diff options
108 files changed, 1217 insertions, 503 deletions
@@ -512,6 +512,7 @@ Praveen BP <praveenbp@ti.com> Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com> <pradeepc@codeaurora.org> Prasad Sodagudi <quic_psodagud@quicinc.com> <psodagud@codeaurora.org> Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com> +Puranjay Mohan <puranjay@kernel.org> <puranjay12@gmail.com> Qais Yousef <qyousef@layalina.io> <qais.yousef@imgtec.com> Qais Yousef <qyousef@layalina.io> <qais.yousef@arm.com> Quentin Monnet <qmo@kernel.org> <quentin.monnet@netronome.com> diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index ed73c612174d..bcc370c876be 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -671,7 +671,7 @@ configuration, worker pools and how workqueues map to the pools: :: events_unbound unbound 9 9 10 10 8 events_freezable percpu 0 2 4 6 events_power_efficient percpu 0 2 4 6 - events_freezable_power_ percpu 0 2 4 6 + events_freezable_pwr_ef percpu 0 2 4 6 rcu_gp percpu 0 2 4 6 rcu_par_gp percpu 0 2 4 6 slub_flushwq percpu 0 2 4 6 @@ -694,7 +694,7 @@ Use tools/workqueue/wq_monitor.py to monitor workqueue operations: :: events_unbound 38306 0 0.1 - 7 - - events_freezable 0 0 0.0 0 0 - - events_power_efficient 29598 0 0.2 0 0 - - - events_freezable_power_ 10 0 0.0 0 0 - - + events_freezable_pwr_ef 10 0 0.0 0 0 - - sock_diag_events 0 0 0.0 0 0 - - total infl CPUtime CPUhog CMW/RPR mayday rescued @@ -704,7 +704,7 @@ Use tools/workqueue/wq_monitor.py to monitor workqueue operations: :: events_unbound 38322 0 0.1 - 7 - - events_freezable 0 0 0.0 0 0 - - events_power_efficient 29603 0 0.2 0 0 - - - events_freezable_power_ 10 0 0.0 0 0 - - + events_freezable_pwr_ef 10 0 0.0 0 0 - - sock_diag_events 0 0 0.0 0 0 - - ... diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml index d476de82e5c3..4d5a957fa232 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml @@ -120,7 +120,9 @@ additionalProperties: slew-rate: true gpio-hog: true gpios: true + input: true input-enable: true + output-enable: true output-high: true output-low: true line-name: true diff --git a/Documentation/translations/zh_CN/core-api/workqueue.rst b/Documentation/translations/zh_CN/core-api/workqueue.rst index 7fac6f75d078..fe0ff5a127f3 100644 --- a/Documentation/translations/zh_CN/core-api/workqueue.rst +++ b/Documentation/translations/zh_CN/core-api/workqueue.rst @@ -7,12 +7,13 @@ å¸å»¶è…¾ Yanteng Si <siyanteng@loongson.cn> 周彬彬 Binbin Zhou <zhoubinbin@loongson.cn> + é™ˆå…´å‹ Xingyou Chen <rockrush@rockwork.org> .. _cn_workqueue.rst: -========================= -并å‘管ç†çš„工作队列 (cmwq) -========================= +======== +工作队列 +======== :日期: September, 2010 :作者: Tejun Heo <tj@kernel.org> @@ -22,7 +23,7 @@ 简介 ==== -在很多情况下,需è¦ä¸€ä¸ªå¼‚æ¥è¿›ç¨‹çš„执行环境,工作队列(wq)API是这ç§æƒ…况下 +在很多情况下,需è¦ä¸€ä¸ªå¼‚æ¥çš„程åºæ‰§è¡ŒçŽ¯å¢ƒï¼Œå·¥ä½œé˜Ÿåˆ—(wq)API是这ç§æƒ…况下 最常用的机制。 当需è¦è¿™æ ·ä¸€ä¸ªå¼‚æ¥æ‰§è¡Œä¸Šä¸‹æ–‡æ—¶ï¼Œä¸€ä¸ªæè¿°å°†è¦æ‰§è¡Œçš„函数的工作项(work, @@ -34,8 +35,8 @@ 队列时,工作者åˆå¼€å§‹æ‰§è¡Œã€‚ -为什么è¦cmwq? -============= +为什么è¦æœ‰å¹¶å‘管ç†å·¥ä½œé˜Ÿåˆ—? +=========================== 在最åˆçš„wq实现ä¸ï¼Œå¤šçº¿ç¨‹ï¼ˆMT)wq在æ¯ä¸ªCPU上有一个工作者线程,而å•çº¿ç¨‹ (ST)wq在全系统有一个工作者线程。一个MT wq需è¦ä¿æŒä¸ŽCPUæ•°é‡ç›¸åŒçš„å·¥ @@ -73,9 +74,11 @@ å‘该函数的工作项,并在工作队列ä¸æŽ’队ç‰å¾…该工作项。(就是挂到workqueue 队列里é¢åŽ»ï¼‰ -特定目的线程,称为工作线程(工作者),一个接一个地执行队列ä¸çš„功能。 -如果没有工作项排队,工作者线程就会闲置。这些工作者线程被管ç†åœ¨æ‰€è°“ -çš„å·¥ä½œè€…æ± ä¸ã€‚ +工作项å¯ä»¥åœ¨çº¿ç¨‹æˆ–BH(软ä¸æ–)上下文ä¸æ‰§è¡Œã€‚ + +å¯¹äºŽç”±çº¿ç¨‹æ‰§è¡Œçš„å·¥ä½œé˜Ÿåˆ—ï¼Œè¢«ç§°ä¸ºï¼ˆå†…æ ¸ï¼‰å·¥ä½œè€…ï¼ˆ[k]worker)的特殊 +线程会ä¾æ¬¡æ‰§è¡Œå…¶ä¸çš„函数。如果没有工作项排队,工作者线程就会闲置。 +这些工作者线程被管ç†åœ¨æ‰€è°“çš„å·¥ä½œè€…æ± ä¸ã€‚ cmwq设计区分了é¢å‘用户的工作队列,å系统和驱动程åºåœ¨ä¸Šé¢æŽ’队工作, 以åŠç®¡ç†å·¥ä½œè€…æ± å’Œå¤„ç†æŽ’队工作项的åŽç«¯æœºåˆ¶ã€‚ @@ -84,6 +87,10 @@ cmwq设计区分了é¢å‘用户的工作队列,å系统和驱动程åºåœ¨ä¸Šé 优先级的工作项,还有一些é¢å¤–çš„å·¥ä½œè€…æ± ï¼Œç”¨äºŽæœåŠ¡æœªç»‘定工作队列的工 作项目——这些åŽå¤‡æ± çš„æ•°é‡æ˜¯åŠ¨æ€çš„。 +BH工作队列使用相åŒçš„结构。然而,由于åŒä¸€æ—¶é—´åªå¯èƒ½æœ‰ä¸€ä¸ªæ‰§è¡Œä¸Šä¸‹æ–‡ï¼Œ +ä¸éœ€è¦æ‹…心并å‘问题。æ¯ä¸ªCPU上的BHå·¥ä½œè€…æ± åªåŒ…å«ä¸€ä¸ªç”¨äºŽè¡¨ç¤ºBH执行 +上下文的虚拟工作者。BH工作队列å¯ä»¥è¢«çœ‹ä½œè½¯ä¸æ–的便æ·æŽ¥å£ã€‚ + 当他们认为åˆé€‚的时候,å系统和驱动程åºå¯ä»¥é€šè¿‡ç‰¹æ®Šçš„ ``workqueue API`` 函数创建和排队工作项。他们å¯ä»¥é€šè¿‡åœ¨å·¥ä½œé˜Ÿåˆ—上 è®¾ç½®æ ‡å¿—æ¥å½±å“工作项执行方å¼çš„æŸäº›æ–¹é¢ï¼Œä»–们把工作项放在那里。这些 @@ -95,9 +102,9 @@ cmwq设计区分了é¢å‘用户的工作队列,å系统和驱动程åºåœ¨ä¸Šé å¦åˆ™ä¸€ä¸ªç»‘定的工作队列的工作项将被排在与å‘起线程è¿è¡Œçš„CPU相关的普 é€šæˆ–é«˜çº§å·¥ä½œå·¥ä½œè€…æ± çš„å·¥ä½œé¡¹åˆ—è¡¨ä¸ã€‚ -å¯¹äºŽä»»ä½•å·¥ä½œè€…æ± çš„å®žæ–½ï¼Œç®¡ç†å¹¶å‘水平(有多少执行上下文处于活动状 -æ€ï¼‰æ˜¯ä¸€ä¸ªé‡è¦é—®é¢˜ã€‚最低水平是为了节çœèµ„æºï¼Œè€Œé¥±å’Œæ°´å¹³æ˜¯æŒ‡ç³»ç»Ÿè¢« -充分使用。 +å¯¹äºŽä»»ä½•çº¿ç¨‹æ± çš„å®žæ–½ï¼Œç®¡ç†å¹¶å‘水平(有多少执行上下文处于活动状 +æ€ï¼‰æ˜¯ä¸€ä¸ªé‡è¦é—®é¢˜ã€‚cmwq试图将并å‘ä¿æŒåœ¨ä¸€ä¸ªå°½å¯èƒ½ä½Žä¸”充足的 +水平。最低水平是为了节çœèµ„æºï¼Œè€Œå……足是为了使系统能被充分使用。 æ¯ä¸ªä¸Žå®žé™…CPU绑定的worker-pool通过钩ä½è°ƒåº¦å™¨æ¥å®žçŽ°å¹¶å‘管ç†ã€‚æ¯å½“ 一个活动的工作者被唤醒或ç¡çœ æ—¶ï¼Œå·¥ä½œè€…æ± å°±ä¼šå¾—åˆ°é€šçŸ¥ï¼Œå¹¶è·Ÿè¸ªå½“å‰å¯ @@ -140,6 +147,17 @@ workqueue将自动创建与属性相匹é…çš„åŽå¤‡å·¥ä½œè€…æ± ã€‚è°ƒèŠ‚å¹¶å‘æ° ``flags`` --------- +``WQ_BH`` + BH工作队列å¯ä»¥è¢«çœ‹ä½œè½¯ä¸æ–的便æ·æŽ¥å£ã€‚它总是æ¯ä¸ªCPU一份, + å…¶ä¸çš„å„个工作项也会按在队列ä¸çš„顺åºï¼Œè¢«æ‰€å±žCPU在软ä¸æ– + 上下文ä¸æ‰§è¡Œã€‚ + + BH工作队列的 ``max_active`` 值必须为0,且åªèƒ½å•ç‹¬æˆ–å’Œ + ``WQ_HIGHPRI`` æ ‡å¿—ç»„åˆä½¿ç”¨ã€‚ + + BH工作项ä¸å¯ä»¥ç¡çœ 。åƒå»¶è¿ŸæŽ’队ã€å†²æ´—ã€å–消ç‰æ‰€æœ‰å…¶ä»–特性 + 都是支æŒçš„。 + ``WQ_UNBOUND`` 排队到éžç»‘定wqçš„å·¥ä½œé¡¹ç”±ç‰¹æ®Šçš„å·¥ä½œè€…æ± æä¾›æœåŠ¡ï¼Œè¿™äº›å·¥ä½œè€…ä¸ ç»‘å®šåœ¨ä»»ä½•ç‰¹å®šçš„CPU上。这使得wq表现得åƒä¸€ä¸ªç®€å•çš„执行环境æ @@ -184,25 +202,21 @@ workqueue将自动创建与属性相匹é…çš„åŽå¤‡å·¥ä½œè€…æ± ã€‚è°ƒèŠ‚å¹¶å‘æ° -------------- ``@max_active`` 决定了æ¯ä¸ªCPUå¯ä»¥åˆ†é…ç»™wq的工作项的最大执行上 -下文数é‡ã€‚例如,如果 ``@max_active为16`` ,æ¯ä¸ªCPU最多å¯ä»¥åŒ -时执行16个wq的工作项。 +下文数é‡ã€‚例如,如果 ``@max_active`` 为16 ,æ¯ä¸ªCPU最多å¯ä»¥åŒ +时执行16个wq的工作项。它总是æ¯CPU属性,å³ä¾¿å¯¹äºŽæœªç»‘定 wq。 -ç›®å‰ï¼Œå¯¹äºŽä¸€ä¸ªç»‘定的wq, ``@max_active`` 的最大é™åˆ¶æ˜¯512,当指 -定为0时使用的默认值是256。对于éžç»‘定的wq,其é™åˆ¶æ˜¯512å’Œ -4 * ``num_possible_cpus()`` ä¸çš„较高值。这些值被选得足够高,所 -以它们ä¸æ˜¯é™åˆ¶æ€§å› ç´ ï¼ŒåŒæ—¶ä¼šåœ¨å¤±æŽ§æƒ…况下æä¾›ä¿æŠ¤ã€‚ +``@max_active`` 的最大é™åˆ¶æ˜¯512,当指定为0时使用的默认值是256。 +这些值被选得足够高,所以它们ä¸æ˜¯é™åˆ¶æ€§å› ç´ ï¼ŒåŒæ—¶ä¼šåœ¨å¤±æŽ§æƒ…况下æä¾› +ä¿æŠ¤ã€‚ 一个wq的活动工作项的数é‡é€šå¸¸ç”±wq的用户æ¥è°ƒèŠ‚,更具体地说,是由用 户在åŒä¸€æ—¶é—´å¯ä»¥æŽ’列多少个工作项æ¥è°ƒèŠ‚。除éžæœ‰ç‰¹å®šçš„需求æ¥æŽ§åˆ¶æ´»åŠ¨ 工作项的数é‡ï¼Œå¦åˆ™å»ºè®®æŒ‡å®š 为"0"。 -一些用户ä¾èµ–于ST wqçš„ä¸¥æ ¼æ‰§è¡Œé¡ºåºã€‚ ``@max_active`` 为1å’Œ ``WQ_UNBOUND`` -的组åˆç”¨æ¥å®žçŽ°è¿™ç§è¡Œä¸ºã€‚è¿™ç§wqä¸Šçš„å·¥ä½œé¡¹ç›®æ€»æ˜¯è¢«æŽ’åˆ°æœªç»‘å®šçš„å·¥ä½œæ± -ä¸ï¼Œå¹¶ä¸”在任何时候都åªæœ‰ä¸€ä¸ªå·¥ä½œé¡¹ç›®å¤„于活动状æ€ï¼Œä»Žè€Œå®žçŽ°ä¸ŽST wq相 -åŒçš„排åºå±žæ€§ã€‚ - -在目å‰çš„实现ä¸ï¼Œä¸Šè¿°é…ç½®åªä¿è¯äº†ç‰¹å®šNUMA节点内的ST行为。相å, -``alloc_ordered_workqueue()`` 应该被用æ¥å®žçŽ°å…¨ç³»ç»Ÿçš„ST行为。 +一些用户ä¾èµ–于任æ„时刻最多åªæœ‰ä¸€ä¸ªå·¥ä½œé¡¹è¢«æ‰§è¡Œï¼Œä¸”å„å·¥ä½œé¡¹è¢«æŒ‰é˜Ÿåˆ—ä¸ +顺åºå¤„ç†å¸¦æ¥çš„ä¸¥æ ¼æ‰§è¡Œé¡ºåºã€‚``@max_active`` 为1å’Œ ``WQ_UNBOUND`` +的组åˆæ›¾è¢«ç”¨æ¥å®žçŽ°è¿™ç§è¡Œä¸ºï¼ŒçŽ°åœ¨ä¸ç”¨äº†ã€‚请使用 +``alloc_ordered_workqueue()`` 。 执行场景示例 @@ -285,7 +299,7 @@ And with cmwq with ``@max_active`` >= 3, :: * 除éžæœ‰ç‰¹æ®Šéœ€è¦ï¼Œå»ºè®®ä½¿ç”¨0作为@max_active。在大多数使用情 况下,并å‘水平通常ä¿æŒåœ¨é»˜è®¤é™åˆ¶ä¹‹ä¸‹ã€‚ -* 一个wq作为å‰è¿›è¿›åº¦ä¿è¯ï¼ˆWQ_MEM_RECLAIM,冲洗(flush)和工 +* 一个wq作为å‰è¿›è¿›åº¦ä¿è¯ï¼Œ``WQ_MEM_RECLAIM`` ,冲洗(flush)和工 作项属性的域。ä¸æ¶‰åŠå†…å˜å›žæ”¶çš„工作项,ä¸éœ€è¦ä½œä¸ºå·¥ä½œé¡¹ç»„的一 部分被刷新,也ä¸éœ€è¦ä»»ä½•ç‰¹æ®Šå±žæ€§ï¼Œå¯ä»¥ä½¿ç”¨ç³»ç»Ÿä¸çš„一个wq。使 用专用wq和系统wq在执行特性上没有区别。 @@ -294,6 +308,337 @@ And with cmwq with ``@max_active`` >= 3, :: ç›Šçš„ï¼Œå› ä¸ºwqæ“作和工作项执行ä¸çš„定ä½æ°´å¹³æ高了。 +亲和性作用域 +============ + +一个éžç»‘å®šå·¥ä½œé˜Ÿåˆ—æ ¹æ®å…¶äº²å’Œæ€§ä½œç”¨åŸŸæ¥å¯¹CPU进行分组以æé«˜ç¼“å˜ +局部性。比如如果一个工作队列使用默认的“cacheâ€äº²å’Œæ€§ä½œç”¨åŸŸï¼Œ +å®ƒå°†æ ¹æ®æœ€åŽä¸€çº§ç¼“å˜çš„边界æ¥åˆ†ç»„处ç†å™¨ã€‚这个工作队列上的工作项 +将被分é…给一个与å‘èµ·CPU共用最åŽçº§ç¼“å˜çš„处ç†å™¨ä¸Šçš„å·¥ä½œè€…ã€‚æ ¹æ® +``affinity_strict`` 的设置,工作者在å¯åŠ¨åŽå¯èƒ½è¢«å…许移出 +所在作用域,也å¯èƒ½ä¸è¢«å…许。 + +工作队列目å‰æ”¯æŒä»¥ä¸‹äº²å’Œæ€§ä½œç”¨åŸŸã€‚ + +``default`` + 使用模å—å‚æ•° ``workqueue.default_affinity_scope`` 指定 + 的作用域,该å‚数总是会被设为以下作用域ä¸çš„一个。 + +``cpu`` + CPUä¸è¢«åˆ†ç»„。一个CPU上å‘起的工作项会被åŒä¸€CPU上的工作者执行。 + 这使éžç»‘定工作队列表现得åƒæ˜¯ä¸å«å¹¶å‘管ç†çš„æ¯CPU工作队列。 + +``smt`` + CPU被按SMT边界分组。这通常æ„味ç€æ¯ä¸ªç‰©ç†CPUæ ¸ä¸Šçš„å„逻辑CPU会 + 被分进åŒä¸€ç»„。 + +``cache`` + CPU被按缓å˜è¾¹ç•Œåˆ†ç»„。采用哪个缓å˜è¾¹ç•Œç”±æž¶æž„代ç 决定。很多情况 + 下会使用L3。这是默认的亲和性作用域。 + +``numa`` + CPU被按NUMA边界分组。 + +``system`` + 所有CPU被放在åŒä¸€ç»„。工作队列ä¸å°è¯•åœ¨ä¸´è¿‘å‘èµ·CPUçš„CPU上è¿è¡Œ + 工作项。 + +默认的亲和性作用域å¯ä»¥è¢«æ¨¡å—å‚æ•° ``workqueue.default_affinity_scope`` +修改,特定工作队列的亲和性作用域å¯ä»¥é€šè¿‡ ``apply_workqueue_attrs()`` +被更改。 + +如果设置了 ``WQ_SYSFS`` ,工作队列会在它的 ``/sys/devices/virtual/workqueue/WQ_NAME/`` +目录ä¸æœ‰ä»¥ä¸‹äº²å’Œæ€§ä½œç”¨åŸŸç›¸å…³çš„接å£æ–‡ä»¶ã€‚ + +``affinity_scope`` + 读æ“作以查看当å‰çš„亲和性作用域。写æ“作用于更改设置。 + + 当å‰ä½œç”¨åŸŸæ˜¯é»˜è®¤å€¼æ—¶ï¼Œå½“å‰ç”Ÿæ•ˆçš„作用域也å¯ä»¥è¢«ä»Žè¿™ä¸ªæ–‡ä»¶ä¸ + 读到(å°æ‹¬å·å†…),例如 ``default (cache)`` 。 + +``affinity_strict`` + 默认值0表明亲和性作用域ä¸æ˜¯ä¸¥æ ¼çš„。当一个工作项开始执行时, + 工作队列尽é‡å°è¯•ä½¿å·¥ä½œè€…处于亲和性作用域内,称为é£è¿”。å¯åŠ¨åŽï¼Œ + 调度器å¯ä»¥è‡ªç”±åœ°å°†å·¥ä½œè€…调度到系统ä¸ä»»æ„它认为åˆé€‚的地方去。 + 这使得在ä¿ç•™ä½¿ç”¨å…¶ä»–CPU(如果必需且有å¯ç”¨ï¼‰èƒ½åŠ›çš„åŒæ—¶ï¼Œ + 还能从作用域局部性上获益。 + + 如果设置为1,作用域内的所有工作者将被ä¿è¯æ€»æ˜¯å¤„于作用域内。 + 这在跨亲和性作用域会导致如功耗ã€è´Ÿè½½éš”离ç‰æ–¹é¢çš„潜在影å“æ—¶ + ä¼šæœ‰ç”¨ã€‚ä¸¥æ ¼çš„NUMA作用域也å¯ç”¨äºŽå’Œæ—§ç‰ˆå†…æ ¸ä¸å·¥ä½œé˜Ÿåˆ—的行为 + ä¿æŒä¸€è‡´ã€‚ + + +亲和性作用域与性能 +================== + +如果éžç»‘定工作队列的行为对ç»å¤§å¤šæ•°ä½¿ç”¨åœºæ™¯æ¥è¯´éƒ½æ˜¯æœ€ä¼˜çš„, +ä¸éœ€è¦æ›´å¤šè°ƒèŠ‚,就完美了。很ä¸å¹¸ï¼Œåœ¨å½“å‰å†…æ ¸ä¸ï¼Œé‡åº¦ä½¿ç”¨ +工作队列时,需è¦åœ¨å±€éƒ¨æ€§å’Œåˆ©ç”¨çŽ‡é—´æ˜¾å¼åœ°ä½œä¸€ä¸ªæ˜Žæ˜¾çš„æƒè¡¡ã€‚ + +更高的局部性带æ¥æ›´é«˜æ•ˆçŽ‡ï¼Œä¹Ÿå°±æ˜¯ç›¸åŒæ•°é‡çš„CPU周期内å¯ä»¥åš +更多工作。然而,如果å‘起者没能将工作项充分地分散在亲和性 +作用域间,更高的局部性也å¯èƒ½å¸¦æ¥æ›´ä½Žçš„整体系统利用率。以下 +dm-crypt 的性能测试清楚地é˜æ˜Žäº†è¿™ä¸€å–èˆã€‚ + +测试è¿è¡Œåœ¨ä¸€ä¸ª12æ ¸24线程ã€4个L3缓å˜çš„处ç†å™¨ï¼ˆAMD Ryzen +9 3900x)上。为ä¿æŒä¸€è‡´æ€§ï¼Œå…³é—CPU超频。 ``/dev/dm-0`` +是NVME SSD(三星 990 PRO)上创建,用 ``cryptsetup`` +以默认é…置打开的一个 dm-crypt 设备。 + + +场景 1: 机器上é布ç€æœ‰å……足的å‘èµ·è€…å’Œå·¥ä½œé‡ +------------------------------------------ + +使用命令::: + + $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k --ioengine=libaio \ + --iodepth=64 --runtime=60 --numjobs=24 --time_based --group_reporting \ + --name=iops-test-job --verify=sha512 + +这里有24个å‘起者,æ¯ä¸ªåŒæ—¶å‘èµ·64个IO。 ``--verify=sha512`` +使得 ``fio`` æ¯æ¬¡ç”Ÿæˆå’Œè¯»å›žå†…容å—å‘起者和 ``kcryptd`` +间的执行局部性影å“。下é¢æ˜¯åŸºäºŽä¸åŒ ``kcryptd`` 的亲和性 +作用域设置,å„ç»è¿‡äº”次测试得到的读å–带宽和CPU利用率数æ®ã€‚ + +.. list-table:: + :widths: 16 20 20 + :header-rows: 1 + + * - 亲和性 + - 带宽 (MiBps) + - CPU利用率(%) + + * - system + - 1159.40 ±1.34 + - 99.31 ±0.02 + + * - cache + - 1166.40 ±0.89 + - 99.34 ±0.01 + + * - cache (strict) + - 1166.00 ±0.71 + - 99.35 ±0.01 + +在系统ä¸åˆ†å¸ƒç€è¶³å¤Ÿå¤šå‘起者的情况下,ä¸è®ºä¸¥æ ¼ä¸Žå¦ï¼Œâ€œcache†+没有表现得更差。三ç§é…ç½®å‡ä½¿æ•´ä¸ªæœºå™¨è¾¾åˆ°é¥±å’Œï¼Œä½†ç”±äºŽæ高了 +局部性,缓å˜ç›¸å…³çš„两ç§æœ‰0.6%的(带宽)æå‡ã€‚ + + +场景 2: æ›´å°‘å‘èµ·è€…ï¼Œè¶³ä»¥è¾¾åˆ°é¥±å’Œçš„å·¥ä½œé‡ +---------------------------------------- + +使用命令::: + + $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k \ + --ioengine=libaio --iodepth=64 --runtime=60 --numjobs=8 \ + --time_based --group_reporting --name=iops-test-job --verify=sha512 + +与上一个场景唯一的区别是 ``--numjobs=8``。 å‘èµ·è€…æ•°é‡ +å‡å°‘为三分之一,但ä»ç„¶æœ‰è¶³ä»¥ä½¿ç³»ç»Ÿè¾¾åˆ°é¥±å’Œçš„工作总é‡ã€‚ + +.. list-table:: + :widths: 16 20 20 + :header-rows: 1 + + * - 亲和性 + - 带宽 (MiBps) + - CPU利用率(%) + + * - system + - 1155.40 ±0.89 + - 97.41 ±0.05 + + * - cache + - 1154.40 ±1.14 + - 96.15 ±0.09 + + * - cache (strict) + - 1112.00 ±4.64 + - 93.26 ±0.35 + +这里有超过使系统达到饱和所需的工作é‡ã€‚“systemâ€å’Œâ€œcache†+都接近但并未使机器完全饱和。“cacheâ€æ¶ˆè€—æ›´å°‘çš„CPU但更高的 +效率使其得到和“systemâ€ç›¸åŒçš„带宽。 + +八个å‘起者盘桓在四个L3缓å˜ä½œç”¨åŸŸé—´ä»ç„¶å…许“cache (strict)†+å‡ ä¹Žä½¿æœºå™¨é¥±å’Œï¼Œä½†ç¼ºå°‘å¯¹å·¥ä½œçš„ä¿æŒï¼ˆä¸ç§»åˆ°ç©ºé—²å¤„ç†å™¨ä¸Šï¼‰ +开始带æ¥3.7%的带宽æŸå¤±ã€‚ + + +场景 3: æ›´å°‘å‘起者,ä¸å……è¶³çš„å·¥ä½œé‡ +---------------------------------- + +使用命令::: + + $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k \ + --ioengine=libaio --iodepth=64 --runtime=60 --numjobs=4 \ + --time_based --group_reporting --name=iops-test-job --verify=sha512 + +å†æ¬¡ï¼Œå”¯ä¸€çš„区别是 ``--numjobs=4``。由于å‘起者å‡å°‘到四个, +现在没有足以使系统饱和的工作é‡ï¼Œå¸¦å®½å˜å¾—ä¾èµ–于完æˆæ—¶å»¶ã€‚ + +.. list-table:: + :widths: 16 20 20 + :header-rows: 1 + + * - 亲和性 + - 带宽 (MiBps) + - CPU利用率(%) + + * - system + - 993.60 ±1.82 + - 75.49 ±0.06 + + * - cache + - 973.40 ±1.52 + - 74.90 ±0.07 + + * - cache (strict) + - 828.20 ±4.49 + - 66.84 ±0.29 + +现在,局部性和利用率间的æƒè¡¡æ›´æ¸…晰了。“cacheâ€å±•ç¤ºå‡ºç›¸æ¯” +“systemâ€2%的带宽æŸå¤±ï¼Œè€Œâ€œcache (strict)â€è·Œåˆ°20%。 + + +结论和建议 +---------- + +在以上试验ä¸ï¼Œè™½ç„¶ä¸€è‡´å¹¶ä¸”也明显,但“cacheâ€äº²å’Œæ€§ä½œç”¨åŸŸ +相比“systemâ€çš„性能优势并ä¸å¤§ã€‚然而,这影å“是ä¾èµ–于作用域 +é—´è·ç¦»çš„,在更å¤æ‚的处ç†å™¨æ‹“扑下å¯èƒ½æœ‰æ›´æ˜Žæ˜¾çš„å½±å“。 + +虽然这些情形下缺少工作ä¿æŒæ˜¯æœ‰å处的,但比“cache (strict)†+好多了,而且最大化工作队列利用率的需求也并ä¸å¸¸è§ã€‚å› æ¤ï¼Œ +“cacheâ€æ˜¯éžç»‘å®šæ± çš„é»˜è®¤äº²å’Œæ€§ä½œç”¨åŸŸã€‚ + +* 由于ä¸å˜åœ¨ä¸€ä¸ªé€‚用于大多数场景的选择,对于å¯èƒ½éœ€è¦æ¶ˆè€— + 大é‡CPU的工作队列,建议通过 ``apply_workqueue_attrs()`` + 进行(专门)é…置,并考虑是å¦å¯ç”¨ ``WQ_SYSFS``。 + +* è®¾ç½®äº†ä¸¥æ ¼â€œcpuâ€äº²å’Œæ€§ä½œç”¨åŸŸçš„éžç»‘定工作队列,它的行为与 + ``WQ_CPU_INTENSIVE`` æ¯CPUå·¥ä½œé˜Ÿåˆ—ä¸€æ ·ã€‚åŽè€…æ²¡æœ‰çœŸæ£ + 优势,而å‰è€…æ供了大幅度的çµæ´»æ€§ã€‚ + +* 亲和性作用域是从Linux v6.5起引入的。为了模拟旧版行为, + å¯ä»¥ä½¿ç”¨ä¸¥æ ¼çš„“numaâ€äº²å’Œæ€§ä½œç”¨åŸŸã€‚ + +* ä¸ä¸¥æ ¼çš„亲和性作用域ä¸ï¼Œç¼ºå°‘工作ä¿æŒå¤§æ¦‚ç¼˜äºŽè°ƒåº¦å™¨ã€‚å†…æ ¸ + 为什么没能维护好大多数场景下的工作ä¿æŒï¼ŒæŠŠäº‹æƒ…作对,还没有 + ç†è®ºä¸Šçš„è§£é‡Šã€‚å› æ¤ï¼Œæœªæ¥è°ƒåº¦å™¨çš„改进å¯èƒ½ä¼šä½¿æˆ‘们ä¸å†éœ€è¦ + 这些调节项。 + + +检查é…ç½® +======== + +使用 tools/workqueue/wq_dump.py(drgn脚本) æ¥æ£€æŸ¥æœª +绑定CPU的亲和性é…ç½®ï¼Œå·¥ä½œè€…æ± ï¼Œä»¥åŠå·¥ä½œé˜Ÿåˆ—å¦‚ä½•æ˜ å°„åˆ°æ± ä¸Š: :: + + $ tools/workqueue/wq_dump.py + Affinity Scopes + =============== + wq_unbound_cpumask=0000000f + + CPU + nr_pods 4 + pod_cpus [0]=00000001 [1]=00000002 [2]=00000004 [3]=00000008 + pod_node [0]=0 [1]=0 [2]=1 [3]=1 + cpu_pod [0]=0 [1]=1 [2]=2 [3]=3 + + SMT + nr_pods 4 + pod_cpus [0]=00000001 [1]=00000002 [2]=00000004 [3]=00000008 + pod_node [0]=0 [1]=0 [2]=1 [3]=1 + cpu_pod [0]=0 [1]=1 [2]=2 [3]=3 + + CACHE (default) + nr_pods 2 + pod_cpus [0]=00000003 [1]=0000000c + pod_node [0]=0 [1]=1 + cpu_pod [0]=0 [1]=0 [2]=1 [3]=1 + + NUMA + nr_pods 2 + pod_cpus [0]=00000003 [1]=0000000c + pod_node [0]=0 [1]=1 + cpu_pod [0]=0 [1]=0 [2]=1 [3]=1 + + SYSTEM + nr_pods 1 + pod_cpus [0]=0000000f + pod_node [0]=-1 + cpu_pod [0]=0 [1]=0 [2]=0 [3]=0 + + Worker Pools + ============ + pool[00] ref= 1 nice= 0 idle/workers= 4/ 4 cpu= 0 + pool[01] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 0 + pool[02] ref= 1 nice= 0 idle/workers= 4/ 4 cpu= 1 + pool[03] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 1 + pool[04] ref= 1 nice= 0 idle/workers= 4/ 4 cpu= 2 + pool[05] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 2 + pool[06] ref= 1 nice= 0 idle/workers= 3/ 3 cpu= 3 + pool[07] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 3 + pool[08] ref=42 nice= 0 idle/workers= 6/ 6 cpus=0000000f + pool[09] ref=28 nice= 0 idle/workers= 3/ 3 cpus=00000003 + pool[10] ref=28 nice= 0 idle/workers= 17/ 17 cpus=0000000c + pool[11] ref= 1 nice=-20 idle/workers= 1/ 1 cpus=0000000f + pool[12] ref= 2 nice=-20 idle/workers= 1/ 1 cpus=00000003 + pool[13] ref= 2 nice=-20 idle/workers= 1/ 1 cpus=0000000c + + Workqueue CPU -> pool + ===================== + [ workqueue \ CPU 0 1 2 3 dfl] + events percpu 0 2 4 6 + events_highpri percpu 1 3 5 7 + events_long percpu 0 2 4 6 + events_unbound unbound 9 9 10 10 8 + events_freezable percpu 0 2 4 6 + events_power_efficient percpu 0 2 4 6 + events_freezable_power_ percpu 0 2 4 6 + rcu_gp percpu 0 2 4 6 + rcu_par_gp percpu 0 2 4 6 + slub_flushwq percpu 0 2 4 6 + netns ordered 8 8 8 8 8 + ... + +å‚è§å‘½ä»¤çš„帮助消æ¯ä»¥èŽ·å–更多信æ¯ã€‚ + + +监视 +==== + +使用 tools/workqueue/wq_monitor.py æ¥ç›‘视工作队列的è¿è¡Œï¼š :: + + $ tools/workqueue/wq_monitor.py events + total infl CPUtime CPUhog CMW/RPR mayday rescued + events 18545 0 6.1 0 5 - - + events_highpri 8 0 0.0 0 0 - - + events_long 3 0 0.0 0 0 - - + events_unbound 38306 0 0.1 - 7 - - + events_freezable 0 0 0.0 0 0 - - + events_power_efficient 29598 0 0.2 0 0 - - + events_freezable_power_ 10 0 0.0 0 0 - - + sock_diag_events 0 0 0.0 0 0 - - + + total infl CPUtime CPUhog CMW/RPR mayday rescued + events 18548 0 6.1 0 5 - - + events_highpri 8 0 0.0 0 0 - - + events_long 3 0 0.0 0 0 - - + events_unbound 38322 0 0.1 - 7 - - + events_freezable 0 0 0.0 0 0 - - + events_power_efficient 29603 0 0.2 0 0 - - + events_freezable_power_ 10 0 0.0 0 0 - - + sock_diag_events 0 0 0.0 0 0 - - + + ... + +å‚è§å‘½ä»¤çš„帮助消æ¯ä»¥èŽ·å–更多信æ¯ã€‚ + + 调试 ==== @@ -330,7 +675,6 @@ And with cmwq with ``@max_active`` >= 3, :: 工作队列ä¿è¯ï¼Œå¦‚果在工作项排队åŽæ»¡è¶³ä»¥ä¸‹æ¡ä»¶ï¼Œåˆ™å·¥ä½œé¡¹ä¸èƒ½é‡å…¥ï¼š - 1. 工作函数没有被改å˜ã€‚ 2. 没有人将该工作项排到å¦ä¸€ä¸ªå·¥ä½œé˜Ÿåˆ—ä¸ã€‚ 3. 该工作项尚未被é‡æ–°å¯åŠ¨ã€‚ diff --git a/MAINTAINERS b/MAINTAINERS index f6dc90559341..ec0284125e8f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -553,7 +553,7 @@ F: Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml F: drivers/input/misc/adxl34x.c ADXL355 THREE-AXIS DIGITAL ACCELEROMETER DRIVER -M: Puranjay Mohan <puranjay12@gmail.com> +M: Puranjay Mohan <puranjay@kernel.org> L: linux-iio@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/iio/accel/adi,adxl355.yaml @@ -3714,7 +3714,7 @@ F: drivers/iio/imu/bmi323/ BPF JIT for ARM M: Russell King <linux@armlinux.org.uk> -M: Puranjay Mohan <puranjay12@gmail.com> +M: Puranjay Mohan <puranjay@kernel.org> L: bpf@vger.kernel.org S: Maintained F: arch/arm/net/ @@ -3764,6 +3764,8 @@ X: arch/riscv/net/bpf_jit_comp64.c BPF JIT for RISC-V (64-bit) M: Björn Töpel <bjorn@kernel.org> +R: Pu Lehui <pulehui@huawei.com> +R: Puranjay Mohan <puranjay@kernel.org> L: bpf@vger.kernel.org S: Maintained F: arch/riscv/net/ @@ -4191,7 +4193,6 @@ S: Supported F: drivers/scsi/bnx2i/ BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER -M: Ariel Elior <aelior@marvell.com> M: Sudarsana Kalluru <skalluru@marvell.com> M: Manish Chopra <manishc@marvell.com> L: netdev@vger.kernel.org @@ -15160,9 +15161,8 @@ F: drivers/scsi/myrb.* F: drivers/scsi/myrs.* MYRICOM MYRI-10G 10GbE DRIVER (MYRI10GE) -M: Chris Lee <christopher.lee@cspi.com> L: netdev@vger.kernel.org -S: Supported +S: Orphan W: https://www.cspi.com/ethernet-products/support/downloads/ F: drivers/net/ethernet/myricom/myri10ge/ @@ -17990,7 +17990,6 @@ S: Supported F: drivers/scsi/qedi/ QLOGIC QL4xxx ETHERNET DRIVER -M: Ariel Elior <aelior@marvell.com> M: Manish Chopra <manishc@marvell.com> L: netdev@vger.kernel.org S: Supported @@ -18000,7 +17999,6 @@ F: include/linux/qed/ QLOGIC QL4xxx RDMA DRIVER M: Michal Kalderon <mkalderon@marvell.com> -M: Ariel Elior <aelior@marvell.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/hw/qedr/ @@ -21918,7 +21916,7 @@ F: include/linux/soc/ti/ti_sci_inta_msi.h F: include/linux/soc/ti/ti_sci_protocol.h TEXAS INSTRUMENTS' TMP117 TEMPERATURE SENSOR DRIVER -M: Puranjay Mohan <puranjay12@gmail.com> +M: Puranjay Mohan <puranjay@kernel.org> L: linux-iio@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml @@ -24459,6 +24457,14 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/har F: Documentation/admin-guide/LSM/Yama.rst F: security/yama/ +YAML NETLINK (YNL) +M: Donald Hunter <donald.hunter@gmail.com> +M: Jakub Kicinski <kuba@kernel.org> +F: Documentation/netlink/ +F: Documentation/userspace-api/netlink/intro-specs.rst +F: Documentation/userspace-api/netlink/specs.rst +F: tools/net/ynl/ + YEALINK PHONE DRIVER M: Henk Vergonet <Henk.Vergonet@gmail.com> L: usbb2k-api-dev@nongnu.org diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 1d672457d02f..72b5cd697f5d 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -871,16 +871,11 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[], } /* dst = src (4 bytes)*/ -static inline void emit_a32_mov_r(const s8 dst, const s8 src, const u8 off, - struct jit_ctx *ctx) { +static inline void emit_a32_mov_r(const s8 dst, const s8 src, struct jit_ctx *ctx) { const s8 *tmp = bpf2a32[TMP_REG_1]; s8 rt; rt = arm_bpf_get_reg32(src, tmp[0], ctx); - if (off && off != 32) { - emit(ARM_LSL_I(rt, rt, 32 - off), ctx); - emit(ARM_ASR_I(rt, rt, 32 - off), ctx); - } arm_bpf_put_reg32(dst, rt, ctx); } @@ -889,15 +884,15 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[], const s8 src[], struct jit_ctx *ctx) { if (!is64) { - emit_a32_mov_r(dst_lo, src_lo, 0, ctx); + emit_a32_mov_r(dst_lo, src_lo, ctx); if (!ctx->prog->aux->verifier_zext) /* Zero out high 4 bytes */ emit_a32_mov_i(dst_hi, 0, ctx); } else if (__LINUX_ARM_ARCH__ < 6 && ctx->cpu_architecture < CPU_ARCH_ARMv5TE) { /* complete 8 byte move */ - emit_a32_mov_r(dst_lo, src_lo, 0, ctx); - emit_a32_mov_r(dst_hi, src_hi, 0, ctx); + emit_a32_mov_r(dst_lo, src_lo, ctx); + emit_a32_mov_r(dst_hi, src_hi, ctx); } else if (is_stacked(src_lo) && is_stacked(dst_lo)) { const u8 *tmp = bpf2a32[TMP_REG_1]; @@ -917,17 +912,52 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[], static inline void emit_a32_movsx_r64(const bool is64, const u8 off, const s8 dst[], const s8 src[], struct jit_ctx *ctx) { const s8 *tmp = bpf2a32[TMP_REG_1]; - const s8 *rt; + s8 rs; + s8 rd; - rt = arm_bpf_get_reg64(dst, tmp, ctx); + if (is_stacked(dst_lo)) + rd = tmp[1]; + else + rd = dst_lo; + rs = arm_bpf_get_reg32(src_lo, rd, ctx); + /* rs may be one of src[1], dst[1], or tmp[1] */ + + /* Sign extend rs if needed. If off == 32, lower 32-bits of src are moved to dst and sign + * extension only happens in the upper 64 bits. + */ + if (off != 32) { + /* Sign extend rs into rd */ + emit(ARM_LSL_I(rd, rs, 32 - off), ctx); + emit(ARM_ASR_I(rd, rd, 32 - off), ctx); + } else { + rd = rs; + } + + /* Write rd to dst_lo + * + * Optimization: + * Assume: + * 1. dst == src and stacked. + * 2. off == 32 + * + * In this case src_lo was loaded into rd(tmp[1]) but rd was not sign extended as off==32. + * So, we don't need to write rd back to dst_lo as they have the same value. + * This saves us one str instruction. + */ + if (dst_lo != src_lo || off != 32) + arm_bpf_put_reg32(dst_lo, rd, ctx); - emit_a32_mov_r(dst_lo, src_lo, off, ctx); if (!is64) { if (!ctx->prog->aux->verifier_zext) /* Zero out high 4 bytes */ emit_a32_mov_i(dst_hi, 0, ctx); } else { - emit(ARM_ASR_I(rt[0], rt[1], 31), ctx); + if (is_stacked(dst_hi)) { + emit(ARM_ASR_I(tmp[0], rd, 31), ctx); + arm_bpf_put_reg32(dst_hi, tmp[0], ctx); + } else { + emit(ARM_ASR_I(dst_hi, rd, 31), ctx); + } } } diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index f48b8dab8b3d..1d26bb5b02f4 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -338,12 +338,12 @@ int kvm_register_vgic_device(unsigned long type) int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { - int cpuid; + int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); - cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); - - reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; + reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); + if (!reg_attr->vcpu) + return -EINVAL; return 0; } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 122021f9bdfc..13eac43c632d 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1844,15 +1844,15 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l, emit_call(enter_prog, ctx); + /* save return value to callee saved register x20 */ + emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ branch = ctx->image + ctx->idx; emit(A64_NOP, ctx); - /* save return value to callee saved register x20 */ - emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); - emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx); if (!p->jited) emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx); diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 1adf2f39ce59..ec9d692838fc 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -722,6 +722,9 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of if (ret) return ret; + /* store prog start time */ + emit_mv(RV_REG_S1, RV_REG_A0, ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ @@ -729,9 +732,6 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of /* nop reserved for conditional jump */ emit(rv_nop(), ctx); - /* store prog start time */ - emit_mv(RV_REG_S1, RV_REG_A0, ctx); - /* arg1: &args_off */ emit_addi(RV_REG_A0, RV_REG_FP, -args_off, ctx); if (!p->jited) diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 99f7e1f2b70a..99ea3f12c5d2 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -125,8 +125,19 @@ struct s390_pxts_ctx { static inline int __paes_keyblob2pkey(struct key_blob *kb, struct pkey_protkey *pk) { - return pkey_keyblob2pkey(kb->key, kb->keylen, - pk->protkey, &pk->len, &pk->type); + int i, ret = -EIO; + + /* try three times in case of busy card */ + for (i = 0; ret && i < 3; i++) { + if (ret == -EBUSY && in_task()) { + if (msleep_interruptible(1000)) + return -EINTR; + } + ret = pkey_keyblob2pkey(kb->key, kb->keylen, + pk->protkey, &pk->len, &pk->type); + } + + return ret; } static inline int __paes_convert_key(struct s390_paes_ctx *ctx) diff --git a/arch/s390/include/asm/dwarf.h b/arch/s390/include/asm/dwarf.h index 4f21ae561e4d..390906b8e386 100644 --- a/arch/s390/include/asm/dwarf.h +++ b/arch/s390/include/asm/dwarf.h @@ -9,6 +9,7 @@ #define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset #define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset #define CFI_RESTORE .cfi_restore +#define CFI_REL_OFFSET .cfi_rel_offset #ifdef CONFIG_AS_CFI_VAL_OFFSET #define CFI_VAL_OFFSET .cfi_val_offset diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S index 57f62596e53b..85247ef5a41b 100644 --- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S @@ -24,8 +24,10 @@ __kernel_\func: CFI_DEF_CFA_OFFSET (STACK_FRAME_OVERHEAD + WRAPPER_FRAME_SIZE) CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD stg %r14,STACK_FRAME_OVERHEAD(%r15) + CFI_REL_OFFSET 14, STACK_FRAME_OVERHEAD brasl %r14,__s390_vdso_\func lg %r14,STACK_FRAME_OVERHEAD(%r15) + CFI_RESTORE 14 aghi %r15,WRAPPER_FRAME_SIZE CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD CFI_RESTORE 15 diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 094b43b121cd..12d22a7fa32f 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2661,7 +2661,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, return 0; start = pmd_val(*pmd) & HPAGE_MASK; - end = start + HPAGE_SIZE - 1; + end = start + HPAGE_SIZE; __storage_key_init_range(start, end); set_bit(PG_arch_1, &page->flags); cond_resched(); diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index c2e8242bd15d..dc3db86e13ff 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -139,7 +139,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste) } if (!test_and_set_bit(PG_arch_1, &page->flags)) - __storage_key_init_range(paddr, paddr + size - 1); + __storage_key_init_range(paddr, paddr + size); } void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index df5fac428408..59cbc94b6e69 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1807,36 +1807,41 @@ populate_extable: if (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEMSX) { /* Conservatively check that src_reg + insn->off is a kernel address: - * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE - * src_reg is used as scratch for src_reg += insn->off and restored - * after emit_ldx if necessary + * src_reg + insn->off > TASK_SIZE_MAX + PAGE_SIZE + * and + * src_reg + insn->off < VSYSCALL_ADDR */ - u64 limit = TASK_SIZE_MAX + PAGE_SIZE; + u64 limit = TASK_SIZE_MAX + PAGE_SIZE - VSYSCALL_ADDR; u8 *end_of_jmp; - /* At end of these emitted checks, insn->off will have been added - * to src_reg, so no need to do relative load with insn->off offset - */ - insn_off = 0; + /* movabsq r10, VSYSCALL_ADDR */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)VSYSCALL_ADDR >> 32, + (u32)(long)VSYSCALL_ADDR); - /* movabsq r11, limit */ - EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG)); - EMIT((u32)limit, 4); - EMIT(limit >> 32, 4); + /* mov src_reg, r11 */ + EMIT_mov(AUX_REG, src_reg); if (insn->off) { - /* add src_reg, insn->off */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off); + /* add r11, insn->off */ + maybe_emit_1mod(&prog, AUX_REG, true); + EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); } - /* cmp src_reg, r11 */ - maybe_emit_mod(&prog, src_reg, AUX_REG, true); - EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG)); + /* sub r11, r10 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x29, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); + + /* movabsq r10, limit */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)limit >> 32, + (u32)(long)limit); + + /* cmp r10, r11 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x39, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); - /* if unsigned '>=', goto load */ - EMIT2(X86_JAE, 0); + /* if unsigned '>', goto load */ + EMIT2(X86_JA, 0); end_of_jmp = prog; /* xor dst_reg, dst_reg */ @@ -1862,18 +1867,6 @@ populate_extable: /* populate jmp_offset for JMP above */ start_of_ldx[-1] = prog - start_of_ldx; - if (insn->off && src_reg != dst_reg) { - /* sub src_reg, insn->off - * Restore src_reg after "add src_reg, insn->off" in prev - * if statement. But if src_reg == dst_reg, emit_ldx - * above already clobbered src_reg, so no need to restore. - * If add src_reg, insn->off was unnecessary, no need to - * restore either. - */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off); - } - if (!bpf_prog->aux->extable) break; @@ -3473,3 +3466,9 @@ bool bpf_jit_supports_ptr_xchg(void) { return true; } + +/* x86-64 JIT emits its own code to filter user addresses so return 0 here */ +u64 bpf_arch_uaddress_limit(void) +{ + return 0; +} diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index 38bcecb0e457..a2b6bb5429f5 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -100,6 +100,10 @@ void flush_cache_range(struct vm_area_struct*, ulong, ulong); void flush_icache_range(unsigned long start, unsigned long end); void flush_cache_page(struct vm_area_struct*, unsigned long, unsigned long); +#define flush_cache_all flush_cache_all +#define flush_cache_range flush_cache_range +#define flush_icache_range flush_icache_range +#define flush_cache_page flush_cache_page #else #define flush_cache_all local_flush_cache_all #define flush_cache_range local_flush_cache_range @@ -136,20 +140,7 @@ void local_flush_cache_page(struct vm_area_struct *vma, #else -#define flush_cache_all() do { } while (0) -#define flush_cache_mm(mm) do { } while (0) -#define flush_cache_dup_mm(mm) do { } while (0) - -#define flush_cache_vmap(start,end) do { } while (0) -#define flush_cache_vmap_early(start,end) do { } while (0) -#define flush_cache_vunmap(start,end) do { } while (0) - -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define flush_dcache_page(page) do { } while (0) - #define flush_icache_range local_flush_icache_range -#define flush_cache_page(vma, addr, pfn) do { } while (0) -#define flush_cache_range(vma, start, end) do { } while (0) #endif @@ -162,15 +153,14 @@ void local_flush_cache_page(struct vm_area_struct *vma, __invalidate_icache_range(start,(end) - (start)); \ } while (0) -#define flush_dcache_mmap_lock(mapping) do { } while (0) -#define flush_dcache_mmap_unlock(mapping) do { } while (0) - #if defined(CONFIG_MMU) && (DCACHE_WAY_SIZE > PAGE_SIZE) extern void copy_to_user_page(struct vm_area_struct*, struct page*, unsigned long, void*, const void*, unsigned long); extern void copy_from_user_page(struct vm_area_struct*, struct page*, unsigned long, void*, const void*, unsigned long); +#define copy_to_user_page copy_to_user_page +#define copy_from_user_page copy_from_user_page #else @@ -186,4 +176,6 @@ extern void copy_from_user_page(struct vm_area_struct*, struct page*, #endif +#include <asm-generic/cacheflush.h> + #endif /* _XTENSA_CACHEFLUSH_H */ diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index d008a153a2b9..7ed1a2085bd7 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -115,9 +115,9 @@ #define MAKE_RA_FOR_CALL(ra,ws) (((ra) & 0x3fffffff) | (ws) << 30) /* Convert return address to a valid pc - * Note: We assume that the stack pointer is in the same 1GB ranges as the ra + * Note: 'text' is the address within the same 1GB range as the ra */ -#define MAKE_PC_FROM_RA(ra,sp) (((ra) & 0x3fffffff) | ((sp) & 0xc0000000)) +#define MAKE_PC_FROM_RA(ra, text) (((ra) & 0x3fffffff) | ((unsigned long)(text) & 0xc0000000)) #elif defined(__XTENSA_CALL0_ABI__) @@ -127,9 +127,9 @@ #define MAKE_RA_FOR_CALL(ra, ws) (ra) /* Convert return address to a valid pc - * Note: We assume that the stack pointer is in the same 1GB ranges as the ra + * Note: 'text' is not used as 'ra' is always the full address */ -#define MAKE_PC_FROM_RA(ra, sp) (ra) +#define MAKE_PC_FROM_RA(ra, text) (ra) #else #error Unsupported Xtensa ABI diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h index a270467556dc..86c70117371b 100644 --- a/arch/xtensa/include/asm/ptrace.h +++ b/arch/xtensa/include/asm/ptrace.h @@ -87,7 +87,7 @@ struct pt_regs { # define user_mode(regs) (((regs)->ps & 0x00000020)!=0) # define instruction_pointer(regs) ((regs)->pc) # define return_pointer(regs) (MAKE_PC_FROM_RA((regs)->areg[0], \ - (regs)->areg[1])) + (regs)->pc)) # ifndef CONFIG_SMP # define profile_pc(regs) instruction_pointer(regs) diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index a815577d25fd..7bd66677f7b6 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -47,6 +47,7 @@ #include <asm/asm-offsets.h> #include <asm/regs.h> #include <asm/hw_breakpoint.h> +#include <asm/sections.h> #include <asm/traps.h> extern void ret_from_fork(void); @@ -380,7 +381,7 @@ unsigned long __get_wchan(struct task_struct *p) int count = 0; sp = p->thread.sp; - pc = MAKE_PC_FROM_RA(p->thread.ra, p->thread.sp); + pc = MAKE_PC_FROM_RA(p->thread.ra, _text); do { if (sp < stack_page + sizeof(struct task_struct) || @@ -392,7 +393,7 @@ unsigned long __get_wchan(struct task_struct *p) /* Stack layout: sp-4: ra, sp-3: sp' */ - pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), sp); + pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), _text); sp = SPILL_SLOT(sp, 1); } while (count++ < 16); return 0; diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c index 831ffb648bda..ed324fdf2a2f 100644 --- a/arch/xtensa/kernel/stacktrace.c +++ b/arch/xtensa/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include <linux/stacktrace.h> #include <asm/ftrace.h> +#include <asm/sections.h> #include <asm/stacktrace.h> #include <asm/traps.h> #include <linux/uaccess.h> @@ -189,7 +190,7 @@ void walk_stackframe(unsigned long *sp, if (a1 <= (unsigned long)sp) break; - frame.pc = MAKE_PC_FROM_RA(a0, a1); + frame.pc = MAKE_PC_FROM_RA(a0, _text); frame.sp = a1; if (fn(&frame, data)) diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 8896e691c051..abec44b687df 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -166,10 +166,8 @@ late_initcall(rs_init); static void iss_console_write(struct console *co, const char *s, unsigned count) { - if (s && *s != 0) { - int len = strlen(s); - simc_write(1, s, count < len ? count : len); - } + if (s && *s != 0) + simc_write(1, s, min(count, strlen(s))); } static struct tty_driver* iss_console_device(struct console *c, int *index) diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c index b0d671db178a..ea31ac7ac1ca 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -148,10 +148,12 @@ packet_buffer_get(struct client *client, char __user *data, size_t user_length) if (atomic_read(&buffer->size) == 0) return -ENODEV; - /* FIXME: Check length <= user_length. */ + length = buffer->head->length; + + if (length > user_length) + return 0; end = buffer->data + buffer->capacity; - length = buffer->head->length; if (&buffer->head->data[length] < end) { if (copy_to_user(data, buffer->head->data, length)) diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 38d19410a2be..b9ae0340b8a7 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -1556,6 +1556,8 @@ static int handle_at_packet(struct context *context, #define HEADER_GET_DATA_LENGTH(q) (((q) >> 16) & 0xffff) #define HEADER_GET_EXTENDED_TCODE(q) (((q) >> 0) & 0xffff) +static u32 get_cycle_time(struct fw_ohci *ohci); + static void handle_local_rom(struct fw_ohci *ohci, struct fw_packet *packet, u32 csr) { @@ -1580,6 +1582,8 @@ static void handle_local_rom(struct fw_ohci *ohci, (void *) ohci->config_rom + i, length); } + // Timestamping on behalf of the hardware. + response.timestamp = cycle_time_to_ohci_tstamp(get_cycle_time(ohci)); fw_core_handle_response(&ohci->card, &response); } @@ -1628,6 +1632,8 @@ static void handle_local_lock(struct fw_ohci *ohci, fw_fill_response(&response, packet->header, RCODE_BUSY, NULL, 0); out: + // Timestamping on behalf of the hardware. + response.timestamp = cycle_time_to_ohci_tstamp(get_cycle_time(ohci)); fw_core_handle_response(&ohci->card, &response); } @@ -1670,8 +1676,6 @@ static void handle_local_request(struct context *ctx, struct fw_packet *packet) } } -static u32 get_cycle_time(struct fw_ohci *ohci); - static void at_context_transmit(struct context *ctx, struct fw_packet *packet) { unsigned long flags; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 59b5dd0e2f41..14daf432f30b 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -5705,7 +5705,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6141, .family = MV88E6XXX_FAMILY_6341, .name = "Marvell 88E6141", - .num_databases = 4096, + .num_databases = 256, .num_macs = 2048, .num_ports = 6, .num_internal_phys = 5, @@ -6164,7 +6164,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6341, .family = MV88E6XXX_FAMILY_6341, .name = "Marvell 88E6341", - .num_databases = 4096, + .num_databases = 256, .num_macs = 2048, .num_internal_phys = 5, .num_ports = 6, diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index b1f84b37032a..c7e7dac057a3 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2,7 +2,7 @@ /* * Broadcom GENET (Gigabit Ethernet) controller driver * - * Copyright (c) 2014-2020 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #define pr_fmt(fmt) "bcmgenet: " fmt @@ -2467,14 +2467,18 @@ static void umac_enable_set(struct bcmgenet_priv *priv, u32 mask, bool enable) { u32 reg; + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); - if (reg & CMD_SW_RESET) + if (reg & CMD_SW_RESET) { + spin_unlock_bh(&priv->reg_lock); return; + } if (enable) reg |= mask; else reg &= ~mask; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); /* UniMAC stops on a packet boundary, wait for a full-size packet * to be processed @@ -2490,8 +2494,10 @@ static void reset_umac(struct bcmgenet_priv *priv) udelay(10); /* issue soft reset and disable MAC while updating its registers */ + spin_lock_bh(&priv->reg_lock); bcmgenet_umac_writel(priv, CMD_SW_RESET, UMAC_CMD); udelay(2); + spin_unlock_bh(&priv->reg_lock); } static void bcmgenet_intr_disable(struct bcmgenet_priv *priv) @@ -3334,7 +3340,9 @@ static void bcmgenet_netif_start(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); /* Start the network engine */ + netif_addr_lock_bh(dev); bcmgenet_set_rx_mode(dev); + netif_addr_unlock_bh(dev); bcmgenet_enable_rx_napi(priv); umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true); @@ -3595,16 +3603,19 @@ static void bcmgenet_set_rx_mode(struct net_device *dev) * 3. The number of filters needed exceeds the number filters * supported by the hardware. */ + spin_lock(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); if ((dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) || (nfilter > MAX_MDF_FILTER)) { reg |= CMD_PROMISC; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock(&priv->reg_lock); bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL); return; } else { reg &= ~CMD_PROMISC; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock(&priv->reg_lock); } /* update MDF filter */ @@ -4003,6 +4014,7 @@ static int bcmgenet_probe(struct platform_device *pdev) goto err; } + spin_lock_init(&priv->reg_lock); spin_lock_init(&priv->lock); /* Set default pause parameters */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 7523b60b3c1c..43b923c48b14 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2014-2020 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #ifndef __BCMGENET_H__ @@ -573,6 +573,8 @@ struct bcmgenet_rxnfc_rule { /* device context */ struct bcmgenet_priv { void __iomem *base; + /* reg_lock: lock to serialize access to shared registers */ + spinlock_t reg_lock; enum bcmgenet_version version; struct net_device *dev; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index 7a41cad5788f..1248792d7fd4 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -2,7 +2,7 @@ /* * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support * - * Copyright (c) 2014-2020 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #define pr_fmt(fmt) "bcmgenet_wol: " fmt @@ -151,6 +151,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, } /* Can't suspend with WoL if MAC is still in reset */ + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); if (reg & CMD_SW_RESET) reg &= ~CMD_SW_RESET; @@ -158,6 +159,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, /* disable RX */ reg &= ~CMD_RX_EN; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); mdelay(10); if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) { @@ -203,6 +205,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, } /* Enable CRC forward */ + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); priv->crc_fwd_en = 1; reg |= CMD_CRC_FWD; @@ -210,6 +213,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, /* Receiver must be enabled for WOL MP detection */ reg |= CMD_RX_EN; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); reg = UMAC_IRQ_MPD_R; if (hfb_enable) @@ -256,7 +260,9 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, } /* Disable CRC Forward */ + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); reg &= ~CMD_CRC_FWD; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); } diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 9ada89355747..c4a3698cef66 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -2,7 +2,7 @@ /* * Broadcom GENET MDIO routines * - * Copyright (c) 2014-2017 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #include <linux/acpi.h> @@ -76,6 +76,7 @@ static void bcmgenet_mac_config(struct net_device *dev) reg |= RGMII_LINK; bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); reg &= ~((CMD_SPEED_MASK << CMD_SPEED_SHIFT) | CMD_HD_EN | @@ -88,6 +89,7 @@ static void bcmgenet_mac_config(struct net_device *dev) reg |= CMD_TX_EN | CMD_RX_EN; } bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); active = phy_init_eee(phydev, 0) >= 0; bcmgenet_eee_enable_set(dev, @@ -275,6 +277,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) * block for the interface to work, unconditionally clear the * Out-of-band disable since we do not need it. */ + mutex_lock(&phydev->lock); reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); reg &= ~OOB_DISABLE; if (priv->ext_phy) { @@ -286,6 +289,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) reg |= RGMII_MODE_EN; } bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + mutex_unlock(&phydev->lock); if (init) dev_info(kdev, "configuring instance for %s\n", phy_name); diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c index 7246e13dd559..97291bfbeea5 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c +++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c @@ -312,7 +312,7 @@ bnad_debugfs_write_regrd(struct file *file, const char __user *buf, void *kern_buf; /* Copy the user space buf */ - kern_buf = memdup_user(buf, nbytes); + kern_buf = memdup_user_nul(buf, nbytes); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); @@ -372,7 +372,7 @@ bnad_debugfs_write_regwr(struct file *file, const char __user *buf, void *kern_buf; /* Copy the user space buf */ - kern_buf = memdup_user(buf, nbytes); + kern_buf = memdup_user_nul(buf, nbytes); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 49d5808b7d11..de52bcb884c4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2670,12 +2670,12 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) lb->loopback = 1; q = &adap->sge.ethtxq[pi->first_qset]; - __netif_tx_lock(q->txq, smp_processor_id()); + __netif_tx_lock_bh(q->txq); reclaim_completed_tx(adap, &q->q, -1, true); credits = txq_avail(&q->q) - ndesc; if (unlikely(credits < 0)) { - __netif_tx_unlock(q->txq); + __netif_tx_unlock_bh(q->txq); return -ENOMEM; } @@ -2710,7 +2710,7 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) init_completion(&lb->completion); txq_advance(&q->q, ndesc); cxgb4_ring_tx_db(adap, &q->q, ndesc); - __netif_tx_unlock(q->txq); + __netif_tx_unlock_bh(q->txq); /* wait for the pkt to return */ ret = wait_for_completion_timeout(&lb->completion, 10 * HZ); diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index 93544f1cc2a5..f7ae0e0aa4a4 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -157,7 +157,7 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) * the lower time out */ for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { - usleep_range(50, 60); + udelay(50); mdic = er32(MDIC); if (mdic & E1000_MDIC_READY) break; @@ -181,7 +181,7 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) * reading duplicate data in the next MDIC transaction. */ if (hw->mac.type == e1000_pch2lan) - usleep_range(100, 150); + udelay(100); if (success) { *data = (u16)mdic; @@ -237,7 +237,7 @@ s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) * the lower time out */ for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { - usleep_range(50, 60); + udelay(50); mdic = er32(MDIC); if (mdic & E1000_MDIC_READY) break; @@ -261,7 +261,7 @@ s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) * reading duplicate data in the next MDIC transaction. */ if (hw->mac.type == e1000_pch2lan) - usleep_range(100, 150); + udelay(100); if (success) return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_debugfs.c b/drivers/net/ethernet/intel/ice/ice_debugfs.c index d252d98218d0..9fc0fd95a13d 100644 --- a/drivers/net/ethernet/intel/ice/ice_debugfs.c +++ b/drivers/net/ethernet/intel/ice/ice_debugfs.c @@ -171,7 +171,7 @@ ice_debugfs_module_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 8) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); @@ -257,7 +257,7 @@ ice_debugfs_nr_messages_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 4) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); @@ -332,7 +332,7 @@ ice_debugfs_enable_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 2) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); @@ -428,7 +428,7 @@ ice_debugfs_log_size_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 5) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 2500f5ba4f5a..881d704644fb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -999,12 +999,10 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, u16 pcifunc; int ret, lf; - cmd_buf = memdup_user(buffer, count + 1); + cmd_buf = memdup_user_nul(buffer, count); if (IS_ERR(cmd_buf)) return -ENOMEM; - cmd_buf[count] = '\0'; - cmd_buf_tmp = strchr(cmd_buf, '\n'); if (cmd_buf_tmp) { *cmd_buf_tmp = '\0'; diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index a5ac21a0ee33..cb6b33a228ea 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1868,8 +1868,8 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, struct flow_cls_offload *f) { struct qede_arfs_fltr_node *n; - int min_hlen, rc = -EINVAL; struct qede_arfs_tuple t; + int min_hlen, rc; __qede_lock(edev); @@ -1879,7 +1879,8 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, } /* parse flower attribute and prepare filter */ - if (qede_parse_flow_attr(edev, proto, f->rule, &t)) + rc = qede_parse_flow_attr(edev, proto, f->rule, &t); + if (rc) goto unlock; /* Validate profile mode and number of filters */ @@ -1888,11 +1889,13 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, DP_NOTICE(edev, "Filter configuration invalidated, filter mode=0x%x, configured mode=0x%x, filter count=0x%x\n", t.mode, edev->arfs->mode, edev->arfs->filter_count); + rc = -EINVAL; goto unlock; } /* parse tc actions and get the vf_id */ - if (qede_parse_actions(edev, &f->rule->action, f->common.extack)) + rc = qede_parse_actions(edev, &f->rule->action, f->common.extack); + if (rc) goto unlock; if (qede_flow_find_fltr(edev, &t)) { @@ -1998,10 +2001,9 @@ static int qede_flow_spec_to_rule(struct qede_dev *edev, if (IS_ERR(flow)) return PTR_ERR(flow); - if (qede_parse_flow_attr(edev, proto, flow->rule, t)) { - err = -EINVAL; + err = qede_parse_flow_attr(edev, proto, flow->rule, t); + if (err) goto err_out; - } /* Make sure location is valid and filter isn't already set */ err = qede_flow_spec_validate(edev, &flow->rule->action, t, diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index ba319fc21957..3a9148fb1422 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1674,6 +1674,7 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) bool raw_proto = false; void *oiph; __be32 vni = 0; + int nh; /* Need UDP and VXLAN header to be present */ if (!pskb_may_pull(skb, VXLAN_HLEN)) @@ -1762,12 +1763,28 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) skb->pkt_type = PACKET_HOST; } - oiph = skb_network_header(skb); + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(vxlan->dev, rx_length_errors); + DEV_STATS_INC(vxlan->dev, rx_errors); + vxlan_vnifilter_count(vxlan, vni, vninode, + VXLAN_VNI_STATS_RX_ERRORS, 0); + goto drop; + } + + /* Get the outer header. */ + oiph = skb->head + nh; + if (!vxlan_ecn_decapsulate(vs, oiph, skb)) { - ++vxlan->dev->stats.rx_frame_errors; - ++vxlan->dev->stats.rx_errors; + DEV_STATS_INC(vxlan->dev, rx_frame_errors); + DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; @@ -1837,7 +1854,9 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) goto out; if (!pskb_may_pull(skb, arp_hdr_len(dev))) { - dev->stats.tx_dropped++; + dev_core_stats_tx_dropped_inc(dev); + vxlan_vnifilter_count(vxlan, vni, NULL, + VXLAN_VNI_STATS_TX_DROPS, 0); goto out; } parp = arp_hdr(skb); @@ -1893,7 +1912,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) reply->pkt_type = PACKET_HOST; if (netif_rx(reply) == NET_RX_DROP) { - dev->stats.rx_dropped++; + dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } @@ -2052,7 +2071,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) goto out; if (netif_rx(reply) == NET_RX_DROP) { - dev->stats.rx_dropped++; + dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } @@ -2263,7 +2282,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, len); } else { drop: - dev->stats.rx_dropped++; + dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } @@ -2295,7 +2314,7 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, addr_family, dst_port, vxlan->cfg.flags); if (!dst_vxlan) { - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb(skb); @@ -2559,7 +2578,7 @@ out_unlock: return; drop: - dev->stats.tx_dropped++; + dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); return; @@ -2567,11 +2586,11 @@ drop: tx_error: rcu_read_unlock(); if (err == -ELOOP) - dev->stats.collisions++; + DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); dst_release(ndst); - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb(skb); } @@ -2604,7 +2623,7 @@ static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, return; drop: - dev->stats.tx_dropped++; + dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); @@ -2642,7 +2661,7 @@ static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev, return NETDEV_TX_OK; drop: - dev->stats.tx_dropped++; + dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); @@ -2739,7 +2758,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) !is_multicast_ether_addr(eth->h_dest)) vxlan_fdb_miss(vxlan, eth->h_dest); - dev->stats.tx_dropped++; + dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb(skb); diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index d376fa7114d1..029efe16f8cc 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -43,7 +43,7 @@ #define SCU614 0x614 /* Disable GPIO Internal Pull-Down #1 */ #define SCU618 0x618 /* Disable GPIO Internal Pull-Down #2 */ #define SCU61C 0x61c /* Disable GPIO Internal Pull-Down #3 */ -#define SCU620 0x620 /* Disable GPIO Internal Pull-Down #4 */ +#define SCU630 0x630 /* Disable GPIO Internal Pull-Down #4 */ #define SCU634 0x634 /* Disable GPIO Internal Pull-Down #5 */ #define SCU638 0x638 /* Disable GPIO Internal Pull-Down #6 */ #define SCU690 0x690 /* Multi-function Pin Control #24 */ @@ -2495,38 +2495,38 @@ static struct aspeed_pin_config aspeed_g6_configs[] = { ASPEED_PULL_DOWN_PINCONF(D14, SCU61C, 0), /* GPIOS7 */ - ASPEED_PULL_DOWN_PINCONF(T24, SCU620, 23), + ASPEED_PULL_DOWN_PINCONF(T24, SCU630, 23), /* GPIOS6 */ - ASPEED_PULL_DOWN_PINCONF(P23, SCU620, 22), + ASPEED_PULL_DOWN_PINCONF(P23, SCU630, 22), /* GPIOS5 */ - ASPEED_PULL_DOWN_PINCONF(P24, SCU620, 21), + ASPEED_PULL_DOWN_PINCONF(P24, SCU630, 21), /* GPIOS4 */ - ASPEED_PULL_DOWN_PINCONF(R26, SCU620, 20), + ASPEED_PULL_DOWN_PINCONF(R26, SCU630, 20), /* GPIOS3*/ - ASPEED_PULL_DOWN_PINCONF(R24, SCU620, 19), + ASPEED_PULL_DOWN_PINCONF(R24, SCU630, 19), /* GPIOS2 */ - ASPEED_PULL_DOWN_PINCONF(T26, SCU620, 18), + ASPEED_PULL_DOWN_PINCONF(T26, SCU630, 18), /* GPIOS1 */ - ASPEED_PULL_DOWN_PINCONF(T25, SCU620, 17), + ASPEED_PULL_DOWN_PINCONF(T25, SCU630, 17), /* GPIOS0 */ - ASPEED_PULL_DOWN_PINCONF(R23, SCU620, 16), + ASPEED_PULL_DOWN_PINCONF(R23, SCU630, 16), /* GPIOR7 */ - ASPEED_PULL_DOWN_PINCONF(U26, SCU620, 15), + ASPEED_PULL_DOWN_PINCONF(U26, SCU630, 15), /* GPIOR6 */ - ASPEED_PULL_DOWN_PINCONF(W26, SCU620, 14), + ASPEED_PULL_DOWN_PINCONF(W26, SCU630, 14), /* GPIOR5 */ - ASPEED_PULL_DOWN_PINCONF(T23, SCU620, 13), + ASPEED_PULL_DOWN_PINCONF(T23, SCU630, 13), /* GPIOR4 */ - ASPEED_PULL_DOWN_PINCONF(U25, SCU620, 12), + ASPEED_PULL_DOWN_PINCONF(U25, SCU630, 12), /* GPIOR3*/ - ASPEED_PULL_DOWN_PINCONF(V26, SCU620, 11), + ASPEED_PULL_DOWN_PINCONF(V26, SCU630, 11), /* GPIOR2 */ - ASPEED_PULL_DOWN_PINCONF(V24, SCU620, 10), + ASPEED_PULL_DOWN_PINCONF(V24, SCU630, 10), /* GPIOR1 */ - ASPEED_PULL_DOWN_PINCONF(U24, SCU620, 9), + ASPEED_PULL_DOWN_PINCONF(U24, SCU630, 9), /* GPIOR0 */ - ASPEED_PULL_DOWN_PINCONF(V25, SCU620, 8), + ASPEED_PULL_DOWN_PINCONF(V25, SCU630, 8), /* GPIOX7 */ ASPEED_PULL_DOWN_PINCONF(AB10, SCU634, 31), diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index 6649357637ff..cffeb869130d 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2124,13 +2124,7 @@ int pinctrl_enable(struct pinctrl_dev *pctldev) error = pinctrl_claim_hogs(pctldev); if (error) { - dev_err(pctldev->dev, "could not claim hogs: %i\n", - error); - pinctrl_free_pindescs(pctldev, pctldev->desc->pins, - pctldev->desc->npins); - mutex_destroy(&pctldev->mutex); - kfree(pctldev); - + dev_err(pctldev->dev, "could not claim hogs: %i\n", error); return error; } diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index df1efc2e5202..6a94ecd6a8de 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -220,14 +220,16 @@ int pinctrl_dt_to_map(struct pinctrl *p, struct pinctrl_dev *pctldev) for (state = 0; ; state++) { /* Retrieve the pinctrl-* property */ propname = kasprintf(GFP_KERNEL, "pinctrl-%d", state); - if (!propname) - return -ENOMEM; + if (!propname) { + ret = -ENOMEM; + goto err; + } prop = of_find_property(np, propname, &size); kfree(propname); if (!prop) { if (state == 0) { - of_node_put(np); - return -ENODEV; + ret = -ENODEV; + goto err; } break; } diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index ac97724c59ba..4e87f5b875c0 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -231,6 +231,7 @@ static const unsigned int byt_score_pins_map[BYT_NGPIO_SCORE] = { /* SCORE groups */ static const unsigned int byt_score_uart1_pins[] = { 70, 71, 72, 73 }; static const unsigned int byt_score_uart2_pins[] = { 74, 75, 76, 77 }; +static const unsigned int byt_score_uart3_pins[] = { 57, 61 }; static const unsigned int byt_score_pwm0_pins[] = { 94 }; static const unsigned int byt_score_pwm1_pins[] = { 95 }; @@ -278,37 +279,38 @@ static const unsigned int byt_score_plt_clk5_pins[] = { 101 }; static const unsigned int byt_score_smbus_pins[] = { 51, 52, 53 }; static const struct intel_pingroup byt_score_groups[] = { - PIN_GROUP("uart1_grp", byt_score_uart1_pins, 1), - PIN_GROUP("uart2_grp", byt_score_uart2_pins, 1), - PIN_GROUP("pwm0_grp", byt_score_pwm0_pins, 1), - PIN_GROUP("pwm1_grp", byt_score_pwm1_pins, 1), - PIN_GROUP("ssp2_grp", byt_score_ssp2_pins, 1), - PIN_GROUP("sio_spi_grp", byt_score_sio_spi_pins, 1), - PIN_GROUP("i2c5_grp", byt_score_i2c5_pins, 1), - PIN_GROUP("i2c6_grp", byt_score_i2c6_pins, 1), - PIN_GROUP("i2c4_grp", byt_score_i2c4_pins, 1), - PIN_GROUP("i2c3_grp", byt_score_i2c3_pins, 1), - PIN_GROUP("i2c2_grp", byt_score_i2c2_pins, 1), - PIN_GROUP("i2c1_grp", byt_score_i2c1_pins, 1), - PIN_GROUP("i2c0_grp", byt_score_i2c0_pins, 1), - PIN_GROUP("ssp0_grp", byt_score_ssp0_pins, 1), - PIN_GROUP("ssp1_grp", byt_score_ssp1_pins, 1), - PIN_GROUP("sdcard_grp", byt_score_sdcard_pins, byt_score_sdcard_mux_values), - PIN_GROUP("sdio_grp", byt_score_sdio_pins, 1), - PIN_GROUP("emmc_grp", byt_score_emmc_pins, 1), - PIN_GROUP("lpc_grp", byt_score_ilb_lpc_pins, 1), - PIN_GROUP("sata_grp", byt_score_sata_pins, 1), - PIN_GROUP("plt_clk0_grp", byt_score_plt_clk0_pins, 1), - PIN_GROUP("plt_clk1_grp", byt_score_plt_clk1_pins, 1), - PIN_GROUP("plt_clk2_grp", byt_score_plt_clk2_pins, 1), - PIN_GROUP("plt_clk3_grp", byt_score_plt_clk3_pins, 1), - PIN_GROUP("plt_clk4_grp", byt_score_plt_clk4_pins, 1), - PIN_GROUP("plt_clk5_grp", byt_score_plt_clk5_pins, 1), - PIN_GROUP("smbus_grp", byt_score_smbus_pins, 1), + PIN_GROUP_GPIO("uart1_grp", byt_score_uart1_pins, 1), + PIN_GROUP_GPIO("uart2_grp", byt_score_uart2_pins, 1), + PIN_GROUP_GPIO("uart3_grp", byt_score_uart3_pins, 1), + PIN_GROUP_GPIO("pwm0_grp", byt_score_pwm0_pins, 1), + PIN_GROUP_GPIO("pwm1_grp", byt_score_pwm1_pins, 1), + PIN_GROUP_GPIO("ssp2_grp", byt_score_ssp2_pins, 1), + PIN_GROUP_GPIO("sio_spi_grp", byt_score_sio_spi_pins, 1), + PIN_GROUP_GPIO("i2c5_grp", byt_score_i2c5_pins, 1), + PIN_GROUP_GPIO("i2c6_grp", byt_score_i2c6_pins, 1), + PIN_GROUP_GPIO("i2c4_grp", byt_score_i2c4_pins, 1), + PIN_GROUP_GPIO("i2c3_grp", byt_score_i2c3_pins, 1), + PIN_GROUP_GPIO("i2c2_grp", byt_score_i2c2_pins, 1), + PIN_GROUP_GPIO("i2c1_grp", byt_score_i2c1_pins, 1), + PIN_GROUP_GPIO("i2c0_grp", byt_score_i2c0_pins, 1), + PIN_GROUP_GPIO("ssp0_grp", byt_score_ssp0_pins, 1), + PIN_GROUP_GPIO("ssp1_grp", byt_score_ssp1_pins, 1), + PIN_GROUP_GPIO("sdcard_grp", byt_score_sdcard_pins, byt_score_sdcard_mux_values), + PIN_GROUP_GPIO("sdio_grp", byt_score_sdio_pins, 1), + PIN_GROUP_GPIO("emmc_grp", byt_score_emmc_pins, 1), + PIN_GROUP_GPIO("lpc_grp", byt_score_ilb_lpc_pins, 1), + PIN_GROUP_GPIO("sata_grp", byt_score_sata_pins, 1), + PIN_GROUP_GPIO("plt_clk0_grp", byt_score_plt_clk0_pins, 1), + PIN_GROUP_GPIO("plt_clk1_grp", byt_score_plt_clk1_pins, 1), + PIN_GROUP_GPIO("plt_clk2_grp", byt_score_plt_clk2_pins, 1), + PIN_GROUP_GPIO("plt_clk3_grp", byt_score_plt_clk3_pins, 1), + PIN_GROUP_GPIO("plt_clk4_grp", byt_score_plt_clk4_pins, 1), + PIN_GROUP_GPIO("plt_clk5_grp", byt_score_plt_clk5_pins, 1), + PIN_GROUP_GPIO("smbus_grp", byt_score_smbus_pins, 1), }; static const char * const byt_score_uart_groups[] = { - "uart1_grp", "uart2_grp", + "uart1_grp", "uart2_grp", "uart3_grp", }; static const char * const byt_score_pwm_groups[] = { "pwm0_grp", "pwm1_grp", @@ -332,12 +334,14 @@ static const char * const byt_score_plt_clk_groups[] = { }; static const char * const byt_score_smbus_groups[] = { "smbus_grp" }; static const char * const byt_score_gpio_groups[] = { - "uart1_grp", "uart2_grp", "pwm0_grp", "pwm1_grp", "ssp0_grp", - "ssp1_grp", "ssp2_grp", "sio_spi_grp", "i2c0_grp", "i2c1_grp", - "i2c2_grp", "i2c3_grp", "i2c4_grp", "i2c5_grp", "i2c6_grp", - "sdcard_grp", "sdio_grp", "emmc_grp", "lpc_grp", "sata_grp", - "plt_clk0_grp", "plt_clk1_grp", "plt_clk2_grp", "plt_clk3_grp", - "plt_clk4_grp", "plt_clk5_grp", "smbus_grp", + "uart1_grp_gpio", "uart2_grp_gpio", "uart3_grp_gpio", "pwm0_grp_gpio", + "pwm1_grp_gpio", "ssp0_grp_gpio", "ssp1_grp_gpio", "ssp2_grp_gpio", + "sio_spi_grp_gpio", "i2c0_grp_gpio", "i2c1_grp_gpio", "i2c2_grp_gpio", + "i2c3_grp_gpio", "i2c4_grp_gpio", "i2c5_grp_gpio", "i2c6_grp_gpio", + "sdcard_grp_gpio", "sdio_grp_gpio", "emmc_grp_gpio", "lpc_grp_gpio", + "sata_grp_gpio", "plt_clk0_grp_gpio", "plt_clk1_grp_gpio", + "plt_clk2_grp_gpio", "plt_clk3_grp_gpio", "plt_clk4_grp_gpio", + "plt_clk5_grp_gpio", "smbus_grp_gpio", }; static const struct intel_function byt_score_functions[] = { @@ -456,8 +460,8 @@ static const struct intel_pingroup byt_sus_groups[] = { PIN_GROUP("usb_oc_grp_gpio", byt_sus_usb_over_current_pins, byt_sus_usb_over_current_gpio_mode_values), PIN_GROUP("usb_ulpi_grp_gpio", byt_sus_usb_ulpi_pins, byt_sus_usb_ulpi_gpio_mode_values), PIN_GROUP("pcu_spi_grp_gpio", byt_sus_pcu_spi_pins, byt_sus_pcu_spi_gpio_mode_values), - PIN_GROUP("pmu_clk1_grp", byt_sus_pmu_clk1_pins, 1), - PIN_GROUP("pmu_clk2_grp", byt_sus_pmu_clk2_pins, 1), + PIN_GROUP_GPIO("pmu_clk1_grp", byt_sus_pmu_clk1_pins, 1), + PIN_GROUP_GPIO("pmu_clk2_grp", byt_sus_pmu_clk2_pins, 1), }; static const char * const byt_sus_usb_groups[] = { @@ -469,7 +473,7 @@ static const char * const byt_sus_pmu_clk_groups[] = { }; static const char * const byt_sus_gpio_groups[] = { "usb_oc_grp_gpio", "usb_ulpi_grp_gpio", "pcu_spi_grp_gpio", - "pmu_clk1_grp", "pmu_clk2_grp", + "pmu_clk1_grp_gpio", "pmu_clk2_grp_gpio", }; static const struct intel_function byt_sus_functions[] = { diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h index fde65e18cd14..6981e2fab93f 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.h +++ b/drivers/pinctrl/intel/pinctrl-intel.h @@ -179,6 +179,10 @@ struct intel_community { .modes = __builtin_choose_expr(__builtin_constant_p((m)), NULL, (m)), \ } +#define PIN_GROUP_GPIO(n, p, m) \ + PIN_GROUP(n, p, m), \ + PIN_GROUP(n "_gpio", p, 0) + #define FUNCTION(n, g) \ { \ .func = PINCTRL_PINFUNCTION((n), (g), ARRAY_SIZE(g)), \ diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c index b6bc31abd2b0..b19bc391705e 100644 --- a/drivers/pinctrl/mediatek/pinctrl-paris.c +++ b/drivers/pinctrl/mediatek/pinctrl-paris.c @@ -165,20 +165,21 @@ static int mtk_pinconf_get(struct pinctrl_dev *pctldev, err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_SR, &ret); break; case PIN_CONFIG_INPUT_ENABLE: - case PIN_CONFIG_OUTPUT_ENABLE: + err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_IES, &ret); + if (!ret) + err = -EINVAL; + break; + case PIN_CONFIG_OUTPUT: err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DIR, &ret); if (err) break; - /* CONFIG Current direction return value - * ------------- ----------------- ---------------------- - * OUTPUT_ENABLE output 1 (= HW value) - * input 0 (= HW value) - * INPUT_ENABLE output 0 (= reverse HW value) - * input 1 (= reverse HW value) - */ - if (param == PIN_CONFIG_INPUT_ENABLE) - ret = !ret; + if (!ret) { + err = -EINVAL; + break; + } + + err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DO, &ret); break; case PIN_CONFIG_INPUT_SCHMITT_ENABLE: err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DIR, &ret); @@ -193,6 +194,8 @@ static int mtk_pinconf_get(struct pinctrl_dev *pctldev, } err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_SMT, &ret); + if (!ret) + err = -EINVAL; break; case PIN_CONFIG_DRIVE_STRENGTH: if (!hw->soc->drive_get) @@ -281,26 +284,9 @@ static int mtk_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, break; err = hw->soc->bias_set_combo(hw, desc, 0, arg); break; - case PIN_CONFIG_OUTPUT_ENABLE: - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_SMT, - MTK_DISABLE); - /* Keep set direction to consider the case that a GPIO pin - * does not have SMT control - */ - if (err != -ENOTSUPP) - break; - - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_DIR, - MTK_OUTPUT); - break; case PIN_CONFIG_INPUT_ENABLE: /* regard all non-zero value as enable */ err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_IES, !!arg); - if (err) - break; - - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_DIR, - MTK_INPUT); break; case PIN_CONFIG_SLEW_RATE: /* regard all non-zero value as enable */ diff --git a/drivers/pinctrl/meson/pinctrl-meson-a1.c b/drivers/pinctrl/meson/pinctrl-meson-a1.c index 79f5d753d7e1..50a87d9618a8 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-a1.c +++ b/drivers/pinctrl/meson/pinctrl-meson-a1.c @@ -250,7 +250,7 @@ static const unsigned int pdm_dclk_x_pins[] = { GPIOX_10 }; static const unsigned int pdm_din2_a_pins[] = { GPIOA_6 }; static const unsigned int pdm_din1_a_pins[] = { GPIOA_7 }; static const unsigned int pdm_din0_a_pins[] = { GPIOA_8 }; -static const unsigned int pdm_dclk_pins[] = { GPIOA_9 }; +static const unsigned int pdm_dclk_a_pins[] = { GPIOA_9 }; /* gen_clk */ static const unsigned int gen_clk_x_pins[] = { GPIOX_7 }; @@ -591,7 +591,7 @@ static struct meson_pmx_group meson_a1_periphs_groups[] = { GROUP(pdm_din2_a, 3), GROUP(pdm_din1_a, 3), GROUP(pdm_din0_a, 3), - GROUP(pdm_dclk, 3), + GROUP(pdm_dclk_a, 3), GROUP(pwm_c_a, 3), GROUP(pwm_b_a, 3), @@ -755,7 +755,7 @@ static const char * const spi_a_groups[] = { static const char * const pdm_groups[] = { "pdm_din0_x", "pdm_din1_x", "pdm_din2_x", "pdm_dclk_x", "pdm_din2_a", - "pdm_din1_a", "pdm_din0_a", "pdm_dclk", + "pdm_din1_a", "pdm_din0_a", "pdm_dclk_a", }; static const char * const gen_clk_groups[] = { diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index eb5a8c654260..20425afc6b33 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -2045,7 +2045,9 @@ static void rzg2l_gpio_irq_restore(struct rzg2l_pinctrl *pctrl) for (unsigned int i = 0; i < RZG2L_TINT_MAX_INTERRUPT; i++) { struct irq_data *data; + unsigned long flags; unsigned int virq; + int ret; if (!pctrl->hwirq[i]) continue; @@ -2063,8 +2065,18 @@ static void rzg2l_gpio_irq_restore(struct rzg2l_pinctrl *pctrl) continue; } - if (!irqd_irq_disabled(data)) + /* + * This has to be atomically executed to protect against a concurrent + * interrupt. + */ + raw_spin_lock_irqsave(&pctrl->lock.rlock, flags); + ret = rzg2l_gpio_irq_set_type(data, irqd_get_trigger_type(data)); + if (!ret && !irqd_irq_disabled(data)) rzg2l_gpio_irq_enable(data); + raw_spin_unlock_irqrestore(&pctrl->lock.rlock, flags); + + if (ret) + dev_crit(pctrl->dev, "Failed to set IRQ type for virq=%u\n", virq); } } diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index 30951f7131cd..1accdaaf282c 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -721,6 +721,7 @@ static struct miscdevice isst_if_char_driver = { static const struct x86_cpu_id hpm_cpu_ids[] = { X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, NULL), X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, NULL), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT, NULL), X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, NULL), {} }; diff --git a/drivers/power/supply/mt6360_charger.c b/drivers/power/supply/mt6360_charger.c index 1305cba61edd..aca123783efc 100644 --- a/drivers/power/supply/mt6360_charger.c +++ b/drivers/power/supply/mt6360_charger.c @@ -588,7 +588,7 @@ static const struct regulator_ops mt6360_chg_otg_ops = { }; static const struct regulator_desc mt6360_otg_rdesc = { - .of_match = "usb-otg-vbus", + .of_match = "usb-otg-vbus-regulator", .name = "usb-otg-vbus", .ops = &mt6360_chg_otg_ops, .owner = THIS_MODULE, diff --git a/drivers/power/supply/rt9455_charger.c b/drivers/power/supply/rt9455_charger.c index c345a77f9f78..e4dbacd50a43 100644 --- a/drivers/power/supply/rt9455_charger.c +++ b/drivers/power/supply/rt9455_charger.c @@ -192,6 +192,7 @@ static const int rt9455_voreg_values[] = { 4450000, 4450000, 4450000, 4450000, 4450000, 4450000, 4450000, 4450000 }; +#if IS_ENABLED(CONFIG_USB_PHY) /* * When the charger is in boost mode, REG02[7:2] represent boost output * voltage. @@ -207,6 +208,7 @@ static const int rt9455_boost_voltage_values[] = { 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, }; +#endif /* REG07[3:0] (VMREG) in uV */ static const int rt9455_vmreg_values[] = { diff --git a/drivers/regulator/irq_helpers.c b/drivers/regulator/irq_helpers.c index fe7ae0f3f46a..5ab1a0befe12 100644 --- a/drivers/regulator/irq_helpers.c +++ b/drivers/regulator/irq_helpers.c @@ -352,6 +352,9 @@ void *regulator_irq_helper(struct device *dev, h->irq = irq; h->desc = *d; + h->desc.name = devm_kstrdup(dev, d->name, GFP_KERNEL); + if (!h->desc.name) + return ERR_PTR(-ENOMEM); ret = init_rdev_state(dev, h, rdev, common_errs, per_rdev_errs, rdev_amount); diff --git a/drivers/regulator/mt6360-regulator.c b/drivers/regulator/mt6360-regulator.c index ad6587a378d0..24cc9fc94e90 100644 --- a/drivers/regulator/mt6360-regulator.c +++ b/drivers/regulator/mt6360-regulator.c @@ -319,15 +319,15 @@ static unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode) } } -#define MT6360_REGULATOR_DESC(_name, _sname, ereg, emask, vreg, vmask, \ - mreg, mmask, streg, stmask, vranges, \ - vcnts, offon_delay, irq_tbls) \ +#define MT6360_REGULATOR_DESC(match, _name, _sname, ereg, emask, vreg, \ + vmask, mreg, mmask, streg, stmask, \ + vranges, vcnts, offon_delay, irq_tbls) \ { \ .desc = { \ .name = #_name, \ .supply_name = #_sname, \ .id = MT6360_REGULATOR_##_name, \ - .of_match = of_match_ptr(#_name), \ + .of_match = of_match_ptr(match), \ .regulators_node = of_match_ptr("regulator"), \ .of_map_mode = mt6360_regulator_of_map_mode, \ .owner = THIS_MODULE, \ @@ -351,21 +351,29 @@ static unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode) } static const struct mt6360_regulator_desc mt6360_regulator_descs[] = { - MT6360_REGULATOR_DESC(BUCK1, BUCK1_VIN, 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04, + MT6360_REGULATOR_DESC("buck1", BUCK1, BUCK1_VIN, + 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04, buck_vout_ranges, 256, 0, buck1_irq_tbls), - MT6360_REGULATOR_DESC(BUCK2, BUCK2_VIN, 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04, + MT6360_REGULATOR_DESC("buck2", BUCK2, BUCK2_VIN, + 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04, buck_vout_ranges, 256, 0, buck2_irq_tbls), - MT6360_REGULATOR_DESC(LDO6, LDO_VIN3, 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04, + MT6360_REGULATOR_DESC("ldo6", LDO6, LDO_VIN3, + 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04, ldo_vout_ranges1, 256, 0, ldo6_irq_tbls), - MT6360_REGULATOR_DESC(LDO7, LDO_VIN3, 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04, + MT6360_REGULATOR_DESC("ldo7", LDO7, LDO_VIN3, + 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04, ldo_vout_ranges1, 256, 0, ldo7_irq_tbls), - MT6360_REGULATOR_DESC(LDO1, LDO_VIN1, 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04, + MT6360_REGULATOR_DESC("ldo1", LDO1, LDO_VIN1, + 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04, ldo_vout_ranges2, 256, 0, ldo1_irq_tbls), - MT6360_REGULATOR_DESC(LDO2, LDO_VIN1, 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04, + MT6360_REGULATOR_DESC("ldo2", LDO2, LDO_VIN1, + 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04, ldo_vout_ranges2, 256, 0, ldo2_irq_tbls), - MT6360_REGULATOR_DESC(LDO3, LDO_VIN1, 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04, + MT6360_REGULATOR_DESC("ldo3", LDO3, LDO_VIN1, + 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04, ldo_vout_ranges2, 256, 100, ldo3_irq_tbls), - MT6360_REGULATOR_DESC(LDO5, LDO_VIN2, 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04, + MT6360_REGULATOR_DESC("ldo5", LDO5, LDO_VIN2, + 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04, ldo_vout_ranges3, 128, 100, ldo5_irq_tbls), }; diff --git a/drivers/regulator/qcom-refgen-regulator.c b/drivers/regulator/qcom-refgen-regulator.c index 656fe330d38f..063e12c08e75 100644 --- a/drivers/regulator/qcom-refgen-regulator.c +++ b/drivers/regulator/qcom-refgen-regulator.c @@ -140,6 +140,7 @@ static const struct of_device_id qcom_refgen_match_table[] = { { .compatible = "qcom,sm8250-refgen-regulator", .data = &sm8250_refgen_desc }, { } }; +MODULE_DEVICE_TABLE(of, qcom_refgen_match_table); static struct platform_driver qcom_refgen_driver = { .probe = qcom_refgen_probe, diff --git a/drivers/regulator/vqmmc-ipq4019-regulator.c b/drivers/regulator/vqmmc-ipq4019-regulator.c index 086da36abc0b..4955616517ce 100644 --- a/drivers/regulator/vqmmc-ipq4019-regulator.c +++ b/drivers/regulator/vqmmc-ipq4019-regulator.c @@ -84,6 +84,7 @@ static const struct of_device_id regulator_ipq4019_of_match[] = { { .compatible = "qcom,vqmmc-ipq4019-regulator", }, {}, }; +MODULE_DEVICE_TABLE(of, regulator_ipq4019_of_match); static struct platform_driver ipq4019_regulator_driver = { .probe = ipq4019_regulator_probe, diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c index 37173cb0f5f5..c57694be9bd3 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -162,7 +162,8 @@ struct raw3270_request *raw3270_request_alloc(size_t size) /* * Setup ccw. */ - rq->ccw.cda = virt_to_dma32(rq->buffer); + if (rq->buffer) + rq->ccw.cda = virt_to_dma32(rq->buffer); rq->ccw.flags = CCW_FLAG_SLI; return rq; @@ -188,7 +189,8 @@ int raw3270_request_reset(struct raw3270_request *rq) return -EBUSY; rq->ccw.cmd_code = 0; rq->ccw.count = 0; - rq->ccw.cda = virt_to_dma32(rq->buffer); + if (rq->buffer) + rq->ccw.cda = virt_to_dma32(rq->buffer); rq->ccw.flags = CCW_FLAG_SLI; rq->rescnt = 0; rq->rc = 0; diff --git a/drivers/s390/cio/cio_inject.c b/drivers/s390/cio/cio_inject.c index 8613fa937237..a2e771ebae8e 100644 --- a/drivers/s390/cio/cio_inject.c +++ b/drivers/s390/cio/cio_inject.c @@ -95,7 +95,7 @@ static ssize_t crw_inject_write(struct file *file, const char __user *buf, return -EINVAL; } - buffer = vmemdup_user(buf, lbuf); + buffer = memdup_user_nul(buf, lbuf); if (IS_ERR(buffer)) return -ENOMEM; diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 0a3a678ffc7e..6087547328ce 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -658,7 +658,7 @@ int cca_sec2protkey(u16 cardnr, u16 domain, (int)prepcblk->ccp_rtcode, (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) - rc = -EAGAIN; + rc = -EBUSY; else rc = -EIO; goto out; @@ -1263,7 +1263,7 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, (int)prepcblk->ccp_rtcode, (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) - rc = -EAGAIN; + rc = -EBUSY; else rc = -EIO; goto out; @@ -1426,7 +1426,7 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, (int)prepcblk->ccp_rtcode, (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) - rc = -EAGAIN; + rc = -EBUSY; else rc = -EIO; goto out; diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index eb7f5489ccf9..9bcf8fc69ebe 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -556,13 +556,29 @@ static int check_reply_pl(const u8 *pl, const char *func) pl += 2; ret = *((u32 *)pl); if (ret != 0) { - ZCRYPT_DBF_ERR("%s return value 0x%04x != 0\n", func, ret); + ZCRYPT_DBF_ERR("%s return value 0x%08x != 0\n", func, ret); return -EIO; } return 0; } +/* Check ep11 reply cprb, return 0 or suggested errno value. */ +static int check_reply_cprb(const struct ep11_cprb *rep, const char *func) +{ + /* check ep11 reply return code field */ + if (rep->ret_code) { + ZCRYPT_DBF_ERR("%s ep11 reply ret_code=0x%08x\n", __func__, + rep->ret_code); + if (rep->ret_code == 0x000c0003) + return -EBUSY; + else + return -EIO; + } + + return 0; +} + /* * Helper function which does an ep11 query with given query type. */ @@ -627,6 +643,12 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, goto out; } + /* check ep11 reply cprb */ + rc = check_reply_cprb(rep, __func__); + if (rc) + goto out; + + /* check payload */ rc = check_reply_pl((u8 *)rep_pl, __func__); if (rc) goto out; @@ -877,6 +899,12 @@ static int _ep11_genaeskey(u16 card, u16 domain, goto out; } + /* check ep11 reply cprb */ + rc = check_reply_cprb(rep, __func__); + if (rc) + goto out; + + /* check payload */ rc = check_reply_pl((u8 *)rep_pl, __func__); if (rc) goto out; @@ -1028,6 +1056,12 @@ static int ep11_cryptsingle(u16 card, u16 domain, goto out; } + /* check ep11 reply cprb */ + rc = check_reply_cprb(rep, __func__); + if (rc) + goto out; + + /* check payload */ rc = check_reply_pl((u8 *)rep_pl, __func__); if (rc) goto out; @@ -1185,6 +1219,12 @@ static int _ep11_unwrapkey(u16 card, u16 domain, goto out; } + /* check ep11 reply cprb */ + rc = check_reply_cprb(rep, __func__); + if (rc) + goto out; + + /* check payload */ rc = check_reply_pl((u8 *)rep_pl, __func__); if (rc) goto out; @@ -1339,6 +1379,12 @@ static int _ep11_wrapkey(u16 card, u16 domain, goto out; } + /* check ep11 reply cprb */ + rc = check_reply_cprb(rep, __func__); + if (rc) + goto out; + + /* check payload */ rc = check_reply_pl((u8 *)rep_pl, __func__); if (rc) goto out; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index f0b8b709649f..a3adaec5504e 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -364,30 +364,33 @@ out: return rc; } +static void qeth_free_cq(struct qeth_card *card) +{ + if (card->qdio.c_q) { + qeth_free_qdio_queue(card->qdio.c_q); + card->qdio.c_q = NULL; + } +} + static int qeth_alloc_cq(struct qeth_card *card) { if (card->options.cq == QETH_CQ_ENABLED) { QETH_CARD_TEXT(card, 2, "cqon"); - card->qdio.c_q = qeth_alloc_qdio_queue(); if (!card->qdio.c_q) { - dev_err(&card->gdev->dev, "Failed to create completion queue\n"); - return -ENOMEM; + card->qdio.c_q = qeth_alloc_qdio_queue(); + if (!card->qdio.c_q) { + dev_err(&card->gdev->dev, + "Failed to create completion queue\n"); + return -ENOMEM; + } } } else { QETH_CARD_TEXT(card, 2, "nocq"); - card->qdio.c_q = NULL; + qeth_free_cq(card); } return 0; } -static void qeth_free_cq(struct qeth_card *card) -{ - if (card->qdio.c_q) { - qeth_free_qdio_queue(card->qdio.c_q); - card->qdio.c_q = NULL; - } -} - static enum iucv_tx_notify qeth_compute_cq_notification(int sbalf15, int delayed) { @@ -2628,6 +2631,10 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) QETH_CARD_TEXT(card, 2, "allcqdbf"); + /* completion */ + if (qeth_alloc_cq(card)) + goto out_err; + if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_UNINITIALIZED, QETH_QDIO_ALLOCATED) != QETH_QDIO_UNINITIALIZED) return 0; @@ -2663,10 +2670,6 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT; } - /* completion */ - if (qeth_alloc_cq(card)) - goto out_freeoutq; - return 0; out_freeoutq: @@ -2677,6 +2680,8 @@ out_freeoutq: qeth_free_buffer_pool(card); out_buffer_pool: atomic_set(&card->qdio.state, QETH_QDIO_UNINITIALIZED); + qeth_free_cq(card); +out_err: return -ENOMEM; } @@ -2684,11 +2689,12 @@ static void qeth_free_qdio_queues(struct qeth_card *card) { int i, j; + qeth_free_cq(card); + if (atomic_xchg(&card->qdio.state, QETH_QDIO_UNINITIALIZED) == QETH_QDIO_UNINITIALIZED) return; - qeth_free_cq(card); for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) { if (card->qdio.in_q->bufs[j].rx_skb) { consume_skb(card->qdio.in_q->bufs[j].rx_skb); @@ -3742,24 +3748,11 @@ static void qeth_qdio_poll(struct ccw_device *cdev, unsigned long card_ptr) int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) { - int rc; - - if (card->options.cq == QETH_CQ_NOTAVAILABLE) { - rc = -1; - goto out; - } else { - if (card->options.cq == cq) { - rc = 0; - goto out; - } - - qeth_free_qdio_queues(card); - card->options.cq = cq; - rc = 0; - } -out: - return rc; + if (card->options.cq == QETH_CQ_NOTAVAILABLE) + return -1; + card->options.cq = cq; + return 0; } EXPORT_SYMBOL_GPL(qeth_configure_cq); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 58fdf679341d..65cdc8b77e35 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3120,6 +3120,7 @@ static void sd_read_io_hints(struct scsi_disk *sdkp, unsigned char *buffer) { struct scsi_device *sdp = sdkp->device; const struct scsi_io_group_descriptor *desc, *start, *end; + u16 permanent_stream_count_old; struct scsi_sense_hdr sshdr; struct scsi_mode_data data; int res; @@ -3140,12 +3141,13 @@ static void sd_read_io_hints(struct scsi_disk *sdkp, unsigned char *buffer) for (desc = start; desc < end; desc++) if (!desc->st_enble || !sd_is_perm_stream(sdkp, desc - start)) break; + permanent_stream_count_old = sdkp->permanent_stream_count; sdkp->permanent_stream_count = desc - start; if (sdkp->rscs && sdkp->permanent_stream_count < 2) sd_printk(KERN_INFO, sdkp, "Unexpected: RSCS has been set and the permanent stream count is %u\n", sdkp->permanent_stream_count); - else if (sdkp->permanent_stream_count) + else if (sdkp->permanent_stream_count != permanent_stream_count_old) sd_printk(KERN_INFO, sdkp, "permanent stream count = %d\n", sdkp->permanent_stream_count); } diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c index 7cc219d78551..e358ac5b4509 100644 --- a/drivers/spi/spi-axi-spi-engine.c +++ b/drivers/spi/spi-axi-spi-engine.c @@ -623,7 +623,7 @@ static int spi_engine_probe(struct platform_device *pdev) version = readl(spi_engine->base + ADI_AXI_REG_VERSION); if (ADI_AXI_PCORE_VER_MAJOR(version) != 1) { - dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%c\n", + dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%u\n", ADI_AXI_PCORE_VER_MAJOR(version), ADI_AXI_PCORE_VER_MINOR(version), ADI_AXI_PCORE_VER_PATCH(version)); diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c index 35ef5e8e2ffd..77e9738e42f6 100644 --- a/drivers/spi/spi-hisi-kunpeng.c +++ b/drivers/spi/spi-hisi-kunpeng.c @@ -151,8 +151,6 @@ static const struct debugfs_reg32 hisi_spi_regs[] = { HISI_SPI_DBGFS_REG("ENR", HISI_SPI_ENR), HISI_SPI_DBGFS_REG("FIFOC", HISI_SPI_FIFOC), HISI_SPI_DBGFS_REG("IMR", HISI_SPI_IMR), - HISI_SPI_DBGFS_REG("DIN", HISI_SPI_DIN), - HISI_SPI_DBGFS_REG("DOUT", HISI_SPI_DOUT), HISI_SPI_DBGFS_REG("SR", HISI_SPI_SR), HISI_SPI_DBGFS_REG("RISR", HISI_SPI_RISR), HISI_SPI_DBGFS_REG("ISR", HISI_SPI_ISR), diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ff75838c1b5d..a2c467d9e92f 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -4523,6 +4523,7 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message) wait_for_completion(&done); status = message->status; } + message->complete = NULL; message->context = NULL; return status; diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c index d78d54ae2605..5693cc8b231a 100644 --- a/drivers/thermal/thermal_debugfs.c +++ b/drivers/thermal/thermal_debugfs.c @@ -139,11 +139,13 @@ struct tz_episode { * we keep track of the current position in the history array. * * @tz_episodes: a list of thermal mitigation episodes + * @tz: thermal zone this object belongs to * @trips_crossed: an array of trip points crossed by id * @nr_trips: the number of trip points currently being crossed */ struct tz_debugfs { struct list_head tz_episodes; + struct thermal_zone_device *tz; int *trips_crossed; int nr_trips; }; @@ -503,15 +505,23 @@ void thermal_debug_cdev_add(struct thermal_cooling_device *cdev) */ void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev) { - struct thermal_debugfs *thermal_dbg = cdev->debugfs; + struct thermal_debugfs *thermal_dbg; - if (!thermal_dbg) + mutex_lock(&cdev->lock); + + thermal_dbg = cdev->debugfs; + if (!thermal_dbg) { + mutex_unlock(&cdev->lock); return; + } + + cdev->debugfs = NULL; + + mutex_unlock(&cdev->lock); mutex_lock(&thermal_dbg->lock); thermal_debugfs_cdev_clear(&thermal_dbg->cdev_dbg); - cdev->debugfs = NULL; mutex_unlock(&thermal_dbg->lock); @@ -716,8 +726,7 @@ out: static void *tze_seq_start(struct seq_file *s, loff_t *pos) { - struct thermal_zone_device *tz = s->private; - struct thermal_debugfs *thermal_dbg = tz->debugfs; + struct thermal_debugfs *thermal_dbg = s->private; struct tz_debugfs *tz_dbg = &thermal_dbg->tz_dbg; mutex_lock(&thermal_dbg->lock); @@ -727,8 +736,7 @@ static void *tze_seq_start(struct seq_file *s, loff_t *pos) static void *tze_seq_next(struct seq_file *s, void *v, loff_t *pos) { - struct thermal_zone_device *tz = s->private; - struct thermal_debugfs *thermal_dbg = tz->debugfs; + struct thermal_debugfs *thermal_dbg = s->private; struct tz_debugfs *tz_dbg = &thermal_dbg->tz_dbg; return seq_list_next(v, &tz_dbg->tz_episodes, pos); @@ -736,15 +744,15 @@ static void *tze_seq_next(struct seq_file *s, void *v, loff_t *pos) static void tze_seq_stop(struct seq_file *s, void *v) { - struct thermal_zone_device *tz = s->private; - struct thermal_debugfs *thermal_dbg = tz->debugfs; + struct thermal_debugfs *thermal_dbg = s->private; mutex_unlock(&thermal_dbg->lock); } static int tze_seq_show(struct seq_file *s, void *v) { - struct thermal_zone_device *tz = s->private; + struct thermal_debugfs *thermal_dbg = s->private; + struct thermal_zone_device *tz = thermal_dbg->tz_dbg.tz; struct thermal_trip *trip; struct tz_episode *tze; const char *type; @@ -810,6 +818,8 @@ void thermal_debug_tz_add(struct thermal_zone_device *tz) tz_dbg = &thermal_dbg->tz_dbg; + tz_dbg->tz = tz; + tz_dbg->trips_crossed = kzalloc(sizeof(int) * tz->num_trips, GFP_KERNEL); if (!tz_dbg->trips_crossed) { thermal_debugfs_remove_id(thermal_dbg); @@ -818,23 +828,44 @@ void thermal_debug_tz_add(struct thermal_zone_device *tz) INIT_LIST_HEAD(&tz_dbg->tz_episodes); - debugfs_create_file("mitigations", 0400, thermal_dbg->d_top, tz, &tze_fops); + debugfs_create_file("mitigations", 0400, thermal_dbg->d_top, + thermal_dbg, &tze_fops); tz->debugfs = thermal_dbg; } void thermal_debug_tz_remove(struct thermal_zone_device *tz) { - struct thermal_debugfs *thermal_dbg = tz->debugfs; + struct thermal_debugfs *thermal_dbg; + struct tz_episode *tze, *tmp; + struct tz_debugfs *tz_dbg; + int *trips_crossed; - if (!thermal_dbg) + mutex_lock(&tz->lock); + + thermal_dbg = tz->debugfs; + if (!thermal_dbg) { + mutex_unlock(&tz->lock); return; + } + + tz->debugfs = NULL; + + mutex_unlock(&tz->lock); + + tz_dbg = &thermal_dbg->tz_dbg; mutex_lock(&thermal_dbg->lock); - tz->debugfs = NULL; + trips_crossed = tz_dbg->trips_crossed; + + list_for_each_entry_safe(tze, tmp, &tz_dbg->tz_episodes, node) { + list_del(&tze->node); + kfree(tze); + } mutex_unlock(&thermal_dbg->lock); thermal_debugfs_remove_id(thermal_dbg); + kfree(trips_crossed); } diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index c60794264da2..45cb8149d374 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -57,13 +57,14 @@ static void found_btree_node_to_key(struct bkey_i *k, const struct found_btree_n bp->v.seq = cpu_to_le64(f->cookie); bp->v.sectors_written = 0; bp->v.flags = 0; + bp->v.sectors_written = cpu_to_le16(f->sectors_written); bp->v.min_key = f->min_key; SET_BTREE_PTR_RANGE_UPDATED(&bp->v, f->range_updated); memcpy(bp->v.start, f->ptrs, sizeof(struct bch_extent_ptr) * f->nr_ptrs); } static bool found_btree_node_is_readable(struct btree_trans *trans, - const struct found_btree_node *f) + struct found_btree_node *f) { struct { __BKEY_PADDED(k, BKEY_BTREE_PTR_VAL_U64s_MAX); } k; @@ -71,8 +72,10 @@ static bool found_btree_node_is_readable(struct btree_trans *trans, struct btree *b = bch2_btree_node_get_noiter(trans, &k.k, f->btree_id, f->level, false); bool ret = !IS_ERR_OR_NULL(b); - if (ret) + if (ret) { + f->sectors_written = b->written; six_unlock_read(&b->c.lock); + } /* * We might update this node's range; if that happens, we need the node diff --git a/fs/bcachefs/btree_node_scan_types.h b/fs/bcachefs/btree_node_scan_types.h index abb7b27d556a..5cfaeb5ac831 100644 --- a/fs/bcachefs/btree_node_scan_types.h +++ b/fs/bcachefs/btree_node_scan_types.h @@ -9,6 +9,7 @@ struct found_btree_node { bool overwritten:1; u8 btree_id; u8 level; + unsigned sectors_written; u32 seq; u64 cookie; diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index 941401a210f5..82f179258867 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -525,7 +525,6 @@ int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca, "different types of data in same bucket: %s, %s", bch2_data_type_str(g->data_type), bch2_data_type_str(data_type))) { - BUG(); ret = -EIO; goto err; } @@ -629,7 +628,6 @@ int bch2_check_bucket_ref(struct btree_trans *trans, bch2_data_type_str(ptr_data_type), (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf)); - BUG(); ret = -EIO; goto err; } diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index ca4a066e9a54..0f95d7fb5ec0 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -606,7 +606,7 @@ int bch2_trigger_inode(struct btree_trans *trans, struct bkey_s new, unsigned flags) { - s64 nr = bkey_is_inode(new.k) - bkey_is_inode(old.k); + s64 nr = (s64) bkey_is_inode(new.k) - (s64) bkey_is_inode(old.k); if (flags & BTREE_TRIGGER_TRANSACTIONAL) { if (nr) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 55f3ba6a831c..0493272a7668 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3758,15 +3758,43 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) goto drop_write; } - down_write(&fs_info->subvol_sem); - switch (sa->cmd) { case BTRFS_QUOTA_CTL_ENABLE: case BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA: + down_write(&fs_info->subvol_sem); ret = btrfs_quota_enable(fs_info, sa); + up_write(&fs_info->subvol_sem); break; case BTRFS_QUOTA_CTL_DISABLE: + /* + * Lock the cleaner mutex to prevent races with concurrent + * relocation, because relocation may be building backrefs for + * blocks of the quota root while we are deleting the root. This + * is like dropping fs roots of deleted snapshots/subvolumes, we + * need the same protection. + * + * This also prevents races between concurrent tasks trying to + * disable quotas, because we will unlock and relock + * qgroup_ioctl_lock across BTRFS_FS_QUOTA_ENABLED changes. + * + * We take this here because we have the dependency of + * + * inode_lock -> subvol_sem + * + * because of rename. With relocation we can prealloc extents, + * so that makes the dependency chain + * + * cleaner_mutex -> inode_lock -> subvol_sem + * + * so we must take the cleaner_mutex here before we take the + * subvol_sem. The deadlock can't actually happen, but this + * quiets lockdep. + */ + mutex_lock(&fs_info->cleaner_mutex); + down_write(&fs_info->subvol_sem); ret = btrfs_quota_disable(fs_info); + up_write(&fs_info->subvol_sem); + mutex_unlock(&fs_info->cleaner_mutex); break; default: ret = -EINVAL; @@ -3774,7 +3802,6 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) } kfree(sa); - up_write(&fs_info->subvol_sem); drop_write: mnt_drop_write_file(file); return ret; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index b749ba45da2b..c2a42bcde98e 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -1188,6 +1188,7 @@ struct btrfs_ordered_extent *btrfs_split_ordered_extent( ordered->disk_bytenr += len; ordered->num_bytes -= len; ordered->disk_num_bytes -= len; + ordered->ram_bytes -= len; if (test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags)) { ASSERT(ordered->bytes_left == 0); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index cf8820ce7aa2..364acc9bbe73 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1342,16 +1342,10 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) lockdep_assert_held_write(&fs_info->subvol_sem); /* - * Lock the cleaner mutex to prevent races with concurrent relocation, - * because relocation may be building backrefs for blocks of the quota - * root while we are deleting the root. This is like dropping fs roots - * of deleted snapshots/subvolumes, we need the same protection. - * - * This also prevents races between concurrent tasks trying to disable - * quotas, because we will unlock and relock qgroup_ioctl_lock across - * BTRFS_FS_QUOTA_ENABLED changes. + * Relocation will mess with backrefs, so make sure we have the + * cleaner_mutex held to protect us from relocate. */ - mutex_lock(&fs_info->cleaner_mutex); + lockdep_assert_held(&fs_info->cleaner_mutex); mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) @@ -1373,9 +1367,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); + /* + * We have nothing held here and no trans handle, just return the error + * if there is one. + */ ret = flush_reservations(fs_info); if (ret) - goto out_unlock_cleaner; + return ret; /* * 1 For the root item @@ -1439,9 +1437,6 @@ out: btrfs_end_transaction(trans); else if (trans) ret = btrfs_commit_transaction(trans); -out_unlock_cleaner: - mutex_unlock(&fs_info->cleaner_mutex); - return ret; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index f15591f3e54f..ef6bd2f4251b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3455,6 +3455,7 @@ again: * alignment and size). */ ret = -EUCLEAN; + mutex_unlock(&fs_info->reclaim_bgs_lock); goto error; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 8aff1a724805..62da538d91cb 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -151,7 +151,7 @@ static int erofs_fscache_read_io_async(struct fscache_cookie *cookie, if (WARN_ON(len == 0)) source = NETFS_INVALID_READ; if (source != NETFS_READ_FROM_CACHE) { - erofs_err(NULL, "prepare_read failed (source %d)", source); + erofs_err(NULL, "prepare_ondemand_read failed (source %d)", source); return -EIO; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 39c67119f43b..d28ccfc0352b 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -84,13 +84,6 @@ struct erofs_dev_context { bool flatdev; }; -struct erofs_fs_context { - struct erofs_mount_opts opt; - struct erofs_dev_context *devs; - char *fsid; - char *domain_id; -}; - /* all filesystem-wide lz4 configurations */ struct erofs_sb_lz4_info { /* # of pages needed for EROFS lz4 rolling decompression */ diff --git a/fs/erofs/super.c b/fs/erofs/super.c index c0eb139adb07..30b49b2eee53 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -370,18 +370,18 @@ out: return ret; } -static void erofs_default_options(struct erofs_fs_context *ctx) +static void erofs_default_options(struct erofs_sb_info *sbi) { #ifdef CONFIG_EROFS_FS_ZIP - ctx->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND; - ctx->opt.max_sync_decompress_pages = 3; - ctx->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO; + sbi->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND; + sbi->opt.max_sync_decompress_pages = 3; + sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO; #endif #ifdef CONFIG_EROFS_FS_XATTR - set_opt(&ctx->opt, XATTR_USER); + set_opt(&sbi->opt, XATTR_USER); #endif #ifdef CONFIG_EROFS_FS_POSIX_ACL - set_opt(&ctx->opt, POSIX_ACL); + set_opt(&sbi->opt, POSIX_ACL); #endif } @@ -426,16 +426,16 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode) { #ifdef CONFIG_FS_DAX - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; switch (mode) { case EROFS_MOUNT_DAX_ALWAYS: - set_opt(&ctx->opt, DAX_ALWAYS); - clear_opt(&ctx->opt, DAX_NEVER); + set_opt(&sbi->opt, DAX_ALWAYS); + clear_opt(&sbi->opt, DAX_NEVER); return true; case EROFS_MOUNT_DAX_NEVER: - set_opt(&ctx->opt, DAX_NEVER); - clear_opt(&ctx->opt, DAX_ALWAYS); + set_opt(&sbi->opt, DAX_NEVER); + clear_opt(&sbi->opt, DAX_ALWAYS); return true; default: DBG_BUGON(1); @@ -450,7 +450,7 @@ static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode) static int erofs_fc_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; struct fs_parse_result result; struct erofs_device_info *dif; int opt, ret; @@ -463,9 +463,9 @@ static int erofs_fc_parse_param(struct fs_context *fc, case Opt_user_xattr: #ifdef CONFIG_EROFS_FS_XATTR if (result.boolean) - set_opt(&ctx->opt, XATTR_USER); + set_opt(&sbi->opt, XATTR_USER); else - clear_opt(&ctx->opt, XATTR_USER); + clear_opt(&sbi->opt, XATTR_USER); #else errorfc(fc, "{,no}user_xattr options not supported"); #endif @@ -473,16 +473,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, case Opt_acl: #ifdef CONFIG_EROFS_FS_POSIX_ACL if (result.boolean) - set_opt(&ctx->opt, POSIX_ACL); + set_opt(&sbi->opt, POSIX_ACL); else - clear_opt(&ctx->opt, POSIX_ACL); + clear_opt(&sbi->opt, POSIX_ACL); #else errorfc(fc, "{,no}acl options not supported"); #endif break; case Opt_cache_strategy: #ifdef CONFIG_EROFS_FS_ZIP - ctx->opt.cache_strategy = result.uint_32; + sbi->opt.cache_strategy = result.uint_32; #else errorfc(fc, "compression not supported, cache_strategy ignored"); #endif @@ -504,27 +504,27 @@ static int erofs_fc_parse_param(struct fs_context *fc, kfree(dif); return -ENOMEM; } - down_write(&ctx->devs->rwsem); - ret = idr_alloc(&ctx->devs->tree, dif, 0, 0, GFP_KERNEL); - up_write(&ctx->devs->rwsem); + down_write(&sbi->devs->rwsem); + ret = idr_alloc(&sbi->devs->tree, dif, 0, 0, GFP_KERNEL); + up_write(&sbi->devs->rwsem); if (ret < 0) { kfree(dif->path); kfree(dif); return ret; } - ++ctx->devs->extra_devices; + ++sbi->devs->extra_devices; break; #ifdef CONFIG_EROFS_FS_ONDEMAND case Opt_fsid: - kfree(ctx->fsid); - ctx->fsid = kstrdup(param->string, GFP_KERNEL); - if (!ctx->fsid) + kfree(sbi->fsid); + sbi->fsid = kstrdup(param->string, GFP_KERNEL); + if (!sbi->fsid) return -ENOMEM; break; case Opt_domain_id: - kfree(ctx->domain_id); - ctx->domain_id = kstrdup(param->string, GFP_KERNEL); - if (!ctx->domain_id) + kfree(sbi->domain_id); + sbi->domain_id = kstrdup(param->string, GFP_KERNEL); + if (!sbi->domain_id) return -ENOMEM; break; #else @@ -581,8 +581,7 @@ static const struct export_operations erofs_export_ops = { static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; - struct erofs_sb_info *sbi; - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = EROFS_SB(sb); int err; sb->s_magic = EROFS_SUPER_MAGIC; @@ -590,19 +589,6 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_op = &erofs_sops; - sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); - if (!sbi) - return -ENOMEM; - - sb->s_fs_info = sbi; - sbi->opt = ctx->opt; - sbi->devs = ctx->devs; - ctx->devs = NULL; - sbi->fsid = ctx->fsid; - ctx->fsid = NULL; - sbi->domain_id = ctx->domain_id; - ctx->domain_id = NULL; - sbi->blkszbits = PAGE_SHIFT; if (erofs_is_fscache_mode(sb)) { sb->s_blocksize = PAGE_SIZE; @@ -706,9 +692,9 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) static int erofs_fc_get_tree(struct fs_context *fc) { - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; - if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && ctx->fsid) + if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) return get_tree_nodev(fc, erofs_fc_fill_super); return get_tree_bdev(fc, erofs_fc_fill_super); @@ -718,19 +704,19 @@ static int erofs_fc_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct erofs_sb_info *sbi = EROFS_SB(sb); - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *new_sbi = fc->s_fs_info; DBG_BUGON(!sb_rdonly(sb)); - if (ctx->fsid || ctx->domain_id) + if (new_sbi->fsid || new_sbi->domain_id) erofs_info(sb, "ignoring reconfiguration for fsid|domain_id."); - if (test_opt(&ctx->opt, POSIX_ACL)) + if (test_opt(&new_sbi->opt, POSIX_ACL)) fc->sb_flags |= SB_POSIXACL; else fc->sb_flags &= ~SB_POSIXACL; - sbi->opt = ctx->opt; + sbi->opt = new_sbi->opt; fc->sb_flags |= SB_RDONLY; return 0; @@ -761,12 +747,15 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) static void erofs_fc_free(struct fs_context *fc) { - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; - erofs_free_dev_context(ctx->devs); - kfree(ctx->fsid); - kfree(ctx->domain_id); - kfree(ctx); + if (!sbi) + return; + + erofs_free_dev_context(sbi->devs); + kfree(sbi->fsid); + kfree(sbi->domain_id); + kfree(sbi); } static const struct fs_context_operations erofs_context_ops = { @@ -778,38 +767,35 @@ static const struct fs_context_operations erofs_context_ops = { static int erofs_init_fs_context(struct fs_context *fc) { - struct erofs_fs_context *ctx; + struct erofs_sb_info *sbi; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + if (!sbi) return -ENOMEM; - ctx->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL); - if (!ctx->devs) { - kfree(ctx); + + sbi->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL); + if (!sbi->devs) { + kfree(sbi); return -ENOMEM; } - fc->fs_private = ctx; + fc->s_fs_info = sbi; - idr_init(&ctx->devs->tree); - init_rwsem(&ctx->devs->rwsem); - erofs_default_options(ctx); + idr_init(&sbi->devs->tree); + init_rwsem(&sbi->devs->rwsem); + erofs_default_options(sbi); fc->ops = &erofs_context_ops; return 0; } static void erofs_kill_sb(struct super_block *sb) { - struct erofs_sb_info *sbi; + struct erofs_sb_info *sbi = EROFS_SB(sb); - if (erofs_is_fscache_mode(sb)) + if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) kill_anon_super(sb); else kill_block_super(sb); - sbi = EROFS_SB(sb); - if (!sbi) - return; - erofs_free_dev_context(sbi->devs); fs_put_dax(sbi->dax_dev, NULL); erofs_fscache_unregister_fs(sb); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index c709c296ea9a..acef52ecb1bb 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2429,7 +2429,12 @@ static int nfs_net_init(struct net *net) struct nfs_net *nn = net_generic(net, nfs_net_id); nfs_clients_init(net); - rpc_proc_register(net, &nn->rpcstats); + + if (!rpc_proc_register(net, &nn->rpcstats)) { + nfs_clients_exit(net); + return -ENOMEM; + } + return nfs_fs_proc_net_init(net); } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 1955481832e0..a644460f3a5e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3515,6 +3515,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, args.exp = exp; args.dentry = dentry; args.ignore_crossmnt = (ignore_crossmnt != 0); + args.acl = NULL; /* * Make a local copy of the attribute bitmap that can be modified. @@ -3573,7 +3574,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, } else args.fhp = fhp; - args.acl = NULL; if (attrmask[0] & FATTR4_WORD0_ACL) { err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl); if (err == -EOPNOTSUPP) diff --git a/include/linux/filter.h b/include/linux/filter.h index c99bc3df2d28..219ee7a76874 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -963,6 +963,7 @@ bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); +u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 4660582a3302..ed180ca419da 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -320,13 +320,13 @@ devm_regulator_get_exclusive(struct device *dev, const char *id) static inline int devm_regulator_get_enable(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline int devm_regulator_get_enable_optional(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline struct regulator *__must_check diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e65ec3fd2799..a509caf823d6 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -461,10 +461,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { + read_lock_bh(&sk->sk_callback_lock); if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); + read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, diff --git a/include/net/gro.h b/include/net/gro.h index 50f1e403dbbb..c1d4ca0463a1 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -87,6 +87,15 @@ struct napi_gro_cb { /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; + + /* L3 offsets */ + union { + struct { + u16 network_offset; + u16 inner_network_offset; + }; + u16 network_offsets[2]; + }; }; #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) diff --git a/kernel/bounds.c b/kernel/bounds.c index c5a9fcd2d622..29b2cd00df2c 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -19,7 +19,7 @@ int main(void) DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS); DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES); #ifdef CONFIG_SMP - DEFINE(NR_CPUS_BITS, bits_per(CONFIG_NR_CPUS)); + DEFINE(NR_CPUS_BITS, order_base_2(CONFIG_NR_CPUS)); #endif DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); #ifdef CONFIG_LRU_GEN diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 696bc55de8e8..1ea5ce5bb599 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2942,6 +2942,15 @@ bool __weak bpf_jit_supports_arena(void) return false; } +u64 __weak bpf_arch_uaddress_limit(void) +{ +#if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) + return TASK_SIZE; +#else + return 0; +#endif +} + /* Return TRUE if the JIT backend satisfies the following two conditions: * 1) JIT backend supports atomic_xchg() on pointer-sized words. * 2) Under the specific arch, the implementation of xchg() is the same diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 98188379d5c7..cb7ad1f795e1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18289,8 +18289,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) f = fdget(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { - verbose(env, "fd %d is not pointing to valid bpf_map\n", - insn[0].imm); + verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); return PTR_ERR(map); } @@ -19676,6 +19675,36 @@ static int do_misc_fixups(struct bpf_verifier_env *env) goto next_insn; } + /* Make it impossible to de-reference a userspace address */ + if (BPF_CLASS(insn->code) == BPF_LDX && + (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) { + struct bpf_insn *patch = &insn_buf[0]; + u64 uaddress_limit = bpf_arch_uaddress_limit(); + + if (!uaddress_limit) + goto next_insn; + + *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); + if (insn->off) + *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off); + *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32); + *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2); + *patch++ = *insn; + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0); + + cnt = patch - insn_buf; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; + } + /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 0066c8f6c154..d2dbe099286b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1277,8 +1277,12 @@ static bool kick_pool(struct worker_pool *pool) !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); - p->wake_cpu = cpumask_any_distribute(pool->attrs->__pod_cpumask); - get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; + int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask, + cpu_online_mask); + if (wake_cpu < nr_cpu_ids) { + p->wake_cpu = wake_cpu; + get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; + } } #endif wake_up_process(p); @@ -1594,6 +1598,15 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) if (off_cpu >= 0) total_cpus--; + /* If all CPUs of the wq get offline, use the default values */ + if (unlikely(!total_cpus)) { + for_each_node(node) + wq_node_nr_active(wq, node)->max = min_active; + + wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; + return; + } + for_each_node(node) { int node_cpus; @@ -1606,7 +1619,7 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) min_active, max_active); } - wq_node_nr_active(wq, NUMA_NO_NODE)->max = min_active; + wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; } /** diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c63a5fbf1f1c..291185f54ee4 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -375,7 +375,7 @@ config DEBUG_INFO_SPLIT Incompatible with older versions of ccache. config DEBUG_INFO_BTF - bool "Generate BTF typeinfo" + bool "Generate BTF type information" depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST depends on BPF_SYSCALL @@ -408,7 +408,8 @@ config PAHOLE_HAS_LANG_EXCLUDE using DEBUG_INFO_BTF_MODULES. config DEBUG_INFO_BTF_MODULES - def_bool y + bool "Generate BTF type information for kernel modules" + default y depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF help Generate compact split BTF type information for kernel modules. diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 68b45c82c37a..7bc2220fea80 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -1124,7 +1124,7 @@ static ssize_t extract_user_to_sg(struct iov_iter *iter, do { res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max, extraction_flags, &off); - if (res < 0) + if (res <= 0) goto failed; len = res; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index f00158234505..9404dd551dfd 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -478,6 +478,8 @@ static struct sk_buff *vlan_gro_receive(struct list_head *head, if (unlikely(!vhdr)) goto out; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = hlen; + type = vhdr->h_vlan_encapsulated_proto; ptype = gro_find_receive_by_type(type); diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 7431f89e897b..d7c35f55bd69 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -266,7 +266,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, if (skb->dev == p->dev && ether_addr_equal(src, addr)) return; - skb = skb_copy(skb, GFP_ATOMIC); + skb = pskb_copy(skb, GFP_ATOMIC); if (!skb) { DEV_STATS_INC(dev, tx_dropped); return; diff --git a/net/core/filter.c b/net/core/filter.c index 8adf95765cdd..ae5254f712c9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4360,10 +4360,12 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + u32 flags = ri->flags; struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (unlikely(!xdpf)) { @@ -4375,11 +4377,20 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - map = READ_ONCE(ri->map); - if (unlikely(map)) { + if (unlikely(flags & BPF_F_BROADCAST)) { + map = READ_ONCE(ri->map); + + /* The map pointer is cleared when the map is being torn + * down by bpf_clear_redirect_map() + */ + if (unlikely(!map)) { + err = -ENOENT; + break; + } + WRITE_ONCE(ri->map, NULL); err = dev_map_enqueue_multi(xdpf, dev, map, - ri->flags & BPF_F_EXCLUDE_INGRESS); + flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_enqueue(fwd, xdpf, dev); } @@ -4442,9 +4453,9 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, - void *fwd, - enum bpf_map_type map_type, u32 map_id) + struct bpf_prog *xdp_prog, void *fwd, + enum bpf_map_type map_type, u32 map_id, + u32 flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map; @@ -4454,11 +4465,20 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - map = READ_ONCE(ri->map); - if (unlikely(map)) { + if (unlikely(flags & BPF_F_BROADCAST)) { + map = READ_ONCE(ri->map); + + /* The map pointer is cleared when the map is being torn + * down by bpf_clear_redirect_map() + */ + if (unlikely(!map)) { + err = -ENOENT; + break; + } + WRITE_ONCE(ri->map, NULL); err = dev_map_redirect_multi(dev, skb, xdp_prog, map, - ri->flags & BPF_F_EXCLUDE_INGRESS); + flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_generic_redirect(fwd, skb, xdp_prog); } @@ -4495,9 +4515,11 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + u32 flags = ri->flags; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { @@ -4517,7 +4539,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, return 0; } - return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id); + return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id, flags); err: _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err); return err; diff --git a/net/core/gro.c b/net/core/gro.c index 83f35d99a682..c7901253a1a8 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -371,6 +371,7 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) const skb_frag_t *frag0; unsigned int headlen; + NAPI_GRO_CB(skb)->network_offset = 0; NAPI_GRO_CB(skb)->data_offset = 0; headlen = skb_headlen(skb); NAPI_GRO_CB(skb)->frag0 = skb->data; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b99127712e67..4096e679f61c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2123,11 +2123,17 @@ static inline int skb_alloc_rx_flag(const struct sk_buff *skb) struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { - int headerlen = skb_headroom(skb); - unsigned int size = skb_end_offset(skb) + skb->data_len; - struct sk_buff *n = __alloc_skb(size, gfp_mask, - skb_alloc_rx_flag(skb), NUMA_NO_NODE); + struct sk_buff *n; + unsigned int size; + int headerlen; + + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) + return NULL; + headerlen = skb_headroom(skb); + size = skb_end_offset(skb) + skb->data_len; + n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; @@ -2455,12 +2461,17 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask, skb_alloc_rx_flag(skb), - NUMA_NO_NODE); - int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; + struct sk_buff *n; + int oldheadroom; + + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) + return NULL; + oldheadroom = skb_headroom(skb); + n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); if (!n) return NULL; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 4d75ef9d24bf..fd20aae30be2 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1226,11 +1226,8 @@ static void sk_psock_verdict_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); - if (psock) { - read_lock_bh(&sk->sk_callback_lock); + if (psock) sk_psock_data_ready(sk, psock); - read_unlock_bh(&sk->sk_callback_lock); - } rcu_read_unlock(); } } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 55bd72997b31..fafb123f798b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1572,6 +1572,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) /* The above will be needed by the transport layer if there is one * immediately following this IP hdr. */ + NAPI_GRO_CB(skb)->inner_network_offset = off; /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1fe794967211..39229fd0601a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1473,7 +1473,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * by icmp_hdr(skb)->type. */ if (sk->sk_type == SOCK_RAW && - !inet_test_bit(HDRINCL, sk)) + !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index dcb11f22cbf2..4cb43401e0e0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -612,6 +612,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = 0; + fl4.fl4_icmp_code = 0; + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 420905be5f30..b32cf2eeeb41 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -532,7 +532,8 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct net *net = dev_net(skb->dev); int iif, sdif; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 3498dd1d0694..8721fe5beca2 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -471,6 +471,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *p; unsigned int ulen; int ret = 0; + int flush; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { @@ -504,13 +505,22 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, return p; } + flush = NAPI_GRO_CB(p)->flush; + + if (NAPI_GRO_CB(p)->flush_id != 1 || + NAPI_GRO_CB(p)->count != 1 || + !NAPI_GRO_CB(p)->is_atomic) + flush |= NAPI_GRO_CB(p)->flush_id; + else + NAPI_GRO_CB(p)->is_atomic = false; + /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ - if (ulen > ntohs(uh2->len)) { + if (ulen > ntohs(uh2->len) || flush) { pp = p; } else { if (NAPI_GRO_CB(skb)->is_flist) { @@ -718,7 +728,8 @@ EXPORT_SYMBOL(udp_gro_complete); INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index b41e35af69ea..c8b909a9904f 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -237,6 +237,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, goto out; skb_set_network_header(skb, off); + NAPI_GRO_CB(skb)->inner_network_offset = off; flush += ntohs(iph->payload_len) != skb->len - hlen; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1a4cccdd40c9..8f7aa8bac1e7 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -272,7 +272,8 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { - const struct ipv6hdr *iph = ipv6_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset); struct net *net = dev_net(skb->dev); int iif, sdif; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index bbd347de00b4..b41152dd4246 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -164,7 +164,8 @@ flush: INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) { - const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 39e487ccc468..8ba00ad433c2 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -127,6 +127,9 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, /* checksums verified by L2TP */ skb->ip_summed = CHECKSUM_NONE; + /* drop outer flow-hash */ + skb_clear_hash(skb); + skb_dst_drop(skb); nf_reset_ct(skb); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7e74b812e366..965eb69dc5de 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3723,6 +3723,9 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT); mptcp_subflow_early_fallback(msk, subflow); } + + WRITE_ONCE(msk->write_seq, subflow->idsn); + WRITE_ONCE(msk->snd_nxt, subflow->idsn); if (likely(!__mptcp_check_fallback(msk))) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE); diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index f4a38bd6a7e0..bfb7758063f3 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -77,13 +77,15 @@ EXPORT_SYMBOL_GPL(nsh_pop); static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { + unsigned int outer_hlen, mac_len, nsh_len; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; - unsigned int nsh_len, mac_len; - __be16 proto; + __be16 outer_proto, proto; skb_reset_network_header(skb); + outer_proto = skb->protocol; + outer_hlen = skb_mac_header_len(skb); mac_len = skb->mac_len; if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) @@ -113,10 +115,10 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, } for (skb = segs; skb; skb = skb->next) { - skb->protocol = htons(ETH_P_NSH); - __skb_push(skb, nsh_len); - skb->mac_header = mac_offset; - skb->network_header = skb->mac_header + mac_len; + skb->protocol = outer_proto; + __skb_push(skb, nsh_len + outer_hlen); + skb_reset_mac_header(skb); + skb_set_network_header(skb, outer_hlen); skb->mac_len = mac_len; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 0af4642aeec4..1539d315afe7 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -119,18 +119,13 @@ struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *lo switch (srx->transport.family) { case AF_INET: if (peer->srx.transport.sin.sin_port != - srx->transport.sin.sin_port || - peer->srx.transport.sin.sin_addr.s_addr != - srx->transport.sin.sin_addr.s_addr) + srx->transport.sin.sin_port) goto not_found; break; #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: if (peer->srx.transport.sin6.sin6_port != - srx->transport.sin6.sin6_port || - memcmp(&peer->srx.transport.sin6.sin6_addr, - &srx->transport.sin6.sin6_addr, - sizeof(struct in6_addr)) != 0) + srx->transport.sin6.sin6_port) goto not_found; break; #endif diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index f2701068ed9e..6716c021a532 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -19,7 +19,7 @@ static int none_init_connection_security(struct rxrpc_connection *conn, */ static struct rxrpc_txbuf *none_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp) { - return rxrpc_alloc_data_txbuf(call, min_t(size_t, remain, RXRPC_JUMBO_DATALEN), 0, gfp); + return rxrpc_alloc_data_txbuf(call, min_t(size_t, remain, RXRPC_JUMBO_DATALEN), 1, gfp); } static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index f1a68270862d..48a1475e6b06 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -155,7 +155,7 @@ static struct rxrpc_txbuf *rxkad_alloc_txbuf(struct rxrpc_call *call, size_t rem switch (call->conn->security_level) { default: space = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); - return rxrpc_alloc_data_txbuf(call, space, 0, gfp); + return rxrpc_alloc_data_txbuf(call, space, 1, gfp); case RXRPC_SECURITY_AUTH: shdr = sizeof(struct rxkad_level1_hdr); break; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index e0679658d9de..c3913d8a50d3 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -21,20 +21,20 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_ { struct rxrpc_wire_header *whdr; struct rxrpc_txbuf *txb; - size_t total, hoff = 0; + size_t total, hoff; void *buf; txb = kmalloc(sizeof(*txb), gfp); if (!txb) return NULL; - if (data_align) - hoff = round_up(sizeof(*whdr), data_align) - sizeof(*whdr); + hoff = round_up(sizeof(*whdr), data_align) - sizeof(*whdr); total = hoff + sizeof(*whdr) + data_size; + data_align = umax(data_align, L1_CACHE_BYTES); mutex_lock(&call->conn->tx_data_alloc_lock); - buf = __page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp, - ~(data_align - 1) & ~(L1_CACHE_BYTES - 1)); + buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp, + data_align); mutex_unlock(&call->conn->tx_data_alloc_lock); if (!buf) { kfree(txb); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index bb9b747d58a1..ce18716491c8 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2664,6 +2664,7 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work) .xprtsec = { .policy = RPC_XPRTSEC_NONE, }, + .stats = upper_clnt->cl_stats, }; unsigned int pflags = current->flags; struct rpc_clnt *lower_clnt; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 5c9fd4791c4b..76284fc538eb 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -142,9 +142,9 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; - *buf = NULL; if (skb_has_frag_list(frag) && __skb_linearize(frag)) goto err; + *buf = NULL; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; @@ -156,6 +156,11 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (!head) goto err; + /* Either the input skb ownership is transferred to headskb + * or the input skb is freed, clear the reference to avoid + * bad access on error path. + */ + *buf = NULL; if (skb_try_coalesce(head, frag, &headstolen, &delta)) { kfree_skb_partial(frag, headstolen); } else { @@ -179,7 +184,6 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) *headbuf = NULL; return 1; } - *buf = NULL; return 0; err: kfree_skb(*buf); diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 39ad96a18123..edcd26106557 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -205,6 +205,9 @@ __weak noinline struct file *bpf_testmod_return_ptr(int arg) case 5: return (void *)~(1ull << 30); /* trigger extable */ case 6: return &f; /* valid addr */ case 7: return (void *)((long)&f | 1); /* kernel tricks */ +#ifdef CONFIG_X86_64 + case 8: return (void *)VSYSCALL_ADDR; /* vsyscall page address */ +#endif default: return NULL; } } diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c index eef816b80993..ca917c71ff60 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_init.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c @@ -84,6 +84,18 @@ static struct vm_gic vm_gic_create_with_vcpus(uint32_t gic_dev_type, return v; } +static struct vm_gic vm_gic_create_barebones(uint32_t gic_dev_type) +{ + struct vm_gic v; + + v.gic_dev_type = gic_dev_type; + v.vm = vm_create_barebones(); + v.gic_fd = kvm_create_device(v.vm, gic_dev_type); + + return v; +} + + static void vm_gic_destroy(struct vm_gic *v) { close(v->gic_fd); @@ -357,6 +369,40 @@ static void test_vcpus_then_vgic(uint32_t gic_dev_type) vm_gic_destroy(&v); } +#define KVM_VGIC_V2_ATTR(offset, cpu) \ + (FIELD_PREP(KVM_DEV_ARM_VGIC_OFFSET_MASK, offset) | \ + FIELD_PREP(KVM_DEV_ARM_VGIC_CPUID_MASK, cpu)) + +#define GIC_CPU_CTRL 0x00 + +static void test_v2_uaccess_cpuif_no_vcpus(void) +{ + struct vm_gic v; + u64 val = 0; + int ret; + + v = vm_gic_create_barebones(KVM_DEV_TYPE_ARM_VGIC_V2); + subtest_dist_rdist(&v); + + ret = __kvm_has_device_attr(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS, + KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0)); + TEST_ASSERT(ret && errno == EINVAL, + "accessed non-existent CPU interface, want errno: %i", + EINVAL); + ret = __kvm_device_attr_get(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS, + KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0), &val); + TEST_ASSERT(ret && errno == EINVAL, + "accessed non-existent CPU interface, want errno: %i", + EINVAL); + ret = __kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS, + KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0), &val); + TEST_ASSERT(ret && errno == EINVAL, + "accessed non-existent CPU interface, want errno: %i", + EINVAL); + + vm_gic_destroy(&v); +} + static void test_v3_new_redist_regions(void) { struct kvm_vcpu *vcpus[NR_VCPUS]; @@ -675,6 +721,9 @@ void run_tests(uint32_t gic_dev_type) test_vcpus_then_vgic(gic_dev_type); test_vgic_then_vcpus(gic_dev_type); + if (VGIC_DEV_IS_V2(gic_dev_type)) + test_v2_uaccess_cpuif_no_vcpus(); + if (VGIC_DEV_IS_V3(gic_dev_type)) { test_v3_new_redist_regions(); test_v3_typer_accesses(); |