diff --git a/Documentation/cpu-freq/core.txt b/Documentation/cpu-freq/core.txt index 4bc7287806de..978463a7c81e 100644 --- a/Documentation/cpu-freq/core.txt +++ b/Documentation/cpu-freq/core.txt @@ -8,6 +8,8 @@ Dominik Brodowski David Kimdon + Rafael J. Wysocki + Viresh Kumar @@ -36,10 +38,11 @@ speed limits (like LCD drivers on ARM architecture). Additionally, the kernel "constant" loops_per_jiffy is updated on frequency changes here. -Reference counting is done by cpufreq_get_cpu and cpufreq_put_cpu, -which make sure that the cpufreq processor driver is correctly -registered with the core, and will not be unloaded until -cpufreq_put_cpu is called. +Reference counting of the cpufreq policies is done by cpufreq_cpu_get +and cpufreq_cpu_put, which make sure that the cpufreq driver is +correctly registered with the core, and will not be unloaded until +cpufreq_put_cpu is called. That also ensures that the respective cpufreq +policy doesn't get freed while being used. 2. CPUFreq notifiers ==================== @@ -69,18 +72,16 @@ CPUFreq policy notifier is called twice for a policy transition: The phase is specified in the second argument to the notifier. The third argument, a void *pointer, points to a struct cpufreq_policy -consisting of five values: cpu, min, max, policy and max_cpu_freq. min -and max are the lower and upper frequencies (in kHz) of the new -policy, policy the new policy, cpu the number of the affected CPU; and -max_cpu_freq the maximum supported CPU frequency. This value is given -for informational purposes only. +consisting of several values, including min, max (the lower and upper +frequencies (in kHz) of the new policy). 2.2 CPUFreq transition notifiers -------------------------------- -These are notified twice when the CPUfreq driver switches the CPU core -frequency and this change has any external implications. +These are notified twice for each online CPU in the policy, when the +CPUfreq driver switches the CPU core frequency and this change has no +any external implications. The second argument specifies the phase - CPUFREQ_PRECHANGE or CPUFREQ_POSTCHANGE. @@ -90,6 +91,7 @@ values: cpu - number of the affected CPU old - old frequency new - new frequency +flags - flags of the cpufreq driver 3. CPUFreq Table Generation with Operating Performance Point (OPP) ================================================================== diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt index 772b94fde264..f71e6be26b83 100644 --- a/Documentation/cpu-freq/cpu-drivers.txt +++ b/Documentation/cpu-freq/cpu-drivers.txt @@ -9,6 +9,8 @@ Dominik Brodowski + Rafael J. Wysocki + Viresh Kumar @@ -49,49 +51,65 @@ using cpufreq_register_driver() What shall this struct cpufreq_driver contain? -cpufreq_driver.name - The name of this driver. + .name - The name of this driver. -cpufreq_driver.init - A pointer to the per-CPU initialization - function. + .init - A pointer to the per-policy initialization function. -cpufreq_driver.verify - A pointer to a "verification" function. + .verify - A pointer to a "verification" function. -cpufreq_driver.setpolicy _or_ -cpufreq_driver.target/ -target_index - See below on the differences. + .setpolicy _or_ .fast_switch _or_ .target _or_ .target_index - See + below on the differences. And optionally -cpufreq_driver.exit - A pointer to a per-CPU cleanup - function called during CPU_POST_DEAD - phase of cpu hotplug process. + .flags - Hints for the cpufreq core. -cpufreq_driver.stop_cpu - A pointer to a per-CPU stop function - called during CPU_DOWN_PREPARE phase of - cpu hotplug process. + .driver_data - cpufreq driver specific data. -cpufreq_driver.resume - A pointer to a per-CPU resume function - which is called with interrupts disabled - and _before_ the pre-suspend frequency - and/or policy is restored by a call to - ->target/target_index or ->setpolicy. + .resolve_freq - Returns the most appropriate frequency for a target + frequency. Doesn't change the frequency though. -cpufreq_driver.attr - A pointer to a NULL-terminated list of - "struct freq_attr" which allow to - export values to sysfs. + .get_intermediate and target_intermediate - Used to switch to stable + frequency while changing CPU frequency. -cpufreq_driver.get_intermediate -and target_intermediate Used to switch to stable frequency while - changing CPU frequency. + .get - Returns current frequency of the CPU. + + .bios_limit - Returns HW/BIOS max frequency limitations for the CPU. + + .exit - A pointer to a per-policy cleanup function called during + CPU_POST_DEAD phase of cpu hotplug process. + + .stop_cpu - A pointer to a per-policy stop function called during + CPU_DOWN_PREPARE phase of cpu hotplug process. + + .suspend - A pointer to a per-policy suspend function which is called + with interrupts disabled and _after_ the governor is stopped for the + policy. + + .resume - A pointer to a per-policy resume function which is called + with interrupts disabled and _before_ the governor is started again. + + .ready - A pointer to a per-policy ready function which is called after + the policy is fully initialized. + + .attr - A pointer to a NULL-terminated list of "struct freq_attr" which + allow to export values to sysfs. + + .boost_enabled - If set, boost frequencies are enabled. + + .set_boost - A pointer to a per-policy function to enable/disable boost + frequencies. 1.2 Per-CPU Initialization -------------------------- Whenever a new CPU is registered with the device model, or after the -cpufreq driver registers itself, the per-CPU initialization function -cpufreq_driver.init is called. It takes a struct cpufreq_policy -*policy as argument. What to do now? +cpufreq driver registers itself, the per-policy initialization function +cpufreq_driver.init is called if no cpufreq policy existed for the CPU. +Note that the .init() and .exit() routines are called only once for the +policy and not for each CPU managed by the policy. It takes a struct +cpufreq_policy *policy as argument. What to do now? If necessary, activate the CPUfreq support on your CPU. @@ -117,47 +135,45 @@ policy->governor must contain the "default policy" for cpufreq_driver.setpolicy or cpufreq_driver.target/target_index is called with these values. +policy->cpus Update this with the masks of the + (online + offline) CPUs that do DVFS + along with this CPU (i.e. that share + clock/voltage rails with it). For setting some of these values (cpuinfo.min[max]_freq, policy->min[max]), the frequency table helpers might be helpful. See the section 2 for more information on them. -SMP systems normally have same clock source for a group of cpus. For these the -.init() would be called only once for the first online cpu. Here the .init() -routine must initialize policy->cpus with mask of all possible cpus (Online + -Offline) that share the clock. Then the core would copy this mask onto -policy->related_cpus and will reset policy->cpus to carry only online cpus. - 1.3 verify ------------- +---------- When the user decides a new policy (consisting of "policy,governor,min,max") shall be set, this policy must be validated so that incompatible values can be corrected. For verifying these -values, a frequency table helper and/or the -cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned -int min_freq, unsigned int max_freq) function might be helpful. See -section 2 for details on frequency table helpers. +values cpufreq_verify_within_limits(struct cpufreq_policy *policy, +unsigned int min_freq, unsigned int max_freq) function might be helpful. +See section 2 for details on frequency table helpers. You need to make sure that at least one valid frequency (or operating range) is within policy->min and policy->max. If necessary, increase policy->max first, and only if this is no solution, decrease policy->min. -1.4 target/target_index or setpolicy? ----------------------------- +1.4 target or target_index or setpolicy or fast_switch? +------------------------------------------------------- Most cpufreq drivers or even most cpu frequency scaling algorithms -only allow the CPU to be set to one frequency. For these, you use the -->target/target_index call. +only allow the CPU frequency to be set to predefined fixed values. For +these, you use the ->target(), ->target_index() or ->fast_switch() +callbacks. -Some cpufreq-capable processors switch the frequency between certain -limits on their own. These shall use the ->setpolicy call +Some cpufreq capable processors switch the frequency between certain +limits on their own. These shall use the ->setpolicy() callback. 1.5. target/target_index -------------- +------------------------ The target_index call has two arguments: struct cpufreq_policy *policy, and unsigned int index (into the exposed frequency table). @@ -186,9 +202,20 @@ actual frequency must be determined using the following rules: Here again the frequency table helper might assist you - see section 2 for details. +1.6. fast_switch +---------------- -1.6 setpolicy ---------------- +This function is used for frequency switching from scheduler's context. +Not all drivers are expected to implement it, as sleeping from within +this callback isn't allowed. This callback must be highly optimized to +do switching as fast as possible. + +This function has two arguments: struct cpufreq_policy *policy and +unsigned int target_frequency. + + +1.7 setpolicy +------------- The setpolicy call only takes a struct cpufreq_policy *policy as argument. You need to set the lower limit of the in-processor or @@ -198,7 +225,7 @@ setting when policy->policy is CPUFREQ_POLICY_PERFORMANCE, and a powersaving-oriented setting when CPUFREQ_POLICY_POWERSAVE. Also check the reference implementation in drivers/cpufreq/longrun.c -1.7 get_intermediate and target_intermediate +1.8 get_intermediate and target_intermediate -------------------------------------------- Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION unset. @@ -222,42 +249,36 @@ failures as core would send notifications for that. As most cpufreq processors only allow for being set to a few specific frequencies, a "frequency table" with some functions might assist in -some work of the processor driver. Such a "frequency table" consists -of an array of struct cpufreq_frequency_table entries, with any value in -"driver_data" you want to use, and the corresponding frequency in -"frequency". At the end of the table, you need to add a -cpufreq_frequency_table entry with frequency set to CPUFREQ_TABLE_END. And -if you want to skip one entry in the table, set the frequency to -CPUFREQ_ENTRY_INVALID. The entries don't need to be in ascending -order. +some work of the processor driver. Such a "frequency table" consists of +an array of struct cpufreq_frequency_table entries, with driver specific +values in "driver_data", the corresponding frequency in "frequency" and +flags set. At the end of the table, you need to add a +cpufreq_frequency_table entry with frequency set to CPUFREQ_TABLE_END. +And if you want to skip one entry in the table, set the frequency to +CPUFREQ_ENTRY_INVALID. The entries don't need to be in sorted in any +particular order, but if they are cpufreq core will do DVFS a bit +quickly for them as search for best match is faster. -By calling cpufreq_table_validate_and_show(struct cpufreq_policy *policy, - struct cpufreq_frequency_table *table); -the cpuinfo.min_freq and cpuinfo.max_freq values are detected, and -policy->min and policy->max are set to the same values. This is -helpful for the per-CPU initialization stage. +By calling cpufreq_table_validate_and_show(), the cpuinfo.min_freq and +cpuinfo.max_freq values are detected, and policy->min and policy->max +are set to the same values. This is helpful for the per-CPU +initialization stage. -int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, - struct cpufreq_frequency_table *table); -assures that at least one valid frequency is within policy->min and -policy->max, and all other criteria are met. This is helpful for the -->verify call. +cpufreq_frequency_table_verify() assures that at least one valid +frequency is within policy->min and policy->max, and all other criteria +are met. This is helpful for the ->verify call. -int cpufreq_frequency_table_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation); - -is the corresponding frequency table helper for the ->target -stage. Just pass the values to this function, and this function -returns the number of the frequency table entry which contains -the frequency the CPU shall be set to. +cpufreq_frequency_table_target() is the corresponding frequency table +helper for the ->target stage. Just pass the values to this function, +and this function returns the of the frequency table entry which +contains the frequency the CPU shall be set to. The following macros can be used as iterators over cpufreq_frequency_table: cpufreq_for_each_entry(pos, table) - iterates over all entries of frequency table. -cpufreq-for_each_valid_entry(pos, table) - iterates over all entries, +cpufreq_for_each_valid_entry(pos, table) - iterates over all entries, excluding CPUFREQ_ENTRY_INVALID frequencies. Use arguments "pos" - a cpufreq_frequency_table * as a loop cursor and "table" - the cpufreq_frequency_table * you want to iterate over. diff --git a/Documentation/cpu-freq/cpufreq-stats.txt b/Documentation/cpu-freq/cpufreq-stats.txt index 3c355f6ad834..2bbe207354ed 100644 --- a/Documentation/cpu-freq/cpufreq-stats.txt +++ b/Documentation/cpu-freq/cpufreq-stats.txt @@ -34,10 +34,10 @@ cpufreq stats provides following statistics (explained in detail below). - total_trans - trans_table -All the statistics will be from the time the stats driver has been inserted -to the time when a read of a particular statistic is done. Obviously, stats -driver will not have any information about the frequency transitions before -the stats driver insertion. +All the statistics will be from the time the stats driver has been inserted +(or the time the stats were reset) to the time when a read of a particular +statistic is done. Obviously, stats driver will not have any information +about the frequency transitions before the stats driver insertion. -------------------------------------------------------------------------------- :/sys/devices/system/cpu/cpu0/cpufreq/stats # ls -l @@ -110,25 +110,13 @@ Config Main Menu CPU Frequency scaling ---> [*] CPU Frequency scaling [*] CPU frequency translation statistics - [*] CPU frequency translation statistics details "CPU Frequency scaling" (CONFIG_CPU_FREQ) should be enabled to configure cpufreq-stats. "CPU frequency translation statistics" (CONFIG_CPU_FREQ_STAT) provides the -basic statistics which includes time_in_state and total_trans. +statistics which includes time_in_state, total_trans and trans_table. -"CPU frequency translation statistics details" (CONFIG_CPU_FREQ_STAT_DETAILS) -provides fine grained cpufreq stats by trans_table. The reason for having a -separate config option for trans_table is: -- trans_table goes against the traditional /sysfs rule of one value per - interface. It provides a whole bunch of value in a 2 dimensional matrix - form. - -Once these two options are enabled and your CPU supports cpufrequency, you +Once this option is enabled and your CPU supports cpufrequency, you will be able to see the CPU frequency statistics in /sysfs. - - - - diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt index c15aa75f5227..61b3184b6c24 100644 --- a/Documentation/cpu-freq/governors.txt +++ b/Documentation/cpu-freq/governors.txt @@ -10,6 +10,8 @@ Dominik Brodowski some additions and corrections by Nico Golde + Rafael J. Wysocki + Viresh Kumar @@ -28,32 +30,27 @@ Contents: 2.3 Userspace 2.4 Ondemand 2.5 Conservative +2.6 Schedutil 3. The Governor Interface in the CPUfreq Core +4. References 1. What Is A CPUFreq Governor? ============================== Most cpufreq drivers (except the intel_pstate and longrun) or even most -cpu frequency scaling algorithms only offer the CPU to be set to one -frequency. In order to offer dynamic frequency scaling, the cpufreq -core must be able to tell these drivers of a "target frequency". So -these specific drivers will be transformed to offer a "->target/target_index" -call instead of the existing "->setpolicy" call. For "longrun", all -stays the same, though. +cpu frequency scaling algorithms only allow the CPU frequency to be set +to predefined fixed values. In order to offer dynamic frequency +scaling, the cpufreq core must be able to tell these drivers of a +"target frequency". So these specific drivers will be transformed to +offer a "->target/target_index/fast_switch()" call instead of the +"->setpolicy()" call. For set_policy drivers, all stays the same, +though. How to decide what frequency within the CPUfreq policy should be used? -That's done using "cpufreq governors". Two are already in this patch --- they're the already existing "powersave" and "performance" which -set the frequency statically to the lowest or highest frequency, -respectively. At least two more such governors will be ready for -addition in the near future, but likely many more as there are various -different theories and models about dynamic frequency scaling -around. Using such a generic interface as cpufreq offers to scaling -governors, these can be tested extensively, and the best one can be -selected for each specific use. +That's done using "cpufreq governors". Basically, it's the following flow graph: @@ -71,7 +68,7 @@ CPU can be set to switch independently | CPU can only be set / the limits of policy->{min,max} / \ / \ - Using the ->setpolicy call, Using the ->target/target_index call, + Using the ->setpolicy call, Using the ->target/target_index/fast_switch call, the limits and the the frequency closest "policy" is set. to target_freq is set. It is assured that it @@ -109,114 +106,159 @@ directory. 2.4 Ondemand ------------ -The CPUfreq governor "ondemand" sets the CPU depending on the -current usage. To do this the CPU must have the capability to -switch the frequency very quickly. There are a number of sysfs file -accessible parameters: +The CPUfreq governor "ondemand" sets the CPU frequency depending on the +current system load. Load estimation is triggered by the scheduler +through the update_util_data->func hook; when triggered, cpufreq checks +the CPU-usage statistics over the last period and the governor sets the +CPU accordingly. The CPU must have the capability to switch the +frequency very quickly. -sampling_rate: measured in uS (10^-6 seconds), this is how often you -want the kernel to look at the CPU usage and to make decisions on -what to do about the frequency. Typically this is set to values of -around '10000' or more. It's default value is (cmp. with users-guide.txt): -transition_latency * 1000 -Be aware that transition latency is in ns and sampling_rate is in us, so you -get the same sysfs value by default. -Sampling rate should always get adjusted considering the transition latency -To set the sampling rate 750 times as high as the transition latency -in the bash (as said, 1000 is default), do: -echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) \ - >ondemand/sampling_rate +Sysfs files: -sampling_rate_min: -The sampling rate is limited by the HW transition latency: -transition_latency * 100 -Or by kernel restrictions: -If CONFIG_NO_HZ_COMMON is set, the limit is 10ms fixed. -If CONFIG_NO_HZ_COMMON is not set or nohz=off boot parameter is used, the -limits depend on the CONFIG_HZ option: -HZ=1000: min=20000us (20ms) -HZ=250: min=80000us (80ms) -HZ=100: min=200000us (200ms) -The highest value of kernel and HW latency restrictions is shown and -used as the minimum sampling rate. +* sampling_rate: -up_threshold: defines what the average CPU usage between the samplings -of 'sampling_rate' needs to be for the kernel to make a decision on -whether it should increase the frequency. For example when it is set -to its default value of '95' it means that between the checking -intervals the CPU needs to be on average more than 95% in use to then -decide that the CPU frequency needs to be increased. + Measured in uS (10^-6 seconds), this is how often you want the kernel + to look at the CPU usage and to make decisions on what to do about the + frequency. Typically this is set to values of around '10000' or more. + It's default value is (cmp. with users-guide.txt): transition_latency + * 1000. Be aware that transition latency is in ns and sampling_rate + is in us, so you get the same sysfs value by default. Sampling rate + should always get adjusted considering the transition latency to set + the sampling rate 750 times as high as the transition latency in the + bash (as said, 1000 is default), do: -ignore_nice_load: this parameter takes a value of '0' or '1'. When -set to '0' (its default), all processes are counted towards the -'cpu utilisation' value. When set to '1', the processes that are -run with a 'nice' value will not count (and thus be ignored) in the -overall usage calculation. This is useful if you are running a CPU -intensive calculation on your laptop that you do not care how long it -takes to complete as you can 'nice' it and prevent it from taking part -in the deciding process of whether to increase your CPU frequency. + $ echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) > ondemand/sampling_rate -sampling_down_factor: this parameter controls the rate at which the -kernel makes a decision on when to decrease the frequency while running -at top speed. When set to 1 (the default) decisions to reevaluate load -are made at the same interval regardless of current clock speed. But -when set to greater than 1 (e.g. 100) it acts as a multiplier for the -scheduling interval for reevaluating load when the CPU is at its top -speed due to high load. This improves performance by reducing the overhead -of load evaluation and helping the CPU stay at its top speed when truly -busy, rather than shifting back and forth in speed. This tunable has no -effect on behavior at lower speeds/lower CPU loads. +* sampling_rate_min: -powersave_bias: this parameter takes a value between 0 to 1000. It -defines the percentage (times 10) value of the target frequency that -will be shaved off of the target. For example, when set to 100 -- 10%, -when ondemand governor would have targeted 1000 MHz, it will target -1000 MHz - (10% of 1000 MHz) = 900 MHz instead. This is set to 0 -(disabled) by default. -When AMD frequency sensitivity powersave bias driver -- -drivers/cpufreq/amd_freq_sensitivity.c is loaded, this parameter -defines the workload frequency sensitivity threshold in which a lower -frequency is chosen instead of ondemand governor's original target. -The frequency sensitivity is a hardware reported (on AMD Family 16h -Processors and above) value between 0 to 100% that tells software how -the performance of the workload running on a CPU will change when -frequency changes. A workload with sensitivity of 0% (memory/IO-bound) -will not perform any better on higher core frequency, whereas a -workload with sensitivity of 100% (CPU-bound) will perform better -higher the frequency. When the driver is loaded, this is set to 400 -by default -- for CPUs running workloads with sensitivity value below -40%, a lower frequency is chosen. Unloading the driver or writing 0 -will disable this feature. + The sampling rate is limited by the HW transition latency: + transition_latency * 100 + + Or by kernel restrictions: + - If CONFIG_NO_HZ_COMMON is set, the limit is 10ms fixed. + - If CONFIG_NO_HZ_COMMON is not set or nohz=off boot parameter is + used, the limits depend on the CONFIG_HZ option: + HZ=1000: min=20000us (20ms) + HZ=250: min=80000us (80ms) + HZ=100: min=200000us (200ms) + + The highest value of kernel and HW latency restrictions is shown and + used as the minimum sampling rate. + +* up_threshold: + + This defines what the average CPU usage between the samplings of + 'sampling_rate' needs to be for the kernel to make a decision on + whether it should increase the frequency. For example when it is set + to its default value of '95' it means that between the checking + intervals the CPU needs to be on average more than 95% in use to then + decide that the CPU frequency needs to be increased. + +* ignore_nice_load: + + This parameter takes a value of '0' or '1'. When set to '0' (its + default), all processes are counted towards the 'cpu utilisation' + value. When set to '1', the processes that are run with a 'nice' + value will not count (and thus be ignored) in the overall usage + calculation. This is useful if you are running a CPU intensive + calculation on your laptop that you do not care how long it takes to + complete as you can 'nice' it and prevent it from taking part in the + deciding process of whether to increase your CPU frequency. + +* sampling_down_factor: + + This parameter controls the rate at which the kernel makes a decision + on when to decrease the frequency while running at top speed. When set + to 1 (the default) decisions to reevaluate load are made at the same + interval regardless of current clock speed. But when set to greater + than 1 (e.g. 100) it acts as a multiplier for the scheduling interval + for reevaluating load when the CPU is at its top speed due to high + load. This improves performance by reducing the overhead of load + evaluation and helping the CPU stay at its top speed when truly busy, + rather than shifting back and forth in speed. This tunable has no + effect on behavior at lower speeds/lower CPU loads. + +* powersave_bias: + + This parameter takes a value between 0 to 1000. It defines the + percentage (times 10) value of the target frequency that will be + shaved off of the target. For example, when set to 100 -- 10%, when + ondemand governor would have targeted 1000 MHz, it will target + 1000 MHz - (10% of 1000 MHz) = 900 MHz instead. This is set to 0 + (disabled) by default. + + When AMD frequency sensitivity powersave bias driver -- + drivers/cpufreq/amd_freq_sensitivity.c is loaded, this parameter + defines the workload frequency sensitivity threshold in which a lower + frequency is chosen instead of ondemand governor's original target. + The frequency sensitivity is a hardware reported (on AMD Family 16h + Processors and above) value between 0 to 100% that tells software how + the performance of the workload running on a CPU will change when + frequency changes. A workload with sensitivity of 0% (memory/IO-bound) + will not perform any better on higher core frequency, whereas a + workload with sensitivity of 100% (CPU-bound) will perform better + higher the frequency. When the driver is loaded, this is set to 400 by + default -- for CPUs running workloads with sensitivity value below + 40%, a lower frequency is chosen. Unloading the driver or writing 0 + will disable this feature. 2.5 Conservative ---------------- The CPUfreq governor "conservative", much like the "ondemand" -governor, sets the CPU depending on the current usage. It differs in -behaviour in that it gracefully increases and decreases the CPU speed -rather than jumping to max speed the moment there is any load on the -CPU. This behaviour more suitable in a battery powered environment. -The governor is tweaked in the same manner as the "ondemand" governor -through sysfs with the addition of: +governor, sets the CPU frequency depending on the current usage. It +differs in behaviour in that it gracefully increases and decreases the +CPU speed rather than jumping to max speed the moment there is any load +on the CPU. This behaviour is more suitable in a battery powered +environment. The governor is tweaked in the same manner as the +"ondemand" governor through sysfs with the addition of: -freq_step: this describes what percentage steps the cpu freq should be -increased and decreased smoothly by. By default the cpu frequency will -increase in 5% chunks of your maximum cpu frequency. You can change this -value to anywhere between 0 and 100 where '0' will effectively lock your -CPU at a speed regardless of its load whilst '100' will, in theory, make -it behave identically to the "ondemand" governor. +* freq_step: -down_threshold: same as the 'up_threshold' found for the "ondemand" -governor but for the opposite direction. For example when set to its -default value of '20' it means that if the CPU usage needs to be below -20% between samples to have the frequency decreased. + This describes what percentage steps the cpu freq should be increased + and decreased smoothly by. By default the cpu frequency will increase + in 5% chunks of your maximum cpu frequency. You can change this value + to anywhere between 0 and 100 where '0' will effectively lock your CPU + at a speed regardless of its load whilst '100' will, in theory, make + it behave identically to the "ondemand" governor. + +* down_threshold: + + Same as the 'up_threshold' found for the "ondemand" governor but for + the opposite direction. For example when set to its default value of + '20' it means that if the CPU usage needs to be below 20% between + samples to have the frequency decreased. + +* sampling_down_factor: + + Similar functionality as in "ondemand" governor. But in + "conservative", it controls the rate at which the kernel makes a + decision on when to decrease the frequency while running in any speed. + Load for frequency increase is still evaluated every sampling rate. + + +2.6 Schedutil +------------- + +The "schedutil" governor aims at better integration with the Linux +kernel scheduler. Load estimation is achieved through the scheduler's +Per-Entity Load Tracking (PELT) mechanism, which also provides +information about the recent load [1]. This governor currently does +load based DVFS only for tasks managed by CFS. RT and DL scheduler tasks +are always run at the highest frequency. Unlike all the other +governors, the code is located under the kernel/sched/ directory. + +Sysfs files: + +* rate_limit_us: + + This contains a value in microseconds. The governor waits for + rate_limit_us time before reevaluating the load again, after it has + evaluated the load once. + +For an in-depth comparison with the other governors refer to [2]. -sampling_down_factor: similar functionality as in "ondemand" governor. -But in "conservative", it controls the rate at which the kernel makes -a decision on when to decrease the frequency while running in any -speed. Load for frequency increase is still evaluated every -sampling rate. 3. The Governor Interface in the CPUfreq Core ============================================= @@ -225,26 +267,10 @@ A new governor must register itself with the CPUfreq core using "cpufreq_register_governor". The struct cpufreq_governor, which has to be passed to that function, must contain the following values: -governor->name - A unique name for this governor -governor->governor - The governor callback function -governor->owner - .THIS_MODULE for the governor module (if - appropriate) - -The governor->governor callback is called with the current (or to-be-set) -cpufreq_policy struct for that CPU, and an unsigned int event. The -following events are currently defined: - -CPUFREQ_GOV_START: This governor shall start its duty for the CPU - policy->cpu -CPUFREQ_GOV_STOP: This governor shall end its duty for the CPU - policy->cpu -CPUFREQ_GOV_LIMITS: The limits for CPU policy->cpu have changed to - policy->min and policy->max. - -If you need other "events" externally of your driver, _only_ use the -cpufreq_governor_l(unsigned int cpu, unsigned int event) call to the -CPUfreq core to ensure proper locking. +governor->name - A unique name for this governor. +governor->owner - .THIS_MODULE for the governor module (if appropriate). +plus a set of hooks to the functions implementing the governor's logic. The CPUfreq governor may call the CPU processor driver using one of these two functions: @@ -258,12 +284,18 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int relation); target_freq must be within policy->min and policy->max, of course. -What's the difference between these two functions? When your governor -still is in a direct code path of a call to governor->governor, the -per-CPU cpufreq lock is still held in the cpufreq core, and there's -no need to lock it again (in fact, this would cause a deadlock). So -use __cpufreq_driver_target only in these cases. In all other cases -(for example, when there's a "daemonized" function that wakes up -every second), use cpufreq_driver_target to lock the cpufreq per-CPU -lock before the command is passed to the cpufreq processor driver. +What's the difference between these two functions? When your governor is +in a direct code path of a call to governor callbacks, like +governor->start(), the policy->rwsem is still held in the cpufreq core, +and there's no need to lock it again (in fact, this would cause a +deadlock). So use __cpufreq_driver_target only in these cases. In all +other cases (for example, when there's a "daemonized" function that +wakes up every second), use cpufreq_driver_target to take policy->rwsem +before the command is passed to the cpufreq driver. + +4. References +============= + +[1] Per-entity load tracking: https://lwn.net/Articles/531853/ +[2] Improvements in CPU frequency management: https://lwn.net/Articles/682391/ diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt index dc024ab4054f..ef1d39247b05 100644 --- a/Documentation/cpu-freq/index.txt +++ b/Documentation/cpu-freq/index.txt @@ -18,16 +18,29 @@ Documents in this directory: ---------------------------- -core.txt - General description of the CPUFreq core and - of CPUFreq notifiers -cpu-drivers.txt - How to implement a new cpufreq processor driver +amd-powernow.txt - AMD powernow driver specific file. + +boost.txt - Frequency boosting support. + +core.txt - General description of the CPUFreq core and + of CPUFreq notifiers. + +cpu-drivers.txt - How to implement a new cpufreq processor driver. + +cpufreq-nforce2.txt - nVidia nForce2 platform specific file. + +cpufreq-stats.txt - General description of sysfs cpufreq stats. governors.txt - What are cpufreq governors and how to implement them? index.txt - File index, Mailing list and Links (this document) +intel-pstate.txt - Intel pstate cpufreq driver specific file. + +pcc-cpufreq.txt - PCC cpufreq driver specific file. + user-guide.txt - User Guide to CPUFreq @@ -35,9 +48,7 @@ Mailing List ------------ There is a CPU frequency changing CVS commit and general list where you can report bugs, problems or submit patches. To post a message, -send an email to linux-pm@vger.kernel.org, to subscribe go to -http://vger.kernel.org/vger-lists.html#linux-pm and follow the -instructions there. +send an email to linux-pm@vger.kernel.org. Links ----- @@ -48,7 +59,7 @@ how to access the CVS repository: * http://cvs.arm.linux.org.uk/ the CPUFreq Mailing list: -* http://vger.kernel.org/vger-lists.html#cpufreq +* http://vger.kernel.org/vger-lists.html#linux-pm Clock and voltage scaling for the SA-1100: * http://www.lartmaker.nl/projects/scaling diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt index 1953994ef5e6..3fdcdfd968ba 100644 --- a/Documentation/cpu-freq/intel-pstate.txt +++ b/Documentation/cpu-freq/intel-pstate.txt @@ -85,6 +85,21 @@ Sysfs will show : Refer to "Intel® 64 and IA-32 Architectures Software Developer’s Manual Volume 3: System Programming Guide" to understand ratios. +There is one more sysfs attribute in /sys/devices/system/cpu/intel_pstate/ +that can be used for controlling the operation mode of the driver: + + status: Three settings are possible: + "off" - The driver is not in use at this time. + "active" - The driver works as a P-state governor (default). + "passive" - The driver works as a regular cpufreq one and collaborates + with the generic cpufreq governors (it sets P-states as + requested by those governors). + The current setting is returned by reads from this attribute. Writing one + of the above strings to it changes the operation mode as indicated by that + string, if possible. If HW-managed P-states (HWP) are enabled, it is not + possible to change the driver's operation mode and attempts to write to + this attribute will fail. + cpufreq sysfs for Intel P-State Since this driver registers with cpufreq, cpufreq sysfs is also presented. diff --git a/Documentation/cpu-freq/user-guide.txt b/Documentation/cpu-freq/user-guide.txt index 109e97bbab77..107f6fdd7d14 100644 --- a/Documentation/cpu-freq/user-guide.txt +++ b/Documentation/cpu-freq/user-guide.txt @@ -18,7 +18,7 @@ Contents: --------- 1. Supported Architectures and Processors -1.1 ARM +1.1 ARM and ARM64 1.2 x86 1.3 sparc64 1.4 ppc @@ -37,16 +37,10 @@ Contents: 1. Supported Architectures and Processors ========================================= -1.1 ARM -------- - -The following ARM processors are supported by cpufreq: - -ARM Integrator -ARM-SA1100 -ARM-SA1110 -Intel PXA +1.1 ARM and ARM64 +----------------- +Almost all ARM and ARM64 platforms support CPU frequency scaling. 1.2 x86 ------- @@ -69,6 +63,7 @@ Transmeta Crusoe Transmeta Efficeon VIA Cyrix 3 / C3 various processors on some ACPI 2.0-compatible systems [*] +And many more [*] Only if "ACPI Processor Performance States" are available to the ACPI<->BIOS interface. @@ -147,10 +142,19 @@ mounted it at /sys, the cpufreq interface is located in a subdirectory "cpufreq" within the cpu-device directory (e.g. /sys/devices/system/cpu/cpu0/cpufreq/ for the first CPU). +affected_cpus : List of Online CPUs that require software + coordination of frequency. + +cpuinfo_cur_freq : Current frequency of the CPU as obtained from + the hardware, in KHz. This is the frequency + the CPU actually runs at. + cpuinfo_min_freq : this file shows the minimum operating frequency the processor can run at(in kHz) + cpuinfo_max_freq : this file shows the maximum operating frequency the processor can run at(in kHz) + cpuinfo_transition_latency The time it takes on this CPU to switch between two frequencies in nano seconds. If unknown or known to be @@ -163,25 +167,30 @@ cpuinfo_transition_latency The time it takes on this CPU to userspace daemon. Make sure to not switch the frequency too often resulting in performance loss. -scaling_driver : this file shows what cpufreq driver is - used to set the frequency on this CPU + +related_cpus : List of Online + Offline CPUs that need software + coordination of frequency. + +scaling_available_frequencies : List of available frequencies, in KHz. scaling_available_governors : this file shows the CPUfreq governors available in this kernel. You can see the currently activated governor in +scaling_cur_freq : Current frequency of the CPU as determined by + the governor and cpufreq core, in KHz. This is + the frequency the kernel thinks the CPU runs + at. + +scaling_driver : this file shows what cpufreq driver is + used to set the frequency on this CPU + scaling_governor, and by "echoing" the name of another governor you can change it. Please note that some governors won't load - they only work on some specific architectures or processors. -cpuinfo_cur_freq : Current frequency of the CPU as obtained from - the hardware, in KHz. This is the frequency - the CPU actually runs at. - -scaling_available_frequencies : List of available frequencies, in KHz. - scaling_min_freq and scaling_max_freq show the current "policy limits" (in kHz). By echoing new values into these @@ -190,16 +199,11 @@ scaling_max_freq show the current "policy limits" (in first set scaling_max_freq, then scaling_min_freq. -affected_cpus : List of Online CPUs that require software - coordination of frequency. - -related_cpus : List of Online + Offline CPUs that need software - coordination of frequency. - -scaling_cur_freq : Current frequency of the CPU as determined by - the governor and cpufreq core, in KHz. This is - the frequency the kernel thinks the CPU runs - at. +scaling_setspeed This can be read to get the currently programmed + value by the governor. This can be written to + change the current frequency for a group of + CPUs, represented by a policy. This is supported + currently only by the userspace governor. bios_limit : If the BIOS tells the OS to limit a CPU to lower frequencies, the user can read out the diff --git a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt index 0dcb7c7d3e40..944657684d73 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt @@ -15,6 +15,9 @@ Properties: Second cell specifies the irq distribution mode to cores 0=Round Robin; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3 + The second cell in interrupts property is deprecated and may be ignored by + the kernel. + intc accessed via the special ARC AUX register interface, hence "reg" property is not specified. diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt index c010fafc66a8..c7194e87d5f4 100644 --- a/Documentation/devicetree/bindings/net/mediatek-net.txt +++ b/Documentation/devicetree/bindings/net/mediatek-net.txt @@ -7,7 +7,7 @@ have dual GMAC each represented by a child node.. * Ethernet controller node Required properties: -- compatible: Should be "mediatek,mt7623-eth" +- compatible: Should be "mediatek,mt2701-eth" - reg: Address and length of the register set for the device - interrupts: Should contain the three frame engines interrupts in numeric order. These are fe_int0, fe_int1 and fe_int2. diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt index ff1bc4b1bb3b..fb5056b22685 100644 --- a/Documentation/devicetree/bindings/net/phy.txt +++ b/Documentation/devicetree/bindings/net/phy.txt @@ -19,8 +19,9 @@ Optional Properties: specifications. If neither of these are specified, the default is to assume clause 22. - If the phy's identifier is known then the list may contain an entry - of the form: "ethernet-phy-idAAAA.BBBB" where + If the PHY reports an incorrect ID (or none at all) then the + "compatible" list may contain an entry with the correct PHY ID in the + form: "ethernet-phy-idAAAA.BBBB" where AAAA - The value of the 16 bit Phy Identifier 1 register as 4 hex digits. This is the chip vendor OUI bits 3:18 BBBB - The value of the 16 bit Phy Identifier 2 register as diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 72624a16b792..c94b4675d021 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -212,10 +212,11 @@ asynchronous manner and the value may not be very precise. To see a precise snapshot of a moment, you can see /proc//smaps file and scan page table. It's slow but very precise. -Table 1-2: Contents of the status files (as of 4.1) +Table 1-2: Contents of the status files (as of 4.8) .............................................................................. Field Content Name filename of the executable + Umask file mode creation mask State state (R is running, S is sleeping, D is sleeping in an uninterruptible wait, Z is zombie, T is traced or stopped) @@ -226,7 +227,6 @@ Table 1-2: Contents of the status files (as of 4.1) TracerPid PID of process tracing this process (0 if not) Uid Real, effective, saved set, and file system UIDs Gid Real, effective, saved set, and file system GIDs - Umask file mode creation mask FDSize number of file descriptor slots currently allocated Groups supplementary group list NStgid descendant namespace thread group ID hierarchy @@ -236,6 +236,7 @@ Table 1-2: Contents of the status files (as of 4.1) VmPeak peak virtual memory size VmSize total program size VmLck locked memory size + VmPin pinned memory size VmHWM peak resident set size ("high water mark") VmRSS size of memory portions. It contains the three following parts (VmRSS = RssAnon + RssFile + RssShmem) diff --git a/Documentation/power/states.txt b/Documentation/power/states.txt index 8a39ce45d8a0..008ecb588317 100644 --- a/Documentation/power/states.txt +++ b/Documentation/power/states.txt @@ -35,9 +35,7 @@ only one way to cause the system to go into the Suspend-To-RAM state (write The default suspend mode (ie. the one to be used without writing anything into /sys/power/mem_sleep) is either "deep" (if Suspend-To-RAM is supported) or "s2idle", but it can be overridden by the value of the "mem_sleep_default" -parameter in the kernel command line. On some ACPI-based systems, depending on -the information in the FADT, the default may be "s2idle" even if Suspend-To-RAM -is supported. +parameter in the kernel command line. The properties of all of the sleep states are described below. diff --git a/MAINTAINERS b/MAINTAINERS index 26edd832c64e..5f10c28b2e15 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3567,7 +3567,7 @@ F: drivers/infiniband/hw/cxgb3/ F: include/uapi/rdma/cxgb3-abi.h CXGB4 ETHERNET DRIVER (CXGB4) -M: Hariprasad S +M: Ganesh Goudar L: netdev@vger.kernel.org W: http://www.chelsio.com S: Supported @@ -4100,12 +4100,18 @@ F: drivers/gpu/drm/bridge/ DRM DRIVER FOR BOCHS VIRTUAL GPU M: Gerd Hoffmann -S: Odd Fixes +L: virtualization@lists.linux-foundation.org +T: git git://git.kraxel.org/linux drm-qemu +S: Maintained F: drivers/gpu/drm/bochs/ DRM DRIVER FOR QEMU'S CIRRUS DEVICE M: Dave Airlie -S: Odd Fixes +M: Gerd Hoffmann +L: virtualization@lists.linux-foundation.org +T: git git://git.kraxel.org/linux drm-qemu +S: Obsolete +W: https://www.kraxel.org/blog/2014/10/qemu-using-cirrus-considered-harmful/ F: drivers/gpu/drm/cirrus/ RADEON and AMDGPU DRM DRIVERS @@ -4147,7 +4153,7 @@ F: Documentation/gpu/i915.rst INTEL GVT-g DRIVERS (Intel GPU Virtualization) M: Zhenyu Wang M: Zhi Wang -L: igvt-g-dev@lists.01.org +L: intel-gvt-dev@lists.freedesktop.org L: intel-gfx@lists.freedesktop.org W: https://01.org/igvt-g T: git https://github.com/01org/gvt-linux.git @@ -4298,7 +4304,10 @@ F: Documentation/devicetree/bindings/display/renesas,du.txt DRM DRIVER FOR QXL VIRTUAL GPU M: Dave Airlie -S: Odd Fixes +M: Gerd Hoffmann +L: virtualization@lists.linux-foundation.org +T: git git://git.kraxel.org/linux drm-qemu +S: Maintained F: drivers/gpu/drm/qxl/ F: include/uapi/drm/qxl_drm.h @@ -13092,6 +13101,7 @@ M: David Airlie M: Gerd Hoffmann L: dri-devel@lists.freedesktop.org L: virtualization@lists.linux-foundation.org +T: git git://git.kraxel.org/linux drm-qemu S: Maintained F: drivers/gpu/drm/virtio/ F: include/uapi/linux/virtio_gpu.h @@ -13443,6 +13453,7 @@ F: arch/x86/ X86 PLATFORM DRIVERS M: Darren Hart +M: Andy Shevchenko L: platform-driver-x86@vger.kernel.org T: git git://git.infradead.org/users/dvhart/linux-platform-drivers-x86.git S: Maintained @@ -13614,6 +13625,7 @@ F: drivers/net/hamradio/z8530.h ZBUD COMPRESSED PAGE ALLOCATOR M: Seth Jennings +M: Dan Streetman L: linux-mm@kvack.org S: Maintained F: mm/zbud.c @@ -13669,6 +13681,7 @@ F: Documentation/vm/zsmalloc.txt ZSWAP COMPRESSED SWAP CACHING M: Seth Jennings +M: Dan Streetman L: linux-mm@kvack.org S: Maintained F: mm/zswap.c diff --git a/Makefile b/Makefile index 098840012b9b..96b27a888285 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ VERSION = 4 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc5 -NAME = Anniversary Edition +EXTRAVERSION = -rc6 +NAME = Fearless Coyote # *DOCUMENTATION* # To see a list of typical targets execute "make help" diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index a36e8601114d..d5da2115d78a 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -26,7 +26,9 @@ static inline void __delay(unsigned long loops) " lp 1f \n" " nop \n" "1: \n" - : : "r"(loops)); + : + : "r"(loops) + : "lp_count"); } extern void __bad_udelay(void); diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 689dd867fdff..8b90d25a15cc 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -71,14 +71,14 @@ ENTRY(stext) GET_CPU_ID r5 cmp r5, 0 mov.nz r0, r5 -#ifdef CONFIG_ARC_SMP_HALT_ON_RESET - ; Non-Master can proceed as system would be booted sufficiently - jnz first_lines_of_secondary -#else + bz .Lmaster_proceed + ; Non-Masters wait for Master to boot enough and bring them up - jnz arc_platform_smp_wait_to_boot -#endif - ; Master falls thru + ; when they resume, tail-call to entry point + mov blink, @first_lines_of_secondary + j arc_platform_smp_wait_to_boot + +.Lmaster_proceed: #endif ; Clear BSS before updating any globals diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 9274f8ade8c7..9f6b68fd4f3b 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -93,11 +93,10 @@ static void mcip_probe_n_setup(void) READ_BCR(ARC_REG_MCIP_BCR, mp); sprintf(smp_cpuinfo_buf, - "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n", + "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n", mp.ver, mp.num_cores, IS_AVAIL1(mp.ipi, "IPI "), IS_AVAIL1(mp.idu, "IDU "), - IS_AVAIL1(mp.llm, "LLM "), IS_AVAIL1(mp.dbg, "DEBUG "), IS_AVAIL1(mp.gfrc, "GFRC")); @@ -175,7 +174,6 @@ static void idu_irq_unmask(struct irq_data *data) raw_spin_unlock_irqrestore(&mcip_lock, flags); } -#ifdef CONFIG_SMP static int idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask, bool force) @@ -205,12 +203,27 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask, return IRQ_SET_MASK_OK; } -#endif + +static void idu_irq_enable(struct irq_data *data) +{ + /* + * By default send all common interrupts to all available online CPUs. + * The affinity of common interrupts in IDU must be set manually since + * in some cases the kernel will not call irq_set_affinity() by itself: + * 1. When the kernel is not configured with support of SMP. + * 2. When the kernel is configured with support of SMP but upper + * interrupt controllers does not support setting of the affinity + * and cannot propagate it to IDU. + */ + idu_irq_set_affinity(data, cpu_online_mask, false); + idu_irq_unmask(data); +} static struct irq_chip idu_irq_chip = { .name = "MCIP IDU Intc", .irq_mask = idu_irq_mask, .irq_unmask = idu_irq_unmask, + .irq_enable = idu_irq_enable, #ifdef CONFIG_SMP .irq_set_affinity = idu_irq_set_affinity, #endif @@ -243,36 +256,14 @@ static int idu_irq_xlate(struct irq_domain *d, struct device_node *n, const u32 *intspec, unsigned int intsize, irq_hw_number_t *out_hwirq, unsigned int *out_type) { - irq_hw_number_t hwirq = *out_hwirq = intspec[0]; - int distri = intspec[1]; - unsigned long flags; - + /* + * Ignore value of interrupt distribution mode for common interrupts in + * IDU which resides in intspec[1] since setting an affinity using value + * from Device Tree is deprecated in ARC. + */ + *out_hwirq = intspec[0]; *out_type = IRQ_TYPE_NONE; - /* XXX: validate distribution scheme again online cpu mask */ - if (distri == 0) { - /* 0 - Round Robin to all cpus, otherwise 1 bit per core */ - raw_spin_lock_irqsave(&mcip_lock, flags); - idu_set_dest(hwirq, BIT(num_online_cpus()) - 1); - idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR); - raw_spin_unlock_irqrestore(&mcip_lock, flags); - } else { - /* - * DEST based distribution for Level Triggered intr can only - * have 1 CPU, so generalize it to always contain 1 cpu - */ - int cpu = ffs(distri); - - if (cpu != fls(distri)) - pr_warn("IDU irq %lx distri mode set to cpu %x\n", - hwirq, cpu); - - raw_spin_lock_irqsave(&mcip_lock, flags); - idu_set_dest(hwirq, cpu); - idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_DEST); - raw_spin_unlock_irqrestore(&mcip_lock, flags); - } - return 0; } diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 88674d972c9d..2afbafadb6ab 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -90,22 +90,37 @@ void __init smp_cpus_done(unsigned int max_cpus) */ static volatile int wake_flag; +#ifdef CONFIG_ISA_ARCOMPACT + +#define __boot_read(f) f +#define __boot_write(f, v) f = v + +#else + +#define __boot_read(f) arc_read_uncached_32(&f) +#define __boot_write(f, v) arc_write_uncached_32(&f, v) + +#endif + static void arc_default_smp_cpu_kick(int cpu, unsigned long pc) { BUG_ON(cpu == 0); - wake_flag = cpu; + + __boot_write(wake_flag, cpu); } void arc_platform_smp_wait_to_boot(int cpu) { - while (wake_flag != cpu) + /* for halt-on-reset, we've waited already */ + if (IS_ENABLED(CONFIG_ARC_SMP_HALT_ON_RESET)) + return; + + while (__boot_read(wake_flag) != cpu) ; - wake_flag = 0; - __asm__ __volatile__("j @first_lines_of_secondary \n"); + __boot_write(wake_flag, 0); } - const char *arc_platform_smp_cpuinfo(void) { return plat_smp_ops.info ? : ""; diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index abd961f3e763..91ebe382147f 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -241,8 +241,9 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, if (state.fault) goto fault; + /* clear any remanants of delay slot */ if (delay_mode(regs)) { - regs->ret = regs->bta; + regs->ret = regs->bta ~1U; regs->status32 &= ~STATUS_DE_MASK; } else { regs->ret += state.instr_len; diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig index 79c415c33f69..809f0bf3042a 100644 --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -24,7 +24,7 @@ CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x41000000,8M console=ttySAC1,115200 init=/linuxrc mem=256M" CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig index 361686a362f1..69a4bd13eea5 100644 --- a/arch/arm/configs/multi_v5_defconfig +++ b/arch/arm/configs/multi_v5_defconfig @@ -58,7 +58,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_IDLE=y CONFIG_ARM_KIRKWOOD_CPUIDLE=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 028d2b70e3b5..8d7b17f52750 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -132,7 +132,7 @@ CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_KEXEC=y CONFIG_EFI=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m diff --git a/arch/arm/configs/mvebu_v5_defconfig b/arch/arm/configs/mvebu_v5_defconfig index f7f6039419aa..4b598da0d086 100644 --- a/arch/arm/configs/mvebu_v5_defconfig +++ b/arch/arm/configs/mvebu_v5_defconfig @@ -44,7 +44,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_IDLE=y CONFIG_ARM_KIRKWOOD_CPUIDLE=y diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index e4314b1227a3..271dc7e78e43 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -97,7 +97,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_CMDLINE="root=/dev/ram0 ro" CONFIG_KEXEC=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig index 1b0f8ae36fb3..adeaecd831a4 100644 --- a/arch/arm/configs/shmobile_defconfig +++ b/arch/arm/configs/shmobile_defconfig @@ -38,7 +38,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_ARM_APPENDED_DTB=y CONFIG_KEXEC=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 23e9e13bd2aa..655e65f38f31 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -11,6 +11,7 @@ * for more details. */ +#include #include #include #include @@ -209,7 +210,12 @@ static struct notifier_block init_cpu_capacity_notifier = { static int __init register_cpufreq_notifier(void) { - if (cap_parsing_failed) + /* + * on ACPI-based systems we need to use the default cpu capacity + * until we have the necessary code to parse the cpu capacity, so + * skip registering cpufreq notifier. + */ + if (!acpi_disabled || cap_parsing_failed) return -EINVAL; if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) { diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h index 1c2a5e264fc7..e93c9494503a 100644 --- a/arch/frv/include/asm/atomic.h +++ b/arch/frv/include/asm/atomic.h @@ -139,7 +139,7 @@ static inline void atomic64_dec(atomic64_t *v) #define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0) #define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) #define atomic64_inc_and_test(v) (atomic64_inc_return((v)) == 0) - +#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) #define atomic_cmpxchg(v, old, new) (cmpxchg(&(v)->counter, old, new)) #define atomic_xchg(v, new) (xchg(&(v)->counter, new)) @@ -161,6 +161,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) return c; } +static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u) +{ + long long c, old; + + c = atomic64_read(v); + for (;;) { + if (unlikely(c == u)) + break; + old = atomic64_cmpxchg(v, c, c + i); + if (likely(old == c)) + break; + c = old; + } + return c != u; +} + +static inline long long atomic64_dec_if_positive(atomic64_t *v) +{ + long long c, old, dec; + + c = atomic64_read(v); + for (;;) { + dec = c - 1; + if (unlikely(dec < 0)) + break; + old = atomic64_cmpxchg((v), c, dec); + if (likely(old == c)) + break; + c = old; + } + return dec; +} + #define ATOMIC_OP(op) \ static inline int atomic_fetch_##op(int i, atomic_t *v) \ { \ diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig index 5da76e0e120f..bed745596d86 100644 --- a/arch/mips/configs/lemote2f_defconfig +++ b/arch/mips/configs/lemote2f_defconfig @@ -40,7 +40,6 @@ CONFIG_PM_STD_PARTITION="/dev/hda3" CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_DEBUG=y CONFIG_CPU_FREQ_STAT=m -CONFIG_CPU_FREQ_STAT_DETAILS=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m diff --git a/arch/mn10300/include/asm/switch_to.h b/arch/mn10300/include/asm/switch_to.h index 393d311735c8..67e333aa7629 100644 --- a/arch/mn10300/include/asm/switch_to.h +++ b/arch/mn10300/include/asm/switch_to.h @@ -16,7 +16,7 @@ struct task_struct; struct thread_struct; -#if !defined(CONFIG_LAZY_SAVE_FPU) +#if defined(CONFIG_FPU) && !defined(CONFIG_LAZY_SAVE_FPU) struct fpu_state_struct; extern asmlinkage void fpu_save(struct fpu_state_struct *); #define switch_fpu(prev, next) \ diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h index 3f9406d9b9d6..da87943328a5 100644 --- a/arch/parisc/include/asm/bitops.h +++ b/arch/parisc/include/asm/bitops.h @@ -6,7 +6,7 @@ #endif #include -#include /* for BITS_PER_LONG/SHIFT_PER_LONG */ +#include #include #include #include @@ -17,6 +17,12 @@ * to include/asm-i386/bitops.h or kerneldoc */ +#if __BITS_PER_LONG == 64 +#define SHIFT_PER_LONG 6 +#else +#define SHIFT_PER_LONG 5 +#endif + #define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1)) diff --git a/arch/parisc/include/uapi/asm/bitsperlong.h b/arch/parisc/include/uapi/asm/bitsperlong.h index e0a23c7bdd43..07fa7e50bdc0 100644 --- a/arch/parisc/include/uapi/asm/bitsperlong.h +++ b/arch/parisc/include/uapi/asm/bitsperlong.h @@ -3,10 +3,8 @@ #if defined(__LP64__) #define __BITS_PER_LONG 64 -#define SHIFT_PER_LONG 6 #else #define __BITS_PER_LONG 32 -#define SHIFT_PER_LONG 5 #endif #include diff --git a/arch/parisc/include/uapi/asm/swab.h b/arch/parisc/include/uapi/asm/swab.h index e78403b129ef..928e1bbac98f 100644 --- a/arch/parisc/include/uapi/asm/swab.h +++ b/arch/parisc/include/uapi/asm/swab.h @@ -1,6 +1,7 @@ #ifndef _PARISC_SWAB_H #define _PARISC_SWAB_H +#include #include #include @@ -38,7 +39,7 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x) } #define __arch_swab32 __arch_swab32 -#if BITS_PER_LONG > 32 +#if __BITS_PER_LONG > 32 /* ** From "PA-RISC 2.0 Architecture", HP Professional Books. ** See Appendix I page 8 , "Endian Byte Swapping". @@ -61,6 +62,6 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x) return x; } #define __arch_swab64 __arch_swab64 -#endif /* BITS_PER_LONG > 32 */ +#endif /* __BITS_PER_LONG > 32 */ #endif /* _PARISC_SWAB_H */ diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 3ce91a3df27f..1d2d69dd6409 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -62,7 +62,6 @@ CONFIG_MPC8610_HPCD=y CONFIG_GEF_SBC610=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_STAT=m -CONFIG_CPU_FREQ_STAT_DETAILS=y CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 7447ba509c30..12020b55887b 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -963,6 +963,11 @@ static int s390_fpregs_set(struct task_struct *target, if (target == current) save_fpu_regs(); + if (MACHINE_HAS_VX) + convert_vx_to_fp(fprs, target->thread.fpu.vxrs); + else + memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs)); + /* If setting FPC, must validate it first. */ if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) { u32 ufpc[2] = { target->thread.fpu.fpc, 0 }; @@ -1067,6 +1072,9 @@ static int s390_vxrs_low_set(struct task_struct *target, if (target == current) save_fpu_regs(); + for (i = 0; i < __NUM_VXRS_LOW; i++) + vxrs[i] = *((__u64 *)(target->thread.fpu.vxrs + i) + 1); + rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1); if (rc == 0) for (i = 0; i < __NUM_VXRS_LOW; i++) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 7a1897c51c54..d56ef26d4681 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -202,7 +202,7 @@ static inline pgste_t ptep_xchg_start(struct mm_struct *mm, return pgste; } -static inline void ptep_xchg_commit(struct mm_struct *mm, +static inline pte_t ptep_xchg_commit(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pgste_t pgste, pte_t old, pte_t new) { @@ -220,6 +220,7 @@ static inline void ptep_xchg_commit(struct mm_struct *mm, } else { *ptep = new; } + return old; } pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr, @@ -231,7 +232,7 @@ pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr, preempt_disable(); pgste = ptep_xchg_start(mm, addr, ptep); old = ptep_flush_direct(mm, addr, ptep); - ptep_xchg_commit(mm, addr, ptep, pgste, old, new); + old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new); preempt_enable(); return old; } @@ -246,7 +247,7 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr, preempt_disable(); pgste = ptep_xchg_start(mm, addr, ptep); old = ptep_flush_lazy(mm, addr, ptep); - ptep_xchg_commit(mm, addr, ptep, pgste, old, new); + old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new); preempt_enable(); return old; } diff --git a/arch/sh/configs/sh7785lcr_32bit_defconfig b/arch/sh/configs/sh7785lcr_32bit_defconfig index 9bdcf72ec06a..2fce54d9c388 100644 --- a/arch/sh/configs/sh7785lcr_32bit_defconfig +++ b/arch/sh/configs/sh7785lcr_32bit_defconfig @@ -25,7 +25,7 @@ CONFIG_SH_SH7785LCR=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_SH_CPU_FREQ=y CONFIG_HEARTBEAT=y diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c index d89b7011667c..e279572824b1 100644 --- a/arch/tile/kernel/ptrace.c +++ b/arch/tile/kernel/ptrace.c @@ -111,7 +111,7 @@ static int tile_gpr_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { int ret; - struct pt_regs regs; + struct pt_regs regs = *task_pt_regs(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0, sizeof(regs)); diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c index 82b0b5710979..b0399e8f6d27 100644 --- a/drivers/acpi/acpica/tbdata.c +++ b/drivers/acpi/acpica/tbdata.c @@ -852,23 +852,18 @@ acpi_tb_install_and_load_table(acpi_physical_address address, ACPI_FUNCTION_TRACE(tb_install_and_load_table); - (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); - /* Install the table and load it into the namespace */ status = acpi_tb_install_standard_table(address, flags, TRUE, override, &i); if (ACPI_FAILURE(status)) { - goto unlock_and_exit; + goto exit; } - (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); status = acpi_tb_load_table(i, acpi_gbl_root_node); - (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); -unlock_and_exit: +exit: *table_index = i; - (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); return_ACPI_STATUS(status); } diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c index 5fdf251a9f97..01e1b3d63fc0 100644 --- a/drivers/acpi/acpica/tbinstal.c +++ b/drivers/acpi/acpica/tbinstal.c @@ -217,6 +217,10 @@ acpi_tb_install_standard_table(acpi_physical_address address, goto release_and_exit; } + /* Acquire the table lock */ + + (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); + if (reload) { /* * Validate the incoming table signature. @@ -244,7 +248,7 @@ acpi_tb_install_standard_table(acpi_physical_address address, new_table_desc.signature.integer)); status = AE_BAD_SIGNATURE; - goto release_and_exit; + goto unlock_and_exit; } /* Check if table is already registered */ @@ -279,7 +283,7 @@ acpi_tb_install_standard_table(acpi_physical_address address, /* Table is still loaded, this is an error */ status = AE_ALREADY_EXISTS; - goto release_and_exit; + goto unlock_and_exit; } else { /* * Table was unloaded, allow it to be reloaded. @@ -290,6 +294,7 @@ acpi_tb_install_standard_table(acpi_physical_address address, * indicate the re-installation. */ acpi_tb_uninstall_table(&new_table_desc); + (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); *table_index = i; return_ACPI_STATUS(AE_OK); } @@ -303,11 +308,19 @@ acpi_tb_install_standard_table(acpi_physical_address address, /* Invoke table handler if present */ + (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); if (acpi_gbl_table_handler) { (void)acpi_gbl_table_handler(ACPI_TABLE_EVENT_INSTALL, new_table_desc.pointer, acpi_gbl_table_handler_context); } + (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); + +unlock_and_exit: + + /* Release the table lock */ + + (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); release_and_exit: diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index f0b4a981b8d3..18b72eec3507 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -75,10 +75,8 @@ static int acpi_processor_ppc_notifier(struct notifier_block *nb, struct acpi_processor *pr; unsigned int ppc = 0; - if (event == CPUFREQ_START && ignore_ppc <= 0) { + if (ignore_ppc < 0) ignore_ppc = 0; - return 0; - } if (ignore_ppc) return 0; diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 9b6cebe227a0..54abb26b7366 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -674,14 +674,6 @@ static void acpi_sleep_suspend_setup(void) if (acpi_sleep_state_supported(i)) sleep_states[i] = 1; - /* - * Use suspend-to-idle by default if ACPI_FADT_LOW_POWER_S0 is set and - * the default suspend mode was not selected from the command line. - */ - if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0 && - mem_sleep_default > PM_SUSPEND_MEM) - mem_sleep_default = PM_SUSPEND_FREEZE; - suspend_set_ops(old_suspend_ordering ? &acpi_suspend_ops_old : &acpi_suspend_ops); freeze_set_ops(&acpi_freeze_ops); diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 02ded25c82e4..7f48156cbc0c 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -305,17 +305,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Dell System XPS L702X"), }, }, - { - /* https://bugzilla.redhat.com/show_bug.cgi?id=1204476 */ - /* https://bugs.launchpad.net/ubuntu/+source/linux-lts-trusty/+bug/1416940 */ - .callback = video_detect_force_native, - .ident = "HP Pavilion dv6", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv6 Notebook PC"), - }, - }, - { }, }; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 8ab8ea1253e6..dacb6a8418aa 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -408,14 +408,14 @@ static ssize_t show_valid_zones(struct device *dev, sprintf(buf, "%s", zone->name); /* MMOP_ONLINE_KERNEL */ - zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL); + zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL, &zone_shift); if (zone_shift) { strcat(buf, " "); strcat(buf, (zone + zone_shift)->name); } /* MMOP_ONLINE_MOVABLE */ - zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE); + zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE, &zone_shift); if (zone_shift) { strcat(buf, " "); strcat(buf, (zone + zone_shift)->name); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index b2bdfa81f929..265f1a7072e9 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -197,13 +197,13 @@ struct blkfront_info /* Number of pages per ring buffer. */ unsigned int nr_ring_pages; struct request_queue *rq; - unsigned int feature_flush; - unsigned int feature_fua; + unsigned int feature_flush:1; + unsigned int feature_fua:1; unsigned int feature_discard:1; unsigned int feature_secdiscard:1; + unsigned int feature_persistent:1; unsigned int discard_granularity; unsigned int discard_alignment; - unsigned int feature_persistent:1; /* Number of 4KB segments handled */ unsigned int max_indirect_segments; int is_ready; @@ -2223,7 +2223,7 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo) } else grants = info->max_indirect_segments; - psegs = grants / GRANTS_PER_PSEG; + psegs = DIV_ROUND_UP(grants, GRANTS_PER_PSEG); err = fill_grant_buffer(rinfo, (grants + INDIRECT_GREFS(grants)) * BLK_RING_SIZE(info)); @@ -2323,13 +2323,16 @@ static void blkfront_gather_backend_features(struct blkfront_info *info) blkfront_setup_discard(info); info->feature_persistent = - xenbus_read_unsigned(info->xbdev->otherend, - "feature-persistent", 0); + !!xenbus_read_unsigned(info->xbdev->otherend, + "feature-persistent", 0); indirect_segments = xenbus_read_unsigned(info->xbdev->otherend, "feature-max-indirect-segments", 0); - info->max_indirect_segments = min(indirect_segments, - xen_blkif_max_segments); + if (indirect_segments > xen_blkif_max_segments) + indirect_segments = xen_blkif_max_segments; + if (indirect_segments <= BLKIF_MAX_SEGMENTS_PER_REQUEST) + indirect_segments = 0; + info->max_indirect_segments = indirect_segments; } /* @@ -2652,6 +2655,9 @@ static int __init xlblk_init(void) if (!xen_domain()) return -ENODEV; + if (xen_blkif_max_segments < BLKIF_MAX_SEGMENTS_PER_REQUEST) + xen_blkif_max_segments = BLKIF_MAX_SEGMENTS_PER_REQUEST; + if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) { pr_info("Invalid max_ring_order (%d), will use default max: %d.\n", xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER); diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index d8b164a7c4e5..15adef473d42 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -37,14 +37,6 @@ config CPU_FREQ_STAT If in doubt, say N. -config CPU_FREQ_STAT_DETAILS - bool "CPU frequency transition statistics details" - depends on CPU_FREQ_STAT - help - Show detailed CPU frequency transition table in sysfs. - - If in doubt, say N. - choice prompt "Default CPUFreq governor" default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1100_CPUFREQ || ARM_SA1110_CPUFREQ diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index cc475eff90b3..408479540566 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1078,15 +1078,11 @@ err_free_policy: return NULL; } -static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify) +static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy) { struct kobject *kobj; struct completion *cmp; - if (notify) - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_REMOVE_POLICY, policy); - down_write(&policy->rwsem); cpufreq_stats_free_table(policy); kobj = &policy->kobj; @@ -1104,7 +1100,7 @@ static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify) pr_debug("wait complete\n"); } -static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify) +static void cpufreq_policy_free(struct cpufreq_policy *policy) { unsigned long flags; int cpu; @@ -1117,7 +1113,7 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify) per_cpu(cpufreq_cpu_data, cpu) = NULL; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - cpufreq_policy_put_kobj(policy, notify); + cpufreq_policy_put_kobj(policy); free_cpumask_var(policy->real_cpus); free_cpumask_var(policy->related_cpus); free_cpumask_var(policy->cpus); @@ -1244,17 +1240,12 @@ static int cpufreq_online(unsigned int cpu) goto out_exit_policy; cpufreq_stats_create_table(policy); - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_CREATE_POLICY, policy); write_lock_irqsave(&cpufreq_driver_lock, flags); list_add(&policy->policy_list, &cpufreq_policy_list); write_unlock_irqrestore(&cpufreq_driver_lock, flags); } - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_START, policy); - ret = cpufreq_init_policy(policy); if (ret) { pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n", @@ -1282,7 +1273,7 @@ out_exit_policy: if (cpufreq_driver->exit) cpufreq_driver->exit(policy); out_free_policy: - cpufreq_policy_free(policy, !new_policy); + cpufreq_policy_free(policy); return ret; } @@ -1403,7 +1394,7 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) remove_cpu_dev_symlink(policy, dev); if (cpumask_empty(policy->real_cpus)) - cpufreq_policy_free(policy, true); + cpufreq_policy_free(policy); } /** diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index ac284e66839c..18abd454da43 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -25,9 +25,7 @@ struct cpufreq_stats { unsigned int last_index; u64 *time_in_state; unsigned int *freq_table; -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS unsigned int *trans_table; -#endif }; static int cpufreq_stats_update(struct cpufreq_stats *stats) @@ -46,9 +44,7 @@ static void cpufreq_stats_clear_table(struct cpufreq_stats *stats) unsigned int count = stats->max_state; memset(stats->time_in_state, 0, count * sizeof(u64)); -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS memset(stats->trans_table, 0, count * count * sizeof(int)); -#endif stats->last_time = get_jiffies_64(); stats->total_trans = 0; } @@ -84,7 +80,6 @@ static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf, return count; } -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) { struct cpufreq_stats *stats = policy->stats; @@ -129,7 +124,6 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) return len; } cpufreq_freq_attr_ro(trans_table); -#endif cpufreq_freq_attr_ro(total_trans); cpufreq_freq_attr_ro(time_in_state); @@ -139,9 +133,7 @@ static struct attribute *default_attrs[] = { &total_trans.attr, &time_in_state.attr, &reset.attr, -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS &trans_table.attr, -#endif NULL }; static struct attribute_group stats_attr_group = { @@ -200,9 +192,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) alloc_size = count * sizeof(int) + count * sizeof(u64); -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS alloc_size += count * count * sizeof(int); -#endif /* Allocate memory for time_in_state/freq_table/trans_table in one go */ stats->time_in_state = kzalloc(alloc_size, GFP_KERNEL); @@ -211,9 +201,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) stats->freq_table = (unsigned int *)(stats->time_in_state + count); -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS stats->trans_table = stats->freq_table + count; -#endif stats->max_state = count; @@ -259,8 +247,6 @@ void cpufreq_stats_record_transition(struct cpufreq_policy *policy, cpufreq_stats_update(stats); stats->last_index = new_index; -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS stats->trans_table[old_index * stats->max_state + new_index]++; -#endif stats->total_trans++; } diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 86e36544925f..eb0f7fb71685 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -358,6 +358,8 @@ static struct pstate_funcs pstate_funcs __read_mostly; static int hwp_active __read_mostly; static bool per_cpu_limits __read_mostly; +static bool driver_registered __read_mostly; + #ifdef CONFIG_ACPI static bool acpi_ppc; #endif @@ -394,6 +396,7 @@ static struct perf_limits *limits = &performance_limits; static struct perf_limits *limits = &powersave_limits; #endif +static DEFINE_MUTEX(intel_pstate_driver_lock); static DEFINE_MUTEX(intel_pstate_limits_lock); #ifdef CONFIG_ACPI @@ -538,7 +541,6 @@ static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) acpi_processor_unregister_performance(policy->cpu); } - #else static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) { @@ -873,7 +875,10 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy) rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap); hw_min = HWP_LOWEST_PERF(cap); - hw_max = HWP_HIGHEST_PERF(cap); + if (limits->no_turbo) + hw_max = HWP_GUARANTEED_PERF(cap); + else + hw_max = HWP_HIGHEST_PERF(cap); range = hw_max - hw_min; max_perf_pct = perf_limits->max_perf_pct; @@ -887,11 +892,6 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy) adj_range = max_perf_pct * range / 100; max = hw_min + adj_range; - if (limits->no_turbo) { - hw_max = HWP_GUARANTEED_PERF(cap); - if (hw_max < max) - max = hw_max; - } value &= ~HWP_MAX_PERF(~0L); value |= HWP_MAX_PERF(max); @@ -1007,37 +1007,59 @@ static int pid_param_get(void *data, u64 *val) } DEFINE_SIMPLE_ATTRIBUTE(fops_pid_param, pid_param_get, pid_param_set, "%llu\n"); +static struct dentry *debugfs_parent; + struct pid_param { char *name; void *value; + struct dentry *dentry; }; static struct pid_param pid_files[] = { - {"sample_rate_ms", &pid_params.sample_rate_ms}, - {"d_gain_pct", &pid_params.d_gain_pct}, - {"i_gain_pct", &pid_params.i_gain_pct}, - {"deadband", &pid_params.deadband}, - {"setpoint", &pid_params.setpoint}, - {"p_gain_pct", &pid_params.p_gain_pct}, - {NULL, NULL} + {"sample_rate_ms", &pid_params.sample_rate_ms, }, + {"d_gain_pct", &pid_params.d_gain_pct, }, + {"i_gain_pct", &pid_params.i_gain_pct, }, + {"deadband", &pid_params.deadband, }, + {"setpoint", &pid_params.setpoint, }, + {"p_gain_pct", &pid_params.p_gain_pct, }, + {NULL, NULL, } }; -static void __init intel_pstate_debug_expose_params(void) +static void intel_pstate_debug_expose_params(void) { - struct dentry *debugfs_parent; - int i = 0; + int i; debugfs_parent = debugfs_create_dir("pstate_snb", NULL); if (IS_ERR_OR_NULL(debugfs_parent)) return; - while (pid_files[i].name) { - debugfs_create_file(pid_files[i].name, 0660, - debugfs_parent, pid_files[i].value, - &fops_pid_param); - i++; + + for (i = 0; pid_files[i].name; i++) { + struct dentry *dentry; + + dentry = debugfs_create_file(pid_files[i].name, 0660, + debugfs_parent, pid_files[i].value, + &fops_pid_param); + if (!IS_ERR(dentry)) + pid_files[i].dentry = dentry; } } +static void intel_pstate_debug_hide_params(void) +{ + int i; + + if (IS_ERR_OR_NULL(debugfs_parent)) + return; + + for (i = 0; pid_files[i].name; i++) { + debugfs_remove(pid_files[i].dentry); + pid_files[i].dentry = NULL; + } + + debugfs_remove(debugfs_parent); + debugfs_parent = NULL; +} + /************************** debugfs end ************************/ /************************** sysfs begin ************************/ @@ -1048,6 +1070,34 @@ static void __init intel_pstate_debug_expose_params(void) return sprintf(buf, "%u\n", limits->object); \ } +static ssize_t intel_pstate_show_status(char *buf); +static int intel_pstate_update_status(const char *buf, size_t size); + +static ssize_t show_status(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + ssize_t ret; + + mutex_lock(&intel_pstate_driver_lock); + ret = intel_pstate_show_status(buf); + mutex_unlock(&intel_pstate_driver_lock); + + return ret; +} + +static ssize_t store_status(struct kobject *a, struct attribute *b, + const char *buf, size_t count) +{ + char *p = memchr(buf, '\n', count); + int ret; + + mutex_lock(&intel_pstate_driver_lock); + ret = intel_pstate_update_status(buf, p ? p - buf : count); + mutex_unlock(&intel_pstate_driver_lock); + + return ret < 0 ? ret : count; +} + static ssize_t show_turbo_pct(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -1055,12 +1105,22 @@ static ssize_t show_turbo_pct(struct kobject *kobj, int total, no_turbo, turbo_pct; uint32_t turbo_fp; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + cpu = all_cpu_data[0]; total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1; no_turbo = cpu->pstate.max_pstate - cpu->pstate.min_pstate + 1; turbo_fp = div_fp(no_turbo, total); turbo_pct = 100 - fp_toint(mul_fp(turbo_fp, int_tofp(100))); + + mutex_unlock(&intel_pstate_driver_lock); + return sprintf(buf, "%u\n", turbo_pct); } @@ -1070,8 +1130,18 @@ static ssize_t show_num_pstates(struct kobject *kobj, struct cpudata *cpu; int total; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + cpu = all_cpu_data[0]; total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1; + + mutex_unlock(&intel_pstate_driver_lock); + return sprintf(buf, "%u\n", total); } @@ -1080,12 +1150,21 @@ static ssize_t show_no_turbo(struct kobject *kobj, { ssize_t ret; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + update_turbo_state(); if (limits->turbo_disabled) ret = sprintf(buf, "%u\n", limits->turbo_disabled); else ret = sprintf(buf, "%u\n", limits->no_turbo); + mutex_unlock(&intel_pstate_driver_lock); + return ret; } @@ -1099,12 +1178,20 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + mutex_lock(&intel_pstate_limits_lock); update_turbo_state(); if (limits->turbo_disabled) { pr_warn("Turbo disabled by BIOS or unavailable on processor\n"); mutex_unlock(&intel_pstate_limits_lock); + mutex_unlock(&intel_pstate_driver_lock); return -EPERM; } @@ -1114,6 +1201,8 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, intel_pstate_update_policies(); + mutex_unlock(&intel_pstate_driver_lock); + return count; } @@ -1127,6 +1216,13 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + mutex_lock(&intel_pstate_limits_lock); limits->max_sysfs_pct = clamp_t(int, input, 0 , 100); @@ -1142,6 +1238,8 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, intel_pstate_update_policies(); + mutex_unlock(&intel_pstate_driver_lock); + return count; } @@ -1155,6 +1253,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + mutex_lock(&intel_pstate_limits_lock); limits->min_sysfs_pct = clamp_t(int, input, 0 , 100); @@ -1170,12 +1275,15 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, intel_pstate_update_policies(); + mutex_unlock(&intel_pstate_driver_lock); + return count; } show_one(max_perf_pct, max_perf_pct); show_one(min_perf_pct, min_perf_pct); +define_one_global_rw(status); define_one_global_rw(no_turbo); define_one_global_rw(max_perf_pct); define_one_global_rw(min_perf_pct); @@ -1183,6 +1291,7 @@ define_one_global_ro(turbo_pct); define_one_global_ro(num_pstates); static struct attribute *intel_pstate_attributes[] = { + &status.attr, &no_turbo.attr, &turbo_pct.attr, &num_pstates.attr, @@ -1364,48 +1473,71 @@ static int core_get_max_pstate_physical(void) return (value >> 8) & 0xFF; } +static int core_get_tdp_ratio(u64 plat_info) +{ + /* Check how many TDP levels present */ + if (plat_info & 0x600000000) { + u64 tdp_ctrl; + u64 tdp_ratio; + int tdp_msr; + int err; + + /* Get the TDP level (0, 1, 2) to get ratios */ + err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl); + if (err) + return err; + + /* TDP MSR are continuous starting at 0x648 */ + tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x03); + err = rdmsrl_safe(tdp_msr, &tdp_ratio); + if (err) + return err; + + /* For level 1 and 2, bits[23:16] contain the ratio */ + if (tdp_ctrl & 0x03) + tdp_ratio >>= 16; + + tdp_ratio &= 0xff; /* ratios are only 8 bits long */ + pr_debug("tdp_ratio %x\n", (int)tdp_ratio); + + return (int)tdp_ratio; + } + + return -ENXIO; +} + static int core_get_max_pstate(void) { u64 tar; u64 plat_info; int max_pstate; + int tdp_ratio; int err; rdmsrl(MSR_PLATFORM_INFO, plat_info); max_pstate = (plat_info >> 8) & 0xFF; + tdp_ratio = core_get_tdp_ratio(plat_info); + if (tdp_ratio <= 0) + return max_pstate; + + if (hwp_active) { + /* Turbo activation ratio is not used on HWP platforms */ + return tdp_ratio; + } + err = rdmsrl_safe(MSR_TURBO_ACTIVATION_RATIO, &tar); if (!err) { + int tar_levels; + /* Do some sanity checking for safety */ - if (plat_info & 0x600000000) { - u64 tdp_ctrl; - u64 tdp_ratio; - int tdp_msr; - - err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl); - if (err) - goto skip_tar; - - tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x3); - err = rdmsrl_safe(tdp_msr, &tdp_ratio); - if (err) - goto skip_tar; - - /* For level 1 and 2, bits[23:16] contain the ratio */ - if (tdp_ctrl) - tdp_ratio >>= 16; - - tdp_ratio &= 0xff; /* ratios are only 8 bits long */ - if (tdp_ratio - 1 == tar) { - max_pstate = tar; - pr_debug("max_pstate=TAC %x\n", max_pstate); - } else { - goto skip_tar; - } + tar_levels = tar & 0xff; + if (tdp_ratio - 1 == tar_levels) { + max_pstate = tar_levels; + pr_debug("max_pstate=TAC %x\n", max_pstate); } } -skip_tar: return max_pstate; } @@ -2035,7 +2167,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) limits = &performance_limits; perf_limits = limits; } - if (policy->max >= policy->cpuinfo.max_freq) { + if (policy->max >= policy->cpuinfo.max_freq && + !limits->no_turbo) { pr_debug("set performance\n"); intel_pstate_set_performance_limits(perf_limits); goto out; @@ -2071,12 +2204,37 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) static int intel_pstate_verify_policy(struct cpufreq_policy *policy) { + struct cpudata *cpu = all_cpu_data[policy->cpu]; + struct perf_limits *perf_limits; + + if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) + perf_limits = &performance_limits; + else + perf_limits = &powersave_limits; + + update_turbo_state(); + policy->cpuinfo.max_freq = perf_limits->turbo_disabled || + perf_limits->no_turbo ? + cpu->pstate.max_freq : + cpu->pstate.turbo_freq; + cpufreq_verify_within_cpu_limits(policy); if (policy->policy != CPUFREQ_POLICY_POWERSAVE && policy->policy != CPUFREQ_POLICY_PERFORMANCE) return -EINVAL; + /* When per-CPU limits are used, sysfs limits are not used */ + if (!per_cpu_limits) { + unsigned int max_freq, min_freq; + + max_freq = policy->cpuinfo.max_freq * + limits->max_sysfs_pct / 100; + min_freq = policy->cpuinfo.max_freq * + limits->min_sysfs_pct / 100; + cpufreq_verify_within_limits(policy, min_freq, max_freq); + } + return 0; } @@ -2287,6 +2445,111 @@ static struct cpufreq_driver intel_cpufreq = { static struct cpufreq_driver *intel_pstate_driver = &intel_pstate; +static void intel_pstate_driver_cleanup(void) +{ + unsigned int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) { + if (all_cpu_data[cpu]) { + if (intel_pstate_driver == &intel_pstate) + intel_pstate_clear_update_util_hook(cpu); + + kfree(all_cpu_data[cpu]); + all_cpu_data[cpu] = NULL; + } + } + put_online_cpus(); +} + +static int intel_pstate_register_driver(void) +{ + int ret; + + ret = cpufreq_register_driver(intel_pstate_driver); + if (ret) { + intel_pstate_driver_cleanup(); + return ret; + } + + mutex_lock(&intel_pstate_limits_lock); + driver_registered = true; + mutex_unlock(&intel_pstate_limits_lock); + + if (intel_pstate_driver == &intel_pstate && !hwp_active && + pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load) + intel_pstate_debug_expose_params(); + + return 0; +} + +static int intel_pstate_unregister_driver(void) +{ + if (hwp_active) + return -EBUSY; + + if (intel_pstate_driver == &intel_pstate && !hwp_active && + pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load) + intel_pstate_debug_hide_params(); + + mutex_lock(&intel_pstate_limits_lock); + driver_registered = false; + mutex_unlock(&intel_pstate_limits_lock); + + cpufreq_unregister_driver(intel_pstate_driver); + intel_pstate_driver_cleanup(); + + return 0; +} + +static ssize_t intel_pstate_show_status(char *buf) +{ + if (!driver_registered) + return sprintf(buf, "off\n"); + + return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ? + "active" : "passive"); +} + +static int intel_pstate_update_status(const char *buf, size_t size) +{ + int ret; + + if (size == 3 && !strncmp(buf, "off", size)) + return driver_registered ? + intel_pstate_unregister_driver() : -EINVAL; + + if (size == 6 && !strncmp(buf, "active", size)) { + if (driver_registered) { + if (intel_pstate_driver == &intel_pstate) + return 0; + + ret = intel_pstate_unregister_driver(); + if (ret) + return ret; + } + + intel_pstate_driver = &intel_pstate; + return intel_pstate_register_driver(); + } + + if (size == 7 && !strncmp(buf, "passive", size)) { + if (driver_registered) { + if (intel_pstate_driver != &intel_pstate) + return 0; + + ret = intel_pstate_unregister_driver(); + if (ret) + return ret; + } + + intel_pstate_driver = &intel_cpufreq; + return intel_pstate_register_driver(); + } + + return -EINVAL; +} + static int no_load __initdata; static int no_hwp __initdata; static int hwp_only __initdata; @@ -2474,9 +2737,9 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = { static int __init intel_pstate_init(void) { - int cpu, rc = 0; const struct x86_cpu_id *id; struct cpu_defaults *cpu_def; + int rc = 0; if (no_load) return -ENODEV; @@ -2508,45 +2771,29 @@ hwp_cpu_matched: if (intel_pstate_platform_pwr_mgmt_exists()) return -ENODEV; + if (!hwp_active && hwp_only) + return -ENOTSUPP; + pr_info("Intel P-state driver initializing\n"); all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus()); if (!all_cpu_data) return -ENOMEM; - if (!hwp_active && hwp_only) - goto out; - intel_pstate_request_control_from_smm(); - rc = cpufreq_register_driver(intel_pstate_driver); - if (rc) - goto out; - - if (intel_pstate_driver == &intel_pstate && !hwp_active && - pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load) - intel_pstate_debug_expose_params(); - intel_pstate_sysfs_expose_params(); + mutex_lock(&intel_pstate_driver_lock); + rc = intel_pstate_register_driver(); + mutex_unlock(&intel_pstate_driver_lock); + if (rc) + return rc; + if (hwp_active) pr_info("HWP enabled\n"); - return rc; -out: - get_online_cpus(); - for_each_online_cpu(cpu) { - if (all_cpu_data[cpu]) { - if (intel_pstate_driver == &intel_pstate) - intel_pstate_clear_update_util_hook(cpu); - - kfree(all_cpu_data[cpu]); - } - } - - put_online_cpus(); - vfree(all_cpu_data); - return -ENODEV; + return 0; } device_initcall(intel_pstate_init); diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 37671b545880..3ff5160451b4 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -144,6 +144,7 @@ static struct powernv_pstate_info { unsigned int max; unsigned int nominal; unsigned int nr_pstates; + bool wof_enabled; } powernv_pstate_info; /* Use following macros for conversions between pstate_id and index */ @@ -203,6 +204,7 @@ static int init_powernv_pstates(void) const __be32 *pstate_ids, *pstate_freqs; u32 len_ids, len_freqs; u32 pstate_min, pstate_max, pstate_nominal; + u32 pstate_turbo, pstate_ultra_turbo; power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); if (!power_mgt) { @@ -225,8 +227,29 @@ static int init_powernv_pstates(void) pr_warn("ibm,pstate-nominal not found\n"); return -ENODEV; } + + if (of_property_read_u32(power_mgt, "ibm,pstate-ultra-turbo", + &pstate_ultra_turbo)) { + powernv_pstate_info.wof_enabled = false; + goto next; + } + + if (of_property_read_u32(power_mgt, "ibm,pstate-turbo", + &pstate_turbo)) { + powernv_pstate_info.wof_enabled = false; + goto next; + } + + if (pstate_turbo == pstate_ultra_turbo) + powernv_pstate_info.wof_enabled = false; + else + powernv_pstate_info.wof_enabled = true; + +next: pr_info("cpufreq pstate min %d nominal %d max %d\n", pstate_min, pstate_nominal, pstate_max); + pr_info("Workload Optimized Frequency is %s in the platform\n", + (powernv_pstate_info.wof_enabled) ? "enabled" : "disabled"); pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids); if (!pstate_ids) { @@ -268,6 +291,13 @@ static int init_powernv_pstates(void) powernv_pstate_info.nominal = i; else if (id == pstate_min) powernv_pstate_info.min = i; + + if (powernv_pstate_info.wof_enabled && id == pstate_turbo) { + int j; + + for (j = i - 1; j >= (int)powernv_pstate_info.max; j--) + powernv_freqs[j].flags = CPUFREQ_BOOST_FREQ; + } } /* End of list marker entry */ @@ -305,9 +335,12 @@ static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy, struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq = __ATTR_RO(cpuinfo_nominal_freq); +#define SCALING_BOOST_FREQS_ATTR_INDEX 2 + static struct freq_attr *powernv_cpu_freq_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, &cpufreq_freq_attr_cpuinfo_nominal_freq, + &cpufreq_freq_attr_scaling_boost_freqs, NULL, }; @@ -1013,11 +1046,22 @@ static int __init powernv_cpufreq_init(void) register_reboot_notifier(&powernv_cpufreq_reboot_nb); opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb); - rc = cpufreq_register_driver(&powernv_cpufreq_driver); - if (!rc) - return 0; + if (powernv_pstate_info.wof_enabled) + powernv_cpufreq_driver.boost_enabled = true; + else + powernv_cpu_freq_attr[SCALING_BOOST_FREQS_ATTR_INDEX] = NULL; - pr_info("Failed to register the cpufreq driver (%d)\n", rc); + rc = cpufreq_register_driver(&powernv_cpufreq_driver); + if (rc) { + pr_info("Failed to register the cpufreq driver (%d)\n", rc); + goto cleanup_notifiers; + } + + if (powernv_pstate_info.wof_enabled) + cpufreq_enable_boost_support(); + + return 0; +cleanup_notifiers: unregister_all_notifiers(); clean_chip_info(); out: diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c index dc112481a408..eeaa92251512 100644 --- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c +++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c @@ -100,9 +100,6 @@ static int pmi_notifier(struct notifier_block *nb, /* Should this really be called for CPUFREQ_ADJUST and CPUFREQ_NOTIFY * policy events?) */ - if (event == CPUFREQ_START) - return 0; - node = cbe_cpu_to_node(policy->cpu); pr_debug("got notified, event=%lu, node=%u\n", event, node); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 86bf3b84ada5..a07ae9e37930 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1723,7 +1723,7 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip) } /** - * _gpiochip_irqchip_add() - adds an irqchip to a gpiochip + * gpiochip_irqchip_add_key() - adds an irqchip to a gpiochip * @gpiochip: the gpiochip to add the irqchip to * @irqchip: the irqchip to add to the gpiochip * @first_irq: if not dynamically assigned, the base (first) IRQ to @@ -1749,13 +1749,13 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip) * the pins on the gpiochip can generate a unique IRQ. Everything else * need to be open coded. */ -int _gpiochip_irqchip_add(struct gpio_chip *gpiochip, - struct irq_chip *irqchip, - unsigned int first_irq, - irq_flow_handler_t handler, - unsigned int type, - bool nested, - struct lock_class_key *lock_key) +int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type, + bool nested, + struct lock_class_key *lock_key) { struct device_node *of_node; bool irq_base_set = false; @@ -1840,7 +1840,7 @@ int _gpiochip_irqchip_add(struct gpio_chip *gpiochip, return 0; } -EXPORT_SYMBOL_GPL(_gpiochip_irqchip_add); +EXPORT_SYMBOL_GPL(gpiochip_irqchip_add_key); #else /* CONFIG_GPIOLIB_IRQCHIP */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 29d6d84d1c28..41e41f90265d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -83,6 +83,13 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, } break; } + + if (!(*out_ring && (*out_ring)->adev)) { + DRM_ERROR("Ring %d is not initialized on IP %d\n", + ring, ip_type); + return -EINVAL; + } + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index 9999dc71b998..ccb5e02e7b20 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -2512,6 +2512,8 @@ static int dce_v10_0_cursor_move_locked(struct drm_crtc *crtc, WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y); WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin); + WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, + ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1)); return 0; } @@ -2537,7 +2539,6 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc, int32_t hot_y) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; struct drm_gem_object *obj; struct amdgpu_bo *aobj; int ret; @@ -2578,7 +2579,9 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc, dce_v10_0_lock_cursor(crtc, true); - if (hot_x != amdgpu_crtc->cursor_hot_x || + if (width != amdgpu_crtc->cursor_width || + height != amdgpu_crtc->cursor_height || + hot_x != amdgpu_crtc->cursor_hot_x || hot_y != amdgpu_crtc->cursor_hot_y) { int x, y; @@ -2587,16 +2590,10 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc, dce_v10_0_cursor_move_locked(crtc, x, y); - amdgpu_crtc->cursor_hot_x = hot_x; - amdgpu_crtc->cursor_hot_y = hot_y; - } - - if (width != amdgpu_crtc->cursor_width || - height != amdgpu_crtc->cursor_height) { - WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, - (width - 1) << 16 | (height - 1)); amdgpu_crtc->cursor_width = width; amdgpu_crtc->cursor_height = height; + amdgpu_crtc->cursor_hot_x = hot_x; + amdgpu_crtc->cursor_hot_y = hot_y; } dce_v10_0_show_cursor(crtc); @@ -2620,7 +2617,6 @@ unpin: static void dce_v10_0_cursor_reset(struct drm_crtc *crtc) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; if (amdgpu_crtc->cursor_bo) { dce_v10_0_lock_cursor(crtc, true); @@ -2628,10 +2624,6 @@ static void dce_v10_0_cursor_reset(struct drm_crtc *crtc) dce_v10_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x, amdgpu_crtc->cursor_y); - WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, - (amdgpu_crtc->cursor_width - 1) << 16 | - (amdgpu_crtc->cursor_height - 1)); - dce_v10_0_show_cursor(crtc); dce_v10_0_lock_cursor(crtc, false); diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 2006abbbfb62..a7af5b33a5e3 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -2532,6 +2532,8 @@ static int dce_v11_0_cursor_move_locked(struct drm_crtc *crtc, WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y); WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin); + WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, + ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1)); return 0; } @@ -2557,7 +2559,6 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc, int32_t hot_y) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; struct drm_gem_object *obj; struct amdgpu_bo *aobj; int ret; @@ -2598,7 +2599,9 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc, dce_v11_0_lock_cursor(crtc, true); - if (hot_x != amdgpu_crtc->cursor_hot_x || + if (width != amdgpu_crtc->cursor_width || + height != amdgpu_crtc->cursor_height || + hot_x != amdgpu_crtc->cursor_hot_x || hot_y != amdgpu_crtc->cursor_hot_y) { int x, y; @@ -2607,16 +2610,10 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc, dce_v11_0_cursor_move_locked(crtc, x, y); - amdgpu_crtc->cursor_hot_x = hot_x; - amdgpu_crtc->cursor_hot_y = hot_y; - } - - if (width != amdgpu_crtc->cursor_width || - height != amdgpu_crtc->cursor_height) { - WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, - (width - 1) << 16 | (height - 1)); amdgpu_crtc->cursor_width = width; amdgpu_crtc->cursor_height = height; + amdgpu_crtc->cursor_hot_x = hot_x; + amdgpu_crtc->cursor_hot_y = hot_y; } dce_v11_0_show_cursor(crtc); @@ -2640,7 +2637,6 @@ unpin: static void dce_v11_0_cursor_reset(struct drm_crtc *crtc) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; if (amdgpu_crtc->cursor_bo) { dce_v11_0_lock_cursor(crtc, true); @@ -2648,10 +2644,6 @@ static void dce_v11_0_cursor_reset(struct drm_crtc *crtc) dce_v11_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x, amdgpu_crtc->cursor_y); - WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, - (amdgpu_crtc->cursor_width - 1) << 16 | - (amdgpu_crtc->cursor_height - 1)); - dce_v11_0_show_cursor(crtc); dce_v11_0_lock_cursor(crtc, false); diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index b4e4ec630e8c..39df6a50637f 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -1859,6 +1859,8 @@ static int dce_v6_0_cursor_move_locked(struct drm_crtc *crtc, struct amdgpu_device *adev = crtc->dev->dev_private; int xorigin = 0, yorigin = 0; + int w = amdgpu_crtc->cursor_width; + amdgpu_crtc->cursor_x = x; amdgpu_crtc->cursor_y = y; @@ -1878,6 +1880,8 @@ static int dce_v6_0_cursor_move_locked(struct drm_crtc *crtc, WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y); WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin); + WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, + ((w - 1) << 16) | (amdgpu_crtc->cursor_height - 1)); return 0; } @@ -1903,7 +1907,6 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc, int32_t hot_y) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; struct drm_gem_object *obj; struct amdgpu_bo *aobj; int ret; @@ -1944,7 +1947,9 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc, dce_v6_0_lock_cursor(crtc, true); - if (hot_x != amdgpu_crtc->cursor_hot_x || + if (width != amdgpu_crtc->cursor_width || + height != amdgpu_crtc->cursor_height || + hot_x != amdgpu_crtc->cursor_hot_x || hot_y != amdgpu_crtc->cursor_hot_y) { int x, y; @@ -1953,16 +1958,10 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc, dce_v6_0_cursor_move_locked(crtc, x, y); - amdgpu_crtc->cursor_hot_x = hot_x; - amdgpu_crtc->cursor_hot_y = hot_y; - } - - if (width != amdgpu_crtc->cursor_width || - height != amdgpu_crtc->cursor_height) { - WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, - (width - 1) << 16 | (height - 1)); amdgpu_crtc->cursor_width = width; amdgpu_crtc->cursor_height = height; + amdgpu_crtc->cursor_hot_x = hot_x; + amdgpu_crtc->cursor_hot_y = hot_y; } dce_v6_0_show_cursor(crtc); @@ -1986,7 +1985,6 @@ unpin: static void dce_v6_0_cursor_reset(struct drm_crtc *crtc) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; if (amdgpu_crtc->cursor_bo) { dce_v6_0_lock_cursor(crtc, true); @@ -1994,10 +1992,6 @@ static void dce_v6_0_cursor_reset(struct drm_crtc *crtc) dce_v6_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x, amdgpu_crtc->cursor_y); - WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, - (amdgpu_crtc->cursor_width - 1) << 16 | - (amdgpu_crtc->cursor_height - 1)); - dce_v6_0_show_cursor(crtc); dce_v6_0_lock_cursor(crtc, false); } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 584abe834a3c..28102bb1704d 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -2363,6 +2363,8 @@ static int dce_v8_0_cursor_move_locked(struct drm_crtc *crtc, WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y); WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin); + WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, + ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1)); return 0; } @@ -2388,7 +2390,6 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc, int32_t hot_y) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; struct drm_gem_object *obj; struct amdgpu_bo *aobj; int ret; @@ -2429,7 +2430,9 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc, dce_v8_0_lock_cursor(crtc, true); - if (hot_x != amdgpu_crtc->cursor_hot_x || + if (width != amdgpu_crtc->cursor_width || + height != amdgpu_crtc->cursor_height || + hot_x != amdgpu_crtc->cursor_hot_x || hot_y != amdgpu_crtc->cursor_hot_y) { int x, y; @@ -2438,16 +2441,10 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc, dce_v8_0_cursor_move_locked(crtc, x, y); - amdgpu_crtc->cursor_hot_x = hot_x; - amdgpu_crtc->cursor_hot_y = hot_y; - } - - if (width != amdgpu_crtc->cursor_width || - height != amdgpu_crtc->cursor_height) { - WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, - (width - 1) << 16 | (height - 1)); amdgpu_crtc->cursor_width = width; amdgpu_crtc->cursor_height = height; + amdgpu_crtc->cursor_hot_x = hot_x; + amdgpu_crtc->cursor_hot_y = hot_y; } dce_v8_0_show_cursor(crtc); @@ -2471,7 +2468,6 @@ unpin: static void dce_v8_0_cursor_reset(struct drm_crtc *crtc) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; if (amdgpu_crtc->cursor_bo) { dce_v8_0_lock_cursor(crtc, true); @@ -2479,10 +2475,6 @@ static void dce_v8_0_cursor_reset(struct drm_crtc *crtc) dce_v8_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x, amdgpu_crtc->cursor_y); - WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, - (amdgpu_crtc->cursor_width - 1) << 16 | - (amdgpu_crtc->cursor_height - 1)); - dce_v8_0_show_cursor(crtc); dce_v8_0_lock_cursor(crtc, false); diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index 762f8e82ceb7..e9a176891e13 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -627,11 +627,8 @@ static const struct drm_encoder_helper_funcs dce_virtual_encoder_helper_funcs = static void dce_virtual_encoder_destroy(struct drm_encoder *encoder) { - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - - kfree(amdgpu_encoder->enc_priv); drm_encoder_cleanup(encoder); - kfree(amdgpu_encoder); + kfree(encoder); } static const struct drm_encoder_funcs dce_virtual_encoder_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index 45a573e63d4a..e2b0b1646f99 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -44,6 +44,7 @@ MODULE_FIRMWARE("radeon/tahiti_mc.bin"); MODULE_FIRMWARE("radeon/pitcairn_mc.bin"); MODULE_FIRMWARE("radeon/verde_mc.bin"); MODULE_FIRMWARE("radeon/oland_mc.bin"); +MODULE_FIRMWARE("radeon/si58_mc.bin"); #define MC_SEQ_MISC0__MT__MASK 0xf0000000 #define MC_SEQ_MISC0__MT__GDDR1 0x10000000 @@ -113,6 +114,7 @@ static int gmc_v6_0_init_microcode(struct amdgpu_device *adev) const char *chip_name; char fw_name[30]; int err; + bool is_58_fw = false; DRM_DEBUG("\n"); @@ -135,7 +137,14 @@ static int gmc_v6_0_init_microcode(struct amdgpu_device *adev) default: BUG(); } - snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + /* this memory configuration requires special firmware */ + if (((RREG32(mmMC_SEQ_MISC0) & 0xff000000) >> 24) == 0x58) + is_58_fw = true; + + if (is_58_fw) + snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin"); + else + snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); err = request_firmware(&adev->mc.fw, fw_name, adev->dev); if (err) goto out; @@ -463,19 +472,11 @@ static int gmc_v6_0_gart_enable(struct amdgpu_device *adev) WREG32(mmVM_CONTEXT1_CNTL, VM_CONTEXT1_CNTL__ENABLE_CONTEXT_MASK | (1UL << VM_CONTEXT1_CNTL__PAGE_TABLE_DEPTH__SHIFT) | - ((amdgpu_vm_block_size - 9) << VM_CONTEXT1_CNTL__PAGE_TABLE_BLOCK_SIZE__SHIFT) | - VM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK | - VM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK | - VM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK | - VM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK | - VM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK | - VM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_DEFAULT_MASK | - VM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK | - VM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_DEFAULT_MASK | - VM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK | - VM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_DEFAULT_MASK | - VM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK | - VM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK); + ((amdgpu_vm_block_size - 9) << VM_CONTEXT1_CNTL__PAGE_TABLE_BLOCK_SIZE__SHIFT)); + if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) + gmc_v6_0_set_fault_enable_default(adev, false); + else + gmc_v6_0_set_fault_enable_default(adev, true); gmc_v6_0_gart_flush_gpu_tlb(adev, 0); dev_info(adev->dev, "PCIE GART of %uM enabled (table at 0x%016llX).\n", @@ -754,7 +755,10 @@ static int gmc_v6_0_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); + if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS) + return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); + else + return 0; } static int gmc_v6_0_sw_init(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index 10bedfac27b8..6e150db8f380 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -64,6 +64,7 @@ MODULE_FIRMWARE("radeon/oland_smc.bin"); MODULE_FIRMWARE("radeon/oland_k_smc.bin"); MODULE_FIRMWARE("radeon/hainan_smc.bin"); MODULE_FIRMWARE("radeon/hainan_k_smc.bin"); +MODULE_FIRMWARE("radeon/banks_k_2_smc.bin"); union power_info { struct _ATOM_POWERPLAY_INFO info; @@ -3487,17 +3488,6 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, (adev->pdev->device == 0x6817) || (adev->pdev->device == 0x6806)) max_mclk = 120000; - } else if (adev->asic_type == CHIP_OLAND) { - if ((adev->pdev->revision == 0xC7) || - (adev->pdev->revision == 0x80) || - (adev->pdev->revision == 0x81) || - (adev->pdev->revision == 0x83) || - (adev->pdev->revision == 0x87) || - (adev->pdev->device == 0x6604) || - (adev->pdev->device == 0x6605)) { - max_sclk = 75000; - max_mclk = 80000; - } } else if (adev->asic_type == CHIP_HAINAN) { if ((adev->pdev->revision == 0x81) || (adev->pdev->revision == 0x83) || @@ -3506,7 +3496,6 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, (adev->pdev->device == 0x6665) || (adev->pdev->device == 0x6667)) { max_sclk = 75000; - max_mclk = 80000; } } /* Apply dpm quirks */ @@ -7713,10 +7702,11 @@ static int si_dpm_init_microcode(struct amdgpu_device *adev) ((adev->pdev->device == 0x6660) || (adev->pdev->device == 0x6663) || (adev->pdev->device == 0x6665) || - (adev->pdev->device == 0x6667))) || - ((adev->pdev->revision == 0xc3) && - (adev->pdev->device == 0x6665))) + (adev->pdev->device == 0x6667)))) chip_name = "hainan_k"; + else if ((adev->pdev->revision == 0xc3) && + (adev->pdev->device == 0x6665)) + chip_name = "banks_k_2"; else chip_name = "hainan"; break; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c index 96444e4d862a..7fb9137dd89b 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c @@ -40,13 +40,14 @@ #include "smu/smu_7_0_1_sh_mask.h" static void uvd_v4_2_mc_resume(struct amdgpu_device *adev); -static void uvd_v4_2_init_cg(struct amdgpu_device *adev); static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev); static void uvd_v4_2_set_irq_funcs(struct amdgpu_device *adev); static int uvd_v4_2_start(struct amdgpu_device *adev); static void uvd_v4_2_stop(struct amdgpu_device *adev); static int uvd_v4_2_set_clockgating_state(void *handle, enum amd_clockgating_state state); +static void uvd_v4_2_set_dcm(struct amdgpu_device *adev, + bool sw_mode); /** * uvd_v4_2_ring_get_rptr - get read pointer * @@ -140,7 +141,8 @@ static int uvd_v4_2_sw_fini(void *handle) return r; } - +static void uvd_v4_2_enable_mgcg(struct amdgpu_device *adev, + bool enable); /** * uvd_v4_2_hw_init - start and test UVD block * @@ -155,8 +157,7 @@ static int uvd_v4_2_hw_init(void *handle) uint32_t tmp; int r; - uvd_v4_2_init_cg(adev); - uvd_v4_2_set_clockgating_state(adev, AMD_CG_STATE_GATE); + uvd_v4_2_enable_mgcg(adev, true); amdgpu_asic_set_uvd_clocks(adev, 10000, 10000); r = uvd_v4_2_start(adev); if (r) @@ -266,11 +267,13 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) struct amdgpu_ring *ring = &adev->uvd.ring; uint32_t rb_bufsz; int i, j, r; - /* disable byte swapping */ u32 lmi_swap_cntl = 0; u32 mp_swap_cntl = 0; + WREG32(mmUVD_CGC_GATE, 0); + uvd_v4_2_set_dcm(adev, true); + uvd_v4_2_mc_resume(adev); /* disable interupt */ @@ -406,6 +409,8 @@ static void uvd_v4_2_stop(struct amdgpu_device *adev) /* Unstall UMC and register bus */ WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8)); + + uvd_v4_2_set_dcm(adev, false); } /** @@ -619,19 +624,6 @@ static void uvd_v4_2_set_dcm(struct amdgpu_device *adev, WREG32_UVD_CTX(ixUVD_CGC_CTRL2, tmp2); } -static void uvd_v4_2_init_cg(struct amdgpu_device *adev) -{ - bool hw_mode = true; - - if (hw_mode) { - uvd_v4_2_set_dcm(adev, false); - } else { - u32 tmp = RREG32(mmUVD_CGC_CTRL); - tmp &= ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK; - WREG32(mmUVD_CGC_CTRL, tmp); - } -} - static bool uvd_v4_2_is_idle(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -685,17 +677,6 @@ static int uvd_v4_2_process_interrupt(struct amdgpu_device *adev, static int uvd_v4_2_set_clockgating_state(void *handle, enum amd_clockgating_state state) { - bool gate = false; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG)) - return 0; - - if (state == AMD_CG_STATE_GATE) - gate = true; - - uvd_v4_2_enable_mgcg(adev, gate); - return 0; } @@ -711,9 +692,6 @@ static int uvd_v4_2_set_powergating_state(void *handle, */ struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD)) - return 0; - if (state == AMD_PG_STATE_GATE) { uvd_v4_2_stop(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c index 5fb0b7f5c065..37ca685e5a9a 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c @@ -43,9 +43,13 @@ #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT 0x04 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK 0x10 +#define GRBM_GFX_INDEX__VCE_ALL_PIPE 0x07 + #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0 0x8616 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1 0x8617 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2 0x8618 +#define mmGRBM_GFX_INDEX_DEFAULT 0xE0000000 + #define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK 0x02 #define VCE_V3_0_FW_SIZE (384 * 1024) @@ -54,6 +58,9 @@ #define FW_52_8_3 ((52 << 24) | (8 << 16) | (3 << 8)) +#define GET_VCE_INSTANCE(i) ((i) << GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT \ + | GRBM_GFX_INDEX__VCE_ALL_PIPE) + static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx); static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev); static void vce_v3_0_set_irq_funcs(struct amdgpu_device *adev); @@ -175,7 +182,7 @@ static void vce_v3_0_set_vce_sw_clock_gating(struct amdgpu_device *adev, WREG32(mmVCE_UENC_CLOCK_GATING_2, data); data = RREG32(mmVCE_UENC_REG_CLOCK_GATING); - data &= ~0xffc00000; + data &= ~0x3ff; WREG32(mmVCE_UENC_REG_CLOCK_GATING, data); data = RREG32(mmVCE_UENC_DMA_DCLK_CTRL); @@ -249,7 +256,7 @@ static int vce_v3_0_start(struct amdgpu_device *adev) if (adev->vce.harvest_config & (1 << idx)) continue; - WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, idx); + WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx)); vce_v3_0_mc_resume(adev, idx); WREG32_FIELD(VCE_STATUS, JOB_BUSY, 1); @@ -273,7 +280,7 @@ static int vce_v3_0_start(struct amdgpu_device *adev) } } - WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0); + WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT); mutex_unlock(&adev->grbm_idx_mutex); return 0; @@ -288,7 +295,7 @@ static int vce_v3_0_stop(struct amdgpu_device *adev) if (adev->vce.harvest_config & (1 << idx)) continue; - WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, idx); + WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx)); if (adev->asic_type >= CHIP_STONEY) WREG32_P(mmVCE_VCPU_CNTL, 0, ~0x200001); @@ -306,7 +313,7 @@ static int vce_v3_0_stop(struct amdgpu_device *adev) vce_v3_0_set_vce_sw_clock_gating(adev, false); } - WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0); + WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT); mutex_unlock(&adev->grbm_idx_mutex); return 0; @@ -586,17 +593,17 @@ static bool vce_v3_0_check_soft_reset(void *handle) * VCE team suggest use bit 3--bit 6 for busy status check */ mutex_lock(&adev->grbm_idx_mutex); - WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0); + WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0)); if (RREG32(mmVCE_STATUS) & AMDGPU_VCE_STATUS_BUSY_MASK) { srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE0, 1); srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1); } - WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0x10); + WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1)); if (RREG32(mmVCE_STATUS) & AMDGPU_VCE_STATUS_BUSY_MASK) { srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE0, 1); srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1); } - WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0); + WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0)); mutex_unlock(&adev->grbm_idx_mutex); if (srbm_soft_reset) { @@ -734,7 +741,7 @@ static int vce_v3_0_set_clockgating_state(void *handle, if (adev->vce.harvest_config & (1 << i)) continue; - WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, i); + WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(i)); if (enable) { /* initialize VCE_CLOCK_GATING_A: Clock ON/OFF delay */ @@ -753,7 +760,7 @@ static int vce_v3_0_set_clockgating_state(void *handle, vce_v3_0_set_vce_sw_clock_gating(adev, enable); } - WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0); + WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT); mutex_unlock(&adev->grbm_idx_mutex); return 0; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c index b0c63c5f54c9..6bb79c94cb9f 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c @@ -200,7 +200,7 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate) cgs_set_clockgating_state( hwmgr->device, AMD_IP_BLOCK_TYPE_VCE, - AMD_CG_STATE_UNGATE); + AMD_CG_STATE_GATE); cgs_set_powergating_state( hwmgr->device, AMD_IP_BLOCK_TYPE_VCE, @@ -218,7 +218,7 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate) cgs_set_clockgating_state( hwmgr->device, AMD_IP_BLOCK_TYPE_VCE, - AMD_PG_STATE_GATE); + AMD_PG_STATE_UNGATE); cz_dpm_update_vce_dpm(hwmgr); cz_enable_disable_vce_dpm(hwmgr, true); return 0; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c index 4b14f259a147..0fb4e8c8f5e1 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c @@ -1402,14 +1402,22 @@ int cz_dpm_update_vce_dpm(struct pp_hwmgr *hwmgr) cz_hwmgr->vce_dpm.hard_min_clk, PPSMC_MSG_SetEclkHardMin)); } else { - /*EPR# 419220 -HW limitation to to */ - cz_hwmgr->vce_dpm.hard_min_clk = hwmgr->vce_arbiter.ecclk; - smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, - PPSMC_MSG_SetEclkHardMin, - cz_get_eclk_level(hwmgr, - cz_hwmgr->vce_dpm.hard_min_clk, - PPSMC_MSG_SetEclkHardMin)); - + /*Program HardMin based on the vce_arbiter.ecclk */ + if (hwmgr->vce_arbiter.ecclk == 0) { + smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, + PPSMC_MSG_SetEclkHardMin, 0); + /* disable ECLK DPM 0. Otherwise VCE could hang if + * switching SCLK from DPM 0 to 6/7 */ + smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, + PPSMC_MSG_SetEclkSoftMin, 1); + } else { + cz_hwmgr->vce_dpm.hard_min_clk = hwmgr->vce_arbiter.ecclk; + smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, + PPSMC_MSG_SetEclkHardMin, + cz_get_eclk_level(hwmgr, + cz_hwmgr->vce_dpm.hard_min_clk, + PPSMC_MSG_SetEclkHardMin)); + } } return 0; } diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 908011d2c8f5..7abda94fc2cf 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -113,6 +113,7 @@ struct ast_private { struct ttm_bo_kmap_obj cache_kmap; int next_cursor; bool support_wide_screen; + bool DisableP2A; enum ast_tx_chip tx_chip_type; u8 dp501_maxclk; diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index f75c6421db62..533e762d036d 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -124,6 +124,12 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) } else *need_post = false; + /* Check P2A Access */ + ast->DisableP2A = true; + data = ast_read32(ast, 0xf004); + if (data != 0xFFFFFFFF) + ast->DisableP2A = false; + /* Check if we support wide screen */ switch (ast->chip) { case AST1180: @@ -140,15 +146,17 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) ast->support_wide_screen = true; else { ast->support_wide_screen = false; - /* Read SCU7c (silicon revision register) */ - ast_write32(ast, 0xf004, 0x1e6e0000); - ast_write32(ast, 0xf000, 0x1); - data = ast_read32(ast, 0x1207c); - data &= 0x300; - if (ast->chip == AST2300 && data == 0x0) /* ast1300 */ - ast->support_wide_screen = true; - if (ast->chip == AST2400 && data == 0x100) /* ast1400 */ - ast->support_wide_screen = true; + if (ast->DisableP2A == false) { + /* Read SCU7c (silicon revision register) */ + ast_write32(ast, 0xf004, 0x1e6e0000); + ast_write32(ast, 0xf000, 0x1); + data = ast_read32(ast, 0x1207c); + data &= 0x300; + if (ast->chip == AST2300 && data == 0x0) /* ast1300 */ + ast->support_wide_screen = true; + if (ast->chip == AST2400 && data == 0x100) /* ast1400 */ + ast->support_wide_screen = true; + } } break; } @@ -216,80 +224,81 @@ static int ast_get_dram_info(struct drm_device *dev) uint32_t data, data2; uint32_t denum, num, div, ref_pll; - ast_write32(ast, 0xf004, 0x1e6e0000); - ast_write32(ast, 0xf000, 0x1); - - - ast_write32(ast, 0x10000, 0xfc600309); - - do { - if (pci_channel_offline(dev->pdev)) - return -EIO; - } while (ast_read32(ast, 0x10000) != 0x01); - data = ast_read32(ast, 0x10004); - - if (data & 0x40) + if (ast->DisableP2A) + { ast->dram_bus_width = 16; + ast->dram_type = AST_DRAM_1Gx16; + ast->mclk = 396; + } else - ast->dram_bus_width = 32; + { + ast_write32(ast, 0xf004, 0x1e6e0000); + ast_write32(ast, 0xf000, 0x1); + data = ast_read32(ast, 0x10004); - if (ast->chip == AST2300 || ast->chip == AST2400) { - switch (data & 0x03) { - case 0: - ast->dram_type = AST_DRAM_512Mx16; - break; - default: - case 1: - ast->dram_type = AST_DRAM_1Gx16; + if (data & 0x40) + ast->dram_bus_width = 16; + else + ast->dram_bus_width = 32; + + if (ast->chip == AST2300 || ast->chip == AST2400) { + switch (data & 0x03) { + case 0: + ast->dram_type = AST_DRAM_512Mx16; + break; + default: + case 1: + ast->dram_type = AST_DRAM_1Gx16; + break; + case 2: + ast->dram_type = AST_DRAM_2Gx16; + break; + case 3: + ast->dram_type = AST_DRAM_4Gx16; + break; + } + } else { + switch (data & 0x0c) { + case 0: + case 4: + ast->dram_type = AST_DRAM_512Mx16; + break; + case 8: + if (data & 0x40) + ast->dram_type = AST_DRAM_1Gx16; + else + ast->dram_type = AST_DRAM_512Mx32; + break; + case 0xc: + ast->dram_type = AST_DRAM_1Gx32; + break; + } + } + + data = ast_read32(ast, 0x10120); + data2 = ast_read32(ast, 0x10170); + if (data2 & 0x2000) + ref_pll = 14318; + else + ref_pll = 12000; + + denum = data & 0x1f; + num = (data & 0x3fe0) >> 5; + data = (data & 0xc000) >> 14; + switch (data) { + case 3: + div = 0x4; break; case 2: - ast->dram_type = AST_DRAM_2Gx16; + case 1: + div = 0x2; break; - case 3: - ast->dram_type = AST_DRAM_4Gx16; - break; - } - } else { - switch (data & 0x0c) { - case 0: - case 4: - ast->dram_type = AST_DRAM_512Mx16; - break; - case 8: - if (data & 0x40) - ast->dram_type = AST_DRAM_1Gx16; - else - ast->dram_type = AST_DRAM_512Mx32; - break; - case 0xc: - ast->dram_type = AST_DRAM_1Gx32; + default: + div = 0x1; break; } + ast->mclk = ref_pll * (num + 2) / (denum + 2) * (div * 1000); } - - data = ast_read32(ast, 0x10120); - data2 = ast_read32(ast, 0x10170); - if (data2 & 0x2000) - ref_pll = 14318; - else - ref_pll = 12000; - - denum = data & 0x1f; - num = (data & 0x3fe0) >> 5; - data = (data & 0xc000) >> 14; - switch (data) { - case 3: - div = 0x4; - break; - case 2: - case 1: - div = 0x2; - break; - default: - div = 0x1; - break; - } - ast->mclk = ref_pll * (num + 2) / (denum + 2) * (div * 1000); return 0; } diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index 810c51d92b99..5331ee1df086 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -379,12 +379,20 @@ void ast_post_gpu(struct drm_device *dev) ast_open_key(ast); ast_set_def_ext_reg(dev); - if (ast->chip == AST2300 || ast->chip == AST2400) - ast_init_dram_2300(dev); - else - ast_init_dram_reg(dev); + if (ast->DisableP2A == false) + { + if (ast->chip == AST2300 || ast->chip == AST2400) + ast_init_dram_2300(dev); + else + ast_init_dram_reg(dev); - ast_init_3rdtx(dev); + ast_init_3rdtx(dev); + } + else + { + if (ast->tx_chip_type != AST_TX_NONE) + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x80); /* Enable DVO */ + } } /* AST 2300 DRAM settings */ diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index eb9bf8786c24..18eefdcbf1ba 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1382,6 +1382,7 @@ int analogix_dp_bind(struct device *dev, struct drm_device *drm_dev, pm_runtime_enable(dev); + pm_runtime_get_sync(dev); phy_power_on(dp->phy); analogix_dp_init_dp(dp); @@ -1414,9 +1415,15 @@ int analogix_dp_bind(struct device *dev, struct drm_device *drm_dev, goto err_disable_pm_runtime; } + phy_power_off(dp->phy); + pm_runtime_put(dev); + return 0; err_disable_pm_runtime: + + phy_power_off(dp->phy); + pm_runtime_put(dev); pm_runtime_disable(dev); return ret; diff --git a/drivers/gpu/drm/cirrus/Kconfig b/drivers/gpu/drm/cirrus/Kconfig index 04b3c161dfae..7f4cc6e172ab 100644 --- a/drivers/gpu/drm/cirrus/Kconfig +++ b/drivers/gpu/drm/cirrus/Kconfig @@ -7,3 +7,12 @@ config DRM_CIRRUS_QEMU This is a KMS driver for emulated cirrus device in qemu. It is *NOT* intended for real cirrus devices. This requires the modesetting userspace X.org driver. + + Cirrus is obsolete, the hardware was designed in the 90ies + and can't keep up with todays needs. More background: + https://www.kraxel.org/blog/2014/10/qemu-using-cirrus-considered-harmful/ + + Better alternatives are: + - stdvga (DRM_BOCHS, qemu -vga std, default in qemu 2.2+) + - qxl (DRM_QXL, qemu -vga qxl, works best with spice) + - virtio (DRM_VIRTIO_GPU), qemu -vga virtio) diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 60697482b94c..50f5cf7b69d1 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -291,15 +291,15 @@ drm_atomic_get_crtc_state(struct drm_atomic_state *state, EXPORT_SYMBOL(drm_atomic_get_crtc_state); static void set_out_fence_for_crtc(struct drm_atomic_state *state, - struct drm_crtc *crtc, s64 __user *fence_ptr) + struct drm_crtc *crtc, s32 __user *fence_ptr) { state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = fence_ptr; } -static s64 __user *get_out_fence_for_crtc(struct drm_atomic_state *state, +static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state, struct drm_crtc *crtc) { - s64 __user *fence_ptr; + s32 __user *fence_ptr; fence_ptr = state->crtcs[drm_crtc_index(crtc)].out_fence_ptr; state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = NULL; @@ -512,7 +512,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, state->color_mgmt_changed |= replaced; return ret; } else if (property == config->prop_out_fence_ptr) { - s64 __user *fence_ptr = u64_to_user_ptr(val); + s32 __user *fence_ptr = u64_to_user_ptr(val); if (!fence_ptr) return 0; @@ -1915,7 +1915,7 @@ EXPORT_SYMBOL(drm_atomic_clean_old_fb); */ struct drm_out_fence_state { - s64 __user *out_fence_ptr; + s32 __user *out_fence_ptr; struct sync_file *sync_file; int fd; }; @@ -1952,7 +1952,7 @@ static int prepare_crtc_signaling(struct drm_device *dev, return 0; for_each_crtc_in_state(state, crtc, crtc_state, i) { - u64 __user *fence_ptr; + s32 __user *fence_ptr; fence_ptr = get_out_fence_for_crtc(crtc_state->state, crtc); diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index ac6a35212501..e6b19bc9021a 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1460,6 +1460,13 @@ drm_mode_create_from_cmdline_mode(struct drm_device *dev, return NULL; mode->type |= DRM_MODE_TYPE_USERDEF; + /* fix up 1368x768: GFT/CVT can't express 1366 width due to alignment */ + if (cmd->xres == 1366 && mode->hdisplay == 1368) { + mode->hdisplay = 1366; + mode->hsync_start--; + mode->hsync_end--; + drm_mode_set_name(mode); + } drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V); return mode; } diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index ac953f037be7..cf8f0128c161 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -143,8 +143,18 @@ void drm_kms_helper_poll_enable_locked(struct drm_device *dev) } if (dev->mode_config.delayed_event) { + /* + * FIXME: + * + * Use short (1s) delay to handle the initial delayed event. + * This delay should not be needed, but Optimus/nouveau will + * fail in a mysterious way if the delayed event is handled as + * soon as possible like it is done in + * drm_helper_probe_single_connector_modes() in case the poll + * was enabled before. + */ poll = true; - delay = 0; + delay = HZ; } if (poll) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c index 169ac96e8f08..fe0e85b41310 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c @@ -116,9 +116,14 @@ static int etnaviv_iommu_find_iova(struct etnaviv_iommu *mmu, struct list_head list; bool found; + /* + * XXX: The DRM_MM_SEARCH_BELOW is really a hack to trick + * drm_mm into giving out a low IOVA after address space + * rollover. This needs a proper fix. + */ ret = drm_mm_insert_node_in_range(&mmu->mm, node, size, 0, mmu->last_iova, ~0UL, - DRM_MM_SEARCH_DEFAULT); + mmu->last_iova ? DRM_MM_SEARCH_DEFAULT : DRM_MM_SEARCH_BELOW); if (ret != -ENOSPC) break; diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 6ca1f3117fe8..75eeb831ed6a 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -46,7 +46,8 @@ enum decon_flag_bits { BIT_CLKS_ENABLED, BIT_IRQS_ENABLED, BIT_WIN_UPDATED, - BIT_SUSPENDED + BIT_SUSPENDED, + BIT_REQUEST_UPDATE }; struct decon_context { @@ -141,12 +142,6 @@ static void decon_commit(struct exynos_drm_crtc *crtc) m->crtc_vsync_end = m->crtc_vsync_start + 1; } - decon_set_bits(ctx, DECON_VIDCON0, VIDCON0_ENVID, 0); - - /* enable clock gate */ - val = CMU_CLKGAGE_MODE_SFR_F | CMU_CLKGAGE_MODE_MEM_F; - writel(val, ctx->addr + DECON_CMU); - if (ctx->out_type & (IFTYPE_I80 | I80_HW_TRG)) decon_setup_trigger(ctx); @@ -315,6 +310,7 @@ static void decon_update_plane(struct exynos_drm_crtc *crtc, /* window enable */ decon_set_bits(ctx, DECON_WINCONx(win), WINCONx_ENWIN_F, ~0); + set_bit(BIT_REQUEST_UPDATE, &ctx->flags); } static void decon_disable_plane(struct exynos_drm_crtc *crtc, @@ -327,6 +323,7 @@ static void decon_disable_plane(struct exynos_drm_crtc *crtc, return; decon_set_bits(ctx, DECON_WINCONx(win), WINCONx_ENWIN_F, 0); + set_bit(BIT_REQUEST_UPDATE, &ctx->flags); } static void decon_atomic_flush(struct exynos_drm_crtc *crtc) @@ -340,8 +337,8 @@ static void decon_atomic_flush(struct exynos_drm_crtc *crtc) for (i = ctx->first_win; i < WINDOWS_NR; i++) decon_shadow_protect_win(ctx, i, false); - /* standalone update */ - decon_set_bits(ctx, DECON_UPDATE, STANDALONE_UPDATE_F, ~0); + if (test_and_clear_bit(BIT_REQUEST_UPDATE, &ctx->flags)) + decon_set_bits(ctx, DECON_UPDATE, STANDALONE_UPDATE_F, ~0); if (ctx->out_type & IFTYPE_I80) set_bit(BIT_WIN_UPDATED, &ctx->flags); diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c index 0d41ebc4aea6..f7bce8603958 100644 --- a/drivers/gpu/drm/i915/gvt/aperture_gm.c +++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c @@ -37,13 +37,6 @@ #include "i915_drv.h" #include "gvt.h" -#define MB_TO_BYTES(mb) ((mb) << 20ULL) -#define BYTES_TO_MB(b) ((b) >> 20ULL) - -#define HOST_LOW_GM_SIZE MB_TO_BYTES(128) -#define HOST_HIGH_GM_SIZE MB_TO_BYTES(384) -#define HOST_FENCE 4 - static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm) { struct intel_gvt *gvt = vgpu->gvt; @@ -165,6 +158,14 @@ void intel_vgpu_write_fence(struct intel_vgpu *vgpu, POSTING_READ(fence_reg_lo); } +static void _clear_vgpu_fence(struct intel_vgpu *vgpu) +{ + int i; + + for (i = 0; i < vgpu_fence_sz(vgpu); i++) + intel_vgpu_write_fence(vgpu, i, 0); +} + static void free_vgpu_fence(struct intel_vgpu *vgpu) { struct intel_gvt *gvt = vgpu->gvt; @@ -178,9 +179,9 @@ static void free_vgpu_fence(struct intel_vgpu *vgpu) intel_runtime_pm_get(dev_priv); mutex_lock(&dev_priv->drm.struct_mutex); + _clear_vgpu_fence(vgpu); for (i = 0; i < vgpu_fence_sz(vgpu); i++) { reg = vgpu->fence.regs[i]; - intel_vgpu_write_fence(vgpu, i, 0); list_add_tail(®->link, &dev_priv->mm.fence_list); } @@ -208,13 +209,14 @@ static int alloc_vgpu_fence(struct intel_vgpu *vgpu) continue; list_del(pos); vgpu->fence.regs[i] = reg; - intel_vgpu_write_fence(vgpu, i, 0); if (++i == vgpu_fence_sz(vgpu)) break; } if (i != vgpu_fence_sz(vgpu)) goto out_free_fence; + _clear_vgpu_fence(vgpu); + mutex_unlock(&dev_priv->drm.struct_mutex); intel_runtime_pm_put(dev_priv); return 0; @@ -313,6 +315,22 @@ void intel_vgpu_free_resource(struct intel_vgpu *vgpu) free_resource(vgpu); } +/** + * intel_vgpu_reset_resource - reset resource state owned by a vGPU + * @vgpu: a vGPU + * + * This function is used to reset resource state owned by a vGPU. + * + */ +void intel_vgpu_reset_resource(struct intel_vgpu *vgpu) +{ + struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; + + intel_runtime_pm_get(dev_priv); + _clear_vgpu_fence(vgpu); + intel_runtime_pm_put(dev_priv); +} + /** * intel_alloc_vgpu_resource - allocate HW resource for a vGPU * @vgpu: vGPU diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index 711c31c8d8b4..4a6a2ed65732 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -282,3 +282,77 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset, } return 0; } + +/** + * intel_vgpu_init_cfg_space - init vGPU configuration space when create vGPU + * + * @vgpu: a vGPU + * @primary: is the vGPU presented as primary + * + */ +void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, + bool primary) +{ + struct intel_gvt *gvt = vgpu->gvt; + const struct intel_gvt_device_info *info = &gvt->device_info; + u16 *gmch_ctl; + int i; + + memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space, + info->cfg_space_size); + + if (!primary) { + vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] = + INTEL_GVT_PCI_CLASS_VGA_OTHER; + vgpu_cfg_space(vgpu)[PCI_CLASS_PROG] = + INTEL_GVT_PCI_CLASS_VGA_OTHER; + } + + /* Show guest that there isn't any stolen memory.*/ + gmch_ctl = (u16 *)(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_GMCH_CONTROL); + *gmch_ctl &= ~(BDW_GMCH_GMS_MASK << BDW_GMCH_GMS_SHIFT); + + intel_vgpu_write_pci_bar(vgpu, PCI_BASE_ADDRESS_2, + gvt_aperture_pa_base(gvt), true); + + vgpu_cfg_space(vgpu)[PCI_COMMAND] &= ~(PCI_COMMAND_IO + | PCI_COMMAND_MEMORY + | PCI_COMMAND_MASTER); + /* + * Clear the bar upper 32bit and let guest to assign the new value + */ + memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4); + memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4); + memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4); + + for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) { + vgpu->cfg_space.bar[i].size = pci_resource_len( + gvt->dev_priv->drm.pdev, i * 2); + vgpu->cfg_space.bar[i].tracked = false; + } +} + +/** + * intel_vgpu_reset_cfg_space - reset vGPU configuration space + * + * @vgpu: a vGPU + * + */ +void intel_vgpu_reset_cfg_space(struct intel_vgpu *vgpu) +{ + u8 cmd = vgpu_cfg_space(vgpu)[PCI_COMMAND]; + bool primary = vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] != + INTEL_GVT_PCI_CLASS_VGA_OTHER; + + if (cmd & PCI_COMMAND_MEMORY) { + trap_gttmmio(vgpu, false); + map_aperture(vgpu, false); + } + + /** + * Currently we only do such reset when vGPU is not + * owned by any VM, so we simply restore entire cfg + * space to default value. + */ + intel_vgpu_init_cfg_space(vgpu, primary); +} diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index d26a092c70e8..e4563984cb1e 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -481,7 +481,6 @@ struct parser_exec_state { (s->vgpu->gvt->device_info.gmadr_bytes_in_cmd >> 2) static unsigned long bypass_scan_mask = 0; -static bool bypass_batch_buffer_scan = true; /* ring ALL, type = 0 */ static struct sub_op_bits sub_op_mi[] = { @@ -1525,9 +1524,6 @@ static int batch_buffer_needs_scan(struct parser_exec_state *s) { struct intel_gvt *gvt = s->vgpu->gvt; - if (bypass_batch_buffer_scan) - return 0; - if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)) { /* BDW decides privilege based on address space */ if (cmd_val(s, 0) & (1 << 8)) diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c index f32bb6f6495c..34083731669d 100644 --- a/drivers/gpu/drm/i915/gvt/execlist.c +++ b/drivers/gpu/drm/i915/gvt/execlist.c @@ -364,58 +364,30 @@ static void free_workload(struct intel_vgpu_workload *workload) #define get_desc_from_elsp_dwords(ed, i) \ ((struct execlist_ctx_descriptor_format *)&((ed)->data[i * 2])) - -#define BATCH_BUFFER_ADDR_MASK ((1UL << 32) - (1U << 2)) -#define BATCH_BUFFER_ADDR_HIGH_MASK ((1UL << 16) - (1U)) -static int set_gma_to_bb_cmd(struct intel_shadow_bb_entry *entry_obj, - unsigned long add, int gmadr_bytes) -{ - if (WARN_ON(gmadr_bytes != 4 && gmadr_bytes != 8)) - return -1; - - *((u32 *)(entry_obj->bb_start_cmd_va + (1 << 2))) = add & - BATCH_BUFFER_ADDR_MASK; - if (gmadr_bytes == 8) { - *((u32 *)(entry_obj->bb_start_cmd_va + (2 << 2))) = - add & BATCH_BUFFER_ADDR_HIGH_MASK; - } - - return 0; -} - static void prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload) { - int gmadr_bytes = workload->vgpu->gvt->device_info.gmadr_bytes_in_cmd; + const int gmadr_bytes = workload->vgpu->gvt->device_info.gmadr_bytes_in_cmd; + struct intel_shadow_bb_entry *entry_obj; /* pin the gem object to ggtt */ - if (!list_empty(&workload->shadow_bb)) { - struct intel_shadow_bb_entry *entry_obj = - list_first_entry(&workload->shadow_bb, - struct intel_shadow_bb_entry, - list); - struct intel_shadow_bb_entry *temp; + list_for_each_entry(entry_obj, &workload->shadow_bb, list) { + struct i915_vma *vma; - list_for_each_entry_safe(entry_obj, temp, &workload->shadow_bb, - list) { - struct i915_vma *vma; - - vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0, - 4, 0); - if (IS_ERR(vma)) { - gvt_err("Cannot pin\n"); - return; - } - - /* FIXME: we are not tracking our pinned VMA leaving it - * up to the core to fix up the stray pin_count upon - * free. - */ - - /* update the relocate gma with shadow batch buffer*/ - set_gma_to_bb_cmd(entry_obj, - i915_ggtt_offset(vma), - gmadr_bytes); + vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0, 4, 0); + if (IS_ERR(vma)) { + gvt_err("Cannot pin\n"); + return; } + + /* FIXME: we are not tracking our pinned VMA leaving it + * up to the core to fix up the stray pin_count upon + * free. + */ + + /* update the relocate gma with shadow batch buffer*/ + entry_obj->bb_start_cmd_va[1] = i915_ggtt_offset(vma); + if (gmadr_bytes == 8) + entry_obj->bb_start_cmd_va[2] = 0; } } @@ -826,7 +798,7 @@ int intel_vgpu_init_execlist(struct intel_vgpu *vgpu) INIT_LIST_HEAD(&vgpu->workload_q_head[i]); } - vgpu->workloads = kmem_cache_create("gvt-g vgpu workload", + vgpu->workloads = kmem_cache_create("gvt-g_vgpu_workload", sizeof(struct intel_vgpu_workload), 0, SLAB_HWCACHE_ALIGN, NULL); diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 6c5fdf5b2ce2..47dec4acf7ff 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -240,15 +240,8 @@ static inline int get_pse_type(int type) static u64 read_pte64(struct drm_i915_private *dev_priv, unsigned long index) { void __iomem *addr = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + index; - u64 pte; -#ifdef readq - pte = readq(addr); -#else - pte = ioread32(addr); - pte |= (u64)ioread32(addr + 4) << 32; -#endif - return pte; + return readq(addr); } static void write_pte64(struct drm_i915_private *dev_priv, @@ -256,12 +249,8 @@ static void write_pte64(struct drm_i915_private *dev_priv, { void __iomem *addr = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + index; -#ifdef writeq writeq(pte, addr); -#else - iowrite32((u32)pte, addr); - iowrite32(pte >> 32, addr + 4); -#endif + I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); POSTING_READ(GFX_FLSH_CNTL_GEN6); } @@ -1380,8 +1369,7 @@ static int gen8_mm_alloc_page_table(struct intel_vgpu_mm *mm) info->gtt_entry_size; mem = kzalloc(mm->has_shadow_page_table ? mm->page_table_entry_size * 2 - : mm->page_table_entry_size, - GFP_ATOMIC); + : mm->page_table_entry_size, GFP_KERNEL); if (!mem) return -ENOMEM; mm->virtual_page_table = mem; @@ -1532,7 +1520,7 @@ struct intel_vgpu_mm *intel_vgpu_create_mm(struct intel_vgpu *vgpu, struct intel_vgpu_mm *mm; int ret; - mm = kzalloc(sizeof(*mm), GFP_ATOMIC); + mm = kzalloc(sizeof(*mm), GFP_KERNEL); if (!mm) { ret = -ENOMEM; goto fail; @@ -1886,30 +1874,27 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu, struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops; int page_entry_num = GTT_PAGE_SIZE >> vgpu->gvt->device_info.gtt_entry_size_shift; - struct page *scratch_pt; + void *scratch_pt; unsigned long mfn; int i; - void *p; if (WARN_ON(type < GTT_TYPE_PPGTT_PTE_PT || type >= GTT_TYPE_MAX)) return -EINVAL; - scratch_pt = alloc_page(GFP_KERNEL | GFP_ATOMIC | __GFP_ZERO); + scratch_pt = (void *)get_zeroed_page(GFP_KERNEL); if (!scratch_pt) { gvt_err("fail to allocate scratch page\n"); return -ENOMEM; } - p = kmap_atomic(scratch_pt); - mfn = intel_gvt_hypervisor_virt_to_mfn(p); + mfn = intel_gvt_hypervisor_virt_to_mfn(scratch_pt); if (mfn == INTEL_GVT_INVALID_ADDR) { - gvt_err("fail to translate vaddr:0x%llx\n", (u64)p); - kunmap_atomic(p); - __free_page(scratch_pt); + gvt_err("fail to translate vaddr:0x%lx\n", (unsigned long)scratch_pt); + free_page((unsigned long)scratch_pt); return -EFAULT; } gtt->scratch_pt[type].page_mfn = mfn; - gtt->scratch_pt[type].page = scratch_pt; + gtt->scratch_pt[type].page = virt_to_page(scratch_pt); gvt_dbg_mm("vgpu%d create scratch_pt: type %d mfn=0x%lx\n", vgpu->id, type, mfn); @@ -1918,7 +1903,7 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu, * scratch_pt[type] indicate the scratch pt/scratch page used by the * 'type' pt. * e.g. scratch_pt[GTT_TYPE_PPGTT_PDE_PT] is used by - * GTT_TYPE_PPGTT_PDE_PT level pt, that means this scatch_pt it self + * GTT_TYPE_PPGTT_PDE_PT level pt, that means this scratch_pt it self * is GTT_TYPE_PPGTT_PTE_PT, and full filled by scratch page mfn. */ if (type > GTT_TYPE_PPGTT_PTE_PT && type < GTT_TYPE_MAX) { @@ -1936,11 +1921,9 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu, se.val64 |= PPAT_CACHED_INDEX; for (i = 0; i < page_entry_num; i++) - ops->set_entry(p, &se, i, false, 0, vgpu); + ops->set_entry(scratch_pt, &se, i, false, 0, vgpu); } - kunmap_atomic(p); - return 0; } @@ -2208,7 +2191,7 @@ int intel_vgpu_g2v_destroy_ppgtt_mm(struct intel_vgpu *vgpu, int intel_gvt_init_gtt(struct intel_gvt *gvt) { int ret; - void *page_addr; + void *page; gvt_dbg_core("init gtt\n"); @@ -2221,17 +2204,14 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt) return -ENODEV; } - gvt->gtt.scratch_ggtt_page = - alloc_page(GFP_KERNEL | GFP_ATOMIC | __GFP_ZERO); - if (!gvt->gtt.scratch_ggtt_page) { + page = (void *)get_zeroed_page(GFP_KERNEL); + if (!page) { gvt_err("fail to allocate scratch ggtt page\n"); return -ENOMEM; } + gvt->gtt.scratch_ggtt_page = virt_to_page(page); - page_addr = page_address(gvt->gtt.scratch_ggtt_page); - - gvt->gtt.scratch_ggtt_mfn = - intel_gvt_hypervisor_virt_to_mfn(page_addr); + gvt->gtt.scratch_ggtt_mfn = intel_gvt_hypervisor_virt_to_mfn(page); if (gvt->gtt.scratch_ggtt_mfn == INTEL_GVT_INVALID_ADDR) { gvt_err("fail to translate scratch ggtt page\n"); __free_page(gvt->gtt.scratch_ggtt_page); @@ -2297,3 +2277,30 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu) for (offset = 0; offset < num_entries; offset++) ops->set_entry(NULL, &e, index + offset, false, 0, vgpu); } + +/** + * intel_vgpu_reset_gtt - reset the all GTT related status + * @vgpu: a vGPU + * @dmlr: true for vGPU Device Model Level Reset, false for GT Reset + * + * This function is called from vfio core to reset reset all + * GTT related status, including GGTT, PPGTT, scratch page. + * + */ +void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr) +{ + int i; + + ppgtt_free_all_shadow_page(vgpu); + if (!dmlr) + return; + + intel_vgpu_reset_ggtt(vgpu); + + /* clear scratch page for security */ + for (i = GTT_TYPE_PPGTT_PTE_PT; i < GTT_TYPE_MAX; i++) { + if (vgpu->gtt.scratch_pt[i].page != NULL) + memset(page_address(vgpu->gtt.scratch_pt[i].page), + 0, PAGE_SIZE); + } +} diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index b315ab3593ec..f88eb5e89bea 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -208,6 +208,7 @@ extern void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu); void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu); extern int intel_gvt_init_gtt(struct intel_gvt *gvt); +extern void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr); extern void intel_gvt_clean_gtt(struct intel_gvt *gvt); extern struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu, diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c index 398877c3d2fd..e6bf5c533fbe 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.c +++ b/drivers/gpu/drm/i915/gvt/gvt.c @@ -201,6 +201,8 @@ void intel_gvt_clean_device(struct drm_i915_private *dev_priv) intel_gvt_hypervisor_host_exit(&dev_priv->drm.pdev->dev, gvt); intel_gvt_clean_vgpu_types(gvt); + idr_destroy(&gvt->vgpu_idr); + kfree(dev_priv->gvt); dev_priv->gvt = NULL; } @@ -237,6 +239,8 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv) gvt_dbg_core("init gvt device\n"); + idr_init(&gvt->vgpu_idr); + mutex_init(&gvt->lock); gvt->dev_priv = dev_priv; @@ -244,7 +248,7 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv) ret = intel_gvt_setup_mmio_info(gvt); if (ret) - return ret; + goto out_clean_idr; ret = intel_gvt_load_firmware(gvt); if (ret) @@ -313,6 +317,8 @@ out_free_firmware: intel_gvt_free_firmware(gvt); out_clean_mmio_info: intel_gvt_clean_mmio_info(gvt); +out_clean_idr: + idr_destroy(&gvt->vgpu_idr); kfree(gvt); return ret; } diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 0af17016f33f..e227caf5859e 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -323,6 +323,7 @@ struct intel_vgpu_creation_params { int intel_vgpu_alloc_resource(struct intel_vgpu *vgpu, struct intel_vgpu_creation_params *param); +void intel_vgpu_reset_resource(struct intel_vgpu *vgpu); void intel_vgpu_free_resource(struct intel_vgpu *vgpu); void intel_vgpu_write_fence(struct intel_vgpu *vgpu, u32 fence, u64 value); @@ -375,6 +376,8 @@ void intel_gvt_clean_vgpu_types(struct intel_gvt *gvt); struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt, struct intel_vgpu_type *type); void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu); +void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, + unsigned int engine_mask); void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu); @@ -411,6 +414,10 @@ int intel_gvt_ggtt_index_g2h(struct intel_vgpu *vgpu, unsigned long g_index, int intel_gvt_ggtt_h2g_index(struct intel_vgpu *vgpu, unsigned long h_index, unsigned long *g_index); +void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, + bool primary); +void intel_vgpu_reset_cfg_space(struct intel_vgpu *vgpu); + int intel_vgpu_emulate_cfg_read(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes); @@ -424,7 +431,6 @@ void intel_vgpu_clean_opregion(struct intel_vgpu *vgpu); int intel_vgpu_init_opregion(struct intel_vgpu *vgpu, u32 gpa); int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci); -int setup_vgpu_mmio(struct intel_vgpu *vgpu); void populate_pvinfo_page(struct intel_vgpu *vgpu); struct intel_gvt_ops { diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 522809710312..ab2ea157da4c 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -93,7 +93,8 @@ static void write_vreg(struct intel_vgpu *vgpu, unsigned int offset, static int new_mmio_info(struct intel_gvt *gvt, u32 offset, u32 flags, u32 size, u32 addr_mask, u32 ro_mask, u32 device, - void *read, void *write) + int (*read)(struct intel_vgpu *, unsigned int, void *, unsigned int), + int (*write)(struct intel_vgpu *, unsigned int, void *, unsigned int)) { struct intel_gvt_mmio_info *info, *p; u32 start, end, i; @@ -219,7 +220,7 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu, default: /*should not hit here*/ gvt_err("invalid forcewake offset 0x%x\n", offset); - return 1; + return -EINVAL; } } else { ack_reg_offset = FORCEWAKE_ACK_HSW_REG; @@ -230,77 +231,45 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu, return 0; } -static int handle_device_reset(struct intel_vgpu *vgpu, unsigned int offset, - void *p_data, unsigned int bytes, unsigned long bitmap) -{ - struct intel_gvt_workload_scheduler *scheduler = - &vgpu->gvt->scheduler; - - vgpu->resetting = true; - - intel_vgpu_stop_schedule(vgpu); - /* - * The current_vgpu will set to NULL after stopping the - * scheduler when the reset is triggered by current vgpu. - */ - if (scheduler->current_vgpu == NULL) { - mutex_unlock(&vgpu->gvt->lock); - intel_gvt_wait_vgpu_idle(vgpu); - mutex_lock(&vgpu->gvt->lock); - } - - intel_vgpu_reset_execlist(vgpu, bitmap); - - /* full GPU reset */ - if (bitmap == 0xff) { - mutex_unlock(&vgpu->gvt->lock); - intel_vgpu_clean_gtt(vgpu); - mutex_lock(&vgpu->gvt->lock); - setup_vgpu_mmio(vgpu); - populate_pvinfo_page(vgpu); - intel_vgpu_init_gtt(vgpu); - } - - vgpu->resetting = false; - - return 0; -} - static int gdrst_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, - void *p_data, unsigned int bytes) + void *p_data, unsigned int bytes) { + unsigned int engine_mask = 0; u32 data; - u64 bitmap = 0; write_vreg(vgpu, offset, p_data, bytes); data = vgpu_vreg(vgpu, offset); if (data & GEN6_GRDOM_FULL) { gvt_dbg_mmio("vgpu%d: request full GPU reset\n", vgpu->id); - bitmap = 0xff; + engine_mask = ALL_ENGINES; + } else { + if (data & GEN6_GRDOM_RENDER) { + gvt_dbg_mmio("vgpu%d: request RCS reset\n", vgpu->id); + engine_mask |= (1 << RCS); + } + if (data & GEN6_GRDOM_MEDIA) { + gvt_dbg_mmio("vgpu%d: request VCS reset\n", vgpu->id); + engine_mask |= (1 << VCS); + } + if (data & GEN6_GRDOM_BLT) { + gvt_dbg_mmio("vgpu%d: request BCS Reset\n", vgpu->id); + engine_mask |= (1 << BCS); + } + if (data & GEN6_GRDOM_VECS) { + gvt_dbg_mmio("vgpu%d: request VECS Reset\n", vgpu->id); + engine_mask |= (1 << VECS); + } + if (data & GEN8_GRDOM_MEDIA2) { + gvt_dbg_mmio("vgpu%d: request VCS2 Reset\n", vgpu->id); + if (HAS_BSD2(vgpu->gvt->dev_priv)) + engine_mask |= (1 << VCS2); + } } - if (data & GEN6_GRDOM_RENDER) { - gvt_dbg_mmio("vgpu%d: request RCS reset\n", vgpu->id); - bitmap |= (1 << RCS); - } - if (data & GEN6_GRDOM_MEDIA) { - gvt_dbg_mmio("vgpu%d: request VCS reset\n", vgpu->id); - bitmap |= (1 << VCS); - } - if (data & GEN6_GRDOM_BLT) { - gvt_dbg_mmio("vgpu%d: request BCS Reset\n", vgpu->id); - bitmap |= (1 << BCS); - } - if (data & GEN6_GRDOM_VECS) { - gvt_dbg_mmio("vgpu%d: request VECS Reset\n", vgpu->id); - bitmap |= (1 << VECS); - } - if (data & GEN8_GRDOM_MEDIA2) { - gvt_dbg_mmio("vgpu%d: request VCS2 Reset\n", vgpu->id); - if (HAS_BSD2(vgpu->gvt->dev_priv)) - bitmap |= (1 << VCS2); - } - return handle_device_reset(vgpu, offset, p_data, bytes, bitmap); + + intel_gvt_reset_vgpu_locked(vgpu, false, engine_mask); + + return 0; } static int gmbus_mmio_read(struct intel_vgpu *vgpu, unsigned int offset, @@ -974,7 +943,7 @@ static int sbi_data_mmio_read(struct intel_vgpu *vgpu, unsigned int offset, return 0; } -static bool sbi_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, +static int sbi_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { u32 data; @@ -1366,7 +1335,6 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, static int gvt_reg_tlb_control_handler(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { - int rc = 0; unsigned int id = 0; write_vreg(vgpu, offset, p_data, bytes); @@ -1389,12 +1357,11 @@ static int gvt_reg_tlb_control_handler(struct intel_vgpu *vgpu, id = VECS; break; default: - rc = -EINVAL; - break; + return -EINVAL; } set_bit(id, (void *)vgpu->tlb_handle_pending); - return rc; + return 0; } static int ring_reset_ctl_write(struct intel_vgpu *vgpu, diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index faaae07ae487..3f656e3a6e5a 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -230,8 +230,8 @@ static struct intel_vgpu_type *intel_gvt_find_vgpu_type(struct intel_gvt *gvt, return NULL; } -static ssize_t available_instance_show(struct kobject *kobj, struct device *dev, - char *buf) +static ssize_t available_instances_show(struct kobject *kobj, + struct device *dev, char *buf) { struct intel_vgpu_type *type; unsigned int num = 0; @@ -269,12 +269,12 @@ static ssize_t description_show(struct kobject *kobj, struct device *dev, type->fence); } -static MDEV_TYPE_ATTR_RO(available_instance); +static MDEV_TYPE_ATTR_RO(available_instances); static MDEV_TYPE_ATTR_RO(device_api); static MDEV_TYPE_ATTR_RO(description); static struct attribute *type_attrs[] = { - &mdev_type_attr_available_instance.attr, + &mdev_type_attr_available_instances.attr, &mdev_type_attr_device_api.attr, &mdev_type_attr_description.attr, NULL, @@ -398,6 +398,7 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev) struct intel_vgpu_type *type; struct device *pdev; void *gvt; + int ret; pdev = mdev_parent_dev(mdev); gvt = kdev_to_i915(pdev)->gvt; @@ -406,13 +407,15 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev) if (!type) { gvt_err("failed to find type %s to create\n", kobject_name(kobj)); - return -EINVAL; + ret = -EINVAL; + goto out; } vgpu = intel_gvt_ops->vgpu_create(gvt, type); if (IS_ERR_OR_NULL(vgpu)) { - gvt_err("create intel vgpu failed\n"); - return -EINVAL; + ret = vgpu == NULL ? -EFAULT : PTR_ERR(vgpu); + gvt_err("failed to create intel vgpu: %d\n", ret); + goto out; } INIT_WORK(&vgpu->vdev.release_work, intel_vgpu_release_work); @@ -422,7 +425,10 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev) gvt_dbg_core("intel_vgpu_create succeeded for mdev: %s\n", dev_name(mdev_dev(mdev))); - return 0; + ret = 0; + +out: + return ret; } static int intel_vgpu_remove(struct mdev_device *mdev) diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c index 09c9450a1946..4df078bc5d04 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.c +++ b/drivers/gpu/drm/i915/gvt/mmio.c @@ -125,25 +125,12 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa, if (WARN_ON(!reg_is_mmio(gvt, offset + bytes - 1))) goto err; - mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4)); - if (!mmio && !vgpu->mmio.disable_warn_untrack) { - gvt_err("vgpu%d: read untracked MMIO %x len %d val %x\n", - vgpu->id, offset, bytes, *(u32 *)p_data); - - if (offset == 0x206c) { - gvt_err("------------------------------------------\n"); - gvt_err("vgpu%d: likely triggers a gfx reset\n", - vgpu->id); - gvt_err("------------------------------------------\n"); - vgpu->mmio.disable_warn_untrack = true; - } - } - if (!intel_gvt_mmio_is_unalign(gvt, offset)) { if (WARN_ON(!IS_ALIGNED(offset, bytes))) goto err; } + mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4)); if (mmio) { if (!intel_gvt_mmio_is_unalign(gvt, mmio->offset)) { if (WARN_ON(offset + bytes > mmio->offset + mmio->size)) @@ -152,9 +139,23 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa, goto err; } ret = mmio->read(vgpu, offset, p_data, bytes); - } else + } else { ret = intel_vgpu_default_mmio_read(vgpu, offset, p_data, bytes); + if (!vgpu->mmio.disable_warn_untrack) { + gvt_err("vgpu%d: read untracked MMIO %x(%dB) val %x\n", + vgpu->id, offset, bytes, *(u32 *)p_data); + + if (offset == 0x206c) { + gvt_err("------------------------------------------\n"); + gvt_err("vgpu%d: likely triggers a gfx reset\n", + vgpu->id); + gvt_err("------------------------------------------\n"); + vgpu->mmio.disable_warn_untrack = true; + } + } + } + if (ret) goto err; @@ -302,3 +303,56 @@ err: mutex_unlock(&gvt->lock); return ret; } + + +/** + * intel_vgpu_reset_mmio - reset virtual MMIO space + * @vgpu: a vGPU + * + */ +void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu) +{ + struct intel_gvt *gvt = vgpu->gvt; + const struct intel_gvt_device_info *info = &gvt->device_info; + + memcpy(vgpu->mmio.vreg, gvt->firmware.mmio, info->mmio_size); + memcpy(vgpu->mmio.sreg, gvt->firmware.mmio, info->mmio_size); + + vgpu_vreg(vgpu, GEN6_GT_THREAD_STATUS_REG) = 0; + + /* set the bit 0:2(Core C-State ) to C0 */ + vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0; +} + +/** + * intel_vgpu_init_mmio - init MMIO space + * @vgpu: a vGPU + * + * Returns: + * Zero on success, negative error code if failed + */ +int intel_vgpu_init_mmio(struct intel_vgpu *vgpu) +{ + const struct intel_gvt_device_info *info = &vgpu->gvt->device_info; + + vgpu->mmio.vreg = vzalloc(info->mmio_size * 2); + if (!vgpu->mmio.vreg) + return -ENOMEM; + + vgpu->mmio.sreg = vgpu->mmio.vreg + info->mmio_size; + + intel_vgpu_reset_mmio(vgpu); + + return 0; +} + +/** + * intel_vgpu_clean_mmio - clean MMIO space + * @vgpu: a vGPU + * + */ +void intel_vgpu_clean_mmio(struct intel_vgpu *vgpu) +{ + vfree(vgpu->mmio.vreg); + vgpu->mmio.vreg = vgpu->mmio.sreg = NULL; +} diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h index 87d5b5e366a3..3bc620f56f35 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.h +++ b/drivers/gpu/drm/i915/gvt/mmio.h @@ -86,6 +86,10 @@ struct intel_gvt_mmio_info *intel_gvt_find_mmio_info(struct intel_gvt *gvt, *offset; \ }) +int intel_vgpu_init_mmio(struct intel_vgpu *vgpu); +void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu); +void intel_vgpu_clean_mmio(struct intel_vgpu *vgpu); + int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa); int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, u64 pa, diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index 81cd921770c6..d9fb41ab7119 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -36,9 +36,9 @@ static int init_vgpu_opregion(struct intel_vgpu *vgpu, u32 gpa) vgpu->id)) return -EINVAL; - vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_ATOMIC | - GFP_DMA32 | __GFP_ZERO, - INTEL_GVT_OPREGION_PORDER); + vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_KERNEL | + __GFP_ZERO, + get_order(INTEL_GVT_OPREGION_SIZE)); if (!vgpu_opregion(vgpu)->va) return -ENOMEM; @@ -97,7 +97,7 @@ void intel_vgpu_clean_opregion(struct intel_vgpu *vgpu) if (intel_gvt_host.hypervisor_type == INTEL_GVT_HYPERVISOR_XEN) { map_vgpu_opregion(vgpu, false); free_pages((unsigned long)vgpu_opregion(vgpu)->va, - INTEL_GVT_OPREGION_PORDER); + get_order(INTEL_GVT_OPREGION_SIZE)); vgpu_opregion(vgpu)->va = NULL; } diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h index 0dfe789d8f02..fbd023a16f18 100644 --- a/drivers/gpu/drm/i915/gvt/reg.h +++ b/drivers/gpu/drm/i915/gvt/reg.h @@ -50,8 +50,7 @@ #define INTEL_GVT_OPREGION_PARM 0x204 #define INTEL_GVT_OPREGION_PAGES 2 -#define INTEL_GVT_OPREGION_PORDER 1 -#define INTEL_GVT_OPREGION_SIZE (2 * 4096) +#define INTEL_GVT_OPREGION_SIZE (INTEL_GVT_OPREGION_PAGES * PAGE_SIZE) #define VGT_SPRSTRIDE(pipe) _PIPE(pipe, _SPRA_STRIDE, _PLANE_STRIDE_2_B) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 4db242250235..e91885dffeff 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -350,13 +350,15 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) { struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler; struct intel_vgpu_workload *workload; + struct intel_vgpu *vgpu; int event; mutex_lock(&gvt->lock); workload = scheduler->current_workload[ring_id]; + vgpu = workload->vgpu; - if (!workload->status && !workload->vgpu->resetting) { + if (!workload->status && !vgpu->resetting) { wait_event(workload->shadow_ctx_status_wq, !atomic_read(&workload->shadow_ctx_active)); @@ -364,8 +366,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) for_each_set_bit(event, workload->pending_events, INTEL_GVT_EVENT_MAX) - intel_vgpu_trigger_virtual_event(workload->vgpu, - event); + intel_vgpu_trigger_virtual_event(vgpu, event); } gvt_dbg_sched("ring id %d complete workload %p status %d\n", @@ -373,11 +374,10 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) scheduler->current_workload[ring_id] = NULL; - atomic_dec(&workload->vgpu->running_workload_num); - list_del_init(&workload->list); workload->complete(workload); + atomic_dec(&vgpu->running_workload_num); wake_up(&scheduler->workload_complete_wq); mutex_unlock(&gvt->lock); } @@ -459,11 +459,11 @@ complete: gvt_dbg_sched("will complete workload %p\n, status: %d\n", workload, workload->status); - complete_current_workload(gvt, ring_id); - if (workload->req) i915_gem_request_put(fetch_and_zero(&workload->req)); + complete_current_workload(gvt, ring_id); + if (need_force_wake) intel_uncore_forcewake_put(gvt->dev_priv, FORCEWAKE_ALL); diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h index 3b30c28bff51..2833dfa8c9ae 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.h +++ b/drivers/gpu/drm/i915/gvt/scheduler.h @@ -113,7 +113,7 @@ struct intel_shadow_bb_entry { struct drm_i915_gem_object *obj; void *va; unsigned long len; - void *bb_start_cmd_va; + u32 *bb_start_cmd_va; }; #define workload_q_head(vgpu, ring_id) \ diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 536d2b9d5777..7295bc8e12fb 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -35,79 +35,6 @@ #include "gvt.h" #include "i915_pvinfo.h" -static void clean_vgpu_mmio(struct intel_vgpu *vgpu) -{ - vfree(vgpu->mmio.vreg); - vgpu->mmio.vreg = vgpu->mmio.sreg = NULL; -} - -int setup_vgpu_mmio(struct intel_vgpu *vgpu) -{ - struct intel_gvt *gvt = vgpu->gvt; - const struct intel_gvt_device_info *info = &gvt->device_info; - - if (vgpu->mmio.vreg) - memset(vgpu->mmio.vreg, 0, info->mmio_size * 2); - else { - vgpu->mmio.vreg = vzalloc(info->mmio_size * 2); - if (!vgpu->mmio.vreg) - return -ENOMEM; - } - - vgpu->mmio.sreg = vgpu->mmio.vreg + info->mmio_size; - - memcpy(vgpu->mmio.vreg, gvt->firmware.mmio, info->mmio_size); - memcpy(vgpu->mmio.sreg, gvt->firmware.mmio, info->mmio_size); - - vgpu_vreg(vgpu, GEN6_GT_THREAD_STATUS_REG) = 0; - - /* set the bit 0:2(Core C-State ) to C0 */ - vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0; - return 0; -} - -static void setup_vgpu_cfg_space(struct intel_vgpu *vgpu, - struct intel_vgpu_creation_params *param) -{ - struct intel_gvt *gvt = vgpu->gvt; - const struct intel_gvt_device_info *info = &gvt->device_info; - u16 *gmch_ctl; - int i; - - memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space, - info->cfg_space_size); - - if (!param->primary) { - vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] = - INTEL_GVT_PCI_CLASS_VGA_OTHER; - vgpu_cfg_space(vgpu)[PCI_CLASS_PROG] = - INTEL_GVT_PCI_CLASS_VGA_OTHER; - } - - /* Show guest that there isn't any stolen memory.*/ - gmch_ctl = (u16 *)(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_GMCH_CONTROL); - *gmch_ctl &= ~(BDW_GMCH_GMS_MASK << BDW_GMCH_GMS_SHIFT); - - intel_vgpu_write_pci_bar(vgpu, PCI_BASE_ADDRESS_2, - gvt_aperture_pa_base(gvt), true); - - vgpu_cfg_space(vgpu)[PCI_COMMAND] &= ~(PCI_COMMAND_IO - | PCI_COMMAND_MEMORY - | PCI_COMMAND_MASTER); - /* - * Clear the bar upper 32bit and let guest to assign the new value - */ - memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4); - memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4); - memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4); - - for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) { - vgpu->cfg_space.bar[i].size = pci_resource_len( - gvt->dev_priv->drm.pdev, i * 2); - vgpu->cfg_space.bar[i].tracked = false; - } -} - void populate_pvinfo_page(struct intel_vgpu *vgpu) { /* setup the ballooning information */ @@ -177,7 +104,7 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt) if (low_avail / min_low == 0) break; gvt->types[i].low_gm_size = min_low; - gvt->types[i].high_gm_size = 3 * gvt->types[i].low_gm_size; + gvt->types[i].high_gm_size = max((min_low<<3), MB_TO_BYTES(384U)); gvt->types[i].fence = 4; gvt->types[i].max_instance = low_avail / min_low; gvt->types[i].avail_instance = gvt->types[i].max_instance; @@ -217,7 +144,7 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt) */ low_gm_avail = MB_TO_BYTES(256) - HOST_LOW_GM_SIZE - gvt->gm.vgpu_allocated_low_gm_size; - high_gm_avail = MB_TO_BYTES(256) * 3 - HOST_HIGH_GM_SIZE - + high_gm_avail = MB_TO_BYTES(256) * 8UL - HOST_HIGH_GM_SIZE - gvt->gm.vgpu_allocated_high_gm_size; fence_avail = gvt_fence_sz(gvt) - HOST_FENCE - gvt->fence.vgpu_allocated_fence_num; @@ -268,7 +195,7 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) intel_vgpu_clean_gtt(vgpu); intel_gvt_hypervisor_detach_vgpu(vgpu); intel_vgpu_free_resource(vgpu); - clean_vgpu_mmio(vgpu); + intel_vgpu_clean_mmio(vgpu); vfree(vgpu); intel_gvt_update_vgpu_types(gvt); @@ -300,11 +227,11 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, vgpu->gvt = gvt; bitmap_zero(vgpu->tlb_handle_pending, I915_NUM_ENGINES); - setup_vgpu_cfg_space(vgpu, param); + intel_vgpu_init_cfg_space(vgpu, param->primary); - ret = setup_vgpu_mmio(vgpu); + ret = intel_vgpu_init_mmio(vgpu); if (ret) - goto out_free_vgpu; + goto out_clean_idr; ret = intel_vgpu_alloc_resource(vgpu, param); if (ret) @@ -354,7 +281,9 @@ out_detach_hypervisor_vgpu: out_clean_vgpu_resource: intel_vgpu_free_resource(vgpu); out_clean_vgpu_mmio: - clean_vgpu_mmio(vgpu); + intel_vgpu_clean_mmio(vgpu); +out_clean_idr: + idr_remove(&gvt->vgpu_idr, vgpu->id); out_free_vgpu: vfree(vgpu); mutex_unlock(&gvt->lock); @@ -398,7 +327,75 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt, } /** - * intel_gvt_reset_vgpu - reset a virtual GPU + * intel_gvt_reset_vgpu_locked - reset a virtual GPU by DMLR or GT reset + * @vgpu: virtual GPU + * @dmlr: vGPU Device Model Level Reset or GT Reset + * @engine_mask: engines to reset for GT reset + * + * This function is called when user wants to reset a virtual GPU through + * device model reset or GT reset. The caller should hold the gvt lock. + * + * vGPU Device Model Level Reset (DMLR) simulates the PCI level reset to reset + * the whole vGPU to default state as when it is created. This vGPU function + * is required both for functionary and security concerns.The ultimate goal + * of vGPU FLR is that reuse a vGPU instance by virtual machines. When we + * assign a vGPU to a virtual machine we must isse such reset first. + * + * Full GT Reset and Per-Engine GT Reset are soft reset flow for GPU engines + * (Render, Blitter, Video, Video Enhancement). It is defined by GPU Spec. + * Unlike the FLR, GT reset only reset particular resource of a vGPU per + * the reset request. Guest driver can issue a GT reset by programming the + * virtual GDRST register to reset specific virtual GPU engine or all + * engines. + * + * The parameter dev_level is to identify if we will do DMLR or GT reset. + * The parameter engine_mask is to specific the engines that need to be + * resetted. If value ALL_ENGINES is given for engine_mask, it means + * the caller requests a full GT reset that we will reset all virtual + * GPU engines. For FLR, engine_mask is ignored. + */ +void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, + unsigned int engine_mask) +{ + struct intel_gvt *gvt = vgpu->gvt; + struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler; + + gvt_dbg_core("------------------------------------------\n"); + gvt_dbg_core("resseting vgpu%d, dmlr %d, engine_mask %08x\n", + vgpu->id, dmlr, engine_mask); + vgpu->resetting = true; + + intel_vgpu_stop_schedule(vgpu); + /* + * The current_vgpu will set to NULL after stopping the + * scheduler when the reset is triggered by current vgpu. + */ + if (scheduler->current_vgpu == NULL) { + mutex_unlock(&gvt->lock); + intel_gvt_wait_vgpu_idle(vgpu); + mutex_lock(&gvt->lock); + } + + intel_vgpu_reset_execlist(vgpu, dmlr ? ALL_ENGINES : engine_mask); + + /* full GPU reset or device model level reset */ + if (engine_mask == ALL_ENGINES || dmlr) { + intel_vgpu_reset_gtt(vgpu, dmlr); + intel_vgpu_reset_resource(vgpu); + intel_vgpu_reset_mmio(vgpu); + populate_pvinfo_page(vgpu); + + if (dmlr) + intel_vgpu_reset_cfg_space(vgpu); + } + + vgpu->resetting = false; + gvt_dbg_core("reset vgpu%d done\n", vgpu->id); + gvt_dbg_core("------------------------------------------\n"); +} + +/** + * intel_gvt_reset_vgpu - reset a virtual GPU (Function Level) * @vgpu: virtual GPU * * This function is called when user wants to reset a virtual GPU. @@ -406,4 +403,7 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt, */ void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu) { + mutex_lock(&vgpu->gvt->lock); + intel_gvt_reset_vgpu_locked(vgpu, true, 0); + mutex_unlock(&vgpu->gvt->lock); } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 445fec9c2841..b2c4a0b8a627 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -2378,7 +2378,7 @@ static int intel_runtime_suspend(struct device *kdev) assert_forcewakes_inactive(dev_priv); - if (!IS_VALLEYVIEW(dev_priv) || !IS_CHERRYVIEW(dev_priv)) + if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv)) intel_hpd_poll_init(dev_priv); DRM_DEBUG_KMS("Device suspended\n"); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 243224aeabf8..69bc3b0c4390 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1977,6 +1977,11 @@ struct drm_i915_private { struct i915_frontbuffer_tracking fb_tracking; + struct intel_atomic_helper { + struct llist_head free_list; + struct work_struct free_work; + } atomic_helper; + u16 orig_clock; bool mchbar_need_disable; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 3dd7fc662859..4b23a7814713 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -595,47 +595,21 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, struct drm_i915_gem_pwrite *args, struct drm_file *file) { - struct drm_device *dev = obj->base.dev; void *vaddr = obj->phys_handle->vaddr + args->offset; char __user *user_data = u64_to_user_ptr(args->data_ptr); - int ret; /* We manually control the domain here and pretend that it * remains coherent i.e. in the GTT domain, like shmem_pwrite. */ - lockdep_assert_held(&obj->base.dev->struct_mutex); - ret = i915_gem_object_wait(obj, - I915_WAIT_INTERRUPTIBLE | - I915_WAIT_LOCKED | - I915_WAIT_ALL, - MAX_SCHEDULE_TIMEOUT, - to_rps_client(file)); - if (ret) - return ret; - intel_fb_obj_invalidate(obj, ORIGIN_CPU); - if (__copy_from_user_inatomic_nocache(vaddr, user_data, args->size)) { - unsigned long unwritten; - - /* The physical object once assigned is fixed for the lifetime - * of the obj, so we can safely drop the lock and continue - * to access vaddr. - */ - mutex_unlock(&dev->struct_mutex); - unwritten = copy_from_user(vaddr, user_data, args->size); - mutex_lock(&dev->struct_mutex); - if (unwritten) { - ret = -EFAULT; - goto out; - } - } + if (copy_from_user(vaddr, user_data, args->size)) + return -EFAULT; drm_clflush_virt_range(vaddr, args->size); - i915_gem_chipset_flush(to_i915(dev)); + i915_gem_chipset_flush(to_i915(obj->base.dev)); -out: intel_fb_obj_flush(obj, false, ORIGIN_CPU); - return ret; + return 0; } void *i915_gem_object_alloc(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index bd08814b015c..d534a316a16e 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -199,6 +199,7 @@ found: } /* Unbinding will emit any required flushes */ + ret = 0; while (!list_empty(&eviction_list)) { vma = list_first_entry(&eviction_list, struct i915_vma, diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index a792dcb902b5..e924a9516079 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -185,6 +185,7 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level, return ret; } + trace_i915_vma_bind(vma, bind_flags); ret = vma->vm->bind_vma(vma, cache_level, bind_flags); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 86ecec5601d4..588470eb8d39 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -499,6 +499,7 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector) struct drm_i915_private *dev_priv = to_i915(crt->base.base.dev); struct edid *edid; struct i2c_adapter *i2c; + bool ret = false; BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG); @@ -515,17 +516,17 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector) */ if (!is_digital) { DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n"); - return true; + ret = true; + } else { + DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n"); } - - DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n"); } else { DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [no valid EDID found]\n"); } kfree(edid); - return false; + return ret; } static enum drm_connector_status diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 3dc8724df400..f0b9aa7a0483 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2251,6 +2251,9 @@ void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation) intel_fill_fb_ggtt_view(&view, fb, rotation); vma = i915_gem_object_to_ggtt(obj, &view); + if (WARN_ON_ONCE(!vma)) + return; + i915_vma_unpin_fence(vma); i915_gem_object_unpin_from_display_plane(vma); } @@ -2585,8 +2588,9 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, * We only keep the x/y offsets, so push all of the * gtt offset into the x/y offsets. */ - _intel_adjust_tile_offset(&x, &y, tile_size, - tile_width, tile_height, pitch_tiles, + _intel_adjust_tile_offset(&x, &y, + tile_width, tile_height, + tile_size, pitch_tiles, gtt_offset_rotated * tile_size, 0); gtt_offset_rotated += rot_info->plane[i].width * rot_info->plane[i].height; @@ -2967,6 +2971,9 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state) unsigned int rotation = plane_state->base.rotation; int ret; + if (!plane_state->base.visible) + return 0; + /* Rotate src coordinates to match rotated GTT view */ if (drm_rotation_90_or_270(rotation)) drm_rect_rotate(&plane_state->base.src, @@ -6846,6 +6853,12 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc) } state = drm_atomic_state_alloc(crtc->dev); + if (!state) { + DRM_DEBUG_KMS("failed to disable [CRTC:%d:%s], out of memory", + crtc->base.id, crtc->name); + return; + } + state->acquire_ctx = crtc->dev->mode_config.acquire_ctx; /* Everything's already locked, -EDEADLK can't happen. */ @@ -11243,6 +11256,7 @@ found: } old->restore_state = restore_state; + drm_atomic_state_put(state); /* let the connector get through one full cycle before testing */ intel_wait_for_vblank(dev_priv, intel_crtc->pipe); @@ -14512,8 +14526,14 @@ intel_atomic_commit_ready(struct i915_sw_fence *fence, break; case FENCE_FREE: - drm_atomic_state_put(&state->base); - break; + { + struct intel_atomic_helper *helper = + &to_i915(state->base.dev)->atomic_helper; + + if (llist_add(&state->freed, &helper->free_list)) + schedule_work(&helper->free_work); + break; + } } return NOTIFY_DONE; @@ -16392,6 +16412,18 @@ fail: drm_modeset_acquire_fini(&ctx); } +static void intel_atomic_helper_free_state(struct work_struct *work) +{ + struct drm_i915_private *dev_priv = + container_of(work, typeof(*dev_priv), atomic_helper.free_work); + struct intel_atomic_state *state, *next; + struct llist_node *freed; + + freed = llist_del_all(&dev_priv->atomic_helper.free_list); + llist_for_each_entry_safe(state, next, freed, freed) + drm_atomic_state_put(&state->base); +} + int intel_modeset_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -16411,6 +16443,9 @@ int intel_modeset_init(struct drm_device *dev) dev->mode_config.funcs = &intel_mode_funcs; + INIT_WORK(&dev_priv->atomic_helper.free_work, + intel_atomic_helper_free_state); + intel_init_quirks(dev); intel_init_pm(dev_priv); @@ -17024,7 +17059,8 @@ void intel_display_resume(struct drm_device *dev) if (ret) DRM_ERROR("Restoring old state failed with %i\n", ret); - drm_atomic_state_put(state); + if (state) + drm_atomic_state_put(state); } void intel_modeset_gem_init(struct drm_device *dev) @@ -17094,6 +17130,9 @@ void intel_modeset_cleanup(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); + flush_work(&dev_priv->atomic_helper.free_work); + WARN_ON(!llist_empty(&dev_priv->atomic_helper.free_list)); + intel_disable_gt_powersave(dev_priv); /* diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index cd132c216a67..cd72ae171eeb 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -370,6 +370,8 @@ struct intel_atomic_state { struct skl_wm_values wm_results; struct i915_sw_fence commit_ready; + + struct llist_node freed; }; struct intel_plane_state { diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index beb08982dc0b..8cf2d80f2254 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -742,6 +742,9 @@ void intel_fbdev_initial_config_async(struct drm_device *dev) { struct intel_fbdev *ifbdev = to_i915(dev)->fbdev; + if (!ifbdev) + return; + ifbdev->cookie = async_schedule(intel_fbdev_initial_config, ifbdev); } diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index d4961fa20c73..beabc17e7c8a 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -979,18 +979,8 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, uint32_t *batch, uint32_t index) { - struct drm_i915_private *dev_priv = engine->i915; uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES); - /* - * WaDisableLSQCROPERFforOCL:kbl - * This WA is implemented in skl_init_clock_gating() but since - * this batch updates GEN8_L3SQCREG4 with default value we need to - * set this bit here to retain the WA during flush. - */ - if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) - l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS; - wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT)); wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4); diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index aeb637dc1fdf..91cb4c422ad5 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1095,14 +1095,6 @@ static int kbl_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(HDC_CHICKEN0, HDC_FENCE_DEST_SLM_DISABLE); - /* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes - * involving this register should also be added to WA batch as required. - */ - if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) - /* WaDisableLSQCROPERFforOCL:kbl */ - I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | - GEN8_LQSC_RO_PERF_DIS); - /* WaToEnableHwFixForPushConstHWBug:kbl */ if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER)) WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 14ff87686a36..686a580c711a 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -345,7 +345,6 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, { struct adreno_platform_config *config = pdev->dev.platform_data; struct msm_gpu *gpu = &adreno_gpu->base; - struct msm_mmu *mmu; int ret; adreno_gpu->funcs = funcs; @@ -385,8 +384,8 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, return ret; } - mmu = gpu->aspace->mmu; - if (mmu) { + if (gpu->aspace && gpu->aspace->mmu) { + struct msm_mmu *mmu = gpu->aspace->mmu; ret = mmu->funcs->attach(mmu, iommu_ports, ARRAY_SIZE(iommu_ports)); if (ret) diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c index 5f6cd8745dbc..c396d459a9d0 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c @@ -119,13 +119,7 @@ static void mdp5_prepare_commit(struct msm_kms *kms, struct drm_atomic_state *st static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *state) { - int i; struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms)); - struct drm_plane *plane; - struct drm_plane_state *plane_state; - - for_each_plane_in_state(state, plane, plane_state, i) - mdp5_plane_complete_commit(plane, plane_state); if (mdp5_kms->smp) mdp5_smp_complete_commit(mdp5_kms->smp, &mdp5_kms->state->smp); diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h index 17b0cc101171..cdfc63d90c7b 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h @@ -104,8 +104,6 @@ struct mdp5_plane_state { /* assigned by crtc blender */ enum mdp_mixer_stage_id stage; - - bool pending : 1; }; #define to_mdp5_plane_state(x) \ container_of(x, struct mdp5_plane_state, base) @@ -232,8 +230,6 @@ int mdp5_irq_domain_init(struct mdp5_kms *mdp5_kms); void mdp5_irq_domain_fini(struct mdp5_kms *mdp5_kms); uint32_t mdp5_plane_get_flush(struct drm_plane *plane); -void mdp5_plane_complete_commit(struct drm_plane *plane, - struct drm_plane_state *state); enum mdp5_pipe mdp5_plane_pipe(struct drm_plane *plane); struct drm_plane *mdp5_plane_init(struct drm_device *dev, bool primary); diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c index c099da7bc212..25d9d0a97156 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c @@ -179,7 +179,6 @@ mdp5_plane_atomic_print_state(struct drm_printer *p, drm_printf(p, "\tzpos=%u\n", pstate->zpos); drm_printf(p, "\talpha=%u\n", pstate->alpha); drm_printf(p, "\tstage=%s\n", stage2name(pstate->stage)); - drm_printf(p, "\tpending=%u\n", pstate->pending); } static void mdp5_plane_reset(struct drm_plane *plane) @@ -220,8 +219,6 @@ mdp5_plane_duplicate_state(struct drm_plane *plane) if (mdp5_state && mdp5_state->base.fb) drm_framebuffer_reference(mdp5_state->base.fb); - mdp5_state->pending = false; - return &mdp5_state->base; } @@ -288,13 +285,6 @@ static int mdp5_plane_atomic_check(struct drm_plane *plane, DBG("%s: check (%d -> %d)", plane->name, plane_enabled(old_state), plane_enabled(state)); - /* We don't allow faster-than-vblank updates.. if we did add this - * some day, we would need to disallow in cases where hwpipe - * changes - */ - if (WARN_ON(to_mdp5_plane_state(old_state)->pending)) - return -EBUSY; - max_width = config->hw->lm.max_width << 16; max_height = config->hw->lm.max_height << 16; @@ -370,12 +360,9 @@ static void mdp5_plane_atomic_update(struct drm_plane *plane, struct drm_plane_state *old_state) { struct drm_plane_state *state = plane->state; - struct mdp5_plane_state *mdp5_state = to_mdp5_plane_state(state); DBG("%s: update", plane->name); - mdp5_state->pending = true; - if (plane_enabled(state)) { int ret; @@ -851,15 +838,6 @@ uint32_t mdp5_plane_get_flush(struct drm_plane *plane) return pstate->hwpipe->flush_mask; } -/* called after vsync in thread context */ -void mdp5_plane_complete_commit(struct drm_plane *plane, - struct drm_plane_state *state) -{ - struct mdp5_plane_state *pstate = to_mdp5_plane_state(plane->state); - - pstate->pending = false; -} - /* initialize plane */ struct drm_plane *mdp5_plane_init(struct drm_device *dev, bool primary) { diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index d8bc59c7e261..8098677a3916 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -294,6 +294,8 @@ put_iova(struct drm_gem_object *obj) WARN_ON(!mutex_is_locked(&dev->struct_mutex)); for (id = 0; id < ARRAY_SIZE(msm_obj->domain); id++) { + if (!priv->aspace[id]) + continue; msm_gem_unmap_vma(priv->aspace[id], &msm_obj->domain[id], msm_obj->sgt); } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index cef08da1da4e..6a157763dfc3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -411,7 +411,8 @@ nouveau_display_init(struct drm_device *dev) return ret; /* enable polling for external displays */ - drm_kms_helper_poll_enable(dev); + if (!dev->mode_config.poll_enabled) + drm_kms_helper_poll_enable(dev); /* enable hotplug interrupts */ list_for_each_entry(connector, &dev->mode_config.connector_list, head) { diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 59348fc41c77..bc85a45f91cd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -773,7 +773,10 @@ nouveau_pmops_runtime_resume(struct device *dev) pci_set_master(pdev); ret = nouveau_do_resume(drm_dev, true); - drm_kms_helper_poll_enable(drm_dev); + + if (!drm_dev->mode_config.poll_enabled) + drm_kms_helper_poll_enable(drm_dev); + /* do magic */ nvif_mask(&device->object, 0x088488, (1 << 25), (1 << 25)); vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON); diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 8d5ed5bfdacb..42c1fa53d431 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -165,6 +165,8 @@ struct nouveau_drm { struct backlight_device *backlight; struct list_head bl_connectors; struct work_struct hpd_work; + struct work_struct fbcon_work; + int fbcon_new_state; #ifdef CONFIG_ACPI struct notifier_block acpi_nb; #endif diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 2f2a3dcd4ad7..fa2d0a978ccc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -470,19 +470,43 @@ static const struct drm_fb_helper_funcs nouveau_fbcon_helper_funcs = { .fb_probe = nouveau_fbcon_create, }; +static void +nouveau_fbcon_set_suspend_work(struct work_struct *work) +{ + struct nouveau_drm *drm = container_of(work, typeof(*drm), fbcon_work); + int state = READ_ONCE(drm->fbcon_new_state); + + if (state == FBINFO_STATE_RUNNING) + pm_runtime_get_sync(drm->dev->dev); + + console_lock(); + if (state == FBINFO_STATE_RUNNING) + nouveau_fbcon_accel_restore(drm->dev); + drm_fb_helper_set_suspend(&drm->fbcon->helper, state); + if (state != FBINFO_STATE_RUNNING) + nouveau_fbcon_accel_save_disable(drm->dev); + console_unlock(); + + if (state == FBINFO_STATE_RUNNING) { + pm_runtime_mark_last_busy(drm->dev->dev); + pm_runtime_put_sync(drm->dev->dev); + } +} + void nouveau_fbcon_set_suspend(struct drm_device *dev, int state) { struct nouveau_drm *drm = nouveau_drm(dev); - if (drm->fbcon) { - console_lock(); - if (state == FBINFO_STATE_RUNNING) - nouveau_fbcon_accel_restore(dev); - drm_fb_helper_set_suspend(&drm->fbcon->helper, state); - if (state != FBINFO_STATE_RUNNING) - nouveau_fbcon_accel_save_disable(dev); - console_unlock(); - } + + if (!drm->fbcon) + return; + + drm->fbcon_new_state = state; + /* Since runtime resume can happen as a result of a sysfs operation, + * it's possible we already have the console locked. So handle fbcon + * init/deinit from a seperate work thread + */ + schedule_work(&drm->fbcon_work); } int @@ -502,6 +526,7 @@ nouveau_fbcon_init(struct drm_device *dev) return -ENOMEM; drm->fbcon = fbcon; + INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work); drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs); diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 00ea0002b539..e0c143b865f3 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -366,11 +366,10 @@ static void radeon_pci_shutdown(struct pci_dev *pdev) { /* if we are running in a VM, make sure the device - * torn down properly on reboot/shutdown. - * unfortunately we can't detect certain - * hypervisors so just do this all the time. + * torn down properly on reboot/shutdown */ - radeon_pci_remove(pdev); + if (radeon_device_is_virtual()) + radeon_pci_remove(pdev); } static int radeon_pmops_suspend(struct device *dev) diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index e8a38d296855..414776811e71 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -114,6 +114,9 @@ MODULE_FIRMWARE("radeon/hainan_mc.bin"); MODULE_FIRMWARE("radeon/hainan_rlc.bin"); MODULE_FIRMWARE("radeon/hainan_smc.bin"); MODULE_FIRMWARE("radeon/hainan_k_smc.bin"); +MODULE_FIRMWARE("radeon/banks_k_2_smc.bin"); + +MODULE_FIRMWARE("radeon/si58_mc.bin"); static u32 si_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh); static void si_pcie_gen3_enable(struct radeon_device *rdev); @@ -1650,6 +1653,8 @@ static int si_init_microcode(struct radeon_device *rdev) int err; int new_fw = 0; bool new_smc = false; + bool si58_fw = false; + bool banks2_fw = false; DRM_DEBUG("\n"); @@ -1727,10 +1732,11 @@ static int si_init_microcode(struct radeon_device *rdev) ((rdev->pdev->device == 0x6660) || (rdev->pdev->device == 0x6663) || (rdev->pdev->device == 0x6665) || - (rdev->pdev->device == 0x6667))) || - ((rdev->pdev->revision == 0xc3) && - (rdev->pdev->device == 0x6665))) + (rdev->pdev->device == 0x6667)))) new_smc = true; + else if ((rdev->pdev->revision == 0xc3) && + (rdev->pdev->device == 0x6665)) + banks2_fw = true; new_chip_name = "hainan"; pfp_req_size = SI_PFP_UCODE_SIZE * 4; me_req_size = SI_PM4_UCODE_SIZE * 4; @@ -1742,6 +1748,10 @@ static int si_init_microcode(struct radeon_device *rdev) default: BUG(); } + /* this memory configuration requires special firmware */ + if (((RREG32(MC_SEQ_MISC0) & 0xff000000) >> 24) == 0x58) + si58_fw = true; + DRM_INFO("Loading %s Microcode\n", new_chip_name); snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", new_chip_name); @@ -1845,7 +1855,10 @@ static int si_init_microcode(struct radeon_device *rdev) } } - snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", new_chip_name); + if (si58_fw) + snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin"); + else + snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", new_chip_name); err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev); if (err) { snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc2.bin", chip_name); @@ -1876,7 +1889,9 @@ static int si_init_microcode(struct radeon_device *rdev) } } - if (new_smc) + if (banks2_fw) + snprintf(fw_name, sizeof(fw_name), "radeon/banks_k_2_smc.bin"); + else if (new_smc) snprintf(fw_name, sizeof(fw_name), "radeon/%s_k_smc.bin", new_chip_name); else snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", new_chip_name); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 13ba73fd9b68..2944916f7102 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -3008,17 +3008,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, (rdev->pdev->device == 0x6817) || (rdev->pdev->device == 0x6806)) max_mclk = 120000; - } else if (rdev->family == CHIP_OLAND) { - if ((rdev->pdev->revision == 0xC7) || - (rdev->pdev->revision == 0x80) || - (rdev->pdev->revision == 0x81) || - (rdev->pdev->revision == 0x83) || - (rdev->pdev->revision == 0x87) || - (rdev->pdev->device == 0x6604) || - (rdev->pdev->device == 0x6605)) { - max_sclk = 75000; - max_mclk = 80000; - } } else if (rdev->family == CHIP_HAINAN) { if ((rdev->pdev->revision == 0x81) || (rdev->pdev->revision == 0x83) || @@ -3027,7 +3016,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, (rdev->pdev->device == 0x6665) || (rdev->pdev->device == 0x6667)) { max_sclk = 75000; - max_mclk = 80000; } } /* Apply dpm quirks */ diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index a0fd3e66bc4b..7aadce1f7e7a 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -839,7 +839,7 @@ static void vc4_crtc_destroy_state(struct drm_crtc *crtc, } - __drm_atomic_helper_crtc_destroy_state(state); + drm_atomic_helper_crtc_destroy_state(crtc, state); } static const struct drm_crtc_funcs vc4_crtc_funcs = { diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index db920771bfb5..ab3016982466 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -594,12 +594,14 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec) args->shader_rec_count); struct vc4_bo *bo; - if (uniforms_offset < shader_rec_offset || + if (shader_rec_offset < args->bin_cl_size || + uniforms_offset < shader_rec_offset || exec_size < uniforms_offset || args->shader_rec_count >= (UINT_MAX / sizeof(struct vc4_shader_state)) || temp_size < exec_size) { DRM_ERROR("overflow in exec arguments\n"); + ret = -EINVAL; goto fail; } diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c index 08886a309757..5cdd003605f5 100644 --- a/drivers/gpu/drm/vc4/vc4_render_cl.c +++ b/drivers/gpu/drm/vc4/vc4_render_cl.c @@ -461,7 +461,7 @@ static int vc4_rcl_surface_setup(struct vc4_exec_info *exec, } ret = vc4_full_res_bounds_check(exec, *obj, surf); - if (!ret) + if (ret) return ret; return 0; diff --git a/drivers/gpu/drm/virtio/virtgpu_fb.c b/drivers/gpu/drm/virtio/virtgpu_fb.c index dd21f950e129..cde9f3758106 100644 --- a/drivers/gpu/drm/virtio/virtgpu_fb.c +++ b/drivers/gpu/drm/virtio/virtgpu_fb.c @@ -331,7 +331,7 @@ static int virtio_gpufb_create(struct drm_fb_helper *helper, info->fbops = &virtio_gpufb_ops; info->pixmap.flags = FB_PIXMAP_SYSTEM; - info->screen_base = obj->vmap; + info->screen_buffer = obj->vmap; info->screen_size = obj->gem_base.size; drm_fb_helper_fill_fix(info, fb->pitches[0], fb->depth); drm_fb_helper_fill_var(info, &vfbdev->helper, diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index 686971263bef..45d6771fac8c 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -962,10 +962,6 @@ static int cdns_i2c_probe(struct platform_device *pdev) goto err_clk_dis; } - ret = i2c_add_adapter(&id->adap); - if (ret < 0) - goto err_clk_dis; - /* * Cadence I2C controller has a bug wherein it generates * invalid read transaction after HW timeout in master receiver mode. @@ -975,6 +971,10 @@ static int cdns_i2c_probe(struct platform_device *pdev) */ cdns_i2c_writereg(CDNS_I2C_TIMEOUT_MAX, CDNS_I2C_TIME_OUT_OFFSET); + ret = i2c_add_adapter(&id->adap); + if (ret < 0) + goto err_clk_dis; + dev_info(&pdev->dev, "%u kHz mmio %08lx irq %d\n", id->i2c_clk / 1000, (unsigned long)r_mem->start, id->irq); diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index c62b7cd475f8..3310f2e0dbd3 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -636,12 +637,31 @@ static int lpi2c_imx_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +static int lpi2c_imx_suspend(struct device *dev) +{ + pinctrl_pm_select_sleep_state(dev); + + return 0; +} + +static int lpi2c_imx_resume(struct device *dev) +{ + pinctrl_pm_select_default_state(dev); + + return 0; +} +#endif + +static SIMPLE_DEV_PM_OPS(imx_lpi2c_pm, lpi2c_imx_suspend, lpi2c_imx_resume); + static struct platform_driver lpi2c_imx_driver = { .probe = lpi2c_imx_probe, .remove = lpi2c_imx_remove, .driver = { .name = DRIVER_NAME, .of_match_table = lpi2c_imx_of_match, + .pm = &imx_lpi2c_pm, }, }; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index e7dcfac877ca..3e70a9c5d79d 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2811,7 +2811,8 @@ static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, if (!src_addr || !src_addr->sa_family) { src_addr = (struct sockaddr *) &id->route.addr.src_addr; src_addr->sa_family = dst_addr->sa_family; - if (dst_addr->sa_family == AF_INET6) { + if (IS_ENABLED(CONFIG_IPV6) && + dst_addr->sa_family == AF_INET6) { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *) src_addr; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *) dst_addr; src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 1e62a5f0cb28..4609b921f899 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -134,6 +134,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND)); if (access & IB_ACCESS_ON_DEMAND) { + put_pid(umem->pid); ret = ib_umem_odp_get(context, umem); if (ret) { kfree(umem); @@ -149,6 +150,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, page_list = (struct page **) __get_free_page(GFP_KERNEL); if (!page_list) { + put_pid(umem->pid); kfree(umem); return ERR_PTR(-ENOMEM); } diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 9d5fe1853da4..6262dc035f3c 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -1135,16 +1135,7 @@ static int iwch_query_port(struct ib_device *ibdev, memset(props, 0, sizeof(struct ib_port_attr)); props->max_mtu = IB_MTU_4096; - if (netdev->mtu >= 4096) - props->active_mtu = IB_MTU_4096; - else if (netdev->mtu >= 2048) - props->active_mtu = IB_MTU_2048; - else if (netdev->mtu >= 1024) - props->active_mtu = IB_MTU_1024; - else if (netdev->mtu >= 512) - props->active_mtu = IB_MTU_512; - else - props->active_mtu = IB_MTU_256; + props->active_mtu = ib_mtu_int_to_enum(netdev->mtu); if (!netif_carrier_ok(netdev)) props->state = IB_PORT_DOWN; diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index f1510cc76d2d..9398143d7c5e 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1804,20 +1804,21 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb) skb_trim(skb, dlen); mutex_lock(&ep->com.mutex); - /* update RX credits */ - update_rx_credits(ep, dlen); - switch (ep->com.state) { case MPA_REQ_SENT: + update_rx_credits(ep, dlen); ep->rcv_seq += dlen; disconnect = process_mpa_reply(ep, skb); break; case MPA_REQ_WAIT: + update_rx_credits(ep, dlen); ep->rcv_seq += dlen; disconnect = process_mpa_request(ep, skb); break; case FPDU_MODE: { struct c4iw_qp_attributes attrs; + + update_rx_credits(ep, dlen); BUG_ON(!ep->com.qp); if (status) pr_err("%s Unexpected streaming data." \ diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index 19c6477af19f..bec82a600d77 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -504,6 +504,15 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe, goto skip_cqe; } + /* + * Special cqe for drain WR completions... + */ + if (CQE_OPCODE(hw_cqe) == C4IW_DRAIN_OPCODE) { + *cookie = CQE_DRAIN_COOKIE(hw_cqe); + *cqe = *hw_cqe; + goto skip_cqe; + } + /* * Gotta tweak READ completions: * 1) the cqe doesn't contain the sq_wptr from the wr. @@ -753,6 +762,9 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc) c4iw_invalidate_mr(qhp->rhp, CQE_WRID_FR_STAG(&cqe)); break; + case C4IW_DRAIN_OPCODE: + wc->opcode = IB_WC_SEND; + break; default: printk(KERN_ERR MOD "Unexpected opcode %d " "in the CQE received for QPID=0x%0x\n", @@ -817,15 +829,8 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc) } } out: - if (wq) { - if (unlikely(qhp->attr.state != C4IW_QP_STATE_RTS)) { - if (t4_sq_empty(wq)) - complete(&qhp->sq_drained); - if (t4_rq_empty(wq)) - complete(&qhp->rq_drained); - } + if (wq) spin_unlock(&qhp->lock); - } return ret; } diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c index 516b0ae6dc3f..40c0e7b9fc6e 100644 --- a/drivers/infiniband/hw/cxgb4/device.c +++ b/drivers/infiniband/hw/cxgb4/device.c @@ -846,9 +846,17 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev) } } + rdev->free_workq = create_singlethread_workqueue("iw_cxgb4_free"); + if (!rdev->free_workq) { + err = -ENOMEM; + goto err_free_status_page; + } + rdev->status_page->db_off = 0; return 0; +err_free_status_page: + free_page((unsigned long)rdev->status_page); destroy_ocqp_pool: c4iw_ocqp_pool_destroy(rdev); destroy_rqtpool: @@ -862,6 +870,7 @@ destroy_resource: static void c4iw_rdev_close(struct c4iw_rdev *rdev) { + destroy_workqueue(rdev->free_workq); kfree(rdev->wr_log); free_page((unsigned long)rdev->status_page); c4iw_pblpool_destroy(rdev); diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index 4788e1a46fde..8cd4d054a87e 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -45,6 +45,7 @@ #include #include #include +#include #include @@ -107,6 +108,7 @@ struct c4iw_dev_ucontext { struct list_head qpids; struct list_head cqids; struct mutex lock; + struct kref kref; }; enum c4iw_rdev_flags { @@ -183,6 +185,7 @@ struct c4iw_rdev { atomic_t wr_log_idx; struct wr_log_entry *wr_log; int wr_log_size; + struct workqueue_struct *free_workq; }; static inline int c4iw_fatal_error(struct c4iw_rdev *rdev) @@ -480,8 +483,8 @@ struct c4iw_qp { wait_queue_head_t wait; struct timer_list timer; int sq_sig_all; - struct completion rq_drained; - struct completion sq_drained; + struct work_struct free_work; + struct c4iw_ucontext *ucontext; }; static inline struct c4iw_qp *to_c4iw_qp(struct ib_qp *ibqp) @@ -495,6 +498,7 @@ struct c4iw_ucontext { u32 key; spinlock_t mmap_lock; struct list_head mmaps; + struct kref kref; }; static inline struct c4iw_ucontext *to_c4iw_ucontext(struct ib_ucontext *c) @@ -502,6 +506,18 @@ static inline struct c4iw_ucontext *to_c4iw_ucontext(struct ib_ucontext *c) return container_of(c, struct c4iw_ucontext, ibucontext); } +void _c4iw_free_ucontext(struct kref *kref); + +static inline void c4iw_put_ucontext(struct c4iw_ucontext *ucontext) +{ + kref_put(&ucontext->kref, _c4iw_free_ucontext); +} + +static inline void c4iw_get_ucontext(struct c4iw_ucontext *ucontext) +{ + kref_get(&ucontext->kref); +} + struct c4iw_mm_entry { struct list_head entry; u64 addr; @@ -615,6 +631,8 @@ static inline int to_ib_qp_state(int c4iw_qp_state) return IB_QPS_ERR; } +#define C4IW_DRAIN_OPCODE FW_RI_SGE_EC_CR_RETURN + static inline u32 c4iw_ib_to_tpt_access(int a) { return (a & IB_ACCESS_REMOTE_WRITE ? FW_RI_MEM_ACCESS_REM_WRITE : 0) | @@ -997,8 +1015,6 @@ extern int c4iw_wr_log; extern int db_fc_threshold; extern int db_coalescing_threshold; extern int use_dsgl; -void c4iw_drain_rq(struct ib_qp *qp); -void c4iw_drain_sq(struct ib_qp *qp); void c4iw_invalidate_mr(struct c4iw_dev *rhp, u32 rkey); #endif diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 49b51b7e0fd7..3345e1c312f7 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -93,17 +93,28 @@ static int c4iw_process_mad(struct ib_device *ibdev, int mad_flags, return -ENOSYS; } -static int c4iw_dealloc_ucontext(struct ib_ucontext *context) +void _c4iw_free_ucontext(struct kref *kref) { - struct c4iw_dev *rhp = to_c4iw_dev(context->device); - struct c4iw_ucontext *ucontext = to_c4iw_ucontext(context); + struct c4iw_ucontext *ucontext; + struct c4iw_dev *rhp; struct c4iw_mm_entry *mm, *tmp; - PDBG("%s context %p\n", __func__, context); + ucontext = container_of(kref, struct c4iw_ucontext, kref); + rhp = to_c4iw_dev(ucontext->ibucontext.device); + + PDBG("%s ucontext %p\n", __func__, ucontext); list_for_each_entry_safe(mm, tmp, &ucontext->mmaps, entry) kfree(mm); c4iw_release_dev_ucontext(&rhp->rdev, &ucontext->uctx); kfree(ucontext); +} + +static int c4iw_dealloc_ucontext(struct ib_ucontext *context) +{ + struct c4iw_ucontext *ucontext = to_c4iw_ucontext(context); + + PDBG("%s context %p\n", __func__, context); + c4iw_put_ucontext(ucontext); return 0; } @@ -127,6 +138,7 @@ static struct ib_ucontext *c4iw_alloc_ucontext(struct ib_device *ibdev, c4iw_init_dev_ucontext(&rhp->rdev, &context->uctx); INIT_LIST_HEAD(&context->mmaps); spin_lock_init(&context->mmap_lock); + kref_init(&context->kref); if (udata->outlen < sizeof(uresp) - sizeof(uresp.reserved)) { if (!warned++) @@ -361,16 +373,7 @@ static int c4iw_query_port(struct ib_device *ibdev, u8 port, memset(props, 0, sizeof(struct ib_port_attr)); props->max_mtu = IB_MTU_4096; - if (netdev->mtu >= 4096) - props->active_mtu = IB_MTU_4096; - else if (netdev->mtu >= 2048) - props->active_mtu = IB_MTU_2048; - else if (netdev->mtu >= 1024) - props->active_mtu = IB_MTU_1024; - else if (netdev->mtu >= 512) - props->active_mtu = IB_MTU_512; - else - props->active_mtu = IB_MTU_256; + props->active_mtu = ib_mtu_int_to_enum(netdev->mtu); if (!netif_carrier_ok(netdev)) props->state = IB_PORT_DOWN; @@ -607,8 +610,6 @@ int c4iw_register_device(struct c4iw_dev *dev) dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION; dev->ibdev.get_port_immutable = c4iw_port_immutable; dev->ibdev.get_dev_fw_str = get_dev_fw_str; - dev->ibdev.drain_sq = c4iw_drain_sq; - dev->ibdev.drain_rq = c4iw_drain_rq; dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL); if (!dev->ibdev.iwcm) diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index cda5542e13a2..04c1c382dedb 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -715,13 +715,32 @@ static int build_inv_stag(union t4_wr *wqe, struct ib_send_wr *wr, u8 *len16) return 0; } -static void _free_qp(struct kref *kref) +static void free_qp_work(struct work_struct *work) +{ + struct c4iw_ucontext *ucontext; + struct c4iw_qp *qhp; + struct c4iw_dev *rhp; + + qhp = container_of(work, struct c4iw_qp, free_work); + ucontext = qhp->ucontext; + rhp = qhp->rhp; + + PDBG("%s qhp %p ucontext %p\n", __func__, qhp, ucontext); + destroy_qp(&rhp->rdev, &qhp->wq, + ucontext ? &ucontext->uctx : &rhp->rdev.uctx); + + if (ucontext) + c4iw_put_ucontext(ucontext); + kfree(qhp); +} + +static void queue_qp_free(struct kref *kref) { struct c4iw_qp *qhp; qhp = container_of(kref, struct c4iw_qp, kref); PDBG("%s qhp %p\n", __func__, qhp); - kfree(qhp); + queue_work(qhp->rhp->rdev.free_workq, &qhp->free_work); } void c4iw_qp_add_ref(struct ib_qp *qp) @@ -733,7 +752,7 @@ void c4iw_qp_add_ref(struct ib_qp *qp) void c4iw_qp_rem_ref(struct ib_qp *qp) { PDBG("%s ib_qp %p\n", __func__, qp); - kref_put(&to_c4iw_qp(qp)->kref, _free_qp); + kref_put(&to_c4iw_qp(qp)->kref, queue_qp_free); } static void add_to_fc_list(struct list_head *head, struct list_head *entry) @@ -776,6 +795,64 @@ static int ring_kernel_rq_db(struct c4iw_qp *qhp, u16 inc) return 0; } +static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr) +{ + struct t4_cqe cqe = {}; + struct c4iw_cq *schp; + unsigned long flag; + struct t4_cq *cq; + + schp = to_c4iw_cq(qhp->ibqp.send_cq); + cq = &schp->cq; + + cqe.u.drain_cookie = wr->wr_id; + cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) | + CQE_OPCODE_V(C4IW_DRAIN_OPCODE) | + CQE_TYPE_V(1) | + CQE_SWCQE_V(1) | + CQE_QPID_V(qhp->wq.sq.qid)); + + spin_lock_irqsave(&schp->lock, flag); + cqe.bits_type_ts = cpu_to_be64(CQE_GENBIT_V((u64)cq->gen)); + cq->sw_queue[cq->sw_pidx] = cqe; + t4_swcq_produce(cq); + spin_unlock_irqrestore(&schp->lock, flag); + + spin_lock_irqsave(&schp->comp_handler_lock, flag); + (*schp->ibcq.comp_handler)(&schp->ibcq, + schp->ibcq.cq_context); + spin_unlock_irqrestore(&schp->comp_handler_lock, flag); +} + +static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr) +{ + struct t4_cqe cqe = {}; + struct c4iw_cq *rchp; + unsigned long flag; + struct t4_cq *cq; + + rchp = to_c4iw_cq(qhp->ibqp.recv_cq); + cq = &rchp->cq; + + cqe.u.drain_cookie = wr->wr_id; + cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) | + CQE_OPCODE_V(C4IW_DRAIN_OPCODE) | + CQE_TYPE_V(0) | + CQE_SWCQE_V(1) | + CQE_QPID_V(qhp->wq.sq.qid)); + + spin_lock_irqsave(&rchp->lock, flag); + cqe.bits_type_ts = cpu_to_be64(CQE_GENBIT_V((u64)cq->gen)); + cq->sw_queue[cq->sw_pidx] = cqe; + t4_swcq_produce(cq); + spin_unlock_irqrestore(&rchp->lock, flag); + + spin_lock_irqsave(&rchp->comp_handler_lock, flag); + (*rchp->ibcq.comp_handler)(&rchp->ibcq, + rchp->ibcq.cq_context); + spin_unlock_irqrestore(&rchp->comp_handler_lock, flag); +} + int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, struct ib_send_wr **bad_wr) { @@ -794,8 +871,8 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, spin_lock_irqsave(&qhp->lock, flag); if (t4_wq_in_error(&qhp->wq)) { spin_unlock_irqrestore(&qhp->lock, flag); - *bad_wr = wr; - return -EINVAL; + complete_sq_drain_wr(qhp, wr); + return err; } num_wrs = t4_sq_avail(&qhp->wq); if (num_wrs == 0) { @@ -937,8 +1014,8 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr, spin_lock_irqsave(&qhp->lock, flag); if (t4_wq_in_error(&qhp->wq)) { spin_unlock_irqrestore(&qhp->lock, flag); - *bad_wr = wr; - return -EINVAL; + complete_rq_drain_wr(qhp, wr); + return err; } num_wrs = t4_rq_avail(&qhp->wq); if (num_wrs == 0) { @@ -1550,7 +1627,12 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp, } break; case C4IW_QP_STATE_CLOSING: - if (!internal) { + + /* + * Allow kernel users to move to ERROR for qp draining. + */ + if (!internal && (qhp->ibqp.uobject || attrs->next_state != + C4IW_QP_STATE_ERROR)) { ret = -EINVAL; goto out; } @@ -1643,7 +1725,6 @@ int c4iw_destroy_qp(struct ib_qp *ib_qp) struct c4iw_dev *rhp; struct c4iw_qp *qhp; struct c4iw_qp_attributes attrs; - struct c4iw_ucontext *ucontext; qhp = to_c4iw_qp(ib_qp); rhp = qhp->rhp; @@ -1663,11 +1744,6 @@ int c4iw_destroy_qp(struct ib_qp *ib_qp) spin_unlock_irq(&rhp->lock); free_ird(rhp, qhp->attr.max_ird); - ucontext = ib_qp->uobject ? - to_c4iw_ucontext(ib_qp->uobject->context) : NULL; - destroy_qp(&rhp->rdev, &qhp->wq, - ucontext ? &ucontext->uctx : &rhp->rdev.uctx); - c4iw_qp_rem_ref(ib_qp); PDBG("%s ib_qp %p qpid 0x%0x\n", __func__, ib_qp, qhp->wq.sq.qid); @@ -1763,11 +1839,10 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs, qhp->attr.max_ird = 0; qhp->sq_sig_all = attrs->sq_sig_type == IB_SIGNAL_ALL_WR; spin_lock_init(&qhp->lock); - init_completion(&qhp->sq_drained); - init_completion(&qhp->rq_drained); mutex_init(&qhp->mutex); init_waitqueue_head(&qhp->wait); kref_init(&qhp->kref); + INIT_WORK(&qhp->free_work, free_qp_work); ret = insert_handle(rhp, &rhp->qpidr, qhp, qhp->wq.sq.qid); if (ret) @@ -1854,6 +1929,9 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs, ma_sync_key_mm->len = PAGE_SIZE; insert_mmap(ucontext, ma_sync_key_mm); } + + c4iw_get_ucontext(ucontext); + qhp->ucontext = ucontext; } qhp->ibqp.qp_num = qhp->wq.sq.qid; init_timer(&(qhp->timer)); @@ -1958,40 +2036,3 @@ int c4iw_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, init_attr->sq_sig_type = qhp->sq_sig_all ? IB_SIGNAL_ALL_WR : 0; return 0; } - -static void move_qp_to_err(struct c4iw_qp *qp) -{ - struct c4iw_qp_attributes attrs = { .next_state = C4IW_QP_STATE_ERROR }; - - (void)c4iw_modify_qp(qp->rhp, qp, C4IW_QP_ATTR_NEXT_STATE, &attrs, 1); -} - -void c4iw_drain_sq(struct ib_qp *ibqp) -{ - struct c4iw_qp *qp = to_c4iw_qp(ibqp); - unsigned long flag; - bool need_to_wait; - - move_qp_to_err(qp); - spin_lock_irqsave(&qp->lock, flag); - need_to_wait = !t4_sq_empty(&qp->wq); - spin_unlock_irqrestore(&qp->lock, flag); - - if (need_to_wait) - wait_for_completion(&qp->sq_drained); -} - -void c4iw_drain_rq(struct ib_qp *ibqp) -{ - struct c4iw_qp *qp = to_c4iw_qp(ibqp); - unsigned long flag; - bool need_to_wait; - - move_qp_to_err(qp); - spin_lock_irqsave(&qp->lock, flag); - need_to_wait = !t4_rq_empty(&qp->wq); - spin_unlock_irqrestore(&qp->lock, flag); - - if (need_to_wait) - wait_for_completion(&qp->rq_drained); -} diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h index 862381aa83c8..640d22148a3e 100644 --- a/drivers/infiniband/hw/cxgb4/t4.h +++ b/drivers/infiniband/hw/cxgb4/t4.h @@ -179,6 +179,7 @@ struct t4_cqe { __be32 wrid_hi; __be32 wrid_low; } gen; + u64 drain_cookie; } u; __be64 reserved; __be64 bits_type_ts; @@ -238,6 +239,7 @@ struct t4_cqe { /* generic accessor macros */ #define CQE_WRID_HI(x) (be32_to_cpu((x)->u.gen.wrid_hi)) #define CQE_WRID_LOW(x) (be32_to_cpu((x)->u.gen.wrid_low)) +#define CQE_DRAIN_COOKIE(x) ((x)->u.drain_cookie) /* macros for flit 3 of the cqe */ #define CQE_GENBIT_S 63 diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 29e97df9e1a7..4c000d60d5c6 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -100,16 +100,7 @@ static int i40iw_query_port(struct ib_device *ibdev, memset(props, 0, sizeof(*props)); props->max_mtu = IB_MTU_4096; - if (netdev->mtu >= 4096) - props->active_mtu = IB_MTU_4096; - else if (netdev->mtu >= 2048) - props->active_mtu = IB_MTU_2048; - else if (netdev->mtu >= 1024) - props->active_mtu = IB_MTU_1024; - else if (netdev->mtu >= 512) - props->active_mtu = IB_MTU_512; - else - props->active_mtu = IB_MTU_256; + props->active_mtu = ib_mtu_int_to_enum(netdev->mtu); props->lid = 1; if (netif_carrier_ok(iwdev->netdev)) diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index aff9fb14768b..5a31f3c6a421 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -478,17 +478,7 @@ static int nes_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr memset(props, 0, sizeof(*props)); props->max_mtu = IB_MTU_4096; - - if (netdev->mtu >= 4096) - props->active_mtu = IB_MTU_4096; - else if (netdev->mtu >= 2048) - props->active_mtu = IB_MTU_2048; - else if (netdev->mtu >= 1024) - props->active_mtu = IB_MTU_1024; - else if (netdev->mtu >= 512) - props->active_mtu = IB_MTU_512; - else - props->active_mtu = IB_MTU_256; + props->active_mtu = ib_mtu_int_to_enum(netdev->mtu); props->lid = 1; props->lmc = 0; diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 7b74d09a8217..3ac8aa5ef37d 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -576,8 +576,7 @@ static int qedr_set_device_attr(struct qedr_dev *dev) return 0; } -void qedr_unaffiliated_event(void *context, - u8 event_code) +void qedr_unaffiliated_event(void *context, u8 event_code) { pr_err("unaffiliated event not implemented yet\n"); } @@ -792,6 +791,9 @@ static struct qedr_dev *qedr_add(struct qed_dev *cdev, struct pci_dev *pdev, if (device_create_file(&dev->ibdev.dev, qedr_attributes[i])) goto sysfs_err; + if (!test_and_set_bit(QEDR_ENET_STATE_BIT, &dev->enet_state)) + qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ACTIVE); + DP_DEBUG(dev, QEDR_MSG_INIT, "qedr driver loaded successfully\n"); return dev; @@ -824,11 +826,10 @@ static void qedr_remove(struct qedr_dev *dev) ib_dealloc_device(&dev->ibdev); } -static int qedr_close(struct qedr_dev *dev) +static void qedr_close(struct qedr_dev *dev) { - qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ERR); - - return 0; + if (test_and_clear_bit(QEDR_ENET_STATE_BIT, &dev->enet_state)) + qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ERR); } static void qedr_shutdown(struct qedr_dev *dev) @@ -837,6 +838,12 @@ static void qedr_shutdown(struct qedr_dev *dev) qedr_remove(dev); } +static void qedr_open(struct qedr_dev *dev) +{ + if (!test_and_set_bit(QEDR_ENET_STATE_BIT, &dev->enet_state)) + qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ACTIVE); +} + static void qedr_mac_address_change(struct qedr_dev *dev) { union ib_gid *sgid = &dev->sgid_tbl[0]; @@ -863,7 +870,7 @@ static void qedr_mac_address_change(struct qedr_dev *dev) ether_addr_copy(dev->gsi_ll2_mac_address, dev->ndev->dev_addr); - qedr_ib_dispatch_event(dev, 1, IB_EVENT_GID_CHANGE); + qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_GID_CHANGE); if (rc) DP_ERR(dev, "Error updating mac filter\n"); @@ -877,7 +884,7 @@ static void qedr_notify(struct qedr_dev *dev, enum qede_roce_event event) { switch (event) { case QEDE_UP: - qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE); + qedr_open(dev); break; case QEDE_DOWN: qedr_close(dev); diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index 620badd7d4fb..bb32e4792ec9 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -113,6 +113,8 @@ struct qedr_device_attr { struct qed_rdma_events events; }; +#define QEDR_ENET_STATE_BIT (0) + struct qedr_dev { struct ib_device ibdev; struct qed_dev *cdev; @@ -153,6 +155,8 @@ struct qedr_dev { struct qedr_cq *gsi_sqcq; struct qedr_cq *gsi_rqcq; struct qedr_qp *gsi_qp; + + unsigned long enet_state; }; #define QEDR_MAX_SQ_PBL (0x8000) @@ -188,6 +192,7 @@ struct qedr_dev { #define QEDR_ROCE_MAX_CNQ_SIZE (0x4000) #define QEDR_MAX_PORT (1) +#define QEDR_PORT (1) #define QEDR_UVERBS(CMD_NAME) (1ull << IB_USER_VERBS_CMD_##CMD_NAME) @@ -251,9 +256,6 @@ struct qedr_cq { u16 icid; - /* Lock to protect completion handler */ - spinlock_t comp_handler_lock; - /* Lock to protect multiplem CQ's */ spinlock_t cq_lock; u8 arm_flags; diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c index 63890ebb72bd..a9a8d8745d2e 100644 --- a/drivers/infiniband/hw/qedr/qedr_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_cm.c @@ -87,11 +87,8 @@ void qedr_ll2_tx_cb(void *_qdev, struct qed_roce_ll2_packet *pkt) qedr_inc_sw_gsi_cons(&qp->sq); spin_unlock_irqrestore(&qp->q_lock, flags); - if (cq->ibcq.comp_handler) { - spin_lock_irqsave(&cq->comp_handler_lock, flags); + if (cq->ibcq.comp_handler) (*cq->ibcq.comp_handler) (&cq->ibcq, cq->ibcq.cq_context); - spin_unlock_irqrestore(&cq->comp_handler_lock, flags); - } } void qedr_ll2_rx_cb(void *_dev, struct qed_roce_ll2_packet *pkt, @@ -113,11 +110,8 @@ void qedr_ll2_rx_cb(void *_dev, struct qed_roce_ll2_packet *pkt, spin_unlock_irqrestore(&qp->q_lock, flags); - if (cq->ibcq.comp_handler) { - spin_lock_irqsave(&cq->comp_handler_lock, flags); + if (cq->ibcq.comp_handler) (*cq->ibcq.comp_handler) (&cq->ibcq, cq->ibcq.cq_context); - spin_unlock_irqrestore(&cq->comp_handler_lock, flags); - } } static void qedr_destroy_gsi_cq(struct qedr_dev *dev, @@ -404,9 +398,9 @@ static inline int qedr_gsi_build_packet(struct qedr_dev *dev, } if (ether_addr_equal(udh.eth.smac_h, udh.eth.dmac_h)) - packet->tx_dest = QED_ROCE_LL2_TX_DEST_NW; - else packet->tx_dest = QED_ROCE_LL2_TX_DEST_LB; + else + packet->tx_dest = QED_ROCE_LL2_TX_DEST_NW; packet->roce_mode = roce_mode; memcpy(packet->header.vaddr, ud_header_buffer, header_size); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 57c8de208077..c7d6c9a783bd 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -471,8 +471,6 @@ struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev, struct ib_ucontext *context, struct ib_udata *udata) { struct qedr_dev *dev = get_qedr_dev(ibdev); - struct qedr_ucontext *uctx = NULL; - struct qedr_alloc_pd_uresp uresp; struct qedr_pd *pd; u16 pd_id; int rc; @@ -489,21 +487,33 @@ struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev, if (!pd) return ERR_PTR(-ENOMEM); - dev->ops->rdma_alloc_pd(dev->rdma_ctx, &pd_id); + rc = dev->ops->rdma_alloc_pd(dev->rdma_ctx, &pd_id); + if (rc) + goto err; - uresp.pd_id = pd_id; pd->pd_id = pd_id; if (udata && context) { + struct qedr_alloc_pd_uresp uresp; + + uresp.pd_id = pd_id; + rc = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); - if (rc) + if (rc) { DP_ERR(dev, "copy error pd_id=0x%x.\n", pd_id); - uctx = get_qedr_ucontext(context); - uctx->pd = pd; - pd->uctx = uctx; + dev->ops->rdma_dealloc_pd(dev->rdma_ctx, pd_id); + goto err; + } + + pd->uctx = get_qedr_ucontext(context); + pd->uctx->pd = pd; } return &pd->ibpd; + +err: + kfree(pd); + return ERR_PTR(rc); } int qedr_dealloc_pd(struct ib_pd *ibpd) @@ -1600,7 +1610,7 @@ err0: return ERR_PTR(-EFAULT); } -enum ib_qp_state qedr_get_ibqp_state(enum qed_roce_qp_state qp_state) +static enum ib_qp_state qedr_get_ibqp_state(enum qed_roce_qp_state qp_state) { switch (qp_state) { case QED_ROCE_QP_STATE_RESET: @@ -1621,7 +1631,8 @@ enum ib_qp_state qedr_get_ibqp_state(enum qed_roce_qp_state qp_state) return IB_QPS_ERR; } -enum qed_roce_qp_state qedr_get_state_from_ibqp(enum ib_qp_state qp_state) +static enum qed_roce_qp_state qedr_get_state_from_ibqp( + enum ib_qp_state qp_state) { switch (qp_state) { case IB_QPS_RESET: @@ -1657,7 +1668,7 @@ static int qedr_update_qp_state(struct qedr_dev *dev, int status = 0; if (new_state == qp->state) - return 1; + return 0; switch (qp->state) { case QED_ROCE_QP_STATE_RESET: @@ -1733,6 +1744,14 @@ static int qedr_update_qp_state(struct qedr_dev *dev, /* ERR->XXX */ switch (new_state) { case QED_ROCE_QP_STATE_RESET: + if ((qp->rq.prod != qp->rq.cons) || + (qp->sq.prod != qp->sq.cons)) { + DP_NOTICE(dev, + "Error->Reset with rq/sq not empty rq.prod=%x rq.cons=%x sq.prod=%x sq.cons=%x\n", + qp->rq.prod, qp->rq.cons, qp->sq.prod, + qp->sq.cons); + status = -EINVAL; + } break; default: status = -EINVAL; @@ -1865,7 +1884,6 @@ int qedr_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, qp_params.sgid.dwords[2], qp_params.sgid.dwords[3]); DP_DEBUG(dev, QEDR_MSG_QP, "remote_mac=[%pM]\n", qp_params.remote_mac_addr); -; qp_params.mtu = qp->mtu; qp_params.lb_indication = false; @@ -2016,7 +2034,7 @@ int qedr_query_qp(struct ib_qp *ibqp, qp_attr->qp_state = qedr_get_ibqp_state(params.state); qp_attr->cur_qp_state = qedr_get_ibqp_state(params.state); - qp_attr->path_mtu = iboe_get_mtu(params.mtu); + qp_attr->path_mtu = ib_mtu_int_to_enum(params.mtu); qp_attr->path_mig_state = IB_MIG_MIGRATED; qp_attr->rq_psn = params.rq_psn; qp_attr->sq_psn = params.sq_psn; @@ -2028,7 +2046,7 @@ int qedr_query_qp(struct ib_qp *ibqp, qp_attr->cap.max_recv_wr = qp->rq.max_wr; qp_attr->cap.max_send_sge = qp->sq.max_sges; qp_attr->cap.max_recv_sge = qp->rq.max_sges; - qp_attr->cap.max_inline_data = qp->max_inline_data; + qp_attr->cap.max_inline_data = ROCE_REQ_MAX_INLINE_DATA_SIZE; qp_init_attr->cap = qp_attr->cap; memcpy(&qp_attr->ah_attr.grh.dgid.raw[0], ¶ms.dgid.bytes[0], @@ -2302,7 +2320,8 @@ int qedr_dereg_mr(struct ib_mr *ib_mr) return rc; } -struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd, int max_page_list_len) +static struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd, + int max_page_list_len) { struct qedr_pd *pd = get_qedr_pd(ibpd); struct qedr_dev *dev = get_qedr_dev(ibpd->device); @@ -2704,7 +2723,7 @@ static int qedr_prepare_reg(struct qedr_qp *qp, return 0; } -enum ib_wc_opcode qedr_ib_to_wc_opcode(enum ib_wr_opcode opcode) +static enum ib_wc_opcode qedr_ib_to_wc_opcode(enum ib_wr_opcode opcode) { switch (opcode) { case IB_WR_RDMA_WRITE: @@ -2729,7 +2748,7 @@ enum ib_wc_opcode qedr_ib_to_wc_opcode(enum ib_wr_opcode opcode) } } -inline bool qedr_can_post_send(struct qedr_qp *qp, struct ib_send_wr *wr) +static inline bool qedr_can_post_send(struct qedr_qp *qp, struct ib_send_wr *wr) { int wq_is_full, err_wr, pbl_is_full; struct qedr_dev *dev = qp->dev; @@ -2766,7 +2785,7 @@ inline bool qedr_can_post_send(struct qedr_qp *qp, struct ib_send_wr *wr) return true; } -int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, +static int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, struct ib_send_wr **bad_wr) { struct qedr_dev *dev = get_qedr_dev(ibqp->device); @@ -3234,9 +3253,10 @@ static int qedr_poll_cq_req(struct qedr_dev *dev, IB_WC_SUCCESS, 0); break; case RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR: - DP_ERR(dev, - "Error: POLL CQ with RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR. CQ icid=0x%x, QP icid=0x%x\n", - cq->icid, qp->icid); + if (qp->state != QED_ROCE_QP_STATE_ERR) + DP_ERR(dev, + "Error: POLL CQ with RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR. CQ icid=0x%x, QP icid=0x%x\n", + cq->icid, qp->icid); cnt = process_req(dev, qp, cq, num_entries, wc, req->sq_cons, IB_WC_WR_FLUSH_ERR, 1); break; diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index 231a1ce1f4be..bd8fbd3d2032 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -1029,7 +1029,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev, if (ret) { dev_err(&pdev->dev, "failed to allocate interrupts\n"); ret = -ENOMEM; - goto err_netdevice; + goto err_free_cq_ring; } /* Allocate UAR table. */ @@ -1092,8 +1092,6 @@ err_free_uar_table: err_free_intrs: pvrdma_free_irq(dev); pvrdma_disable_msi_all(dev); -err_netdevice: - unregister_netdevice_notifier(&dev->nb_netdev); err_free_cq_ring: pvrdma_page_dir_cleanup(dev, &dev->cq_pdir); err_free_async_ring: diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c index 54891370d18a..c2aa52638dcb 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c @@ -306,7 +306,7 @@ struct ib_ucontext *pvrdma_alloc_ucontext(struct ib_device *ibdev, union pvrdma_cmd_resp rsp; struct pvrdma_cmd_create_uc *cmd = &req.create_uc; struct pvrdma_cmd_create_uc_resp *resp = &rsp.create_uc_resp; - struct pvrdma_alloc_ucontext_resp uresp; + struct pvrdma_alloc_ucontext_resp uresp = {0}; int ret; void *ptr; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 342e78163613..4abdeb359fb4 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -555,7 +555,7 @@ struct rxe_dev *rxe_net_add(struct net_device *ndev) } spin_lock_bh(&dev_list_lock); - list_add_tail(&rxe_dev_list, &rxe->list); + list_add_tail(&rxe->list, &rxe_dev_list); spin_unlock_bh(&dev_list_lock); return rxe; } diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 486d576e55bc..44b2108253bd 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -813,8 +813,7 @@ void rxe_qp_destroy(struct rxe_qp *qp) del_timer_sync(&qp->rnr_nak_timer); rxe_cleanup_task(&qp->req.task); - if (qp_type(qp) == IB_QPT_RC) - rxe_cleanup_task(&qp->comp.task); + rxe_cleanup_task(&qp->comp.task); /* flush out any receive wr's or pending requests */ __rxe_do_task(&qp->req.task); diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c index 9104e6b8cac9..e71af717e71b 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.c +++ b/drivers/infiniband/ulp/iser/iscsi_iser.c @@ -651,13 +651,6 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, SHOST_DIX_GUARD_CRC); } - /* - * Limit the sg_tablesize and max_sectors based on the device - * max fastreg page list length. - */ - shost->sg_tablesize = min_t(unsigned short, shost->sg_tablesize, - ib_conn->device->ib_device->attrs.max_fast_reg_page_list_len); - if (iscsi_host_add(shost, ib_conn->device->ib_device->dma_device)) { mutex_unlock(&iser_conn->state_mutex); @@ -679,6 +672,10 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, max_fr_sectors = ((shost->sg_tablesize - 1) * PAGE_SIZE) >> 9; shost->max_sectors = min(iser_max_sectors, max_fr_sectors); + iser_dbg("iser_conn %p, sg_tablesize %u, max_sectors %u\n", + iser_conn, shost->sg_tablesize, + shost->max_sectors); + if (cmds_max > max_cmds) { iser_info("cmds_max changed from %u to %u\n", cmds_max, max_cmds); diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h index 0be6a7c5ddb5..9d0b22ad58c1 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.h +++ b/drivers/infiniband/ulp/iser/iscsi_iser.h @@ -496,7 +496,6 @@ struct ib_conn { * @rx_descs: rx buffers array (cyclic buffer) * @num_rx_descs: number of rx descriptors * @scsi_sg_tablesize: scsi host sg_tablesize - * @scsi_max_sectors: scsi host max sectors */ struct iser_conn { struct ib_conn ib_conn; @@ -519,7 +518,6 @@ struct iser_conn { struct iser_rx_desc *rx_descs; u32 num_rx_descs; unsigned short scsi_sg_tablesize; - unsigned int scsi_max_sectors; bool snd_w_inv; }; diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index 8ae7a3beddb7..6a9d1cb548ee 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -707,18 +707,7 @@ iser_calc_scsi_params(struct iser_conn *iser_conn, sup_sg_tablesize = min_t(unsigned, ISCSI_ISER_MAX_SG_TABLESIZE, device->ib_device->attrs.max_fast_reg_page_list_len); - if (sg_tablesize > sup_sg_tablesize) { - sg_tablesize = sup_sg_tablesize; - iser_conn->scsi_max_sectors = sg_tablesize * SIZE_4K / 512; - } else { - iser_conn->scsi_max_sectors = max_sectors; - } - - iser_conn->scsi_sg_tablesize = sg_tablesize; - - iser_dbg("iser_conn %p, sg_tablesize %u, max_sectors %u\n", - iser_conn, iser_conn->scsi_sg_tablesize, - iser_conn->scsi_max_sectors); + iser_conn->scsi_sg_tablesize = min(sg_tablesize, sup_sg_tablesize); } /** diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 8ddc07123193..79bf48477ddb 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -371,6 +371,7 @@ static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device, struct srp_fr_desc *d; struct ib_mr *mr; int i, ret = -EINVAL; + enum ib_mr_type mr_type; if (pool_size <= 0) goto err; @@ -384,9 +385,13 @@ static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device, spin_lock_init(&pool->lock); INIT_LIST_HEAD(&pool->free_list); + if (device->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG) + mr_type = IB_MR_TYPE_SG_GAPS; + else + mr_type = IB_MR_TYPE_MEM_REG; + for (i = 0, d = &pool->desc[0]; i < pool->size; i++, d++) { - mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, - max_page_list_len); + mr = ib_alloc_mr(pd, mr_type, max_page_list_len); if (IS_ERR(mr)) { ret = PTR_ERR(mr); if (ret == -ENOMEM) @@ -3694,6 +3699,12 @@ static int __init srp_init_module(void) indirect_sg_entries = cmd_sg_entries; } + if (indirect_sg_entries > SG_MAX_SEGMENTS) { + pr_warn("Clamping indirect_sg_entries to %u\n", + SG_MAX_SEGMENTS); + indirect_sg_entries = SG_MAX_SEGMENTS; + } + srp_remove_wq = create_workqueue("srp_remove"); if (!srp_remove_wq) { ret = -ENOMEM; diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c index 1a1d99704fe6..296f1411fe84 100644 --- a/drivers/isdn/hardware/eicon/message.c +++ b/drivers/isdn/hardware/eicon/message.c @@ -11297,7 +11297,8 @@ static void mixer_notify_update(PLCI *plci, byte others) ((CAPI_MSG *) msg)->header.ncci = 0; ((CAPI_MSG *) msg)->info.facility_req.Selector = SELECTOR_LINE_INTERCONNECT; ((CAPI_MSG *) msg)->info.facility_req.structs[0] = 3; - PUT_WORD(&(((CAPI_MSG *) msg)->info.facility_req.structs[1]), LI_REQ_SILENT_UPDATE); + ((CAPI_MSG *) msg)->info.facility_req.structs[1] = LI_REQ_SILENT_UPDATE & 0xff; + ((CAPI_MSG *) msg)->info.facility_req.structs[2] = LI_REQ_SILENT_UPDATE >> 8; ((CAPI_MSG *) msg)->info.facility_req.structs[3] = 0; w = api_put(notify_plci->appl, (CAPI_MSG *) msg); if (w != _QUEUE_FULL) diff --git a/drivers/md/md.c b/drivers/md/md.c index 82821ee0d57f..01175dac0db6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5291,6 +5291,11 @@ int md_run(struct mddev *mddev) if (start_readonly && mddev->ro == 0) mddev->ro = 2; /* read-only, but switch on first write */ + /* + * NOTE: some pers->run(), for example r5l_recovery_log(), wakes + * up mddev->thread. It is important to initialize critical + * resources for mddev->thread BEFORE calling pers->run(). + */ err = pers->run(mddev); if (err) pr_warn("md: pers->run() failed ...\n"); diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 0e8ed2c327b0..302dea3296ba 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -162,6 +162,8 @@ struct r5l_log { /* to submit async io_units, to fulfill ordering of flush */ struct work_struct deferred_io_work; + /* to disable write back during in degraded mode */ + struct work_struct disable_writeback_work; }; /* @@ -611,6 +613,21 @@ static void r5l_submit_io_async(struct work_struct *work) r5l_do_submit_io(log, io); } +static void r5c_disable_writeback_async(struct work_struct *work) +{ + struct r5l_log *log = container_of(work, struct r5l_log, + disable_writeback_work); + struct mddev *mddev = log->rdev->mddev; + + if (log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH) + return; + pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n", + mdname(mddev)); + mddev_suspend(mddev); + log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH; + mddev_resume(mddev); +} + static void r5l_submit_current_io(struct r5l_log *log) { struct r5l_io_unit *io = log->current_io; @@ -1393,8 +1410,6 @@ static void r5l_do_reclaim(struct r5l_log *log) next_checkpoint = r5c_calculate_new_cp(conf); spin_unlock_irq(&log->io_list_lock); - BUG_ON(reclaimable < 0); - if (reclaimable == 0 || !write_super) return; @@ -2062,7 +2077,7 @@ static int r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log, struct r5l_recovery_ctx *ctx) { - struct stripe_head *sh, *next; + struct stripe_head *sh; struct mddev *mddev = log->rdev->mddev; struct page *page; sector_t next_checkpoint = MaxSector; @@ -2076,7 +2091,7 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log, WARN_ON(list_empty(&ctx->cached_list)); - list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) { + list_for_each_entry(sh, &ctx->cached_list, lru) { struct r5l_meta_block *mb; int i; int offset; @@ -2126,14 +2141,39 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log, ctx->pos = write_pos; ctx->seq += 1; next_checkpoint = sh->log_start; - list_del_init(&sh->lru); - raid5_release_stripe(sh); } log->next_checkpoint = next_checkpoint; __free_page(page); return 0; } +static void r5c_recovery_flush_data_only_stripes(struct r5l_log *log, + struct r5l_recovery_ctx *ctx) +{ + struct mddev *mddev = log->rdev->mddev; + struct r5conf *conf = mddev->private; + struct stripe_head *sh, *next; + + if (ctx->data_only_stripes == 0) + return; + + log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_BACK; + + list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) { + r5c_make_stripe_write_out(sh); + set_bit(STRIPE_HANDLE, &sh->state); + list_del_init(&sh->lru); + raid5_release_stripe(sh); + } + + md_wakeup_thread(conf->mddev->thread); + /* reuse conf->wait_for_quiescent in recovery */ + wait_event(conf->wait_for_quiescent, + atomic_read(&conf->active_stripes) == 0); + + log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH; +} + static int r5l_recovery_log(struct r5l_log *log) { struct mddev *mddev = log->rdev->mddev; @@ -2160,32 +2200,31 @@ static int r5l_recovery_log(struct r5l_log *log) pos = ctx.pos; ctx.seq += 10000; - if (ctx.data_only_stripes == 0) { - log->next_checkpoint = ctx.pos; - r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++); - ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS); - } if ((ctx.data_only_stripes == 0) && (ctx.data_parity_stripes == 0)) pr_debug("md/raid:%s: starting from clean shutdown\n", mdname(mddev)); - else { + else pr_debug("md/raid:%s: recovering %d data-only stripes and %d data-parity stripes\n", mdname(mddev), ctx.data_only_stripes, ctx.data_parity_stripes); - if (ctx.data_only_stripes > 0) - if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) { - pr_err("md/raid:%s: failed to rewrite stripes to journal\n", - mdname(mddev)); - return -EIO; - } + if (ctx.data_only_stripes == 0) { + log->next_checkpoint = ctx.pos; + r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++); + ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS); + } else if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) { + pr_err("md/raid:%s: failed to rewrite stripes to journal\n", + mdname(mddev)); + return -EIO; } log->log_start = ctx.pos; log->seq = ctx.seq; log->last_checkpoint = pos; r5l_write_super(log, pos); + + r5c_recovery_flush_data_only_stripes(log, &ctx); return 0; } @@ -2247,6 +2286,10 @@ static ssize_t r5c_journal_mode_store(struct mddev *mddev, val > R5C_JOURNAL_MODE_WRITE_BACK) return -EINVAL; + if (raid5_calc_degraded(conf) > 0 && + val == R5C_JOURNAL_MODE_WRITE_BACK) + return -EINVAL; + mddev_suspend(mddev); conf->log->r5c_journal_mode = val; mddev_resume(mddev); @@ -2301,6 +2344,16 @@ int r5c_try_caching_write(struct r5conf *conf, set_bit(STRIPE_R5C_CACHING, &sh->state); } + /* + * When run in degraded mode, array is set to write-through mode. + * This check helps drain pending write safely in the transition to + * write-through mode. + */ + if (s->failed) { + r5c_make_stripe_write_out(sh); + return -EAGAIN; + } + for (i = disks; i--; ) { dev = &sh->dev[i]; /* if non-overwrite, use writing-out phase */ @@ -2351,6 +2404,8 @@ void r5c_release_extra_page(struct stripe_head *sh) struct page *p = sh->dev[i].orig_page; sh->dev[i].orig_page = sh->dev[i].page; + clear_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags); + if (!using_disk_info_extra_page) put_page(p); } @@ -2555,6 +2610,19 @@ ioerr: return ret; } +void r5c_update_on_rdev_error(struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + struct r5l_log *log = conf->log; + + if (!log) + return; + + if (raid5_calc_degraded(conf) > 0 && + conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK) + schedule_work(&log->disable_writeback_work); +} + int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) { struct request_queue *q = bdev_get_queue(rdev->bdev); @@ -2627,6 +2695,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) spin_lock_init(&log->no_space_stripes_lock); INIT_WORK(&log->deferred_io_work, r5l_submit_io_async); + INIT_WORK(&log->disable_writeback_work, r5c_disable_writeback_async); log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH; INIT_LIST_HEAD(&log->stripe_in_journal_list); @@ -2659,6 +2728,7 @@ io_kc: void r5l_exit_log(struct r5l_log *log) { + flush_work(&log->disable_writeback_work); md_unregister_thread(&log->reclaim_thread); mempool_destroy(log->meta_pool); bioset_free(log->bs); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 36c13e4be9c9..3c7e106c12a2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -556,7 +556,7 @@ static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, * of the two sections, and some non-in_sync devices may * be insync in the section most affected by failed devices. */ -static int calc_degraded(struct r5conf *conf) +int raid5_calc_degraded(struct r5conf *conf) { int degraded, degraded2; int i; @@ -619,7 +619,7 @@ static int has_failed(struct r5conf *conf) if (conf->mddev->reshape_position == MaxSector) return conf->mddev->degraded > conf->max_degraded; - degraded = calc_degraded(conf); + degraded = raid5_calc_degraded(conf); if (degraded > conf->max_degraded) return 1; return 0; @@ -1015,7 +1015,17 @@ again: if (test_bit(R5_SkipCopy, &sh->dev[i].flags)) WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags)); - sh->dev[i].vec.bv_page = sh->dev[i].page; + + if (!op_is_write(op) && + test_bit(R5_InJournal, &sh->dev[i].flags)) + /* + * issuing read for a page in journal, this + * must be preparing for prexor in rmw; read + * the data into orig_page + */ + sh->dev[i].vec.bv_page = sh->dev[i].orig_page; + else + sh->dev[i].vec.bv_page = sh->dev[i].page; bi->bi_vcnt = 1; bi->bi_io_vec[0].bv_len = STRIPE_SIZE; bi->bi_io_vec[0].bv_offset = 0; @@ -2380,6 +2390,13 @@ static void raid5_end_read_request(struct bio * bi) } else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) clear_bit(R5_ReadNoMerge, &sh->dev[i].flags); + if (test_bit(R5_InJournal, &sh->dev[i].flags)) + /* + * end read for a page in journal, this + * must be preparing for prexor in rmw + */ + set_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags); + if (atomic_read(&rdev->read_errors)) atomic_set(&rdev->read_errors, 0); } else { @@ -2538,7 +2555,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) spin_lock_irqsave(&conf->device_lock, flags); clear_bit(In_sync, &rdev->flags); - mddev->degraded = calc_degraded(conf); + mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irqrestore(&conf->device_lock, flags); set_bit(MD_RECOVERY_INTR, &mddev->recovery); @@ -2552,6 +2569,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) bdevname(rdev->bdev, b), mdname(mddev), conf->raid_disks - mddev->degraded); + r5c_update_on_rdev_error(mddev); } /* @@ -2880,6 +2898,30 @@ sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous) return r_sector; } +/* + * There are cases where we want handle_stripe_dirtying() and + * schedule_reconstruction() to delay towrite to some dev of a stripe. + * + * This function checks whether we want to delay the towrite. Specifically, + * we delay the towrite when: + * + * 1. degraded stripe has a non-overwrite to the missing dev, AND this + * stripe has data in journal (for other devices). + * + * In this case, when reading data for the non-overwrite dev, it is + * necessary to handle complex rmw of write back cache (prexor with + * orig_page, and xor with page). To keep read path simple, we would + * like to flush data in journal to RAID disks first, so complex rmw + * is handled in the write patch (handle_stripe_dirtying). + * + */ +static inline bool delay_towrite(struct r5dev *dev, + struct stripe_head_state *s) +{ + return !test_bit(R5_OVERWRITE, &dev->flags) && + !test_bit(R5_Insync, &dev->flags) && s->injournal; +} + static void schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, int rcw, int expand) @@ -2900,7 +2942,7 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - if (dev->towrite) { + if (dev->towrite && !delay_towrite(dev, s)) { set_bit(R5_LOCKED, &dev->flags); set_bit(R5_Wantdrain, &dev->flags); if (!expand) @@ -3295,13 +3337,6 @@ static int want_replace(struct stripe_head *sh, int disk_idx) return rv; } -/* fetch_block - checks the given member device to see if its data needs - * to be read or computed to satisfy a request. - * - * Returns 1 when no more member devices need to be checked, otherwise returns - * 0 to tell the loop in handle_stripe_fill to continue - */ - static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s, int disk_idx, int disks) { @@ -3392,6 +3427,12 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s, return 0; } +/* fetch_block - checks the given member device to see if its data needs + * to be read or computed to satisfy a request. + * + * Returns 1 when no more member devices need to be checked, otherwise returns + * 0 to tell the loop in handle_stripe_fill to continue + */ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s, int disk_idx, int disks) { @@ -3478,10 +3519,26 @@ static void handle_stripe_fill(struct stripe_head *sh, * midst of changing due to a write */ if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state && - !sh->reconstruct_state) + !sh->reconstruct_state) { + + /* + * For degraded stripe with data in journal, do not handle + * read requests yet, instead, flush the stripe to raid + * disks first, this avoids handling complex rmw of write + * back cache (prexor with orig_page, and then xor with + * page) in the read path + */ + if (s->injournal && s->failed) { + if (test_bit(STRIPE_R5C_CACHING, &sh->state)) + r5c_make_stripe_write_out(sh); + goto out; + } + for (i = disks; i--; ) if (fetch_block(sh, s, i, disks)) break; + } +out: set_bit(STRIPE_HANDLE, &sh->state); } @@ -3594,6 +3651,21 @@ unhash: break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS); } +/* + * For RMW in write back cache, we need extra page in prexor to store the + * old data. This page is stored in dev->orig_page. + * + * This function checks whether we have data for prexor. The exact logic + * is: + * R5_UPTODATE && (!R5_InJournal || R5_OrigPageUPTDODATE) + */ +static inline bool uptodate_for_rmw(struct r5dev *dev) +{ + return (test_bit(R5_UPTODATE, &dev->flags)) && + (!test_bit(R5_InJournal, &dev->flags) || + test_bit(R5_OrigPageUPTDODATE, &dev->flags)); +} + static int handle_stripe_dirtying(struct r5conf *conf, struct stripe_head *sh, struct stripe_head_state *s, @@ -3622,12 +3694,11 @@ static int handle_stripe_dirtying(struct r5conf *conf, } else for (i = disks; i--; ) { /* would I have to read this buffer for read_modify_write */ struct r5dev *dev = &sh->dev[i]; - if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx || + if (((dev->towrite && !delay_towrite(dev, s)) || + i == sh->pd_idx || i == sh->qd_idx || test_bit(R5_InJournal, &dev->flags)) && !test_bit(R5_LOCKED, &dev->flags) && - !((test_bit(R5_UPTODATE, &dev->flags) && - (!test_bit(R5_InJournal, &dev->flags) || - dev->page != dev->orig_page)) || + !(uptodate_for_rmw(dev) || test_bit(R5_Wantcompute, &dev->flags))) { if (test_bit(R5_Insync, &dev->flags)) rmw++; @@ -3639,7 +3710,6 @@ static int handle_stripe_dirtying(struct r5conf *conf, i != sh->pd_idx && i != sh->qd_idx && !test_bit(R5_LOCKED, &dev->flags) && !(test_bit(R5_UPTODATE, &dev->flags) || - test_bit(R5_InJournal, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags))) { if (test_bit(R5_Insync, &dev->flags)) rcw++; @@ -3689,13 +3759,11 @@ static int handle_stripe_dirtying(struct r5conf *conf, for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - if ((dev->towrite || + if (((dev->towrite && !delay_towrite(dev, s)) || i == sh->pd_idx || i == sh->qd_idx || test_bit(R5_InJournal, &dev->flags)) && !test_bit(R5_LOCKED, &dev->flags) && - !((test_bit(R5_UPTODATE, &dev->flags) && - (!test_bit(R5_InJournal, &dev->flags) || - dev->page != dev->orig_page)) || + !(uptodate_for_rmw(dev) || test_bit(R5_Wantcompute, &dev->flags)) && test_bit(R5_Insync, &dev->flags)) { if (test_bit(STRIPE_PREREAD_ACTIVE, @@ -3722,7 +3790,6 @@ static int handle_stripe_dirtying(struct r5conf *conf, i != sh->pd_idx && i != sh->qd_idx && !test_bit(R5_LOCKED, &dev->flags) && !(test_bit(R5_UPTODATE, &dev->flags) || - test_bit(R5_InJournal, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags))) { rcw++; if (test_bit(R5_Insync, &dev->flags) && @@ -7025,7 +7092,7 @@ static int raid5_run(struct mddev *mddev) /* * 0 for a fully functional array, 1 or 2 for a degraded array. */ - mddev->degraded = calc_degraded(conf); + mddev->degraded = raid5_calc_degraded(conf); if (has_failed(conf)) { pr_crit("md/raid:%s: not enough operational devices (%d/%d failed)\n", @@ -7272,7 +7339,7 @@ static int raid5_spare_active(struct mddev *mddev) } } spin_lock_irqsave(&conf->device_lock, flags); - mddev->degraded = calc_degraded(conf); + mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irqrestore(&conf->device_lock, flags); print_raid5_conf(conf); return count; @@ -7632,7 +7699,7 @@ static int raid5_start_reshape(struct mddev *mddev) * pre and post number of devices. */ spin_lock_irqsave(&conf->device_lock, flags); - mddev->degraded = calc_degraded(conf); + mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irqrestore(&conf->device_lock, flags); } mddev->raid_disks = conf->raid_disks; @@ -7720,7 +7787,7 @@ static void raid5_finish_reshape(struct mddev *mddev) } else { int d; spin_lock_irq(&conf->device_lock); - mddev->degraded = calc_degraded(conf); + mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irq(&conf->device_lock); for (d = conf->raid_disks ; d < conf->raid_disks - mddev->delta_disks; diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index ed8e1362ab36..1440fa26e296 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -322,6 +322,11 @@ enum r5dev_flags { * data and parity being written are in the journal * device */ + R5_OrigPageUPTDODATE, /* with write back cache, we read old data into + * dev->orig_page for prexor. When this flag is + * set, orig_page contains latest data in the + * raid disk. + */ }; /* @@ -753,6 +758,7 @@ extern sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector, extern struct stripe_head * raid5_get_active_stripe(struct r5conf *conf, sector_t sector, int previous, int noblock, int noquiesce); +extern int raid5_calc_degraded(struct r5conf *conf); extern int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev); extern void r5l_exit_log(struct r5l_log *log); extern int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh); @@ -781,4 +787,5 @@ extern void r5c_flush_cache(struct r5conf *conf, int num); extern void r5c_check_stripe_cache_usage(struct r5conf *conf); extern void r5c_check_cached_full_stripe(struct r5conf *conf); extern struct md_sysfs_entry r5c_journal_mode; +extern void r5c_update_on_rdev_error(struct mddev *mddev); #endif diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index 0ea4efb3de66..ebb5e391b800 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -30,8 +30,9 @@ #include "cec-priv.h" -static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx); -static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx); +static void cec_fill_msg_report_features(struct cec_adapter *adap, + struct cec_msg *msg, + unsigned int la_idx); /* * 400 ms is the time it takes for one 16 byte message to be @@ -288,10 +289,10 @@ static void cec_data_cancel(struct cec_data *data) /* Mark it as an error */ data->msg.tx_ts = ktime_get_ns(); - data->msg.tx_status = CEC_TX_STATUS_ERROR | - CEC_TX_STATUS_MAX_RETRIES; + data->msg.tx_status |= CEC_TX_STATUS_ERROR | + CEC_TX_STATUS_MAX_RETRIES; + data->msg.tx_error_cnt++; data->attempts = 0; - data->msg.tx_error_cnt = 1; /* Queue transmitted message for monitoring purposes */ cec_queue_msg_monitor(data->adap, &data->msg, 1); @@ -851,7 +852,7 @@ static const u8 cec_msg_size[256] = { [CEC_MSG_REQUEST_ARC_TERMINATION] = 2 | DIRECTED, [CEC_MSG_TERMINATE_ARC] = 2 | DIRECTED, [CEC_MSG_REQUEST_CURRENT_LATENCY] = 4 | BCAST, - [CEC_MSG_REPORT_CURRENT_LATENCY] = 7 | BCAST, + [CEC_MSG_REPORT_CURRENT_LATENCY] = 6 | BCAST, [CEC_MSG_CDC_MESSAGE] = 2 | BCAST, }; @@ -1250,30 +1251,49 @@ configured: for (i = 1; i < las->num_log_addrs; i++) las->log_addr[i] = CEC_LOG_ADDR_INVALID; } + for (i = las->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++) + las->log_addr[i] = CEC_LOG_ADDR_INVALID; adap->is_configured = true; adap->is_configuring = false; cec_post_state_event(adap); - mutex_unlock(&adap->lock); + /* + * Now post the Report Features and Report Physical Address broadcast + * messages. Note that these are non-blocking transmits, meaning that + * they are just queued up and once adap->lock is unlocked the main + * thread will kick in and start transmitting these. + * + * If after this function is done (but before one or more of these + * messages are actually transmitted) the CEC adapter is unconfigured, + * then any remaining messages will be dropped by the main thread. + */ for (i = 0; i < las->num_log_addrs; i++) { + struct cec_msg msg = {}; + if (las->log_addr[i] == CEC_LOG_ADDR_INVALID || (las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY)) continue; - /* - * Report Features must come first according - * to CEC 2.0 - */ - if (las->log_addr[i] != CEC_LOG_ADDR_UNREGISTERED) - cec_report_features(adap, i); - cec_report_phys_addr(adap, i); + msg.msg[0] = (las->log_addr[i] << 4) | 0x0f; + + /* Report Features must come first according to CEC 2.0 */ + if (las->log_addr[i] != CEC_LOG_ADDR_UNREGISTERED && + adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0) { + cec_fill_msg_report_features(adap, &msg, i); + cec_transmit_msg_fh(adap, &msg, NULL, false); + } + + /* Report Physical Address */ + cec_msg_report_physical_addr(&msg, adap->phys_addr, + las->primary_device_type[i]); + dprintk(2, "config: la %d pa %x.%x.%x.%x\n", + las->log_addr[i], + cec_phys_addr_exp(adap->phys_addr)); + cec_transmit_msg_fh(adap, &msg, NULL, false); } - for (i = las->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++) - las->log_addr[i] = CEC_LOG_ADDR_INVALID; - mutex_lock(&adap->lock); adap->kthread_config = NULL; - mutex_unlock(&adap->lock); complete(&adap->config_completion); + mutex_unlock(&adap->lock); return 0; unconfigure: @@ -1526,52 +1546,32 @@ EXPORT_SYMBOL_GPL(cec_s_log_addrs); /* High-level core CEC message handling */ -/* Transmit the Report Features message */ -static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx) +/* Fill in the Report Features message */ +static void cec_fill_msg_report_features(struct cec_adapter *adap, + struct cec_msg *msg, + unsigned int la_idx) { - struct cec_msg msg = { }; const struct cec_log_addrs *las = &adap->log_addrs; const u8 *features = las->features[la_idx]; bool op_is_dev_features = false; unsigned int idx; - /* This is 2.0 and up only */ - if (adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0) - return 0; - /* Report Features */ - msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f; - msg.len = 4; - msg.msg[1] = CEC_MSG_REPORT_FEATURES; - msg.msg[2] = adap->log_addrs.cec_version; - msg.msg[3] = las->all_device_types[la_idx]; + msg->msg[0] = (las->log_addr[la_idx] << 4) | 0x0f; + msg->len = 4; + msg->msg[1] = CEC_MSG_REPORT_FEATURES; + msg->msg[2] = adap->log_addrs.cec_version; + msg->msg[3] = las->all_device_types[la_idx]; /* Write RC Profiles first, then Device Features */ for (idx = 0; idx < ARRAY_SIZE(las->features[0]); idx++) { - msg.msg[msg.len++] = features[idx]; + msg->msg[msg->len++] = features[idx]; if ((features[idx] & CEC_OP_FEAT_EXT) == 0) { if (op_is_dev_features) break; op_is_dev_features = true; } } - return cec_transmit_msg(adap, &msg, false); -} - -/* Transmit the Report Physical Address message */ -static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx) -{ - const struct cec_log_addrs *las = &adap->log_addrs; - struct cec_msg msg = { }; - - /* Report Physical Address */ - msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f; - cec_msg_report_physical_addr(&msg, adap->phys_addr, - las->primary_device_type[la_idx]); - dprintk(2, "config: la %d pa %x.%x.%x.%x\n", - las->log_addr[la_idx], - cec_phys_addr_exp(adap->phys_addr)); - return cec_transmit_msg(adap, &msg, false); } /* Transmit the Feature Abort message */ @@ -1777,9 +1777,10 @@ static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg, } case CEC_MSG_GIVE_FEATURES: - if (adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0) - return cec_report_features(adap, la_idx); - return 0; + if (adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0) + return cec_feature_abort(adap, msg); + cec_fill_msg_report_features(adap, &tx_cec_msg, la_idx); + return cec_transmit_msg(adap, &tx_cec_msg, false); default: /* diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index bc5e8cfe7ca2..8f11d7e45993 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -719,6 +719,9 @@ static void dvb_net_ule_check_crc(struct dvb_net_ule_handle *h, skb_copy_from_linear_data(h->priv->ule_skb, dest_addr, ETH_ALEN); skb_pull(h->priv->ule_skb, ETH_ALEN); + } else { + /* dest_addr buffer is only valid if h->priv->ule_dbit == 0 */ + eth_zero_addr(dest_addr); } /* Handle ULE Extension Headers. */ @@ -750,16 +753,8 @@ static void dvb_net_ule_check_crc(struct dvb_net_ule_handle *h, if (!h->priv->ule_bridged) { skb_push(h->priv->ule_skb, ETH_HLEN); h->ethh = (struct ethhdr *)h->priv->ule_skb->data; - if (!h->priv->ule_dbit) { - /* - * dest_addr buffer is only valid if - * h->priv->ule_dbit == 0 - */ - memcpy(h->ethh->h_dest, dest_addr, ETH_ALEN); - eth_zero_addr(h->ethh->h_source); - } else /* zeroize source and dest */ - memset(h->ethh, 0, ETH_ALEN * 2); - + memcpy(h->ethh->h_dest, dest_addr, ETH_ALEN); + eth_zero_addr(h->ethh->h_source); h->ethh->h_proto = htons(h->priv->ule_sndu_type); } /* else: skb is in correct state; nothing to do. */ diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig index b31fa6fae009..b979ea148251 100644 --- a/drivers/media/i2c/Kconfig +++ b/drivers/media/i2c/Kconfig @@ -655,6 +655,7 @@ config VIDEO_S5K6A3 config VIDEO_S5K4ECGX tristate "Samsung S5K4ECGX sensor support" depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API + select CRC32 ---help--- This is a V4L2 sensor-level driver for Samsung S5K4ECGX 5M camera sensor with an embedded SoC image signal processor. diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c index 59872b31f832..f4e92bdfe192 100644 --- a/drivers/media/i2c/smiapp/smiapp-core.c +++ b/drivers/media/i2c/smiapp/smiapp-core.c @@ -2741,9 +2741,7 @@ static const struct v4l2_subdev_internal_ops smiapp_internal_ops = { * I2C Driver */ -#ifdef CONFIG_PM - -static int smiapp_suspend(struct device *dev) +static int __maybe_unused smiapp_suspend(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); struct v4l2_subdev *subdev = i2c_get_clientdata(client); @@ -2768,7 +2766,7 @@ static int smiapp_suspend(struct device *dev) return 0; } -static int smiapp_resume(struct device *dev) +static int __maybe_unused smiapp_resume(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); struct v4l2_subdev *subdev = i2c_get_clientdata(client); @@ -2783,13 +2781,6 @@ static int smiapp_resume(struct device *dev) return rval; } -#else - -#define smiapp_suspend NULL -#define smiapp_resume NULL - -#endif /* CONFIG_PM */ - static struct smiapp_hwconfig *smiapp_get_hwconfig(struct device *dev) { struct smiapp_hwconfig *hwcfg; @@ -2913,13 +2904,9 @@ static int smiapp_probe(struct i2c_client *client, if (IS_ERR(sensor->xshutdown)) return PTR_ERR(sensor->xshutdown); - pm_runtime_enable(&client->dev); - - rval = pm_runtime_get_sync(&client->dev); - if (rval < 0) { - rval = -ENODEV; - goto out_power_off; - } + rval = smiapp_power_on(&client->dev); + if (rval < 0) + return rval; rval = smiapp_identify_module(sensor); if (rval) { @@ -3100,6 +3087,9 @@ static int smiapp_probe(struct i2c_client *client, if (rval < 0) goto out_media_entity_cleanup; + pm_runtime_set_active(&client->dev); + pm_runtime_get_noresume(&client->dev); + pm_runtime_enable(&client->dev); pm_runtime_set_autosuspend_delay(&client->dev, 1000); pm_runtime_use_autosuspend(&client->dev); pm_runtime_put_autosuspend(&client->dev); @@ -3113,8 +3103,7 @@ out_cleanup: smiapp_cleanup(sensor); out_power_off: - pm_runtime_put(&client->dev); - pm_runtime_disable(&client->dev); + smiapp_power_off(&client->dev); return rval; } @@ -3127,8 +3116,10 @@ static int smiapp_remove(struct i2c_client *client) v4l2_async_unregister_subdev(subdev); - pm_runtime_suspend(&client->dev); pm_runtime_disable(&client->dev); + if (!pm_runtime_status_suspended(&client->dev)) + smiapp_power_off(&client->dev); + pm_runtime_set_suspended(&client->dev); for (i = 0; i < sensor->ssds_used; i++) { v4l2_device_unregister_subdev(&sensor->ssds[i].sd); diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c index 3a0fe8cc64e9..48646a7f3fb0 100644 --- a/drivers/media/i2c/tvp5150.c +++ b/drivers/media/i2c/tvp5150.c @@ -291,8 +291,12 @@ static void tvp5150_selmux(struct v4l2_subdev *sd) tvp5150_write(sd, TVP5150_OP_MODE_CTL, opmode); tvp5150_write(sd, TVP5150_VD_IN_SRC_SEL_1, input); - /* Svideo should enable YCrCb output and disable GPCL output - * For Composite and TV, it should be the reverse + /* + * Setup the FID/GLCO/VLK/HVLK and INTREQ/GPCL/VBLK output signals. For + * S-Video we output the vertical lock (VLK) signal on FID/GLCO/VLK/HVLK + * and set INTREQ/GPCL/VBLK to logic 0. For composite we output the + * field indicator (FID) signal on FID/GLCO/VLK/HVLK and set + * INTREQ/GPCL/VBLK to logic 1. */ val = tvp5150_read(sd, TVP5150_MISC_CTL); if (val < 0) { @@ -301,9 +305,9 @@ static void tvp5150_selmux(struct v4l2_subdev *sd) } if (decoder->input == TVP5150_SVIDEO) - val = (val & ~0x40) | 0x10; + val = (val & ~TVP5150_MISC_CTL_GPCL) | TVP5150_MISC_CTL_HVLK; else - val = (val & ~0x10) | 0x40; + val = (val & ~TVP5150_MISC_CTL_HVLK) | TVP5150_MISC_CTL_GPCL; tvp5150_write(sd, TVP5150_MISC_CTL, val); }; @@ -455,7 +459,12 @@ static const struct i2c_reg_value tvp5150_init_enable[] = { },{ /* Automatic offset and AGC enabled */ TVP5150_ANAL_CHL_CTL, 0x15 },{ /* Activate YCrCb output 0x9 or 0xd ? */ - TVP5150_MISC_CTL, 0x6f + TVP5150_MISC_CTL, TVP5150_MISC_CTL_GPCL | + TVP5150_MISC_CTL_INTREQ_OE | + TVP5150_MISC_CTL_YCBCR_OE | + TVP5150_MISC_CTL_SYNC_OE | + TVP5150_MISC_CTL_VBLANK | + TVP5150_MISC_CTL_CLOCK_OE, },{ /* Activates video std autodetection for all standards */ TVP5150_AUTOSW_MSK, 0x0 },{ /* Default format: 0x47. For 4:2:2: 0x40 */ @@ -861,8 +870,6 @@ static int tvp5150_fill_fmt(struct v4l2_subdev *sd, f = &format->format; - tvp5150_reset(sd, 0); - f->width = decoder->rect.width; f->height = decoder->rect.height / 2; @@ -1051,21 +1058,27 @@ static const struct media_entity_operations tvp5150_sd_media_ops = { static int tvp5150_s_stream(struct v4l2_subdev *sd, int enable) { struct tvp5150 *decoder = to_tvp5150(sd); - /* Output format: 8-bit ITU-R BT.656 with embedded syncs */ - int val = 0x09; + int val; - /* Output format: 8-bit 4:2:2 YUV with discrete sync */ - if (decoder->mbus_type == V4L2_MBUS_PARALLEL) - val = 0x0d; + /* Enable or disable the video output signals. */ + val = tvp5150_read(sd, TVP5150_MISC_CTL); + if (val < 0) + return val; - /* Initializes TVP5150 to its default values */ - /* # set PCLK (27MHz) */ - tvp5150_write(sd, TVP5150_CONF_SHARED_PIN, 0x00); + val &= ~(TVP5150_MISC_CTL_YCBCR_OE | TVP5150_MISC_CTL_SYNC_OE | + TVP5150_MISC_CTL_CLOCK_OE); - if (enable) - tvp5150_write(sd, TVP5150_MISC_CTL, val); - else - tvp5150_write(sd, TVP5150_MISC_CTL, 0x00); + if (enable) { + /* + * Enable the YCbCr and clock outputs. In discrete sync mode + * (non-BT.656) additionally enable the the sync outputs. + */ + val |= TVP5150_MISC_CTL_YCBCR_OE | TVP5150_MISC_CTL_CLOCK_OE; + if (decoder->mbus_type == V4L2_MBUS_PARALLEL) + val |= TVP5150_MISC_CTL_SYNC_OE; + } + + tvp5150_write(sd, TVP5150_MISC_CTL, val); return 0; } @@ -1524,7 +1537,6 @@ static int tvp5150_probe(struct i2c_client *c, res = core->hdl.error; goto err; } - v4l2_ctrl_handler_setup(&core->hdl); /* Default is no cropping */ core->rect.top = 0; @@ -1535,6 +1547,8 @@ static int tvp5150_probe(struct i2c_client *c, core->rect.left = 0; core->rect.width = TVP5150_H_MAX; + tvp5150_reset(sd, 0); /* Calls v4l2_ctrl_handler_setup() */ + res = v4l2_async_register_subdev(sd); if (res < 0) goto err; diff --git a/drivers/media/i2c/tvp5150_reg.h b/drivers/media/i2c/tvp5150_reg.h index 25a994944918..30a48c28d05a 100644 --- a/drivers/media/i2c/tvp5150_reg.h +++ b/drivers/media/i2c/tvp5150_reg.h @@ -9,6 +9,15 @@ #define TVP5150_ANAL_CHL_CTL 0x01 /* Analog channel controls */ #define TVP5150_OP_MODE_CTL 0x02 /* Operation mode controls */ #define TVP5150_MISC_CTL 0x03 /* Miscellaneous controls */ +#define TVP5150_MISC_CTL_VBLK_GPCL BIT(7) +#define TVP5150_MISC_CTL_GPCL BIT(6) +#define TVP5150_MISC_CTL_INTREQ_OE BIT(5) +#define TVP5150_MISC_CTL_HVLK BIT(4) +#define TVP5150_MISC_CTL_YCBCR_OE BIT(3) +#define TVP5150_MISC_CTL_SYNC_OE BIT(2) +#define TVP5150_MISC_CTL_VBLANK BIT(1) +#define TVP5150_MISC_CTL_CLOCK_OE BIT(0) + #define TVP5150_AUTOSW_MSK 0x04 /* Autoswitch mask: TVP5150A / TVP5150AM */ /* Reserved 05h */ diff --git a/drivers/media/pci/cobalt/cobalt-driver.c b/drivers/media/pci/cobalt/cobalt-driver.c index 979634000597..d5c911c09e2b 100644 --- a/drivers/media/pci/cobalt/cobalt-driver.c +++ b/drivers/media/pci/cobalt/cobalt-driver.c @@ -308,9 +308,7 @@ static void cobalt_pci_iounmap(struct cobalt *cobalt, struct pci_dev *pci_dev) static void cobalt_free_msi(struct cobalt *cobalt, struct pci_dev *pci_dev) { free_irq(pci_dev->irq, (void *)cobalt); - - if (cobalt->msi_enabled) - pci_disable_msi(pci_dev); + pci_free_irq_vectors(pci_dev); } static int cobalt_setup_pci(struct cobalt *cobalt, struct pci_dev *pci_dev, @@ -387,14 +385,12 @@ static int cobalt_setup_pci(struct cobalt *cobalt, struct pci_dev *pci_dev, from being generated. */ cobalt_set_interrupt(cobalt, false); - if (pci_enable_msi_range(pci_dev, 1, 1) < 1) { + if (pci_alloc_irq_vectors(pci_dev, 1, 1, PCI_IRQ_MSI) < 1) { cobalt_err("Could not enable MSI\n"); - cobalt->msi_enabled = false; ret = -EIO; goto err_release; } msi_config_show(cobalt, pci_dev); - cobalt->msi_enabled = true; /* Register IRQ */ if (request_irq(pci_dev->irq, cobalt_irq_handler, IRQF_SHARED, diff --git a/drivers/media/pci/cobalt/cobalt-driver.h b/drivers/media/pci/cobalt/cobalt-driver.h index ed00dc9d9399..00f773ec359a 100644 --- a/drivers/media/pci/cobalt/cobalt-driver.h +++ b/drivers/media/pci/cobalt/cobalt-driver.h @@ -287,8 +287,6 @@ struct cobalt { u32 irq_none; u32 irq_full_fifo; - bool msi_enabled; - /* omnitek dma */ int dma_channels; int first_fifo_channel; diff --git a/drivers/media/usb/dvb-usb/pctv452e.c b/drivers/media/usb/dvb-usb/pctv452e.c index 07fa08be9e99..d54ebe7e0215 100644 --- a/drivers/media/usb/dvb-usb/pctv452e.c +++ b/drivers/media/usb/dvb-usb/pctv452e.c @@ -97,14 +97,13 @@ struct pctv452e_state { u8 c; /* transaction counter, wraps around... */ u8 initialized; /* set to 1 if 0x15 has been sent */ u16 last_rc_key; - - unsigned char data[80]; }; static int tt3650_ci_msg(struct dvb_usb_device *d, u8 cmd, u8 *data, unsigned int write_len, unsigned int read_len) { struct pctv452e_state *state = (struct pctv452e_state *)d->priv; + u8 *buf; u8 id; unsigned int rlen; int ret; @@ -114,36 +113,39 @@ static int tt3650_ci_msg(struct dvb_usb_device *d, u8 cmd, u8 *data, return -EIO; } - mutex_lock(&state->ca_mutex); + buf = kmalloc(64, GFP_KERNEL); + if (!buf) + return -ENOMEM; + id = state->c++; - state->data[0] = SYNC_BYTE_OUT; - state->data[1] = id; - state->data[2] = cmd; - state->data[3] = write_len; + buf[0] = SYNC_BYTE_OUT; + buf[1] = id; + buf[2] = cmd; + buf[3] = write_len; - memcpy(state->data + 4, data, write_len); + memcpy(buf + 4, data, write_len); rlen = (read_len > 0) ? 64 : 0; - ret = dvb_usb_generic_rw(d, state->data, 4 + write_len, - state->data, rlen, /* delay_ms */ 0); + ret = dvb_usb_generic_rw(d, buf, 4 + write_len, + buf, rlen, /* delay_ms */ 0); if (0 != ret) goto failed; ret = -EIO; - if (SYNC_BYTE_IN != state->data[0] || id != state->data[1]) + if (SYNC_BYTE_IN != buf[0] || id != buf[1]) goto failed; - memcpy(data, state->data + 4, read_len); + memcpy(data, buf + 4, read_len); - mutex_unlock(&state->ca_mutex); + kfree(buf); return 0; failed: err("CI error %d; %02X %02X %02X -> %*ph.", - ret, SYNC_BYTE_OUT, id, cmd, 3, state->data); + ret, SYNC_BYTE_OUT, id, cmd, 3, buf); - mutex_unlock(&state->ca_mutex); + kfree(buf); return ret; } @@ -410,53 +412,57 @@ static int pctv452e_i2c_msg(struct dvb_usb_device *d, u8 addr, u8 *rcv_buf, u8 rcv_len) { struct pctv452e_state *state = (struct pctv452e_state *)d->priv; + u8 *buf; u8 id; int ret; - mutex_lock(&state->ca_mutex); + buf = kmalloc(64, GFP_KERNEL); + if (!buf) + return -ENOMEM; + id = state->c++; ret = -EINVAL; if (snd_len > 64 - 7 || rcv_len > 64 - 7) goto failed; - state->data[0] = SYNC_BYTE_OUT; - state->data[1] = id; - state->data[2] = PCTV_CMD_I2C; - state->data[3] = snd_len + 3; - state->data[4] = addr << 1; - state->data[5] = snd_len; - state->data[6] = rcv_len; + buf[0] = SYNC_BYTE_OUT; + buf[1] = id; + buf[2] = PCTV_CMD_I2C; + buf[3] = snd_len + 3; + buf[4] = addr << 1; + buf[5] = snd_len; + buf[6] = rcv_len; - memcpy(state->data + 7, snd_buf, snd_len); + memcpy(buf + 7, snd_buf, snd_len); - ret = dvb_usb_generic_rw(d, state->data, 7 + snd_len, - state->data, /* rcv_len */ 64, + ret = dvb_usb_generic_rw(d, buf, 7 + snd_len, + buf, /* rcv_len */ 64, /* delay_ms */ 0); if (ret < 0) goto failed; /* TT USB protocol error. */ ret = -EIO; - if (SYNC_BYTE_IN != state->data[0] || id != state->data[1]) + if (SYNC_BYTE_IN != buf[0] || id != buf[1]) goto failed; /* I2C device didn't respond as expected. */ ret = -EREMOTEIO; - if (state->data[5] < snd_len || state->data[6] < rcv_len) + if (buf[5] < snd_len || buf[6] < rcv_len) goto failed; - memcpy(rcv_buf, state->data + 7, rcv_len); - mutex_unlock(&state->ca_mutex); + memcpy(rcv_buf, buf + 7, rcv_len); + kfree(buf); return rcv_len; failed: err("I2C error %d; %02X %02X %02X %02X %02X -> %*ph", ret, SYNC_BYTE_OUT, id, addr << 1, snd_len, rcv_len, - 7, state->data); + 7, buf); - mutex_unlock(&state->ca_mutex); + kfree(buf); return ret; } @@ -505,7 +511,7 @@ static u32 pctv452e_i2c_func(struct i2c_adapter *adapter) static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i) { struct pctv452e_state *state = (struct pctv452e_state *)d->priv; - u8 *rx; + u8 *b0, *rx; int ret; info("%s: %d\n", __func__, i); @@ -516,11 +522,12 @@ static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i) if (state->initialized) return 0; - rx = kmalloc(PCTV_ANSWER_LEN, GFP_KERNEL); - if (!rx) + b0 = kmalloc(5 + PCTV_ANSWER_LEN, GFP_KERNEL); + if (!b0) return -ENOMEM; - mutex_lock(&state->ca_mutex); + rx = b0 + 5; + /* hmm where shoud this should go? */ ret = usb_set_interface(d->udev, 0, ISOC_INTERFACE_ALTERNATIVE); if (ret != 0) @@ -528,66 +535,70 @@ static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i) __func__, ret); /* this is a one-time initialization, dont know where to put */ - state->data[0] = 0xaa; - state->data[1] = state->c++; - state->data[2] = PCTV_CMD_RESET; - state->data[3] = 1; - state->data[4] = 0; + b0[0] = 0xaa; + b0[1] = state->c++; + b0[2] = PCTV_CMD_RESET; + b0[3] = 1; + b0[4] = 0; /* reset board */ - ret = dvb_usb_generic_rw(d, state->data, 5, rx, PCTV_ANSWER_LEN, 0); + ret = dvb_usb_generic_rw(d, b0, 5, rx, PCTV_ANSWER_LEN, 0); if (ret) goto ret; - state->data[1] = state->c++; - state->data[4] = 1; + b0[1] = state->c++; + b0[4] = 1; /* reset board (again?) */ - ret = dvb_usb_generic_rw(d, state->data, 5, rx, PCTV_ANSWER_LEN, 0); + ret = dvb_usb_generic_rw(d, b0, 5, rx, PCTV_ANSWER_LEN, 0); if (ret) goto ret; state->initialized = 1; ret: - mutex_unlock(&state->ca_mutex); - kfree(rx); + kfree(b0); return ret; } static int pctv452e_rc_query(struct dvb_usb_device *d) { struct pctv452e_state *state = (struct pctv452e_state *)d->priv; + u8 *b, *rx; int ret, i; u8 id; - mutex_lock(&state->ca_mutex); + b = kmalloc(CMD_BUFFER_SIZE + PCTV_ANSWER_LEN, GFP_KERNEL); + if (!b) + return -ENOMEM; + + rx = b + CMD_BUFFER_SIZE; + id = state->c++; /* prepare command header */ - state->data[0] = SYNC_BYTE_OUT; - state->data[1] = id; - state->data[2] = PCTV_CMD_IR; - state->data[3] = 0; + b[0] = SYNC_BYTE_OUT; + b[1] = id; + b[2] = PCTV_CMD_IR; + b[3] = 0; /* send ir request */ - ret = dvb_usb_generic_rw(d, state->data, 4, - state->data, PCTV_ANSWER_LEN, 0); + ret = dvb_usb_generic_rw(d, b, 4, rx, PCTV_ANSWER_LEN, 0); if (ret != 0) goto ret; if (debug > 3) { - info("%s: read: %2d: %*ph: ", __func__, ret, 3, state->data); - for (i = 0; (i < state->data[3]) && ((i + 3) < PCTV_ANSWER_LEN); i++) - info(" %02x", state->data[i + 3]); + info("%s: read: %2d: %*ph: ", __func__, ret, 3, rx); + for (i = 0; (i < rx[3]) && ((i+3) < PCTV_ANSWER_LEN); i++) + info(" %02x", rx[i+3]); info("\n"); } - if ((state->data[3] == 9) && (state->data[12] & 0x01)) { + if ((rx[3] == 9) && (rx[12] & 0x01)) { /* got a "press" event */ - state->last_rc_key = RC_SCANCODE_RC5(state->data[7], state->data[6]); + state->last_rc_key = RC_SCANCODE_RC5(rx[7], rx[6]); if (debug > 2) info("%s: cmd=0x%02x sys=0x%02x\n", - __func__, state->data[6], state->data[7]); + __func__, rx[6], rx[7]); rc_keydown(d->rc_dev, RC_TYPE_RC5, state->last_rc_key, 0); } else if (state->last_rc_key) { @@ -595,7 +606,7 @@ static int pctv452e_rc_query(struct dvb_usb_device *d) state->last_rc_key = 0; } ret: - mutex_unlock(&state->ca_mutex); + kfree(b); return ret; } diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index a0547dbf9806..76382c858c35 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -330,7 +330,7 @@ static int h_memstick_read_dev_id(struct memstick_dev *card, struct ms_id_register id_reg; if (!(*mrq)) { - memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, NULL, + memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, &id_reg, sizeof(struct ms_id_register)); *mrq = &card->current_mrq; return 0; diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index b44306b886cb..73db08558e4d 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -3354,10 +3354,11 @@ int dw_mci_runtime_resume(struct device *dev) if (!slot) continue; - if (slot->mmc->pm_flags & MMC_PM_KEEP_POWER) { + if (slot->mmc->pm_flags & MMC_PM_KEEP_POWER) dw_mci_set_ios(slot->mmc, &slot->mmc->ios); - dw_mci_setup_bus(slot, true); - } + + /* Force setup bus to guarantee available clock output */ + dw_mci_setup_bus(slot, true); } /* Now that slots are all setup, we can enable card detect */ diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c index 7be393c96b1a..cf7c18947189 100644 --- a/drivers/net/can/c_can/c_can_pci.c +++ b/drivers/net/can/c_can/c_can_pci.c @@ -161,6 +161,7 @@ static int c_can_pci_probe(struct pci_dev *pdev, dev->irq = pdev->irq; priv->base = addr; + priv->device = &pdev->dev; if (!c_can_pci_data->freq) { dev_err(&pdev->dev, "no clock frequency defined\n"); diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 680d1ff07a55..6749b1829469 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -948,7 +948,12 @@ static int ti_hecc_probe(struct platform_device *pdev) netif_napi_add(ndev, &priv->napi, ti_hecc_rx_poll, HECC_DEF_NAPI_WEIGHT); - clk_enable(priv->clk); + err = clk_prepare_enable(priv->clk); + if (err) { + dev_err(&pdev->dev, "clk_prepare_enable() failed\n"); + goto probe_exit_clk; + } + err = register_candev(ndev); if (err) { dev_err(&pdev->dev, "register_candev() failed\n"); @@ -981,7 +986,7 @@ static int ti_hecc_remove(struct platform_device *pdev) struct ti_hecc_priv *priv = netdev_priv(ndev); unregister_candev(ndev); - clk_disable(priv->clk); + clk_disable_unprepare(priv->clk); clk_put(priv->clk); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); iounmap(priv->base); @@ -1006,7 +1011,7 @@ static int ti_hecc_suspend(struct platform_device *pdev, pm_message_t state) hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_PDR); priv->can.state = CAN_STATE_SLEEPING; - clk_disable(priv->clk); + clk_disable_unprepare(priv->clk); return 0; } @@ -1015,8 +1020,11 @@ static int ti_hecc_resume(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); struct ti_hecc_priv *priv = netdev_priv(dev); + int err; - clk_enable(priv->clk); + err = clk_prepare_enable(priv->clk); + if (err) + return err; hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_PDR); priv->can.state = CAN_STATE_ERROR_ACTIVE; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index 5b7ba25e0065..8a280e7d66bd 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -891,6 +891,8 @@ #define PCS_V1_WINDOW_SELECT 0x03fc #define PCS_V2_WINDOW_DEF 0x9060 #define PCS_V2_WINDOW_SELECT 0x9064 +#define PCS_V2_RV_WINDOW_DEF 0x1060 +#define PCS_V2_RV_WINDOW_SELECT 0x1064 /* PCS register entry bit positions and sizes */ #define PCS_V2_WINDOW_DEF_OFFSET_INDEX 6 diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index aaf0350076a9..a7d16db5c4b2 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1151,7 +1151,7 @@ static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad, offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask); spin_lock_irqsave(&pdata->xpcs_lock, flags); - XPCS32_IOWRITE(pdata, PCS_V2_WINDOW_SELECT, index); + XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index); mmd_data = XPCS16_IOREAD(pdata, offset); spin_unlock_irqrestore(&pdata->xpcs_lock, flags); @@ -1183,7 +1183,7 @@ static void xgbe_write_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad, offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask); spin_lock_irqsave(&pdata->xpcs_lock, flags); - XPCS32_IOWRITE(pdata, PCS_V2_WINDOW_SELECT, index); + XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index); XPCS16_IOWRITE(pdata, offset, mmd_data); spin_unlock_irqrestore(&pdata->xpcs_lock, flags); } @@ -3407,8 +3407,10 @@ static int xgbe_init(struct xgbe_prv_data *pdata) /* Flush Tx queues */ ret = xgbe_flush_tx_queues(pdata); - if (ret) + if (ret) { + netdev_err(pdata->netdev, "error flushing TX queues\n"); return ret; + } /* * Initialize DMA related features diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 9943629fcbf9..1c87cc204075 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1070,7 +1070,9 @@ static int xgbe_start(struct xgbe_prv_data *pdata) DBGPR("-->xgbe_start\n"); - hw_if->init(pdata); + ret = hw_if->init(pdata); + if (ret) + return ret; xgbe_napi_enable(pdata, 1); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c index e76b7f65b805..c2730f15bd8b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c @@ -265,6 +265,7 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct xgbe_prv_data *pdata; struct device *dev = &pdev->dev; void __iomem * const *iomap_table; + struct pci_dev *rdev; unsigned int ma_lo, ma_hi; unsigned int reg; int bar_mask; @@ -326,8 +327,20 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (netif_msg_probe(pdata)) dev_dbg(dev, "xpcs_regs = %p\n", pdata->xpcs_regs); + /* Set the PCS indirect addressing definition registers */ + rdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0)); + if (rdev && + (rdev->vendor == PCI_VENDOR_ID_AMD) && (rdev->device == 0x15d0)) { + pdata->xpcs_window_def_reg = PCS_V2_RV_WINDOW_DEF; + pdata->xpcs_window_sel_reg = PCS_V2_RV_WINDOW_SELECT; + } else { + pdata->xpcs_window_def_reg = PCS_V2_WINDOW_DEF; + pdata->xpcs_window_sel_reg = PCS_V2_WINDOW_SELECT; + } + pci_dev_put(rdev); + /* Configure the PCS indirect addressing support */ - reg = XPCS32_IOREAD(pdata, PCS_V2_WINDOW_DEF); + reg = XPCS32_IOREAD(pdata, pdata->xpcs_window_def_reg); pdata->xpcs_window = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, OFFSET); pdata->xpcs_window <<= 6; pdata->xpcs_window_size = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, SIZE); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index f52a9bd05bac..00108815b55e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -955,6 +955,8 @@ struct xgbe_prv_data { /* XPCS indirect addressing lock */ spinlock_t xpcs_lock; + unsigned int xpcs_window_def_reg; + unsigned int xpcs_window_sel_reg; unsigned int xpcs_window; unsigned int xpcs_window_size; unsigned int xpcs_window_mask; diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index c8f525574d68..7dcc907a449d 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -685,8 +685,6 @@ static int alx_alloc_rings(struct alx_priv *alx) return -ENOMEM; } - alx_reinit_rings(alx); - return 0; } @@ -703,7 +701,7 @@ static void alx_free_rings(struct alx_priv *alx) if (alx->qnapi[0] && alx->qnapi[0]->rxq) kfree(alx->qnapi[0]->rxq->bufs); - if (!alx->descmem.virt) + if (alx->descmem.virt) dma_free_coherent(&alx->hw.pdev->dev, alx->descmem.size, alx->descmem.virt, @@ -984,6 +982,7 @@ static int alx_realloc_resources(struct alx_priv *alx) alx_free_rings(alx); alx_free_napis(alx); alx_disable_advanced_intr(alx); + alx_init_intr(alx, false); err = alx_alloc_napis(alx); if (err) @@ -1241,6 +1240,12 @@ static int __alx_open(struct alx_priv *alx, bool resume) if (err) goto out_free_rings; + /* must be called after alx_request_irq because the chip stops working + * if we copy the dma addresses in alx_init_ring_ptrs twice when + * requesting msi-x interrupts failed + */ + alx_reinit_rings(alx); + netif_set_real_num_tx_queues(alx->dev, alx->num_txq); netif_set_real_num_rx_queues(alx->dev, alx->num_rxq); diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 3b14d5144228..c483618b57bd 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -913,6 +913,8 @@ static int bcm_enet_open(struct net_device *dev) priv->old_link = 0; priv->old_duplex = -1; priv->old_pause = -1; + } else { + phydev = NULL; } /* mask all interrupts and request them */ @@ -1083,7 +1085,7 @@ static int bcm_enet_open(struct net_device *dev) enet_dmac_writel(priv, priv->dma_chan_int_mask, ENETDMAC_IRMASK, priv->tx_chan); - if (priv->has_phy) + if (phydev) phy_start(phydev); else bcm_enet_adjust_link(dev); @@ -1126,7 +1128,7 @@ out_freeirq: free_irq(dev->irq, dev); out_phy_disconnect: - if (priv->has_phy) + if (phydev) phy_disconnect(phydev); return ret; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 9608cb49a11c..4fcc6a84a087 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1099,7 +1099,7 @@ static struct sk_buff *bnxt_gro_func_5730x(struct bnxt_tpa_info *tpa_info, { #ifdef CONFIG_INET struct tcphdr *th; - int len, nw_off, tcp_opt_len; + int len, nw_off, tcp_opt_len = 0; if (tcp_ts) tcp_opt_len = 12; @@ -5314,17 +5314,12 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state) if ((link_info->support_auto_speeds | diff) != link_info->support_auto_speeds) { /* An advertised speed is no longer supported, so we need to - * update the advertisement settings. See bnxt_reset() for - * comments about the rtnl_lock() sequence below. + * update the advertisement settings. Caller holds RTNL + * so we can modify link settings. */ - clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); - rtnl_lock(); link_info->advertising = link_info->support_auto_speeds; - if (test_bit(BNXT_STATE_OPEN, &bp->state) && - (link_info->autoneg & BNXT_AUTONEG_SPEED)) + if (link_info->autoneg & BNXT_AUTONEG_SPEED) bnxt_hwrm_set_link_setting(bp, true, false); - set_bit(BNXT_STATE_IN_SP_TASK, &bp->state); - rtnl_unlock(); } return 0; } @@ -6200,29 +6195,37 @@ bnxt_restart_timer: mod_timer(&bp->timer, jiffies + bp->current_interval); } -/* Only called from bnxt_sp_task() */ -static void bnxt_reset(struct bnxt *bp, bool silent) +static void bnxt_rtnl_lock_sp(struct bnxt *bp) { - /* bnxt_reset_task() calls bnxt_close_nic() which waits - * for BNXT_STATE_IN_SP_TASK to clear. - * If there is a parallel dev_close(), bnxt_close() may be holding + /* We are called from bnxt_sp_task which has BNXT_STATE_IN_SP_TASK + * set. If the device is being closed, bnxt_close() may be holding * rtnl() and waiting for BNXT_STATE_IN_SP_TASK to clear. So we * must clear BNXT_STATE_IN_SP_TASK before holding rtnl(). */ clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); rtnl_lock(); - if (test_bit(BNXT_STATE_OPEN, &bp->state)) - bnxt_reset_task(bp, silent); +} + +static void bnxt_rtnl_unlock_sp(struct bnxt *bp) +{ set_bit(BNXT_STATE_IN_SP_TASK, &bp->state); rtnl_unlock(); } +/* Only called from bnxt_sp_task() */ +static void bnxt_reset(struct bnxt *bp, bool silent) +{ + bnxt_rtnl_lock_sp(bp); + if (test_bit(BNXT_STATE_OPEN, &bp->state)) + bnxt_reset_task(bp, silent); + bnxt_rtnl_unlock_sp(bp); +} + static void bnxt_cfg_ntp_filters(struct bnxt *); static void bnxt_sp_task(struct work_struct *work) { struct bnxt *bp = container_of(work, struct bnxt, sp_task); - int rc; set_bit(BNXT_STATE_IN_SP_TASK, &bp->state); smp_mb__after_atomic(); @@ -6236,16 +6239,6 @@ static void bnxt_sp_task(struct work_struct *work) if (test_and_clear_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event)) bnxt_cfg_ntp_filters(bp); - if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) { - if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, - &bp->sp_event)) - bnxt_hwrm_phy_qcaps(bp); - - rc = bnxt_update_link(bp, true); - if (rc) - netdev_err(bp->dev, "SP task can't update link (rc: %x)\n", - rc); - } if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event)) bnxt_hwrm_exec_fwd_req(bp); if (test_and_clear_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event)) { @@ -6266,18 +6259,39 @@ static void bnxt_sp_task(struct work_struct *work) bnxt_hwrm_tunnel_dst_port_free( bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE); } + if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) + bnxt_hwrm_port_qstats(bp); + + /* These functions below will clear BNXT_STATE_IN_SP_TASK. They + * must be the last functions to be called before exiting. + */ + if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) { + int rc = 0; + + if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, + &bp->sp_event)) + bnxt_hwrm_phy_qcaps(bp); + + bnxt_rtnl_lock_sp(bp); + if (test_bit(BNXT_STATE_OPEN, &bp->state)) + rc = bnxt_update_link(bp, true); + bnxt_rtnl_unlock_sp(bp); + if (rc) + netdev_err(bp->dev, "SP task can't update link (rc: %x)\n", + rc); + } + if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) { + bnxt_rtnl_lock_sp(bp); + if (test_bit(BNXT_STATE_OPEN, &bp->state)) + bnxt_get_port_module_status(bp); + bnxt_rtnl_unlock_sp(bp); + } if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event)) bnxt_reset(bp, false); if (test_and_clear_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event)) bnxt_reset(bp, true); - if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) - bnxt_get_port_module_status(bp); - - if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) - bnxt_hwrm_port_qstats(bp); - smp_mb__before_atomic(); clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); } diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index a6e7afa878be..c1b671667920 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2948,7 +2948,7 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus, } /* try reuse page */ - if (unlikely(page_count(page) != 1)) + if (unlikely(page_count(page) != 1 || page_is_pfmemalloc(page))) return false; /* change offset to the other half */ diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index a831f947ca8c..309f5c66083c 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1601,8 +1601,11 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) netdev->netdev_ops = &ibmveth_netdev_ops; netdev->ethtool_ops = &netdev_ethtool_ops; SET_NETDEV_DEV(netdev, &dev->dev); - netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | - NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + netdev->hw_features = NETIF_F_SG; + if (vio_get_attribute(dev, "ibm,illan-options", NULL) != NULL) { + netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM; + } netdev->features |= netdev->hw_features; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 3dd87889e67e..1c29c86f8709 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2517,7 +2517,7 @@ static int mtk_remove(struct platform_device *pdev) } const struct of_device_id of_mtk_match[] = { - { .compatible = "mediatek,mt7623-eth" }, + { .compatible = "mediatek,mt2701-eth" }, {}, }; MODULE_DEVICE_TABLE(of, of_mtk_match); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index d9c9f86a30df..d5a9372ed84d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1732,8 +1732,6 @@ static void mlx4_en_get_channels(struct net_device *dev, { struct mlx4_en_priv *priv = netdev_priv(dev); - memset(channel, 0, sizeof(*channel)); - channel->max_rx = MAX_RX_RINGS; channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP; @@ -1752,10 +1750,7 @@ static int mlx4_en_set_channels(struct net_device *dev, int xdp_count; int err = 0; - if (channel->other_count || channel->combined_count || - channel->tx_count > MLX4_EN_MAX_TX_RING_P_UP || - channel->rx_count > MAX_RX_RINGS || - !channel->tx_count || !channel->rx_count) + if (!channel->tx_count || !channel->rx_count) return -EINVAL; tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 33a399a8b5d5..5197817e4b2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -543,7 +543,6 @@ static int mlx5e_set_channels(struct net_device *dev, struct ethtool_channels *ch) { struct mlx5e_priv *priv = netdev_priv(dev); - int ncv = mlx5e_get_max_num_channels(priv->mdev); unsigned int count = ch->combined_count; bool arfs_enabled; bool was_opened; @@ -554,16 +553,6 @@ static int mlx5e_set_channels(struct net_device *dev, __func__); return -EINVAL; } - if (ch->rx_count || ch->tx_count) { - netdev_info(dev, "%s: separate rx/tx count not supported\n", - __func__); - return -EINVAL; - } - if (count > ncv) { - netdev_info(dev, "%s: count (%d) > max (%d)\n", - __func__, count, ncv); - return -EINVAL; - } if (priv->params.num_channels == count) return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 0e2fb3ed1790..06d5e6fecb0a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -193,6 +193,9 @@ static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq, return false; } + if (unlikely(page_is_pfmemalloc(dma_info->page))) + return false; + cache->page_cache[cache->tail] = *dma_info; cache->tail = tail_next; return true; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 01d0efa9c5c7..9e494a446b7e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1172,7 +1172,8 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, static int mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop_group *nh_grp) + struct mlxsw_sp_nexthop_group *nh_grp, + bool reallocate) { u32 adj_index = nh_grp->adj_index; /* base */ struct mlxsw_sp_nexthop *nh; @@ -1187,7 +1188,7 @@ mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp, continue; } - if (nh->update) { + if (nh->update || reallocate) { err = mlxsw_sp_nexthop_mac_update(mlxsw_sp, adj_index, nh); if (err) @@ -1248,7 +1249,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, /* Nothing was added or removed, so no need to reallocate. Just * update MAC on existing adjacency indexes. */ - err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp); + err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, + false); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); goto set_trap; @@ -1276,7 +1278,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, nh_grp->adj_index_valid = 1; nh_grp->adj_index = adj_index; nh_grp->ecmp_size = ecmp_size; - err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp); + err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, true); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); goto set_trap; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 8e5cb7605b0f..873ce2cd76ba 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -297,7 +297,7 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle) list_del(&p_pkt->list_entry); b_last_packet = list_empty(&p_tx->active_descq); list_add_tail(&p_pkt->list_entry, &p_tx->free_descq); - if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO) { + if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO) { struct qed_ooo_buffer *p_buffer; p_buffer = (struct qed_ooo_buffer *)p_pkt->cookie; @@ -309,7 +309,7 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle) b_last_frag = p_tx->cur_completing_bd_idx == p_pkt->bd_used; tx_frag = p_pkt->bds_set[0].tx_frag; - if (p_ll2_conn->gsi_enable) + if (p_ll2_conn->conn.gsi_enable) qed_ll2b_release_tx_gsi_packet(p_hwfn, p_ll2_conn-> my_id, @@ -378,7 +378,7 @@ static int qed_ll2_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie) spin_unlock_irqrestore(&p_tx->lock, flags); tx_frag = p_pkt->bds_set[0].tx_frag; - if (p_ll2_conn->gsi_enable) + if (p_ll2_conn->conn.gsi_enable) qed_ll2b_complete_tx_gsi_packet(p_hwfn, p_ll2_conn->my_id, p_pkt->cookie, @@ -550,7 +550,7 @@ static void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle) list_move_tail(&p_pkt->list_entry, &p_rx->free_descq); - if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO) { + if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO) { struct qed_ooo_buffer *p_buffer; p_buffer = (struct qed_ooo_buffer *)p_pkt->cookie; @@ -738,7 +738,7 @@ qed_ooo_submit_tx_buffers(struct qed_hwfn *p_hwfn, rc = qed_ll2_prepare_tx_packet(p_hwfn, p_ll2_conn->my_id, 1, p_buffer->vlan, bd_flags, l4_hdr_offset_w, - p_ll2_conn->tx_dest, 0, + p_ll2_conn->conn.tx_dest, 0, first_frag, p_buffer->packet_length, p_buffer, true); @@ -858,7 +858,7 @@ qed_ll2_acquire_connection_ooo(struct qed_hwfn *p_hwfn, u16 buf_idx; int rc = 0; - if (p_ll2_info->conn_type != QED_LL2_TYPE_ISCSI_OOO) + if (p_ll2_info->conn.conn_type != QED_LL2_TYPE_ISCSI_OOO) return rc; if (!rx_num_ooo_buffers) @@ -901,7 +901,7 @@ static void qed_ll2_establish_connection_ooo(struct qed_hwfn *p_hwfn, struct qed_ll2_info *p_ll2_conn) { - if (p_ll2_conn->conn_type != QED_LL2_TYPE_ISCSI_OOO) + if (p_ll2_conn->conn.conn_type != QED_LL2_TYPE_ISCSI_OOO) return; qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info); @@ -913,7 +913,7 @@ static void qed_ll2_release_connection_ooo(struct qed_hwfn *p_hwfn, { struct qed_ooo_buffer *p_buffer; - if (p_ll2_conn->conn_type != QED_LL2_TYPE_ISCSI_OOO) + if (p_ll2_conn->conn.conn_type != QED_LL2_TYPE_ISCSI_OOO) return; qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info); @@ -945,23 +945,19 @@ static int qed_ll2_start_ooo(struct qed_dev *cdev, { struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); u8 *handle = &hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id; - struct qed_ll2_info *ll2_info; + struct qed_ll2_conn ll2_info; int rc; - ll2_info = kzalloc(sizeof(*ll2_info), GFP_KERNEL); - if (!ll2_info) - return -ENOMEM; - ll2_info->conn_type = QED_LL2_TYPE_ISCSI_OOO; - ll2_info->mtu = params->mtu; - ll2_info->rx_drop_ttl0_flg = params->drop_ttl0_packets; - ll2_info->rx_vlan_removal_en = params->rx_vlan_stripping; - ll2_info->tx_tc = OOO_LB_TC; - ll2_info->tx_dest = CORE_TX_DEST_LB; + ll2_info.conn_type = QED_LL2_TYPE_ISCSI_OOO; + ll2_info.mtu = params->mtu; + ll2_info.rx_drop_ttl0_flg = params->drop_ttl0_packets; + ll2_info.rx_vlan_removal_en = params->rx_vlan_stripping; + ll2_info.tx_tc = OOO_LB_TC; + ll2_info.tx_dest = CORE_TX_DEST_LB; - rc = qed_ll2_acquire_connection(hwfn, ll2_info, + rc = qed_ll2_acquire_connection(hwfn, &ll2_info, QED_LL2_RX_SIZE, QED_LL2_TX_SIZE, handle); - kfree(ll2_info); if (rc) { DP_INFO(cdev, "Failed to acquire LL2 OOO connection\n"); goto out; @@ -1006,7 +1002,7 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn, struct qed_ll2_info *p_ll2_conn, u8 action_on_error) { - enum qed_ll2_conn_type conn_type = p_ll2_conn->conn_type; + enum qed_ll2_conn_type conn_type = p_ll2_conn->conn.conn_type; struct qed_ll2_rx_queue *p_rx = &p_ll2_conn->rx_queue; struct core_rx_start_ramrod_data *p_ramrod = NULL; struct qed_spq_entry *p_ent = NULL; @@ -1032,7 +1028,7 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn, p_ramrod->sb_index = p_rx->rx_sb_index; p_ramrod->complete_event_flg = 1; - p_ramrod->mtu = cpu_to_le16(p_ll2_conn->mtu); + p_ramrod->mtu = cpu_to_le16(p_ll2_conn->conn.mtu); DMA_REGPAIR_LE(p_ramrod->bd_base, p_rx->rxq_chain.p_phys_addr); cqe_pbl_size = (u16)qed_chain_get_page_cnt(&p_rx->rcq_chain); @@ -1040,8 +1036,8 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn, DMA_REGPAIR_LE(p_ramrod->cqe_pbl_addr, qed_chain_get_pbl_phys(&p_rx->rcq_chain)); - p_ramrod->drop_ttl0_flg = p_ll2_conn->rx_drop_ttl0_flg; - p_ramrod->inner_vlan_removal_en = p_ll2_conn->rx_vlan_removal_en; + p_ramrod->drop_ttl0_flg = p_ll2_conn->conn.rx_drop_ttl0_flg; + p_ramrod->inner_vlan_removal_en = p_ll2_conn->conn.rx_vlan_removal_en; p_ramrod->queue_id = p_ll2_conn->queue_id; p_ramrod->main_func_queue = (conn_type == QED_LL2_TYPE_ISCSI_OOO) ? 0 : 1; @@ -1056,14 +1052,14 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn, } p_ramrod->action_on_error.error_type = action_on_error; - p_ramrod->gsi_offload_flag = p_ll2_conn->gsi_enable; + p_ramrod->gsi_offload_flag = p_ll2_conn->conn.gsi_enable; return qed_spq_post(p_hwfn, p_ent, NULL); } static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, struct qed_ll2_info *p_ll2_conn) { - enum qed_ll2_conn_type conn_type = p_ll2_conn->conn_type; + enum qed_ll2_conn_type conn_type = p_ll2_conn->conn.conn_type; struct qed_ll2_tx_queue *p_tx = &p_ll2_conn->tx_queue; struct core_tx_start_ramrod_data *p_ramrod = NULL; struct qed_spq_entry *p_ent = NULL; @@ -1075,7 +1071,7 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, if (!QED_LL2_TX_REGISTERED(p_ll2_conn)) return 0; - if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO) + if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO) p_ll2_conn->tx_stats_en = 0; else p_ll2_conn->tx_stats_en = 1; @@ -1096,7 +1092,7 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, p_ramrod->sb_id = cpu_to_le16(qed_int_get_sp_sb_id(p_hwfn)); p_ramrod->sb_index = p_tx->tx_sb_index; - p_ramrod->mtu = cpu_to_le16(p_ll2_conn->mtu); + p_ramrod->mtu = cpu_to_le16(p_ll2_conn->conn.mtu); p_ramrod->stats_en = p_ll2_conn->tx_stats_en; p_ramrod->stats_id = p_ll2_conn->tx_stats_id; @@ -1106,7 +1102,7 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, p_ramrod->pbl_size = cpu_to_le16(pbl_size); memset(&pq_params, 0, sizeof(pq_params)); - pq_params.core.tc = p_ll2_conn->tx_tc; + pq_params.core.tc = p_ll2_conn->conn.tx_tc; pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params); p_ramrod->qm_pq_id = cpu_to_le16(pq_id); @@ -1123,7 +1119,7 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, DP_NOTICE(p_hwfn, "Unknown connection type: %d\n", conn_type); } - p_ramrod->gsi_offload_flag = p_ll2_conn->gsi_enable; + p_ramrod->gsi_offload_flag = p_ll2_conn->conn.gsi_enable; return qed_spq_post(p_hwfn, p_ent, NULL); } @@ -1224,7 +1220,7 @@ qed_ll2_acquire_connection_rx(struct qed_hwfn *p_hwfn, DP_VERBOSE(p_hwfn, QED_MSG_LL2, "Allocated LL2 Rxq [Type %08x] with 0x%08x buffers\n", - p_ll2_info->conn_type, rx_num_desc); + p_ll2_info->conn.conn_type, rx_num_desc); out: return rc; @@ -1262,7 +1258,7 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn, DP_VERBOSE(p_hwfn, QED_MSG_LL2, "Allocated LL2 Txq [Type %08x] with 0x%08x buffers\n", - p_ll2_info->conn_type, tx_num_desc); + p_ll2_info->conn.conn_type, tx_num_desc); out: if (rc) @@ -1273,7 +1269,7 @@ out: } int qed_ll2_acquire_connection(struct qed_hwfn *p_hwfn, - struct qed_ll2_info *p_params, + struct qed_ll2_conn *p_params, u16 rx_num_desc, u16 tx_num_desc, u8 *p_connection_handle) @@ -1302,15 +1298,7 @@ int qed_ll2_acquire_connection(struct qed_hwfn *p_hwfn, if (!p_ll2_info) return -EBUSY; - p_ll2_info->conn_type = p_params->conn_type; - p_ll2_info->mtu = p_params->mtu; - p_ll2_info->rx_drop_ttl0_flg = p_params->rx_drop_ttl0_flg; - p_ll2_info->rx_vlan_removal_en = p_params->rx_vlan_removal_en; - p_ll2_info->tx_tc = p_params->tx_tc; - p_ll2_info->tx_dest = p_params->tx_dest; - p_ll2_info->ai_err_packet_too_big = p_params->ai_err_packet_too_big; - p_ll2_info->ai_err_no_buf = p_params->ai_err_no_buf; - p_ll2_info->gsi_enable = p_params->gsi_enable; + p_ll2_info->conn = *p_params; rc = qed_ll2_acquire_connection_rx(p_hwfn, p_ll2_info, rx_num_desc); if (rc) @@ -1371,9 +1359,9 @@ static int qed_ll2_establish_connection_rx(struct qed_hwfn *p_hwfn, SET_FIELD(action_on_error, CORE_RX_ACTION_ON_ERROR_PACKET_TOO_BIG, - p_ll2_conn->ai_err_packet_too_big); + p_ll2_conn->conn.ai_err_packet_too_big); SET_FIELD(action_on_error, - CORE_RX_ACTION_ON_ERROR_NO_BUFF, p_ll2_conn->ai_err_no_buf); + CORE_RX_ACTION_ON_ERROR_NO_BUFF, p_ll2_conn->conn.ai_err_no_buf); return qed_sp_ll2_rx_queue_start(p_hwfn, p_ll2_conn, action_on_error); } @@ -1600,7 +1588,7 @@ static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, "LL2 [q 0x%02x cid 0x%08x type 0x%08x] Tx Producer at [0x%04x] - set with a %04x bytes %02x BDs buffer at %08x:%08x\n", p_ll2->queue_id, p_ll2->cid, - p_ll2->conn_type, + p_ll2->conn.conn_type, prod_idx, first_frag_len, num_of_bds, @@ -1676,7 +1664,7 @@ static void qed_ll2_tx_packet_notify(struct qed_hwfn *p_hwfn, (NETIF_MSG_TX_QUEUED | QED_MSG_LL2), "LL2 [q 0x%02x cid 0x%08x type 0x%08x] Doorbelled [producer 0x%04x]\n", p_ll2_conn->queue_id, - p_ll2_conn->cid, p_ll2_conn->conn_type, db_msg.spq_prod); + p_ll2_conn->cid, p_ll2_conn->conn.conn_type, db_msg.spq_prod); } int qed_ll2_prepare_tx_packet(struct qed_hwfn *p_hwfn, @@ -1817,7 +1805,7 @@ int qed_ll2_terminate_connection(struct qed_hwfn *p_hwfn, u8 connection_handle) qed_ll2_rxq_flush(p_hwfn, connection_handle); } - if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO) + if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO) qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info); return rc; @@ -1993,7 +1981,7 @@ static void qed_ll2_register_cb_ops(struct qed_dev *cdev, static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params) { - struct qed_ll2_info ll2_info; + struct qed_ll2_conn ll2_info; struct qed_ll2_buffer *buffer, *tmp_buffer; enum qed_ll2_conn_type conn_type; struct qed_ptt *p_ptt; @@ -2041,6 +2029,7 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params) /* Prepare the temporary ll2 information */ memset(&ll2_info, 0, sizeof(ll2_info)); + ll2_info.conn_type = conn_type; ll2_info.mtu = params->mtu; ll2_info.rx_drop_ttl0_flg = params->drop_ttl0_packets; @@ -2120,7 +2109,6 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params) } ether_addr_copy(cdev->ll2_mac_address, params->ll2_mac_address); - return 0; release_terminate_all: diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h index 6625a3ae5a33..31417928b635 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h @@ -112,15 +112,8 @@ struct qed_ll2_tx_queue { bool b_completing_packet; }; -struct qed_ll2_info { - /* Lock protecting the state of LL2 */ - struct mutex mutex; +struct qed_ll2_conn { enum qed_ll2_conn_type conn_type; - u32 cid; - u8 my_id; - u8 queue_id; - u8 tx_stats_id; - bool b_active; u16 mtu; u8 rx_drop_ttl0_flg; u8 rx_vlan_removal_en; @@ -128,10 +121,21 @@ struct qed_ll2_info { enum core_tx_dest tx_dest; enum core_error_handle ai_err_packet_too_big; enum core_error_handle ai_err_no_buf; + u8 gsi_enable; +}; + +struct qed_ll2_info { + /* Lock protecting the state of LL2 */ + struct mutex mutex; + struct qed_ll2_conn conn; + u32 cid; + u8 my_id; + u8 queue_id; + u8 tx_stats_id; + bool b_active; u8 tx_stats_en; struct qed_ll2_rx_queue rx_queue; struct qed_ll2_tx_queue tx_queue; - u8 gsi_enable; }; /** @@ -149,7 +153,7 @@ struct qed_ll2_info { * @return 0 on success, failure otherwise */ int qed_ll2_acquire_connection(struct qed_hwfn *p_hwfn, - struct qed_ll2_info *p_params, + struct qed_ll2_conn *p_params, u16 rx_num_desc, u16 tx_num_desc, u8 *p_connection_handle); diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index 2a16547c8966..2dbdb3298991 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -2632,7 +2632,7 @@ static int qed_roce_ll2_start(struct qed_dev *cdev, { struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); struct qed_roce_ll2_info *roce_ll2; - struct qed_ll2_info ll2_params; + struct qed_ll2_conn ll2_params; int rc; if (!params) { diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 89ac1e3f6175..301f48755093 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -179,6 +179,49 @@ static struct mdiobb_ops bb_ops = { .get_mdio_data = ravb_get_mdio_data, }; +/* Free TX skb function for AVB-IP */ +static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) +{ + struct ravb_private *priv = netdev_priv(ndev); + struct net_device_stats *stats = &priv->stats[q]; + struct ravb_tx_desc *desc; + int free_num = 0; + int entry; + u32 size; + + for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) { + bool txed; + + entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] * + NUM_TX_DESC); + desc = &priv->tx_ring[q][entry]; + txed = desc->die_dt == DT_FEMPTY; + if (free_txed_only && !txed) + break; + /* Descriptor type must be checked before all other reads */ + dma_rmb(); + size = le16_to_cpu(desc->ds_tagl) & TX_DS; + /* Free the original skb. */ + if (priv->tx_skb[q][entry / NUM_TX_DESC]) { + dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), + size, DMA_TO_DEVICE); + /* Last packet descriptor? */ + if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) { + entry /= NUM_TX_DESC; + dev_kfree_skb_any(priv->tx_skb[q][entry]); + priv->tx_skb[q][entry] = NULL; + if (txed) + stats->tx_packets++; + } + free_num++; + } + if (txed) + stats->tx_bytes += size; + desc->die_dt = DT_EEMPTY; + } + return free_num; +} + /* Free skb's and DMA buffers for Ethernet AVB */ static void ravb_ring_free(struct net_device *ndev, int q) { @@ -194,19 +237,21 @@ static void ravb_ring_free(struct net_device *ndev, int q) kfree(priv->rx_skb[q]); priv->rx_skb[q] = NULL; - /* Free TX skb ringbuffer */ - if (priv->tx_skb[q]) { - for (i = 0; i < priv->num_tx_ring[q]; i++) - dev_kfree_skb(priv->tx_skb[q][i]); - } - kfree(priv->tx_skb[q]); - priv->tx_skb[q] = NULL; - /* Free aligned TX buffers */ kfree(priv->tx_align[q]); priv->tx_align[q] = NULL; if (priv->rx_ring[q]) { + for (i = 0; i < priv->num_rx_ring[q]; i++) { + struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i]; + + if (!dma_mapping_error(ndev->dev.parent, + le32_to_cpu(desc->dptr))) + dma_unmap_single(ndev->dev.parent, + le32_to_cpu(desc->dptr), + PKT_BUF_SZ, + DMA_FROM_DEVICE); + } ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1); dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q], @@ -215,12 +260,20 @@ static void ravb_ring_free(struct net_device *ndev, int q) } if (priv->tx_ring[q]) { + ravb_tx_free(ndev, q, false); + ring_size = sizeof(struct ravb_tx_desc) * (priv->num_tx_ring[q] * NUM_TX_DESC + 1); dma_free_coherent(ndev->dev.parent, ring_size, priv->tx_ring[q], priv->tx_desc_dma[q]); priv->tx_ring[q] = NULL; } + + /* Free TX skb ringbuffer. + * SKBs are freed by ravb_tx_free() call above. + */ + kfree(priv->tx_skb[q]); + priv->tx_skb[q] = NULL; } /* Format skb and descriptor buffer for Ethernet AVB */ @@ -431,44 +484,6 @@ static int ravb_dmac_init(struct net_device *ndev) return 0; } -/* Free TX skb function for AVB-IP */ -static int ravb_tx_free(struct net_device *ndev, int q) -{ - struct ravb_private *priv = netdev_priv(ndev); - struct net_device_stats *stats = &priv->stats[q]; - struct ravb_tx_desc *desc; - int free_num = 0; - int entry; - u32 size; - - for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) { - entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] * - NUM_TX_DESC); - desc = &priv->tx_ring[q][entry]; - if (desc->die_dt != DT_FEMPTY) - break; - /* Descriptor type must be checked before all other reads */ - dma_rmb(); - size = le16_to_cpu(desc->ds_tagl) & TX_DS; - /* Free the original skb. */ - if (priv->tx_skb[q][entry / NUM_TX_DESC]) { - dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - size, DMA_TO_DEVICE); - /* Last packet descriptor? */ - if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) { - entry /= NUM_TX_DESC; - dev_kfree_skb_any(priv->tx_skb[q][entry]); - priv->tx_skb[q][entry] = NULL; - stats->tx_packets++; - } - free_num++; - } - stats->tx_bytes += size; - desc->die_dt = DT_EEMPTY; - } - return free_num; -} - static void ravb_get_tx_tstamp(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); @@ -902,7 +917,7 @@ static int ravb_poll(struct napi_struct *napi, int budget) spin_lock_irqsave(&priv->lock, flags); /* Clear TX interrupt */ ravb_write(ndev, ~mask, TIS); - ravb_tx_free(ndev, q); + ravb_tx_free(ndev, q, true); netif_wake_subqueue(ndev, q); mmiowb(); spin_unlock_irqrestore(&priv->lock, flags); @@ -1567,7 +1582,8 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) priv->cur_tx[q] += NUM_TX_DESC; if (priv->cur_tx[q] - priv->dirty_tx[q] > - (priv->num_tx_ring[q] - 1) * NUM_TX_DESC && !ravb_tx_free(ndev, q)) + (priv->num_tx_ring[q] - 1) * NUM_TX_DESC && + !ravb_tx_free(ndev, q, true)) netif_stop_subqueue(ndev, q); exit: diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 082cd48db6a7..36942f5a6a53 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -351,6 +351,7 @@ void stmmac_remove_config_dt(struct platform_device *pdev, if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); of_node_put(plat->phy_node); + of_node_put(plat->mdio_node); } #else struct plat_stmmacenet_data * diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 8b6810bad54b..99d3df788ce8 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -69,7 +69,6 @@ struct gtp_dev { struct socket *sock0; struct socket *sock1u; - struct net *net; struct net_device *dev; unsigned int hash_size; @@ -316,7 +315,7 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk); - xnet = !net_eq(gtp->net, dev_net(gtp->dev)); + xnet = !net_eq(sock_net(sk), dev_net(gtp->dev)); switch (udp_sk(sk)->encap_type) { case UDP_ENCAP_GTP0: @@ -612,7 +611,7 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) pktinfo.fl4.saddr, pktinfo.fl4.daddr, pktinfo.iph->tos, ip4_dst_hoplimit(&pktinfo.rt->dst), - htons(IP_DF), + 0, pktinfo.gtph_port, pktinfo.gtph_port, true, false); break; @@ -658,7 +657,7 @@ static void gtp_link_setup(struct net_device *dev) static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); static void gtp_hashtable_free(struct gtp_dev *gtp); static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp, - int fd_gtp0, int fd_gtp1, struct net *src_net); + int fd_gtp0, int fd_gtp1); static int gtp_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) @@ -675,7 +674,7 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, fd0 = nla_get_u32(data[IFLA_GTP_FD0]); fd1 = nla_get_u32(data[IFLA_GTP_FD1]); - err = gtp_encap_enable(dev, gtp, fd0, fd1, src_net); + err = gtp_encap_enable(dev, gtp, fd0, fd1); if (err < 0) goto out_err; @@ -821,7 +820,7 @@ static void gtp_hashtable_free(struct gtp_dev *gtp) } static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp, - int fd_gtp0, int fd_gtp1, struct net *src_net) + int fd_gtp0, int fd_gtp1) { struct udp_tunnel_sock_cfg tuncfg = {NULL}; struct socket *sock0, *sock1u; @@ -858,7 +857,6 @@ static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp, gtp->sock0 = sock0; gtp->sock1u = sock1u; - gtp->net = src_net; tuncfg.sk_user_data = gtp; tuncfg.encap_rcv = gtp_encap_recv; @@ -1376,3 +1374,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte "); MODULE_DESCRIPTION("Interface driver for GTP encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("gtp"); +MODULE_ALIAS_GENL_FAMILY("gtp"); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 5c26653eceb5..402618565838 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -825,7 +825,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, return -EINVAL; if (virtio_net_hdr_from_skb(skb, &vnet_hdr, - macvtap_is_little_endian(q))) + macvtap_is_little_endian(q), true)) BUG(); if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) != diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index e741bf614c4e..b0492ef2cdaa 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -21,6 +21,23 @@ MODULE_DESCRIPTION("Broadcom 63xx internal PHY driver"); MODULE_AUTHOR("Maxime Bizon "); MODULE_LICENSE("GPL"); +static int bcm63xx_config_intr(struct phy_device *phydev) +{ + int reg, err; + + reg = phy_read(phydev, MII_BCM63XX_IR); + if (reg < 0) + return reg; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + reg &= ~MII_BCM63XX_IR_GMASK; + else + reg |= MII_BCM63XX_IR_GMASK; + + err = phy_write(phydev, MII_BCM63XX_IR, reg); + return err; +} + static int bcm63xx_config_init(struct phy_device *phydev) { int reg, err; @@ -55,7 +72,7 @@ static struct phy_driver bcm63xx_driver[] = { .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = bcm_phy_ack_intr, - .config_intr = bcm_phy_config_intr, + .config_intr = bcm63xx_config_intr, }, { /* same phy as above, with just a different OUI */ .phy_id = 0x002bdc00, @@ -67,7 +84,7 @@ static struct phy_driver bcm63xx_driver[] = { .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = bcm_phy_ack_intr, - .config_intr = bcm_phy_config_intr, + .config_intr = bcm63xx_config_intr, } }; module_phy_driver(bcm63xx_driver); diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c index 800b39f06279..a10d0e7fc5f7 100644 --- a/drivers/net/phy/dp83848.c +++ b/drivers/net/phy/dp83848.c @@ -17,6 +17,7 @@ #include #define TI_DP83848C_PHY_ID 0x20005ca0 +#define TI_DP83620_PHY_ID 0x20005ce0 #define NS_DP83848C_PHY_ID 0x20005c90 #define TLK10X_PHY_ID 0x2000a210 #define TI_DP83822_PHY_ID 0x2000a240 @@ -77,6 +78,7 @@ static int dp83848_config_intr(struct phy_device *phydev) static struct mdio_device_id __maybe_unused dp83848_tbl[] = { { TI_DP83848C_PHY_ID, 0xfffffff0 }, { NS_DP83848C_PHY_ID, 0xfffffff0 }, + { TI_DP83620_PHY_ID, 0xfffffff0 }, { TLK10X_PHY_ID, 0xfffffff0 }, { TI_DP83822_PHY_ID, 0xfffffff0 }, { } @@ -106,6 +108,7 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl); static struct phy_driver dp83848_driver[] = { DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY"), DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"), + DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY"), DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"), DP83848_PHY_DRIVER(TI_DP83822_PHY_ID, "TI DP83822 10/100 Mbps PHY"), }; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 0b78210c0fa7..ed0d235cf850 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1679,6 +1679,8 @@ static struct phy_driver marvell_drivers[] = { .ack_interrupt = &marvell_ack_interrupt, .config_intr = &marvell_config_intr, .did_interrupt = &m88e1121_did_interrupt, + .get_wol = &m88e1318_get_wol, + .set_wol = &m88e1318_set_wol, .resume = &marvell_resume, .suspend = &marvell_suspend, .get_sset_count = marvell_get_sset_count, diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 9a77289109b7..e55809c5beb7 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1008,6 +1008,20 @@ static struct phy_driver ksphy_driver[] = { .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, +}, { + .phy_id = PHY_ID_KSZ8795, + .phy_id_mask = MICREL_PHY_ID_MASK, + .name = "Micrel KSZ8795", + .features = (SUPPORTED_Pause | SUPPORTED_Asym_Pause), + .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, + .config_init = kszphy_config_init, + .config_aneg = ksz8873mll_config_aneg, + .read_status = ksz8873mll_read_status, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, + .suspend = genphy_suspend, + .resume = genphy_resume, } }; module_phy_driver(ksphy_driver); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 48da6e93c3f7..7cc1b7dcfe05 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -649,14 +650,18 @@ void phy_start_machine(struct phy_device *phydev) * phy_trigger_machine - trigger the state machine to run * * @phydev: the phy_device struct + * @sync: indicate whether we should wait for the workqueue cancelation * * Description: There has been a change in state which requires that the * state machine runs. */ -static void phy_trigger_machine(struct phy_device *phydev) +static void phy_trigger_machine(struct phy_device *phydev, bool sync) { - cancel_delayed_work_sync(&phydev->state_queue); + if (sync) + cancel_delayed_work_sync(&phydev->state_queue); + else + cancel_delayed_work(&phydev->state_queue); queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0); } @@ -693,7 +698,7 @@ static void phy_error(struct phy_device *phydev) phydev->state = PHY_HALTED; mutex_unlock(&phydev->lock); - phy_trigger_machine(phydev); + phy_trigger_machine(phydev, false); } /** @@ -840,7 +845,7 @@ void phy_change(struct phy_device *phydev) } /* reschedule state queue work to run as soon as possible */ - phy_trigger_machine(phydev); + phy_trigger_machine(phydev, true); return; ignore: @@ -942,7 +947,7 @@ void phy_start(struct phy_device *phydev) if (do_resume) phy_resume(phydev); - phy_trigger_machine(phydev); + phy_trigger_machine(phydev, true); } EXPORT_SYMBOL(phy_start); diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c index fa62bdf2f526..94ca42e630bb 100644 --- a/drivers/net/phy/phy_led_triggers.c +++ b/drivers/net/phy/phy_led_triggers.c @@ -12,6 +12,7 @@ */ #include #include +#include #include static struct phy_led_trigger *phy_speed_to_led_trigger(struct phy_device *phy, @@ -102,8 +103,10 @@ int phy_led_triggers_register(struct phy_device *phy) sizeof(struct phy_led_trigger) * phy->phy_num_led_triggers, GFP_KERNEL); - if (!phy->phy_led_triggers) - return -ENOMEM; + if (!phy->phy_led_triggers) { + err = -ENOMEM; + goto out_clear; + } for (i = 0; i < phy->phy_num_led_triggers; i++) { err = phy_led_trigger_register(phy, &phy->phy_led_triggers[i], @@ -120,6 +123,8 @@ out_unreg: while (i--) phy_led_trigger_unregister(&phy->phy_led_triggers[i]); devm_kfree(&phy->mdio.dev, phy->phy_led_triggers); +out_clear: + phy->phy_num_led_triggers = 0; return err; } EXPORT_SYMBOL_GPL(phy_led_triggers_register); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index cd8e02c94be0..2cd10b26b650 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1360,7 +1360,7 @@ static ssize_t tun_put_user(struct tun_struct *tun, return -EINVAL; if (virtio_net_hdr_from_skb(skb, &gso, - tun_is_little_endian(tun))) { + tun_is_little_endian(tun), true)) { struct skb_shared_info *sinfo = skb_shinfo(skb); pr_err("unexpected GSO type: " "0x%x, gso_size %d, hdr_len %d\n", diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index fe7b2886cb6b..86144f9a80ee 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -531,6 +531,7 @@ static const struct driver_info wwan_info = { #define SAMSUNG_VENDOR_ID 0x04e8 #define LENOVO_VENDOR_ID 0x17ef #define NVIDIA_VENDOR_ID 0x0955 +#define HP_VENDOR_ID 0x03f0 static const struct usb_device_id products[] = { /* BLACKLIST !! @@ -677,6 +678,13 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +/* HP lt2523 (Novatel E371) - handled by qmi_wwan */ +{ + USB_DEVICE_AND_INTERFACE_INFO(HP_VENDOR_ID, 0x421d, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* AnyDATA ADU960S - handled by qmi_wwan */ { USB_DEVICE_AND_INTERFACE_INFO(0x16d5, 0x650a, USB_CLASS_COMM, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6fe1cdb0174f..24d5272cdce5 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -654,6 +654,13 @@ static const struct usb_device_id products[] = { USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&qmi_wwan_info, }, + { /* HP lt2523 (Novatel E371) */ + USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&qmi_wwan_info, + }, { /* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */ USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7), .driver_info = (unsigned long)&qmi_wwan_info, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index f3b48ad90865..ad42295356dd 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -32,7 +32,7 @@ #define NETNEXT_VERSION "08" /* Information for net */ -#define NET_VERSION "6" +#define NET_VERSION "8" #define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION #define DRIVER_AUTHOR "Realtek linux nic maintainers " @@ -1936,6 +1936,9 @@ static int r8152_poll(struct napi_struct *napi, int budget) napi_complete(napi); if (!list_empty(&tp->rx_done)) napi_schedule(napi); + else if (!skb_queue_empty(&tp->tx_queue) && + !list_empty(&tp->tx_free)) + napi_schedule(napi); } return work_done; @@ -3155,10 +3158,13 @@ static void set_carrier(struct r8152 *tp) if (!netif_carrier_ok(netdev)) { tp->rtl_ops.enable(tp); set_bit(RTL8152_SET_RX_MODE, &tp->flags); + netif_stop_queue(netdev); napi_disable(&tp->napi); netif_carrier_on(netdev); rtl_start_rx(tp); napi_enable(&tp->napi); + netif_wake_queue(netdev); + netif_info(tp, link, netdev, "carrier on\n"); } } else { if (netif_carrier_ok(netdev)) { @@ -3166,6 +3172,7 @@ static void set_carrier(struct r8152 *tp) napi_disable(&tp->napi); tp->rtl_ops.disable(tp); napi_enable(&tp->napi); + netif_info(tp, link, netdev, "carrier off\n"); } } } @@ -3515,12 +3522,12 @@ static int rtl8152_pre_reset(struct usb_interface *intf) if (!netif_running(netdev)) return 0; + netif_stop_queue(netdev); napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); if (netif_carrier_ok(netdev)) { - netif_stop_queue(netdev); mutex_lock(&tp->control); tp->rtl_ops.disable(tp); mutex_unlock(&tp->control); @@ -3545,12 +3552,17 @@ static int rtl8152_post_reset(struct usb_interface *intf) if (netif_carrier_ok(netdev)) { mutex_lock(&tp->control); tp->rtl_ops.enable(tp); + rtl_start_rx(tp); rtl8152_set_rx_mode(netdev); mutex_unlock(&tp->control); - netif_wake_queue(netdev); } napi_enable(&tp->napi); + netif_wake_queue(netdev); + usb_submit_urb(tp->intr_urb, GFP_KERNEL); + + if (!list_empty(&tp->rx_done)) + napi_schedule(&tp->napi); return 0; } @@ -3572,6 +3584,8 @@ static bool delay_autosuspend(struct r8152 *tp) */ if (!sw_linking && tp->rtl_ops.in_nway(tp)) return true; + else if (!skb_queue_empty(&tp->tx_queue)) + return true; else return false; } @@ -3581,10 +3595,15 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp) struct net_device *netdev = tp->netdev; int ret = 0; + set_bit(SELECTIVE_SUSPEND, &tp->flags); + smp_mb__after_atomic(); + if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) { u32 rcr = 0; if (delay_autosuspend(tp)) { + clear_bit(SELECTIVE_SUSPEND, &tp->flags); + smp_mb__after_atomic(); ret = -EBUSY; goto out1; } @@ -3601,6 +3620,8 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp) if (!(ocp_data & RXFIFO_EMPTY)) { rxdy_gated_en(tp, false); ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr); + clear_bit(SELECTIVE_SUSPEND, &tp->flags); + smp_mb__after_atomic(); ret = -EBUSY; goto out1; } @@ -3620,8 +3641,6 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp) } } - set_bit(SELECTIVE_SUSPEND, &tp->flags); - out1: return ret; } @@ -3677,12 +3696,15 @@ static int rtl8152_resume(struct usb_interface *intf) if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) { if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { tp->rtl_ops.autosuspend_en(tp, false); - clear_bit(SELECTIVE_SUSPEND, &tp->flags); napi_disable(&tp->napi); set_bit(WORK_ENABLE, &tp->flags); if (netif_carrier_ok(tp->netdev)) rtl_start_rx(tp); napi_enable(&tp->napi); + clear_bit(SELECTIVE_SUSPEND, &tp->flags); + smp_mb__after_atomic(); + if (!list_empty(&tp->rx_done)) + napi_schedule(&tp->napi); } else { tp->rtl_ops.up(tp); netif_carrier_off(tp->netdev); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 4a105006ca63..765c2d6358da 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -48,8 +48,16 @@ module_param(gso, bool, 0444); */ DECLARE_EWMA(pkt_len, 1, 64) +/* With mergeable buffers we align buffer address and use the low bits to + * encode its true size. Buffer size is up to 1 page so we need to align to + * square root of page size to ensure we reserve enough bits to encode the true + * size. + */ +#define MERGEABLE_BUFFER_MIN_ALIGN_SHIFT ((PAGE_SHIFT + 1) / 2) + /* Minimum alignment for mergeable packet buffers. */ -#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, 256) +#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, \ + 1 << MERGEABLE_BUFFER_MIN_ALIGN_SHIFT) #define VIRTNET_DRIVER_VERSION "1.0.0" @@ -1104,7 +1112,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) hdr = skb_vnet_hdr(skb); if (virtio_net_hdr_from_skb(skb, &hdr->hdr, - virtio_is_little_endian(vi->vdev))) + virtio_is_little_endian(vi->vdev), false)) BUG(); if (vi->mergeable_rx_bufs) @@ -1707,6 +1715,11 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog) u16 xdp_qp = 0, curr_qp; int i, err; + if (prog && prog->xdp_adjust_head) { + netdev_warn(dev, "Does not support bpf_xdp_adjust_head()\n"); + return -EOPNOTSUPP; + } + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) || @@ -1890,8 +1903,12 @@ static void free_receive_page_frags(struct virtnet_info *vi) put_page(vi->rq[i].alloc_frag.page); } -static bool is_xdp_queue(struct virtnet_info *vi, int q) +static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) { + /* For small receive mode always use kfree_skb variants */ + if (!vi->mergeable_rx_bufs) + return false; + if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) return false; else if (q < vi->curr_queue_pairs) @@ -1908,7 +1925,7 @@ static void free_unused_bufs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) { - if (!is_xdp_queue(vi, i)) + if (!is_xdp_raw_buffer_queue(vi, i)) dev_kfree_skb(buf); else put_page(virt_to_head_page(buf)); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ca7196c40060..50b62db213b0 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2268,7 +2268,7 @@ static void vxlan_cleanup(unsigned long arg) = container_of(p, struct vxlan_fdb, hlist); unsigned long timeout; - if (f->state & NUD_PERMANENT) + if (f->state & (NUD_PERMANENT | NUD_NOARP)) continue; timeout = f->used + vxlan->cfg.age_interval * HZ; @@ -2354,7 +2354,7 @@ static int vxlan_open(struct net_device *dev) } /* Purge the forwarding table */ -static void vxlan_flush(struct vxlan_dev *vxlan) +static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all) { unsigned int h; @@ -2364,6 +2364,8 @@ static void vxlan_flush(struct vxlan_dev *vxlan) hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); + if (!do_all && (f->state & (NUD_PERMANENT | NUD_NOARP))) + continue; /* the all_zeros_mac entry is deleted at vxlan_uninit */ if (!is_zero_ether_addr(f->eth_addr)) vxlan_fdb_destroy(vxlan, f); @@ -2385,7 +2387,7 @@ static int vxlan_stop(struct net_device *dev) del_timer_sync(&vxlan->age_timer); - vxlan_flush(vxlan); + vxlan_flush(vxlan, false); vxlan_sock_release(vxlan); return ret; @@ -2890,7 +2892,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, memcpy(&vxlan->cfg, conf, sizeof(*conf)); if (!vxlan->cfg.dst_port) { if (conf->flags & VXLAN_F_GPE) - vxlan->cfg.dst_port = 4790; /* IANA assigned VXLAN-GPE port */ + vxlan->cfg.dst_port = htons(4790); /* IANA VXLAN-GPE port */ else vxlan->cfg.dst_port = default_port; } @@ -3058,6 +3060,8 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head) struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + vxlan_flush(vxlan, true); + spin_lock(&vn->sock_lock); if (!hlist_unhashed(&vxlan->hlist)) hlist_del_rcu(&vxlan->hlist); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index e30ffd29b7e9..579521327b03 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -221,18 +221,18 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); struct xenvif_queue *queue = NULL; - unsigned int num_queues = vif->num_queues; unsigned long rx_bytes = 0; unsigned long rx_packets = 0; unsigned long tx_bytes = 0; unsigned long tx_packets = 0; unsigned int index; + spin_lock(&vif->lock); if (vif->queues == NULL) goto out; /* Aggregate tx and rx stats from each queue */ - for (index = 0; index < num_queues; ++index) { + for (index = 0; index < vif->num_queues; ++index) { queue = &vif->queues[index]; rx_bytes += queue->stats.rx_bytes; rx_packets += queue->stats.rx_packets; @@ -241,6 +241,8 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev) } out: + spin_unlock(&vif->lock); + vif->dev->stats.rx_bytes = rx_bytes; vif->dev->stats.rx_packets = rx_packets; vif->dev->stats.tx_bytes = tx_bytes; diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 3124eaec9427..85b742e1c42f 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -493,11 +493,22 @@ static int backend_create_xenvif(struct backend_info *be) static void backend_disconnect(struct backend_info *be) { if (be->vif) { + unsigned int queue_index; + xen_unregister_watchers(be->vif); #ifdef CONFIG_DEBUG_FS xenvif_debugfs_delif(be->vif); #endif /* CONFIG_DEBUG_FS */ xenvif_disconnect_data(be->vif); + for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index) + xenvif_deinit_queue(&be->vif->queues[queue_index]); + + spin_lock(&be->vif->lock); + vfree(be->vif->queues); + be->vif->num_queues = 0; + be->vif->queues = NULL; + spin_unlock(&be->vif->lock); + xenvif_disconnect_ctrl(be->vif); } } @@ -1034,6 +1045,8 @@ static void connect(struct backend_info *be) err: if (be->vif->num_queues > 0) xenvif_disconnect_data(be->vif); /* Clean up existing queues */ + for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index) + xenvif_deinit_queue(&be->vif->queues[queue_index]); vfree(be->vif->queues); be->vif->queues = NULL; be->vif->num_queues = 0; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index a479cd99911d..8315fe73ecd0 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -321,7 +321,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue) queue->rx.req_prod_pvt = req_prod; /* Not enough requests? Try again later. */ - if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN) { + if (req_prod - queue->rx.sring->req_prod < NET_RX_SLOTS_MIN) { mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10)); return; } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index fcc9dcfdf675..e65041c640cb 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1663,13 +1663,13 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq, return 0; freq->sg_table.sgl = freq->first_sgl; - ret = sg_alloc_table_chained(&freq->sg_table, rq->nr_phys_segments, - freq->sg_table.sgl); + ret = sg_alloc_table_chained(&freq->sg_table, + blk_rq_nr_phys_segments(rq), freq->sg_table.sgl); if (ret) return -ENOMEM; op->nents = blk_rq_map_sg(rq->q, rq, freq->sg_table.sgl); - WARN_ON(op->nents > rq->nr_phys_segments); + WARN_ON(op->nents > blk_rq_nr_phys_segments(rq)); dir = (rq_data_dir(rq) == WRITE) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; freq->sg_cnt = fc_dma_map_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents, dir); diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 6f5074153dcd..be8c800078e2 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -631,6 +631,7 @@ static void nvmet_subsys_release(struct config_item *item) { struct nvmet_subsys *subsys = to_subsys(item); + nvmet_subsys_del_ctrls(subsys); nvmet_subsys_put(subsys); } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index b1d66ed655c9..fc5ba2f9e15f 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -200,7 +200,7 @@ static void nvmet_keep_alive_timer(struct work_struct *work) pr_err("ctrl %d keep-alive timer (%d seconds) expired!\n", ctrl->cntlid, ctrl->kato); - ctrl->ops->delete_ctrl(ctrl); + nvmet_ctrl_fatal_error(ctrl); } static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl) @@ -816,6 +816,9 @@ static void nvmet_ctrl_free(struct kref *ref) list_del(&ctrl->subsys_entry); mutex_unlock(&subsys->lock); + flush_work(&ctrl->async_event_work); + cancel_work_sync(&ctrl->fatal_err_work); + ida_simple_remove(&subsys->cntlid_ida, ctrl->cntlid); nvmet_subsys_put(subsys); @@ -935,6 +938,16 @@ static void nvmet_subsys_free(struct kref *ref) kfree(subsys); } +void nvmet_subsys_del_ctrls(struct nvmet_subsys *subsys) +{ + struct nvmet_ctrl *ctrl; + + mutex_lock(&subsys->lock); + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) + ctrl->ops->delete_ctrl(ctrl); + mutex_unlock(&subsys->lock); +} + void nvmet_subsys_put(struct nvmet_subsys *subsys) { kref_put(&subsys->ref, nvmet_subsys_free); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 173e842f19c9..ba57f9852bde 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1314,7 +1314,7 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, (struct fcnvme_ls_disconnect_rqst *)iod->rqstbuf; struct fcnvme_ls_disconnect_acc *acc = (struct fcnvme_ls_disconnect_acc *)iod->rspbuf; - struct nvmet_fc_tgt_queue *queue; + struct nvmet_fc_tgt_queue *queue = NULL; struct nvmet_fc_tgt_assoc *assoc; int ret = 0; bool del_assoc = false; @@ -1348,7 +1348,18 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, assoc = nvmet_fc_find_target_assoc(tgtport, be64_to_cpu(rqst->associd.association_id)); iod->assoc = assoc; - if (!assoc) + if (assoc) { + if (rqst->discon_cmd.scope == + FCNVME_DISCONN_CONNECTION) { + queue = nvmet_fc_find_target_queue(tgtport, + be64_to_cpu( + rqst->discon_cmd.id)); + if (!queue) { + nvmet_fc_tgt_a_put(assoc); + ret = VERR_NO_CONN; + } + } + } else ret = VERR_NO_ASSOC; } @@ -1373,21 +1384,18 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, FCNVME_LS_DISCONNECT); - if (rqst->discon_cmd.scope == FCNVME_DISCONN_CONNECTION) { - queue = nvmet_fc_find_target_queue(tgtport, - be64_to_cpu(rqst->discon_cmd.id)); - if (queue) { - int qid = queue->qid; + /* are we to delete a Connection ID (queue) */ + if (queue) { + int qid = queue->qid; - nvmet_fc_delete_target_queue(queue); + nvmet_fc_delete_target_queue(queue); - /* release the get taken by find_target_queue */ - nvmet_fc_tgt_q_put(queue); + /* release the get taken by find_target_queue */ + nvmet_fc_tgt_q_put(queue); - /* tear association down if io queue terminated */ - if (!qid) - del_assoc = true; - } + /* tear association down if io queue terminated */ + if (!qid) + del_assoc = true; } /* release get taken in nvmet_fc_find_target_assoc */ diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 23d5eb1c944f..cc7ad06b43a7 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -282,6 +282,7 @@ void nvmet_ctrl_put(struct nvmet_ctrl *ctrl); struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, enum nvme_subsys_type type); void nvmet_subsys_put(struct nvmet_subsys *subsys); +void nvmet_subsys_del_ctrls(struct nvmet_subsys *subsys); struct nvmet_ns *nvmet_find_namespace(struct nvmet_ctrl *ctrl, __le32 nsid); void nvmet_put_namespace(struct nvmet_ns *ns); diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 8c3760a78ac0..60990220bd83 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -438,6 +438,10 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev, { struct ib_recv_wr *bad_wr; + ib_dma_sync_single_for_device(ndev->device, + cmd->sge[0].addr, cmd->sge[0].length, + DMA_FROM_DEVICE); + if (ndev->srq) return ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr); return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr); @@ -538,6 +542,11 @@ static void nvmet_rdma_queue_response(struct nvmet_req *req) first_wr = &rsp->send_wr; nvmet_rdma_post_recv(rsp->queue->dev, rsp->cmd); + + ib_dma_sync_single_for_device(rsp->queue->dev->device, + rsp->send_sge.addr, rsp->send_sge.length, + DMA_TO_DEVICE); + if (ib_post_send(cm_id->qp, first_wr, &bad_wr)) { pr_err("sending cmd response failed\n"); nvmet_rdma_release_rsp(rsp); @@ -698,6 +707,14 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue, cmd->n_rdma = 0; cmd->req.port = queue->port; + + ib_dma_sync_single_for_cpu(queue->dev->device, + cmd->cmd->sge[0].addr, cmd->cmd->sge[0].length, + DMA_FROM_DEVICE); + ib_dma_sync_single_for_cpu(queue->dev->device, + cmd->send_sge.addr, cmd->send_sge.length, + DMA_TO_DEVICE); + if (!nvmet_req_init(&cmd->req, &queue->nvme_cq, &queue->nvme_sq, &nvmet_rdma_ops)) return; diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c index dd6d4ccb41e4..3858b87fd0bb 100644 --- a/drivers/parport/parport_gsc.c +++ b/drivers/parport/parport_gsc.c @@ -293,7 +293,7 @@ struct parport *parport_gsc_probe_port(unsigned long base, p->irq = PARPORT_IRQ_NONE; } if (p->irq != PARPORT_IRQ_NONE) { - printk(", irq %d", p->irq); + pr_cont(", irq %d", p->irq); if (p->dma == PARPORT_DMA_AUTO) { p->dma = PARPORT_DMA_NONE; @@ -303,8 +303,8 @@ struct parport *parport_gsc_probe_port(unsigned long base, is mandatory (see above) */ p->dma = PARPORT_DMA_NONE; - printk(" ["); -#define printmode(x) {if(p->modes&PARPORT_MODE_##x){printk("%s%s",f?",":"",#x);f++;}} + pr_cont(" ["); +#define printmode(x) {if(p->modes&PARPORT_MODE_##x){pr_cont("%s%s",f?",":"",#x);f++;}} { int f = 0; printmode(PCSPP); @@ -315,7 +315,7 @@ struct parport *parport_gsc_probe_port(unsigned long base, // printmode(DMA); } #undef printmode - printk("]\n"); + pr_cont("]\n"); if (p->irq != PARPORT_IRQ_NONE) { if (request_irq (p->irq, parport_irq_handler, diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index 37300634b7d2..c123488266ce 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -1092,6 +1092,7 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset, enum pin_config_param param = pinconf_to_config_param(*config); void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG); void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG); + void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG); unsigned long flags; u32 conf, pull, val, debounce; u16 arg = 0; @@ -1128,7 +1129,7 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset, return -EINVAL; raw_spin_lock_irqsave(&vg->lock, flags); - debounce = readl(byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG)); + debounce = readl(db_reg); raw_spin_unlock_irqrestore(&vg->lock, flags); switch (debounce & BYT_DEBOUNCE_PULSE_MASK) { @@ -1176,6 +1177,7 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev, unsigned int param, arg; void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG); void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG); + void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG); unsigned long flags; u32 conf, val, debounce; int i, ret = 0; @@ -1238,36 +1240,40 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev, break; case PIN_CONFIG_INPUT_DEBOUNCE: - debounce = readl(byt_gpio_reg(vg, offset, - BYT_DEBOUNCE_REG)); - conf &= ~BYT_DEBOUNCE_PULSE_MASK; + debounce = readl(db_reg); + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; switch (arg) { + case 0: + conf &= BYT_DEBOUNCE_EN; + break; case 375: - conf |= BYT_DEBOUNCE_PULSE_375US; + debounce |= BYT_DEBOUNCE_PULSE_375US; break; case 750: - conf |= BYT_DEBOUNCE_PULSE_750US; + debounce |= BYT_DEBOUNCE_PULSE_750US; break; case 1500: - conf |= BYT_DEBOUNCE_PULSE_1500US; + debounce |= BYT_DEBOUNCE_PULSE_1500US; break; case 3000: - conf |= BYT_DEBOUNCE_PULSE_3MS; + debounce |= BYT_DEBOUNCE_PULSE_3MS; break; case 6000: - conf |= BYT_DEBOUNCE_PULSE_6MS; + debounce |= BYT_DEBOUNCE_PULSE_6MS; break; case 12000: - conf |= BYT_DEBOUNCE_PULSE_12MS; + debounce |= BYT_DEBOUNCE_PULSE_12MS; break; case 24000: - conf |= BYT_DEBOUNCE_PULSE_24MS; + debounce |= BYT_DEBOUNCE_PULSE_24MS; break; default: ret = -EINVAL; } + if (!ret) + writel(debounce, db_reg); break; default: ret = -ENOTSUPP; @@ -1617,6 +1623,8 @@ static void byt_gpio_irq_handler(struct irq_desc *desc) static void byt_gpio_irq_init_hw(struct byt_gpio *vg) { + struct gpio_chip *gc = &vg->chip; + struct device *dev = &vg->pdev->dev; void __iomem *reg; u32 base, value; int i; @@ -1638,10 +1646,12 @@ static void byt_gpio_irq_init_hw(struct byt_gpio *vg) } value = readl(reg); - if ((value & BYT_PIN_MUX) == byt_get_gpio_mux(vg, i) && - !(value & BYT_DIRECT_IRQ_EN)) { + if (value & BYT_DIRECT_IRQ_EN) { + clear_bit(i, gc->irq_valid_mask); + dev_dbg(dev, "excluding GPIO %d from IRQ domain\n", i); + } else if ((value & BYT_PIN_MUX) == byt_get_gpio_mux(vg, i)) { byt_gpio_clear_triggering(vg, i); - dev_dbg(&vg->pdev->dev, "disabling GPIO %d\n", i); + dev_dbg(dev, "disabling GPIO %d\n", i); } } @@ -1680,6 +1690,7 @@ static int byt_gpio_probe(struct byt_gpio *vg) gc->can_sleep = false; gc->parent = &vg->pdev->dev; gc->ngpio = vg->soc_data->npins; + gc->irq_need_valid_mask = true; #ifdef CONFIG_PM_SLEEP vg->saved_context = devm_kcalloc(&vg->pdev->dev, gc->ngpio, diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c index 59cb7a6fc5be..901b356b09d7 100644 --- a/drivers/pinctrl/intel/pinctrl-broxton.c +++ b/drivers/pinctrl/intel/pinctrl-broxton.c @@ -19,7 +19,7 @@ #define BXT_PAD_OWN 0x020 #define BXT_HOSTSW_OWN 0x080 -#define BXT_PADCFGLOCK 0x090 +#define BXT_PADCFGLOCK 0x060 #define BXT_GPI_IE 0x110 #define BXT_COMMUNITY(s, e) \ diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 1e139672f1af..6df35dcb29ae 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -353,6 +353,21 @@ static int intel_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned function, return 0; } +static void __intel_gpio_set_direction(void __iomem *padcfg0, bool input) +{ + u32 value; + + value = readl(padcfg0); + if (input) { + value &= ~PADCFG0_GPIORXDIS; + value |= PADCFG0_GPIOTXDIS; + } else { + value &= ~PADCFG0_GPIOTXDIS; + value |= PADCFG0_GPIORXDIS; + } + writel(value, padcfg0); +} + static int intel_gpio_request_enable(struct pinctrl_dev *pctldev, struct pinctrl_gpio_range *range, unsigned pin) @@ -375,11 +390,11 @@ static int intel_gpio_request_enable(struct pinctrl_dev *pctldev, /* Disable SCI/SMI/NMI generation */ value &= ~(PADCFG0_GPIROUTIOXAPIC | PADCFG0_GPIROUTSCI); value &= ~(PADCFG0_GPIROUTSMI | PADCFG0_GPIROUTNMI); - /* Disable TX buffer and enable RX (this will be input) */ - value &= ~PADCFG0_GPIORXDIS; - value |= PADCFG0_GPIOTXDIS; writel(value, padcfg0); + /* Disable TX buffer and enable RX (this will be input) */ + __intel_gpio_set_direction(padcfg0, true); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; @@ -392,18 +407,11 @@ static int intel_gpio_set_direction(struct pinctrl_dev *pctldev, struct intel_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev); void __iomem *padcfg0; unsigned long flags; - u32 value; raw_spin_lock_irqsave(&pctrl->lock, flags); padcfg0 = intel_get_padcfg(pctrl, pin, PADCFG0); - - value = readl(padcfg0); - if (input) - value |= PADCFG0_GPIOTXDIS; - else - value &= ~PADCFG0_GPIOTXDIS; - writel(value, padcfg0); + __intel_gpio_set_direction(padcfg0, input); raw_spin_unlock_irqrestore(&pctrl->lock, flags); diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c index c3928aa3fefa..e0bca4df2a2f 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c +++ b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c @@ -253,9 +253,8 @@ static const unsigned int uart_tx_ao_a_pins[] = { PIN(GPIOAO_0, 0) }; static const unsigned int uart_rx_ao_a_pins[] = { PIN(GPIOAO_1, 0) }; static const unsigned int uart_cts_ao_a_pins[] = { PIN(GPIOAO_2, 0) }; static const unsigned int uart_rts_ao_a_pins[] = { PIN(GPIOAO_3, 0) }; -static const unsigned int uart_tx_ao_b_pins[] = { PIN(GPIOAO_0, 0) }; -static const unsigned int uart_rx_ao_b_pins[] = { PIN(GPIOAO_1, 0), - PIN(GPIOAO_5, 0) }; +static const unsigned int uart_tx_ao_b_pins[] = { PIN(GPIOAO_4, 0) }; +static const unsigned int uart_rx_ao_b_pins[] = { PIN(GPIOAO_5, 0) }; static const unsigned int uart_cts_ao_b_pins[] = { PIN(GPIOAO_2, 0) }; static const unsigned int uart_rts_ao_b_pins[] = { PIN(GPIOAO_3, 0) }; @@ -498,7 +497,7 @@ static struct meson_pmx_group meson_gxbb_aobus_groups[] = { GPIO_GROUP(GPIOAO_13, 0), /* bank AO */ - GROUP(uart_tx_ao_b, 0, 26), + GROUP(uart_tx_ao_b, 0, 24), GROUP(uart_rx_ao_b, 0, 25), GROUP(uart_tx_ao_a, 0, 12), GROUP(uart_rx_ao_a, 0, 11), diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxl.c b/drivers/pinctrl/meson/pinctrl-meson-gxl.c index 25694f7094c7..b69743b07a1d 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-gxl.c +++ b/drivers/pinctrl/meson/pinctrl-meson-gxl.c @@ -214,9 +214,8 @@ static const unsigned int uart_tx_ao_a_pins[] = { PIN(GPIOAO_0, 0) }; static const unsigned int uart_rx_ao_a_pins[] = { PIN(GPIOAO_1, 0) }; static const unsigned int uart_cts_ao_a_pins[] = { PIN(GPIOAO_2, 0) }; static const unsigned int uart_rts_ao_a_pins[] = { PIN(GPIOAO_3, 0) }; -static const unsigned int uart_tx_ao_b_pins[] = { PIN(GPIOAO_0, 0) }; -static const unsigned int uart_rx_ao_b_pins[] = { PIN(GPIOAO_1, 0), - PIN(GPIOAO_5, 0) }; +static const unsigned int uart_tx_ao_b_pins[] = { PIN(GPIOAO_4, 0) }; +static const unsigned int uart_rx_ao_b_pins[] = { PIN(GPIOAO_5, 0) }; static const unsigned int uart_cts_ao_b_pins[] = { PIN(GPIOAO_2, 0) }; static const unsigned int uart_rts_ao_b_pins[] = { PIN(GPIOAO_3, 0) }; @@ -409,7 +408,7 @@ static struct meson_pmx_group meson_gxl_aobus_groups[] = { GPIO_GROUP(GPIOAO_9, 0), /* bank AO */ - GROUP(uart_tx_ao_b, 0, 26), + GROUP(uart_tx_ao_b, 0, 24), GROUP(uart_rx_ao_b, 0, 25), GROUP(uart_tx_ao_a, 0, 12), GROUP(uart_rx_ao_a, 0, 11), diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index c9a146948192..537b52055756 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -202,6 +202,8 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) i = 128; pin_num = AMD_GPIO_PINS_BANK2 + i; break; + default: + return; } for (; i < pin_num; i++) { diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c index aa8bd9794683..96686336e3a3 100644 --- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c +++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c @@ -561,7 +561,7 @@ static const int ether_rgmii_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}; static const unsigned ether_rmii_pins[] = {30, 31, 32, 33, 34, 35, 36, 37, 39, 41, 42, 45}; -static const int ether_rmii_muxvals[] = {1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1}; +static const int ether_rmii_muxvals[] = {0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1}; static const unsigned i2c0_pins[] = {63, 64}; static const int i2c0_muxvals[] = {0, 0}; static const unsigned i2c1_pins[] = {65, 66}; diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 410741acb3c9..f46ece2ce3c4 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -813,6 +813,7 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data) case 8: case 7: case 6: + case 1: ideapad_input_report(priv, vpc_bit); break; case 5: diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c index 1fc0de870ff8..361770568ad0 100644 --- a/drivers/platform/x86/intel_mid_powerbtn.c +++ b/drivers/platform/x86/intel_mid_powerbtn.c @@ -77,7 +77,7 @@ static int mfld_pb_probe(struct platform_device *pdev) input_set_capability(input, EV_KEY, KEY_POWER); - error = request_threaded_irq(irq, NULL, mfld_pb_isr, 0, + error = request_threaded_irq(irq, NULL, mfld_pb_isr, IRQF_ONESHOT, DRIVER_NAME, input); if (error) { dev_err(&pdev->dev, "Unable to request irq %d for mfld power" diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index 97b4c3a219c0..25f15df5c2d7 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -326,7 +326,7 @@ static int __init mlxplat_init(void) return 0; fail_platform_mux_register: - for (i--; i > 0 ; i--) + while (--i >= 0) platform_device_unregister(priv->pdev_mux[i]); platform_device_unregister(priv->pdev_i2c); fail_alloc: diff --git a/drivers/platform/x86/surface3-wmi.c b/drivers/platform/x86/surface3-wmi.c index cbf4d83a7271..25b176996cb7 100644 --- a/drivers/platform/x86/surface3-wmi.c +++ b/drivers/platform/x86/surface3-wmi.c @@ -139,7 +139,7 @@ static acpi_status s3_wmi_attach_spi_device(acpi_handle handle, static int s3_wmi_check_platform_device(struct device *dev, void *data) { - struct acpi_device *adev, *ts_adev; + struct acpi_device *adev, *ts_adev = NULL; acpi_handle handle; acpi_status status; @@ -244,13 +244,11 @@ static int s3_wmi_remove(struct platform_device *device) return 0; } -#ifdef CONFIG_PM -static int s3_wmi_resume(struct device *dev) +static int __maybe_unused s3_wmi_resume(struct device *dev) { s3_wmi_send_lid_state(); return 0; } -#endif static SIMPLE_DEV_PM_OPS(s3_wmi_pm, NULL, s3_wmi_resume); static struct platform_driver s3_wmi_driver = { diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 0b09638fa39b..1f5d92a25a49 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -836,6 +836,7 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) struct bio *bio = rq->bio; sector_t sector = blk_rq_pos(rq); unsigned int nr_sectors = blk_rq_sectors(rq); + unsigned int nr_bytes = blk_rq_bytes(rq); int ret; if (sdkp->device->no_write_same) @@ -868,7 +869,21 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) cmd->transfersize = sdp->sector_size; cmd->allowed = SD_MAX_RETRIES; - return scsi_init_io(cmd); + + /* + * For WRITE SAME the data transferred via the DATA OUT buffer is + * different from the amount of data actually written to the target. + * + * We set up __data_len to the amount of data transferred via the + * DATA OUT buffer so that blk_rq_map_sg sets up the proper S/G list + * to transfer a single sector of data first, but then reset it to + * the amount of data to be written right after so that the I/O path + * knows how much to actually write. + */ + rq->__data_len = sdp->sector_size; + ret = scsi_init_io(cmd); + rq->__data_len = nr_bytes; + return ret; } static int sd_setup_flush_cmnd(struct scsi_cmnd *cmd) diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index c4a508a124dc..541af5946203 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -58,6 +58,14 @@ static LIST_HEAD(thermal_hwmon_list); static DEFINE_MUTEX(thermal_hwmon_list_lock); +static ssize_t +name_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct thermal_hwmon_device *hwmon = dev_get_drvdata(dev); + return sprintf(buf, "%s\n", hwmon->type); +} +static DEVICE_ATTR_RO(name); + static ssize_t temp_input_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -157,12 +165,15 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) INIT_LIST_HEAD(&hwmon->tz_list); strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH); - hwmon->device = hwmon_device_register_with_info(NULL, hwmon->type, - hwmon, NULL, NULL); + hwmon->device = hwmon_device_register(NULL); if (IS_ERR(hwmon->device)) { result = PTR_ERR(hwmon->device); goto free_mem; } + dev_set_drvdata(hwmon->device, hwmon); + result = device_create_file(hwmon->device, &dev_attr_name); + if (result) + goto free_mem; register_sys_interface: temp = kzalloc(sizeof(*temp), GFP_KERNEL); @@ -211,8 +222,10 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) free_temp_mem: kfree(temp); unregister_name: - if (new_hwmon_device) + if (new_hwmon_device) { + device_remove_file(hwmon->device, &dev_attr_name); hwmon_device_unregister(hwmon->device); + } free_mem: if (new_hwmon_device) kfree(hwmon); @@ -254,6 +267,7 @@ void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) list_del(&hwmon->node); mutex_unlock(&thermal_hwmon_list_lock); + device_remove_file(hwmon->device, &dev_attr_name); hwmon_device_unregister(hwmon->device); kfree(hwmon); } diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index c8823578a1b2..128d10282d16 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -1270,6 +1270,10 @@ static int tce_iommu_attach_group(void *iommu_data, /* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n", iommu_group_id(iommu_group), iommu_group); */ table_group = iommu_group_get_iommudata(iommu_group); + if (!table_group) { + ret = -ENODEV; + goto unlock_exit; + } if (tce_groups_attached(container) && (!table_group->ops || !table_group->ops->take_ownership || diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index bbbf588540ed..ce5e63d2c66a 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -373,6 +373,7 @@ static void vhost_vsock_handle_rx_kick(struct vhost_work *work) static int vhost_vsock_start(struct vhost_vsock *vsock) { + struct vhost_virtqueue *vq; size_t i; int ret; @@ -383,19 +384,20 @@ static int vhost_vsock_start(struct vhost_vsock *vsock) goto err; for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { - struct vhost_virtqueue *vq = &vsock->vqs[i]; + vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); if (!vhost_vq_access_ok(vq)) { ret = -EFAULT; - mutex_unlock(&vq->mutex); goto err_vq; } if (!vq->private_data) { vq->private_data = vsock; - vhost_vq_init_access(vq); + ret = vhost_vq_init_access(vq); + if (ret) + goto err_vq; } mutex_unlock(&vq->mutex); @@ -405,8 +407,11 @@ static int vhost_vsock_start(struct vhost_vsock *vsock) return 0; err_vq: + vq->private_data = NULL; + mutex_unlock(&vq->mutex); + for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { - struct vhost_virtqueue *vq = &vsock->vqs[i]; + vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); vq->private_data = NULL; diff --git a/drivers/video/fbdev/core/fbcmap.c b/drivers/video/fbdev/core/fbcmap.c index f89245b8ba8e..68a113594808 100644 --- a/drivers/video/fbdev/core/fbcmap.c +++ b/drivers/video/fbdev/core/fbcmap.c @@ -163,17 +163,18 @@ void fb_dealloc_cmap(struct fb_cmap *cmap) int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to) { - int tooff = 0, fromoff = 0; - int size; + unsigned int tooff = 0, fromoff = 0; + size_t size; if (to->start > from->start) fromoff = to->start - from->start; else tooff = from->start - to->start; - size = to->len - tooff; - if (size > (int) (from->len - fromoff)) - size = from->len - fromoff; - if (size <= 0) + if (fromoff >= from->len || tooff >= to->len) + return -EINVAL; + + size = min_t(size_t, to->len - tooff, from->len - fromoff); + if (size == 0) return -EINVAL; size *= sizeof(u16); @@ -187,17 +188,18 @@ int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to) int fb_cmap_to_user(const struct fb_cmap *from, struct fb_cmap_user *to) { - int tooff = 0, fromoff = 0; - int size; + unsigned int tooff = 0, fromoff = 0; + size_t size; if (to->start > from->start) fromoff = to->start - from->start; else tooff = from->start - to->start; - size = to->len - tooff; - if (size > (int) (from->len - fromoff)) - size = from->len - fromoff; - if (size <= 0) + if (fromoff >= from->len || tooff >= to->len) + return -EINVAL; + + size = min_t(size_t, to->len - tooff, from->len - fromoff); + if (size == 0) return -EINVAL; size *= sizeof(u16); diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index d47a2fcef818..c71fde5fe835 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -59,6 +59,7 @@ #define pr_fmt(fmt) "virtio-mmio: " fmt #include +#include #include #include #include @@ -498,6 +499,7 @@ static int virtio_mmio_probe(struct platform_device *pdev) struct virtio_mmio_device *vm_dev; struct resource *mem; unsigned long magic; + int rc; mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!mem) @@ -547,9 +549,25 @@ static int virtio_mmio_probe(struct platform_device *pdev) } vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID); - if (vm_dev->version == 1) + if (vm_dev->version == 1) { writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE); + rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + /* + * In the legacy case, ensure our coherently-allocated virtio + * ring will be at an address expressable as a 32-bit PFN. + */ + if (!rc) + dma_set_coherent_mask(&pdev->dev, + DMA_BIT_MASK(32 + PAGE_SHIFT)); + } else { + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + } + if (rc) + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (rc) + dev_warn(&pdev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n"); + platform_set_drvdata(pdev, vm_dev); return register_virtio_device(&vm_dev->vdev); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 409aeaa49246..7e38ed79c3fc 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -159,6 +159,13 @@ static bool vring_use_dma_api(struct virtio_device *vdev) if (xen_domain()) return true; + /* + * On ARM-based machines, the DMA ops will do the right thing, + * so always use them with legacy devices. + */ + if (IS_ENABLED(CONFIG_ARM) || IS_ENABLED(CONFIG_ARM64)) + return !virtio_has_feature(vdev, VIRTIO_F_VERSION_1); + return false; } diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index f905d6eeb048..f8afc6dcc29f 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -414,9 +414,9 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, if (map == SWIOTLB_MAP_ERROR) return DMA_ERROR_CODE; + dev_addr = xen_phys_to_bus(map); xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT), dev_addr, map & ~PAGE_MASK, size, dir, attrs); - dev_addr = xen_phys_to_bus(map); /* * Ensure that the address returned is DMA'ble @@ -575,13 +575,14 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, sg_dma_len(sgl) = 0; return 0; } + dev_addr = xen_phys_to_bus(map); xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT), dev_addr, map & ~PAGE_MASK, sg->length, dir, attrs); - sg->dma_address = xen_phys_to_bus(map); + sg->dma_address = dev_addr; } else { /* we are not interested in the dma_addr returned by * xen_dma_map_page, only in the potential cache flushes executed diff --git a/fs/Kconfig b/fs/Kconfig index c2a377cdda2b..83eab52fb3f6 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -38,6 +38,7 @@ config FS_DAX bool "Direct Access (DAX) support" depends on MMU depends on !(ARM || MIPS || SPARC) + select FS_IOMAP help Direct Access (DAX) can be used on memory-backed block devices. If the block device supports DAX and the filesystem supports DAX, diff --git a/fs/block_dev.c b/fs/block_dev.c index 5db5d1340d69..3c47614a4b32 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -331,7 +331,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) struct blk_plug plug; struct blkdev_dio *dio; struct bio *bio; - bool is_read = (iov_iter_rw(iter) == READ); + bool is_read = (iov_iter_rw(iter) == READ), is_sync; loff_t pos = iocb->ki_pos; blk_qc_t qc = BLK_QC_T_NONE; int ret; @@ -344,7 +344,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) bio_get(bio); /* extra ref for the completion handler */ dio = container_of(bio, struct blkdev_dio, bio); - dio->is_sync = is_sync_kiocb(iocb); + dio->is_sync = is_sync = is_sync_kiocb(iocb); if (dio->is_sync) dio->waiter = current; else @@ -398,7 +398,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } blk_finish_plug(&plug); - if (!dio->is_sync) + if (!is_sync) return -EIOCBQUEUED; for (;;) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4e024260ad71..1e861a063721 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3835,10 +3835,7 @@ cache_acl: break; case S_IFDIR: inode->i_fop = &btrfs_dir_file_operations; - if (root == fs_info->tree_root) - inode->i_op = &btrfs_dir_ro_inode_operations; - else - inode->i_op = &btrfs_dir_inode_operations; + inode->i_op = &btrfs_dir_inode_operations; break; case S_IFLNK: inode->i_op = &btrfs_symlink_inode_operations; @@ -4505,8 +4502,19 @@ search_again: if (found_type > min_type) { del_item = 1; } else { - if (item_end < new_size) + if (item_end < new_size) { + /* + * With NO_HOLES mode, for the following mapping + * + * [0-4k][hole][8k-12k] + * + * if truncating isize down to 6k, it ends up + * isize being 8k. + */ + if (btrfs_fs_incompat(root->fs_info, NO_HOLES)) + last_size = new_size; break; + } if (found_key.offset >= new_size) del_item = 1; else @@ -5710,6 +5718,7 @@ static struct inode *new_simple_dir(struct super_block *s, inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID; inode->i_op = &btrfs_dir_ro_inode_operations; + inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &simple_dir_operations; inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO; inode->i_mtime = current_time(inode); @@ -7215,7 +7224,6 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode, struct extent_map *em = NULL; int ret; - down_read(&BTRFS_I(inode)->dio_sem); if (type != BTRFS_ORDERED_NOCOW) { em = create_pinned_em(inode, start, len, orig_start, block_start, block_len, orig_block_len, @@ -7234,7 +7242,6 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode, em = ERR_PTR(ret); } out: - up_read(&BTRFS_I(inode)->dio_sem); return em; } @@ -8692,6 +8699,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) dio_data.unsubmitted_oe_range_start = (u64)offset; dio_data.unsubmitted_oe_range_end = (u64)offset; current->journal_info = &dio_data; + down_read(&BTRFS_I(inode)->dio_sem); } else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags)) { inode_dio_end(inode); @@ -8704,6 +8712,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) iter, btrfs_get_blocks_direct, NULL, btrfs_submit_direct, flags); if (iov_iter_rw(iter) == WRITE) { + up_read(&BTRFS_I(inode)->dio_sem); current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) { if (dio_data.reserve) @@ -9212,6 +9221,7 @@ static int btrfs_truncate(struct inode *inode) break; } + btrfs_block_rsv_release(fs_info, rsv, -1); ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv, min_size, 0); BUG_ON(ret); /* shouldn't happen */ @@ -10579,8 +10589,6 @@ static const struct inode_operations btrfs_dir_inode_operations = { static const struct inode_operations btrfs_dir_ro_inode_operations = { .lookup = btrfs_lookup, .permission = btrfs_permission, - .get_acl = btrfs_get_acl, - .set_acl = btrfs_set_acl, .update_time = btrfs_update_time, }; diff --git a/fs/dax.c b/fs/dax.c index ddcddfeaa03b..3af2da5e64ce 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -990,7 +990,6 @@ int __dax_zero_page_range(struct block_device *bdev, sector_t sector, } EXPORT_SYMBOL_GPL(__dax_zero_page_range); -#ifdef CONFIG_FS_IOMAP static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos) { return iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9); @@ -1428,4 +1427,3 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault); #endif /* CONFIG_FS_DAX_PMD */ -#endif /* CONFIG_FS_IOMAP */ diff --git a/fs/ext2/Kconfig b/fs/ext2/Kconfig index 36bea5adcaba..c634874e12d9 100644 --- a/fs/ext2/Kconfig +++ b/fs/ext2/Kconfig @@ -1,6 +1,5 @@ config EXT2_FS tristate "Second extended fs support" - select FS_IOMAP if FS_DAX help Ext2 is a standard Linux file system for hard disks. diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 7b90691e98c4..e38039fd96ff 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -37,7 +37,6 @@ config EXT4_FS select CRC16 select CRYPTO select CRYPTO_CRC32C - select FS_IOMAP if FS_DAX help This is the next generation of the ext3 filesystem. diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ecc151697fd4..0a0eaecf9676 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2700,7 +2700,8 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata, sattr->ia_valid |= ATTR_MTIME; /* Except MODE, it seems harmless of setting twice. */ - if ((attrset[1] & FATTR4_WORD1_MODE)) + if (opendata->o_arg.createmode != NFS4_CREATE_EXCLUSIVE && + attrset[1] & FATTR4_WORD1_MODE) sattr->ia_valid &= ~ATTR_MODE; if (attrset[2] & FATTR4_WORD2_SECURITY_LABEL) @@ -8490,6 +8491,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, goto out; } + nfs4_sequence_free_slot(&lgp->res.seq_res); err = nfs4_handle_exception(server, nfs4err, exception); if (!status) { if (exception->retry) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 90e6193ce6be..daeb94e3acd4 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1091,6 +1091,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid) case -NFS4ERR_BADXDR: case -NFS4ERR_RESOURCE: case -NFS4ERR_NOFILEHANDLE: + case -NFS4ERR_MOVED: /* Non-seqid mutating errors */ return; }; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 59554f3adf29..dd042498ce7c 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1200,10 +1200,10 @@ _pnfs_return_layout(struct inode *ino) send = pnfs_prepare_layoutreturn(lo, &stateid, NULL); spin_unlock(&ino->i_lock); - pnfs_free_lseg_list(&tmp_list); if (send) status = pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true); out_put_layout_hdr: + pnfs_free_lseg_list(&tmp_list); pnfs_put_layout_hdr(lo); out: dprintk("<-- %s status: %d\n", __func__, status); diff --git a/fs/proc/base.c b/fs/proc/base.c index 8e7e61b28f31..87c9a9aacda3 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3179,6 +3179,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) iter.tgid += 1, iter = next_tgid(ns, iter)) { char name[PROC_NUMBUF]; int len; + + cond_resched(); if (!has_pid_permissions(ns, iter.task, 2)) continue; diff --git a/fs/romfs/super.c b/fs/romfs/super.c index d0f8a38dfafa..0186fe6d39f3 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -74,6 +74,7 @@ #include #include #include +#include #include "internal.h" static struct kmem_cache *romfs_inode_cachep; @@ -416,7 +417,22 @@ static void romfs_destroy_inode(struct inode *inode) static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; - u64 id = huge_encode_dev(sb->s_bdev->bd_dev); + u64 id = 0; + + /* When calling huge_encode_dev(), + * use sb->s_bdev->bd_dev when, + * - CONFIG_ROMFS_ON_BLOCK defined + * use sb->s_dev when, + * - CONFIG_ROMFS_ON_BLOCK undefined and + * - CONFIG_ROMFS_ON_MTD defined + * leave id as 0 when, + * - CONFIG_ROMFS_ON_BLOCK undefined and + * - CONFIG_ROMFS_ON_MTD undefined + */ + if (sb->s_bdev) + id = huge_encode_dev(sb->s_bdev->bd_dev); + else if (sb->s_dev) + id = huge_encode_dev(sb->s_dev); buf->f_type = ROMFS_MAGIC; buf->f_namelen = ROMFS_MAXFN; @@ -489,6 +505,11 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags |= MS_RDONLY | MS_NOATIME; sb->s_op = &romfs_super_ops; +#ifdef CONFIG_ROMFS_ON_MTD + /* Use same dev ID from the underlying mtdblock device */ + if (sb->s_mtd) + sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index); +#endif /* read the image superblock and check it */ rsb = kmalloc(512, GFP_KERNEL); if (!rsb) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d96e2f30084b..43953e03c356 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -63,6 +63,7 @@ struct userfaultfd_wait_queue { struct uffd_msg msg; wait_queue_t wq; struct userfaultfd_ctx *ctx; + bool waken; }; struct userfaultfd_wake_range { @@ -86,6 +87,12 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode, if (len && (start > uwq->msg.arg.pagefault.address || start + len <= uwq->msg.arg.pagefault.address)) goto out; + WRITE_ONCE(uwq->waken, true); + /* + * The implicit smp_mb__before_spinlock in try_to_wake_up() + * renders uwq->waken visible to other CPUs before the task is + * waken. + */ ret = wake_up_state(wq->private, mode); if (ret) /* @@ -264,6 +271,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) struct userfaultfd_wait_queue uwq; int ret; bool must_wait, return_to_userland; + long blocking_state; BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); @@ -334,10 +342,13 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) uwq.wq.private = current; uwq.msg = userfault_msg(vmf->address, vmf->flags, reason); uwq.ctx = ctx; + uwq.waken = false; return_to_userland = (vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) == (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE); + blocking_state = return_to_userland ? TASK_INTERRUPTIBLE : + TASK_KILLABLE; spin_lock(&ctx->fault_pending_wqh.lock); /* @@ -350,8 +361,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) * following the spin_unlock to happen before the list_add in * __add_wait_queue. */ - set_current_state(return_to_userland ? TASK_INTERRUPTIBLE : - TASK_KILLABLE); + set_current_state(blocking_state); spin_unlock(&ctx->fault_pending_wqh.lock); must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, @@ -364,6 +374,29 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) wake_up_poll(&ctx->fd_wqh, POLLIN); schedule(); ret |= VM_FAULT_MAJOR; + + /* + * False wakeups can orginate even from rwsem before + * up_read() however userfaults will wait either for a + * targeted wakeup on the specific uwq waitqueue from + * wake_userfault() or for signals or for uffd + * release. + */ + while (!READ_ONCE(uwq.waken)) { + /* + * This needs the full smp_store_mb() + * guarantee as the state write must be + * visible to other CPUs before reading + * uwq.waken from other CPUs. + */ + set_current_state(blocking_state); + if (READ_ONCE(uwq.waken) || + READ_ONCE(ctx->released) || + (return_to_userland ? signal_pending(current) : + fatal_signal_pending(current))) + break; + schedule(); + } } __set_current_state(TASK_RUNNING); diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index d346d42c54d1..33db69be4832 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -39,6 +39,7 @@ #include "xfs_rmap_btree.h" #include "xfs_btree.h" #include "xfs_refcount_btree.h" +#include "xfs_ialloc_btree.h" /* * Per-AG Block Reservations @@ -200,22 +201,30 @@ __xfs_ag_resv_init( struct xfs_mount *mp = pag->pag_mount; struct xfs_ag_resv *resv; int error; + xfs_extlen_t reserved; - resv = xfs_perag_resv(pag, type); if (used > ask) ask = used; - resv->ar_asked = ask; - resv->ar_reserved = resv->ar_orig_reserved = ask - used; - mp->m_ag_max_usable -= ask; + reserved = ask - used; - trace_xfs_ag_resv_init(pag, type, ask); - - error = xfs_mod_fdblocks(mp, -(int64_t)resv->ar_reserved, true); - if (error) + error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true); + if (error) { trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno, error, _RET_IP_); + xfs_warn(mp, +"Per-AG reservation for AG %u failed. Filesystem may run out of space.", + pag->pag_agno); + return error; + } - return error; + mp->m_ag_max_usable -= ask; + + resv = xfs_perag_resv(pag, type); + resv->ar_asked = ask; + resv->ar_reserved = resv->ar_orig_reserved = reserved; + + trace_xfs_ag_resv_init(pag, type, ask); + return 0; } /* Create a per-AG block reservation. */ @@ -223,6 +232,8 @@ int xfs_ag_resv_init( struct xfs_perag *pag) { + struct xfs_mount *mp = pag->pag_mount; + xfs_agnumber_t agno = pag->pag_agno; xfs_extlen_t ask; xfs_extlen_t used; int error = 0; @@ -231,23 +242,45 @@ xfs_ag_resv_init( if (pag->pag_meta_resv.ar_asked == 0) { ask = used = 0; - error = xfs_refcountbt_calc_reserves(pag->pag_mount, - pag->pag_agno, &ask, &used); + error = xfs_refcountbt_calc_reserves(mp, agno, &ask, &used); + if (error) + goto out; + + error = xfs_finobt_calc_reserves(mp, agno, &ask, &used); if (error) goto out; error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA, ask, used); - if (error) - goto out; + if (error) { + /* + * Because we didn't have per-AG reservations when the + * finobt feature was added we might not be able to + * reserve all needed blocks. Warn and fall back to the + * old and potentially buggy code in that case, but + * ensure we do have the reservation for the refcountbt. + */ + ask = used = 0; + + mp->m_inotbt_nores = true; + + error = xfs_refcountbt_calc_reserves(mp, agno, &ask, + &used); + if (error) + goto out; + + error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA, + ask, used); + if (error) + goto out; + } } /* Create the AGFL metadata reservation */ if (pag->pag_agfl_resv.ar_asked == 0) { ask = used = 0; - error = xfs_rmapbt_calc_reserves(pag->pag_mount, pag->pag_agno, - &ask, &used); + error = xfs_rmapbt_calc_reserves(mp, agno, &ask, &used); if (error) goto out; @@ -256,9 +289,16 @@ xfs_ag_resv_init( goto out; } +#ifdef DEBUG + /* need to read in the AGF for the ASSERT below to work */ + error = xfs_alloc_pagf_init(pag->pag_mount, NULL, pag->pag_agno, 0); + if (error) + return error; + ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved + xfs_perag_resv(pag, XFS_AG_RESV_AGFL)->ar_reserved <= pag->pagf_freeblks + pag->pagf_flcount); +#endif out: return error; } diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index af1ecb19121e..6622d46ddec3 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -131,9 +131,6 @@ xfs_attr_get( if (XFS_FORCED_SHUTDOWN(ip->i_mount)) return -EIO; - if (!xfs_inode_hasattr(ip)) - return -ENOATTR; - error = xfs_attr_args_init(&args, ip, name, flags); if (error) return error; @@ -392,9 +389,6 @@ xfs_attr_remove( if (XFS_FORCED_SHUTDOWN(dp->i_mount)) return -EIO; - if (!xfs_inode_hasattr(dp)) - return -ENOATTR; - error = xfs_attr_args_init(&args, dp, name, flags); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 44773c9eb957..bfc00de5c6f1 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3629,7 +3629,7 @@ xfs_bmap_btalloc( align = xfs_get_cowextsz_hint(ap->ip); else if (xfs_alloc_is_userdata(ap->datatype)) align = xfs_get_extsz_hint(ap->ip); - if (unlikely(align)) { + if (align) { error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, align, 0, ap->eof, 0, ap->conv, &ap->offset, &ap->length); @@ -3701,7 +3701,7 @@ xfs_bmap_btalloc( args.minlen = ap->minlen; } /* apply extent size hints if obtained earlier */ - if (unlikely(align)) { + if (align) { args.prod = align; if ((args.mod = (xfs_extlen_t)do_mod(ap->offset, args.prod))) args.mod = (xfs_extlen_t)(args.prod - args.mod); @@ -4514,8 +4514,6 @@ xfs_bmapi_write( int n; /* current extent index */ xfs_fileoff_t obno; /* old block number (offset) */ int whichfork; /* data or attr fork */ - char inhole; /* current location is hole in file */ - char wasdelay; /* old extent was delayed */ #ifdef DEBUG xfs_fileoff_t orig_bno; /* original block number value */ @@ -4603,22 +4601,44 @@ xfs_bmapi_write( bma.firstblock = firstblock; while (bno < end && n < *nmap) { - inhole = eof || bma.got.br_startoff > bno; - wasdelay = !inhole && isnullstartblock(bma.got.br_startblock); + bool need_alloc = false, wasdelay = false; - /* - * Make sure we only reflink into a hole. - */ - if (flags & XFS_BMAPI_REMAP) - ASSERT(inhole); - if (flags & XFS_BMAPI_COWFORK) - ASSERT(!inhole); + /* in hole or beyoned EOF? */ + if (eof || bma.got.br_startoff > bno) { + if (flags & XFS_BMAPI_DELALLOC) { + /* + * For the COW fork we can reasonably get a + * request for converting an extent that races + * with other threads already having converted + * part of it, as there converting COW to + * regular blocks is not protected using the + * IOLOCK. + */ + ASSERT(flags & XFS_BMAPI_COWFORK); + if (!(flags & XFS_BMAPI_COWFORK)) { + error = -EIO; + goto error0; + } + + if (eof || bno >= end) + break; + } else { + need_alloc = true; + } + } else { + /* + * Make sure we only reflink into a hole. + */ + ASSERT(!(flags & XFS_BMAPI_REMAP)); + if (isnullstartblock(bma.got.br_startblock)) + wasdelay = true; + } /* * First, deal with the hole before the allocated space * that we found, if any. */ - if (inhole || wasdelay) { + if (need_alloc || wasdelay) { bma.eof = eof; bma.conv = !!(flags & XFS_BMAPI_CONVERT); bma.wasdel = wasdelay; diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index cecd094404cc..cdef87db5262 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -110,6 +110,9 @@ struct xfs_extent_free_item /* Map something in the CoW fork. */ #define XFS_BMAPI_COWFORK 0x200 +/* Only convert delalloc space, don't allocate entirely new extents */ +#define XFS_BMAPI_DELALLOC 0x400 + #define XFS_BMAPI_FLAGS \ { XFS_BMAPI_ENTIRE, "ENTIRE" }, \ { XFS_BMAPI_METADATA, "METADATA" }, \ @@ -120,7 +123,8 @@ struct xfs_extent_free_item { XFS_BMAPI_CONVERT, "CONVERT" }, \ { XFS_BMAPI_ZERO, "ZERO" }, \ { XFS_BMAPI_REMAP, "REMAP" }, \ - { XFS_BMAPI_COWFORK, "COWFORK" } + { XFS_BMAPI_COWFORK, "COWFORK" }, \ + { XFS_BMAPI_DELALLOC, "DELALLOC" } static inline int xfs_bmapi_aflag(int w) diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 0fd086d03d41..7c471881c9a6 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -82,11 +82,12 @@ xfs_finobt_set_root( } STATIC int -xfs_inobt_alloc_block( +__xfs_inobt_alloc_block( struct xfs_btree_cur *cur, union xfs_btree_ptr *start, union xfs_btree_ptr *new, - int *stat) + int *stat, + enum xfs_ag_resv_type resv) { xfs_alloc_arg_t args; /* block allocation args */ int error; /* error return value */ @@ -103,6 +104,7 @@ xfs_inobt_alloc_block( args.maxlen = 1; args.prod = 1; args.type = XFS_ALLOCTYPE_NEAR_BNO; + args.resv = resv; error = xfs_alloc_vextent(&args); if (error) { @@ -122,6 +124,27 @@ xfs_inobt_alloc_block( return 0; } +STATIC int +xfs_inobt_alloc_block( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *start, + union xfs_btree_ptr *new, + int *stat) +{ + return __xfs_inobt_alloc_block(cur, start, new, stat, XFS_AG_RESV_NONE); +} + +STATIC int +xfs_finobt_alloc_block( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *start, + union xfs_btree_ptr *new, + int *stat) +{ + return __xfs_inobt_alloc_block(cur, start, new, stat, + XFS_AG_RESV_METADATA); +} + STATIC int xfs_inobt_free_block( struct xfs_btree_cur *cur, @@ -328,7 +351,7 @@ static const struct xfs_btree_ops xfs_finobt_ops = { .dup_cursor = xfs_inobt_dup_cursor, .set_root = xfs_finobt_set_root, - .alloc_block = xfs_inobt_alloc_block, + .alloc_block = xfs_finobt_alloc_block, .free_block = xfs_inobt_free_block, .get_minrecs = xfs_inobt_get_minrecs, .get_maxrecs = xfs_inobt_get_maxrecs, @@ -480,3 +503,64 @@ xfs_inobt_rec_check_count( return 0; } #endif /* DEBUG */ + +static xfs_extlen_t +xfs_inobt_max_size( + struct xfs_mount *mp) +{ + /* Bail out if we're uninitialized, which can happen in mkfs. */ + if (mp->m_inobt_mxr[0] == 0) + return 0; + + return xfs_btree_calc_size(mp, mp->m_inobt_mnr, + (uint64_t)mp->m_sb.sb_agblocks * mp->m_sb.sb_inopblock / + XFS_INODES_PER_CHUNK); +} + +static int +xfs_inobt_count_blocks( + struct xfs_mount *mp, + xfs_agnumber_t agno, + xfs_btnum_t btnum, + xfs_extlen_t *tree_blocks) +{ + struct xfs_buf *agbp; + struct xfs_btree_cur *cur; + int error; + + error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp); + if (error) + return error; + + cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, btnum); + error = xfs_btree_count_blocks(cur, tree_blocks); + xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); + xfs_buf_relse(agbp); + + return error; +} + +/* + * Figure out how many blocks to reserve and how many are used by this btree. + */ +int +xfs_finobt_calc_reserves( + struct xfs_mount *mp, + xfs_agnumber_t agno, + xfs_extlen_t *ask, + xfs_extlen_t *used) +{ + xfs_extlen_t tree_len = 0; + int error; + + if (!xfs_sb_version_hasfinobt(&mp->m_sb)) + return 0; + + error = xfs_inobt_count_blocks(mp, agno, XFS_BTNUM_FINO, &tree_len); + if (error) + return error; + + *ask += xfs_inobt_max_size(mp); + *used += tree_len; + return 0; +} diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h index bd88453217ce..aa81e2e63f3f 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.h +++ b/fs/xfs/libxfs/xfs_ialloc_btree.h @@ -72,4 +72,7 @@ int xfs_inobt_rec_check_count(struct xfs_mount *, #define xfs_inobt_rec_check_count(mp, rec) 0 #endif /* DEBUG */ +int xfs_finobt_calc_reserves(struct xfs_mount *mp, xfs_agnumber_t agno, + xfs_extlen_t *ask, xfs_extlen_t *used); + #endif /* __XFS_IALLOC_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 2580262e4ea0..584ec896a533 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -242,7 +242,7 @@ xfs_mount_validate_sb( sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG || sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG || sbp->sb_blocksize != (1 << sbp->sb_blocklog) || - sbp->sb_dirblklog > XFS_MAX_BLOCKSIZE_LOG || + sbp->sb_dirblklog + sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG || sbp->sb_inodesize < XFS_DINODE_MIN_SIZE || sbp->sb_inodesize > XFS_DINODE_MAX_SIZE || sbp->sb_inodelog < XFS_DINODE_MIN_LOG || diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index b9abce524c33..c1417919ab0a 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -528,7 +528,6 @@ xfs_getbmap( xfs_bmbt_irec_t *map; /* buffer for user's data */ xfs_mount_t *mp; /* file system mount point */ int nex; /* # of user extents can do */ - int nexleft; /* # of user extents left */ int subnex; /* # of bmapi's can do */ int nmap; /* number of map entries */ struct getbmapx *out; /* output structure */ @@ -686,10 +685,8 @@ xfs_getbmap( goto out_free_map; } - nexleft = nex; - do { - nmap = (nexleft > subnex) ? subnex : nexleft; + nmap = (nex> subnex) ? subnex : nex; error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset), XFS_BB_TO_FSB(mp, bmv->bmv_length), map, &nmap, bmapi_flags); @@ -697,8 +694,8 @@ xfs_getbmap( goto out_free_map; ASSERT(nmap <= subnex); - for (i = 0; i < nmap && nexleft && bmv->bmv_length && - cur_ext < bmv->bmv_count; i++) { + for (i = 0; i < nmap && bmv->bmv_length && + cur_ext < bmv->bmv_count - 1; i++) { out[cur_ext].bmv_oflags = 0; if (map[i].br_state == XFS_EXT_UNWRITTEN) out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC; @@ -760,16 +757,27 @@ xfs_getbmap( continue; } + /* + * In order to report shared extents accurately, + * we report each distinct shared/unshared part + * of a single bmbt record using multiple bmap + * extents. To make that happen, we iterate the + * same map array item multiple times, each + * time trimming out the subextent that we just + * reported. + * + * Because of this, we must check the out array + * index (cur_ext) directly against bmv_count-1 + * to avoid overflows. + */ if (inject_map.br_startblock != NULLFSBLOCK) { map[i] = inject_map; i--; - } else - nexleft--; + } bmv->bmv_entries++; cur_ext++; } - } while (nmap && nexleft && bmv->bmv_length && - cur_ext < bmv->bmv_count); + } while (nmap && bmv->bmv_length && cur_ext < bmv->bmv_count - 1); out_free_map: kmem_free(map); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 7f0a01f7b592..ac3b4db519df 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -422,6 +422,7 @@ retry: out_free_pages: for (i = 0; i < bp->b_page_count; i++) __free_page(bp->b_pages[i]); + bp->b_flags &= ~_XBF_PAGES; return error; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index b9557795eb74..de32f0fe47c8 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1792,22 +1792,23 @@ xfs_inactive_ifree( int error; /* - * The ifree transaction might need to allocate blocks for record - * insertion to the finobt. We don't want to fail here at ENOSPC, so - * allow ifree to dip into the reserved block pool if necessary. - * - * Freeing large sets of inodes generally means freeing inode chunks, - * directory and file data blocks, so this should be relatively safe. - * Only under severe circumstances should it be possible to free enough - * inodes to exhaust the reserve block pool via finobt expansion while - * at the same time not creating free space in the filesystem. + * We try to use a per-AG reservation for any block needed by the finobt + * tree, but as the finobt feature predates the per-AG reservation + * support a degraded file system might not have enough space for the + * reservation at mount time. In that case try to dip into the reserved + * pool and pray. * * Send a warning if the reservation does happen to fail, as the inode * now remains allocated and sits on the unlinked list until the fs is * repaired. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, - XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp); + if (unlikely(mp->m_inotbt_nores)) { + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, + XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, + &tp); + } else { + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, 0, 0, 0, &tp); + } if (error) { if (error == -ENOSPC) { xfs_warn_ratelimited(mp, diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 0d147428971e..1aa3abd67b36 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -681,7 +681,7 @@ xfs_iomap_write_allocate( xfs_trans_t *tp; int nimaps; int error = 0; - int flags = 0; + int flags = XFS_BMAPI_DELALLOC; int nres; if (whichfork == XFS_COW_FORK) diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 84f785218907..7f351f706b7a 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -140,6 +140,7 @@ typedef struct xfs_mount { int m_fixedfsid[2]; /* unchanged for life of FS */ uint m_dmevmask; /* DMI events for this FS */ __uint64_t m_flags; /* global mount flags */ + bool m_inotbt_nores; /* no per-AG finobt resv. */ int m_ialloc_inos; /* inodes in inode allocation */ int m_ialloc_blks; /* blocks in inode allocation */ int m_ialloc_min_blks;/* min blocks in sparse inode diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 45e50ea90769..b669b123287b 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1177,7 +1177,8 @@ xfs_qm_dqusage_adjust( * the case in all other instances. It's OK that we do this because * quotacheck is done only at mount time. */ - error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip); + error = xfs_iget(mp, NULL, ino, XFS_IGET_DONTCACHE, XFS_ILOCK_EXCL, + &ip); if (error) { *res = BULKSTAT_RV_NOTHING; return error; diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index d6d241f63b9f..56814e8ae7ea 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -144,7 +144,7 @@ struct __drm_crtcs_state { struct drm_crtc *ptr; struct drm_crtc_state *state; struct drm_crtc_commit *commit; - s64 __user *out_fence_ptr; + s32 __user *out_fence_ptr; }; struct __drm_connnectors_state { diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index bf9991b20611..137432386310 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -488,7 +488,7 @@ struct drm_mode_config { /** * @prop_out_fence_ptr: Sync File fd pointer representing the * outgoing fences for a CRTC. Userspace should provide a pointer to a - * value of type s64, and then cast that pointer to u64. + * value of type s32, and then cast that pointer to u64. */ struct drm_property *prop_out_fence_ptr; /** diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 05cf951df3fe..3ed1f3b1d594 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -247,6 +247,8 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); +void *bpf_map_area_alloc(size_t size); +void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 7e05c5e4e45c..87165f06a307 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -31,7 +31,7 @@ #define CPUFREQ_ETERNAL (-1) #define CPUFREQ_NAME_LEN 16 -/* Print length for names. Extra 1 space for accomodating '\n' in prints */ +/* Print length for names. Extra 1 space for accommodating '\n' in prints */ #define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1) struct cpufreq_governor; @@ -115,7 +115,7 @@ struct cpufreq_policy { * guarantee that frequency can be changed on any CPU sharing the * policy and that the change will affect all of the policy CPUs then. * - fast_switch_enabled is to be set by governors that support fast - * freqnency switching with the help of cpufreq_enable_fast_switch(). + * frequency switching with the help of cpufreq_enable_fast_switch(). */ bool fast_switch_possible; bool fast_switch_enabled; @@ -415,9 +415,6 @@ static inline void cpufreq_resume(void) {} /* Policy Notifiers */ #define CPUFREQ_ADJUST (0) #define CPUFREQ_NOTIFY (1) -#define CPUFREQ_START (2) -#define CPUFREQ_CREATE_POLICY (3) -#define CPUFREQ_REMOVE_POLICY (4) #ifdef CONFIG_CPU_FREQ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index c2748accea71..e973faba69dc 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -274,37 +274,67 @@ void gpiochip_set_nested_irqchip(struct gpio_chip *gpiochip, struct irq_chip *irqchip, int parent_irq); -int _gpiochip_irqchip_add(struct gpio_chip *gpiochip, - struct irq_chip *irqchip, - unsigned int first_irq, - irq_flow_handler_t handler, - unsigned int type, - bool nested, - struct lock_class_key *lock_key); +int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type, + bool nested, + struct lock_class_key *lock_key); + +#ifdef CONFIG_LOCKDEP + +/* + * Lockdep requires that each irqchip instance be created with a + * unique key so as to avoid unnecessary warnings. This upfront + * boilerplate static inlines provides such a key for each + * unique instance. + */ +static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type) +{ + static struct lock_class_key key; + + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, false, &key); +} -/* FIXME: I assume threaded IRQchips do not have the lockdep problem */ static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, struct irq_chip *irqchip, unsigned int first_irq, irq_flow_handler_t handler, unsigned int type) { - return _gpiochip_irqchip_add(gpiochip, irqchip, first_irq, - handler, type, true, NULL); + + static struct lock_class_key key; + + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, true, &key); +} +#else +static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type) +{ + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, false, NULL); } -#ifdef CONFIG_LOCKDEP -#define gpiochip_irqchip_add(...) \ -( \ - ({ \ - static struct lock_class_key _key; \ - _gpiochip_irqchip_add(__VA_ARGS__, false, &_key); \ - }) \ -) -#else -#define gpiochip_irqchip_add(...) \ - _gpiochip_irqchip_add(__VA_ARGS__, false, NULL) -#endif +static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type) +{ + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, true, NULL); +} +#endif /* CONFIG_LOCKDEP */ #endif /* CONFIG_GPIOLIB_IRQCHIP */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 01033fadea47..c1784c0b4f35 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -284,7 +284,7 @@ extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, unsigned long map_offset); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); -extern int zone_can_shift(unsigned long pfn, unsigned long nr_pages, - enum zone_type target); +extern bool zone_can_shift(unsigned long pfn, unsigned long nr_pages, + enum zone_type target, int *zone_shift); #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 257173e0095e..f541da68d1e7 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -35,6 +35,8 @@ #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 +#define PHY_ID_KSZ8795 0x00221550 + /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 #define MICREL_PHY_FXEN 0x00000002 diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 36d9896fbc1e..f4aac87adcc3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -972,12 +972,16 @@ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, * @zonelist - The zonelist to search for a suitable zone * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with - * @zone - The first suitable zone found is returned via this parameter + * @return - Zoneref pointer for the first suitable zone found (see below) * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. + * + * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is + * never NULL). This may happen either genuinely, or due to concurrent nodemask + * update due to cpuset modification. */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index bca536341d1a..1b1ca04820a3 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -282,7 +282,7 @@ enum nfsstat4 { static inline bool seqid_mutating_err(u32 err) { - /* rfc 3530 section 8.1.5: */ + /* See RFC 7530, section 9.1.7 */ switch (err) { case NFS4ERR_STALE_CLIENTID: case NFS4ERR_STALE_STATEID: @@ -291,6 +291,7 @@ static inline bool seqid_mutating_err(u32 err) case NFS4ERR_BADXDR: case NFS4ERR_RESOURCE: case NFS4ERR_NOFILEHANDLE: + case NFS4ERR_MOVED: return false; }; return true; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index aacca824a6ae..0a3fadc32693 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -110,6 +110,7 @@ extern int watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; extern unsigned long *watchdog_cpumask_bits; +extern atomic_t watchdog_park_in_progress; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; diff --git a/include/linux/phy.h b/include/linux/phy.h index f7d95f644eed..7fc1105605bf 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -25,7 +25,6 @@ #include #include #include -#include #include diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h index a2daea0a37d2..b37b05bfd1a6 100644 --- a/include/linux/phy_led_triggers.h +++ b/include/linux/phy_led_triggers.h @@ -18,11 +18,11 @@ struct phy_device; #ifdef CONFIG_LED_TRIGGER_PHY #include +#include #define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 10 -#define PHY_MII_BUS_ID_SIZE (20 - 3) -#define PHY_LINK_LED_TRIGGER_NAME_SIZE (PHY_MII_BUS_ID_SIZE + \ +#define PHY_LINK_LED_TRIGGER_NAME_SIZE (MII_BUS_ID_SIZE + \ FIELD_SIZEOF(struct mdio_device, addr)+\ PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE) diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 85cc819676e8..333ad11b3dd9 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -216,5 +216,6 @@ void rpc_clnt_xprt_switch_put(struct rpc_clnt *); void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *); bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, const struct sockaddr *sap); +void rpc_cleanup_clids(void); #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 0c729c3c8549..d9718378a8be 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -194,8 +194,6 @@ struct platform_freeze_ops { }; #ifdef CONFIG_SUSPEND -extern suspend_state_t mem_sleep_default; - /** * suspend_set_ops - set platform dependent suspend operations * @ops: The new suspend operations to set. diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 66204007d7ac..5209b5ed2a64 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -56,7 +56,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, - bool little_endian) + bool little_endian, + bool has_data_valid) { memset(hdr, 0, sizeof(*hdr)); /* no info leak */ @@ -91,7 +92,8 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, skb_checksum_start_offset(skb)); hdr->csum_offset = __cpu_to_virtio16(little_endian, skb->csum_offset); - } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + } else if (has_data_valid && + skb->ip_summed == CHECKSUM_UNNECESSARY) { hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 487e57391664..7afe991e900e 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -871,7 +871,7 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); * upper-layer output functions */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, - struct ipv6_txoptions *opt, int tclass); + __u32 mark, struct ipv6_txoptions *opt, int tclass); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index d4c1c75b8862..73dd87647460 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -44,6 +44,8 @@ struct lwtunnel_encap_ops { int (*get_encap_size)(struct lwtunnel_state *lwtstate); int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b); int (*xmit)(struct sk_buff *skb); + + struct module *owner; }; #ifdef CONFIG_LWTUNNEL @@ -105,6 +107,8 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num); +int lwtunnel_valid_encap_type(u16 encap_type); +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len); int lwtunnel_build_state(struct net_device *dev, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, @@ -168,6 +172,15 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, return -EOPNOTSUPP; } +static inline int lwtunnel_valid_encap_type(u16 encap_type) +{ + return -EOPNOTSUPP; +} +static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len) +{ + return -EOPNOTSUPP; +} + static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 924325c46aab..7dfdb517f0be 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -207,9 +207,9 @@ struct nft_set_iter { unsigned int skip; int err; int (*fn)(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, const struct nft_set_iter *iter, - const struct nft_set_elem *elem); + struct nft_set_elem *elem); }; /** @@ -301,7 +301,7 @@ struct nft_set_ops { void (*remove)(const struct nft_set *set, const struct nft_set_elem *elem); void (*walk)(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, struct nft_set_iter *iter); unsigned int (*privsize)(const struct nlattr * const nla[]); diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index cbedda077db2..5ceb2205e4e3 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -9,6 +9,12 @@ struct nft_fib { extern const struct nla_policy nft_fib_policy[]; +static inline bool +nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in) +{ + return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; +} + int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr); int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 958a24d8fae7..b567e4452a47 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -352,6 +352,20 @@ static inline int ib_mtu_enum_to_int(enum ib_mtu mtu) } } +static inline enum ib_mtu ib_mtu_int_to_enum(int mtu) +{ + if (mtu >= 4096) + return IB_MTU_4096; + else if (mtu >= 2048) + return IB_MTU_2048; + else if (mtu >= 1024) + return IB_MTU_1024; + else if (mtu >= 512) + return IB_MTU_512; + else + return IB_MTU_256; +} + enum ib_port_state { IB_PORT_NOP = 0, IB_PORT_DOWN = 1, diff --git a/include/soc/arc/mcip.h b/include/soc/arc/mcip.h index 6902c2a8bd23..4b6b489a8d7c 100644 --- a/include/soc/arc/mcip.h +++ b/include/soc/arc/mcip.h @@ -55,17 +55,17 @@ struct mcip_cmd { struct mcip_bcr { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int pad3:8, - idu:1, llm:1, num_cores:6, - iocoh:1, gfrc:1, dbg:1, pad2:1, - msg:1, sem:1, ipi:1, pad:1, + unsigned int pad4:6, pw_dom:1, pad3:1, + idu:1, pad2:1, num_cores:6, + pad:1, gfrc:1, dbg:1, pw:1, + msg:1, sem:1, ipi:1, slv:1, ver:8; #else unsigned int ver:8, - pad:1, ipi:1, sem:1, msg:1, - pad2:1, dbg:1, gfrc:1, iocoh:1, - num_cores:6, llm:1, idu:1, - pad3:8; + slv:1, ipi:1, sem:1, msg:1, + pw:1, dbg:1, gfrc:1, pad:1, + num_cores:6, pad2:1, idu:1, + pad3:1, pw_dom:1, pad4:6; #endif }; diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index 3cbc327801d6..c451eec42a83 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -1665,14 +1665,15 @@ static inline void cec_msg_report_current_latency(struct cec_msg *msg, __u8 audio_out_compensated, __u8 audio_out_delay) { - msg->len = 7; + msg->len = 6; msg->msg[0] |= 0xf; /* broadcast */ msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; msg->msg[4] = video_latency; msg->msg[5] = (low_latency_mode << 2) | audio_out_compensated; - msg->msg[6] = audio_out_delay; + if (audio_out_compensated == 3) + msg->msg[msg->len++] = audio_out_delay; } static inline void cec_ops_report_current_latency(const struct cec_msg *msg, @@ -1686,7 +1687,10 @@ static inline void cec_ops_report_current_latency(const struct cec_msg *msg, *video_latency = msg->msg[4]; *low_latency_mode = (msg->msg[5] >> 2) & 1; *audio_out_compensated = msg->msg[5] & 3; - *audio_out_delay = msg->msg[6]; + if (*audio_out_compensated == 3 && msg->len >= 7) + *audio_out_delay = msg->msg[6]; + else + *audio_out_delay = 0; } static inline void cec_msg_request_current_latency(struct cec_msg *msg, diff --git a/include/uapi/linux/netfilter/nf_log.h b/include/uapi/linux/netfilter/nf_log.h index 8be21e02387d..d0b5fa91ff54 100644 --- a/include/uapi/linux/netfilter/nf_log.h +++ b/include/uapi/linux/netfilter/nf_log.h @@ -9,4 +9,6 @@ #define NF_LOG_MACDECODE 0x20 /* Decode MAC header */ #define NF_LOG_MASK 0x2f +#define NF_LOG_PREFIXLEN 128 + #endif /* _NETFILTER_NF_LOG_H */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 881d49e94569..e3f27e09eb2b 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -235,7 +235,7 @@ enum nft_rule_compat_flags { /** * enum nft_rule_compat_attributes - nf_tables rule compat attributes * - * @NFTA_RULE_COMPAT_PROTO: numerice value of handled protocol (NLA_U32) + * @NFTA_RULE_COMPAT_PROTO: numeric value of handled protocol (NLA_U32) * @NFTA_RULE_COMPAT_FLAGS: bitmask of enum nft_rule_compat_flags (NLA_U32) */ enum nft_rule_compat_attributes { @@ -499,7 +499,7 @@ enum nft_bitwise_attributes { * enum nft_byteorder_ops - nf_tables byteorder operators * * @NFT_BYTEORDER_NTOH: network to host operator - * @NFT_BYTEORDER_HTON: host to network opertaor + * @NFT_BYTEORDER_HTON: host to network operator */ enum nft_byteorder_ops { NFT_BYTEORDER_NTOH, diff --git a/include/uapi/rdma/Kbuild b/include/uapi/rdma/Kbuild index 82bdf5626859..bb68cb1b04ed 100644 --- a/include/uapi/rdma/Kbuild +++ b/include/uapi/rdma/Kbuild @@ -16,3 +16,4 @@ header-y += nes-abi.h header-y += ocrdma-abi.h header-y += hns-abi.h header-y += vmw_pvrdma-abi.h +header-y += qedr-abi.h diff --git a/include/uapi/rdma/cxgb3-abi.h b/include/uapi/rdma/cxgb3-abi.h index 48a19bda071b..d24eee12128f 100644 --- a/include/uapi/rdma/cxgb3-abi.h +++ b/include/uapi/rdma/cxgb3-abi.h @@ -30,7 +30,7 @@ * SOFTWARE. */ #ifndef CXGB3_ABI_USER_H -#define CXBG3_ABI_USER_H +#define CXGB3_ABI_USER_H #include diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 229a5d5df977..3d55d95dcf49 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -11,7 +11,6 @@ */ #include #include -#include #include #include #include @@ -74,14 +73,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) if (array_size >= U32_MAX - PAGE_SIZE) return ERR_PTR(-ENOMEM); - /* allocate all map elements and zero-initialize them */ - array = kzalloc(array_size, GFP_USER | __GFP_NOWARN); - if (!array) { - array = vzalloc(array_size); - if (!array) - return ERR_PTR(-ENOMEM); - } + array = bpf_map_area_alloc(array_size); + if (!array) + return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ array->map.map_type = attr->map_type; @@ -97,7 +92,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) if (array_size >= U32_MAX - PAGE_SIZE || elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) { - kvfree(array); + bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } out: @@ -262,7 +257,7 @@ static void array_map_free(struct bpf_map *map) if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); - kvfree(array); + bpf_map_area_free(array); } static const struct bpf_map_ops array_ops = { @@ -319,7 +314,8 @@ static void fd_array_map_free(struct bpf_map *map) /* make sure it's empty */ for (i = 0; i < array->map.max_entries; i++) BUG_ON(array->ptrs[i] != NULL); - kvfree(array); + + bpf_map_area_free(array); } static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3f2bb58952d8..a753bbe7df0a 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -13,7 +13,6 @@ #include #include #include -#include #include "percpu_freelist.h" #include "bpf_lru_list.h" @@ -103,7 +102,7 @@ static void htab_free_elems(struct bpf_htab *htab) free_percpu(pptr); } free_elems: - vfree(htab->elems); + bpf_map_area_free(htab->elems); } static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, @@ -125,7 +124,8 @@ static int prealloc_init(struct bpf_htab *htab) { int err = -ENOMEM, i; - htab->elems = vzalloc(htab->elem_size * htab->map.max_entries); + htab->elems = bpf_map_area_alloc(htab->elem_size * + htab->map.max_entries); if (!htab->elems) return -ENOMEM; @@ -320,14 +320,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) goto free_htab; err = -ENOMEM; - htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket), - GFP_USER | __GFP_NOWARN); - - if (!htab->buckets) { - htab->buckets = vmalloc(htab->n_buckets * sizeof(struct bucket)); - if (!htab->buckets) - goto free_htab; - } + htab->buckets = bpf_map_area_alloc(htab->n_buckets * + sizeof(struct bucket)); + if (!htab->buckets) + goto free_htab; for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_HEAD(&htab->buckets[i].head); @@ -354,7 +350,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) free_extra_elems: free_percpu(htab->extra_elems); free_buckets: - kvfree(htab->buckets); + bpf_map_area_free(htab->buckets); free_htab: kfree(htab); return ERR_PTR(err); @@ -1014,7 +1010,7 @@ static void htab_map_free(struct bpf_map *map) prealloc_destroy(htab); free_percpu(htab->extra_elems); - kvfree(htab->buckets); + bpf_map_area_free(htab->buckets); kfree(htab); } diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 732ae16d12b7..be8519148c25 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -7,7 +7,6 @@ #include #include #include -#include #include #include #include "percpu_freelist.h" @@ -32,7 +31,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; int err; - smap->elems = vzalloc(elem_size * smap->map.max_entries); + smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries); if (!smap->elems) return -ENOMEM; @@ -45,7 +44,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) return 0; free_elems: - vfree(smap->elems); + bpf_map_area_free(smap->elems); return err; } @@ -76,12 +75,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); - smap = kzalloc(cost, GFP_USER | __GFP_NOWARN); - if (!smap) { - smap = vzalloc(cost); - if (!smap) - return ERR_PTR(-ENOMEM); - } + smap = bpf_map_area_alloc(cost); + if (!smap) + return ERR_PTR(-ENOMEM); err = -E2BIG; cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); @@ -112,7 +108,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) put_buffers: put_callchain_buffers(); free_smap: - kvfree(smap); + bpf_map_area_free(smap); return ERR_PTR(err); } @@ -262,9 +258,9 @@ static void stack_map_free(struct bpf_map *map) /* wait for bpf programs to complete before freeing stack map */ synchronize_rcu(); - vfree(smap->elems); + bpf_map_area_free(smap->elems); pcpu_freelist_destroy(&smap->freelist); - kvfree(smap); + bpf_map_area_free(smap); put_callchain_buffers(); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1d6b29e4e2c3..19b6129eab23 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include #include @@ -49,6 +51,30 @@ void bpf_register_map_type(struct bpf_map_type_list *tl) list_add(&tl->list_node, &bpf_map_types); } +void *bpf_map_area_alloc(size_t size) +{ + /* We definitely need __GFP_NORETRY, so OOM killer doesn't + * trigger under memory pressure as we really just want to + * fail instead. + */ + const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO; + void *area; + + if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { + area = kmalloc(size, GFP_USER | flags); + if (area != NULL) + return area; + } + + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags, + PAGE_KERNEL); +} + +void bpf_map_area_free(void *area) +{ + kvfree(area); +} + int bpf_map_precharge_memlock(u32 pages) { struct user_struct *user = get_current_user(); diff --git a/kernel/panic.c b/kernel/panic.c index 901c4fb46002..08aa88dde7de 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -249,7 +249,7 @@ void panic(const char *fmt, ...) * Delay timeout seconds before rebooting the machine. * We can't use the "normal" timers since we just panicked. */ - pr_emerg("Rebooting in %d seconds..", panic_timeout); + pr_emerg("Rebooting in %d seconds..\n", panic_timeout); for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index f67ceb7768b8..15e6baef5c73 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -46,7 +46,7 @@ static const char * const mem_sleep_labels[] = { const char *mem_sleep_states[PM_SUSPEND_MAX]; suspend_state_t mem_sleep_current = PM_SUSPEND_FREEZE; -suspend_state_t mem_sleep_default = PM_SUSPEND_MAX; +static suspend_state_t mem_sleep_default = PM_SUSPEND_MEM; unsigned int pm_suspend_global_flags; EXPORT_SYMBOL_GPL(pm_suspend_global_flags); @@ -168,7 +168,7 @@ void suspend_set_ops(const struct platform_suspend_ops *ops) } if (valid_state(PM_SUSPEND_MEM)) { mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM]; - if (mem_sleep_default >= PM_SUSPEND_MEM) + if (mem_sleep_default == PM_SUSPEND_MEM) mem_sleep_current = PM_SUSPEND_MEM; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8dbaec0e4f7f..1aea594a54db 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2475,6 +2475,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int break; if (neg) continue; + val = convmul * val / convdiv; if ((min && val < *min) || (max && val > *max)) continue; *i = val; diff --git a/kernel/ucount.c b/kernel/ucount.c index 9d20d5dd298a..4bbd38ec3788 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -128,10 +128,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) struct hlist_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; - spin_lock(&ucounts_lock); + spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (!ucounts) { - spin_unlock(&ucounts_lock); + spin_unlock_irq(&ucounts_lock); new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) @@ -141,7 +141,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) new->uid = uid; atomic_set(&new->count, 0); - spin_lock(&ucounts_lock); + spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (ucounts) { kfree(new); @@ -152,16 +152,18 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) } if (!atomic_add_unless(&ucounts->count, 1, INT_MAX)) ucounts = NULL; - spin_unlock(&ucounts_lock); + spin_unlock_irq(&ucounts_lock); return ucounts; } static void put_ucounts(struct ucounts *ucounts) { + unsigned long flags; + if (atomic_dec_and_test(&ucounts->count)) { - spin_lock(&ucounts_lock); + spin_lock_irqsave(&ucounts_lock, flags); hlist_del_init(&ucounts->node); - spin_unlock(&ucounts_lock); + spin_unlock_irqrestore(&ucounts_lock, flags); kfree(ucounts); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d4b0fa01cae3..63177be0159e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -49,6 +49,8 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); #define for_each_watchdog_cpu(cpu) \ for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) +atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); + /* * The 'watchdog_running' variable is set to 1 when the watchdog threads * are registered/started and is set to 0 when the watchdog threads are @@ -260,6 +262,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; + if (atomic_read(&watchdog_park_in_progress) != 0) + return HRTIMER_NORESTART; + /* kick the hardlockup detector */ watchdog_interrupt_count(); @@ -467,12 +472,16 @@ static int watchdog_park_threads(void) { int cpu, ret = 0; + atomic_set(&watchdog_park_in_progress, 1); + for_each_watchdog_cpu(cpu) { ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); if (ret) break; } + atomic_set(&watchdog_park_in_progress, 0); + return ret; } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 84016c8aee6b..12b8dd640786 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -84,6 +84,9 @@ static void watchdog_overflow_callback(struct perf_event *event, /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; + if (atomic_read(&watchdog_park_in_progress) != 0) + return; + if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; diff --git a/lib/ioremap.c b/lib/ioremap.c index 86c8911b0e3a..a3e14ce92a56 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -144,4 +144,3 @@ int ioremap_page_range(unsigned long addr, return err; } -EXPORT_SYMBOL_GPL(ioremap_page_range); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 0b92d605fb69..84812a9fb16f 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -769,7 +769,7 @@ static void radix_tree_free_nodes(struct radix_tree_node *node) struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; - WARN_ON_ONCE(!list_empty(&node->private_list)); + WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9a6bd6c8d55a..5f3ad65c85de 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -783,6 +783,12 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, assert_spin_locked(pmd_lockptr(mm, pmd)); + /* + * When we COW a devmap PMD entry, we split it into PTEs, so we should + * not be in this function with `flags & FOLL_COW` set. + */ + WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set"); + if (flags & FOLL_WRITE && !pmd_write(*pmd)) return NULL; @@ -1128,6 +1134,16 @@ out_unlock: return ret; } +/* + * FOLL_FORCE can write to even unwritable pmd's, but only + * after we've gone through a COW cycle and they are dirty. + */ +static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +{ + return pmd_write(pmd) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); +} + struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, @@ -1138,7 +1154,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, assert_spin_locked(pmd_lockptr(mm, pmd)); - if (flags & FOLL_WRITE && !pmd_write(*pmd)) + if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) goto out; /* Avoid dumping huge zero page */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a63a8f832664..b822e158b319 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4353,9 +4353,9 @@ static int mem_cgroup_do_precharge(unsigned long count) return ret; } - /* Try charges one by one with reclaim */ + /* Try charges one by one with reclaim, but do not retry */ while (count--) { - ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1); + ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1); if (ret) return ret; mc.precharge++; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e43142c15631..ca2723d47338 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1033,36 +1033,39 @@ static void node_states_set_node(int node, struct memory_notify *arg) node_set_state(node, N_MEMORY); } -int zone_can_shift(unsigned long pfn, unsigned long nr_pages, - enum zone_type target) +bool zone_can_shift(unsigned long pfn, unsigned long nr_pages, + enum zone_type target, int *zone_shift) { struct zone *zone = page_zone(pfn_to_page(pfn)); enum zone_type idx = zone_idx(zone); int i; + *zone_shift = 0; + if (idx < target) { /* pages must be at end of current zone */ if (pfn + nr_pages != zone_end_pfn(zone)) - return 0; + return false; /* no zones in use between current zone and target */ for (i = idx + 1; i < target; i++) if (zone_is_initialized(zone - idx + i)) - return 0; + return false; } if (target < idx) { /* pages must be at beginning of current zone */ if (pfn != zone->zone_start_pfn) - return 0; + return false; /* no zones in use between current zone and target */ for (i = target + 1; i < idx; i++) if (zone_is_initialized(zone - idx + i)) - return 0; + return false; } - return target - idx; + *zone_shift = target - idx; + return true; } /* Must be protected by mem_hotplug_begin() */ @@ -1089,10 +1092,13 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ !can_online_high_movable(zone)) return -EINVAL; - if (online_type == MMOP_ONLINE_KERNEL) - zone_shift = zone_can_shift(pfn, nr_pages, ZONE_NORMAL); - else if (online_type == MMOP_ONLINE_MOVABLE) - zone_shift = zone_can_shift(pfn, nr_pages, ZONE_MOVABLE); + if (online_type == MMOP_ONLINE_KERNEL) { + if (!zone_can_shift(pfn, nr_pages, ZONE_NORMAL, &zone_shift)) + return -EINVAL; + } else if (online_type == MMOP_ONLINE_MOVABLE) { + if (!zone_can_shift(pfn, nr_pages, ZONE_MOVABLE, &zone_shift)) + return -EINVAL; + } zone = move_pfn_range(zone_shift, pfn, pfn + nr_pages); if (!zone) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2e346645eb80..1e7873e40c9a 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2017,8 +2017,8 @@ retry_cpuset: nmask = policy_nodemask(gfp, pol); zl = policy_zonelist(gfp, pol, node); - mpol_cond_put(pol); page = __alloc_pages_nodemask(gfp, order, zl, nmask); + mpol_cond_put(pol); out: if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d604d2596b7b..f3e0c69a97b7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3523,12 +3523,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct page *page = NULL; unsigned int alloc_flags; unsigned long did_some_progress; - enum compact_priority compact_priority = DEF_COMPACT_PRIORITY; + enum compact_priority compact_priority; enum compact_result compact_result; - int compaction_retries = 0; - int no_progress_loops = 0; + int compaction_retries; + int no_progress_loops; unsigned long alloc_start = jiffies; unsigned int stall_timeout = 10 * HZ; + unsigned int cpuset_mems_cookie; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -3549,6 +3550,23 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) gfp_mask &= ~__GFP_ATOMIC; +retry_cpuset: + compaction_retries = 0; + no_progress_loops = 0; + compact_priority = DEF_COMPACT_PRIORITY; + cpuset_mems_cookie = read_mems_allowed_begin(); + /* + * We need to recalculate the starting point for the zonelist iterator + * because we might have used different nodemask in the fast path, or + * there was a cpuset modification and we are retrying - otherwise we + * could end up iterating over non-eligible zones endlessly. + */ + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->high_zoneidx, ac->nodemask); + if (!ac->preferred_zoneref->zone) + goto nopage; + + /* * The fast path uses conservative alloc_flags to succeed only until * kswapd needs to be woken up, and to avoid the cost of setting up @@ -3708,6 +3726,13 @@ retry: &compaction_retries)) goto retry; + /* + * It's possible we raced with cpuset update so the OOM would be + * premature (see below the nopage: label for full explanation). + */ + if (read_mems_allowed_retry(cpuset_mems_cookie)) + goto retry_cpuset; + /* Reclaim has failed us, start killing things */ page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); if (page) @@ -3720,6 +3745,16 @@ retry: } nopage: + /* + * When updating a task's mems_allowed or mempolicy nodemask, it is + * possible to race with parallel threads in such a way that our + * allocation can fail while the mask is being updated. If we are about + * to fail, check if the cpuset changed during allocation and if so, + * retry. + */ + if (read_mems_allowed_retry(cpuset_mems_cookie)) + goto retry_cpuset; + warn_alloc(gfp_mask, "page allocation failure: order:%u", order); got_pg: @@ -3734,7 +3769,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, nodemask_t *nodemask) { struct page *page; - unsigned int cpuset_mems_cookie; unsigned int alloc_flags = ALLOC_WMARK_LOW; gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */ struct alloc_context ac = { @@ -3771,9 +3805,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; -retry_cpuset: - cpuset_mems_cookie = read_mems_allowed_begin(); - /* Dirty zone balancing only done in the fast path */ ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE); @@ -3784,8 +3815,13 @@ retry_cpuset: */ ac.preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx, ac.nodemask); - if (!ac.preferred_zoneref) { + if (!ac.preferred_zoneref->zone) { page = NULL; + /* + * This might be due to race with cpuset_current_mems_allowed + * update, so make sure we retry with original nodemask in the + * slow path. + */ goto no_zone; } @@ -3794,6 +3830,7 @@ retry_cpuset: if (likely(page)) goto out; +no_zone: /* * Runtime PM, block IO and its error handling path can deadlock * because I/O on the device might not complete. @@ -3805,21 +3842,10 @@ retry_cpuset: * Restore the original nodemask if it was potentially replaced with * &cpuset_current_mems_allowed to optimize the fast-path attempt. */ - if (cpusets_enabled()) + if (unlikely(ac.nodemask != nodemask)) ac.nodemask = nodemask; - page = __alloc_pages_slowpath(alloc_mask, order, &ac); -no_zone: - /* - * When updating a task's mems_allowed, it is possible to race with - * parallel threads in such a way that an allocation can fail while - * the mask is being updated. If a page allocation is about to fail, - * check if the cpuset changed during allocation and if so, retry. - */ - if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) { - alloc_mask = gfp_mask; - goto retry_cpuset; - } + page = __alloc_pages_slowpath(alloc_mask, order, &ac); out: if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page && @@ -7248,6 +7274,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .zone = page_zone(pfn_to_page(start)), .mode = MIGRATE_SYNC, .ignore_skip_hint = true, + .gfp_mask = GFP_KERNEL, }; INIT_LIST_HEAD(&cc.migratepages); diff --git a/mm/slub.c b/mm/slub.c index 067598a00849..7aa6f433f4de 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -496,10 +496,11 @@ static inline int check_valid_pointer(struct kmem_cache *s, return 1; } -static void print_section(char *text, u8 *addr, unsigned int length) +static void print_section(char *level, char *text, u8 *addr, + unsigned int length) { metadata_access_enable(); - print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr, + print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, 16, 1, addr, length, 1); metadata_access_disable(); } @@ -636,14 +637,15 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) p, p - addr, get_freepointer(s, p)); if (s->flags & SLAB_RED_ZONE) - print_section("Redzone ", p - s->red_left_pad, s->red_left_pad); + print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, + s->red_left_pad); else if (p > addr + 16) - print_section("Bytes b4 ", p - 16, 16); + print_section(KERN_ERR, "Bytes b4 ", p - 16, 16); - print_section("Object ", p, min_t(unsigned long, s->object_size, - PAGE_SIZE)); + print_section(KERN_ERR, "Object ", p, + min_t(unsigned long, s->object_size, PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) - print_section("Redzone ", p + s->object_size, + print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); if (s->offset) @@ -658,7 +660,8 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (off != size_from_object(s)) /* Beginning of the filler is the free pointer */ - print_section("Padding ", p + off, size_from_object(s) - off); + print_section(KERN_ERR, "Padding ", p + off, + size_from_object(s) - off); dump_stack(); } @@ -820,7 +823,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) end--; slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1); - print_section("Padding ", end - remainder, remainder); + print_section(KERN_ERR, "Padding ", end - remainder, remainder); restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end); return 0; @@ -973,7 +976,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object, page->freelist); if (!alloc) - print_section("Object ", (void *)object, + print_section(KERN_INFO, "Object ", (void *)object, s->object_size); dump_stack(); diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 9c561e683f4b..0854ebd8613e 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -474,7 +474,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) { ret = -EINVAL; - goto put_primary_if; + goto free_skb; } /* Create one header to be copied to all fragments */ @@ -502,7 +502,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, skb_fragment = batadv_frag_create(skb, &frag_header, mtu); if (!skb_fragment) { ret = -ENOMEM; - goto free_skb; + goto put_primary_if; } batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_TX); @@ -511,7 +511,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, ret = batadv_send_unicast_skb(skb_fragment, neigh_node); if (ret != NET_XMIT_SUCCESS) { ret = NET_XMIT_DROP; - goto free_skb; + goto put_primary_if; } frag_header.no++; @@ -519,7 +519,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, /* The initial check in this function should cover this case */ if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1) { ret = -EINVAL; - goto free_skb; + goto put_primary_if; } } @@ -527,7 +527,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, if (batadv_skb_head_push(skb, header_size) < 0 || pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0) { ret = -ENOMEM; - goto free_skb; + goto put_primary_if; } memcpy(skb->data, &frag_header, header_size); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 71c7453268c1..7109b389ea58 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -781,20 +781,6 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int br_dev_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) -{ - struct net_bridge *br = netdev_priv(dev); - - if (tb[IFLA_ADDRESS]) { - spin_lock_bh(&br->lock); - br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); - spin_unlock_bh(&br->lock); - } - - return register_netdevice(dev); -} - static int br_port_slave_changelink(struct net_device *brdev, struct net_device *dev, struct nlattr *tb[], @@ -1115,6 +1101,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], return 0; } +static int br_dev_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net_bridge *br = netdev_priv(dev); + int err; + + if (tb[IFLA_ADDRESS]) { + spin_lock_bh(&br->lock); + br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); + spin_unlock_bh(&br->lock); + } + + err = br_changelink(dev, tb, data); + if (err) + return err; + + return register_netdevice(dev); +} + static size_t br_get_size(const struct net_device *brdev) { return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ diff --git a/net/core/dev.c b/net/core/dev.c index 07b307b0b414..7f218e095361 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2795,9 +2795,9 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); - } else if (illegal_highdma(skb->dev, skb)) { - features &= ~NETIF_F_SG; } + if (illegal_highdma(skb->dev, skb)) + features &= ~NETIF_F_SG; return features; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index e23766c7e3ba..236a21e3c878 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1712,7 +1712,7 @@ static noinline_for_stack int ethtool_get_channels(struct net_device *dev, static noinline_for_stack int ethtool_set_channels(struct net_device *dev, void __user *useraddr) { - struct ethtool_channels channels, max; + struct ethtool_channels channels, max = { .cmd = ETHTOOL_GCHANNELS }; u32 max_rx_in_use = 0; if (!dev->ethtool_ops->set_channels || !dev->ethtool_ops->get_channels) diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 71bb3e2eca08..b3eef90b2df9 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -386,6 +386,7 @@ static const struct lwtunnel_encap_ops bpf_encap_ops = { .fill_encap = bpf_fill_encap_info, .get_encap_size = bpf_encap_nlsize, .cmp_encap = bpf_encap_cmp, + .owner = THIS_MODULE, }; static int __init bpf_lwt_init(void) diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index a5d4e866ce88..c23465005f2f 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -26,6 +26,7 @@ #include #include #include +#include #ifdef CONFIG_MODULES @@ -114,26 +115,78 @@ int lwtunnel_build_state(struct net_device *dev, u16 encap_type, ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); -#ifdef CONFIG_MODULES - if (!ops) { - const char *encap_type_str = lwtunnel_encap_str(encap_type); - - if (encap_type_str) { - rcu_read_unlock(); - request_module("rtnl-lwt-%s", encap_type_str); - rcu_read_lock(); - ops = rcu_dereference(lwtun_encaps[encap_type]); - } - } -#endif - if (likely(ops && ops->build_state)) + if (likely(ops && ops->build_state && try_module_get(ops->owner))) { ret = ops->build_state(dev, encap, family, cfg, lws); + if (ret) + module_put(ops->owner); + } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(lwtunnel_build_state); +int lwtunnel_valid_encap_type(u16 encap_type) +{ + const struct lwtunnel_encap_ops *ops; + int ret = -EINVAL; + + if (encap_type == LWTUNNEL_ENCAP_NONE || + encap_type > LWTUNNEL_ENCAP_MAX) + return ret; + + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[encap_type]); + rcu_read_unlock(); +#ifdef CONFIG_MODULES + if (!ops) { + const char *encap_type_str = lwtunnel_encap_str(encap_type); + + if (encap_type_str) { + __rtnl_unlock(); + request_module("rtnl-lwt-%s", encap_type_str); + rtnl_lock(); + + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[encap_type]); + rcu_read_unlock(); + } + } +#endif + return ops ? 0 : -EOPNOTSUPP; +} +EXPORT_SYMBOL(lwtunnel_valid_encap_type); + +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) +{ + struct rtnexthop *rtnh = (struct rtnexthop *)attr; + struct nlattr *nla_entype; + struct nlattr *attrs; + struct nlattr *nla; + u16 encap_type; + int attrlen; + + while (rtnh_ok(rtnh, remaining)) { + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + attrs = rtnh_attrs(rtnh); + nla = nla_find(attrs, attrlen, RTA_ENCAP); + nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); + + if (nla_entype) { + encap_type = nla_get_u16(nla_entype); + + if (lwtunnel_valid_encap_type(encap_type) != 0) + return -EOPNOTSUPP; + } + } + rtnh = rtnh_next(rtnh, &remaining); + } + + return 0; +} +EXPORT_SYMBOL(lwtunnel_valid_encap_type_attr); + void lwtstate_free(struct lwtunnel_state *lws) { const struct lwtunnel_encap_ops *ops = lwtun_encaps[lws->type]; @@ -144,6 +197,7 @@ void lwtstate_free(struct lwtunnel_state *lws) } else { kfree(lws); } + module_put(ops->owner); } EXPORT_SYMBOL(lwtstate_free); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index adfc790f7193..c4e879c02186 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -227,7 +227,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); + err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -281,7 +281,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); - ip6_xmit(ctl_sk, skb, &fl6, NULL, 0); + ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0); DCCP_INC_STATS(DCCP_MIB_OUTSEGS); DCCP_INC_STATS(DCCP_MIB_OUTRSTS); return; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 68c9eea00518..7d4596110851 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1105,10 +1105,8 @@ static int dsa_slave_phy_connect(struct dsa_slave_priv *p, /* Use already configured phy mode */ if (p->phy_interface == PHY_INTERFACE_MODE_NA) p->phy_interface = p->phy->interface; - phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, - p->phy_interface); - - return 0; + return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, + p->phy_interface); } static int dsa_slave_phy_setup(struct dsa_slave_priv *p, @@ -1203,6 +1201,8 @@ int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_slave_priv *p = netdev_priv(slave_dev); + netif_device_detach(slave_dev); + if (p->phy) { phy_stop(p->phy); p->old_pause = -1; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index eae0332b0e8c..7db2ad2e82d3 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #ifndef CONFIG_IP_MULTIPLE_TABLES @@ -677,6 +678,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, cfg->fc_mx_len = nla_len(attr); break; case RTA_MULTIPATH: + err = lwtunnel_valid_encap_type_attr(nla_data(attr), + nla_len(attr)); + if (err < 0) + goto errout; cfg->fc_mp = nla_data(attr); cfg->fc_mp_len = nla_len(attr); break; @@ -691,6 +696,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + if (err < 0) + goto errout; break; } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index fac275c48108..b67719f45953 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1629,6 +1629,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = sysctl_wmem_default; + sk->sk_mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index fed3d29f9eb3..0fd1976ab63b 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -313,6 +313,7 @@ static const struct lwtunnel_encap_ops ip_tun_lwt_ops = { .fill_encap = ip_tun_fill_encap_info, .get_encap_size = ip_tun_encap_nlsize, .cmp_encap = ip_tun_cmp_encap, + .owner = THIS_MODULE, }; static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { @@ -403,6 +404,7 @@ static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = { .fill_encap = ip6_tun_fill_encap_info, .get_encap_size = ip6_tun_encap_nlsize, .cmp_encap = ip_tun_cmp_encap, + .owner = THIS_MODULE, }; void __init ip_tunnel_core_init(void) diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index a6b8c1a4102b..0a783cd73faf 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -144,7 +144,12 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry) rcu_read_lock_bh(); c = __clusterip_config_find(net, clusterip); if (c) { - if (!c->pde || unlikely(!atomic_inc_not_zero(&c->refcount))) +#ifdef CONFIG_PROC_FS + if (!c->pde) + c = NULL; + else +#endif + if (unlikely(!atomic_inc_not_zero(&c->refcount))) c = NULL; else if (entry) atomic_inc(&c->entries); diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index f273098e48fd..37fb9552e858 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -63,10 +63,10 @@ static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4, return dev_match || flags & XT_RPFILTER_LOOSE; } -static bool rpfilter_is_local(const struct sk_buff *skb) +static bool +rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in) { - const struct rtable *rt = skb_rtable(skb); - return rt && (rt->rt_flags & RTCF_LOCAL); + return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; } static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) @@ -79,7 +79,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) info = par->matchinfo; invert = info->flags & XT_RPFILTER_INVERT; - if (rpfilter_is_local(skb)) + if (rpfilter_is_loopback(skb, xt_in(par))) return true ^ invert; iph = ip_hdr(skb); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index fd8220213afc..146d86105183 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -126,6 +126,8 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); + nskb->mark = IP4_REPLY_MARK(net, oldskb->mark); + skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, ip4_dst_hoplimit(skb_dst(nskb))); diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index 965b1a161369..2981291910dd 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -26,13 +26,6 @@ static __be32 get_saddr(__be32 addr) return addr; } -static bool fib4_is_local(const struct sk_buff *skb) -{ - const struct rtable *rt = skb_rtable(skb); - - return rt && (rt->rt_flags & RTCF_LOCAL); -} - #define DSCP_BITS 0xfc void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, @@ -95,8 +88,10 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, else oif = NULL; - if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib4_is_local(pkt->skb)) { - nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX); + if (nft_hook(pkt) == NF_INET_PRE_ROUTING && + nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { + nft_fib_store_result(dest, priv->result, pkt, + nft_in(pkt)->ifindex); return; } @@ -131,7 +126,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, switch (res.type) { case RTN_UNICAST: break; - case RTN_LOCAL: /* should not appear here, see fib4_is_local() above */ + case RTN_LOCAL: /* Should not see RTN_LOCAL here */ return; default: break; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index f51919535ca7..dd2560c83a85 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -205,6 +205,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, * scaled. So correct it appropriately. */ tp->snd_wnd = ntohs(tcp_hdr(skb)->window); + tp->max_window = tp->snd_wnd; /* Activate the retrans timer so that SYNACK can be retransmitted. * The request socket is not added to the ehash diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6c790754ae3e..41dcbd568cbe 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5078,7 +5078,7 @@ static void tcp_check_space(struct sock *sk) if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) { sock_reset_flag(sk, SOCK_QUEUE_SHRUNK); /* pairs with tcp_poll() */ - smp_mb__after_atomic(); + smp_mb(); if (sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { tcp_new_space(sk); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c1e124bc8e1e..f60e88e56255 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5540,8 +5540,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf) struct net_device *dev; struct inet6_dev *idev; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { + for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); @@ -5550,7 +5549,6 @@ static void addrconf_disable_change(struct net *net, __s32 newf) dev_disable_change(idev); } } - rcu_read_unlock(); } static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index a7bc54ab46e2..13b5e85fe0d5 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -238,6 +238,7 @@ static const struct lwtunnel_encap_ops ila_encap_ops = { .fill_encap = ila_fill_encap_info, .get_encap_size = ila_encap_nlsize, .cmp_encap = ila_encap_cmp, + .owner = THIS_MODULE, }; int ila_lwt_init(void) diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 7396e75e161b..75c308239243 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -176,7 +176,7 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused /* Restore final destination back after routing done */ fl6.daddr = sk->sk_v6_daddr; - res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt), + res = ip6_xmit(sk, skb, &fl6, sk->sk_mark, rcu_dereference(np->opt), np->tclass); rcu_read_unlock(); return res; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 75b6108234dd..558631860d91 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -582,6 +582,9 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) return -1; offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); + /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ + ipv6h = ipv6_hdr(skb); + if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 38122d04fadc..2c0df09e9036 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -172,7 +172,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) * which are using proper atomic operations or spinlocks. */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, - struct ipv6_txoptions *opt, int tclass) + __u32 mark, struct ipv6_txoptions *opt, int tclass) { struct net *net = sock_net(sk); const struct ipv6_pinfo *np = inet6_sk(sk); @@ -240,7 +240,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->mark = mark; mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 753d6d0860fb..ff8ee06491c3 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -400,18 +400,19 @@ ip6_tnl_dev_uninit(struct net_device *dev) __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) { - const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw; - __u8 nexthdr = ipv6h->nexthdr; - __u16 off = sizeof(*ipv6h); + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw; + unsigned int nhoff = raw - skb->data; + unsigned int off = nhoff + sizeof(*ipv6h); + u8 next, nexthdr = ipv6h->nexthdr; while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) { - __u16 optlen = 0; struct ipv6_opt_hdr *hdr; - if (raw + off + sizeof(*hdr) > skb->data && - !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr))) + u16 optlen; + + if (!pskb_may_pull(skb, off + sizeof(*hdr))) break; - hdr = (struct ipv6_opt_hdr *) (raw + off); + hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr; if (frag_hdr->frag_off) @@ -422,20 +423,29 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) } else { optlen = ipv6_optlen(hdr); } + /* cache hdr->nexthdr, since pskb_may_pull() might + * invalidate hdr + */ + next = hdr->nexthdr; if (nexthdr == NEXTHDR_DEST) { - __u16 i = off + 2; + u16 i = 2; + + /* Remember : hdr is no longer valid at this point. */ + if (!pskb_may_pull(skb, off + optlen)) + break; + while (1) { struct ipv6_tlv_tnl_enc_lim *tel; /* No more room for encapsulation limit */ - if (i + sizeof (*tel) > off + optlen) + if (i + sizeof(*tel) > optlen) break; - tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i]; + tel = (struct ipv6_tlv_tnl_enc_lim *) skb->data + off + i; /* return index of option if found and valid */ if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT && tel->length == 1) - return i; + return i + off - nhoff; /* else jump to next option */ if (tel->type) i += tel->length + 2; @@ -443,7 +453,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) i++; } } - nexthdr = hdr->nexthdr; + nexthdr = next; off += optlen; } return 0; @@ -1303,6 +1313,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) fl6.flowlabel = key->label; } else { offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); + /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ + ipv6h = ipv6_hdr(skb); if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index d5263dc364a9..b12e61b7b16c 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -72,10 +72,10 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, return ret; } -static bool rpfilter_is_local(const struct sk_buff *skb) +static bool +rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in) { - const struct rt6_info *rt = (const void *) skb_dst(skb); - return rt && (rt->rt6i_flags & RTF_LOCAL); + return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; } static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) @@ -85,7 +85,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) struct ipv6hdr *iph; bool invert = info->flags & XT_RPFILTER_INVERT; - if (rpfilter_is_local(skb)) + if (rpfilter_is_loopback(skb, xt_in(par))) return true ^ invert; iph = ipv6_hdr(skb); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 10090400c72f..eedee5d108d9 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -157,6 +157,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev); + fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark); security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { @@ -180,6 +181,8 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) skb_dst_set(nskb, dst); + nskb->mark = fl6.flowi6_mark; + skb_reserve(nskb, hh_len + dst->header_len); ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, ip6_dst_hoplimit(dst)); diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index c947aad8bcc6..765facf03d45 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -18,13 +18,6 @@ #include #include -static bool fib6_is_local(const struct sk_buff *skb) -{ - const struct rt6_info *rt = (const void *)skb_dst(skb); - - return rt && (rt->rt6i_flags & RTF_LOCAL); -} - static int get_ifindex(const struct net_device *dev) { return dev ? dev->ifindex : 0; @@ -164,8 +157,10 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif); - if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib6_is_local(pkt->skb)) { - nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX); + if (nft_hook(pkt) == NF_INET_PRE_ROUTING && + nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { + nft_fib_store_result(dest, priv->result, pkt, + nft_in(pkt)->ifindex); return; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4f6b067c8753..7ea85370c11c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2896,6 +2896,11 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_MULTIPATH]) { cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); + + err = lwtunnel_valid_encap_type_attr(cfg->fc_mp, + cfg->fc_mp_len); + if (err < 0) + goto errout; } if (tb[RTA_PREF]) { @@ -2909,9 +2914,14 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_ENCAP]) cfg->fc_encap = tb[RTA_ENCAP]; - if (tb[RTA_ENCAP_TYPE]) + if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + if (err < 0) + goto errout; + } + if (tb[RTA_EXPIRES]) { unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ); diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index b172d85c650a..a855eb325b03 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -176,6 +176,8 @@ static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info) val = nla_data(info->attrs[SEG6_ATTR_DST]); t_new = kmemdup(val, sizeof(*val), GFP_KERNEL); + if (!t_new) + return -ENOMEM; mutex_lock(&sdata->lock); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 1d60cb132835..c46f8cbf5ab5 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -422,6 +422,7 @@ static const struct lwtunnel_encap_ops seg6_iptun_ops = { .fill_encap = seg6_fill_encap_info, .get_encap_size = seg6_encap_nlsize, .cmp_encap = seg6_encap_cmp, + .owner = THIS_MODULE, }; int __init seg6_iptunnel_init(void) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 73bc8fc68acd..cb8929681dc7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -469,7 +469,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, opt, np->tclass); + err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -840,7 +840,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); - ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass); + ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass); TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS(net, TCP_MIB_OUTRSTS); diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 9e2641d45587..206698bc93f4 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -40,8 +40,6 @@ void rate_control_rate_init(struct sta_info *sta) ieee80211_sta_set_rx_nss(sta); - ieee80211_recalc_min_chandef(sta->sdata); - if (!ref) return; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 15fe97644ffe..5b77377e5a15 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -98,18 +98,19 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) } EXPORT_SYMBOL_GPL(mpls_pkt_too_big); -static u32 mpls_multipath_hash(struct mpls_route *rt, - struct sk_buff *skb, bool bos) +static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb) { struct mpls_entry_decoded dec; + unsigned int mpls_hdr_len = 0; struct mpls_shim_hdr *hdr; bool eli_seen = false; int label_index; u32 hash = 0; - for (label_index = 0; label_index < MAX_MP_SELECT_LABELS && !bos; + for (label_index = 0; label_index < MAX_MP_SELECT_LABELS; label_index++) { - if (!pskb_may_pull(skb, sizeof(*hdr) * label_index)) + mpls_hdr_len += sizeof(*hdr); + if (!pskb_may_pull(skb, mpls_hdr_len)) break; /* Read and decode the current label */ @@ -134,37 +135,38 @@ static u32 mpls_multipath_hash(struct mpls_route *rt, eli_seen = true; } - bos = dec.bos; - if (bos && pskb_may_pull(skb, sizeof(*hdr) * label_index + - sizeof(struct iphdr))) { + if (!dec.bos) + continue; + + /* found bottom label; does skb have room for a header? */ + if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) { const struct iphdr *v4hdr; - v4hdr = (const struct iphdr *)(mpls_hdr(skb) + - label_index); + v4hdr = (const struct iphdr *)(hdr + 1); if (v4hdr->version == 4) { hash = jhash_3words(ntohl(v4hdr->saddr), ntohl(v4hdr->daddr), v4hdr->protocol, hash); } else if (v4hdr->version == 6 && - pskb_may_pull(skb, sizeof(*hdr) * label_index + - sizeof(struct ipv6hdr))) { + pskb_may_pull(skb, mpls_hdr_len + + sizeof(struct ipv6hdr))) { const struct ipv6hdr *v6hdr; - v6hdr = (const struct ipv6hdr *)(mpls_hdr(skb) + - label_index); - + v6hdr = (const struct ipv6hdr *)(hdr + 1); hash = __ipv6_addr_jhash(&v6hdr->saddr, hash); hash = __ipv6_addr_jhash(&v6hdr->daddr, hash); hash = jhash_1word(v6hdr->nexthdr, hash); } } + + break; } return hash; } static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, - struct sk_buff *skb, bool bos) + struct sk_buff *skb) { int alive = ACCESS_ONCE(rt->rt_nhn_alive); u32 hash = 0; @@ -180,7 +182,7 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, if (alive <= 0) return NULL; - hash = mpls_multipath_hash(rt, skb, bos); + hash = mpls_multipath_hash(rt, skb); nh_index = hash % alive; if (alive == rt->rt_nhn) goto out; @@ -278,17 +280,11 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, hdr = mpls_hdr(skb); dec = mpls_entry_decode(hdr); - /* Pop the label */ - skb_pull(skb, sizeof(*hdr)); - skb_reset_network_header(skb); - - skb_orphan(skb); - rt = mpls_route_input_rcu(net, dec.label); if (!rt) goto drop; - nh = mpls_select_multipath(rt, skb, dec.bos); + nh = mpls_select_multipath(rt, skb); if (!nh) goto drop; @@ -297,6 +293,12 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, if (!mpls_output_possible(out_dev)) goto drop; + /* Pop the label */ + skb_pull(skb, sizeof(*hdr)); + skb_reset_network_header(skb); + + skb_orphan(skb); + if (skb_warn_if_lro(skb)) goto drop; diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 2f7ccd934416..1d281c1ff7c1 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -215,6 +215,7 @@ static const struct lwtunnel_encap_ops mpls_iptun_ops = { .fill_encap = mpls_fill_encap_info, .get_encap_size = mpls_encap_nlsize, .cmp_encap = mpls_encap_cmp, + .owner = THIS_MODULE, }; static int __init mpls_iptunnel_init(void) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 63729b489c2c..bbc45f8a7b2d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -494,7 +494,7 @@ config NFT_CT depends on NF_CONNTRACK tristate "Netfilter nf_tables conntrack module" help - This option adds the "meta" expression that you can use to match + This option adds the "ct" expression that you can use to match connection tracking information such as the flow state. config NFT_SET_RBTREE diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3a073cd9fcf4..4e8083c5e01d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -85,11 +85,11 @@ static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; /* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */ -#define GC_MAX_BUCKETS_DIV 64u -/* upper bound of scan intervals */ -#define GC_INTERVAL_MAX (2 * HZ) -/* maximum conntracks to evict per gc run */ -#define GC_MAX_EVICTS 256u +#define GC_MAX_BUCKETS_DIV 128u +/* upper bound of full table scan */ +#define GC_MAX_SCAN_JIFFIES (16u * HZ) +/* desired ratio of entries found to be expired */ +#define GC_EVICT_RATIO 50u static struct conntrack_gc_work conntrack_gc_work; @@ -938,6 +938,7 @@ static noinline int early_drop(struct net *net, unsigned int _hash) static void gc_worker(struct work_struct *work) { + unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u); unsigned int i, goal, buckets = 0, expired_count = 0; struct conntrack_gc_work *gc_work; unsigned int ratio, scanned = 0; @@ -979,8 +980,7 @@ static void gc_worker(struct work_struct *work) */ rcu_read_unlock(); cond_resched_rcu_qs(); - } while (++buckets < goal && - expired_count < GC_MAX_EVICTS); + } while (++buckets < goal); if (gc_work->exiting) return; @@ -997,27 +997,25 @@ static void gc_worker(struct work_struct *work) * 1. Minimize time until we notice a stale entry * 2. Maximize scan intervals to not waste cycles * - * Normally, expired_count will be 0, this increases the next_run time - * to priorize 2) above. + * Normally, expire ratio will be close to 0. * - * As soon as a timed-out entry is found, move towards 1) and increase - * the scan frequency. - * In case we have lots of evictions next scan is done immediately. + * As soon as a sizeable fraction of the entries have expired + * increase scan frequency. */ ratio = scanned ? expired_count * 100 / scanned : 0; - if (ratio >= 90 || expired_count == GC_MAX_EVICTS) { - gc_work->next_gc_run = 0; - next_run = 0; - } else if (expired_count) { - gc_work->next_gc_run /= 2U; - next_run = msecs_to_jiffies(1); + if (ratio > GC_EVICT_RATIO) { + gc_work->next_gc_run = min_interval; } else { - if (gc_work->next_gc_run < GC_INTERVAL_MAX) - gc_work->next_gc_run += msecs_to_jiffies(1); + unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV; - next_run = gc_work->next_gc_run; + BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0); + + gc_work->next_gc_run += min_interval; + if (gc_work->next_gc_run > max) + gc_work->next_gc_run = max; } + next_run = gc_work->next_gc_run; gc_work->last_bucket = i; queue_delayed_work(system_long_wq, &gc_work->dwork, next_run); } @@ -1025,7 +1023,7 @@ static void gc_worker(struct work_struct *work) static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work) { INIT_DELAYED_WORK(&gc_work->dwork, gc_worker); - gc_work->next_gc_run = GC_INTERVAL_MAX; + gc_work->next_gc_run = HZ; gc_work->exiting = false; } @@ -1917,7 +1915,7 @@ int nf_conntrack_init_start(void) nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED); conntrack_gc_work_init(&conntrack_gc_work); - queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, GC_INTERVAL_MAX); + queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, HZ); return 0; diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 3dca90dc24ad..ffb9e8ada899 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -13,7 +13,6 @@ /* Internal logging interface, which relies on the real LOG target modules */ -#define NF_LOG_PREFIXLEN 128 #define NFLOGGER_NAME_LEN 64 static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0db5f9782265..1b913760f205 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -928,7 +928,8 @@ static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table, } static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = { - [NFTA_CHAIN_TABLE] = { .type = NLA_STRING }, + [NFTA_CHAIN_TABLE] = { .type = NLA_STRING, + .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_CHAIN_HANDLE] = { .type = NLA_U64 }, [NFTA_CHAIN_NAME] = { .type = NLA_STRING, .len = NFT_CHAIN_MAXNAMELEN - 1 }, @@ -1854,7 +1855,8 @@ static struct nft_rule *nf_tables_rule_lookup(const struct nft_chain *chain, } static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { - [NFTA_RULE_TABLE] = { .type = NLA_STRING }, + [NFTA_RULE_TABLE] = { .type = NLA_STRING, + .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_RULE_CHAIN] = { .type = NLA_STRING, .len = NFT_CHAIN_MAXNAMELEN - 1 }, [NFTA_RULE_HANDLE] = { .type = NLA_U64 }, @@ -2443,7 +2445,8 @@ nft_select_set_ops(const struct nlattr * const nla[], } static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { - [NFTA_SET_TABLE] = { .type = NLA_STRING }, + [NFTA_SET_TABLE] = { .type = NLA_STRING, + .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_SET_NAME] = { .type = NLA_STRING, .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_SET_FLAGS] = { .type = NLA_U32 }, @@ -3084,9 +3087,9 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, } static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, const struct nft_set_iter *iter, - const struct nft_set_elem *elem) + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); enum nft_registers dreg; @@ -3192,8 +3195,10 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = { }; static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = { - [NFTA_SET_ELEM_LIST_TABLE] = { .type = NLA_STRING }, - [NFTA_SET_ELEM_LIST_SET] = { .type = NLA_STRING }, + [NFTA_SET_ELEM_LIST_TABLE] = { .type = NLA_STRING, + .len = NFT_TABLE_MAXNAMELEN - 1 }, + [NFTA_SET_ELEM_LIST_SET] = { .type = NLA_STRING, + .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_SET_ELEM_LIST_ELEMENTS] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 }, }; @@ -3303,9 +3308,9 @@ struct nft_set_dump_args { }; static int nf_tables_dump_setelem(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, const struct nft_set_iter *iter, - const struct nft_set_elem *elem) + struct nft_set_elem *elem) { struct nft_set_dump_args *args; @@ -3317,7 +3322,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); u8 genmask = nft_genmask_cur(net); - const struct nft_set *set; + struct nft_set *set; struct nft_set_dump_args args; struct nft_ctx ctx; struct nlattr *nla[NFTA_SET_ELEM_LIST_MAX + 1]; @@ -3740,10 +3745,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err5; } + if (set->size && + !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) { + err = -ENFILE; + goto err6; + } + nft_trans_elem(trans) = elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; +err6: + set->ops->remove(set, &elem); err5: kfree(trans); err4: @@ -3790,15 +3803,9 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, return -EBUSY; nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { - if (set->size && - !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) - return -ENFILE; - err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags); - if (err < 0) { - atomic_dec(&set->nelems); + if (err < 0) break; - } } return err; } @@ -3883,9 +3890,9 @@ err1: } static int nft_flush_set(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, const struct nft_set_iter *iter, - const struct nft_set_elem *elem) + struct nft_set_elem *elem) { struct nft_trans *trans; int err; @@ -3899,9 +3906,10 @@ static int nft_flush_set(const struct nft_ctx *ctx, err = -ENOENT; goto err1; } + set->ndeact++; - nft_trans_elem_set(trans) = (struct nft_set *)set; - nft_trans_elem(trans) = *((struct nft_set_elem *)elem); + nft_trans_elem_set(trans) = set; + nft_trans_elem(trans) = *elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; @@ -4032,8 +4040,10 @@ struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, EXPORT_SYMBOL_GPL(nf_tables_obj_lookup); static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = { - [NFTA_OBJ_TABLE] = { .type = NLA_STRING }, - [NFTA_OBJ_NAME] = { .type = NLA_STRING }, + [NFTA_OBJ_TABLE] = { .type = NLA_STRING, + .len = NFT_TABLE_MAXNAMELEN - 1 }, + [NFTA_OBJ_NAME] = { .type = NLA_STRING, + .len = NFT_OBJ_MAXNAMELEN - 1 }, [NFTA_OBJ_TYPE] = { .type = NLA_U32 }, [NFTA_OBJ_DATA] = { .type = NLA_NESTED }, }; @@ -4262,10 +4272,11 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); - if (filter->table[0] && + if (filter && filter->table[0] && strcmp(filter->table, table->name)) goto cont; - if (filter->type != NFT_OBJECT_UNSPEC && + if (filter && + filter->type != NFT_OBJECT_UNSPEC && obj->type->type != filter->type) goto cont; @@ -5009,9 +5020,9 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, const struct nft_chain *chain); static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, const struct nft_set_iter *iter, - const struct nft_set_elem *elem) + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); const struct nft_data *data; @@ -5035,7 +5046,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, { const struct nft_rule *rule; const struct nft_expr *expr, *last; - const struct nft_set *set; + struct nft_set *set; struct nft_set_binding *binding; struct nft_set_iter iter; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 7de2f46734a4..049ad2d9ee66 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -98,7 +98,8 @@ out: } static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = { - [NFTA_DYNSET_SET_NAME] = { .type = NLA_STRING }, + [NFTA_DYNSET_SET_NAME] = { .type = NLA_STRING, + .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_DYNSET_SET_ID] = { .type = NLA_U32 }, [NFTA_DYNSET_OP] = { .type = NLA_U32 }, [NFTA_DYNSET_SREG_KEY] = { .type = NLA_U32 }, diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 6271e40a3dd6..6f6e64423643 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -39,7 +39,8 @@ static void nft_log_eval(const struct nft_expr *expr, static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = { [NFTA_LOG_GROUP] = { .type = NLA_U16 }, - [NFTA_LOG_PREFIX] = { .type = NLA_STRING }, + [NFTA_LOG_PREFIX] = { .type = NLA_STRING, + .len = NF_LOG_PREFIXLEN - 1 }, [NFTA_LOG_SNAPLEN] = { .type = NLA_U32 }, [NFTA_LOG_QTHRESHOLD] = { .type = NLA_U16 }, [NFTA_LOG_LEVEL] = { .type = NLA_U32 }, diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index d4f97fa7e21d..e21aea7e5ec8 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -49,7 +49,8 @@ static void nft_lookup_eval(const struct nft_expr *expr, } static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = { - [NFTA_LOOKUP_SET] = { .type = NLA_STRING }, + [NFTA_LOOKUP_SET] = { .type = NLA_STRING, + .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_LOOKUP_SET_ID] = { .type = NLA_U32 }, [NFTA_LOOKUP_SREG] = { .type = NLA_U32 }, [NFTA_LOOKUP_DREG] = { .type = NLA_U32 }, diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 415a65ba2b85..1ae8c49ca4a1 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -193,10 +193,12 @@ nft_objref_select_ops(const struct nft_ctx *ctx, } static const struct nla_policy nft_objref_policy[NFTA_OBJREF_MAX + 1] = { - [NFTA_OBJREF_IMM_NAME] = { .type = NLA_STRING }, + [NFTA_OBJREF_IMM_NAME] = { .type = NLA_STRING, + .len = NFT_OBJ_MAXNAMELEN - 1 }, [NFTA_OBJREF_IMM_TYPE] = { .type = NLA_U32 }, [NFTA_OBJREF_SET_SREG] = { .type = NLA_U32 }, - [NFTA_OBJREF_SET_NAME] = { .type = NLA_STRING }, + [NFTA_OBJREF_SET_NAME] = { .type = NLA_STRING, + .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_OBJREF_SET_ID] = { .type = NLA_U32 }, }; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 1e20e2bbb6d9..e36069fb76ae 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -212,7 +212,7 @@ static void nft_hash_remove(const struct nft_set *set, rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); } -static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, +static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_hash *priv = nft_set_priv(set); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 08376e50f6cd..f06f55ee516d 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -221,7 +221,7 @@ static void *nft_rbtree_deactivate(const struct net *net, } static void nft_rbtree_walk(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, struct nft_set_iter *iter) { const struct nft_rbtree *priv = nft_set_priv(set); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b9e1a13b4ba3..3d555c79a7b5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1976,7 +1976,7 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, return -EINVAL; *len -= sizeof(vnet_hdr); - if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le())) + if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true)) return -EINVAL; return memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr)); @@ -2237,7 +2237,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (po->has_vnet_hdr) { if (virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), - vio_le())) { + vio_le(), true)) { spin_lock(&sk->sk_receive_queue.lock); goto drop_n_account; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 5ed8e79bf102..64dfd35ccdcc 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -222,7 +222,8 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); rcu_read_lock(); - res = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), np->tclass); + res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt), + np->tclass); rcu_read_unlock(); return res; } diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 7e869d0cca69..4f5a2b580aa5 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -68,7 +68,7 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, goto out; } - segs = skb_segment(skb, features | NETIF_F_HW_CSUM); + segs = skb_segment(skb, features | NETIF_F_HW_CSUM | NETIF_F_SG); if (IS_ERR(segs)) goto out; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 318c6786d653..37eeab7899fc 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -235,8 +235,12 @@ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk, sctp_assoc_t id) { struct sctp_association *addr_asoc = NULL, *id_asoc = NULL; - struct sctp_transport *transport; + struct sctp_af *af = sctp_get_af_specific(addr->ss_family); union sctp_addr *laddr = (union sctp_addr *)addr; + struct sctp_transport *transport; + + if (sctp_verify_addr(sk, laddr, af->sockaddr_len)) + return NULL; addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep, laddr, diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 1efbe48e794f..1dc9f3bac099 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -336,6 +336,11 @@ out: static DEFINE_IDA(rpc_clids); +void rpc_cleanup_clids(void) +{ + ida_destroy(&rpc_clids); +} + static int rpc_alloc_clid(struct rpc_clnt *clnt) { int clid; diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index d1c330a7953a..c73de181467a 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -119,6 +119,7 @@ out: static void __exit cleanup_sunrpc(void) { + rpc_cleanup_clids(); rpcauth_remove_module(); cleanup_socket_xprt(); svc_cleanup_xprt_sock(); diff --git a/net/tipc/node.c b/net/tipc/node.c index 9d2f4c2b08ab..27753325e06e 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -263,6 +263,11 @@ static void tipc_node_write_lock(struct tipc_node *n) write_lock_bh(&n->lock); } +static void tipc_node_write_unlock_fast(struct tipc_node *n) +{ + write_unlock_bh(&n->lock); +} + static void tipc_node_write_unlock(struct tipc_node *n) { struct net *net = n->net; @@ -417,7 +422,7 @@ void tipc_node_subscribe(struct net *net, struct list_head *subscr, u32 addr) } tipc_node_write_lock(n); list_add_tail(subscr, &n->publ_list); - tipc_node_write_unlock(n); + tipc_node_write_unlock_fast(n); tipc_node_put(n); } @@ -435,7 +440,7 @@ void tipc_node_unsubscribe(struct net *net, struct list_head *subscr, u32 addr) } tipc_node_write_lock(n); list_del_init(subscr); - tipc_node_write_unlock(n); + tipc_node_write_unlock_fast(n); tipc_node_put(n); } diff --git a/net/tipc/server.c b/net/tipc/server.c index 215849ce453d..3cd6402e812c 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -86,12 +86,12 @@ struct outqueue_entry { static void tipc_recv_work(struct work_struct *work); static void tipc_send_work(struct work_struct *work); static void tipc_clean_outqueues(struct tipc_conn *con); -static void tipc_sock_release(struct tipc_conn *con); static void tipc_conn_kref_release(struct kref *kref) { struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); - struct sockaddr_tipc *saddr = con->server->saddr; + struct tipc_server *s = con->server; + struct sockaddr_tipc *saddr = s->saddr; struct socket *sock = con->sock; struct sock *sk; @@ -103,9 +103,13 @@ static void tipc_conn_kref_release(struct kref *kref) } saddr->scope = -TIPC_NODE_SCOPE; kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr)); - tipc_sock_release(con); sock_release(sock); con->sock = NULL; + + spin_lock_bh(&s->idr_lock); + idr_remove(&s->conn_idr, con->conid); + s->idr_in_use--; + spin_unlock_bh(&s->idr_lock); } tipc_clean_outqueues(con); @@ -128,8 +132,10 @@ static struct tipc_conn *tipc_conn_lookup(struct tipc_server *s, int conid) spin_lock_bh(&s->idr_lock); con = idr_find(&s->conn_idr, conid); - if (con) + if (con && test_bit(CF_CONNECTED, &con->flags)) conn_get(con); + else + con = NULL; spin_unlock_bh(&s->idr_lock); return con; } @@ -186,26 +192,15 @@ static void tipc_unregister_callbacks(struct tipc_conn *con) write_unlock_bh(&sk->sk_callback_lock); } -static void tipc_sock_release(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - - if (con->conid) - s->tipc_conn_release(con->conid, con->usr_data); - - tipc_unregister_callbacks(con); -} - static void tipc_close_conn(struct tipc_conn *con) { struct tipc_server *s = con->server; if (test_and_clear_bit(CF_CONNECTED, &con->flags)) { + tipc_unregister_callbacks(con); - spin_lock_bh(&s->idr_lock); - idr_remove(&s->conn_idr, con->conid); - s->idr_in_use--; - spin_unlock_bh(&s->idr_lock); + if (con->conid) + s->tipc_conn_release(con->conid, con->usr_data); /* We shouldn't flush pending works as we may be in the * thread. In fact the races with pending rx/tx work structs @@ -458,6 +453,11 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid, if (!con) return -EINVAL; + if (!test_bit(CF_CONNECTED, &con->flags)) { + conn_put(con); + return 0; + } + e = tipc_alloc_entry(data, len); if (!e) { conn_put(con); @@ -471,12 +471,8 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid, list_add_tail(&e->list, &con->outqueue); spin_unlock_bh(&con->outqueue_lock); - if (test_bit(CF_CONNECTED, &con->flags)) { - if (!queue_work(s->send_wq, &con->swork)) - conn_put(con); - } else { + if (!queue_work(s->send_wq, &con->swork)) conn_put(con); - } return 0; } @@ -500,7 +496,7 @@ static void tipc_send_to_sock(struct tipc_conn *con) int ret; spin_lock_bh(&con->outqueue_lock); - while (1) { + while (test_bit(CF_CONNECTED, &con->flags)) { e = list_entry(con->outqueue.next, struct outqueue_entry, list); if ((struct list_head *) e == &con->outqueue) @@ -623,14 +619,12 @@ int tipc_server_start(struct tipc_server *s) void tipc_server_stop(struct tipc_server *s) { struct tipc_conn *con; - int total = 0; int id; spin_lock_bh(&s->idr_lock); - for (id = 0; total < s->idr_in_use; id++) { + for (id = 0; s->idr_in_use; id++) { con = idr_find(&s->conn_idr, id); if (con) { - total++; spin_unlock_bh(&s->idr_lock); tipc_close_conn(con); spin_lock_bh(&s->idr_lock); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 0dd02244e21d..9d94e65d0894 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -54,6 +54,8 @@ struct tipc_subscriber { static void tipc_subscrp_delete(struct tipc_subscription *sub); static void tipc_subscrb_put(struct tipc_subscriber *subscriber); +static void tipc_subscrp_put(struct tipc_subscription *subscription); +static void tipc_subscrp_get(struct tipc_subscription *subscription); /** * htohl - convert value to endianness used by destination @@ -123,6 +125,7 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower, { struct tipc_name_seq seq; + tipc_subscrp_get(sub); tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq); if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper)) return; @@ -132,30 +135,23 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower, tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref, node); + tipc_subscrp_put(sub); } static void tipc_subscrp_timeout(unsigned long data) { struct tipc_subscription *sub = (struct tipc_subscription *)data; - struct tipc_subscriber *subscriber = sub->subscriber; /* Notify subscriber of timeout */ tipc_subscrp_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper, TIPC_SUBSCR_TIMEOUT, 0, 0); - spin_lock_bh(&subscriber->lock); - tipc_subscrp_delete(sub); - spin_unlock_bh(&subscriber->lock); - - tipc_subscrb_put(subscriber); + tipc_subscrp_put(sub); } static void tipc_subscrb_kref_release(struct kref *kref) { - struct tipc_subscriber *subcriber = container_of(kref, - struct tipc_subscriber, kref); - - kfree(subcriber); + kfree(container_of(kref,struct tipc_subscriber, kref)); } static void tipc_subscrb_put(struct tipc_subscriber *subscriber) @@ -168,6 +164,59 @@ static void tipc_subscrb_get(struct tipc_subscriber *subscriber) kref_get(&subscriber->kref); } +static void tipc_subscrp_kref_release(struct kref *kref) +{ + struct tipc_subscription *sub = container_of(kref, + struct tipc_subscription, + kref); + struct tipc_net *tn = net_generic(sub->net, tipc_net_id); + struct tipc_subscriber *subscriber = sub->subscriber; + + spin_lock_bh(&subscriber->lock); + tipc_nametbl_unsubscribe(sub); + list_del(&sub->subscrp_list); + atomic_dec(&tn->subscription_count); + spin_unlock_bh(&subscriber->lock); + kfree(sub); + tipc_subscrb_put(subscriber); +} + +static void tipc_subscrp_put(struct tipc_subscription *subscription) +{ + kref_put(&subscription->kref, tipc_subscrp_kref_release); +} + +static void tipc_subscrp_get(struct tipc_subscription *subscription) +{ + kref_get(&subscription->kref); +} + +/* tipc_subscrb_subscrp_delete - delete a specific subscription or all + * subscriptions for a given subscriber. + */ +static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber, + struct tipc_subscr *s) +{ + struct list_head *subscription_list = &subscriber->subscrp_list; + struct tipc_subscription *sub, *temp; + + spin_lock_bh(&subscriber->lock); + list_for_each_entry_safe(sub, temp, subscription_list, subscrp_list) { + if (s && memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) + continue; + + tipc_subscrp_get(sub); + spin_unlock_bh(&subscriber->lock); + tipc_subscrp_delete(sub); + tipc_subscrp_put(sub); + spin_lock_bh(&subscriber->lock); + + if (s) + break; + } + spin_unlock_bh(&subscriber->lock); +} + static struct tipc_subscriber *tipc_subscrb_create(int conid) { struct tipc_subscriber *subscriber; @@ -177,8 +226,8 @@ static struct tipc_subscriber *tipc_subscrb_create(int conid) pr_warn("Subscriber rejected, no memory\n"); return NULL; } - kref_init(&subscriber->kref); INIT_LIST_HEAD(&subscriber->subscrp_list); + kref_init(&subscriber->kref); subscriber->conid = conid; spin_lock_init(&subscriber->lock); @@ -187,55 +236,22 @@ static struct tipc_subscriber *tipc_subscrb_create(int conid) static void tipc_subscrb_delete(struct tipc_subscriber *subscriber) { - struct tipc_subscription *sub, *temp; - u32 timeout; - - spin_lock_bh(&subscriber->lock); - /* Destroy any existing subscriptions for subscriber */ - list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list, - subscrp_list) { - timeout = htohl(sub->evt.s.timeout, sub->swap); - if ((timeout == TIPC_WAIT_FOREVER) || del_timer(&sub->timer)) { - tipc_subscrp_delete(sub); - tipc_subscrb_put(subscriber); - } - } - spin_unlock_bh(&subscriber->lock); - + tipc_subscrb_subscrp_delete(subscriber, NULL); tipc_subscrb_put(subscriber); } static void tipc_subscrp_delete(struct tipc_subscription *sub) { - struct tipc_net *tn = net_generic(sub->net, tipc_net_id); + u32 timeout = htohl(sub->evt.s.timeout, sub->swap); - tipc_nametbl_unsubscribe(sub); - list_del(&sub->subscrp_list); - kfree(sub); - atomic_dec(&tn->subscription_count); + if (timeout == TIPC_WAIT_FOREVER || del_timer(&sub->timer)) + tipc_subscrp_put(sub); } static void tipc_subscrp_cancel(struct tipc_subscr *s, struct tipc_subscriber *subscriber) { - struct tipc_subscription *sub, *temp; - u32 timeout; - - spin_lock_bh(&subscriber->lock); - /* Find first matching subscription, exit if not found */ - list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list, - subscrp_list) { - if (!memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) { - timeout = htohl(sub->evt.s.timeout, sub->swap); - if ((timeout == TIPC_WAIT_FOREVER) || - del_timer(&sub->timer)) { - tipc_subscrp_delete(sub); - tipc_subscrb_put(subscriber); - } - break; - } - } - spin_unlock_bh(&subscriber->lock); + tipc_subscrb_subscrp_delete(subscriber, s); } static struct tipc_subscription *tipc_subscrp_create(struct net *net, @@ -272,6 +288,7 @@ static struct tipc_subscription *tipc_subscrp_create(struct net *net, sub->swap = swap; memcpy(&sub->evt.s, s, sizeof(*s)); atomic_inc(&tn->subscription_count); + kref_init(&sub->kref); return sub; } @@ -288,17 +305,16 @@ static void tipc_subscrp_subscribe(struct net *net, struct tipc_subscr *s, spin_lock_bh(&subscriber->lock); list_add(&sub->subscrp_list, &subscriber->subscrp_list); - tipc_subscrb_get(subscriber); sub->subscriber = subscriber; tipc_nametbl_subscribe(sub); + tipc_subscrb_get(subscriber); spin_unlock_bh(&subscriber->lock); - timeout = htohl(sub->evt.s.timeout, swap); - if (timeout == TIPC_WAIT_FOREVER) - return; - setup_timer(&sub->timer, tipc_subscrp_timeout, (unsigned long)sub); - mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout)); + timeout = htohl(sub->evt.s.timeout, swap); + + if (timeout != TIPC_WAIT_FOREVER) + mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout)); } /* Handle one termination request for the subscriber */ diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index be60103082c9..ffdc214c117a 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -57,6 +57,7 @@ struct tipc_subscriber; * @evt: template for events generated by subscription */ struct tipc_subscription { + struct kref kref; struct tipc_subscriber *subscriber; struct net *net; struct timer_list timer; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 127656ebe7be..cef79873b09d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -995,6 +995,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) unsigned int hash; struct unix_address *addr; struct hlist_head *list; + struct path path = { NULL, NULL }; err = -EINVAL; if (sunaddr->sun_family != AF_UNIX) @@ -1010,9 +1011,20 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; + if (sun_path[0]) { + umode_t mode = S_IFSOCK | + (SOCK_INODE(sock)->i_mode & ~current_umask()); + err = unix_mknod(sun_path, mode, &path); + if (err) { + if (err == -EEXIST) + err = -EADDRINUSE; + goto out; + } + } + err = mutex_lock_interruptible(&u->bindlock); if (err) - goto out; + goto out_put; err = -EINVAL; if (u->addr) @@ -1029,16 +1041,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) atomic_set(&addr->refcnt, 1); if (sun_path[0]) { - struct path path; - umode_t mode = S_IFSOCK | - (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(sun_path, mode, &path); - if (err) { - if (err == -EEXIST) - err = -EADDRINUSE; - unix_release_addr(addr); - goto out_up; - } addr->hash = UNIX_HASH_SIZE; hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); @@ -1065,6 +1067,9 @@ out_unlock: spin_unlock(&unix_table_lock); out_up: mutex_unlock(&u->bindlock); +out_put: + if (err) + path_put(&path); out: return err; } diff --git a/samples/bpf/tc_l2_redirect_kern.c b/samples/bpf/tc_l2_redirect_kern.c index 92a44729dbe4..7ef2a12b25b2 100644 --- a/samples/bpf/tc_l2_redirect_kern.c +++ b/samples/bpf/tc_l2_redirect_kern.c @@ -4,6 +4,7 @@ * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */ +#define KBUILD_MODNAME "foo" #include #include #include diff --git a/samples/bpf/xdp_tx_iptunnel_kern.c b/samples/bpf/xdp_tx_iptunnel_kern.c index 85c38ecd3a2d..0f4f6e8c8611 100644 --- a/samples/bpf/xdp_tx_iptunnel_kern.c +++ b/samples/bpf/xdp_tx_iptunnel_kern.c @@ -8,6 +8,7 @@ * encapsulating the incoming packet in an IPv4/v6 header * and then XDP_TX it out. */ +#define KBUILD_MODNAME "foo" #include #include #include diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index b13fed534d76..9f7bd1915c21 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -67,21 +67,23 @@ static int map_equal(int lru_map, int expected) return map_subset(lru_map, expected) && map_subset(expected, lru_map); } -static int sched_next_online(int pid, int next_to_try) +static int sched_next_online(int pid, int *next_to_try) { cpu_set_t cpuset; + int next = *next_to_try; + int ret = -1; - if (next_to_try == nr_cpus) - return -1; - - while (next_to_try < nr_cpus) { + while (next < nr_cpus) { CPU_ZERO(&cpuset); - CPU_SET(next_to_try++, &cpuset); - if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) + CPU_SET(next++, &cpuset); + if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) { + ret = 0; break; + } } - return next_to_try; + *next_to_try = next; + return ret; } /* Size of the LRU amp is 2 @@ -96,11 +98,12 @@ static void test_lru_sanity0(int map_type, int map_flags) { unsigned long long key, value[nr_cpus]; int lru_map_fd, expected_map_fd; + int next_cpu = 0; printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, map_flags); - assert(sched_next_online(0, 0) != -1); + assert(sched_next_online(0, &next_cpu) != -1); if (map_flags & BPF_F_NO_COMMON_LRU) lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus); @@ -183,6 +186,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) int lru_map_fd, expected_map_fd; unsigned int batch_size; unsigned int map_size; + int next_cpu = 0; if (map_flags & BPF_F_NO_COMMON_LRU) /* Ther percpu lru list (i.e each cpu has its own LRU @@ -196,7 +200,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, map_flags); - assert(sched_next_online(0, 0) != -1); + assert(sched_next_online(0, &next_cpu) != -1); batch_size = tgt_free / 2; assert(batch_size * 2 == tgt_free); @@ -262,6 +266,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) int lru_map_fd, expected_map_fd; unsigned int batch_size; unsigned int map_size; + int next_cpu = 0; if (map_flags & BPF_F_NO_COMMON_LRU) /* Ther percpu lru list (i.e each cpu has its own LRU @@ -275,7 +280,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, map_flags); - assert(sched_next_online(0, 0) != -1); + assert(sched_next_online(0, &next_cpu) != -1); batch_size = tgt_free / 2; assert(batch_size * 2 == tgt_free); @@ -370,11 +375,12 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) int lru_map_fd, expected_map_fd; unsigned int batch_size; unsigned int map_size; + int next_cpu = 0; printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, map_flags); - assert(sched_next_online(0, 0) != -1); + assert(sched_next_online(0, &next_cpu) != -1); batch_size = tgt_free / 2; assert(batch_size * 2 == tgt_free); @@ -430,11 +436,12 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free) int lru_map_fd, expected_map_fd; unsigned long long key, value[nr_cpus]; unsigned long long end_key; + int next_cpu = 0; printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, map_flags); - assert(sched_next_online(0, 0) != -1); + assert(sched_next_online(0, &next_cpu) != -1); if (map_flags & BPF_F_NO_COMMON_LRU) lru_map_fd = create_map(map_type, map_flags, @@ -502,9 +509,8 @@ static void do_test_lru_sanity5(unsigned long long last_key, int map_fd) static void test_lru_sanity5(int map_type, int map_flags) { unsigned long long key, value[nr_cpus]; - int next_sched_cpu = 0; + int next_cpu = 0; int map_fd; - int i; if (map_flags & BPF_F_NO_COMMON_LRU) return; @@ -519,27 +525,20 @@ static void test_lru_sanity5(int map_type, int map_flags) key = 0; assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST)); - for (i = 0; i < nr_cpus; i++) { + while (sched_next_online(0, &next_cpu) != -1) { pid_t pid; pid = fork(); if (pid == 0) { - next_sched_cpu = sched_next_online(0, next_sched_cpu); - if (next_sched_cpu != -1) - do_test_lru_sanity5(key, map_fd); + do_test_lru_sanity5(key, map_fd); exit(0); } else if (pid == -1) { - printf("couldn't spawn #%d process\n", i); + printf("couldn't spawn process to test key:%llu\n", + key); exit(1); } else { int status; - /* It is mostly redundant and just allow the parent - * process to update next_shced_cpu for the next child - * process - */ - next_sched_cpu = sched_next_online(pid, next_sched_cpu); - assert(waitpid(pid, &status, 0) == pid); assert(status == 0); key++; @@ -547,6 +546,8 @@ static void test_lru_sanity5(int map_type, int map_flags) } close(map_fd); + /* At least one key should be tested */ + assert(key > 0); printf("Pass\n"); }