return; } - udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0); + udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK); if (udp < 0) { close(dgram); close(tcp); @@ -1373,6 +1373,43 @@ end: test_sockmap_pass_prog__destroy(skel); } +/* A socket in a sockmap without a verdict program keeps its ingress data + * in sk_receive_queue: FIONREAD must account for it. + */ +static void test_sockmap_no_verdict_fionread(void) +{ + int err, map, zero = 0, sent, avail; + int c0 = -1, c1 = -1, p0 = -1, p1 = -1; + struct test_sockmap_pass_prog *skel; + char buf[256] = "0123456789"; + + skel = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = create_socket_pairs(AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs()")) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + + sent = xsend(p1, &buf, sizeof(buf), 0); + ASSERT_EQ(sent, sizeof(buf), "xsend(p1)"); + avail = wait_for_fionread(c1, sizeof(buf), IO_TIMEOUT_SEC); + ASSERT_EQ(avail, sizeof(buf), "ioctl(FIONREAD)"); + +out_close: + close(c0); + close(p0); + close(c1); + close(p1); +out: + test_sockmap_pass_prog__destroy(skel); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -1415,6 +1452,8 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_shutdown(); if (test__start_subtest("sockmap skb_verdict fionread")) test_sockmap_skb_verdict_fionread(true); + if (test__start_subtest("sockmap no_verdict fionread")) + test_sockmap_no_verdict_fionread(); if (test__start_subtest("sockmap skb_verdict fionread on drop")) test_sockmap_skb_verdict_fionread(false); if (test__start_subtest("sockmap skb_verdict change tail")) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index cc0c68bab907..1c96a3cf4b97 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -53,8 +53,8 @@ static void test_insert_opened(struct test_sockmap_listen *skel __always_unused, int family, int sotype, int mapfd) { u32 key = 0; - u64 value; int err, s; + u64 value; s = xsocket(family, sotype, 0); if (s == -1) @@ -63,11 +63,8 @@ static void test_insert_opened(struct test_sockmap_listen *skel __always_unused, errno = 0; value = s; err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); - if (sotype == SOCK_STREAM) { - if (!err || errno != EOPNOTSUPP) - FAIL_ERRNO("map_update: expected EOPNOTSUPP"); - } else if (err) - FAIL_ERRNO("map_update: expected success"); + ASSERT_ERR(err, "map_update"); + ASSERT_EQ(errno, EOPNOTSUPP, "errno"); xclose(s); } @@ -77,8 +74,8 @@ static void test_insert_bound(struct test_sockmap_listen *skel __always_unused, struct sockaddr_storage addr; socklen_t len = 0; u32 key = 0; - u64 value; int err, s; + u64 value; init_addr_loopback(family, &addr, &len); @@ -93,8 +90,12 @@ static void test_insert_bound(struct test_sockmap_listen *skel __always_unused, errno = 0; value = s; err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); - if (!err || errno != EOPNOTSUPP) - FAIL_ERRNO("map_update: expected EOPNOTSUPP"); + if (sotype == SOCK_STREAM) { + ASSERT_ERR(err, "map_update"); + ASSERT_EQ(errno, EOPNOTSUPP, "errno"); + } else { + ASSERT_OK(err, "map_update"); + } close: xclose(s); } @@ -1289,7 +1290,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, /* insert */ TEST(test_insert_invalid), TEST(test_insert_opened), - TEST(test_insert_bound, SOCK_STREAM), + TEST(test_insert_bound), TEST(test_insert), /* delete */ TEST(test_delete_after_insert), diff --git a/tools/testing/selftests/bpf/prog_tests/tc_qevent.c b/tools/testing/selftests/bpf/prog_tests/tc_qevent.c new file mode 100644 index 000000000000..67e1d17567ab --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_qevent.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <network_helpers.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <unistd.h> +#include <string.h> + +#include "test_tc_qevent.skel.h" + +#define NS_TX "tc_qevent_tx" +#define NS_RX "tc_qevent_rx" +#define IP_TX "10.255.0.1" +#define IP_RX "10.255.0.2" +#define PIN_PATH "/sys/fs/bpf/tc_qevent_redirect" + +static void blast_udp(void) +{ + struct sockaddr_in dst = {}; + char buf[1400] = {}; + int fd, i; + + fd = socket(AF_INET, SOCK_DGRAM, 0); + if (!ASSERT_GE(fd, 0, "udp socket")) + return; + + dst.sin_family = AF_INET; + dst.sin_port = htons(12345); + inet_pton(AF_INET, IP_RX, &dst.sin_addr); + + /* + * Push far more than the RED queue can hold. Once qavg crosses qth_min + * every further packet hits the congestion_drop / early_drop qevent. + */ + for (i = 0; i < 50000; i++) + sendto(fd, buf, sizeof(buf), MSG_DONTWAIT, + (struct sockaddr *)&dst, sizeof(dst)); + + close(fd); +} + +static void run_qevent_redirect(struct bpf_program *prog, __u64 *counter) +{ + struct nstoken *tok = NULL; + int err; + + SYS_NOFAIL("ip netns del %s", NS_TX); + SYS_NOFAIL("ip netns del %s", NS_RX); + unlink(PIN_PATH); + + err = bpf_program__pin(prog, PIN_PATH); + if (!ASSERT_OK(err, "pin prog")) + return; + + SYS(unpin, "ip netns add %s", NS_TX); + SYS(del_tx, "ip netns add %s", NS_RX); + SYS(del_rx, "ip -n %s link add veth0 type veth peer name veth1 netns %s", NS_TX, NS_RX); + SYS(del_rx, "ip -n %s addr add %s/24 dev veth0", NS_TX, IP_TX); + SYS(del_rx, "ip -n %s link set veth0 up", NS_TX); + SYS(del_rx, "ip -n %s addr add %s/24 dev veth1", NS_RX, IP_RX); + SYS(del_rx, "ip -n %s link set veth1 up", NS_RX); + + tok = open_netns(NS_TX); + if (!ASSERT_OK_PTR(tok, "open_netns")) + goto del_rx; + + SYS(close_ns, "tc qdisc add dev veth0 root handle 1: htb default 1"); + SYS(close_ns, "tc class add dev veth0 parent 1: classid 1:1 htb rate 1mbit ceil 1mbit"); + + if (system("tc qdisc add dev veth0 parent 1:1 handle 11: red " + "limit 500000 avpkt 1000 probability 1 min 5000 max 6000 " + "burst 6 qevent early_drop block 10 2>/dev/null")) { + test__skip(); + goto close_ns; + } + + if (system("tc filter add block 10 bpf da object-pinned " + PIN_PATH " 2>/dev/null")) { + test__skip(); + goto close_ns; + } + + blast_udp(); + ASSERT_GT(*counter, 0, "qevent classifier ran"); +close_ns: + close_netns(tok); +del_rx: + SYS_NOFAIL("ip netns del %s", NS_RX); +del_tx: + SYS_NOFAIL("ip netns del %s", NS_TX); +unpin: + bpf_program__unpin(prog, PIN_PATH); +} + +void test_tc_qevent(void) +{ + struct test_tc_qevent *skel; + + skel = test_tc_qevent__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + if (test__start_subtest("redirect_verdict")) + run_qevent_redirect(skel->progs.qevent_redirect_verdict, + &skel->bss->verdict_calls); + if (test__start_subtest("redirect_helper")) + run_qevent_redirect(skel->progs.qevent_redirect_helper, + &skel->bss->helper_calls); + + test_tc_qevent__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 8a3d69e2453c..be97f6887f0e 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -78,6 +78,7 @@ #include "verifier_precision.skel.h" #include "verifier_prevent_map_lookup.skel.h" #include "verifier_private_stack.skel.h" +#include "verifier_ptr_to_buf.skel.h" #include "verifier_raw_stack.skel.h" #include "verifier_raw_tp_writable.skel.h" #include "verifier_reg_equal.skel.h" @@ -230,6 +231,7 @@ void test_verifier_or_jmp32_k(void) { RUN(verifier_or_jmp32_k); } void test_verifier_precision(void) { RUN(verifier_precision); } void test_verifier_prevent_map_lookup(void) { RUN(verifier_prevent_map_lookup); } void test_verifier_private_stack(void) { RUN(verifier_private_stack); } +void test_verifier_ptr_to_buf(void) { RUN(verifier_ptr_to_buf); } void test_verifier_raw_stack(void) { RUN(verifier_raw_stack); } void test_verifier_raw_tp_writable(void) { RUN(verifier_raw_tp_writable); } void test_verifier_reg_equal(void) { RUN(verifier_reg_equal); } diff --git a/tools/testing/selftests/bpf/progs/kfunc_implicit_args_tracing.c b/tools/testing/selftests/bpf/progs/kfunc_implicit_args_tracing.c new file mode 100644 index 000000000000..995f8b8b5b9e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_implicit_args_tracing.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <errno.h> + +extern int bpf_kfunc_implicit_arg(int a) __weak __ksym; + +char _license[] SEC("license") = "GPL"; + +/* Shared arg checks; reports arg count and aux, returns 1 on success. */ +static __always_inline __u64 +check_implicit_args(void *ctx, __u64 *arg_cnt, __u64 *aux_arg) +{ + __u64 a = 0, aux = 0, z = 0; + __u64 result; + __s64 err; + + *arg_cnt = bpf_get_func_arg_cnt(ctx); + result = *arg_cnt == 2; + + err = bpf_get_func_arg(ctx, 0, &a); + result &= err == 0 && (int)a == 5; + + err = bpf_get_func_arg(ctx, 1, &aux); + *aux_arg = aux; + result &= err == 0 && aux != 0; + + err = bpf_get_func_arg(ctx, 2, &z); + result &= err == -EINVAL; + + return result; +} + +__u64 fentry_result; +__u64 fentry_arg_cnt; +__u64 fentry_aux_arg; + +SEC("fentry/bpf_kfunc_implicit_arg") +int BPF_PROG(trace_implicit_arg_fentry) +{ + __u64 ret = 0; + __s64 err; + + fentry_result = check_implicit_args(ctx, &fentry_arg_cnt, &fentry_aux_arg); + + err = bpf_get_func_ret(ctx, &ret); + fentry_result &= err == -EOPNOTSUPP; + + return 0; +} + +__u64 fexit_result; +__u64 fexit_arg_cnt; +__u64 fexit_aux_arg; + +SEC("fexit/bpf_kfunc_implicit_arg") +int BPF_PROG(trace_implicit_arg_fexit) +{ + __u64 ret = 0; + __s64 err; + + fexit_result = check_implicit_args(ctx, &fexit_arg_cnt, &fexit_aux_arg); + + err = bpf_get_func_ret(ctx, &ret); + fexit_result &= err == 0 && ret == 5; + + return 0; +} + +SEC("syscall") +int trigger_implicit_arg(void *ctx) +{ + return bpf_kfunc_implicit_arg(5); +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_qevent.c b/tools/testing/selftests/bpf/progs/test_tc_qevent.c new file mode 100644 index 000000000000..1529c111f4aa --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_qevent.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +int redirect_ifindex = 1; +__u64 verdict_calls = 0; +__u64 helper_calls = 0; + +SEC("tc") +int qevent_redirect_verdict(struct __sk_buff *skb) +{ + __sync_fetch_and_add(&verdict_calls, 1); + return TCX_REDIRECT; +} + +SEC("tc") +int qevent_redirect_helper(struct __sk_buff *skb) +{ + __sync_fetch_and_add(&helper_calls, 1); + return bpf_redirect(redirect_ifindex, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_ptr_to_buf.c b/tools/testing/selftests/bpf/progs/verifier_ptr_to_buf.c new file mode 100644 index 000000000000..12cf24db46a0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_ptr_to_buf.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("iter/bpf_map_elem") +__description("PTR_TO_BUF: reject negative const offset") +__failure +__msg("invalid negative rdwr buffer offset") +__naked void ptr_to_buf_reject_negative_const_offset(void) +{ + asm volatile ("r0 = 0; \ + r2 = *(u64 *)(r1 + %[value_off]); \ + if r2 == 0 goto l0_%=; \ + r2 += -8; \ + r0 = *(u64 *)(r2 + 0); \ +l0_%=: \ + exit; \ + " + : + : __imm_const(value_off, + offsetof(struct bpf_iter__bpf_map_elem, value)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c b/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c index 14a0172e2141..4055a6443bc2 100644 --- a/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c +++ b/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c @@ -47,4 +47,20 @@ l0_%=: /* shift the buffer pointer to a variable location */\ : __clobber_all); } +SEC("raw_tracepoint.w") +__description("raw_tracepoint_writable: reject negative const offset") +__failure +__msg("invalid negative tracepoint buffer offset") +__naked void tracepoint_writable_reject_negative_const_offset(void) +{ + asm volatile (" \ + r6 = *(u64 *)(r1 + 0); \ + r6 += -8; \ + r0 = *(u64 *)(r6 + 0); \ + exit; \ +" : + : + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index c32da7bd8be2..6a2641ee7897 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -759,16 +759,15 @@ static void test_sockmap(unsigned int tasks, void *data) goto out_sockmap; } - /* Test update with unsupported UDP socket */ + /* Test update with unsupported unbound UDP socket */ udp = socket(AF_INET, SOCK_DGRAM, 0); - i = 0; - err = bpf_map_update_elem(fd, &i, &udp, BPF_ANY); - if (err) { - printf("Failed socket update SOCK_DGRAM '%i:%i'\n", - i, udp); + CHECK(udp < 0, "socket(AF_INET, SOCK_DGRAM)", "errno:%d\n", errno); + err = bpf_map_update_elem(fd, &(int){0}, &udp, BPF_ANY); + close(udp); + if (!err) { + printf("Unexpectedly succeeded unbound UDP update '0:%i'\n", udp); goto out_sockmap; } - close(udp); /* Test update without programs */ for (i = 0; i < 6; i++) { diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index 91d4fd410914..2070e890e064 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -4,6 +4,8 @@ CONFIG_DEBUG_INFO_BTF_MODULES=n CONFIG_INET_PSP=y CONFIG_IPV6=y CONFIG_MACSEC=m +CONFIG_NET_CLS_ACT=y +CONFIG_NET_CLS_BPF=y CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_NETCONSOLE_EXTENDED_LOG=y @@ -11,6 +13,7 @@ CONFIG_NETDEVSIM=m CONFIG_NETKIT=y CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_FQ=m +CONFIG_NET_SCH_INGRESS=y CONFIG_PPP=y CONFIG_PPPOE=y CONFIG_VLAN_8021Q=m diff --git a/tools/testing/selftests/drivers/net/netconsole/netcons_cmdline.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_cmdline.sh index 96d704b8d9d9..4436567abc94 100755 --- a/tools/testing/selftests/drivers/net/netconsole/netcons_cmdline.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_cmdline.sh @@ -50,7 +50,7 @@ do # Send the message echo "${MSG}: ${TARGET}" > /dev/kmsg # Wait until socat saves the file to disk - busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" || true # Make sure the message was received in the dst part # and exit validate_msg "${OUTPUT_FILE}" diff --git a/tools/testing/selftests/drivers/net/netconsole/netcons_fragmented_msg.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_fragmented_msg.sh index 0dc7280c3080..fc3db40c1df5 100755 --- a/tools/testing/selftests/drivers/net/netconsole/netcons_fragmented_msg.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_fragmented_msg.sh @@ -104,7 +104,7 @@ wait_local_port_listen "${NAMESPACE}" "${PORT}" udp # Send the message echo "${MSG}: ${TARGET}" > /dev/kmsg # Wait until socat saves the file to disk -busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" || true # Check if the message was not corrupted validate_fragmented_result "${OUTPUT_FILE}" @@ -117,6 +117,6 @@ disable_release_append listen_port_and_save_to "${OUTPUT_FILE}" & wait_local_port_listen "${NAMESPACE}" "${PORT}" udp echo "${MSG}: ${TARGET}" > /dev/kmsg -busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" || true validate_fragmented_result "${OUTPUT_FILE}" exit "${ksft_pass}" diff --git a/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh index cb59cf436dd0..b379dff9087e 100755 --- a/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh @@ -44,7 +44,8 @@ function trigger_reactivation() { # Restore MACs ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" \ address "${SAVED_DSTMAC}" - if [ "${BINDMODE}" == "mac" ]; then + if [ "${BINDMODE}" == "mac" ] && + [ "$(mac_get "${SRCIF}")" != "${SAVED_SRCMAC}" ]; then ip link set dev "${SRCIF}" down ip link set dev "${SRCIF}" address "${SAVED_SRCMAC}" # Rename device in order to trigger target resume, as initial @@ -107,7 +108,7 @@ do # Send the message echo "${MSG}: ${TARGET}" > /dev/kmsg # Wait until socat saves the file to disk - busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" || true # Make sure the message was received in the dst part # and exit validate_msg "${OUTPUT_FILE}" diff --git a/tools/testing/selftests/drivers/net/netconsole/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_sysdata.sh index 3fb8c4afe3d2..7089f7bd1e34 100755 --- a/tools/testing/selftests/drivers/net/netconsole/netcons_sysdata.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_sysdata.sh @@ -197,7 +197,7 @@ function runtest { # Send the message taskset -c "${CPU}" echo "${MSG}: ${TARGET}" > /dev/kmsg # Wait until socat saves the file to disk - busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" || true } # ========== # diff --git a/tools/testing/selftests/drivers/net/settings b/tools/testing/selftests/drivers/net/settings new file mode 100644 index 000000000000..eef533824a3c --- /dev/null +++ b/tools/testing/selftests/drivers/net/settings @@ -0,0 +1 @@ +timeout=360 diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc index 2915206777b6..89660a9adf44 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc @@ -16,23 +16,32 @@ echo > dynamic_events FUNC1='foo_bar*' FUNC2='vfs_read' +:;: "Save enabled functions count" ;: +ecount=`cat enabled_functions | wc -l` + +count_enabled_functions() { + count=`cat enabled_functions | wc -l` + count=$(($count-$ecount)) + echo $count +} + :;: "Add an event on the test module" ;: echo "f:test1 $FUNC1" >> dynamic_events echo 1 > events/fprobes/test1/enable :;: "Ensure it is enabled" ;: -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -ne 0 :;: "Check the enabled_functions is cleared on unloading" ;: rmmod trace-events-sample -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -eq 0 :;: "Check it is kept clean" ;: modprobe trace-events-sample echo 1 > events/fprobes/test1/enable || echo "OK" -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -eq 0 :;: "Add another event not on the test module" ;: @@ -40,19 +49,19 @@ echo "f:test2 $FUNC2" >> dynamic_events echo 1 > events/fprobes/test2/enable :;: "Ensure it is enabled" ;: -ofuncs=`cat enabled_functions | wc -l` +ofuncs=`count_enabled_functions` test $ofuncs -ne 0 :;: "Disable and remove the first event" echo 0 > events/fprobes/test1/enable echo "-:fprobes/test1" >> dynamic_events -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $ofuncs -eq $funcs :;: "Disable and remove other events" ;: echo 0 > events/fprobes/enable echo > dynamic_events -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -eq 0 rmmod trace-events-sample @@ -63,12 +72,12 @@ echo "f:test1 $FUNC1" >> dynamic_events echo 1 > events/fprobes/test1/enable echo "f:test2 $FUNC2" >> dynamic_events echo 1 > events/fprobes/test2/enable -ofuncs=`cat enabled_functions | wc -l` +ofuncs=`count_enabled_functions` test $ofuncs -ne 0 :;: "Unload module (ftrace entry should be removed)" ;: rmmod trace-events-sample -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -ne 0 test $ofuncs -ne $funcs @@ -77,7 +86,7 @@ echo 0 > events/fprobes/test2/enable echo "-:fprobes/test2" >> dynamic_events :;: "Ensure ftrace is disabled." ;: -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -eq 0 echo 0 > events/fprobes/enable diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc index 8d275e3238d9..04eb8546fc07 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test poll wait on histogram -# requires: set_event events/sched/sched_process_free/trigger events/sched/sched_process_free/hist +# requires: set_event events/sched/sched_process_exit/trigger events/sched/sched_process_exit/hist # flags: instance POLL=${FTRACETEST_ROOT}/poll @@ -11,7 +11,7 @@ if [ ! -x ${POLL} ]; then exit_unresolved fi -EVENT=events/sched/sched_process_free/ +EVENT=events/sched/sched_process_exit/ # Check poll ops is supported. Before implementing poll on hist file, it # returns soon with POLLIN | POLLOUT, but not POLLPRI. diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index d28a057fa6c2..6fc34e9bf8e1 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -174,6 +174,7 @@ TEST_GEN_PROGS_arm64 += arm64/hello_el2 TEST_GEN_PROGS_arm64 += arm64/host_sve TEST_GEN_PROGS_arm64 += arm64/hypercalls TEST_GEN_PROGS_arm64 += arm64/external_aborts +TEST_GEN_PROGS_arm64 += arm64/mmio_sign_ext TEST_GEN_PROGS_arm64 += arm64/page_fault_test TEST_GEN_PROGS_arm64 += arm64/psci_test TEST_GEN_PROGS_arm64 += arm64/sea_to_user diff --git a/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c b/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c new file mode 100644 index 000000000000..25196f1e6322 --- /dev/null +++ b/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mmio_sign_ext - Test sign-extending MMIO load emulation (LDRSB/LDRSH/LDRSW) + * + * Copyright (c) 2026 Google LLC + * Author: Fuad Tabba <fuad.tabba@linux.dev> + */ + +#include <asm/ptrace.h> + +#include "processor.h" +#include "test_util.h" + +#define MMIO_ADDR 0x8000000ULL + +/* AP[1]: allow unprivileged (EL0) access to a mapping. */ +#define PTE_USER BIT(6) + +/* SPSR for ERET to EL0t with DAIF masked. */ +#define SPSR_EL0 (PSR_MODE_EL0t | PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) + +struct mmio_test { + const char *name; + uint64_t data; /* access-width value, host byte order */ + uint8_t len; + uint64_t expected; /* sign-extended result; same for LE and BE */ +}; + +/* Paired 1:1, in order, with the loads in guest_loads_le() and el0_be_loads. */ +static const struct mmio_test tests[] = { + /* LDRSB Xt: byte sign-extended to 64 bits */ + { "LDRSB Xt 0xFF", 0xFF, 1, 0xFFFFFFFFFFFFFFFFULL }, + { "LDRSB Xt 0x7F", 0x7F, 1, 0x7FULL }, + + /* LDRSB Wt: byte sign-extended to 32 bits, upper 32 bits zeroed */ + { "LDRSB Wt 0xFF", 0xFF, 1, 0xFFFFFFFFULL }, + { "LDRSB Wt 0x7F", 0x7F, 1, 0x7FULL }, + + /* LDRSH Xt: halfword sign-extended to 64 bits */ + { "LDRSH Xt 0x8001", 0x8001, 2, 0xFFFFFFFFFFFF8001ULL }, + { "LDRSH Xt 0x7FFF", 0x7FFF, 2, 0x7FFFULL }, + + /* LDRSH Wt: halfword sign-extended to 32 bits, upper 32 bits zeroed */ + { "LDRSH Wt 0x8001", 0x8001, 2, 0xFFFF8001ULL }, + { "LDRSH Wt 0x7FFF", 0x7FFF, 2, 0x7FFFULL }, + + /* LDRSW Xt: word sign-extended to 64 bits (no Wt form) */ + { "LDRSW Xt 0x80000001", 0x80000001, 4, 0xFFFFFFFF80000001ULL }, + { "LDRSW Xt 0x7FFFFFFF", 0x7FFFFFFF, 4, 0x7FFFFFFFULL }, +}; + +/* Issue one sign-extending load from MMIO and report the result. */ +#define GUEST_LDRS(load) do { \ + uint64_t val; \ + \ + asm volatile(load : "=r"(val) : "r"(MMIO_ADDR) : "memory"); \ + GUEST_SYNC(val); \ +} while (0) + +/* Little-endian pass: loads issued at EL1. */ +static void guest_loads_le(void) +{ + GUEST_LDRS("ldrsb %0, [%1]"); + GUEST_LDRS("ldrsb %0, [%1]"); + GUEST_LDRS("ldrsb %w0, [%1]"); + GUEST_LDRS("ldrsb %w0, [%1]"); + GUEST_LDRS("ldrsh %0, [%1]"); + GUEST_LDRS("ldrsh %0, [%1]"); + GUEST_LDRS("ldrsh %w0, [%1]"); + GUEST_LDRS("ldrsh %w0, [%1]"); + GUEST_LDRS("ldrsw %0, [%1]"); + GUEST_LDRS("ldrsw %0, [%1]"); +} + +/* + * Run the big-endian loads at EL0, where SCTLR_EL1.E0E flips only the data + * endianness; at EL1, SCTLR_EL1.EE would also flip the page-table walk and + * fault on the little-endian tables. x0 holds MMIO_ADDR; results return in + * x19..x28 (tests[] order) via a single SVC. + */ +extern char el0_be_loads[]; +asm( +" .pushsection .text, \"ax\"\n" +" .global el0_be_loads\n" +"el0_be_loads:\n" +" ldrsb x19, [x0]\n" +" ldrsb x20, [x0]\n" +" ldrsb w21, [x0]\n" +" ldrsb w22, [x0]\n" +" ldrsh x23, [x0]\n" +" ldrsh x24, [x0]\n" +" ldrsh w25, [x0]\n" +" ldrsh w26, [x0]\n" +" ldrsw x27, [x0]\n" +" ldrsw x28, [x0]\n" +" svc #0\n" +" .popsection\n" +); + +/* EL1 handler for the EL0 SVC: report the results, then finish. */ +static void el0_svc_handler(struct ex_regs *regs) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(tests); i++) + GUEST_SYNC(regs->regs[19 + i]); + + GUEST_DONE(); +} + +static bool guest_mixed_endian_el0(void) +{ + uint64_t mmfr0 = read_sysreg(id_aa64mmfr0_el1); + + return SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGEND, mmfr0) || + SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGENDEL0, mmfr0); +} + +static void guest_code(void) +{ + guest_loads_le(); + + if (guest_mixed_endian_el0()) { + write_sysreg(read_sysreg(sctlr_el1) | SCTLR_EL1_E0E, sctlr_el1); + isb(); + + asm volatile( + " msr elr_el1, %[pc]\n" + " msr spsr_el1, %[spsr]\n" + " mov x0, %[mmio]\n" + " isb\n" + " eret\n" + : + : [pc] "r"(el0_be_loads), + [spsr] "r"((uint64_t)SPSR_EL0), + [mmio] "r"(MMIO_ADDR) + : "x0", "memory"); + __builtin_unreachable(); /* el0_svc_handler ends the test */ + } + + GUEST_DONE(); +} + +static void handle_mmio(struct kvm_run *run, const struct mmio_test *t, bool be) +{ + int i; + + TEST_ASSERT_EQ(run->mmio.phys_addr, MMIO_ADDR); + TEST_ASSERT(!run->mmio.is_write, "Expected MMIO read for %s", t->name); + TEST_ASSERT_EQ(run->mmio.len, t->len); + + memset(run->mmio.data, 0, sizeof(run->mmio.data)); + if (be) { + /* The guest reads the device bytes most-significant first. */ + for (i = 0; i < t->len; i++) + run->mmio.data[i] = t->data >> (8 * (t->len - 1 - i)); + } else { + /* Works because arm64 KVM hosts are always little-endian. */ + memcpy(run->mmio.data, &t->data, t->len); + } +} + +static void expect_sync(struct kvm_vcpu *vcpu, struct ucall *uc, + const struct mmio_test *t) +{ + switch (get_ucall(vcpu, uc)) { + case UCALL_SYNC: + TEST_ASSERT(uc->args[1] == t->expected, + "%s: got %#lx, want %#lx", t->name, + (unsigned long)uc->args[1], (unsigned long)t->expected); + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(*uc); + break; + default: + TEST_FAIL("Unexpected ucall for %s", t->name); + } +} + +/* OR PTE_USER into the leaf descriptors covering [gva, gva + len). */ +static void make_el0_accessible(struct kvm_vm *vm, uint64_t gva, uint64_t len) +{ + uint64_t addr; + + for (addr = gva & ~((uint64_t)vm->page_size - 1); addr < gva + len; + addr += vm->page_size) + *virt_get_pte_hva(vm, addr) |= PTE_USER; +} + +static bool vcpu_mixed_endian_el0(struct kvm_vcpu *vcpu) +{ + uint64_t mmfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1)); + + return SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGEND, mmfr0) || + SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGENDEL0, mmfr0); +} + +int main(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + unsigned int i; + bool be; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + virt_map(vm, MMIO_ADDR, MMIO_ADDR, 1); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + vm_install_sync_handler(vm, VECTOR_SYNC_LOWER_64, ESR_ELx_EC_SVC64, + el0_svc_handler); + + be = vcpu_mixed_endian_el0(vcpu); + if (be) + make_el0_accessible(vm, MMIO_ADDR, vm->page_size); + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(tests) * (be ? 2 : 1)); + + /* Little-endian pass: one load and one result per iteration. */ + for (i = 0; i < ARRAY_SIZE(tests); i++) { + const struct mmio_test *t = &tests[i]; + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_MMIO); + handle_mmio(vcpu->run, t, false); + + vcpu_run(vcpu); + expect_sync(vcpu, &uc, t); + + ksft_test_result_pass("%s\n", t->name); + } + + if (be) { + /* The EL0 stub issues all the loads, then reports the results. */ + for (i = 0; i < ARRAY_SIZE(tests); i++) { + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_MMIO); + handle_mmio(vcpu->run, &tests[i], true); + } + for (i = 0; i < ARRAY_SIZE(tests); i++) { + vcpu_run(vcpu); + expect_sync(vcpu, &uc, &tests[i]); + ksft_test_result_pass("BE %s\n", tests[i].name); + } + } + + vcpu_run(vcpu); + TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE, "Expected UCALL_DONE"); + + kvm_vm_free(vm); + + ksft_finished(); +} diff --git a/tools/testing/selftests/kvm/x86/sev_init2_tests.c b/tools/testing/selftests/kvm/x86/sev_init2_tests.c index 8db88c355f16..689390c10f7c 100644 --- a/tools/testing/selftests/kvm/x86/sev_init2_tests.c +++ b/tools/testing/selftests/kvm/x86/sev_init2_tests.c @@ -130,12 +130,18 @@ int main(int argc, char *argv[]) KVM_X86_SEV_VMSA_FEATURES, &supported_vmsa_features); - have_sev = kvm_cpu_has(X86_FEATURE_SEV); - TEST_ASSERT(have_sev == !!(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM)), - "sev: KVM_CAP_VM_TYPES (%x) does not match cpuid (checking %x)", - kvm_check_cap(KVM_CAP_VM_TYPES), 1 << KVM_X86_SEV_VM); + /* + * Whether a VM type is available depends on KVM, not just CPUID: e.g. + * when all SEV ASIDs are assigned to SEV-SNP, KVM does not offer the + * SEV VM type even though X86_FEATURE_SEV is set. Derive availability + * from KVM_CAP_VM_TYPES and only assert the one-way implication that a + * type offered by KVM must also be reported in CPUID. + */ + have_sev = kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM); + TEST_ASSERT(!have_sev || kvm_cpu_has(X86_FEATURE_SEV), + "sev: SEV_VM supported without SEV in CPUID"); - TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM)); + TEST_REQUIRE(have_sev); have_sev_es = kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_ES_VM); TEST_ASSERT(!have_sev_es || kvm_cpu_has(X86_FEATURE_SEV_ES), diff --git a/tools/testing/selftests/kvm/x86/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c index 42bc023d5193..d59abb198d86 100644 --- a/tools/testing/selftests/kvm/x86/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c @@ -313,6 +313,49 @@ out: kvm_vm_free(vm_no_vcpu); } +static void test_sev_snp_migrate_reject(void) +{ + struct kvm_vm *src_vm, *dst_vm; + int ret; + + src_vm = vm_create_barebones_type(KVM_X86_SNP_VM); + snp_vm_init(src_vm); + __vm_vcpu_add(src_vm, 0); + vm_sev_launch(src_vm, snp_default_policy(), NULL); + + dst_vm = vm_create_barebones_type(KVM_X86_SNP_VM); + __vm_vcpu_add(dst_vm, 0); + + ret = __sev_migrate_from(dst_vm, src_vm); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "SNP VM migration should be rejected. ret: %d, errno: %d", + ret, errno); + + kvm_vm_free(src_vm); + kvm_vm_free(dst_vm); +} + +static void test_sev_snp_mirror_reject(void) +{ + struct kvm_vm *src_vm, *dst_vm; + int ret; + + src_vm = vm_create_barebones_type(KVM_X86_SNP_VM); + snp_vm_init(src_vm); + __vm_vcpu_add(src_vm, 0); + vm_sev_launch(src_vm, snp_default_policy(), NULL); + + dst_vm = aux_vm_create(false); + + ret = __sev_mirror_create(dst_vm, src_vm); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "SNP VM mirroring should be rejected. ret: %d, errno: %d", + ret, errno); + + kvm_vm_free(src_vm); + kvm_vm_free(dst_vm); +} + static void test_sev_move_copy(void) { struct kvm_vm *dst_vm, *dst2_vm, *dst3_vm, *sev_vm, *mirror_vm, @@ -384,12 +427,16 @@ int main(int argc, char *argv[]) test_sev_migrate_parameters(); if (kvm_has_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) test_sev_move_copy(); + if (kvm_cpu_has(X86_FEATURE_SEV_SNP)) + test_sev_snp_migrate_reject(); } if (kvm_has_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { test_sev_mirror(/* es= */ false); if (have_sev_es) test_sev_mirror(/* es= */ true); test_sev_mirror_parameters(); + if (kvm_cpu_has(X86_FEATURE_SEV_SNP)) + test_sev_snp_mirror_reject(); } return 0; } diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c index 6b2cbe2a90b7..bf27b6187afa 100644 --- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c @@ -247,7 +247,14 @@ int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); - test_sev_smoke(guest_sev_code, KVM_X86_SEV_VM, 0); + /* + * Only exercise VM types the host actually offers. CPUID reporting + * SEV does not guarantee KVM offers the SEV VM type: when all SEV + * ASIDs are assigned to SEV-SNP, KVM_X86_SEV_VM is unavailable even + * though X86_FEATURE_SEV is set. Gate every type on KVM_CAP_VM_TYPES. + */ + if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM)) + test_sev_smoke(guest_sev_code, KVM_X86_SEV_VM, 0); if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_ES_VM)) test_sev_smoke(guest_sev_es_code, KVM_X86_SEV_ES_VM, SEV_POLICY_ES); diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index 2ed1f76b7a8b..be2eb88092fb 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -1281,6 +1281,103 @@ TEST_F(protocol, connect_unspec) EXPECT_EQ(0, close(bind_fd)); } +TEST_F(protocol, tcp_fastopen) +{ + const bool restricted = variant->sandbox == TCP_SANDBOX && + variant->prot.type == SOCK_STREAM && + (variant->prot.protocol == IPPROTO_TCP || + variant->prot.protocol == IPPROTO_IP) && + (variant->prot.domain == AF_INET || + variant->prot.domain == AF_INET6); + const struct landlock_ruleset_attr ruleset_attr = { + .handled_access_net = LANDLOCK_ACCESS_NET_CONNECT_TCP, + }; + int bind_fd, client_fd, status; + char buf; + pid_t child; + + bind_fd = socket_variant(&self->srv0); + ASSERT_LE(0, bind_fd); + EXPECT_EQ(0, bind_variant(bind_fd, &self->srv0)); + if (self->srv0.protocol.type == SOCK_STREAM) + EXPECT_EQ(0, listen(bind_fd, backlog)); + + child = fork(); + ASSERT_LE(0, child); + if (child == 0) { + int connect_fd, ret; + + /* Closes listening socket for the child. */ + EXPECT_EQ(0, close(bind_fd)); + + connect_fd = socket_variant(&self->srv0); + ASSERT_LE(0, connect_fd); + + if (variant->sandbox == TCP_SANDBOX) { + const int ruleset_fd = landlock_create_ruleset( + &ruleset_attr, sizeof(ruleset_attr), 0); + ASSERT_LE(0, ruleset_fd); + + enforce_ruleset(_metadata, ruleset_fd); + EXPECT_EQ(0, close(ruleset_fd)); + } + + /* Fast Open with no address. */ + ret = sendto_variant(connect_fd, NULL, NULL, 0, MSG_FASTOPEN); + if (self->srv0.protocol.domain == AF_UNIX) { + EXPECT_EQ(-ENOTCONN, ret); + } else if (self->srv0.protocol.type == SOCK_DGRAM) { + EXPECT_EQ(-EDESTADDRREQ, ret); + } else { + EXPECT_EQ(-EINVAL, ret); + } + + /* Fast Open to a denied address. */ + ret = sendto_variant(connect_fd, &self->srv0, "A", 1, + MSG_FASTOPEN); + if (restricted) { + EXPECT_EQ(-EACCES, ret); + } else if (self->srv0.protocol.domain == AF_UNIX && + self->srv0.protocol.type == SOCK_STREAM) { + EXPECT_EQ(-EOPNOTSUPP, ret); + } else { + EXPECT_EQ(0, ret); + } + + EXPECT_EQ(0, close(connect_fd)); + _exit(_metadata->exit_code); + return; + } + + client_fd = bind_fd; + if (!restricted && self->srv0.protocol.type == SOCK_STREAM && + self->srv0.protocol.domain != AF_UNIX) { + client_fd = accept(bind_fd, NULL, 0); + ASSERT_LE(0, client_fd); + } + + if (restricted) { + EXPECT_EQ(-1, read(client_fd, &buf, 1)); + EXPECT_EQ(ENOTCONN, errno); + } else if (self->srv0.protocol.domain == AF_UNIX && + self->srv0.protocol.type == SOCK_STREAM) { + EXPECT_EQ(-1, read(client_fd, &buf, 1)); + EXPECT_EQ(EINVAL, errno); + } else { + EXPECT_EQ(1, read(client_fd, &buf, 1)); + EXPECT_EQ('A', buf); + } + + EXPECT_EQ(child, waitpid(child, &status, 0)); + EXPECT_EQ(1, WIFEXITED(status)); + EXPECT_EQ(EXIT_SUCCESS, WEXITSTATUS(status)); + + if (client_fd != bind_fd) + EXPECT_LE(0, close(client_fd)); + + EXPECT_EQ(0, close(bind_fd)); +} + TEST_F(protocol, sendmsg_stream) { int srv0_fd, tmp_fd, client_fd, res; diff --git a/tools/testing/selftests/landlock/scoped_signal_test.c b/tools/testing/selftests/landlock/scoped_signal_test.c index f24f2c28f62e..2d37d0c06c06 100644 --- a/tools/testing/selftests/landlock/scoped_signal_test.c +++ b/tools/testing/selftests/landlock/scoped_signal_test.c @@ -249,12 +249,12 @@ TEST_F(scoped_domains, check_access_signal) _metadata->exit_code = KSFT_FAIL; } -enum thread_return { - THREAD_INVALID = 0, - THREAD_SUCCESS = 1, - THREAD_ERROR = 2, - THREAD_TEST_FAILED = 3, -}; +/* clang-format off */ +#define THREAD_INVALID ((void *)0) +#define THREAD_SUCCESS ((void *)1) +#define THREAD_ERROR ((void *)2) +#define THREAD_TEST_FAILED ((void *)3) +/* clang-format on */ static void *thread_sync(void *arg) { @@ -262,15 +262,15 @@ static void *thread_sync(void *arg) char buf; if (read(pipe_read, &buf, 1) != 1) - return (void *)THREAD_ERROR; + return THREAD_ERROR; - return (void *)THREAD_SUCCESS; + return THREAD_SUCCESS; } TEST(signal_scoping_thread_before) { pthread_t no_sandbox_thread; - enum thread_return ret = THREAD_INVALID; + void *ret = THREAD_INVALID; int thread_pipe[2]; drop_caps(_metadata); @@ -285,7 +285,7 @@ TEST(signal_scoping_thread_before) EXPECT_EQ(0, pthread_kill(no_sandbox_thread, 0)); EXPECT_EQ(1, write(thread_pipe[1], ".", 1)); - EXPECT_EQ(0, pthread_join(no_sandbox_thread, (void **)&ret)); + EXPECT_EQ(0, pthread_join(no_sandbox_thread, &ret)); EXPECT_EQ(THREAD_SUCCESS, ret); EXPECT_EQ(0, close(thread_pipe[0])); @@ -295,7 +295,7 @@ TEST(signal_scoping_thread_before) TEST(signal_scoping_thread_after) { pthread_t scoped_thread; - enum thread_return ret = THREAD_INVALID; + void *ret = THREAD_INVALID; int thread_pipe[2]; drop_caps(_metadata); @@ -310,7 +310,7 @@ TEST(signal_scoping_thread_after) EXPECT_EQ(0, pthread_kill(scoped_thread, 0)); EXPECT_EQ(1, write(thread_pipe[1], ".", 1)); - EXPECT_EQ(0, pthread_join(scoped_thread, (void **)&ret)); + EXPECT_EQ(0, pthread_join(scoped_thread, &ret)); EXPECT_EQ(THREAD_SUCCESS, ret); EXPECT_EQ(0, close(thread_pipe[0])); @@ -327,20 +327,20 @@ void *thread_setuid(void *ptr) char buf; if (read(arg->pipe_read, &buf, 1) != 1) - return (void *)THREAD_ERROR; + return THREAD_ERROR; /* libc's setuid() should update all thread's credentials. */ if (getuid() != arg->new_uid) - return (void *)THREAD_TEST_FAILED; + return THREAD_TEST_FAILED; - return (void *)THREAD_SUCCESS; + return THREAD_SUCCESS; } TEST(signal_scoping_thread_setuid) { struct thread_setuid_args arg; pthread_t no_sandbox_thread; - enum thread_return ret = THREAD_INVALID; + void *ret = THREAD_INVALID; int pipe_parent[2]; int prev_uid; @@ -367,7 +367,7 @@ TEST(signal_scoping_thread_setuid) EXPECT_EQ(arg.new_uid, getuid()); EXPECT_EQ(1, write(pipe_parent[1], ".", 1)); - EXPECT_EQ(0, pthread_join(no_sandbox_thread, (void **)&ret)); + EXPECT_EQ(0, pthread_join(no_sandbox_thread, &ret)); EXPECT_EQ(THREAD_SUCCESS, ret); clear_cap(_metadata, CAP_SETUID); @@ -400,6 +400,24 @@ static int setup_signal_handler(int signal) return sigaction(SIGURG, &sa, NULL); } +/* + * MSG_OOB might be disabled in the kernel via the CONFIG_AF_UNIX_OOB + * switch, so this function can be used for probing for its availability. + */ +static bool has_af_unix_oob(void) +{ + bool available = false; + int sp[2]; + + if (socketpair(AF_UNIX, SOCK_STREAM, 0, sp) == 0) { + available = (send(sp[0], ".", 1, MSG_OOB) == 1); + close(sp[0]); + close(sp[1]); + } + + return available; +} + /* clang-format off */ FIXTURE(fown) {}; /* clang-format on */ @@ -462,6 +480,9 @@ TEST_F(fown, sigurg_socket) int pipe_parent[2], pipe_child[2]; pid_t child; + if (!has_af_unix_oob()) + SKIP(return, "CONFIG_AF_UNIX_OOB / MSG_OOB not available"); + memset(&server_address, 0, sizeof(server_address)); set_unix_address(&server_address, 0); @@ -667,20 +688,20 @@ static void *thread_setown_scoped(void *arg) ruleset_fd = landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); if (ruleset_fd < 0) - return (void *)THREAD_ERROR; + return THREAD_ERROR; if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) || landlock_restrict_self(ruleset_fd, 0)) { close(ruleset_fd); - return (void *)THREAD_ERROR; + return THREAD_ERROR; } close(ruleset_fd); /* Makes this process group own the SIGIO source. */ if (fcntl(fd, F_SETSIG, SIGURG) || fcntl(fd, F_SETOWN, -getpgrp()) || fcntl(fd, F_SETFL, O_ASYNC)) - return (void *)THREAD_ERROR; + return THREAD_ERROR; - return (void *)THREAD_SUCCESS; + return THREAD_SUCCESS; } /* @@ -702,7 +723,7 @@ TEST(sigio_to_pgid_self) { int trigger[2]; pthread_t thread; - enum thread_return ret = THREAD_INVALID; + void *ret = THREAD_INVALID; int i; drop_caps(_metadata); @@ -722,7 +743,7 @@ TEST(sigio_to_pgid_self) */ ASSERT_EQ(0, pthread_create(&thread, NULL, thread_setown_scoped, &trigger[0])); - ASSERT_EQ(0, pthread_join(thread, (void **)&ret)); + ASSERT_EQ(0, pthread_join(thread, &ret)); ASSERT_EQ(THREAD_SUCCESS, ret); /* Fans SIGURG out to the process group. */ diff --git a/tools/testing/selftests/net/af_unix/config b/tools/testing/selftests/net/af_unix/config index b5429c15a53c..41dbb03c747e 100644 --- a/tools/testing/selftests/net/af_unix/config +++ b/tools/testing/selftests/net/af_unix/config @@ -1,3 +1,4 @@ CONFIG_AF_UNIX_OOB=y CONFIG_UNIX=y CONFIG_UNIX_DIAG=m +CONFIG_USER_NS=y diff --git a/tools/testing/selftests/net/bridge_vlan_dump.sh b/tools/testing/selftests/net/bridge_vlan_dump.sh index ad66731d2a6f..90e18e2104e3 100755 --- a/tools/testing/selftests/net/bridge_vlan_dump.sh +++ b/tools/testing/selftests/net/bridge_vlan_dump.sh @@ -13,6 +13,7 @@ ALL_TESTS=" vlan_range_mcast_max_groups vlan_range_mcast_n_groups vlan_range_mcast_enabled + vlan_range_pvid " setup_prepare() @@ -191,6 +192,28 @@ vlan_range_mcast_enabled() log_test "VLAN range grouping with mcast_enabled" } +vlan_range_pvid() +{ + RET=0 + + ip -n "$NS" link set dev br0 type bridge vlan_default_pvid 1 + check_err $? "Failed to configure default PVID" + defer ip -n "$NS" link set dev br0 type bridge vlan_default_pvid 0 + + bridge -n "$NS" vlan add vid 2 dev dummy0 untagged + check_err $? "Failed to add VLAN 2" + defer bridge -n "$NS" vlan del vid 2 dev dummy0 + + bridge -n "$NS" -d vlan show dev dummy0 | + grep -Eq '(^|[[:space:]])2([[:space:]]|$)' + check_err $? "VLAN following PVID is missing from detailed dump" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "1-2" + check_fail $? "PVID was incorrectly included in a VLAN range" + + log_test "PVID is isolated from VLAN dump ranges" +} + # Verify the newest tested option is supported if ! bridge vlan help 2>&1 | grep -q "neigh_suppress"; then echo "SKIP: iproute2 too old, missing per-VLAN neighbor suppression support" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index e9ae1806ab07..30a809752d1b 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -212,7 +212,7 @@ make_connection() ./mptcp_connect -s MPTCP -w 300 -p $app_port -l $listen_addr > /dev/null 2>&1 & local server_pid=$! - mptcp_lib_wait_local_port_listen "${ns1}" "${port}" + mptcp_lib_wait_local_port_listen "${ns1}" "${app_port}" # Run the client, transfer $file and stay connected to the server # to conduct tests diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index 08ad07500e8a..fb1c59d45567 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -736,6 +736,61 @@ if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "on bridge"; then ret=1 fi +if ip -net "$nsr1" link show tun0 > /dev/null 2>&1 && + ip -net "$nsr2" link show tun0 > /dev/null 2>&1; then + ip -net "$nsr1" route change default via 192.168.100.2 + ip -net "$nsr2" route change default via 192.168.100.1 + ip -6 -net "$nsr1" route delete default + ip -6 -net "$nsr1" route add default via fee1:3::2 + ip -6 -net "$nsr2" route delete default + ip -6 -net "$nsr2" route add default via fee1:3::1 + ip -net "$ns2" route add default via 10.0.2.1 + ip -6 -net "$ns2" route add default via dead:2::1 + + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "tun0" tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "tun6" tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "veth0" tcp sport 12345 ct mark set 1 flow add @f1 counter name routed_repl accept' + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "br0" tcp sport 12345 ct mark set 1 flow add @f1 counter name routed_repl accept' + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "tun0" accept' + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "tun6" accept' + + ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null + + if test_tcp_forwarding "$ns1" "$ns2" 1 4 10.0.2.99 12345; then + check_counters "bridge + IPIP tunnel" + else + echo "FAIL: flow offload for ns1/ns2 with bridge + IPIP tunnel" 1>&2 + ip netns exec "$nsr1" nft list ruleset + ret=1 + fi + + if test_tcp_forwarding "$ns1" "$ns2" 1 6 "[dead:2::99]" 12345; then + check_counters "bridge + IP6IP6 tunnel" + else + echo "FAIL: flow offload for ns1/ns2 with bridge + IP6IP6 tunnel" 1>&2 + ip netns exec "$nsr1" nft list ruleset + ret=1 + fi + + ip -net "$nsr1" route change default via 192.168.10.2 + ip -net "$nsr2" route change default via 192.168.10.1 + ip -net "$ns2" route del default via 10.0.2.1 + ip -6 -net "$nsr1" route delete default + ip -6 -net "$nsr1" route add default via fee1:2::2 + ip -6 -net "$nsr2" route delete default + ip -6 -net "$nsr2" route add default via fee1:2::1 + ip -6 -net "$ns2" route del default via dead:2::1 +else + echo "SKIP: bridge + tunnel flowtable regression (tun0 missing)" + [ "$ret" -eq 0 ] && ret=$ksft_skip +fi + # Another test: # Add bridge interface br0 to Router1, with NAT and VLAN. diff --git a/tools/testing/selftests/net/openvswitch/config b/tools/testing/selftests/net/openvswitch/config new file mode 100644 index 000000000000..c659749cd086 --- /dev/null +++ b/tools/testing/selftests/net/openvswitch/config @@ -0,0 +1,16 @@ +CONFIG_GENEVE=m +CONFIG_INET_DIAG=y +CONFIG_IPV6=y +CONFIG_NETFILTER=y +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_OVS=y +CONFIG_OPENVSWITCH=m +CONFIG_OPENVSWITCH_GENEVE=m +CONFIG_OPENVSWITCH_GRE=m +CONFIG_OPENVSWITCH_VXLAN=m +CONFIG_PSAMPLE=m +CONFIG_VETH=y +CONFIG_VLAN_8021Q=y +CONFIG_VXLAN=m diff --git a/tools/testing/selftests/net/ovpn/config b/tools/testing/selftests/net/ovpn/config index d6cf033d555e..6b424762e46e 100644 --- a/tools/testing/selftests/net/ovpn/config +++ b/tools/testing/selftests/net/ovpn/config @@ -4,6 +4,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=y CONFIG_CRYPTO_GCM=y CONFIG_DST_CACHE=y CONFIG_INET=y +CONFIG_IPV6=y CONFIG_NET=y CONFIG_NETFILTER=y CONFIG_NET_UDP_TUNNEL=y @@ -11,3 +12,4 @@ CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y CONFIG_OVPN=m CONFIG_STREAM_PARSER=y +CONFIG_VETH=y diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c index d40953375c86..f4effa7580c0 100644 --- a/tools/testing/selftests/net/ovpn/ovpn-cli.c +++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c @@ -1785,7 +1785,7 @@ static int ovpn_parse_remote(struct ovpn_ctx *ovpn, const char *host, const char *service, const char *vpnip) { int ret; - struct addrinfo *result; + struct addrinfo *result = NULL; struct addrinfo hints = { .ai_family = ovpn->sa_family, .ai_socktype = SOCK_DGRAM, @@ -1809,6 +1809,8 @@ static int ovpn_parse_remote(struct ovpn_ctx *ovpn, const char *host, } memcpy(&ovpn->remote, result->ai_addr, result->ai_addrlen); + freeaddrinfo(result); + result = NULL; } if (vpnip) { diff --git a/tools/testing/selftests/net/ovpn/settings b/tools/testing/selftests/net/ovpn/settings new file mode 100644 index 000000000000..ba4d85f74cd6 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/settings @@ -0,0 +1 @@ +timeout=90 diff --git a/tools/testing/selftests/net/packetdrill/tcp_rfc5961_rst-syn-recv.pkt b/tools/testing/selftests/net/packetdrill/tcp_rfc5961_rst-syn-recv.pkt new file mode 100644 index 000000000000..3fc2de03658a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rfc5961_rst-syn-recv.pkt @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// RFC 9293 Section 3.10.7.4: in SYN-RECEIVED, an exact RST resets +// the connection. A non-exact in-window RST elicits a challenge ACK, +// while an out-of-window RST is silently discarded. + +`./defaults.sh` + +// An exact RST removes the request socket. + 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 < S 0:0(0) win 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R 1:1(0) win 1000 + +.1 < . 1:1(0) ack 1 win 1000 + +0 > R 1:1(0) + +0 close(3) = 0 + +// A non-exact in-window RST gets a challenge ACK and the request survives. + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 < S 0:0(0) win 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R 2:2(0) win 1000 + +0 > . 1:1(0) ack 1 + +0 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 close(4) = 0 + +0 close(3) = 0 + +// RST sequence validation precedes ACK validation. Even an RST|ACK +// with an unacceptable ACK value gets a challenge ACK. + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 < S 0:0(0) win 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R. 2:2(0) ack 100 win 1000 + +0 > . 1:1(0) ack 1 + +0 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 close(4) = 0 + +0 close(3) = 0 + +// An out-of-window RST is silent and does not remove the request. + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 < S 0:0(0) win 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R 100001:100001(0) win 1000 + +.1 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 close(4) = 0 + +0 close(3) = 0 diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c index cf106a49b55e..abe488bac50b 100644 --- a/tools/testing/selftests/net/tun.c +++ b/tools/testing/selftests/net/tun.c @@ -42,19 +42,19 @@ static struct in_addr param_ipaddr4_inner_src = { }; static struct in6_addr param_ipaddr6_outer_dst = { - { { 0x20, 0x02, 0x0d, 0xb8, 0x01, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1 } }, + { { 0xfd, 0x00, 0x0d, 0xb8, 0x01, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1 } }, }; static struct in6_addr param_ipaddr6_outer_src = { - { { 0x20, 0x02, 0x0d, 0xb8, 0x01, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2 } }, + { { 0xfd, 0x00, 0x0d, 0xb8, 0x01, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2 } }, }; static struct in6_addr param_ipaddr6_inner_dst = { - { { 0x20, 0x02, 0x0d, 0xb8, 0x02, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1 } }, + { { 0xfd, 0x00, 0x0d, 0xb8, 0x02, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1 } }, }; static struct in6_addr param_ipaddr6_inner_src = { - { { 0x20, 0x02, 0x0d, 0xb8, 0x02, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2 } }, + { { 0xfd, 0x00, 0x0d, 0xb8, 0x02, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2 } }, }; #ifndef BIT diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 5d2dffca0e91..3cfe90e0f34f 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -176,6 +176,7 @@ auto-test-targets := \ maybe_null \ minimal \ non_scx_kfunc_deny \ + nohz_tick \ numa \ allowed_cpus \ peek_dsq \ diff --git a/tools/testing/selftests/sched_ext/nohz_tick.bpf.c b/tools/testing/selftests/sched_ext/nohz_tick.bpf.c new file mode 100644 index 000000000000..6998c5dd6bcb --- /dev/null +++ b/tools/testing/selftests/sched_ext/nohz_tick.bpf.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES + * + * Exercise tick dependency transitions between infinite and finite slices. + */ +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +const volatile s32 test_cpu; +bool finite_phase; +u64 nr_inf_running; +u64 nr_finite_running; +u64 nr_finite_ticks; + +UEI_DEFINE(uei); + +s32 BPF_STRUCT_OPS(nohz_tick_select_cpu, struct task_struct *p, s32 prev_cpu, + u64 wake_flags) +{ + return prev_cpu; +} + +void BPF_STRUCT_OPS(nohz_tick_enqueue, struct task_struct *p, u64 enq_flags) +{ + u64 slice = finite_phase ? 1000000ULL : SCX_SLICE_INF; + + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, slice, enq_flags); + if (enq_flags & SCX_ENQ_LAST) + scx_bpf_kick_cpu(test_cpu, SCX_KICK_IDLE); +} + +void BPF_STRUCT_OPS(nohz_tick_running, struct task_struct *p) +{ + if (bpf_get_smp_processor_id() != test_cpu) + return; + + if (finite_phase) + __sync_fetch_and_add(&nr_finite_running, 1); + else + __sync_fetch_and_add(&nr_inf_running, 1); +} + +void BPF_STRUCT_OPS(nohz_tick_tick, struct task_struct *p) +{ + if (bpf_get_smp_processor_id() == test_cpu && finite_phase) + __sync_fetch_and_add(&nr_finite_ticks, 1); +} + +void BPF_STRUCT_OPS(nohz_tick_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops nohz_tick_ops = { + .select_cpu = (void *)nohz_tick_select_cpu, + .enqueue = (void *)nohz_tick_enqueue, + .running = (void *)nohz_tick_running, + .tick = (void *)nohz_tick_tick, + .exit = (void *)nohz_tick_exit, + .name = "nohz_tick", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/nohz_tick.c b/tools/testing/selftests/sched_ext/nohz_tick.c new file mode 100644 index 000000000000..028f54391c2c --- /dev/null +++ b/tools/testing/selftests/sched_ext/nohz_tick.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES + * + * Validate that a finite-slice EXT task restarts the scheduler tick when it + * follows an infinite-slice EXT task and an idle interval on a NOHZ_FULL CPU. + */ +#define _GNU_SOURCE + +#include <bpf/bpf.h> +#include <errno.h> +#include <sched.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> + +#include <scx/common.h> + +#include "nohz_tick.bpf.skel.h" +#include "scx_test.h" + +#ifndef SCHED_EXT +#define SCHED_EXT 7 +#endif + +#define MIN_FINITE_TICKS 3 +#define PHASE_TIMEOUT_MS 1000 + +struct nohz_tick_ctx { + struct nohz_tick *skel; + cpu_set_t original_mask; + int test_cpu; +}; + +static int first_allowed_cpu(const cpu_set_t *mask, int first, int last) +{ + int cpu; + + for (cpu = first; cpu <= last && cpu < CPU_SETSIZE; cpu++) + if (CPU_ISSET(cpu, mask)) + return cpu; + + return -1; +} + +static int find_nohz_full_cpu(const cpu_set_t *allowed) +{ + char buf[4096], *cur, *end; + FILE *file; + + file = fopen("/sys/devices/system/cpu/nohz_full", "r"); + if (!file) + return -1; + if (!fgets(buf, sizeof(buf), file)) { + fclose(file); + return -1; + } + fclose(file); + + cur = buf; + while (*cur) { + long first, last; + int cpu; + + while (*cur == ' ' || *cur == '\t' || *cur == ',') + cur++; + if (*cur < '0' || *cur > '9') + break; + + errno = 0; + first = strtol(cur, &end, 10); + if (errno || end == cur || first < 0 || first >= CPU_SETSIZE) + return -1; + cur = end; + last = first; + if (*cur == '-') { + cur++; + errno = 0; + last = strtol(cur, &end, 10); + if (errno || end == cur || last < first) + return -1; + cur = end; + } + + cpu = first_allowed_cpu(allowed, first, last); + if (cpu >= 0) + return cpu; + } + + return -1; +} + +static pid_t start_worker(int cpu) +{ + struct sched_param param = {}; + cpu_set_t mask; + pid_t parent; + pid_t pid; + + parent = getpid(); + pid = fork(); + if (pid != 0) + return pid; + if (prctl(PR_SET_PDEATHSIG, SIGKILL) || getppid() != parent) + _exit(1); + + /* + * Become EXT before touching the target so it stays idle until wakeup. + */ + if (sched_setscheduler(0, SCHED_EXT, ¶m)) + _exit(1); + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask)) + _exit(1); + + for (;;) + asm volatile("" ::: "memory"); +} + +static void stop_worker(pid_t pid) +{ + if (pid <= 0) + return; + + kill(pid, SIGKILL); + waitpid(pid, NULL, 0); +} + +static int pause_worker(pid_t pid) +{ + int status; + + if (kill(pid, SIGSTOP)) + return -errno; + if (waitpid(pid, &status, WUNTRACED) != pid) + return -errno; + if (!WIFSTOPPED(status)) + return -ECHILD; + + return 0; +} + +static bool wait_for_counter(const u64 *counter, u64 value, int timeout_ms) +{ + int elapsed; + + for (elapsed = 0; elapsed < timeout_ms; elapsed++) { + if (__atomic_load_n(counter, __ATOMIC_RELAXED) >= value) + return true; + usleep(1000); + } + + return false; +} + +static enum scx_test_status setup(void **ctx_ptr) +{ + struct nohz_tick_ctx *ctx; + cpu_set_t controller_mask; + int cpu; + + ctx = calloc(1, sizeof(*ctx)); + SCX_FAIL_IF(!ctx, "Failed to allocate context"); + if (sched_getaffinity(0, sizeof(ctx->original_mask), + &ctx->original_mask)) { + free(ctx); + SCX_FAIL("Failed to get affinity (%d)", errno); + } + + cpu = find_nohz_full_cpu(&ctx->original_mask); + if (cpu < 0) { + fprintf(stderr, "SKIP: no allowed NOHZ_FULL CPU\n"); + free(ctx); + return SCX_TEST_SKIP; + } + + controller_mask = ctx->original_mask; + CPU_CLR(cpu, &controller_mask); + if (CPU_COUNT(&controller_mask) == 0) { + fprintf(stderr, "SKIP: no housekeeping CPU available\n"); + free(ctx); + return SCX_TEST_SKIP; + } + + ctx->test_cpu = cpu; + ctx->skel = nohz_tick__open(); + if (!ctx->skel) { + free(ctx); + SCX_FAIL("Failed to open skeleton"); + } + + SCX_ENUM_INIT(ctx->skel); + ctx->skel->rodata->test_cpu = cpu; + ctx->skel->struct_ops.nohz_tick_ops->flags |= SCX_OPS_SWITCH_PARTIAL | + SCX_OPS_ENQ_LAST; + if (nohz_tick__load(ctx->skel)) { + nohz_tick__destroy(ctx->skel); + free(ctx); + SCX_FAIL("Failed to load skeleton"); + } + + if (sched_setaffinity(0, sizeof(controller_mask), &controller_mask)) { + nohz_tick__destroy(ctx->skel); + free(ctx); + SCX_FAIL("Failed to move controller off CPU %d (%d)", cpu, errno); + } + + *ctx_ptr = ctx; + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx_ptr) +{ + struct nohz_tick_ctx *ctx = ctx_ptr; + struct nohz_tick *skel = ctx->skel; + struct bpf_link *link = NULL; + enum scx_test_status status = SCX_TEST_FAIL; + pid_t finite_worker = -1; + pid_t inf_worker = -1; + u64 finite_running; + u64 finite_ticks; + int ret; + + link = bpf_map__attach_struct_ops(skel->maps.nohz_tick_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + goto out; + } + + /* + * Establish SCX_RQ_CAN_STOP_TICK with an infinite-slice task. + */ + inf_worker = start_worker(ctx->test_cpu); + if (inf_worker < 0) { + SCX_ERR("Failed to start infinite-slice worker (%d)", errno); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_inf_running, 1, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Infinite-slice worker was not scheduled"); + goto out; + } + + /* Block without exiting so the rq retains the infinite-slice state. */ + ret = pause_worker(inf_worker); + if (ret) { + SCX_ERR("Failed to stop infinite-slice worker (%d)", ret); + goto out; + } + + /* Let the target enter idle with its tick stopped. */ + usleep(100000); + + /* + * The next EXT task receives a finite slice and must restart the tick. + */ + __atomic_store_n(&skel->bss->finite_phase, true, __ATOMIC_RELEASE); + finite_worker = start_worker(ctx->test_cpu); + if (finite_worker < 0) { + SCX_ERR("Failed to start finite-slice worker (%d)", errno); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_running, 1, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Finite-slice worker was not scheduled"); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_ticks, MIN_FINITE_TICKS, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Finite-slice worker received only %llu scheduler ticks", + (unsigned long long)skel->bss->nr_finite_ticks); + goto out; + } + stop_worker(finite_worker); + finite_worker = -1; + + /* + * Leave the CPU idle after a finite-slice task. The next finite-slice + * task must restart the tick even though the slice type is unchanged. + */ + usleep(100000); + finite_running = __atomic_load_n(&skel->bss->nr_finite_running, + __ATOMIC_RELAXED); + finite_ticks = __atomic_load_n(&skel->bss->nr_finite_ticks, + __ATOMIC_RELAXED); + + finite_worker = start_worker(ctx->test_cpu); + if (finite_worker < 0) { + SCX_ERR("Failed to start second finite-slice worker (%d)", errno); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_running, + finite_running + 1, PHASE_TIMEOUT_MS)) { + SCX_ERR("Second finite-slice worker was not scheduled"); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_ticks, + finite_ticks + MIN_FINITE_TICKS, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Second finite-slice worker received only %llu scheduler ticks", + (unsigned long long)(skel->bss->nr_finite_ticks - + finite_ticks)); + goto out; + } + + if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) { + SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)", + (unsigned long long)skel->data->uei.kind, + (long long)skel->data->uei.exit_code); + goto out; + } + + fprintf(stderr, "CPU %d received %llu finite-slice ticks\n", + ctx->test_cpu, + (unsigned long long)skel->bss->nr_finite_ticks); + status = SCX_TEST_PASS; +out: + stop_worker(finite_worker); + stop_worker(inf_worker); + if (link) + bpf_link__destroy(link); + return status; +} + +static void cleanup(void *ctx_ptr) +{ + struct nohz_tick_ctx *ctx = ctx_ptr; + + sched_setaffinity(0, sizeof(ctx->original_mask), &ctx->original_mask); + nohz_tick__destroy(ctx->skel); + free(ctx); +} + +struct scx_test nohz_tick = { + .name = "nohz_tick", + .description = "Verify finite EXT slices restart the NOHZ_FULL tick", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&nohz_tick) diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 76be0e4a7f0e..b4ff9f946565 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -2347,6 +2347,88 @@ static void test_stream_tx_credit_bounds_server(const struct test_opts *opts) close(fd); } +/* Test that many small packets don't cause a connection reset under pressure + * and that data integrity is preserved. Packet sizes vary randomly between + * 129 and 512 bytes, above GOOD_COPY_LEN (128) to bypass in-place coalescing + * in recv_enqueue, forcing each one into its own skb. Without receive queue + * collapsing, the per-skb overhead eventually exceeds buf_alloc and the + * connection is reset. + */ +#define COLLAPSE_PKT_MIN 129 +#define COLLAPSE_PKT_MAX 512 +#define COLLAPSE_TOTAL (2 * 1024 * 1024) + +static void test_stream_collapse_client(const struct test_opts *opts) +{ + unsigned char *data; + unsigned long hash; + size_t offset = 0; + int i, fd; + + data = malloc(COLLAPSE_TOTAL); + if (!data) { + perror("malloc"); + exit(EXIT_FAILURE); + } + + for (i = 0; i < COLLAPSE_TOTAL; i++) + data[i] = rand() & 0xff; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + while (offset < COLLAPSE_TOTAL) { + size_t pkt_size = COLLAPSE_PKT_MIN + + rand() % (COLLAPSE_PKT_MAX - COLLAPSE_PKT_MIN + 1); + + pkt_size = min(pkt_size, COLLAPSE_TOTAL - offset); + + send_buf(fd, data + offset, pkt_size, 0, pkt_size); + offset += pkt_size; + } + + hash = hash_djb2(data, COLLAPSE_TOTAL); + control_writeulong(hash); + + free(data); + close(fd); +} + +static void test_stream_collapse_server(const struct test_opts *opts) +{ + unsigned long hash, remote_hash; + unsigned char *data; + int fd; + + data = malloc(COLLAPSE_TOTAL); + if (!data) { + perror("malloc"); + exit(EXIT_FAILURE); + } + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + recv_buf(fd, data, COLLAPSE_TOTAL, 0, COLLAPSE_TOTAL); + + hash = hash_djb2(data, COLLAPSE_TOTAL); + remote_hash = control_readulong(); + if (hash != remote_hash) { + fprintf(stderr, "hash mismatch: local %lu remote %lu\n", + hash, remote_hash); + exit(EXIT_FAILURE); + } + + free(data); + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -2546,6 +2628,11 @@ static struct test_case test_cases[] = { .run_client = test_stream_msg_peek_client, .run_server = test_stream_peek_after_recv_server, }, + { + .name = "SOCK_STREAM small packets backpressure", + .run_client = test_stream_collapse_client, + .run_server = test_stream_collapse_server, + }, {}, }; diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index 60a102538988..387bc6cc18f0 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -45,6 +45,9 @@ else LIB_OUTPUT = $(CURDIR)/lib endif +LIB_CTYPE = $(LIB_OUTPUT)/ctype.o +LIB_CTYPE_SRC = $(srctree)/tools/lib/ctype.c + LIB_STRING = $(LIB_OUTPUT)/string.o LIB_STRING_SRC = $(srctree)/tools/lib/string.c @@ -117,12 +120,12 @@ tests/bpf/bpf_action_map.o: tests/bpf/bpf_action_map.c $(Q)echo "BPF skeleton support is disabled, skipping tests/bpf/bpf_action_map.o" endif -$(RTLA): $(RTLA_IN) $(LIBSUBCMD) $(LIB_STRING) $(LIB_STR_ERROR_R) - $(QUIET_LINK)$(CC) $(LDFLAGS) -o $(RTLA) $(RTLA_IN) $(LIBSUBCMD) $(LIB_STRING) $(LIB_STR_ERROR_R) $(EXTLIBS) +$(RTLA): $(RTLA_IN) $(LIBSUBCMD) $(LIB_CTYPE) $(LIB_STRING) $(LIB_STR_ERROR_R) + $(QUIET_LINK)$(CC) $(LDFLAGS) -o $(RTLA) $(RTLA_IN) $(LIBSUBCMD) $(LIB_CTYPE) $(LIB_STRING) $(LIB_STR_ERROR_R) $(EXTLIBS) -static: $(RTLA_IN) $(LIBSUBCMD) $(LIB_STRING) $(LIB_STR_ERROR_R) +static: $(RTLA_IN) $(LIBSUBCMD) $(LIB_CTYPE) $(LIB_STRING) $(LIB_STR_ERROR_R) $(eval LDFLAGS += -static) - $(QUIET_LINK)$(CC) -static $(LDFLAGS) -o $(RTLA)-static $(RTLA_IN) $(LIBSUBCMD) $(LIB_STRING) $(LIB_STR_ERROR_R) $(EXTLIBS) + $(QUIET_LINK)$(CC) -static $(LDFLAGS) -o $(RTLA)-static $(RTLA_IN) $(LIBSUBCMD) $(LIB_CTYPE) $(LIB_STRING) $(LIB_STR_ERROR_R) $(EXTLIBS) rtla.%: fixdep FORCE make -f $(srctree)/tools/build/Makefile.build dir=. $@ @@ -150,6 +153,9 @@ $(LIB_STR_ERROR_R): $(LIB_STR_ERROR_R_SRC) | $(LIB_OUTPUT) $(LIB_STRING): $(LIB_STRING_SRC) | $(LIB_OUTPUT) $(QUIET_CC)$(CC) $(CFLAGS) -c -o $@ $< +$(LIB_CTYPE): $(LIB_CTYPE_SRC) | $(LIB_OUTPUT) + $(QUIET_CC)$(CC) $(CFLAGS) -c -o $@ $< + libsubcmd-clean: $(call QUIET_CLEAN, libsubcmd) $(Q)$(RM) -r -- $(LIBSUBCMD_OUTPUT) diff --git a/tools/tracing/rtla/src/common.c b/tools/tracing/rtla/src/common.c index d0a8a6edbf0c..8c7f5e75b2ec 100644 --- a/tools/tracing/rtla/src/common.c +++ b/tools/tracing/rtla/src/common.c @@ -5,6 +5,7 @@ #include <signal.h> #include <stdlib.h> #include <string.h> +#include <unistd.h> #include <sys/sysinfo.h> #include "common.h" diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e44c20c04961..45e784462ec6 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -6069,25 +6069,19 @@ struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr) { struct kvm_io_bus *bus; - int dev_idx, srcu_idx; - struct kvm_io_device *iodev = NULL; + int dev_idx; - srcu_idx = srcu_read_lock(&kvm->srcu); + lockdep_assert_held(&kvm->srcu); bus = kvm_get_bus_srcu(kvm, bus_idx); if (!bus) - goto out_unlock; + return NULL; dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1); if (dev_idx < 0) - goto out_unlock; - - iodev = bus->range[dev_idx].dev; - -out_unlock: - srcu_read_unlock(&kvm->srcu, srcu_idx); + return NULL; - return iodev; + return bus->range[dev_idx].dev; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_io_bus_get_dev); |