diff options
1190 files changed, 19013 insertions, 11933 deletions
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html index 6c06e10bd04b..f5120a00f511 100644 --- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html +++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html @@ -380,31 +380,26 @@ and therefore need no protection. as follows: <pre> - 1 unsigned long gpnum; - 2 unsigned long completed; + 1 unsigned long gp_seq; </pre> <p>RCU grace periods are numbered, and -the <tt>->gpnum</tt> field contains the number of the grace -period that started most recently. -The <tt>->completed</tt> field contains the number of the -grace period that completed most recently. -If the two fields are equal, the RCU grace period that most recently -started has already completed, and therefore the corresponding -flavor of RCU is idle. -If <tt>->gpnum</tt> is one greater than <tt>->completed</tt>, -then <tt>->gpnum</tt> gives the number of the current RCU -grace period, which has not yet completed. -Any other combination of values indicates that something is broken. -These two fields are protected by the root <tt>rcu_node</tt>'s +the <tt>->gp_seq</tt> field contains the current grace-period +sequence number. +The bottom two bits are the state of the current grace period, +which can be zero for not yet started or one for in progress. +In other words, if the bottom two bits of <tt>->gp_seq</tt> are +zero, the corresponding flavor of RCU is idle. +Any other value in the bottom two bits indicates that something is broken. +This field is protected by the root <tt>rcu_node</tt> structure's <tt>->lock</tt> field. -</p><p>There are <tt>->gpnum</tt> and <tt>->completed</tt> fields +</p><p>There are <tt>->gp_seq</tt> fields in the <tt>rcu_node</tt> and <tt>rcu_data</tt> structures as well. The fields in the <tt>rcu_state</tt> structure represent the -most current values, and those of the other structures are compared -in order to detect the start of a new grace period in a distributed +most current value, and those of the other structures are compared +in order to detect the beginnings and ends of grace periods in a distributed fashion. The values flow from <tt>rcu_state</tt> to <tt>rcu_node</tt> (down the tree from the root to the leaves) to <tt>rcu_data</tt>. @@ -512,27 +507,47 @@ than to be heisenbugged out of existence. as follows: <pre> - 1 unsigned long gpnum; - 2 unsigned long completed; + 1 unsigned long gp_seq; + 2 unsigned long gp_seq_needed; </pre> -<p>These fields are the counterparts of the fields of the same name in -the <tt>rcu_state</tt> structure. -They each may lag up to one behind their <tt>rcu_state</tt> -counterparts. -If a given <tt>rcu_node</tt> structure's <tt>->gpnum</tt> and -<tt>->complete</tt> fields are equal, then this <tt>rcu_node</tt> +<p>The <tt>rcu_node</tt> structures' <tt>->gp_seq</tt> fields are +the counterparts of the field of the same name in the <tt>rcu_state</tt> +structure. +They each may lag up to one step behind their <tt>rcu_state</tt> +counterpart. +If the bottom two bits of a given <tt>rcu_node</tt> structure's +<tt>->gp_seq</tt> field is zero, then this <tt>rcu_node</tt> structure believes that RCU is idle. -Otherwise, as with the <tt>rcu_state</tt> structure, -the <tt>->gpnum</tt> field will be one greater than the -<tt>->complete</tt> fields, with <tt>->gpnum</tt> -indicating which grace period this <tt>rcu_node</tt> believes -is still being waited for. +</p><p>The <tt>>gp_seq</tt> field of each <tt>rcu_node</tt> +structure is updated at the beginning and the end +of each grace period. + +<p>The <tt>->gp_seq_needed</tt> fields record the +furthest-in-the-future grace period request seen by the corresponding +<tt>rcu_node</tt> structure. The request is considered fulfilled when +the value of the <tt>->gp_seq</tt> field equals or exceeds that of +the <tt>->gp_seq_needed</tt> field. -</p><p>The <tt>>gpnum</tt> field of each <tt>rcu_node</tt> -structure is updated at the beginning -of each grace period, and the <tt>->completed</tt> fields are -updated at the end of each grace period. +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Suppose that this <tt>rcu_node</tt> structure doesn't see + a request for a very long time. + Won't wrapping of the <tt>->gp_seq</tt> field cause + problems? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + No, because if the <tt>->gp_seq_needed</tt> field lags behind the + <tt>->gp_seq</tt> field, the <tt>->gp_seq_needed</tt> field + will be updated at the end of the grace period. + Modulo-arithmetic comparisons therefore will always get the + correct answer, even with wrapping. +</font></td></tr> +<tr><td> </td></tr> +</table> <h5>Quiescent-State Tracking</h5> @@ -626,9 +641,8 @@ normal and expedited grace periods, respectively. </ol> <p><font color="ffffff">So the locking is absolutely required in - order to coordinate - clearing of the bits with the grace-period numbers in - <tt>->gpnum</tt> and <tt>->completed</tt>. + order to coordinate clearing of the bits with updating of the + grace-period sequence number in <tt>->gp_seq</tt>. </font></td></tr> <tr><td> </td></tr> </table> @@ -1038,15 +1052,15 @@ out any <tt>rcu_data</tt> structure for which this flag is not set. as follows: <pre> - 1 unsigned long completed; - 2 unsigned long gpnum; + 1 unsigned long gp_seq; + 2 unsigned long gp_seq_needed; 3 bool cpu_no_qs; 4 bool core_needs_qs; 5 bool gpwrap; 6 unsigned long rcu_qs_ctr_snap; </pre> -<p>The <tt>completed</tt> and <tt>gpnum</tt> +<p>The <tt>->gp_seq</tt> and <tt>->gp_seq_needed</tt> fields are the counterparts of the fields of the same name in the <tt>rcu_state</tt> and <tt>rcu_node</tt> structures. They may each lag up to one behind their <tt>rcu_node</tt> @@ -1054,15 +1068,9 @@ counterparts, but in <tt>CONFIG_NO_HZ_IDLE</tt> and <tt>CONFIG_NO_HZ_FULL</tt> kernels can lag arbitrarily far behind for CPUs in dyntick-idle mode (but these counters will catch up upon exit from dyntick-idle mode). -If a given <tt>rcu_data</tt> structure's <tt>->gpnum</tt> and -<tt>->complete</tt> fields are equal, then this <tt>rcu_data</tt> +If the lower two bits of a given <tt>rcu_data</tt> structure's +<tt>->gp_seq</tt> are zero, then this <tt>rcu_data</tt> structure believes that RCU is idle. -Otherwise, as with the <tt>rcu_state</tt> and <tt>rcu_node</tt> -structure, -the <tt>->gpnum</tt> field will be one greater than the -<tt>->complete</tt> fields, with <tt>->gpnum</tt> -indicating which grace period this <tt>rcu_data</tt> believes -is still being waited for. <table> <tr><th> </th></tr> @@ -1070,13 +1078,13 @@ is still being waited for. <tr><td> All this replication of the grace period numbers can only cause massive confusion. - Why not just keep a global pair of counters and be done with it??? + Why not just keep a global sequence number and be done with it??? </td></tr> <tr><th align="left">Answer:</th></tr> <tr><td bgcolor="#ffffff"><font color="ffffff"> - Because if there was only a single global pair of grace-period + Because if there was only a single global sequence numbers, there would need to be a single global lock to allow - safely accessing and updating them. + safely accessing and updating it. And if we are not going to have a single global lock, we need to carefully manage the numbers on a per-node basis. Recall from the answer to a previous Quick Quiz that the consequences @@ -1091,8 +1099,8 @@ CPU has not yet passed through a quiescent state, while the <tt>->core_needs_qs</tt> flag indicates that the RCU core needs a quiescent state from the corresponding CPU. The <tt>->gpwrap</tt> field indicates that the corresponding -CPU has remained idle for so long that the <tt>completed</tt> -and <tt>gpnum</tt> counters are in danger of overflow, which +CPU has remained idle for so long that the +<tt>gp_seq</tt> counter is in danger of overflow, which will cause the CPU to disregard the values of its counters on its next exit from idle. Finally, the <tt>rcu_qs_ctr_snap</tt> field is used to detect @@ -1130,10 +1138,10 @@ The CPU advances the callbacks in its <tt>rcu_data</tt> structure whenever it notices that another RCU grace period has completed. The CPU detects the completion of an RCU grace period by noticing that the value of its <tt>rcu_data</tt> structure's -<tt>->completed</tt> field differs from that of its leaf +<tt>->gp_seq</tt> field differs from that of its leaf <tt>rcu_node</tt> structure. Recall that each <tt>rcu_node</tt> structure's -<tt>->completed</tt> field is updated at the end of each +<tt>->gp_seq</tt> field is updated at the beginnings and ends of each grace period. <p> diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html index 8651b0b4fd79..a346ce0116eb 100644 --- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html +++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html @@ -357,7 +357,7 @@ parts, starting in this section with the various phases of grace-period initialization. <p>The first ordering-related grace-period initialization action is to -increment the <tt>rcu_state</tt> structure's <tt>->gpnum</tt> +advance the <tt>rcu_state</tt> structure's <tt>->gp_seq</tt> grace-period-number counter, as shown below: </p><p><img src="TreeRCU-gp-init-1.svg" alt="TreeRCU-gp-init-1.svg" width="75%"> @@ -388,7 +388,7 @@ its last CPU and if the next <tt>rcu_node</tt> structure has no online CPUs). <p>The final <tt>rcu_gp_init()</tt> pass through the <tt>rcu_node</tt> tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's -<tt>->gpnum</tt> field to the newly incremented value from the +<tt>->gp_seq</tt> field to the newly advanced value from the <tt>rcu_state</tt> structure, as shown in the following diagram. </p><p><img src="TreeRCU-gp-init-3.svg" alt="TreeRCU-gp-init-1.svg" width="75%"> @@ -398,9 +398,9 @@ tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's to notice that a new grace period has started, as described in the next section. But because the grace-period kthread started the grace period at the -root (with the increment of the <tt>rcu_state</tt> structure's -<tt>->gpnum</tt> field) before setting each leaf <tt>rcu_node</tt> -structure's <tt>->gpnum</tt> field, each CPU's observation of +root (with the advancing of the <tt>rcu_state</tt> structure's +<tt>->gp_seq</tt> field) before setting each leaf <tt>rcu_node</tt> +structure's <tt>->gp_seq</tt> field, each CPU's observation of the start of the grace period will happen after the actual start of the grace period. @@ -466,7 +466,7 @@ section that the grace period must wait on. <tr><td> But a RCU read-side critical section might have started after the beginning of the grace period - (the <tt>->gpnum++</tt> from earlier), so why should + (the advancing of <tt>->gp_seq</tt> from earlier), so why should the grace period wait on such a critical section? </td></tr> <tr><th align="left">Answer:</th></tr> @@ -609,10 +609,8 @@ states outstanding from other CPUs. <h4><a name="Grace-Period Cleanup">Grace-Period Cleanup</a></h4> <p>Grace-period cleanup first scans the <tt>rcu_node</tt> tree -breadth-first setting all the <tt>->completed</tt> fields equal -to the number of the newly completed grace period, then it sets -the <tt>rcu_state</tt> structure's <tt>->completed</tt> field, -again to the number of the newly completed grace period. +breadth-first advancing all the <tt>->gp_seq</tt> fields, then it +advances the <tt>rcu_state</tt> structure's <tt>->gp_seq</tt> field. The ordering effects are shown below: </p><p><img src="TreeRCU-gp-cleanup.svg" alt="TreeRCU-gp-cleanup.svg" width="75%"> @@ -634,7 +632,7 @@ grace-period cleanup is complete, the next grace period can begin. CPU has reported its quiescent state, but it may be some milliseconds before RCU becomes aware of this. The latest reasonable candidate is once the <tt>rcu_state</tt> - structure's <tt>->completed</tt> field has been updated, + structure's <tt>->gp_seq</tt> field has been updated, but it is quite possible that some CPUs have already completed phase two of their updates by that time. In short, if you are going to work with RCU, you need to @@ -647,7 +645,7 @@ grace-period cleanup is complete, the next grace period can begin. <h4><a name="Callback Invocation">Callback Invocation</a></h4> <p>Once a given CPU's leaf <tt>rcu_node</tt> structure's -<tt>->completed</tt> field has been updated, that CPU can begin +<tt>->gp_seq</tt> field has been updated, that CPU can begin invoking its RCU callbacks that were waiting for this grace period to end. These callbacks are identified by <tt>rcu_advance_cbs()</tt>, diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg index 754f426b297a..bf84fbab27ee 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg @@ -384,11 +384,11 @@ inkscape:window-height="1144" id="namedview208" showgrid="true" - inkscape:zoom="0.70710678" - inkscape:cx="617.89017" - inkscape:cy="542.52419" - inkscape:window-x="86" - inkscape:window-y="28" + inkscape:zoom="0.78716603" + inkscape:cx="513.06403" + inkscape:cy="623.1214" + inkscape:window-x="102" + inkscape:window-y="38" inkscape:window-maximized="0" inkscape:current-layer="g3188-3" fit-margin-top="5" @@ -417,13 +417,15 @@ id="g3188"> <text xml:space="preserve" - x="3199.1516" + x="3145.9592" y="13255.592" font-style="normal" font-weight="bold" font-size="192" id="text202" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->completed = ->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3143">rcu_seq_end(&rnp->gp_seq)</tspan></text> <g id="g3107" transform="translate(947.90548,11584.029)"> @@ -502,13 +504,15 @@ </g> <text xml:space="preserve" - x="5324.5371" - y="15414.598" + x="5264.4731" + y="15428.84" font-style="normal" font-weight="bold" font-size="192" - id="text202-753" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-7" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-5">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g style="fill:none;stroke-width:0.025in" @@ -547,15 +551,6 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-6-0">Leaf</tspan></text> - <text - xml:space="preserve" - x="7479.5796" - y="17699.943" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-9" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> <path sodipodi:nodetypes="cc" inkscape:connector-curvature="0" @@ -566,15 +561,6 @@ style="fill:none;stroke-width:0.025in" transform="translate(-737.93887,7732.6672)" id="g3188-3"> - <text - xml:space="preserve" - x="3225.7478" - y="13175.802" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-60" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp->completed =</text> <g id="g3107-62" transform="translate(947.90548,11584.029)"> @@ -607,15 +593,6 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-7">Root</tspan></text> - <text - xml:space="preserve" - x="3225.7478" - y="13390.038" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-60-3" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"> rnp->completed</text> <flowRoot xml:space="preserve" id="flowRoot3356" @@ -627,7 +604,18 @@ height="63.63961" x="332.34018" y="681.87292" /></flowRegion><flowPara - id="flowPara3362" /></flowRoot> </g> + id="flowPara3362" /></flowRoot> <text + xml:space="preserve" + x="3156.6121" + y="13317.754" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-6" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-0">rcu_seq_end(&rsp->gp_seq)</tspan></text> + </g> <g style="fill:none;stroke-width:0.025in" transform="translate(-858.40227,7769.0342)" @@ -859,6 +847,17 @@ id="path3414-8-3-6-6" inkscape:connector-curvature="0" sodipodi:nodetypes="cc" /> + <text + xml:space="preserve" + x="7418.769" + y="17646.104" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-70" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-93">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g transform="translate(-1642.5377,-11611.245)" @@ -887,13 +886,15 @@ </g> <text xml:space="preserve" - x="5327.3057" + x="5274.1133" y="15428.84" font-style="normal" font-weight="bold" font-size="192" id="text202-36" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g transform="translate(-151.71746,-11647.612)" @@ -972,13 +973,15 @@ id="tspan3104-6-5-6-0-92">Leaf</tspan></text> <text xml:space="preserve" - x="7486.4907" - y="17670.119" + x="7408.5918" + y="17619.504" font-style="normal" font-weight="bold" font-size="192" - id="text202-6" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-2" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-9">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g transform="translate(-6817.1997,-11647.612)" @@ -1019,13 +1022,15 @@ id="tspan3104-6-5-6-0-1">Leaf</tspan></text> <text xml:space="preserve" - x="7474.1382" - y="17688.926" + x="7416.8003" + y="17619.504" font-style="normal" font-weight="bold" font-size="192" - id="text202-5" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-3" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-56">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <path style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)" @@ -1059,15 +1064,6 @@ id="path3414-8-3-6" inkscape:connector-curvature="0" sodipodi:nodetypes="cc" /> - <text - xml:space="preserve" - x="7318.9653" - y="6031.6353" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-2" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> <g style="fill:none;stroke-width:0.025in" id="g4504-3-9" @@ -1123,4 +1119,15 @@ id="path3134-9-0-3-5" d="m 6875.6003,15833.906 1595.7755,0" style="fill:none;stroke:#969696;stroke-width:53.19251633;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send-36)" /> + <text + xml:space="preserve" + x="7275.2612" + y="5971.8916" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-1" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-2">rcu_seq_end(&rnp->gp_seq)</tspan></text> </svg> diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg index 0161262904ec..8c207550818f 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg @@ -272,13 +272,13 @@ inkscape:window-height="1144" id="namedview208" showgrid="true" - inkscape:zoom="0.70710678" - inkscape:cx="617.89019" - inkscape:cy="636.57143" - inkscape:window-x="697" + inkscape:zoom="2.6330492" + inkscape:cx="524.82797" + inkscape:cy="519.31194" + inkscape:window-x="79" inkscape:window-y="28" inkscape:window-maximized="0" - inkscape:current-layer="svg2" + inkscape:current-layer="g3188" fit-margin-top="5" fit-margin-right="5" fit-margin-left="5" @@ -305,13 +305,15 @@ id="g3188"> <text xml:space="preserve" - x="3305.5364" + x="3119.363" y="13255.592" font-style="normal" font-weight="bold" font-size="192" id="text202" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp->gpnum++</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3071">rcu_seq_start(rsp->gp_seq)</tspan></text> <g id="g3107" transform="translate(947.90548,11584.029)"> diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg index de6ecc51b00e..d24d7d555dbc 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg @@ -19,7 +19,7 @@ id="svg2" version="1.1" inkscape:version="0.48.4 r9939" - sodipodi:docname="TreeRCU-gp-init-2.svg"> + sodipodi:docname="TreeRCU-gp-init-3.svg"> <metadata id="metadata212"> <rdf:RDF> @@ -257,18 +257,22 @@ inkscape:window-width="1087" inkscape:window-height="1144" id="namedview208" - showgrid="false" - inkscape:zoom="0.70710678" + showgrid="true" + inkscape:zoom="0.68224756" inkscape:cx="617.89019" inkscape:cy="625.84293" - inkscape:window-x="697" + inkscape:window-x="54" inkscape:window-y="28" inkscape:window-maximized="0" - inkscape:current-layer="svg2" + inkscape:current-layer="g3153" fit-margin-top="5" fit-margin-right="5" fit-margin-left="5" - fit-margin-bottom="5" /> + fit-margin-bottom="5"> + <inkscape:grid + type="xygrid" + id="grid3090" /> + </sodipodi:namedview> <path sodipodi:nodetypes="cccccccccccccccccccccccc" inkscape:connector-curvature="0" @@ -281,13 +285,13 @@ id="g3188"> <text xml:space="preserve" - x="3305.5364" + x="3145.9592" y="13255.592" font-style="normal" font-weight="bold" font-size="192" id="text202" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->gp_seq = rsp->gp_seq</text> <g id="g3107" transform="translate(947.90548,11584.029)"> @@ -366,13 +370,13 @@ </g> <text xml:space="preserve" - x="5392.3345" - y="15407.104" + x="5253.6904" + y="15407.032" font-style="normal" font-weight="bold" font-size="192" id="text202-6" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g style="fill:none;stroke-width:0.025in" @@ -413,13 +417,13 @@ id="tspan3104-6-5-6-0">Leaf</tspan></text> <text xml:space="preserve" - x="7536.4883" - y="17640.934" + x="7415.4365" + y="17670.572" font-style="normal" font-weight="bold" font-size="192" id="text202-9" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-1642.5375,-11610.962)" @@ -448,13 +452,13 @@ </g> <text xml:space="preserve" - x="5378.4146" - y="15436.927" + x="5258.0688" + y="15412.313" font-style="normal" font-weight="bold" font-size="192" id="text202-3" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-151.71726,-11647.329)" @@ -533,13 +537,13 @@ id="tspan3104-6-5-6-0-92">Leaf</tspan></text> <text xml:space="preserve" - x="7520.1294" - y="17673.639" + x="7405.2607" + y="17670.572" font-style="normal" font-weight="bold" font-size="192" id="text202-35" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-6817.1998,-11647.329)" @@ -580,13 +584,13 @@ id="tspan3104-6-5-6-0-1">Leaf</tspan></text> <text xml:space="preserve" - x="7521.4663" - y="17666.062" + x="7413.4688" + y="17670.566" font-style="normal" font-weight="bold" font-size="192" id="text202-75" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <path style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)" @@ -622,11 +626,11 @@ sodipodi:nodetypes="cc" /> <text xml:space="preserve" - x="7370.856" - y="5997.5972" + x="7271.9297" + y="6023.2412" font-style="normal" font-weight="bold" font-size="192" id="text202-62" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </svg> diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg index b13b7b01bb3a..acd73c7ad0f4 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg @@ -1070,13 +1070,13 @@ inkscape:window-height="1144" id="namedview208" showgrid="true" - inkscape:zoom="0.6004608" - inkscape:cx="826.65969" - inkscape:cy="483.3047" - inkscape:window-x="66" - inkscape:window-y="28" + inkscape:zoom="0.81932583" + inkscape:cx="840.45848" + inkscape:cy="5052.4242" + inkscape:window-x="787" + inkscape:window-y="24" inkscape:window-maximized="0" - inkscape:current-layer="svg2" + inkscape:current-layer="g4" fit-margin-top="5" fit-margin-right="5" fit-margin-left="5" @@ -1543,15 +1543,6 @@ style="fill:none;stroke-width:0.025in" transform="translate(1749.0282,658.72243)" id="g3188"> - <text - xml:space="preserve" - x="3305.5364" - y="13255.592" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-5" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp->gpnum++</text> <g id="g3107-62" transform="translate(947.90548,11584.029)"> @@ -1584,6 +1575,17 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-7">Root</tspan></text> + <text + xml:space="preserve" + x="3137.9988" + y="13271.316" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-626" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3071">rcu_seq_start(rsp->gp_seq)</tspan></text> </g> <rect ry="0" @@ -2318,15 +2320,6 @@ style="fill:none;stroke-width:0.025in" transform="translate(1739.0986,17188.625)" id="g3188-6"> - <text - xml:space="preserve" - x="3305.5364" - y="13255.592" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-1" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->gpnum = rsp->gpnum</text> <g id="g3107-5" transform="translate(947.90548,11584.029)"> @@ -2359,6 +2352,15 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-1">Root</tspan></text> + <text + xml:space="preserve" + x="3147.9268" + y="13240.524" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-1" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g style="fill:none;stroke-width:0.025in" @@ -2387,13 +2389,13 @@ </g> <text xml:space="preserve" - x="5392.3345" - y="15407.104" + x="5263.1094" + y="15411.646" font-style="normal" font-weight="bold" font-size="192" - id="text202-6-7" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + id="text202-92" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g style="fill:none;stroke-width:0.025in" @@ -2434,13 +2436,13 @@ id="tspan3104-6-5-6-0-94">Leaf</tspan></text> <text xml:space="preserve" - x="7536.4883" - y="17640.934" + x="7417.4053" + y="17655.502" font-style="normal" font-weight="bold" font-size="192" - id="text202-9" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + id="text202-759" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-2353.8462,17224.992)" @@ -2469,13 +2471,13 @@ </g> <text xml:space="preserve" - x="5378.4146" - y="15436.927" + x="5246.1548" + y="15411.648" font-style="normal" font-weight="bold" font-size="192" - id="text202-3" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + id="text202-87" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-863.02613,17188.625)" @@ -2554,13 +2556,13 @@ id="tspan3104-6-5-6-0-92-6">Leaf</tspan></text> <text xml:space="preserve" - x="7520.1294" - y="17673.639" + x="7433.8257" + y="17682.098" font-style="normal" font-weight="bold" font-size="192" - id="text202-35" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + id="text202-2" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-7528.5085,17188.625)" @@ -2601,13 +2603,13 @@ id="tspan3104-6-5-6-0-1-8">Leaf</tspan></text> <text xml:space="preserve" - x="7521.4663" - y="17666.062" + x="7415.4404" + y="17682.098" font-style="normal" font-weight="bold" font-size="192" - id="text202-75-1" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + id="text202-0" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <path style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)" @@ -2641,15 +2643,6 @@ id="path3414-8-3-6-4" inkscape:connector-curvature="0" sodipodi:nodetypes="cc" /> - <text - xml:space="preserve" - x="6659.5469" - y="34833.551" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-62" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> <path sodipodi:nodetypes="ccc" inkscape:connector-curvature="0" @@ -3844,7 +3837,7 @@ font-weight="bold" font-size="192" id="text202-6-6-5" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gp_seq</text> <text xml:space="preserve" x="5035.4155" @@ -4284,15 +4277,6 @@ style="fill:none;stroke-width:0.025in" transform="translate(1874.038,53203.538)" id="g3188-7"> - <text - xml:space="preserve" - x="3199.1516" - y="13255.592" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-82" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->completed = ->gpnum</text> <g id="g3107-53" transform="translate(947.90548,11584.029)"> @@ -4325,6 +4309,17 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-19">Root</tspan></text> + <text + xml:space="preserve" + x="3175.896" + y="13240.11" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-3" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <rect ry="0" @@ -4371,13 +4366,15 @@ </g> <text xml:space="preserve" - x="5324.5371" - y="15414.598" + x="5264.4829" + y="15411.231" font-style="normal" font-weight="bold" font-size="192" - id="text202-753" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-7" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-5">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g style="fill:none;stroke-width:0.025in" @@ -4412,30 +4409,12 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-6-0-4">Leaf</tspan></text> - <text - xml:space="preserve" - x="10084.225" - y="70903.312" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-9-0" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> <path sodipodi:nodetypes="ccc" inkscape:connector-curvature="0" id="path3134-9-0-3-9" d="m 6315.6122,72629.054 -20.9533,8108.684 1648.968,0" style="fill:none;stroke:#969696;stroke-width:53.19251251;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send)" /> - <text - xml:space="preserve" - x="5092.4683" - y="74111.672" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-60" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rsp->completed =</text> <g style="fill:none;stroke-width:0.025in" id="g3107-62-6" @@ -4469,15 +4448,6 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-7-7">Root</tspan></text> - <text - xml:space="preserve" - x="5092.4683" - y="74325.906" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-60-3" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"> rnp->completed</text> <g style="fill:none;stroke-width:0.025in" transform="translate(1746.2528,60972.572)" @@ -4736,13 +4706,15 @@ </g> <text xml:space="preserve" - x="5327.3057" - y="15428.84" + x="5274.1216" + y="15411.231" font-style="normal" font-weight="bold" font-size="192" id="text202-36" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-6">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g transform="translate(-728.08545,53203.538)" @@ -4821,13 +4793,15 @@ id="tspan3104-6-5-6-0-92-5">Leaf</tspan></text> <text xml:space="preserve" - x="7486.4907" - y="17670.119" + x="7435.1987" + y="17708.281" font-style="normal" font-weight="bold" font-size="192" - id="text202-6-2" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-9" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-1">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g transform="translate(-7393.5687,53203.538)" @@ -4868,13 +4842,15 @@ id="tspan3104-6-5-6-0-1-5">Leaf</tspan></text> <text xml:space="preserve" - x="7474.1382" - y="17688.926" + x="7416.8125" + y="17708.281" font-style="normal" font-weight="bold" font-size="192" - id="text202-5-1" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-35" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-62">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <path style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)" @@ -4908,15 +4884,6 @@ id="path3414-8-3-6-67" inkscape:connector-curvature="0" sodipodi:nodetypes="cc" /> - <text - xml:space="preserve" - x="6742.6001" - y="70882.617" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-2" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> <g style="fill:none;stroke-width:0.025in" id="g4504-3-9-6" @@ -5131,5 +5098,47 @@ font-size="192" id="text202-7-9-6-6-7" style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_do_batch()</text> + <text + xml:space="preserve" + x="6698.9019" + y="70885.211" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-2" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-7">rcu_seq_end(&rnp->gp_seq)</tspan></text> + <text + xml:space="preserve" + x="10023.457" + y="70885.234" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-0" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-9">rcu_seq_end(&rnp->gp_seq)</tspan></text> + <text + xml:space="preserve" + x="5023.3389" + y="74209.773" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-36" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-0">rcu_seq_end(&rsp->gp_seq)</tspan></text> + <text + xml:space="preserve" + x="6562.5884" + y="34870.727" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-3" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> </svg> diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg index de3992f4cbe1..149bec2a4493 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg @@ -300,13 +300,13 @@ inkscape:window-height="1144" id="namedview208" showgrid="true" - inkscape:zoom="0.70710678" - inkscape:cx="616.47598" - inkscape:cy="595.41964" - inkscape:window-x="813" + inkscape:zoom="0.96484375" + inkscape:cx="507.0191" + inkscape:cy="885.62207" + inkscape:window-x="47" inkscape:window-y="28" inkscape:window-maximized="0" - inkscape:current-layer="g4405" + inkscape:current-layer="g3115" fit-margin-top="5" fit-margin-right="5" fit-margin-left="5" @@ -710,7 +710,7 @@ font-weight="bold" font-size="192" id="text202-6-6" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gp_seq</text> <text xml:space="preserve" x="5035.4155" diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 4259f95c3261..f99cf11b314b 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -172,7 +172,7 @@ it will print a message similar to the following: INFO: rcu_sched detected stalls on CPUs/tasks: 2-...: (3 GPs behind) idle=06c/0/0 softirq=1453/1455 fqs=0 16-...: (0 ticks this GP) idle=81c/0/0 softirq=764/764 fqs=0 - (detected by 32, t=2603 jiffies, g=7073, c=7072, q=625) + (detected by 32, t=2603 jiffies, g=7075, q=625) This message indicates that CPU 32 detected that CPUs 2 and 16 were both causing stalls, and that the stall was affecting RCU-sched. This message @@ -215,11 +215,10 @@ CPU since the last time that this CPU noted the beginning of a grace period. The "detected by" line indicates which CPU detected the stall (in this -case, CPU 32), how many jiffies have elapsed since the start of the -grace period (in this case 2603), the number of the last grace period -to start and to complete (7073 and 7072, respectively), and an estimate -of the total number of RCU callbacks queued across all CPUs (625 in -this case). +case, CPU 32), how many jiffies have elapsed since the start of the grace +period (in this case 2603), the grace-period sequence number (7075), and +an estimate of the total number of RCU callbacks queued across all CPUs +(625 in this case). In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed for each CPU: @@ -266,15 +265,16 @@ If the relevant grace-period kthread has been unable to run prior to the stall warning, as was the case in the "All QSes seen" line above, the following additional line is printed: - kthread starved for 23807 jiffies! g7073 c7072 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1 + kthread starved for 23807 jiffies! g7075 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1 ->cpu=5 Starving the grace-period kthreads of CPU time can of course result in RCU CPU stall warnings even when all CPUs and tasks have passed -through the required quiescent states. The "g" and "c" numbers flag the -number of the last grace period started and completed, respectively, -the "f" precedes the ->gp_flags command to the grace-period kthread, -the "RCU_GP_WAIT_FQS" indicates that the kthread is waiting for a short -timeout, and the "state" precedes value of the task_struct ->state field. +through the required quiescent states. The "g" number shows the current +grace-period sequence number, the "f" precedes the ->gp_flags command +to the grace-period kthread, the "RCU_GP_WAIT_FQS" indicates that the +kthread is waiting for a short timeout, the "state" precedes value of the +task_struct ->state field, and the "cpu" indicates that the grace-period +kthread last ran on CPU 5. Multiple Warnings From One Stall diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 65eb856526b7..c2a7facf7ff9 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -588,6 +588,7 @@ It is extremely simple: void synchronize_rcu(void) { write_lock(&rcu_gp_mutex); + smp_mb__after_spinlock(); write_unlock(&rcu_gp_mutex); } @@ -609,12 +610,15 @@ don't forget about them when submitting patches making use of RCU!] The rcu_read_lock() and rcu_read_unlock() primitive read-acquire and release a global reader-writer lock. The synchronize_rcu() -primitive write-acquires this same lock, then immediately releases -it. This means that once synchronize_rcu() exits, all RCU read-side -critical sections that were in progress before synchronize_rcu() was -called are guaranteed to have completed -- there is no way that -synchronize_rcu() would have been able to write-acquire the lock -otherwise. +primitive write-acquires this same lock, then releases it. This means +that once synchronize_rcu() exits, all RCU read-side critical sections +that were in progress before synchronize_rcu() was called are guaranteed +to have completed -- there is no way that synchronize_rcu() would have +been able to write-acquire the lock otherwise. The smp_mb__after_spinlock() +promotes synchronize_rcu() to a full memory barrier in compliance with +the "Memory-Barrier Guarantees" listed in: + + Documentation/RCU/Design/Requirements/Requirements.html. It is possible to nest rcu_read_lock(), since reader-writer locks may be recursively acquired. Note also that rcu_read_lock() is immune @@ -816,11 +820,13 @@ RCU list traversal: list_next_rcu list_for_each_entry_rcu list_for_each_entry_continue_rcu + list_for_each_entry_from_rcu hlist_first_rcu hlist_next_rcu hlist_pprev_rcu hlist_for_each_entry_rcu hlist_for_each_entry_rcu_bh + hlist_for_each_entry_from_rcu hlist_for_each_entry_continue_rcu hlist_for_each_entry_continue_rcu_bh hlist_nulls_first_rcu diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 533ff5c68970..c370f5f0eb38 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3632,8 +3632,8 @@ Set time (s) after boot for CPU-hotplug testing. rcutorture.onoff_interval= [KNL] - Set time (s) between CPU-hotplug operations, or - zero to disable CPU-hotplug testing. + Set time (jiffies) between CPU-hotplug operations, + or zero to disable CPU-hotplug testing. rcutorture.shuffle_interval= [KNL] Set task-shuffle interval (s). Shuffling tasks diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst index 2e7165f86f55..724583453e1f 100644 --- a/Documentation/core-api/atomic_ops.rst +++ b/Documentation/core-api/atomic_ops.rst @@ -29,7 +29,7 @@ updated by one CPU, local_t is probably more appropriate. Please see local_t. The first operations to implement for atomic_t's are the initializers and -plain reads. :: +plain writes. :: #define ATOMIC_INIT(i) { (i) } #define atomic_set(v, i) ((v)->counter = (i)) diff --git a/Documentation/device-mapper/writecache.txt b/Documentation/device-mapper/writecache.txt index 4424fa2c67d7..01532b3008ae 100644 --- a/Documentation/device-mapper/writecache.txt +++ b/Documentation/device-mapper/writecache.txt @@ -15,6 +15,8 @@ Constructor parameters: size) 5. the number of optional parameters (the parameters with an argument count as two) + start_sector n (default: 0) + offset from the start of cache device in 512-byte sectors high_watermark n (default: 50) start writeback when the number of used blocks reach this watermark diff --git a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt index bdadc3da9556..6970f30a3770 100644 --- a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt +++ b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt @@ -66,7 +66,7 @@ Required root node properties: - "insignal,arndale-octa" - for Exynos5420-based Insignal Arndale Octa board. - "insignal,origen" - for Exynos4210-based Insignal Origen board. - - "insignal,origen4412 - for Exynos4412-based Insignal Origen board. + - "insignal,origen4412" - for Exynos4412-based Insignal Origen board. Optional nodes: diff --git a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt index 6fddb4f4f71a..3055d5c2c04e 100644 --- a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt +++ b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt @@ -36,7 +36,7 @@ Optional nodes: - port/ports: to describe a connection to an external encoder. The binding follows Documentation/devicetree/bindings/graph.txt and - suppors a single port with a single endpoint. + supports a single port with a single endpoint. - See also Documentation/devicetree/bindings/display/tilcdc/panel.txt and Documentation/devicetree/bindings/display/tilcdc/tfp410.txt for connecting diff --git a/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt b/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt index 20fc72d9e61e..45a61b462287 100644 --- a/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt +++ b/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt @@ -1,7 +1,7 @@ Nintendo Wii (Hollywood) GPIO controller Required properties: -- compatible: "nintendo,hollywood-gpio +- compatible: "nintendo,hollywood-gpio" - reg: Physical base address and length of the controller's registers. - gpio-controller: Marks the device node as a GPIO controller. - #gpio-cells: Should be <2>. The first cell is the pin number and the diff --git a/Documentation/devicetree/bindings/input/touchscreen/hideep.txt b/Documentation/devicetree/bindings/input/touchscreen/hideep.txt index 121d9b7c79a2..1063c30d53f7 100644 --- a/Documentation/devicetree/bindings/input/touchscreen/hideep.txt +++ b/Documentation/devicetree/bindings/input/touchscreen/hideep.txt @@ -32,7 +32,7 @@ i2c@00000000 { reg = <0x6c>; interrupt-parent = <&gpx1>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; - vdd-supply = <&ldo15_reg>"; + vdd-supply = <&ldo15_reg>; vid-supply = <&ldo18_reg>; reset-gpios = <&gpx1 5 0>; touchscreen-size-x = <1080>; diff --git a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt index 5f89fb635a1b..f97fd8ab5e45 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt @@ -4,6 +4,7 @@ Required properties: - compatible : should be "ingenic,<socname>-intc". Valid strings are: ingenic,jz4740-intc + ingenic,jz4725b-intc ingenic,jz4770-intc ingenic,jz4775-intc ingenic,jz4780-intc diff --git a/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt b/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt index 1099fe0788fa..f246ccbf8838 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt @@ -15,7 +15,7 @@ Required properties: include "nvidia,tegra30-ictlr". - reg : Specifies base physical address and size of the registers. Each controller must be described separately (Tegra20 has 4 of them, - whereas Tegra30 and later have 5" + whereas Tegra30 and later have 5). - interrupt-controller : Identifies the node as an interrupt controller. - #interrupt-cells : Specifies the number of cells needed to encode an interrupt source. The value must be 3. diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt index 20f121daa910..697ca2f26d1b 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt @@ -7,6 +7,7 @@ Required properties: - "renesas,irqc-r8a73a4" (R-Mobile APE6) - "renesas,irqc-r8a7743" (RZ/G1M) - "renesas,irqc-r8a7745" (RZ/G1E) + - "renesas,irqc-r8a77470" (RZ/G1C) - "renesas,irqc-r8a7790" (R-Car H2) - "renesas,irqc-r8a7791" (R-Car M2-W) - "renesas,irqc-r8a7792" (R-Car V2H) @@ -16,6 +17,7 @@ Required properties: - "renesas,intc-ex-r8a7796" (R-Car M3-W) - "renesas,intc-ex-r8a77965" (R-Car M3-N) - "renesas,intc-ex-r8a77970" (R-Car V3M) + - "renesas,intc-ex-r8a77980" (R-Car V3H) - "renesas,intc-ex-r8a77995" (R-Car D3) - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in interrupts.txt in this directory diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt index 136bd612bd83..6a36bf66d932 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt @@ -12,7 +12,7 @@ Required properties: specifier, shall be 2 - interrupts: interrupts references to primary interrupt controller (only needed for exti controller with multiple exti under - same parent interrupt: st,stm32-exti and st,stm32h7-exti") + same parent interrupt: st,stm32-exti and st,stm32h7-exti) Example: diff --git a/Documentation/devicetree/bindings/mips/brcm/soc.txt b/Documentation/devicetree/bindings/mips/brcm/soc.txt index 356c29789cf5..3a66d3c483e1 100644 --- a/Documentation/devicetree/bindings/mips/brcm/soc.txt +++ b/Documentation/devicetree/bindings/mips/brcm/soc.txt @@ -152,7 +152,7 @@ Required properties: - compatible : should contain one of: "brcm,bcm7425-timers" "brcm,bcm7429-timers" - "brcm,bcm7435-timers and + "brcm,bcm7435-timers" and "brcm,brcmstb-timers" - reg : the timers register range - interrupts : the interrupt line for this timer block diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt index df873d1f3b7c..f8c33890bc29 100644 --- a/Documentation/devicetree/bindings/net/fsl-fman.txt +++ b/Documentation/devicetree/bindings/net/fsl-fman.txt @@ -238,7 +238,7 @@ PROPERTIES Must include one of the following: - "fsl,fman-dtsec" for dTSEC MAC - "fsl,fman-xgec" for XGEC MAC - - "fsl,fman-memac for mEMAC MAC + - "fsl,fman-memac" for mEMAC MAC - cell-index Usage: required diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt index 9b387f861aed..7dec508987c7 100644 --- a/Documentation/devicetree/bindings/power/power_domain.txt +++ b/Documentation/devicetree/bindings/power/power_domain.txt @@ -133,7 +133,7 @@ located inside a PM domain with index 0 of a power controller represented by a node with the label "power". In the second example the consumer device are partitioned across two PM domains, the first with index 0 and the second with index 1, of a power controller that -is represented by a node with the label "power. +is represented by a node with the label "power". Optional properties: - required-opps: This contains phandle to an OPP node in another device's OPP diff --git a/Documentation/devicetree/bindings/regulator/tps65090.txt b/Documentation/devicetree/bindings/regulator/tps65090.txt index ca69f5e3040c..ae326f263597 100644 --- a/Documentation/devicetree/bindings/regulator/tps65090.txt +++ b/Documentation/devicetree/bindings/regulator/tps65090.txt @@ -16,7 +16,7 @@ Required properties: Optional properties: - ti,enable-ext-control: This is applicable for DCDC1, DCDC2 and DCDC3. If DCDCs are externally controlled then this property should be there. -- "dcdc-ext-control-gpios: This is applicable for DCDC1, DCDC2 and DCDC3. +- dcdc-ext-control-gpios: This is applicable for DCDC1, DCDC2 and DCDC3. If DCDCs are externally controlled and if it is from GPIO then GPIO number should be provided. If it is externally controlled and no GPIO entry then driver will just configure this rails as external control diff --git a/Documentation/devicetree/bindings/reset/st,sti-softreset.txt b/Documentation/devicetree/bindings/reset/st,sti-softreset.txt index a21658f18fe6..3661e6153a92 100644 --- a/Documentation/devicetree/bindings/reset/st,sti-softreset.txt +++ b/Documentation/devicetree/bindings/reset/st,sti-softreset.txt @@ -15,7 +15,7 @@ Please refer to reset.txt in this directory for common reset controller binding usage. Required properties: -- compatible: Should be st,stih407-softreset"; +- compatible: Should be "st,stih407-softreset"; - #reset-cells: 1, see below example: diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt index d330c73de9a2..68b7d6207e3d 100644 --- a/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt +++ b/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt @@ -39,7 +39,7 @@ Required properties: Optional property: - clock-frequency: Desired I2C bus clock frequency in Hz. - When missing default to 400000Hz. + When missing default to 100000Hz. Child nodes should conform to I2C bus binding as described in i2c.txt. diff --git a/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt b/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt index 6a4aadc4ce06..84b28dbe9f15 100644 --- a/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt +++ b/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt @@ -30,7 +30,7 @@ Required properties: Board connectors: * Headset Mic - * Secondary Mic", + * Secondary Mic * DMIC * Ext Spk diff --git a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt index aa54e49fc8a2..c7600a93ab39 100644 --- a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt +++ b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt @@ -35,7 +35,7 @@ This binding describes the APQ8096 sound card, which uses qdsp for audio. "Digital Mic3" Audio pins and MicBias on WCD9335 Codec: - "MIC_BIAS1 + "MIC_BIAS1" "MIC_BIAS2" "MIC_BIAS3" "MIC_BIAS4" diff --git a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt index b1fe7e9de1b4..18d4d0166c76 100644 --- a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt +++ b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt @@ -1,19 +1,25 @@ -Mediatek MT6577, MT6572 and MT6589 Timers ---------------------------------------- +Mediatek Timers +--------------- + +Mediatek SoCs have two different timers on different platforms, +- GPT (General Purpose Timer) +- SYST (System Timer) + +The proper timer will be selected automatically by driver. Required properties: - compatible should contain: - * "mediatek,mt2701-timer" for MT2701 compatible timers - * "mediatek,mt6580-timer" for MT6580 compatible timers - * "mediatek,mt6589-timer" for MT6589 compatible timers - * "mediatek,mt7623-timer" for MT7623 compatible timers - * "mediatek,mt8127-timer" for MT8127 compatible timers - * "mediatek,mt8135-timer" for MT8135 compatible timers - * "mediatek,mt8173-timer" for MT8173 compatible timers - * "mediatek,mt6577-timer" for MT6577 and all above compatible timers -- reg: Should contain location and length for timers register. -- clocks: Clocks driving the timer hardware. This list should include two - clocks. The order is system clock and as second clock the RTC clock. + * "mediatek,mt2701-timer" for MT2701 compatible timers (GPT) + * "mediatek,mt6580-timer" for MT6580 compatible timers (GPT) + * "mediatek,mt6589-timer" for MT6589 compatible timers (GPT) + * "mediatek,mt7623-timer" for MT7623 compatible timers (GPT) + * "mediatek,mt8127-timer" for MT8127 compatible timers (GPT) + * "mediatek,mt8135-timer" for MT8135 compatible timers (GPT) + * "mediatek,mt8173-timer" for MT8173 compatible timers (GPT) + * "mediatek,mt6577-timer" for MT6577 and all above compatible timers (GPT) + * "mediatek,mt6765-timer" for MT6765 compatible timers (SYST) +- reg: Should contain location and length for timer register. +- clocks: Should contain system clock. Examples: @@ -21,5 +27,5 @@ Examples: compatible = "mediatek,mt6577-timer"; reg = <0x10008000 0x80>; interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_LOW>; - clocks = <&system_clk>, <&rtc_clk>; + clocks = <&system_clk>; }; diff --git a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt index 252a05c5d976..c8c4b00ecb94 100644 --- a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt +++ b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt @@ -16,7 +16,8 @@ A child node must exist to represent the core DWC3 IP block. The name of the node is not important. The content of the node is defined in dwc3.txt. Phy documentation is provided in the following places: -Documentation/devicetree/bindings/phy/qcom-dwc3-usb-phy.txt +Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.txt - USB2.0 PHY +Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt - Type-C PHY Example device nodes: diff --git a/Documentation/devicetree/bindings/w1/w1-gpio.txt b/Documentation/devicetree/bindings/w1/w1-gpio.txt index 6e09c35d9f1a..37091902a021 100644 --- a/Documentation/devicetree/bindings/w1/w1-gpio.txt +++ b/Documentation/devicetree/bindings/w1/w1-gpio.txt @@ -15,7 +15,7 @@ Optional properties: Examples: - onewire@0 { + onewire { compatible = "w1-gpio"; gpios = <&gpio 126 0>, <&gpio 105 0>; }; diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt index cb3b0de83fc6..10f4499e677c 100644 --- a/Documentation/kprobes.txt +++ b/Documentation/kprobes.txt @@ -80,6 +80,26 @@ After the instruction is single-stepped, Kprobes executes the "post_handler," if any, that is associated with the kprobe. Execution then continues with the instruction following the probepoint. +Changing Execution Path +----------------------- + +Since kprobes can probe into a running kernel code, it can change the +register set, including instruction pointer. This operation requires +maximum care, such as keeping the stack frame, recovering the execution +path etc. Since it operates on a running kernel and needs deep knowledge +of computer architecture and concurrent computing, you can easily shoot +your foot. + +If you change the instruction pointer (and set up other related +registers) in pre_handler, you must return !0 so that kprobes stops +single stepping and just returns to the given address. +This also means post_handler should not be called anymore. + +Note that this operation may be harder on some architectures which use +TOC (Table of Contents) for function call, since you have to setup a new +TOC for your function in your module, and recover the old one after +returning from it. + Return Probes ------------- @@ -262,7 +282,7 @@ is optimized, that modification is ignored. Thus, if you want to tweak the kernel's execution path, you need to suppress optimization, using one of the following techniques: -- Specify an empty function for the kprobe's post_handler or break_handler. +- Specify an empty function for the kprobe's post_handler. or @@ -474,7 +494,7 @@ error occurs during registration, all probes in the array, up to the bad probe, are safely unregistered before the register_*probes function returns. -- kps/rps/jps: an array of pointers to ``*probe`` data structures +- kps/rps: an array of pointers to ``*probe`` data structures - num: the number of the array entries. .. note:: @@ -566,12 +586,11 @@ the same handler) may run concurrently on different CPUs. Kprobes does not use mutexes or allocate memory except during registration and unregistration. -Probe handlers are run with preemption disabled. Depending on the -architecture and optimization state, handlers may also run with -interrupts disabled (e.g., kretprobe handlers and optimized kprobe -handlers run without interrupt disabled on x86/x86-64). In any case, -your handler should not yield the CPU (e.g., by attempting to acquire -a semaphore). +Probe handlers are run with preemption disabled or interrupt disabled, +which depends on the architecture and optimization state. (e.g., +kretprobe handlers and optimized kprobe handlers run without interrupt +disabled on x86/x86-64). In any case, your handler should not yield +the CPU (e.g., by attempting to acquire a semaphore, or waiting I/O). Since a return probe is implemented by replacing the return address with the trampoline's address, stack backtraces and calls diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index a02d6bbfc9d0..0d8d7ef131e9 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -2179,32 +2179,41 @@ or: event_indicated = 1; wake_up_process(event_daemon); -A write memory barrier is implied by wake_up() and co. if and only if they -wake something up. The barrier occurs before the task state is cleared, and so -sits between the STORE to indicate the event and the STORE to set TASK_RUNNING: +A general memory barrier is executed by wake_up() if it wakes something up. +If it doesn't wake anything up then a memory barrier may or may not be +executed; you must not rely on it. The barrier occurs before the task state +is accessed, in particular, it sits between the STORE to indicate the event +and the STORE to set TASK_RUNNING: - CPU 1 CPU 2 + CPU 1 (Sleeper) CPU 2 (Waker) =============================== =============================== set_current_state(); STORE event_indicated smp_store_mb(); wake_up(); - STORE current->state <write barrier> - <general barrier> STORE current->state - LOAD event_indicated + STORE current->state ... + <general barrier> <general barrier> + LOAD event_indicated if ((LOAD task->state) & TASK_NORMAL) + STORE task->state -To repeat, this write memory barrier is present if and only if something -is actually awakened. To see this, consider the following sequence of -events, where X and Y are both initially zero: +where "task" is the thread being woken up and it equals CPU 1's "current". + +To repeat, a general memory barrier is guaranteed to be executed by wake_up() +if something is actually awakened, but otherwise there is no such guarantee. +To see this, consider the following sequence of events, where X and Y are both +initially zero: CPU 1 CPU 2 =============================== =============================== - X = 1; STORE event_indicated + X = 1; Y = 1; smp_mb(); wake_up(); - Y = 1; wait_event(wq, Y == 1); - wake_up(); load from Y sees 1, no memory barrier - load from X might see 0 + LOAD Y LOAD X + +If a wakeup does occur, one (at least) of the two loads must see 1. If, on +the other hand, a wakeup does not occur, both loads might see 0. -In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed -to see 1. +wake_up_process() always executes a general memory barrier. The barrier again +occurs before the task state is accessed. In particular, if the wake_up() in +the previous snippet were replaced by a call to wake_up_process() then one of +the two loads would be guaranteed to see 1. The available waker functions include: @@ -2224,6 +2233,8 @@ The available waker functions include: wake_up_poll(); wake_up_process(); +In terms of memory ordering, these functions all provide the same guarantees of +a wake_up() (or stronger). [!] Note that the memory barriers implied by the sleeper and the waker do _not_ order multiple stores before the wake-up with respect to loads of those stored diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index c13214d073a4..d3e5dd26db12 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -1490,7 +1490,7 @@ To remove an ARP target: To configure the interval between learning packet transmits: # echo 12 > /sys/class/net/bond0/bonding/lp_interval - NOTE: the lp_inteval is the number of seconds between instances where + NOTE: the lp_interval is the number of seconds between instances where the bonding driver sends learning packets to each slaves peer switch. The default interval is 1 second. diff --git a/Documentation/networking/dpaa2/overview.rst b/Documentation/networking/dpaa2/overview.rst index 79fede4447d6..d638b5a8aadd 100644 --- a/Documentation/networking/dpaa2/overview.rst +++ b/Documentation/networking/dpaa2/overview.rst @@ -1,5 +1,6 @@ .. include:: <isonum.txt> +========================================================= DPAA2 (Data Path Acceleration Architecture Gen2) Overview ========================================================= diff --git a/Documentation/networking/e100.rst b/Documentation/networking/e100.rst index 9708f5fa76de..f81111eba9c5 100644 --- a/Documentation/networking/e100.rst +++ b/Documentation/networking/e100.rst @@ -47,41 +47,45 @@ Driver Configuration Parameters The default value for each parameter is generally the recommended setting, unless otherwise noted. -Rx Descriptors: Number of receive descriptors. A receive descriptor is a data +Rx Descriptors: + Number of receive descriptors. A receive descriptor is a data structure that describes a receive buffer and its attributes to the network controller. The data in the descriptor is used by the controller to write data from the controller to host memory. In the 3.x.x driver the valid range for this parameter is 64-256. The default value is 256. This parameter can be changed using the command:: - ethtool -G eth? rx n + ethtool -G eth? rx n Where n is the number of desired Rx descriptors. -Tx Descriptors: Number of transmit descriptors. A transmit descriptor is a data +Tx Descriptors: + Number of transmit descriptors. A transmit descriptor is a data structure that describes a transmit buffer and its attributes to the network controller. The data in the descriptor is used by the controller to read data from the host memory to the controller. In the 3.x.x driver the valid range for this parameter is 64-256. The default value is 128. This parameter can be changed using the command:: - ethtool -G eth? tx n + ethtool -G eth? tx n Where n is the number of desired Tx descriptors. -Speed/Duplex: The driver auto-negotiates the link speed and duplex settings by +Speed/Duplex: + The driver auto-negotiates the link speed and duplex settings by default. The ethtool utility can be used as follows to force speed/duplex.:: - ethtool -s eth? autoneg off speed {10|100} duplex {full|half} + ethtool -s eth? autoneg off speed {10|100} duplex {full|half} NOTE: setting the speed/duplex to incorrect values will cause the link to fail. -Event Log Message Level: The driver uses the message level flag to log events +Event Log Message Level: + The driver uses the message level flag to log events to syslog. The message level can be set at driver load time. It can also be set using the command:: - ethtool -s eth? msglvl n + ethtool -s eth? msglvl n Additional Configurations @@ -92,7 +96,7 @@ Configuring the Driver on Different Distributions Configuring a network driver to load properly when the system is started is distribution dependent. Typically, the configuration process involves -adding an alias line to /etc/modprobe.d/*.conf as well as editing other +adding an alias line to `/etc/modprobe.d/*.conf` as well as editing other system startup scripts and/or configuration files. Many popular Linux distributions ship with tools to make these changes for you. To learn the proper way to configure a network device for your system, refer to @@ -160,7 +164,10 @@ This results in unbalanced receive traffic. If you have multiple interfaces in a server, either turn on ARP filtering by -(1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter +(1) entering:: + + echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter + (this only works if your kernel's version is higher than 2.4.5), or (2) installing the interfaces in separate broadcast domains (either diff --git a/Documentation/networking/e1000.rst b/Documentation/networking/e1000.rst index 144b87eef153..f10dd4086921 100644 --- a/Documentation/networking/e1000.rst +++ b/Documentation/networking/e1000.rst @@ -34,7 +34,8 @@ Command Line Parameters The default value for each parameter is generally the recommended setting, unless otherwise noted. -NOTES: For more information about the AutoNeg, Duplex, and Speed +NOTES: + For more information about the AutoNeg, Duplex, and Speed parameters, see the "Speed and Duplex Configuration" section in this document. @@ -45,22 +46,27 @@ NOTES: For more information about the AutoNeg, Duplex, and Speed AutoNeg ------- + (Supported only on adapters with copper connections) -Valid Range: 0x01-0x0F, 0x20-0x2F -Default Value: 0x2F + +:Valid Range: 0x01-0x0F, 0x20-0x2F +:Default Value: 0x2F This parameter is a bit-mask that specifies the speed and duplex settings advertised by the adapter. When this parameter is used, the Speed and Duplex parameters must not be specified. -NOTE: Refer to the Speed and Duplex section of this readme for more +NOTE: + Refer to the Speed and Duplex section of this readme for more information on the AutoNeg parameter. Duplex ------ + (Supported only on adapters with copper connections) -Valid Range: 0-2 (0=auto-negotiate, 1=half, 2=full) -Default Value: 0 + +:Valid Range: 0-2 (0=auto-negotiate, 1=half, 2=full) +:Default Value: 0 This defines the direction in which data is allowed to flow. Can be either one or two-directional. If both Duplex and the link partner are @@ -70,18 +76,22 @@ duplex. FlowControl ----------- -Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx) -Default Value: Reads flow control settings from the EEPROM + +:Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx) +:Default Value: Reads flow control settings from the EEPROM This parameter controls the automatic generation(Tx) and response(Rx) to Ethernet PAUSE frames. InterruptThrottleRate --------------------- + (not supported on Intel(R) 82542, 82543 or 82544-based adapters) -Valid Range: 0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative, - 4=simplified balancing) -Default Value: 3 + +:Valid Range: + 0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative, + 4=simplified balancing) +:Default Value: 3 The driver can limit the amount of interrupts per second that the adapter will generate for incoming packets. It does this by writing a value to the @@ -135,13 +145,15 @@ Setting InterruptThrottleRate to 0 turns off any interrupt moderation and may improve small packet latency, but is generally not suitable for bulk throughput traffic. -NOTE: InterruptThrottleRate takes precedence over the TxAbsIntDelay and +NOTE: + InterruptThrottleRate takes precedence over the TxAbsIntDelay and RxAbsIntDelay parameters. In other words, minimizing the receive and/or transmit absolute delays does not force the controller to generate more interrupts than what the Interrupt Throttle Rate allows. -CAUTION: If you are using the Intel(R) PRO/1000 CT Network Connection +CAUTION: + If you are using the Intel(R) PRO/1000 CT Network Connection (controller 82547), setting InterruptThrottleRate to a value greater than 75,000, may hang (stop transmitting) adapters under certain network conditions. If this occurs a NETDEV @@ -151,7 +163,8 @@ CAUTION: If you are using the Intel(R) PRO/1000 CT Network Connection hang, ensure that InterruptThrottleRate is set no greater than 75,000 and is not set to 0. -NOTE: When e1000 is loaded with default settings and multiple adapters +NOTE: + When e1000 is loaded with default settings and multiple adapters are in use simultaneously, the CPU utilization may increase non- linearly. In order to limit the CPU utilization without impacting the overall throughput, we recommend that you load the driver as @@ -168,9 +181,11 @@ NOTE: When e1000 is loaded with default settings and multiple adapters RxDescriptors ------------- -Valid Range: 48-256 for 82542 and 82543-based adapters - 48-4096 for all other supported adapters -Default Value: 256 + +:Valid Range: + - 48-256 for 82542 and 82543-based adapters + - 48-4096 for all other supported adapters +:Default Value: 256 This value specifies the number of receive buffer descriptors allocated by the driver. Increasing this value allows the driver to buffer more @@ -180,15 +195,17 @@ Each descriptor is 16 bytes. A receive buffer is also allocated for each descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending on the MTU setting. The maximum MTU size is 16110. -NOTE: MTU designates the frame size. It only needs to be set for Jumbo +NOTE: + MTU designates the frame size. It only needs to be set for Jumbo Frames. Depending on the available system resources, the request for a higher number of receive descriptors may be denied. In this case, use a lower number. RxIntDelay ---------- -Valid Range: 0-65535 (0=off) -Default Value: 0 + +:Valid Range: 0-65535 (0=off) +:Default Value: 0 This value delays the generation of receive interrupts in units of 1.024 microseconds. Receive interrupt reduction can improve CPU efficiency if @@ -198,7 +215,8 @@ of TCP traffic. If the system is reporting dropped receives, this value may be set too high, causing the driver to run out of available receive descriptors. -CAUTION: When setting RxIntDelay to a value other than 0, adapters may +CAUTION: + When setting RxIntDelay to a value other than 0, adapters may hang (stop transmitting) under certain network conditions. If this occurs a NETDEV WATCHDOG message is logged in the system event log. In addition, the controller is automatically reset, @@ -207,9 +225,11 @@ CAUTION: When setting RxIntDelay to a value other than 0, adapters may RxAbsIntDelay ------------- + (This parameter is supported only on 82540, 82545 and later adapters.) -Valid Range: 0-65535 (0=off) -Default Value: 128 + +:Valid Range: 0-65535 (0=off) +:Default Value: 128 This value, in units of 1.024 microseconds, limits the delay in which a receive interrupt is generated. Useful only if RxIntDelay is non-zero, @@ -220,9 +240,11 @@ conditions. Speed ----- + (This parameter is supported only on adapters with copper connections.) -Valid Settings: 0, 10, 100, 1000 -Default Value: 0 (auto-negotiate at all supported speeds) + +:Valid Settings: 0, 10, 100, 1000 +:Default Value: 0 (auto-negotiate at all supported speeds) Speed forces the line speed to the specified value in megabits per second (Mbps). If this parameter is not specified or is set to 0 and the link @@ -231,22 +253,26 @@ speed. Duplex should also be set when Speed is set to either 10 or 100. TxDescriptors ------------- -Valid Range: 48-256 for 82542 and 82543-based adapters - 48-4096 for all other supported adapters -Default Value: 256 + +:Valid Range: + - 48-256 for 82542 and 82543-based adapters + - 48-4096 for all other supported adapters +:Default Value: 256 This value is the number of transmit descriptors allocated by the driver. Increasing this value allows the driver to queue more transmits. Each descriptor is 16 bytes. -NOTE: Depending on the available system resources, the request for a +NOTE: + Depending on the available system resources, the request for a higher number of transmit descriptors may be denied. In this case, use a lower number. TxIntDelay ---------- -Valid Range: 0-65535 (0=off) -Default Value: 8 + +:Valid Range: 0-65535 (0=off) +:Default Value: 8 This value delays the generation of transmit interrupts in units of 1.024 microseconds. Transmit interrupt reduction can improve CPU @@ -256,9 +282,11 @@ causing the driver to run out of available transmit descriptors. TxAbsIntDelay ------------- + (This parameter is supported only on 82540, 82545 and later adapters.) -Valid Range: 0-65535 (0=off) -Default Value: 32 + +:Valid Range: 0-65535 (0=off) +:Default Value: 32 This value, in units of 1.024 microseconds, limits the delay in which a transmit interrupt is generated. Useful only if TxIntDelay is non-zero, @@ -269,18 +297,21 @@ network conditions. XsumRX ------ + (This parameter is NOT supported on the 82542-based adapter.) -Valid Range: 0-1 -Default Value: 1 + +:Valid Range: 0-1 +:Default Value: 1 A value of '1' indicates that the driver should enable IP checksum offload for received packets (both UDP and TCP) to the adapter hardware. Copybreak --------- -Valid Range: 0-xxxxxxx (0=off) -Default Value: 256 -Usage: modprobe e1000.ko copybreak=128 + +:Valid Range: 0-xxxxxxx (0=off) +:Default Value: 256 +:Usage: modprobe e1000.ko copybreak=128 Driver copies all packets below or equaling this size to a fresh RX buffer before handing it up the stack. @@ -292,8 +323,9 @@ it is also available during runtime at SmartPowerDownEnable -------------------- -Valid Range: 0-1 -Default Value: 0 (disabled) + +:Valid Range: 0-1 +:Default Value: 0 (disabled) Allows PHY to turn off in lower power states. The user can turn off this parameter in supported chipsets. @@ -309,14 +341,14 @@ fiber interface board only links at 1000 Mbps full-duplex. For copper-based boards, the keywords interact as follows: - The default operation is auto-negotiate. The board advertises all +- The default operation is auto-negotiate. The board advertises all supported speed and duplex combinations, and it links at the highest common speed and duplex mode IF the link partner is set to auto-negotiate. - If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps +- If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps is advertised (The 1000BaseT spec requires auto-negotiation.) - If Speed = 10 or 100, then both Speed and Duplex should be set. Auto- +- If Speed = 10 or 100, then both Speed and Duplex should be set. Auto- negotiation is disabled, and the AutoNeg parameter is ignored. Partner SHOULD also be forced. @@ -328,13 +360,15 @@ process. The parameter may be specified as either a decimal or hexadecimal value as determined by the bitmap below. +============== ====== ====== ======= ======= ====== ====== ======= ====== Bit position 7 6 5 4 3 2 1 0 Decimal Value 128 64 32 16 8 4 2 1 Hex value 80 40 20 10 8 4 2 1 Speed (Mbps) N/A N/A 1000 N/A 100 100 10 10 Duplex Full Full Half Full Half +============== ====== ====== ======= ======= ====== ====== ======= ====== -Some examples of using AutoNeg: +Some examples of using AutoNeg:: modprobe e1000 AutoNeg=0x01 (Restricts autonegotiation to 10 Half) modprobe e1000 AutoNeg=1 (Same as above) @@ -357,56 +391,59 @@ Additional Configurations Jumbo Frames ------------ -Jumbo Frames support is enabled by changing the MTU to a value larger -than the default of 1500. Use the ifconfig command to increase the MTU -size. For example:: + + Jumbo Frames support is enabled by changing the MTU to a value larger than + the default of 1500. Use the ifconfig command to increase the MTU size. + For example:: ifconfig eth<x> mtu 9000 up -This setting is not saved across reboots. It can be made permanent if -you add:: + This setting is not saved across reboots. It can be made permanent if + you add:: MTU=9000 -to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example -applies to the Red Hat distributions; other distributions may store this -setting in a different location. + to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example + applies to the Red Hat distributions; other distributions may store this + setting in a different location. + +Notes: + Degradation in throughput performance may be observed in some Jumbo frames + environments. If this is observed, increasing the application's socket buffer + size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help. + See the specific application manual and /usr/src/linux*/Documentation/ + networking/ip-sysctl.txt for more details. -Notes: Degradation in throughput performance may be observed in some -Jumbo frames environments. If this is observed, increasing the -application's socket buffer size and/or increasing the -/proc/sys/net/ipv4/tcp_*mem entry values may help. See the specific -application manual and /usr/src/linux*/Documentation/ -networking/ip-sysctl.txt for more details. + - The maximum MTU setting for Jumbo Frames is 16110. This value coincides + with the maximum Jumbo Frames size of 16128. -- The maximum MTU setting for Jumbo Frames is 16110. This value - coincides with the maximum Jumbo Frames size of 16128. + - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in + poor performance or loss of link. -- Using Jumbo frames at 10 or 100 Mbps is not supported and may result - in poor performance or loss of link. + - Adapters based on the Intel(R) 82542 and 82573V/E controller do not + support Jumbo Frames. These correspond to the following product names:: -- Adapters based on the Intel(R) 82542 and 82573V/E controller do not - support Jumbo Frames. These correspond to the following product names: - Intel(R) PRO/1000 Gigabit Server Adapter Intel(R) PRO/1000 PM Network - Connection + Intel(R) PRO/1000 Gigabit Server Adapter + Intel(R) PRO/1000 PM Network Connection ethtool ------- -The driver utilizes the ethtool interface for driver configuration and -diagnostics, as well as displaying statistical information. The ethtool -version 1.6 or later is required for this functionality. -The latest release of ethtool can be found from -https://www.kernel.org/pub/software/network/ethtool/ + The driver utilizes the ethtool interface for driver configuration and + diagnostics, as well as displaying statistical information. The ethtool + version 1.6 or later is required for this functionality. + + The latest release of ethtool can be found from + https://www.kernel.org/pub/software/network/ethtool/ Enabling Wake on LAN* (WoL) --------------------------- -WoL is configured through the ethtool* utility. -WoL will be enabled on the system during the next shut down or reboot. -For this driver version, in order to enable WoL, the e1000 driver must be -loaded when shutting down or rebooting the system. + WoL is configured through the ethtool* utility. + WoL will be enabled on the system during the next shut down or reboot. + For this driver version, in order to enable WoL, the e1000 driver must be + loaded when shutting down or rebooting the system. Support ======= diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt index 921739d00f69..7f01fb1c1084 100644 --- a/Documentation/translations/ko_KR/memory-barriers.txt +++ b/Documentation/translations/ko_KR/memory-barriers.txt @@ -1891,22 +1891,22 @@ Mandatory ë°°ë¦¬ì–´ë“¤ì€ SMP 시스템ì—ì„œë„ UP 시스템ì—ì„œë„ SMP íš¨ê³ /* ì†Œìœ ê¶Œì„ ìˆ˜ì • */ desc->status = DEVICE_OWN; - /* MMIO 를 통해 디바ì´ìŠ¤ì— 공지를 하기 ì „ì— ë©”ëª¨ë¦¬ë¥¼ ë™ê¸°í™” */ - wmb(); - /* ì—…ë°ì´íŠ¸ëœ 디스í¬ë¦½í„°ì˜ 디바ì´ìŠ¤ì— 공지 */ writel(DESC_NOTIFY, doorbell); } dma_rmb() 는 디스í¬ë¦½í„°ë¡œë¶€í„° ë°ì´í„°ë¥¼ ì½ì–´ì˜¤ê¸° ì „ì— ë””ë°”ì´ìŠ¤ê°€ ì†Œìœ ê¶Œì„ - 내놓았ìŒì„ 보장하게 í•˜ê³ , dma_wmb() 는 디바ì´ìŠ¤ê°€ ìžì‹ ì´ ì†Œìœ ê¶Œì„ ë‹¤ì‹œ - 가졌ìŒì„ 보기 ì „ì— ë””ìŠ¤í¬ë¦½í„°ì— ë°ì´í„°ê°€ 쓰였ìŒì„ 보장합니다. wmb() 는 - ìºì‹œ ì¼ê´€ì„±ì´ 없는 (cache incoherent) MMIO ì˜ì—ì— ì“°ê¸°ë¥¼ ì‹œë„하기 ì „ì— - ìºì‹œ ì¼ê´€ì„±ì´ 있는 메모리 (cache coherent memory) 쓰기가 완료ë˜ì—ˆìŒì„ - 보장해주기 위해 필요합니다. - - consistent memory ì— ëŒ€í•œ ìžì„¸í•œ ë‚´ìš©ì„ ìœ„í•´ì„ Documentation/DMA-API.txt - 문서를 ì°¸ê³ í•˜ì„¸ìš”. + ë‚´ë ¤ë†“ì•˜ì„ ê²ƒì„ ë³´ìž¥í•˜ê³ , dma_wmb() 는 디바ì´ìŠ¤ê°€ ìžì‹ ì´ ì†Œìœ ê¶Œì„ ë‹¤ì‹œ + 가졌ìŒì„ 보기 ì „ì— ë””ìŠ¤í¬ë¦½í„°ì— ë°ì´í„°ê°€ ì“°ì˜€ì„ ê²ƒì„ ë³´ìž¥í•©ë‹ˆë‹¤. ì°¸ê³ ë¡œ, + writel() ì„ ì‚¬ìš©í•˜ë©´ ìºì‹œ ì¼ê´€ì„±ì´ 있는 메모리 (cache coherent memory) + 쓰기가 MMIO ì˜ì—ì—ì˜ ì“°ê¸° ì „ì— ì™„ë£Œë˜ì—ˆì„ ê²ƒì„ ë³´ìž¥í•˜ë¯€ë¡œ writel() ì•žì— + wmb() 를 ì‹¤í–‰í• í•„ìš”ê°€ ì—†ìŒì„ 알아ë‘시기 ë°”ëžë‹ˆë‹¤. writel() 보다 ë¹„ìš©ì´ + ì €ë ´í•œ writel_relaxed() 는 ì´ëŸ° ë³´ìž¥ì„ ì œê³µí•˜ì§€ 않으므로 ì—¬ê¸°ì„ ì‚¬ìš©ë˜ì§€ + 않아야 합니다. + + writel_relaxed() 와 ê°™ì€ ì™„í™”ëœ I/O ì ‘ê·¼ìžë“¤ì— 대한 ìžì„¸í•œ ë‚´ìš©ì„ ìœ„í•´ì„œëŠ” + "ì»¤ë„ I/O ë°°ë¦¬ì–´ì˜ íš¨ê³¼" 섹션ì„, consistent memory ì— ëŒ€í•œ ìžì„¸í•œ ë‚´ìš©ì„ + ìœ„í•´ì„ Documentation/DMA-API.txt 문서를 ì°¸ê³ í•˜ì„¸ìš”. MMIO 쓰기 배리어 diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt index a16aa2113840..f662d3c530e5 100644 --- a/Documentation/x86/intel_rdt_ui.txt +++ b/Documentation/x86/intel_rdt_ui.txt @@ -29,7 +29,11 @@ mount options are: L2 and L3 CDP are controlled seperately. RDT features are orthogonal. A particular system may support only -monitoring, only control, or both monitoring and control. +monitoring, only control, or both monitoring and control. Cache +pseudo-locking is a unique way of using cache control to "pin" or +"lock" data in the cache. Details can be found in +"Cache Pseudo-Locking". + The mount succeeds if either of allocation or monitoring is present, but only those files and directories supported by the system will be created. @@ -65,6 +69,29 @@ related to allocation: some platforms support devices that have their own settings for cache use which can over-ride these bits. +"bit_usage": Annotated capacity bitmasks showing how all + instances of the resource are used. The legend is: + "0" - Corresponding region is unused. When the system's + resources have been allocated and a "0" is found + in "bit_usage" it is a sign that resources are + wasted. + "H" - Corresponding region is used by hardware only + but available for software use. If a resource + has bits set in "shareable_bits" but not all + of these bits appear in the resource groups' + schematas then the bits appearing in + "shareable_bits" but no resource group will + be marked as "H". + "X" - Corresponding region is available for sharing and + used by hardware and software. These are the + bits that appear in "shareable_bits" as + well as a resource group's allocation. + "S" - Corresponding region is used by software + and available for sharing. + "E" - Corresponding region is used exclusively by + one resource group. No sharing allowed. + "P" - Corresponding region is pseudo-locked. No + sharing allowed. Memory bandwitdh(MB) subdirectory contains the following files with respect to allocation: @@ -151,6 +178,9 @@ All groups contain the following files: CPUs to/from this group. As with the tasks file a hierarchy is maintained where MON groups may only include CPUs owned by the parent CTRL_MON group. + When the resouce group is in pseudo-locked mode this file will + only be readable, reflecting the CPUs associated with the + pseudo-locked region. "cpus_list": @@ -163,6 +193,21 @@ When control is enabled all CTRL_MON groups will also contain: A list of all the resources available to this group. Each resource has its own line and format - see below for details. +"size": + Mirrors the display of the "schemata" file to display the size in + bytes of each allocation instead of the bits representing the + allocation. + +"mode": + The "mode" of the resource group dictates the sharing of its + allocations. A "shareable" resource group allows sharing of its + allocations while an "exclusive" resource group does not. A + cache pseudo-locked region is created by first writing + "pseudo-locksetup" to the "mode" file before writing the cache + pseudo-locked region's schemata to the resource group's "schemata" + file. On successful pseudo-locked region creation the mode will + automatically change to "pseudo-locked". + When monitoring is enabled all MON groups will also contain: "mon_data": @@ -379,6 +424,170 @@ L3CODE:0=fffff;1=fffff;2=fffff;3=fffff L3DATA:0=fffff;1=fffff;2=3c0;3=fffff L3CODE:0=fffff;1=fffff;2=fffff;3=fffff +Cache Pseudo-Locking +-------------------- +CAT enables a user to specify the amount of cache space that an +application can fill. Cache pseudo-locking builds on the fact that a +CPU can still read and write data pre-allocated outside its current +allocated area on a cache hit. With cache pseudo-locking, data can be +preloaded into a reserved portion of cache that no application can +fill, and from that point on will only serve cache hits. The cache +pseudo-locked memory is made accessible to user space where an +application can map it into its virtual address space and thus have +a region of memory with reduced average read latency. + +The creation of a cache pseudo-locked region is triggered by a request +from the user to do so that is accompanied by a schemata of the region +to be pseudo-locked. The cache pseudo-locked region is created as follows: +- Create a CAT allocation CLOSNEW with a CBM matching the schemata + from the user of the cache region that will contain the pseudo-locked + memory. This region must not overlap with any current CAT allocation/CLOS + on the system and no future overlap with this cache region is allowed + while the pseudo-locked region exists. +- Create a contiguous region of memory of the same size as the cache + region. +- Flush the cache, disable hardware prefetchers, disable preemption. +- Make CLOSNEW the active CLOS and touch the allocated memory to load + it into the cache. +- Set the previous CLOS as active. +- At this point the closid CLOSNEW can be released - the cache + pseudo-locked region is protected as long as its CBM does not appear in + any CAT allocation. Even though the cache pseudo-locked region will from + this point on not appear in any CBM of any CLOS an application running with + any CLOS will be able to access the memory in the pseudo-locked region since + the region continues to serve cache hits. +- The contiguous region of memory loaded into the cache is exposed to + user-space as a character device. + +Cache pseudo-locking increases the probability that data will remain +in the cache via carefully configuring the CAT feature and controlling +application behavior. There is no guarantee that data is placed in +cache. Instructions like INVD, WBINVD, CLFLUSH, etc. can still evict +“locked†data from cache. Power management C-states may shrink or +power off cache. Deeper C-states will automatically be restricted on +pseudo-locked region creation. + +It is required that an application using a pseudo-locked region runs +with affinity to the cores (or a subset of the cores) associated +with the cache on which the pseudo-locked region resides. A sanity check +within the code will not allow an application to map pseudo-locked memory +unless it runs with affinity to cores associated with the cache on which the +pseudo-locked region resides. The sanity check is only done during the +initial mmap() handling, there is no enforcement afterwards and the +application self needs to ensure it remains affine to the correct cores. + +Pseudo-locking is accomplished in two stages: +1) During the first stage the system administrator allocates a portion + of cache that should be dedicated to pseudo-locking. At this time an + equivalent portion of memory is allocated, loaded into allocated + cache portion, and exposed as a character device. +2) During the second stage a user-space application maps (mmap()) the + pseudo-locked memory into its address space. + +Cache Pseudo-Locking Interface +------------------------------ +A pseudo-locked region is created using the resctrl interface as follows: + +1) Create a new resource group by creating a new directory in /sys/fs/resctrl. +2) Change the new resource group's mode to "pseudo-locksetup" by writing + "pseudo-locksetup" to the "mode" file. +3) Write the schemata of the pseudo-locked region to the "schemata" file. All + bits within the schemata should be "unused" according to the "bit_usage" + file. + +On successful pseudo-locked region creation the "mode" file will contain +"pseudo-locked" and a new character device with the same name as the resource +group will exist in /dev/pseudo_lock. This character device can be mmap()'ed +by user space in order to obtain access to the pseudo-locked memory region. + +An example of cache pseudo-locked region creation and usage can be found below. + +Cache Pseudo-Locking Debugging Interface +--------------------------------------- +The pseudo-locking debugging interface is enabled by default (if +CONFIG_DEBUG_FS is enabled) and can be found in /sys/kernel/debug/resctrl. + +There is no explicit way for the kernel to test if a provided memory +location is present in the cache. The pseudo-locking debugging interface uses +the tracing infrastructure to provide two ways to measure cache residency of +the pseudo-locked region: +1) Memory access latency using the pseudo_lock_mem_latency tracepoint. Data + from these measurements are best visualized using a hist trigger (see + example below). In this test the pseudo-locked region is traversed at + a stride of 32 bytes while hardware prefetchers and preemption + are disabled. This also provides a substitute visualization of cache + hits and misses. +2) Cache hit and miss measurements using model specific precision counters if + available. Depending on the levels of cache on the system the pseudo_lock_l2 + and pseudo_lock_l3 tracepoints are available. + WARNING: triggering this measurement uses from two (for just L2 + measurements) to four (for L2 and L3 measurements) precision counters on + the system, if any other measurements are in progress the counters and + their corresponding event registers will be clobbered. + +When a pseudo-locked region is created a new debugfs directory is created for +it in debugfs as /sys/kernel/debug/resctrl/<newdir>. A single +write-only file, pseudo_lock_measure, is present in this directory. The +measurement on the pseudo-locked region depends on the number, 1 or 2, +written to this debugfs file. Since the measurements are recorded with the +tracing infrastructure the relevant tracepoints need to be enabled before the +measurement is triggered. + +Example of latency debugging interface: +In this example a pseudo-locked region named "newlock" was created. Here is +how we can measure the latency in cycles of reading from this region and +visualize this data with a histogram that is available if CONFIG_HIST_TRIGGERS +is set: +# :> /sys/kernel/debug/tracing/trace +# echo 'hist:keys=latency' > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/trigger +# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable +# echo 1 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure +# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable +# cat /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/hist + +# event histogram +# +# trigger info: hist:keys=latency:vals=hitcount:sort=hitcount:size=2048 [active] +# + +{ latency: 456 } hitcount: 1 +{ latency: 50 } hitcount: 83 +{ latency: 36 } hitcount: 96 +{ latency: 44 } hitcount: 174 +{ latency: 48 } hitcount: 195 +{ latency: 46 } hitcount: 262 +{ latency: 42 } hitcount: 693 +{ latency: 40 } hitcount: 3204 +{ latency: 38 } hitcount: 3484 + +Totals: + Hits: 8192 + Entries: 9 + Dropped: 0 + +Example of cache hits/misses debugging: +In this example a pseudo-locked region named "newlock" was created on the L2 +cache of a platform. Here is how we can obtain details of the cache hits +and misses using the platform's precision counters. + +# :> /sys/kernel/debug/tracing/trace +# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable +# echo 2 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure +# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable +# cat /sys/kernel/debug/tracing/trace + +# tracer: nop +# +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + pseudo_lock_mea-1672 [002] .... 3132.860500: pseudo_lock_l2: hits=4097 miss=0 + + Examples for RDT allocation usage: Example 1 @@ -502,7 +711,172 @@ siblings and only the real time threads are scheduled on the cores 4-7. # echo F0 > p0/cpus -4) Locking between applications +Example 4 +--------- + +The resource groups in previous examples were all in the default "shareable" +mode allowing sharing of their cache allocations. If one resource group +configures a cache allocation then nothing prevents another resource group +to overlap with that allocation. + +In this example a new exclusive resource group will be created on a L2 CAT +system with two L2 cache instances that can be configured with an 8-bit +capacity bitmask. The new exclusive resource group will be configured to use +25% of each cache instance. + +# mount -t resctrl resctrl /sys/fs/resctrl/ +# cd /sys/fs/resctrl + +First, we observe that the default group is configured to allocate to all L2 +cache: + +# cat schemata +L2:0=ff;1=ff + +We could attempt to create the new resource group at this point, but it will +fail because of the overlap with the schemata of the default group: +# mkdir p0 +# echo 'L2:0=0x3;1=0x3' > p0/schemata +# cat p0/mode +shareable +# echo exclusive > p0/mode +-sh: echo: write error: Invalid argument +# cat info/last_cmd_status +schemata overlaps + +To ensure that there is no overlap with another resource group the default +resource group's schemata has to change, making it possible for the new +resource group to become exclusive. +# echo 'L2:0=0xfc;1=0xfc' > schemata +# echo exclusive > p0/mode +# grep . p0/* +p0/cpus:0 +p0/mode:exclusive +p0/schemata:L2:0=03;1=03 +p0/size:L2:0=262144;1=262144 + +A new resource group will on creation not overlap with an exclusive resource +group: +# mkdir p1 +# grep . p1/* +p1/cpus:0 +p1/mode:shareable +p1/schemata:L2:0=fc;1=fc +p1/size:L2:0=786432;1=786432 + +The bit_usage will reflect how the cache is used: +# cat info/L2/bit_usage +0=SSSSSSEE;1=SSSSSSEE + +A resource group cannot be forced to overlap with an exclusive resource group: +# echo 'L2:0=0x1;1=0x1' > p1/schemata +-sh: echo: write error: Invalid argument +# cat info/last_cmd_status +overlaps with exclusive group + +Example of Cache Pseudo-Locking +------------------------------- +Lock portion of L2 cache from cache id 1 using CBM 0x3. Pseudo-locked +region is exposed at /dev/pseudo_lock/newlock that can be provided to +application for argument to mmap(). + +# mount -t resctrl resctrl /sys/fs/resctrl/ +# cd /sys/fs/resctrl + +Ensure that there are bits available that can be pseudo-locked, since only +unused bits can be pseudo-locked the bits to be pseudo-locked needs to be +removed from the default resource group's schemata: +# cat info/L2/bit_usage +0=SSSSSSSS;1=SSSSSSSS +# echo 'L2:1=0xfc' > schemata +# cat info/L2/bit_usage +0=SSSSSSSS;1=SSSSSS00 + +Create a new resource group that will be associated with the pseudo-locked +region, indicate that it will be used for a pseudo-locked region, and +configure the requested pseudo-locked region capacity bitmask: + +# mkdir newlock +# echo pseudo-locksetup > newlock/mode +# echo 'L2:1=0x3' > newlock/schemata + +On success the resource group's mode will change to pseudo-locked, the +bit_usage will reflect the pseudo-locked region, and the character device +exposing the pseudo-locked region will exist: + +# cat newlock/mode +pseudo-locked +# cat info/L2/bit_usage +0=SSSSSSSS;1=SSSSSSPP +# ls -l /dev/pseudo_lock/newlock +crw------- 1 root root 243, 0 Apr 3 05:01 /dev/pseudo_lock/newlock + +/* + * Example code to access one page of pseudo-locked cache region + * from user space. + */ +#define _GNU_SOURCE +#include <fcntl.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/mman.h> + +/* + * It is required that the application runs with affinity to only + * cores associated with the pseudo-locked region. Here the cpu + * is hardcoded for convenience of example. + */ +static int cpuid = 2; + +int main(int argc, char *argv[]) +{ + cpu_set_t cpuset; + long page_size; + void *mapping; + int dev_fd; + int ret; + + page_size = sysconf(_SC_PAGESIZE); + + CPU_ZERO(&cpuset); + CPU_SET(cpuid, &cpuset); + ret = sched_setaffinity(0, sizeof(cpuset), &cpuset); + if (ret < 0) { + perror("sched_setaffinity"); + exit(EXIT_FAILURE); + } + + dev_fd = open("/dev/pseudo_lock/newlock", O_RDWR); + if (dev_fd < 0) { + perror("open"); + exit(EXIT_FAILURE); + } + + mapping = mmap(0, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, + dev_fd, 0); + if (mapping == MAP_FAILED) { + perror("mmap"); + close(dev_fd); + exit(EXIT_FAILURE); + } + + /* Application interacts with pseudo-locked memory @mapping */ + + ret = munmap(mapping, page_size); + if (ret < 0) { + perror("munmap"); + close(dev_fd); + exit(EXIT_FAILURE); + } + + close(dev_fd); + exit(EXIT_SUCCESS); +} + +Locking between applications +---------------------------- Certain operations on the resctrl filesystem, composed of read/writes to/from multiple files, must be atomic. @@ -510,7 +884,7 @@ to/from multiple files, must be atomic. As an example, the allocation of an exclusive reservation of L3 cache involves: - 1. Read the cbmmasks from each directory + 1. Read the cbmmasks from each directory or the per-resource "bit_usage" 2. Find a contiguous set of bits in the global CBM bitmask that is clear in any of the directory cbmmasks 3. Create a new directory diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt index 8d109ef67ab6..3a2ba436721a 100644 --- a/Documentation/x86/x86_64/boot-options.txt +++ b/Documentation/x86/x86_64/boot-options.txt @@ -156,6 +156,10 @@ NUMA If given as an integer, fills all system RAM with N fake nodes interleaved over physical nodes. + numa=fake=<N>U + If given as an integer followed by 'U', it will divide each + physical node into N emulated nodes. + ACPI acpi=off Don't enable ACPI diff --git a/MAINTAINERS b/MAINTAINERS index 192d7f73fd01..629e08703c82 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2523,7 +2523,7 @@ S: Supported F: drivers/scsi/esas2r ATUSB IEEE 802.15.4 RADIO DRIVER -M: Stefan Schmidt <stefan@osg.samsung.com> +M: Stefan Schmidt <stefan@datenfreihafen.org> L: linux-wpan@vger.kernel.org S: Maintained F: drivers/net/ieee802154/atusb.c @@ -5444,6 +5444,7 @@ F: drivers/iommu/exynos-iommu.c EZchip NPS platform support M: Vineet Gupta <vgupta@synopsys.com> +M: Ofer Levi <oferle@mellanox.com> S: Supported F: arch/arc/plat-eznps F: arch/arc/boot/dts/eznps.dts @@ -5790,7 +5791,6 @@ F: include/linux/fsl/ FREESCALE SOC FS_ENET DRIVER M: Pantelis Antoniou <pantelis.antoniou@gmail.com> -M: Vitaly Bordug <vbordug@ru.mvista.com> L: linuxppc-dev@lists.ozlabs.org L: netdev@vger.kernel.org S: Maintained @@ -5930,7 +5930,7 @@ F: Documentation/dev-tools/gcov.rst GDB KERNEL DEBUGGING HELPER SCRIPTS M: Jan Kiszka <jan.kiszka@siemens.com> -M: Kieran Bingham <kieran@bingham.xyz> +M: Kieran Bingham <kbingham@kernel.org> S: Supported F: scripts/gdb/ @@ -6909,7 +6909,7 @@ F: drivers/clk/clk-versaclock5.c IEEE 802.15.4 SUBSYSTEM M: Alexander Aring <alex.aring@gmail.com> -M: Stefan Schmidt <stefan@osg.samsung.com> +M: Stefan Schmidt <stefan@datenfreihafen.org> L: linux-wpan@vger.kernel.org W: http://wpan.cakelab.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git @@ -7096,6 +7096,7 @@ F: include/uapi/linux/input.h F: include/uapi/linux/input-event-codes.h F: include/linux/input/ F: Documentation/devicetree/bindings/input/ +F: Documentation/devicetree/bindings/serio/ F: Documentation/input/ INPUT MULTITOUCH (MT) PROTOCOL @@ -7985,7 +7986,7 @@ F: lib/test_kmod.c F: tools/testing/selftests/kmod/ KPROBES -M: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> +M: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> M: "David S. Miller" <davem@davemloft.net> M: Masami Hiramatsu <mhiramat@kernel.org> @@ -8316,10 +8317,16 @@ M: Jade Alglave <j.alglave@ucl.ac.uk> M: Luc Maranget <luc.maranget@inria.fr> M: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> R: Akira Yokosawa <akiyks@gmail.com> +R: Daniel Lustig <dlustig@nvidia.com> L: linux-kernel@vger.kernel.org +L: linux-arch@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git F: tools/memory-model/ +F: Documentation/atomic_bitops.txt +F: Documentation/atomic_t.txt +F: Documentation/core-api/atomic_ops.rst +F: Documentation/core-api/refcount-vs-atomic.rst F: Documentation/memory-barriers.txt LINUX SECURITY MODULE (LSM) FRAMEWORK @@ -8629,7 +8636,7 @@ MARVELL MWIFIEX WIRELESS DRIVER M: Amitkumar Karwar <amitkarwar@gmail.com> M: Nishant Sarmukadam <nishants@marvell.com> M: Ganapathi Bhat <gbhat@marvell.com> -M: Xinming Hu <huxm@marvell.com> +M: Xinming Hu <huxinming820@gmail.com> L: linux-wireless@vger.kernel.org S: Maintained F: drivers/net/wireless/marvell/mwifiex/ @@ -9075,7 +9082,7 @@ S: Maintained F: drivers/usb/mtu3/ MEGACHIPS STDPXXXX-GE-B850V3-FW LVDS/DP++ BRIDGES -M: Peter Senna Tschudin <peter.senna@collabora.com> +M: Peter Senna Tschudin <peter.senna@gmail.com> M: Martin Donnelly <martin.donnelly@ge.com> M: Martyn Welch <martyn.welch@collabora.co.uk> S: Maintained @@ -12038,9 +12045,9 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git F: Documentation/RCU/ X: Documentation/RCU/torture.txt F: include/linux/rcu* -X: include/linux/srcu.h +X: include/linux/srcu*.h F: kernel/rcu/ -X: kernel/torture.c +X: kernel/rcu/srcu*.c REAL TIME CLOCK (RTC) SUBSYSTEM M: Alessandro Zummo <a.zummo@towertech.it> @@ -13077,8 +13084,8 @@ L: linux-kernel@vger.kernel.org W: http://www.rdrop.com/users/paulmck/RCU/ S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git -F: include/linux/srcu.h -F: kernel/rcu/srcu.c +F: include/linux/srcu*.h +F: kernel/rcu/srcu*.c SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus) M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> @@ -14437,6 +14444,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git F: Documentation/RCU/torture.txt F: kernel/torture.c F: kernel/rcu/rcutorture.c +F: kernel/rcu/rcuperf.c F: kernel/locking/locktorture.c TOSHIBA ACPI EXTRAS DRIVER @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = NAME = Merciless Moray # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index 767bfdd42992..150a1c5d6a2c 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -18,11 +18,11 @@ * To ensure dependency ordering is preserved for the _relaxed and * _release atomics, an smp_read_barrier_depends() is unconditionally * inserted into the _relaxed variants, which are used to build the - * barriered versions. To avoid redundant back-to-back fences, we can - * define the _acquire and _fence versions explicitly. + * barriered versions. Avoid redundant back-to-back fences in the + * _acquire and _fence versions. */ -#define __atomic_op_acquire(op, args...) op##_relaxed(args) -#define __atomic_op_fence __atomic_op_release +#define __atomic_acquire_fence() +#define __atomic_post_full_fence() #define ATOMIC_INIT(i) { (i) } #define ATOMIC64_INIT(i) { (i) } @@ -206,7 +206,7 @@ ATOMIC_OPS(xor, xor) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -214,7 +214,7 @@ ATOMIC_OPS(xor, xor) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, new, old; smp_mb(); @@ -235,38 +235,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) smp_mb(); return old; } - +#define atomic_fetch_add_unless atomic_fetch_add_unless /** - * atomic64_add_unless - add unless the number is a given value + * atomic64_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, so long as it was not @u. - * Returns true iff @v was not @u. + * Returns the old value of @v. */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) +static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u) { - long c, tmp; + long c, new, old; smp_mb(); __asm__ __volatile__( - "1: ldq_l %[tmp],%[mem]\n" - " cmpeq %[tmp],%[u],%[c]\n" - " addq %[tmp],%[a],%[tmp]\n" + "1: ldq_l %[old],%[mem]\n" + " cmpeq %[old],%[u],%[c]\n" + " addq %[old],%[a],%[new]\n" " bne %[c],2f\n" - " stq_c %[tmp],%[mem]\n" - " beq %[tmp],3f\n" + " stq_c %[new],%[mem]\n" + " beq %[new],3f\n" "2:\n" ".subsection 2\n" "3: br 1b\n" ".previous" - : [tmp] "=&r"(tmp), [c] "=&r"(c) + : [old] "=&r"(old), [new] "=&r"(new), [c] "=&r"(c) : [mem] "m"(*v), [a] "rI"(a), [u] "rI"(u) : "memory"); smp_mb(); - return !c; + return old; } +#define atomic64_fetch_add_unless atomic64_fetch_add_unless /* * atomic64_dec_if_positive - decrement by 1 if old value positive @@ -295,31 +296,6 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) smp_mb(); return old - 1; } - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - -#define atomic_dec_return(v) atomic_sub_return(1,(v)) -#define atomic64_dec_return(v) atomic64_sub_return(1,(v)) - -#define atomic_inc_return(v) atomic_add_return(1,(v)) -#define atomic64_inc_return(v) atomic64_add_return(1,(v)) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0) - -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0) - -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) - -#define atomic_inc(v) atomic_add(1,(v)) -#define atomic64_inc(v) atomic64_add(1,(v)) - -#define atomic_dec(v) atomic_sub(1,(v)) -#define atomic64_dec(v) atomic64_sub(1,(v)) +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif /* _ALPHA_ATOMIC_H */ diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 6e921754c8fc..c210a25dd6da 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1180,13 +1180,10 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options, struct rusage32 __user *, ur) { - unsigned int status = 0; struct rusage r; - long err = kernel_wait4(pid, &status, options, &r); + long err = kernel_wait4(pid, ustatus, options, &r); if (err <= 0) return err; - if (put_user(status, ustatus)) - return -EFAULT; if (!ur) return err; if (put_tv_to_tv32(&ur->ru_utime, &r.ru_utime)) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index e81bcd271be7..5151d81476a1 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -50,6 +50,9 @@ config ARC select HAVE_KERNEL_LZMA select ARCH_HAS_PTE_SPECIAL +config ARCH_HAS_CACHE_LINE_SIZE + def_bool y + config MIGHT_HAVE_PCI bool @@ -413,7 +416,7 @@ config ARC_HAS_DIV_REM config ARC_HAS_ACCL_REGS bool "Reg Pair ACCL:ACCH (FPU and/or MPY > 6)" - default n + default y help Depending on the configuration, CPU can contain accumulator reg-pair (also referred to as r58:r59). These can also be used by gcc as GPR so diff --git a/arch/arc/Makefile b/arch/arc/Makefile index d37f49d6a27f..6c1b20dd76ad 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -16,7 +16,7 @@ endif KBUILD_DEFCONFIG := nsim_700_defconfig -cflags-y += -fno-common -pipe -fno-builtin -D__linux__ +cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__ cflags-$(CONFIG_ISA_ARCOMPACT) += -mA7 cflags-$(CONFIG_ISA_ARCV2) += -mcpu=archs @@ -140,16 +140,3 @@ dtbs: scripts archclean: $(Q)$(MAKE) $(clean)=$(boot) - -# Hacks to enable final link due to absence of link-time branch relexation -# and gcc choosing optimal(shorter) branches at -O3 -# -# vineetg Feb 2010: -mlong-calls switched off for overall kernel build -# However lib/decompress_inflate.o (.init.text) calls -# zlib_inflate_workspacesize (.text) causing relocation errors. -# Thus forcing all exten calls in this file to be long calls -export CFLAGS_decompress_inflate.o = -mmedium-calls -export CFLAGS_initramfs.o = -mmedium-calls -ifdef CONFIG_SMP -export CFLAGS_core.o = -mmedium-calls -endif diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index 09f85154c5a4..a635ea972304 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs/" CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 09fed3ef22b6..aa507e423075 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index ea2f6d817d1a..eba07f468654 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index ab231c040efe..098b19fbaa51 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_EXPERT=y CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index cf449cbf440d..0104c404d897 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 1b54c72f4296..6491be0ddbc9 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -9,7 +9,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 31c2c70b34a1..99e05cf63fca 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index a578c721d50f..0dc4f9b737e7 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index 37d7395f3272..be3c30a15e54 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -9,7 +9,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 1e1470e2a7f0..3a74b9b21772 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index 084a6e42685b..ea2834b4dc1d 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index f36d47990415..80a5a1b4924b 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -9,7 +9,6 @@ CONFIG_IKCONFIG_PROC=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 1aca2e8fd1ba..2cc87f909747 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -56,7 +56,6 @@ CONFIG_STMMAC_ETH=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set -CONFIG_DEVPTS_MULTIPLE_INSTANCES=y # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 11859287c52a..4e0072730241 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -187,7 +187,8 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ ATOMIC_OPS(add, +=, add) ATOMIC_OPS(sub, -=, sub) -#define atomic_andnot atomic_andnot +#define atomic_andnot atomic_andnot +#define atomic_fetch_andnot atomic_fetch_andnot #undef ATOMIC_OPS #define ATOMIC_OPS(op, c_op, asm_op) \ @@ -296,8 +297,6 @@ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3) ATOMIC_FETCH_OP(op, c_op, asm_op) ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3) -#define atomic_andnot(mask, v) atomic_and(~(mask), (v)) -#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v)) ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3) ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) @@ -308,48 +307,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v - */ -#define __atomic_add_unless(v, a, u) \ -({ \ - int c, old; \ - \ - /* \ - * Explicit full memory barrier needed before/after as \ - * LLOCK/SCOND thmeselves don't provide any such semantics \ - */ \ - smp_mb(); \ - \ - c = atomic_read(v); \ - while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\ - c = old; \ - \ - smp_mb(); \ - \ - c; \ -}) - -#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) - -#define atomic_inc(v) atomic_add(1, v) -#define atomic_dec(v) atomic_sub(1, v) - -#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0) - - #ifdef CONFIG_GENERIC_ATOMIC64 #include <asm-generic/atomic64.h> @@ -472,7 +429,8 @@ static inline long long atomic64_fetch_##op(long long a, atomic64_t *v) \ ATOMIC64_OP_RETURN(op, op1, op2) \ ATOMIC64_FETCH_OP(op, op1, op2) -#define atomic64_andnot atomic64_andnot +#define atomic64_andnot atomic64_andnot +#define atomic64_fetch_andnot atomic64_fetch_andnot ATOMIC64_OPS(add, add.f, adc) ATOMIC64_OPS(sub, sub.f, sbc) @@ -559,53 +517,43 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) return val; } +#define atomic64_dec_if_positive atomic64_dec_if_positive /** - * atomic64_add_unless - add unless the number is a given value + * atomic64_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * - * if (v != u) { v += a; ret = 1} else {ret = 0} - * Returns 1 iff @v was not @u (i.e. if add actually happened) + * Atomically adds @a to @v, if it was not @u. + * Returns the old value of @v */ -static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) +static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, + long long u) { - long long val; - int op_done; + long long old, temp; smp_mb(); __asm__ __volatile__( "1: llockd %0, [%2] \n" - " mov %1, 1 \n" " brne %L0, %L4, 2f # continue to add since v != u \n" " breq.d %H0, %H4, 3f # return since v == u \n" - " mov %1, 0 \n" "2: \n" - " add.f %L0, %L0, %L3 \n" - " adc %H0, %H0, %H3 \n" - " scondd %0, [%2] \n" + " add.f %L1, %L0, %L3 \n" + " adc %H1, %H0, %H3 \n" + " scondd %1, [%2] \n" " bnz 1b \n" "3: \n" - : "=&r"(val), "=&r" (op_done) + : "=&r"(old), "=&r" (temp) : "r"(&v->counter), "r"(a), "r"(u) : "cc"); /* memory clobber comes from smp_mb() */ smp_mb(); - return op_done; + return old; } - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* !CONFIG_GENERIC_ATOMIC64 */ diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 8486f328cc5d..ff7d3232764a 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -48,7 +48,9 @@ }) /* Largest line length for either L1 or L2 is 128 bytes */ -#define ARCH_DMA_MINALIGN 128 +#define SMP_CACHE_BYTES 128 +#define cache_line_size() SMP_CACHE_BYTES +#define ARCH_DMA_MINALIGN SMP_CACHE_BYTES extern void arc_cache_init(void); extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len); diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index d5da2115d78a..03d6bb0f4e13 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -17,8 +17,11 @@ #ifndef __ASM_ARC_UDELAY_H #define __ASM_ARC_UDELAY_H +#include <asm-generic/types.h> #include <asm/param.h> /* HZ */ +extern unsigned long loops_per_jiffy; + static inline void __delay(unsigned long loops) { __asm__ __volatile__( diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h index ec36d5b6d435..29f3988c9424 100644 --- a/arch/arc/include/asm/entry-compact.h +++ b/arch/arc/include/asm/entry-compact.h @@ -234,6 +234,9 @@ POP gp RESTORE_R12_TO_R0 +#ifdef CONFIG_ARC_CURR_IN_REG + ld r25, [sp, 12] +#endif ld sp, [sp] /* restore original sp */ /* orig_r0, ECR, user_r25 skipped automatically */ .endm @@ -315,6 +318,9 @@ POP gp RESTORE_R12_TO_R0 +#ifdef CONFIG_ARC_CURR_IN_REG + ld r25, [sp, 12] +#endif ld sp, [sp] /* restore original sp */ /* orig_r0, ECR, user_r25 skipped automatically */ .endm diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index 51597f344a62..302b0db8ea2b 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -86,9 +86,6 @@ POP r1 POP r0 -#ifdef CONFIG_ARC_CURR_IN_REG - ld r25, [sp, 12] -#endif .endm /*-------------------------------------------------------------- diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h index 2e52d18e6bc7..2c1b479d5aea 100644 --- a/arch/arc/include/asm/kprobes.h +++ b/arch/arc/include/asm/kprobes.h @@ -45,8 +45,6 @@ struct prev_kprobe { struct kprobe_ctlblk { unsigned int kprobe_status; - struct pt_regs jprobe_saved_regs; - char jprobes_stack[MAX_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h index c28e6c347b49..871f3cb16af9 100644 --- a/arch/arc/include/asm/mach_desc.h +++ b/arch/arc/include/asm/mach_desc.h @@ -34,9 +34,7 @@ struct machine_desc { const char *name; const char **dt_compat; void (*init_early)(void); -#ifdef CONFIG_SMP void (*init_per_cpu)(unsigned int); -#endif void (*init_machine)(void); void (*init_late)(void); diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index 109baa06831c..09ddddf71cc5 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -105,7 +105,7 @@ typedef pte_t * pgtable_t; #define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) /* Default Permissions for stack/heaps pages (Non Executable) */ -#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE) +#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define WANT_PAGE_VIRTUAL 1 diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 8ec5599a0957..cf4be70d5892 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -377,7 +377,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, /* Decode a PTE containing swap "identifier "into constituents */ #define __swp_type(pte_lookalike) (((pte_lookalike).val) & 0x1f) -#define __swp_offset(pte_lookalike) ((pte_lookalike).val << 13) +#define __swp_offset(pte_lookalike) ((pte_lookalike).val >> 13) /* NOPs, to keep generic kernel happy */ #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c index 538b36afe89e..62b185057c04 100644 --- a/arch/arc/kernel/irq.c +++ b/arch/arc/kernel/irq.c @@ -31,10 +31,10 @@ void __init init_IRQ(void) /* a SMP H/w block could do IPI IRQ request here */ if (plat_smp_ops.init_per_cpu) plat_smp_ops.init_per_cpu(smp_processor_id()); +#endif if (machine_desc->init_per_cpu) machine_desc->init_per_cpu(smp_processor_id()); -#endif } /* diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index 42b05046fad9..df35d4c0b0b8 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -225,24 +225,18 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) /* If we have no pre-handler or it returned 0, we continue with * normal processing. If we have a pre-handler and it returned - * non-zero - which is expected from setjmp_pre_handler for - * jprobe, we return without single stepping and leave that to - * the break-handler which is invoked by a kprobe from - * jprobe_return + * non-zero - which means user handler setup registers to exit + * to another instruction, we must skip the single stepping. */ if (!p->pre_handler || !p->pre_handler(p, regs)) { setup_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; + } else { + reset_current_kprobe(); + preempt_enable_no_resched(); } return 1; - } else if (kprobe_running()) { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - setup_singlestep(p, regs); - kcb->kprobe_status = KPROBE_HIT_SS; - return 1; - } } /* no_kprobe: */ @@ -386,38 +380,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long sp_addr = regs->sp; - - kcb->jprobe_saved_regs = *regs; - memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr)); - regs->ret = (unsigned long)(jp->entry); - - return 1; -} - -void __kprobes jprobe_return(void) -{ - __asm__ __volatile__("unimp_s"); - return; -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long sp_addr; - - *regs = kcb->jprobe_saved_regs; - sp_addr = regs->sp; - memcpy((void *)sp_addr, kcb->jprobes_stack, MIN_STACK_SIZE(sp_addr)); - preempt_enable_no_resched(); - - return 1; -} - static void __used kretprobe_trampoline_holder(void) { __asm__ __volatile__(".global kretprobe_trampoline\n" @@ -483,9 +445,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_assert(ri, orig_ret_address, trampoline_address); regs->ret = orig_ret_address; - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 5ac3b547453f..4674541eba3f 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -47,7 +47,8 @@ SYSCALL_DEFINE0(arc_gettls) SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new) { struct pt_regs *regs = current_pt_regs(); - int uval = -EFAULT; + u32 uval; + int ret; /* * This is only for old cores lacking LLOCK/SCOND, which by defintion @@ -60,23 +61,47 @@ SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new) /* Z indicates to userspace if operation succeded */ regs->status32 &= ~STATUS_Z_MASK; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) - return -EFAULT; + ret = access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr)); + if (!ret) + goto fail; +again: preempt_disable(); - if (__get_user(uval, uaddr)) - goto done; + ret = __get_user(uval, uaddr); + if (ret) + goto fault; - if (uval == expected) { - if (!__put_user(new, uaddr)) - regs->status32 |= STATUS_Z_MASK; - } + if (uval != expected) + goto out; -done: - preempt_enable(); + ret = __put_user(new, uaddr); + if (ret) + goto fault; + + regs->status32 |= STATUS_Z_MASK; +out: + preempt_enable(); return uval; + +fault: + preempt_enable(); + + if (unlikely(ret != -EFAULT)) + goto fail; + + down_read(¤t->mm->mmap_sem); + ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr, + FAULT_FLAG_WRITE, NULL); + up_read(¤t->mm->mmap_sem); + + if (likely(!ret)) + goto again; + +fail: + force_sig(SIGSEGV, current); + return ret; } #ifdef CONFIG_ISA_ARCV2 diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 9dbe645ee127..25c631942500 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -1038,7 +1038,7 @@ void flush_cache_mm(struct mm_struct *mm) void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr, unsigned long pfn) { - unsigned int paddr = pfn << PAGE_SHIFT; + phys_addr_t paddr = pfn << PAGE_SHIFT; u_vaddr &= PAGE_MASK; @@ -1058,8 +1058,9 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long u_vaddr) { /* TBD: do we really need to clear the kernel mapping */ - __flush_dcache_page(page_address(page), u_vaddr); - __flush_dcache_page(page_address(page), page_address(page)); + __flush_dcache_page((phys_addr_t)page_address(page), u_vaddr); + __flush_dcache_page((phys_addr_t)page_address(page), + (phys_addr_t)page_address(page)); } @@ -1246,6 +1247,16 @@ void __init arc_cache_init_master(void) } } + /* + * Check that SMP_CACHE_BYTES (and hence ARCH_DMA_MINALIGN) is larger + * or equal to any cache line length. + */ + BUILD_BUG_ON_MSG(L1_CACHE_BYTES > SMP_CACHE_BYTES, + "SMP_CACHE_BYTES must be >= any cache line length"); + if (is_isa_arcv2() && (l2_line_sz > SMP_CACHE_BYTES)) + panic("L2 Cache line [%d] > kernel Config [%d]\n", + l2_line_sz, SMP_CACHE_BYTES); + /* Note that SLC disable not formally supported till HS 3.0 */ if (is_isa_arcv2() && l2_line_sz && !slc_enable) arc_slc_disable(); diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 8c1071840979..ec47e6079f5d 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -129,14 +129,59 @@ int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma, return ret; } +/* + * Cache operations depending on function and direction argument, inspired by + * https://lkml.org/lkml/2018/5/18/979 + * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20] + * dma-mapping: provide a generic dma-noncoherent implementation)" + * + * | map == for_device | unmap == for_cpu + * |---------------------------------------------------------------- + * TO_DEV | writeback writeback | none none + * FROM_DEV | invalidate invalidate | invalidate* invalidate* + * BIDIR | writeback+inv writeback+inv | invalidate invalidate + * + * [*] needed for CPU speculative prefetches + * + * NOTE: we don't check the validity of direction argument as it is done in + * upper layer functions (in include/linux/dma-mapping.h) + */ + void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - dma_cache_wback(paddr, size); + switch (dir) { + case DMA_TO_DEVICE: + dma_cache_wback(paddr, size); + break; + + case DMA_FROM_DEVICE: + dma_cache_inv(paddr, size); + break; + + case DMA_BIDIRECTIONAL: + dma_cache_wback_inv(paddr, size); + break; + + default: + break; + } } void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - dma_cache_inv(paddr, size); + switch (dir) { + case DMA_TO_DEVICE: + break; + + /* FROM_DEVICE invalidate needed if speculative CPU prefetch only */ + case DMA_FROM_DEVICE: + case DMA_BIDIRECTIONAL: + dma_cache_inv(paddr, size); + break; + + default: + break; + } } diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h index 0c7d11022d0f..4f6a1673b3a6 100644 --- a/arch/arc/plat-eznps/include/plat/ctop.h +++ b/arch/arc/plat-eznps/include/plat/ctop.h @@ -21,6 +21,7 @@ #error "Incorrect ctop.h include" #endif +#include <linux/types.h> #include <soc/nps/common.h> /* core auxiliary registers */ @@ -143,6 +144,15 @@ struct nps_host_reg_gim_p_int_dst { }; /* AUX registers definition */ +struct nps_host_reg_aux_dpc { + union { + struct { + u32 ien:1, men:1, hen:1, reserved:29; + }; + u32 value; + }; +}; + struct nps_host_reg_aux_udmc { union { struct { diff --git a/arch/arc/plat-eznps/mtm.c b/arch/arc/plat-eznps/mtm.c index 2388de3d09ef..ed0077ef666e 100644 --- a/arch/arc/plat-eznps/mtm.c +++ b/arch/arc/plat-eznps/mtm.c @@ -15,6 +15,8 @@ */ #include <linux/smp.h> +#include <linux/init.h> +#include <linux/kernel.h> #include <linux/io.h> #include <linux/log2.h> #include <asm/arcregs.h> @@ -157,10 +159,10 @@ void mtm_enable_core(unsigned int cpu) /* Verify and set the value of the mtm hs counter */ static int __init set_mtm_hs_ctr(char *ctr_str) { - long hs_ctr; + int hs_ctr; int ret; - ret = kstrtol(ctr_str, 0, &hs_ctr); + ret = kstrtoint(ctr_str, 0, &hs_ctr); if (ret || hs_ctr > MT_HS_CNT_MAX || hs_ctr < MT_HS_CNT_MIN) { pr_err("** Invalid @nps_mtm_hs_ctr [%d] needs to be [%d:%d] (incl)\n", diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index 19ab3cf98f0f..9356753c2ed8 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -7,5 +7,8 @@ menuconfig ARC_SOC_HSDK bool "ARC HS Development Kit SOC" + depends on ISA_ARCV2 + select ARC_HAS_ACCL_REGS select CLK_HSDK select RESET_HSDK + select MIGHT_HAVE_PCI diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index 2958aedb649a..2588b842407c 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -42,6 +42,66 @@ static void __init hsdk_init_per_cpu(unsigned int cpu) #define SDIO_UHS_REG_EXT (SDIO_BASE + 0x108) #define SDIO_UHS_REG_EXT_DIV_2 (2 << 30) +#define HSDK_GPIO_INTC (ARC_PERIPHERAL_BASE + 0x3000) + +static void __init hsdk_enable_gpio_intc_wire(void) +{ + /* + * Peripherals on CPU Card are wired to cpu intc via intermediate + * DW APB GPIO blocks (mainly for debouncing) + * + * --------------------- + * | snps,archs-intc | + * --------------------- + * | + * ---------------------- + * | snps,archs-idu-intc | + * ---------------------- + * | | | | | + * | [eth] [USB] [... other peripherals] + * | + * ------------------- + * | snps,dw-apb-intc | + * ------------------- + * | | | | + * [Bt] [HAPS] [... other peripherals] + * + * Current implementation of "irq-dw-apb-ictl" driver doesn't work well + * with stacked INTCs. In particular problem happens if its master INTC + * not yet instantiated. See discussion here - + * https://lkml.org/lkml/2015/3/4/755 + * + * So setup the first gpio block as a passive pass thru and hide it from + * DT hardware topology - connect intc directly to cpu intc + * The GPIO "wire" needs to be init nevertheless (here) + * + * One side adv is that peripheral interrupt handling avoids one nested + * intc ISR hop + * + * According to HSDK User's Manual [1], "Table 2 Interrupt Mapping" + * we have the following GPIO input lines used as sources of interrupt: + * - GPIO[0] - Bluetooth interrupt of RS9113 module + * - GPIO[2] - HAPS interrupt (on HapsTrak 3 connector) + * - GPIO[3] - Audio codec (MAX9880A) interrupt + * - GPIO[8-23] - Available on Arduino and PMOD_x headers + * For now there's no use of Arduino and PMOD_x headers in Linux + * use-case so we only enable lines 0, 2 and 3. + * + * [1] https://github.com/foss-for-synopsys-dwc-arc-processors/ARC-Development-Systems-Forum/wiki/docs/ARC_HSDK_User_Guide.pdf + */ +#define GPIO_INTEN (HSDK_GPIO_INTC + 0x30) +#define GPIO_INTMASK (HSDK_GPIO_INTC + 0x34) +#define GPIO_INTTYPE_LEVEL (HSDK_GPIO_INTC + 0x38) +#define GPIO_INT_POLARITY (HSDK_GPIO_INTC + 0x3c) +#define GPIO_INT_CONNECTED_MASK 0x0d + + iowrite32(0xffffffff, (void __iomem *) GPIO_INTMASK); + iowrite32(~GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTMASK); + iowrite32(0x00000000, (void __iomem *) GPIO_INTTYPE_LEVEL); + iowrite32(0xffffffff, (void __iomem *) GPIO_INT_POLARITY); + iowrite32(GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTEN); +} + static void __init hsdk_init_early(void) { /* @@ -62,6 +122,8 @@ static void __init hsdk_init_early(void) * minimum possible div-by-2. */ iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT); + + hsdk_enable_gpio_intc_wire(); } static const char *hsdk_compat[] __initconst = { diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 843edfd000be..d7a81284c272 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -337,8 +337,8 @@ config ARCH_MULTIPLATFORM select TIMER_OF select COMMON_CLK select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select MIGHT_HAVE_PCI - select MULTI_IRQ_HANDLER select PCI_DOMAINS if PCI select SPARSE_IRQ select USE_OF @@ -465,9 +465,9 @@ config ARCH_DOVE bool "Marvell Dove" select CPU_PJ4 select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB select MIGHT_HAVE_PCI - select MULTI_IRQ_HANDLER select MVEBU_MBUS select PINCTRL select PINCTRL_DOVE @@ -512,8 +512,8 @@ config ARCH_LPC32XX select COMMON_CLK select CPU_ARM926T select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB - select MULTI_IRQ_HANDLER select SPARSE_IRQ select USE_OF help @@ -532,11 +532,11 @@ config ARCH_PXA select TIMER_OF select CPU_XSCALE if !CPU_XSC3 select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIO_PXA select GPIOLIB select HAVE_IDE select IRQ_DOMAIN - select MULTI_IRQ_HANDLER select PLAT_PXA select SPARSE_IRQ help @@ -572,11 +572,11 @@ config ARCH_SA1100 select CPU_FREQ select CPU_SA1100 select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB select HAVE_IDE select IRQ_DOMAIN select ISA - select MULTI_IRQ_HANDLER select NEED_MACH_MEMORY_H select SPARSE_IRQ help @@ -590,10 +590,10 @@ config ARCH_S3C24XX select GENERIC_CLOCKEVENTS select GPIO_SAMSUNG select GPIOLIB + select GENERIC_IRQ_MULTI_HANDLER select HAVE_S3C2410_I2C if I2C select HAVE_S3C2410_WATCHDOG if WATCHDOG select HAVE_S3C_RTC if RTC_CLASS - select MULTI_IRQ_HANDLER select NEED_MACH_IO_H select SAMSUNG_ATAGS select USE_OF @@ -627,10 +627,10 @@ config ARCH_OMAP1 select CLKSRC_MMIO select GENERIC_CLOCKEVENTS select GENERIC_IRQ_CHIP + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB select HAVE_IDE select IRQ_DOMAIN - select MULTI_IRQ_HANDLER select NEED_MACH_IO_H if PCCARD select NEED_MACH_MEMORY_H select SPARSE_IRQ @@ -921,11 +921,6 @@ config IWMMXT Enable support for iWMMXt context switching at run time if running on a CPU that supports it. -config MULTI_IRQ_HANDLER - bool - help - Allow each machine to specify it's own IRQ handler at run time. - if !MMU source "arch/arm/Kconfig-nommu" endif diff --git a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi index 19a075aee19e..f14df0baf2ab 100644 --- a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi +++ b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi @@ -692,7 +692,7 @@ dsa,member = <0 0>; eeprom-length = <512>; interrupt-parent = <&gpio6>; - interrupts = <3 IRQ_TYPE_EDGE_FALLING>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index bdf73cbcec3a..e7c3c563ff8f 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -159,13 +159,7 @@ dais = <&mcbsp2_port>, <&mcbsp3_port>; }; -}; - -&dss { - status = "okay"; -}; -&gpio6 { pwm8: dmtimer-pwm-8 { pinctrl-names = "default"; pinctrl-0 = <&vibrator_direction_pin>; @@ -192,7 +186,10 @@ pwm-names = "enable", "direction"; direction-duty-cycle-ns = <10000000>; }; +}; +&dss { + status = "okay"; }; &dsi1 { diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 66d0e215a773..f74756641410 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -130,7 +130,7 @@ static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new) } #define atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int oldval, newval; unsigned long tmp; @@ -156,6 +156,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) return oldval; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #else /* ARM_ARCH_6 */ @@ -215,15 +216,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - - c = atomic_read(v); - while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c) - c = old; - return c; -} +#define atomic_fetch_andnot atomic_fetch_andnot #endif /* __LINUX_ARM_ARCH__ */ @@ -254,17 +247,6 @@ ATOMIC_OPS(xor, ^=, eor) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -#define atomic_inc(v) atomic_add(1, v) -#define atomic_dec(v) atomic_sub(1, v) - -#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic_inc_return_relaxed(v) (atomic_add_return_relaxed(1, v)) -#define atomic_dec_return_relaxed(v) (atomic_sub_return_relaxed(1, v)) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0) - #ifndef CONFIG_GENERIC_ATOMIC64 typedef struct { long long counter; @@ -494,12 +476,13 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) return result; } +#define atomic64_dec_if_positive atomic64_dec_if_positive -static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) +static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, + long long u) { - long long val; + long long oldval, newval; unsigned long tmp; - int ret = 1; smp_mb(); prefetchw(&v->counter); @@ -508,33 +491,23 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) "1: ldrexd %0, %H0, [%4]\n" " teq %0, %5\n" " teqeq %H0, %H5\n" -" moveq %1, #0\n" " beq 2f\n" -" adds %Q0, %Q0, %Q6\n" -" adc %R0, %R0, %R6\n" -" strexd %2, %0, %H0, [%4]\n" +" adds %Q1, %Q0, %Q6\n" +" adc %R1, %R0, %R6\n" +" strexd %2, %1, %H1, [%4]\n" " teq %2, #0\n" " bne 1b\n" "2:" - : "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter) + : "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "r" (u), "r" (a) : "cc"); - if (ret) + if (oldval != u) smp_mb(); - return ret; + return oldval; } - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* !CONFIG_GENERIC_ATOMIC64 */ #endif diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 17f1f1a814ff..38badaae8d9d 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -58,6 +58,9 @@ void efi_virtmap_unload(void); #define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (false) +#define efi_table_attr(table, attr, instance) \ + ((table##_t *)instance)->attr + #define efi_call_proto(protocol, f, instance, ...) \ ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h index e46e4e7bdba3..ac54c06764e6 100644 --- a/arch/arm/include/asm/hw_breakpoint.h +++ b/arch/arm/include/asm/hw_breakpoint.h @@ -111,14 +111,17 @@ static inline void decode_ctrl_reg(u32 reg, asm volatile("mcr p14, 0, %0, " #N "," #M ", " #OP2 : : "r" (VAL));\ } while (0) +struct perf_event_attr; struct notifier_block; struct perf_event; struct pmu; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, int *gen_len, int *gen_type); -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index b6f319606e30..c883fcbe93b6 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -31,11 +31,6 @@ extern void asm_do_IRQ(unsigned int, struct pt_regs *); void handle_IRQ(unsigned int, struct pt_regs *); void init_IRQ(void); -#ifdef CONFIG_MULTI_IRQ_HANDLER -extern void (*handle_arch_irq)(struct pt_regs *); -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); -#endif - #ifdef CONFIG_SMP extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self); diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index 59655459da59..82290f212d8e 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -44,8 +44,6 @@ struct prev_kprobe { struct kprobe_ctlblk { unsigned int kprobe_status; struct prev_kprobe prev_kprobe; - struct pt_regs jprobe_saved_regs; - char jprobes_stack[MAX_STACK_SIZE]; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 5c1ad11aa392..bb8851208e17 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -59,7 +59,7 @@ struct machine_desc { void (*init_time)(void); void (*init_machine)(void); void (*init_late)(void); -#ifdef CONFIG_MULTI_IRQ_HANDLER +#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER void (*handle_irq)(struct pt_regs *); #endif void (*restart)(enum reboot_mode, const char *); diff --git a/arch/arm/include/asm/probes.h b/arch/arm/include/asm/probes.h index 1e5b9bb92270..991c9127c650 100644 --- a/arch/arm/include/asm/probes.h +++ b/arch/arm/include/asm/probes.h @@ -51,7 +51,6 @@ struct arch_probes_insn { * We assume one instruction can consume at most 64 bytes stack, which is * 'push {r0-r15}'. Instructions consume more or unknown stack space like * 'str r0, [sp, #-80]' and 'str r0, [sp, r1]' should be prohibit to probe. - * Both kprobe and jprobe use this macro. */ #define MAX_STACK_SIZE 64 diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 179a9f6bd1e3..e85a3af9ddeb 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -22,7 +22,7 @@ #include <asm/glue-df.h> #include <asm/glue-pf.h> #include <asm/vfpmacros.h> -#ifndef CONFIG_MULTI_IRQ_HANDLER +#ifndef CONFIG_GENERIC_IRQ_MULTI_HANDLER #include <mach/entry-macro.S> #endif #include <asm/thread_notify.h> @@ -39,7 +39,7 @@ * Interrupt handling. */ .macro irq_handler -#ifdef CONFIG_MULTI_IRQ_HANDLER +#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER ldr r1, =handle_arch_irq mov r0, sp badr lr, 9997f @@ -1226,9 +1226,3 @@ vector_addrexcptn: .globl cr_alignment cr_alignment: .space 4 - -#ifdef CONFIG_MULTI_IRQ_HANDLER - .globl handle_arch_irq -handle_arch_irq: - .space 4 -#endif diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 106a1466518d..746565a876dc 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -48,6 +48,7 @@ saved_pc .req lr * from those features make this path too inefficient. */ ret_fast_syscall: +__ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts @@ -78,6 +79,7 @@ fast_work_pending: * call. */ ret_fast_syscall: +__ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 @@ -255,7 +257,7 @@ local_restart: tst r10, #_TIF_SYSCALL_WORK @ are we tracing syscalls? bne __sys_trace - invoke_syscall tbl, scno, r10, ret_fast_syscall + invoke_syscall tbl, scno, r10, __ret_fast_syscall add r1, sp, #S_OFF 2: cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE) diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 629e25152c0d..1d5fbf1d1c67 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -456,14 +456,13 @@ static int get_hbp_len(u8 hbp_len) /* * Check whether bp virtual address is in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = get_hbp_len(info->ctrl.len); + va = hw->address; + len = get_hbp_len(hw->ctrl.len); return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -518,42 +517,42 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, /* * Construct an arch_hw_breakpoint from a perf_event. */ -static int arch_build_bp_info(struct perf_event *bp) +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_X: - info->ctrl.type = ARM_BREAKPOINT_EXECUTE; + hw->ctrl.type = ARM_BREAKPOINT_EXECUTE; break; case HW_BREAKPOINT_R: - info->ctrl.type = ARM_BREAKPOINT_LOAD; + hw->ctrl.type = ARM_BREAKPOINT_LOAD; break; case HW_BREAKPOINT_W: - info->ctrl.type = ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_STORE; break; case HW_BREAKPOINT_RW: - info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; break; default: return -EINVAL; } /* Len */ - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->ctrl.len = ARM_BREAKPOINT_LEN_1; + hw->ctrl.len = ARM_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->ctrl.len = ARM_BREAKPOINT_LEN_2; + hw->ctrl.len = ARM_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_4: - info->ctrl.len = ARM_BREAKPOINT_LEN_4; + hw->ctrl.len = ARM_BREAKPOINT_LEN_4; break; case HW_BREAKPOINT_LEN_8: - info->ctrl.len = ARM_BREAKPOINT_LEN_8; - if ((info->ctrl.type != ARM_BREAKPOINT_EXECUTE) + hw->ctrl.len = ARM_BREAKPOINT_LEN_8; + if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE) && max_watchpoint_len >= 8) break; default: @@ -566,24 +565,24 @@ static int arch_build_bp_info(struct perf_event *bp) * by the hardware and must be aligned to the appropriate number of * bytes. */ - if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE && - info->ctrl.len != ARM_BREAKPOINT_LEN_2 && - info->ctrl.len != ARM_BREAKPOINT_LEN_4) + if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE && + hw->ctrl.len != ARM_BREAKPOINT_LEN_2 && + hw->ctrl.len != ARM_BREAKPOINT_LEN_4) return -EINVAL; /* Address */ - info->address = bp->attr.bp_addr; + hw->address = attr->bp_addr; /* Privilege */ - info->ctrl.privilege = ARM_BREAKPOINT_USER; - if (arch_check_bp_in_kernelspace(bp)) - info->ctrl.privilege |= ARM_BREAKPOINT_PRIV; + hw->ctrl.privilege = ARM_BREAKPOINT_USER; + if (arch_check_bp_in_kernelspace(hw)) + hw->ctrl.privilege |= ARM_BREAKPOINT_PRIV; /* Enabled? */ - info->ctrl.enabled = !bp->attr.disabled; + hw->ctrl.enabled = !attr->disabled; /* Mismatch */ - info->ctrl.mismatch = 0; + hw->ctrl.mismatch = 0; return 0; } @@ -591,9 +590,10 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings. */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); int ret = 0; u32 offset, alignment_mask = 0x3; @@ -602,14 +602,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) return -ENODEV; /* Build the arch_hw_breakpoint. */ - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) goto out; /* Check address alignment. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8) alignment_mask = 0x7; - offset = info->address & alignment_mask; + offset = hw->address & alignment_mask; switch (offset) { case 0: /* Aligned */ @@ -617,19 +617,19 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) case 1: case 2: /* Allow halfword watchpoints and breakpoints. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_2) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; case 3: /* Allow single byte watchpoint. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_1) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; default: ret = -EINVAL; goto out; } - info->address &= ~alignment_mask; - info->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + hw->ctrl.len <<= offset; if (is_default_overflow_handler(bp)) { /* @@ -640,7 +640,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) return -EINVAL; /* We don't allow mismatch breakpoints in kernel space. */ - if (arch_check_bp_in_kernelspace(bp)) + if (arch_check_bp_in_kernelspace(hw)) return -EPERM; /* @@ -655,8 +655,8 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * reports them. */ if (!debug_exception_updates_fsr() && - (info->ctrl.type == ARM_BREAKPOINT_LOAD || - info->ctrl.type == ARM_BREAKPOINT_STORE)) + (hw->ctrl.type == ARM_BREAKPOINT_LOAD || + hw->ctrl.type == ARM_BREAKPOINT_STORE)) return -EINVAL; } diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index ece04a457486..9908dacf9229 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -102,16 +102,6 @@ void __init init_IRQ(void) uniphier_cache_init(); } -#ifdef CONFIG_MULTI_IRQ_HANDLER -void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) -{ - if (handle_arch_irq) - return; - - handle_arch_irq = handle_irq; -} -#endif - #ifdef CONFIG_SPARSE_IRQ int __init arch_probe_nr_irqs(void) { diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 225d1c58d2de..d9c299133111 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -338,6 +338,7 @@ static struct vm_area_struct gate_vma = { static int __init gate_vma_init(void) { + vma_init(&gate_vma, NULL); gate_vma.vm_page_prot = PAGE_READONLY_EXEC; return 0; } diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 35ca494c028c..4c249cb261f3 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -1145,7 +1145,7 @@ void __init setup_arch(char **cmdline_p) reserve_crashkernel(); -#ifdef CONFIG_MULTI_IRQ_HANDLER +#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER handle_arch_irq = mdesc->handle_irq; #endif diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index 39aef4876ed4..04b2f22c2739 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -212,7 +212,7 @@ static DEFINE_MUTEX(ecard_mutex); */ static void ecard_init_pgtables(struct mm_struct *mm) { - struct vm_area_struct vma; + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, VM_EXEC); /* We want to set up the page tables for the following mapping: * Virtual Physical @@ -237,9 +237,6 @@ static void ecard_init_pgtables(struct mm_struct *mm) memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE)); - vma.vm_flags = VM_EXEC; - vma.vm_mm = mm; - flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE); flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE); } diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index e90cc8a08186..f8bd523d64d1 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -47,9 +47,6 @@ (unsigned long)(addr) + \ (size)) -/* Used as a marker in ARM_pc to note when we're in a jprobe. */ -#define JPROBE_MAGIC_ADDR 0xffffffff - DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -289,8 +286,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs) break; case KPROBE_REENTER: /* A nested probe was hit in FIQ, it is a BUG */ - pr_warn("Unrecoverable kprobe detected at %p.\n", - p->addr); + pr_warn("Unrecoverable kprobe detected.\n"); + dump_kprobe(p); /* fall through */ default: /* impossible cases */ @@ -303,10 +300,10 @@ void __kprobes kprobe_handler(struct pt_regs *regs) /* * If we have no pre-handler or it returned 0, we - * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry, - * so get out doing nothing more here. + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. */ if (!p->pre_handler || !p->pre_handler(p, regs)) { kcb->kprobe_status = KPROBE_HIT_SS; @@ -315,20 +312,9 @@ void __kprobes kprobe_handler(struct pt_regs *regs) kcb->kprobe_status = KPROBE_HIT_SSDONE; p->post_handler(p, regs, 0); } - reset_current_kprobe(); - } - } - } else if (cur) { - /* We probably hit a jprobe. Call its break handler. */ - if (cur->break_handler && cur->break_handler(cur, regs)) { - kcb->kprobe_status = KPROBE_HIT_SS; - singlestep(cur, regs, kcb); - if (cur->post_handler) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - cur->post_handler(cur, regs, 0); } + reset_current_kprobe(); } - reset_current_kprobe(); } else { /* * The probe was removed and a race is in progress. @@ -521,117 +507,6 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, regs->ARM_lr = (unsigned long)&kretprobe_trampoline; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long sp_addr = regs->ARM_sp; - long cpsr; - - kcb->jprobe_saved_regs = *regs; - memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr)); - regs->ARM_pc = (long)jp->entry; - - cpsr = regs->ARM_cpsr | PSR_I_BIT; -#ifdef CONFIG_THUMB2_KERNEL - /* Set correct Thumb state in cpsr */ - if (regs->ARM_pc & 1) - cpsr |= PSR_T_BIT; - else - cpsr &= ~PSR_T_BIT; -#endif - regs->ARM_cpsr = cpsr; - - preempt_disable(); - return 1; -} - -void __kprobes jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - __asm__ __volatile__ ( - /* - * Setup an empty pt_regs. Fill SP and PC fields as - * they're needed by longjmp_break_handler. - * - * We allocate some slack between the original SP and start of - * our fabricated regs. To be precise we want to have worst case - * covered which is STMFD with all 16 regs so we allocate 2 * - * sizeof(struct_pt_regs)). - * - * This is to prevent any simulated instruction from writing - * over the regs when they are accessing the stack. - */ -#ifdef CONFIG_THUMB2_KERNEL - "sub r0, %0, %1 \n\t" - "mov sp, r0 \n\t" -#else - "sub sp, %0, %1 \n\t" -#endif - "ldr r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t" - "str %0, [sp, %2] \n\t" - "str r0, [sp, %3] \n\t" - "mov r0, sp \n\t" - "bl kprobe_handler \n\t" - - /* - * Return to the context saved by setjmp_pre_handler - * and restored by longjmp_break_handler. - */ -#ifdef CONFIG_THUMB2_KERNEL - "ldr lr, [sp, %2] \n\t" /* lr = saved sp */ - "ldrd r0, r1, [sp, %5] \n\t" /* r0,r1 = saved lr,pc */ - "ldr r2, [sp, %4] \n\t" /* r2 = saved psr */ - "stmdb lr!, {r0, r1, r2} \n\t" /* push saved lr and */ - /* rfe context */ - "ldmia sp, {r0 - r12} \n\t" - "mov sp, lr \n\t" - "ldr lr, [sp], #4 \n\t" - "rfeia sp! \n\t" -#else - "ldr r0, [sp, %4] \n\t" - "msr cpsr_cxsf, r0 \n\t" - "ldmia sp, {r0 - pc} \n\t" -#endif - : - : "r" (kcb->jprobe_saved_regs.ARM_sp), - "I" (sizeof(struct pt_regs) * 2), - "J" (offsetof(struct pt_regs, ARM_sp)), - "J" (offsetof(struct pt_regs, ARM_pc)), - "J" (offsetof(struct pt_regs, ARM_cpsr)), - "J" (offsetof(struct pt_regs, ARM_lr)) - : "memory", "cc"); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long stack_addr = kcb->jprobe_saved_regs.ARM_sp; - long orig_sp = regs->ARM_sp; - struct jprobe *jp = container_of(p, struct jprobe, kp); - - if (regs->ARM_pc == JPROBE_MAGIC_ADDR) { - if (orig_sp != stack_addr) { - struct pt_regs *saved_regs = - (struct pt_regs *)kcb->jprobe_saved_regs.ARM_sp; - printk("current sp %lx does not match saved sp %lx\n", - orig_sp, stack_addr); - printk("Saved registers for jprobe %p\n", jp); - show_regs(saved_regs); - printk("Current registers\n"); - show_regs(regs); - BUG(); - } - *regs = kcb->jprobe_saved_regs; - memcpy((void *)stack_addr, kcb->jprobes_stack, - MIN_STACK_SIZE(stack_addr)); - preempt_enable_no_resched(); - return 1; - } - return 0; -} - int __kprobes arch_trampoline_kprobe(struct kprobe *p) { return 0; diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c index 14db14152909..cc237fa9b90f 100644 --- a/arch/arm/probes/kprobes/test-core.c +++ b/arch/arm/probes/kprobes/test-core.c @@ -1461,7 +1461,6 @@ fail: print_registers(&result_regs); if (mem) { - pr_err("current_stack=%p\n", current_stack); pr_err("expected_memory:\n"); print_memory(expected_memory, mem_size); pr_err("result_memory:\n"); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 42c090cf0292..3d1011957823 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -74,6 +74,7 @@ config ARM64 select GENERIC_CPU_AUTOPROBE select GENERIC_EARLY_IOREMAP select GENERIC_IDLE_POLL_SETUP + select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL @@ -264,9 +265,6 @@ config ARCH_SUPPORTS_UPROBES config ARCH_PROC_KCORE_TEXT def_bool y -config MULTI_IRQ_HANDLER - def_bool y - source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S index 88f5aef7934c..e3a375c4cb83 100644 --- a/arch/arm64/crypto/aes-ce-ccm-core.S +++ b/arch/arm64/crypto/aes-ce-ccm-core.S @@ -19,33 +19,24 @@ * u32 *macp, u8 const rk[], u32 rounds); */ ENTRY(ce_aes_ccm_auth_data) - frame_push 7 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - - ldr w25, [x22] /* leftover from prev round? */ + ldr w8, [x3] /* leftover from prev round? */ ld1 {v0.16b}, [x0] /* load mac */ - cbz w25, 1f - sub w25, w25, #16 + cbz w8, 1f + sub w8, w8, #16 eor v1.16b, v1.16b, v1.16b -0: ldrb w7, [x20], #1 /* get 1 byte of input */ - subs w21, w21, #1 - add w25, w25, #1 +0: ldrb w7, [x1], #1 /* get 1 byte of input */ + subs w2, w2, #1 + add w8, w8, #1 ins v1.b[0], w7 ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */ beq 8f /* out of input? */ - cbnz w25, 0b + cbnz w8, 0b eor v0.16b, v0.16b, v1.16b -1: ld1 {v3.4s}, [x23] /* load first round key */ - prfm pldl1strm, [x20] - cmp w24, #12 /* which key size? */ - add x6, x23, #16 - sub w7, w24, #2 /* modified # of rounds */ +1: ld1 {v3.4s}, [x4] /* load first round key */ + prfm pldl1strm, [x1] + cmp w5, #12 /* which key size? */ + add x6, x4, #16 + sub w7, w5, #2 /* modified # of rounds */ bmi 2f bne 5f mov v5.16b, v3.16b @@ -64,43 +55,33 @@ ENTRY(ce_aes_ccm_auth_data) ld1 {v5.4s}, [x6], #16 /* load next round key */ bpl 3b aese v0.16b, v4.16b - subs w21, w21, #16 /* last data? */ + subs w2, w2, #16 /* last data? */ eor v0.16b, v0.16b, v5.16b /* final round */ bmi 6f - ld1 {v1.16b}, [x20], #16 /* load next input block */ + ld1 {v1.16b}, [x1], #16 /* load next input block */ eor v0.16b, v0.16b, v1.16b /* xor with mac */ - beq 6f - - if_will_cond_yield_neon - st1 {v0.16b}, [x19] /* store mac */ - do_cond_yield_neon - ld1 {v0.16b}, [x19] /* reload mac */ - endif_yield_neon - - b 1b -6: st1 {v0.16b}, [x19] /* store mac */ + bne 1b +6: st1 {v0.16b}, [x0] /* store mac */ beq 10f - adds w21, w21, #16 + adds w2, w2, #16 beq 10f - mov w25, w21 -7: ldrb w7, [x20], #1 + mov w8, w2 +7: ldrb w7, [x1], #1 umov w6, v0.b[0] eor w6, w6, w7 - strb w6, [x19], #1 - subs w21, w21, #1 + strb w6, [x0], #1 + subs w2, w2, #1 beq 10f ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */ b 7b -8: mov w7, w25 - add w25, w25, #16 +8: mov w7, w8 + add w8, w8, #16 9: ext v1.16b, v1.16b, v1.16b, #1 adds w7, w7, #1 bne 9b eor v0.16b, v0.16b, v1.16b - st1 {v0.16b}, [x19] -10: str w25, [x22] - - frame_pop + st1 {v0.16b}, [x0] +10: str w8, [x3] ret ENDPROC(ce_aes_ccm_auth_data) @@ -145,29 +126,19 @@ ENTRY(ce_aes_ccm_final) ENDPROC(ce_aes_ccm_final) .macro aes_ccm_do_crypt,enc - frame_push 8 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - mov x25, x6 - - ldr x26, [x25, #8] /* load lower ctr */ - ld1 {v0.16b}, [x24] /* load mac */ -CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ + ldr x8, [x6, #8] /* load lower ctr */ + ld1 {v0.16b}, [x5] /* load mac */ +CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */ 0: /* outer loop */ - ld1 {v1.8b}, [x25] /* load upper ctr */ - prfm pldl1strm, [x20] - add x26, x26, #1 - rev x9, x26 - cmp w23, #12 /* which key size? */ - sub w7, w23, #2 /* get modified # of rounds */ + ld1 {v1.8b}, [x6] /* load upper ctr */ + prfm pldl1strm, [x1] + add x8, x8, #1 + rev x9, x8 + cmp w4, #12 /* which key size? */ + sub w7, w4, #2 /* get modified # of rounds */ ins v1.d[1], x9 /* no carry in lower ctr */ - ld1 {v3.4s}, [x22] /* load first round key */ - add x10, x22, #16 + ld1 {v3.4s}, [x3] /* load first round key */ + add x10, x3, #16 bmi 1f bne 4f mov v5.16b, v3.16b @@ -194,9 +165,9 @@ CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ bpl 2b aese v0.16b, v4.16b aese v1.16b, v4.16b - subs w21, w21, #16 - bmi 7f /* partial block? */ - ld1 {v2.16b}, [x20], #16 /* load next input block */ + subs w2, w2, #16 + bmi 6f /* partial block? */ + ld1 {v2.16b}, [x1], #16 /* load next input block */ .if \enc == 1 eor v2.16b, v2.16b, v5.16b /* final round enc+mac */ eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */ @@ -205,29 +176,18 @@ CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ eor v1.16b, v2.16b, v5.16b /* final round enc */ .endif eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */ - st1 {v1.16b}, [x19], #16 /* write output block */ - beq 5f - - if_will_cond_yield_neon - st1 {v0.16b}, [x24] /* store mac */ - do_cond_yield_neon - ld1 {v0.16b}, [x24] /* reload mac */ - endif_yield_neon - - b 0b -5: -CPU_LE( rev x26, x26 ) - st1 {v0.16b}, [x24] /* store mac */ - str x26, [x25, #8] /* store lsb end of ctr (BE) */ - -6: frame_pop - ret - -7: eor v0.16b, v0.16b, v5.16b /* final round mac */ + st1 {v1.16b}, [x0], #16 /* write output block */ + bne 0b +CPU_LE( rev x8, x8 ) + st1 {v0.16b}, [x5] /* store mac */ + str x8, [x6, #8] /* store lsb end of ctr (BE) */ +5: ret + +6: eor v0.16b, v0.16b, v5.16b /* final round mac */ eor v1.16b, v1.16b, v5.16b /* final round enc */ - st1 {v0.16b}, [x24] /* store mac */ - add w21, w21, #16 /* process partial tail block */ -8: ldrb w9, [x20], #1 /* get 1 byte of input */ + st1 {v0.16b}, [x5] /* store mac */ + add w2, w2, #16 /* process partial tail block */ +7: ldrb w9, [x1], #1 /* get 1 byte of input */ umov w6, v1.b[0] /* get top crypted ctr byte */ umov w7, v0.b[0] /* get top mac byte */ .if \enc == 1 @@ -237,13 +197,13 @@ CPU_LE( rev x26, x26 ) eor w9, w9, w6 eor w7, w7, w9 .endif - strb w9, [x19], #1 /* store out byte */ - strb w7, [x24], #1 /* store mac byte */ - subs w21, w21, #1 - beq 6b + strb w9, [x0], #1 /* store out byte */ + strb w7, [x5], #1 /* store mac byte */ + subs w2, w2, #1 + beq 5b ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */ ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */ - b 8b + b 7b .endm /* diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S index dcffb9e77589..c723647b37db 100644 --- a/arch/arm64/crypto/ghash-ce-core.S +++ b/arch/arm64/crypto/ghash-ce-core.S @@ -322,55 +322,41 @@ ENDPROC(pmull_ghash_update_p8) .endm .macro pmull_gcm_do_crypt, enc - frame_push 10 + ld1 {SHASH.2d}, [x4] + ld1 {XL.2d}, [x1] + ldr x8, [x5, #8] // load lower counter - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - mov x25, x6 - mov x26, x7 - .if \enc == 1 - ldr x27, [sp, #96] // first stacked arg - .endif - - ldr x28, [x24, #8] // load lower counter -CPU_LE( rev x28, x28 ) - -0: mov x0, x25 - load_round_keys w26, x0 - ld1 {SHASH.2d}, [x23] - ld1 {XL.2d}, [x20] + load_round_keys w7, x6 movi MASK.16b, #0xe1 ext SHASH2.16b, SHASH.16b, SHASH.16b, #8 +CPU_LE( rev x8, x8 ) shl MASK.2d, MASK.2d, #57 eor SHASH2.16b, SHASH2.16b, SHASH.16b .if \enc == 1 - ld1 {KS.16b}, [x27] + ldr x10, [sp] + ld1 {KS.16b}, [x10] .endif -1: ld1 {CTR.8b}, [x24] // load upper counter - ld1 {INP.16b}, [x22], #16 - rev x9, x28 - add x28, x28, #1 - sub w19, w19, #1 +0: ld1 {CTR.8b}, [x5] // load upper counter + ld1 {INP.16b}, [x3], #16 + rev x9, x8 + add x8, x8, #1 + sub w0, w0, #1 ins CTR.d[1], x9 // set lower counter .if \enc == 1 eor INP.16b, INP.16b, KS.16b // encrypt input - st1 {INP.16b}, [x21], #16 + st1 {INP.16b}, [x2], #16 .endif rev64 T1.16b, INP.16b - cmp w26, #12 - b.ge 4f // AES-192/256? + cmp w7, #12 + b.ge 2f // AES-192/256? -2: enc_round CTR, v21 +1: enc_round CTR, v21 ext T2.16b, XL.16b, XL.16b, #8 ext IN1.16b, T1.16b, T1.16b, #8 @@ -425,39 +411,27 @@ CPU_LE( rev x28, x28 ) .if \enc == 0 eor INP.16b, INP.16b, KS.16b - st1 {INP.16b}, [x21], #16 + st1 {INP.16b}, [x2], #16 .endif - cbz w19, 3f + cbnz w0, 0b - if_will_cond_yield_neon - st1 {XL.2d}, [x20] - .if \enc == 1 - st1 {KS.16b}, [x27] - .endif - do_cond_yield_neon - b 0b - endif_yield_neon +CPU_LE( rev x8, x8 ) + st1 {XL.2d}, [x1] + str x8, [x5, #8] // store lower counter - b 1b - -3: st1 {XL.2d}, [x20] .if \enc == 1 - st1 {KS.16b}, [x27] + st1 {KS.16b}, [x10] .endif -CPU_LE( rev x28, x28 ) - str x28, [x24, #8] // store lower counter - - frame_pop ret -4: b.eq 5f // AES-192? +2: b.eq 3f // AES-192? enc_round CTR, v17 enc_round CTR, v18 -5: enc_round CTR, v19 +3: enc_round CTR, v19 enc_round CTR, v20 - b 2b + b 1b .endm /* diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 7cf0b1aa6ea8..8a10f1d7199a 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -488,9 +488,13 @@ static int gcm_decrypt(struct aead_request *req) err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); } - if (walk.nbytes) - pmull_gcm_encrypt_block(iv, iv, NULL, + if (walk.nbytes) { + kernel_neon_begin(); + pmull_gcm_encrypt_block(iv, iv, ctx->aes_key.key_enc, num_rounds(&ctx->aes_key)); + kernel_neon_end(); + } + } else { __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, num_rounds(&ctx->aes_key)); diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index c0235e0ff849..9bca54dda75c 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -40,17 +40,6 @@ #include <asm/cmpxchg.h> -#define ___atomic_add_unless(v, a, u, sfx) \ -({ \ - typeof((v)->counter) c, old; \ - \ - c = atomic##sfx##_read(v); \ - while (c != (u) && \ - (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c) \ - c = old; \ - c; \ - }) - #define ATOMIC_INIT(i) { (i) } #define atomic_read(v) READ_ONCE((v)->counter) @@ -61,21 +50,11 @@ #define atomic_add_return_release atomic_add_return_release #define atomic_add_return atomic_add_return -#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v)) -#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v)) -#define atomic_inc_return_release(v) atomic_add_return_release(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - #define atomic_sub_return_relaxed atomic_sub_return_relaxed #define atomic_sub_return_acquire atomic_sub_return_acquire #define atomic_sub_return_release atomic_sub_return_release #define atomic_sub_return atomic_sub_return -#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v)) -#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v)) -#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v)) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) - #define atomic_fetch_add_relaxed atomic_fetch_add_relaxed #define atomic_fetch_add_acquire atomic_fetch_add_acquire #define atomic_fetch_add_release atomic_fetch_add_release @@ -119,13 +98,6 @@ cmpxchg_release(&((v)->counter), (old), (new)) #define atomic_cmpxchg(v, old, new) cmpxchg(&((v)->counter), (old), (new)) -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) -#define atomic_add_negative(i, v) (atomic_add_return((i), (v)) < 0) -#define __atomic_add_unless(v, a, u) ___atomic_add_unless(v, a, u,) #define atomic_andnot atomic_andnot /* @@ -140,21 +112,11 @@ #define atomic64_add_return_release atomic64_add_return_release #define atomic64_add_return atomic64_add_return -#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v)) -#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v)) -#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed #define atomic64_sub_return_acquire atomic64_sub_return_acquire #define atomic64_sub_return_release atomic64_sub_return_release #define atomic64_sub_return atomic64_sub_return -#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v)) -#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v)) -#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) - #define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed #define atomic64_fetch_add_acquire atomic64_fetch_add_acquire #define atomic64_fetch_add_release atomic64_fetch_add_release @@ -195,16 +157,9 @@ #define atomic64_cmpxchg_release atomic_cmpxchg_release #define atomic64_cmpxchg atomic_cmpxchg -#define atomic64_inc(v) atomic64_add(1, (v)) -#define atomic64_dec(v) atomic64_sub(1, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0) -#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0) -#define atomic64_add_negative(i, v) (atomic64_add_return((i), (v)) < 0) -#define atomic64_add_unless(v, a, u) (___atomic_add_unless(v, a, u, 64) != u) #define atomic64_andnot atomic64_andnot -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif #endif diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h index 9c19594ce7cb..10d536b1af74 100644 --- a/arch/arm64/include/asm/bitops.h +++ b/arch/arm64/include/asm/bitops.h @@ -17,22 +17,11 @@ #define __ASM_BITOPS_H #include <linux/compiler.h> -#include <asm/barrier.h> #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif -/* - * Little endian assembly atomic bitops. - */ -extern void set_bit(int nr, volatile unsigned long *p); -extern void clear_bit(int nr, volatile unsigned long *p); -extern void change_bit(int nr, volatile unsigned long *p); -extern int test_and_set_bit(int nr, volatile unsigned long *p); -extern int test_and_clear_bit(int nr, volatile unsigned long *p); -extern int test_and_change_bit(int nr, volatile unsigned long *p); - #include <asm-generic/bitops/builtin-__ffs.h> #include <asm-generic/bitops/builtin-ffs.h> #include <asm-generic/bitops/builtin-__fls.h> @@ -44,15 +33,11 @@ extern int test_and_change_bit(int nr, volatile unsigned long *p); #include <asm-generic/bitops/sched.h> #include <asm-generic/bitops/hweight.h> -#include <asm-generic/bitops/lock.h> +#include <asm-generic/bitops/atomic.h> +#include <asm-generic/bitops/lock.h> #include <asm-generic/bitops/non-atomic.h> #include <asm-generic/bitops/le.h> - -/* - * Ext2 is defined to use little-endian byte ordering. - */ -#define ext2_set_bit_atomic(lock, nr, p) test_and_set_bit_le(nr, p) -#define ext2_clear_bit_atomic(lock, nr, p) test_and_clear_bit_le(nr, p) +#include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* __ASM_BITOPS_H */ diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 192d791f1103..7ed320895d1f 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -87,6 +87,9 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, #define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (true) +#define efi_table_attr(table, attr, instance) \ + ((table##_t *)instance)->attr + #define efi_call_proto(protocol, f, instance, ...) \ ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index 41770766d964..6a53e59ced95 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -119,13 +119,16 @@ static inline void decode_ctrl_reg(u32 reg, struct task_struct; struct notifier_block; +struct perf_event_attr; struct perf_event; struct pmu; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, int *gen_len, int *gen_type, int *offset); -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index a0fee6985e6a..b2b0c6405eb0 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -8,8 +8,6 @@ struct pt_regs; -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); - static inline int nr_legacy_irqs(void) { return 0; diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 6deb8d726041..d5a44cf859e9 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -48,7 +48,6 @@ struct kprobe_ctlblk { unsigned long saved_irqflag; struct prev_kprobe prev_kprobe; struct kprobe_step_ctx ss_ctx; - struct pt_regs jprobe_saved_regs; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index ffdaea7954bb..0ad1cf233470 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -37,7 +37,7 @@ static inline void __tlb_remove_table(void *_table) static inline void tlb_flush(struct mmu_gather *tlb) { - struct vm_area_struct vma = { .vm_mm = tlb->mm, }; + struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); /* * The ASID allocator will either invalidate the ASID or mark diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f24892a40d2c..c6d80743f4ed 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1351,9 +1351,9 @@ static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void update_cpu_capabilities(u16 scope_mask) { - __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); __update_cpu_capabilities(arm64_errata, scope_mask, "enabling workaround for"); + __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); } static int __enable_cpu_capability(void *arg) @@ -1408,8 +1408,8 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void __init enable_cpu_capabilities(u16 scope_mask) { - __enable_cpu_capabilities(arm64_features, scope_mask); __enable_cpu_capabilities(arm64_errata, scope_mask); + __enable_cpu_capabilities(arm64_features, scope_mask); } /* diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 413dbe530da8..8c9644376326 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -343,14 +343,13 @@ static int get_hbp_len(u8 hbp_len) /* * Check whether bp virtual address is in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = get_hbp_len(info->ctrl.len); + va = hw->address; + len = get_hbp_len(hw->ctrl.len); return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -421,53 +420,53 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, /* * Construct an arch_hw_breakpoint from a perf_event. */ -static int arch_build_bp_info(struct perf_event *bp) +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_X: - info->ctrl.type = ARM_BREAKPOINT_EXECUTE; + hw->ctrl.type = ARM_BREAKPOINT_EXECUTE; break; case HW_BREAKPOINT_R: - info->ctrl.type = ARM_BREAKPOINT_LOAD; + hw->ctrl.type = ARM_BREAKPOINT_LOAD; break; case HW_BREAKPOINT_W: - info->ctrl.type = ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_STORE; break; case HW_BREAKPOINT_RW: - info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; break; default: return -EINVAL; } /* Len */ - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->ctrl.len = ARM_BREAKPOINT_LEN_1; + hw->ctrl.len = ARM_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->ctrl.len = ARM_BREAKPOINT_LEN_2; + hw->ctrl.len = ARM_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_3: - info->ctrl.len = ARM_BREAKPOINT_LEN_3; + hw->ctrl.len = ARM_BREAKPOINT_LEN_3; break; case HW_BREAKPOINT_LEN_4: - info->ctrl.len = ARM_BREAKPOINT_LEN_4; + hw->ctrl.len = ARM_BREAKPOINT_LEN_4; break; case HW_BREAKPOINT_LEN_5: - info->ctrl.len = ARM_BREAKPOINT_LEN_5; + hw->ctrl.len = ARM_BREAKPOINT_LEN_5; break; case HW_BREAKPOINT_LEN_6: - info->ctrl.len = ARM_BREAKPOINT_LEN_6; + hw->ctrl.len = ARM_BREAKPOINT_LEN_6; break; case HW_BREAKPOINT_LEN_7: - info->ctrl.len = ARM_BREAKPOINT_LEN_7; + hw->ctrl.len = ARM_BREAKPOINT_LEN_7; break; case HW_BREAKPOINT_LEN_8: - info->ctrl.len = ARM_BREAKPOINT_LEN_8; + hw->ctrl.len = ARM_BREAKPOINT_LEN_8; break; default: return -EINVAL; @@ -478,37 +477,37 @@ static int arch_build_bp_info(struct perf_event *bp) * AArch32 also requires breakpoints of length 2 for Thumb. * Watchpoints can be of length 1, 2, 4 or 8 bytes. */ - if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { + if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) { if (is_compat_bp(bp)) { - if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 && - info->ctrl.len != ARM_BREAKPOINT_LEN_4) + if (hw->ctrl.len != ARM_BREAKPOINT_LEN_2 && + hw->ctrl.len != ARM_BREAKPOINT_LEN_4) return -EINVAL; - } else if (info->ctrl.len != ARM_BREAKPOINT_LEN_4) { + } else if (hw->ctrl.len != ARM_BREAKPOINT_LEN_4) { /* * FIXME: Some tools (I'm looking at you perf) assume * that breakpoints should be sizeof(long). This * is nonsense. For now, we fix up the parameter * but we should probably return -EINVAL instead. */ - info->ctrl.len = ARM_BREAKPOINT_LEN_4; + hw->ctrl.len = ARM_BREAKPOINT_LEN_4; } } /* Address */ - info->address = bp->attr.bp_addr; + hw->address = attr->bp_addr; /* * Privilege * Note that we disallow combined EL0/EL1 breakpoints because * that would complicate the stepping code. */ - if (arch_check_bp_in_kernelspace(bp)) - info->ctrl.privilege = AARCH64_BREAKPOINT_EL1; + if (arch_check_bp_in_kernelspace(hw)) + hw->ctrl.privilege = AARCH64_BREAKPOINT_EL1; else - info->ctrl.privilege = AARCH64_BREAKPOINT_EL0; + hw->ctrl.privilege = AARCH64_BREAKPOINT_EL0; /* Enabled? */ - info->ctrl.enabled = !bp->attr.disabled; + hw->ctrl.enabled = !attr->disabled; return 0; } @@ -516,14 +515,15 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings. */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); int ret; u64 alignment_mask, offset; /* Build the arch_hw_breakpoint. */ - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; @@ -537,42 +537,42 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * that here. */ if (is_compat_bp(bp)) { - if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8) alignment_mask = 0x7; else alignment_mask = 0x3; - offset = info->address & alignment_mask; + offset = hw->address & alignment_mask; switch (offset) { case 0: /* Aligned */ break; case 1: /* Allow single byte watchpoint. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_1) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; case 2: /* Allow halfword watchpoints and breakpoints. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_2) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; default: return -EINVAL; } } else { - if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) + if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) alignment_mask = 0x3; else alignment_mask = 0x7; - offset = info->address & alignment_mask; + offset = hw->address & alignment_mask; } - info->address &= ~alignment_mask; - info->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + hw->ctrl.len <<= offset; /* * Disallow per-task kernel breakpoints since these would * complicate the stepping code. */ - if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target) + if (hw->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target) return -EINVAL; return 0; diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 60e5fc661f74..780a12f59a8f 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -42,16 +42,6 @@ int arch_show_interrupts(struct seq_file *p, int prec) return 0; } -void (*handle_arch_irq)(struct pt_regs *) = NULL; - -void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) -{ - if (handle_arch_irq) - return; - - handle_arch_irq = handle_irq; -} - #ifdef CONFIG_VMAP_STACK static void init_irq_stacks(void) { diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index d849d9804011..e78c3ef04d95 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -275,7 +275,7 @@ static int __kprobes reenter_kprobe(struct kprobe *p, break; case KPROBE_HIT_SS: case KPROBE_REENTER: - pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr); + pr_warn("Unrecoverable kprobe detected.\n"); dump_kprobe(p); BUG(); break; @@ -395,9 +395,9 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) /* * If we have no pre-handler or it returned 0, we * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry, - * so get out doing nothing more here. + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. * * pre_handler can hit a breakpoint and can step thru * before return, keep PSTATE D-flag enabled until @@ -405,16 +405,8 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) */ if (!p->pre_handler || !p->pre_handler(p, regs)) { setup_singlestep(p, regs, kcb, 0); - return; - } - } - } else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) == - BRK64_OPCODE_KPROBES) && cur_kprobe) { - /* We probably hit a jprobe. Call its break handler. */ - if (cur_kprobe->break_handler && - cur_kprobe->break_handler(cur_kprobe, regs)) { - setup_singlestep(cur_kprobe, regs, kcb, 0); - return; + } else + reset_current_kprobe(); } } /* @@ -465,74 +457,6 @@ kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr) return DBG_HOOK_HANDLED; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - /* - * Since we can't be sure where in the stack frame "stacked" - * pass-by-value arguments are stored we just don't try to - * duplicate any of the stack. Do not use jprobes on functions that - * use more than 64 bytes (after padding each to an 8 byte boundary) - * of arguments, or pass individual arguments larger than 16 bytes. - */ - - instruction_pointer_set(regs, (unsigned long) jp->entry); - preempt_disable(); - pause_graph_tracing(); - return 1; -} - -void __kprobes jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - /* - * Jprobe handler return by entering break exception, - * encoded same as kprobe, but with following conditions - * -a special PC to identify it from the other kprobes. - * -restore stack addr to original saved pt_regs - */ - asm volatile(" mov sp, %0 \n" - "jprobe_return_break: brk %1 \n" - : - : "r" (kcb->jprobe_saved_regs.sp), - "I" (BRK64_ESR_KPROBES) - : "memory"); - - unreachable(); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long stack_addr = kcb->jprobe_saved_regs.sp; - long orig_sp = kernel_stack_pointer(regs); - struct jprobe *jp = container_of(p, struct jprobe, kp); - extern const char jprobe_return_break[]; - - if (instruction_pointer(regs) != (u64) jprobe_return_break) - return 0; - - if (orig_sp != stack_addr) { - struct pt_regs *saved_regs = - (struct pt_regs *)kcb->jprobe_saved_regs.sp; - pr_err("current sp %lx does not match saved sp %lx\n", - orig_sp, stack_addr); - pr_err("Saved registers for jprobe %p\n", jp); - __show_regs(saved_regs); - pr_err("Current registers\n"); - __show_regs(regs); - BUG(); - } - unpause_graph_tracing(); - *regs = kcb->jprobe_saved_regs; - preempt_enable_no_resched(); - return 1; -} - bool arch_within_kprobe_blacklist(unsigned long addr) { if ((addr >= (unsigned long)__kprobes_text_start && diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 137710f4dac3..68755fd70dcf 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -lib-y := bitops.o clear_user.o delay.o copy_from_user.o \ +lib-y := clear_user.o delay.o copy_from_user.o \ copy_to_user.o copy_in_user.o copy_page.o \ clear_page.o memchr.o memcpy.o memmove.o memset.o \ memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \ diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S deleted file mode 100644 index 43ac736baa5b..000000000000 --- a/arch/arm64/lib/bitops.S +++ /dev/null @@ -1,76 +0,0 @@ -/* - * Based on arch/arm/lib/bitops.h - * - * Copyright (C) 2013 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#include <linux/linkage.h> -#include <asm/assembler.h> -#include <asm/lse.h> - -/* - * x0: bits 5:0 bit offset - * bits 31:6 word offset - * x1: address - */ - .macro bitop, name, llsc, lse -ENTRY( \name ) - and w3, w0, #63 // Get bit offset - eor w0, w0, w3 // Clear low bits - mov x2, #1 - add x1, x1, x0, lsr #3 // Get word offset -alt_lse " prfm pstl1strm, [x1]", "nop" - lsl x3, x2, x3 // Create mask - -alt_lse "1: ldxr x2, [x1]", "\lse x3, [x1]" -alt_lse " \llsc x2, x2, x3", "nop" -alt_lse " stxr w0, x2, [x1]", "nop" -alt_lse " cbnz w0, 1b", "nop" - - ret -ENDPROC(\name ) - .endm - - .macro testop, name, llsc, lse -ENTRY( \name ) - and w3, w0, #63 // Get bit offset - eor w0, w0, w3 // Clear low bits - mov x2, #1 - add x1, x1, x0, lsr #3 // Get word offset -alt_lse " prfm pstl1strm, [x1]", "nop" - lsl x4, x2, x3 // Create mask - -alt_lse "1: ldxr x2, [x1]", "\lse x4, x2, [x1]" - lsr x0, x2, x3 -alt_lse " \llsc x2, x2, x4", "nop" -alt_lse " stlxr w5, x2, [x1]", "nop" -alt_lse " cbnz w5, 1b", "nop" -alt_lse " dmb ish", "nop" - - and x0, x0, #1 - ret -ENDPROC(\name ) - .endm - -/* - * Atomic bit operations. - */ - bitop change_bit, eor, steor - bitop clear_bit, bic, stclr - bitop set_bit, orr, stset - - testop test_and_change_bit, eor, ldeoral - testop test_and_clear_bit, bic, ldclral - testop test_and_set_bit, orr, ldsetal diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index ecc6818191df..192b3ba07075 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -108,7 +108,6 @@ static pte_t get_clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; pte_t orig_pte = huge_ptep_get(ptep); bool valid = pte_valid(orig_pte); unsigned long i, saddr = addr; @@ -125,8 +124,10 @@ static pte_t get_clear_flush(struct mm_struct *mm, orig_pte = pte_mkdirty(orig_pte); } - if (valid) + if (valid) { + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); flush_tlb_range(&vma, saddr, addr); + } return orig_pte; } @@ -145,7 +146,7 @@ static void clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 325cfb3b858a..9abf8a1e7b25 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -611,11 +611,13 @@ void __init mem_init(void) BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64); #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Make sure we chose the upper bound of sizeof(struct page) - * correctly. + * correctly when sizing the VMEMMAP array. */ BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT)); +#endif if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h index 941e7554e886..c6b6a06231b2 100644 --- a/arch/h8300/include/asm/atomic.h +++ b/arch/h8300/include/asm/atomic.h @@ -2,8 +2,10 @@ #ifndef __ARCH_H8300_ATOMIC__ #define __ARCH_H8300_ATOMIC__ +#include <linux/compiler.h> #include <linux/types.h> #include <asm/cmpxchg.h> +#include <asm/irqflags.h> /* * Atomic operations that C can't guarantee us. Useful for @@ -15,8 +17,6 @@ #define atomic_read(v) READ_ONCE((v)->counter) #define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) -#include <linux/kernel.h> - #define ATOMIC_OP_RETURN(op, c_op) \ static inline int atomic_##op##_return(int i, atomic_t *v) \ { \ @@ -69,18 +69,6 @@ ATOMIC_OPS(sub, -=) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_inc_return(v) atomic_add_return(1, v) -#define atomic_dec_return(v) atomic_sub_return(1, v) - -#define atomic_inc(v) (void)atomic_inc_return(v) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec(v) (void)atomic_dec_return(v) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) - static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; @@ -94,7 +82,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int ret; h8300flags flags; @@ -106,5 +94,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) arch_local_irq_restore(flags); return ret; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #endif /* __ARCH_H8300_ATOMIC __ */ diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index fb3dfb2a667e..311b9894ccc8 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -164,7 +164,7 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer to value * @a: amount to add * @u: unless value is equal to u @@ -173,7 +173,7 @@ ATOMIC_OPS(xor) * */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int __oldval; register int tmp; @@ -196,18 +196,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) ); return __oldval; } - -#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) - -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) - -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0) -#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0) - -#define atomic_inc_return(v) (atomic_add_return(1, v)) -#define atomic_dec_return(v) (atomic_sub_return(1, v)) +#define atomic_fetch_add_unless atomic_fetch_add_unless #endif diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 2524fb60fbc2..206530d0751b 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -215,91 +215,10 @@ ATOMIC64_FETCH_OP(xor, ^) (cmpxchg(&((v)->counter), old, new)) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - - -static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -static __inline__ long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - -/* - * Atomically add I to V and return TRUE if the resulting value is - * negative. - */ -static __inline__ int -atomic_add_negative (int i, atomic_t *v) -{ - return atomic_add_return(i, v) < 0; -} - -static __inline__ long -atomic64_add_negative (__s64 i, atomic64_t *v) -{ - return atomic64_add_return(i, v) < 0; -} - -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) -#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0) - #define atomic_add(i,v) (void)atomic_add_return((i), (v)) #define atomic_sub(i,v) (void)atomic_sub_return((i), (v)) -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) #define atomic64_add(i,v) (void)atomic64_add_return((i), (v)) #define atomic64_sub(i,v) (void)atomic64_sub_return((i), (v)) -#define atomic64_inc(v) atomic64_add(1, (v)) -#define atomic64_dec(v) atomic64_sub(1, (v)) #endif /* _ASM_IA64_ATOMIC_H */ diff --git a/arch/ia64/include/asm/kprobes.h b/arch/ia64/include/asm/kprobes.h index 0302b3664789..580356a2eea6 100644 --- a/arch/ia64/include/asm/kprobes.h +++ b/arch/ia64/include/asm/kprobes.h @@ -82,8 +82,6 @@ struct prev_kprobe { #define ARCH_PREV_KPROBE_SZ 2 struct kprobe_ctlblk { unsigned long kprobe_status; - struct pt_regs jprobe_saved_regs; - unsigned long jprobes_saved_stacked_regs[MAX_PARAM_RSE_SIZE]; unsigned long *bsp; unsigned long cfm; atomic_t prev_kprobe_index; diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index 44f0ac0df308..516355a774bf 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -115,12 +115,11 @@ ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned flush_tlb_all(); } else { /* - * XXX fix me: flush_tlb_range() should take an mm pointer instead of a - * vma pointer. + * flush_tlb_range() takes a vma instead of a mm pointer because + * some architectures want the vm_flags for ITLB/DTLB flush. */ - struct vm_area_struct vma; + struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); - vma.vm_mm = tlb->mm; /* flush the address range from the tlb: */ flush_tlb_range(&vma, start, end); /* now flush the virt. page-table area mapping the address range: */ diff --git a/arch/ia64/include/uapi/asm/break.h b/arch/ia64/include/uapi/asm/break.h index 5d742bcb0018..4ca110f0a94b 100644 --- a/arch/ia64/include/uapi/asm/break.h +++ b/arch/ia64/include/uapi/asm/break.h @@ -14,7 +14,6 @@ */ #define __IA64_BREAK_KDB 0x80100 #define __IA64_BREAK_KPROBE 0x81000 /* .. 0x81fff */ -#define __IA64_BREAK_JPROBE 0x82000 /* * OS-specific break numbers: diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 498f3da3f225..d0c0ccdd656a 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -25,7 +25,7 @@ obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_PERFMON) += perfmon_default_smpl.o obj-$(CONFIG_IA64_CYCLONE) += cyclone.o obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o -obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o +obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o diff --git a/arch/ia64/kernel/jprobes.S b/arch/ia64/kernel/jprobes.S deleted file mode 100644 index f69389c7be1d..000000000000 --- a/arch/ia64/kernel/jprobes.S +++ /dev/null @@ -1,90 +0,0 @@ -/* - * Jprobe specific operations - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * Copyright (C) Intel Corporation, 2005 - * - * 2005-May Rusty Lynch <rusty.lynch@intel.com> and Anil S Keshavamurthy - * <anil.s.keshavamurthy@intel.com> initial implementation - * - * Jprobes (a.k.a. "jump probes" which is built on-top of kprobes) allow a - * probe to be inserted into the beginning of a function call. The fundamental - * difference between a jprobe and a kprobe is the jprobe handler is executed - * in the same context as the target function, while the kprobe handlers - * are executed in interrupt context. - * - * For jprobes we initially gain control by placing a break point in the - * first instruction of the targeted function. When we catch that specific - * break, we: - * * set the return address to our jprobe_inst_return() function - * * jump to the jprobe handler function - * - * Since we fixed up the return address, the jprobe handler will return to our - * jprobe_inst_return() function, giving us control again. At this point we - * are back in the parents frame marker, so we do yet another call to our - * jprobe_break() function to fix up the frame marker as it would normally - * exist in the target function. - * - * Our jprobe_return function then transfers control back to kprobes.c by - * executing a break instruction using one of our reserved numbers. When we - * catch that break in kprobes.c, we continue like we do for a normal kprobe - * by single stepping the emulated instruction, and then returning execution - * to the correct location. - */ -#include <asm/asmmacro.h> -#include <asm/break.h> - - /* - * void jprobe_break(void) - */ - .section .kprobes.text, "ax" -ENTRY(jprobe_break) - break.m __IA64_BREAK_JPROBE -END(jprobe_break) - - /* - * void jprobe_inst_return(void) - */ -GLOBAL_ENTRY(jprobe_inst_return) - br.call.sptk.many b0=jprobe_break -END(jprobe_inst_return) - -GLOBAL_ENTRY(invalidate_stacked_regs) - movl r16=invalidate_restore_cfm - ;; - mov b6=r16 - ;; - br.ret.sptk.many b6 - ;; -invalidate_restore_cfm: - mov r16=ar.rsc - ;; - mov ar.rsc=r0 - ;; - loadrs - ;; - mov ar.rsc=r16 - ;; - br.cond.sptk.many rp -END(invalidate_stacked_regs) - -GLOBAL_ENTRY(flush_register_stack) - // flush dirty regs to backing store (must be first in insn group) - flushrs - ;; - br.ret.sptk.many rp -END(flush_register_stack) - diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index f5f3a5e6fcd1..aa41bd5cf9b7 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -35,8 +35,6 @@ #include <asm/sections.h> #include <asm/exception.h> -extern void jprobe_inst_return(void); - DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -480,12 +478,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) */ break; } - kretprobe_assert(ri, orig_ret_address, trampoline_address); - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); @@ -819,14 +814,6 @@ static int __kprobes pre_kprobes_handler(struct die_args *args) prepare_ss(p, regs); kcb->kprobe_status = KPROBE_REENTER; return 1; - } else if (args->err == __IA64_BREAK_JPROBE) { - /* - * jprobe instrumented function just completed - */ - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - goto ss_probe; - } } else if (!is_ia64_break_inst(regs)) { /* The breakpoint instruction was removed by * another cpu right after we hit, no further @@ -861,15 +848,12 @@ static int __kprobes pre_kprobes_handler(struct die_args *args) set_current_kprobe(p, kcb); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) - /* - * Our pre-handler is specifically requesting that we just - * do a return. This is used for both the jprobe pre-handler - * and the kretprobe trampoline - */ + if (p->pre_handler && p->pre_handler(p, regs)) { + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: #if !defined(CONFIG_PREEMPT) if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ @@ -992,7 +976,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, case DIE_BREAK: /* err is break number from ia64_bad_break() */ if ((args->err >> 12) == (__IA64_BREAK_KPROBE >> 12) - || args->err == __IA64_BREAK_JPROBE || args->err == 0) if (pre_kprobes_handler(args)) ret = NOTIFY_STOP; @@ -1040,74 +1023,6 @@ unsigned long arch_deref_entry_point(void *entry) return ((struct fnptr *)entry)->ip; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - unsigned long addr = arch_deref_entry_point(jp->entry); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - struct param_bsp_cfm pa; - int bytes; - - /* - * Callee owns the argument space and could overwrite it, eg - * tail call optimization. So to be absolutely safe - * we save the argument space before transferring the control - * to instrumented jprobe function which runs in - * the process context - */ - pa.ip = regs->cr_iip; - unw_init_running(ia64_get_bsp_cfm, &pa); - bytes = (char *)ia64_rse_skip_regs(pa.bsp, pa.cfm & 0x3f) - - (char *)pa.bsp; - memcpy( kcb->jprobes_saved_stacked_regs, - pa.bsp, - bytes ); - kcb->bsp = pa.bsp; - kcb->cfm = pa.cfm; - - /* save architectural state */ - kcb->jprobe_saved_regs = *regs; - - /* after rfi, execute the jprobe instrumented function */ - regs->cr_iip = addr & ~0xFULL; - ia64_psr(regs)->ri = addr & 0xf; - regs->r1 = ((struct fnptr *)(jp->entry))->gp; - - /* - * fix the return address to our jprobe_inst_return() function - * in the jprobes.S file - */ - regs->b0 = ((struct fnptr *)(jprobe_inst_return))->ip; - - return 1; -} - -/* ia64 does not need this */ -void __kprobes jprobe_return(void) -{ -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - int bytes; - - /* restoring architectural state */ - *regs = kcb->jprobe_saved_regs; - - /* restoring the original argument space */ - flush_register_stack(); - bytes = (char *)ia64_rse_skip_regs(kcb->bsp, kcb->cfm & 0x3f) - - (char *)kcb->bsp; - memcpy( kcb->bsp, - kcb->jprobes_saved_stacked_regs, - bytes ); - invalidate_stacked_regs(); - - preempt_enable_no_resched(); - return 1; -} - static struct kprobe trampoline_p = { .pre_handler = trampoline_probe_handler }; diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 3b38c717008a..46bff1661836 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2278,17 +2278,15 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t DPRINT(("smpl_buf @%p\n", smpl_buf)); /* allocate vma */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (!vma) { DPRINT(("Cannot allocate vma\n")); goto error_kmem; } - INIT_LIST_HEAD(&vma->anon_vma_chain); /* * partially initialize the vma for the sampling buffer */ - vma->vm_mm = mm; vma->vm_file = get_file(filp); vma->vm_flags = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP; vma->vm_page_prot = PAGE_READONLY; /* XXX may need to change */ @@ -2346,7 +2344,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t return 0; error: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); error_kmem: pfm_rvfree(smpl_buf, size); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 18278b448530..3b85c3ecac38 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -114,10 +114,9 @@ ia64_init_addr_space (void) * the problem. When the process attempts to write to the register backing store * for the first time, it will get a SEGFAULT in this case. */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(current->mm); if (vma) { - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = current->mm; + vma_set_anonymous(vma); vma->vm_start = current->thread.rbs_bot & PAGE_MASK; vma->vm_end = vma->vm_start + PAGE_SIZE; vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT; @@ -125,7 +124,7 @@ ia64_init_addr_space (void) down_write(¤t->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(¤t->mm->mmap_sem); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return; } up_write(¤t->mm->mmap_sem); @@ -133,10 +132,9 @@ ia64_init_addr_space (void) /* map NaT-page at address zero to speed up speculative dereferencing of NULL: */ if (!(current->personality & MMAP_PAGE_ZERO)) { - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(current->mm); if (vma) { - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = current->mm; + vma_set_anonymous(vma); vma->vm_end = PAGE_SIZE; vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT); vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO | @@ -144,7 +142,7 @@ ia64_init_addr_space (void) down_write(¤t->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(¤t->mm->mmap_sem); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return; } up_write(¤t->mm->mmap_sem); @@ -277,7 +275,7 @@ static struct vm_area_struct gate_vma; static int __init gate_vma_init(void) { - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 785612b576f7..b29f93774d95 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -2,6 +2,7 @@ config M68K bool default y + select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA select ARCH_MIGHT_HAVE_PC_PARPORT if ISA select ARCH_NO_COHERENT_DMA_MMAP if !MMU select HAVE_IDE @@ -24,6 +25,10 @@ config M68K select MODULES_USE_ELF_RELA select OLD_SIGSUSPEND3 select OLD_SIGACTION + select DMA_NONCOHERENT_OPS if HAS_DMA + select HAVE_MEMBLOCK + select ARCH_DISCARD_MEMBLOCK + select NO_BOOTMEM config CPU_BIG_ENDIAN def_bool y diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c index b2a6bc63f8cd..aef8d42e078d 100644 --- a/arch/m68k/apollo/config.c +++ b/arch/m68k/apollo/config.c @@ -31,7 +31,6 @@ extern void dn_sched_init(irq_handler_t handler); extern void dn_init_IRQ(void); extern u32 dn_gettimeoffset(void); extern int dn_dummy_hwclk(int, struct rtc_time *); -extern int dn_dummy_set_clock_mmss(unsigned long); extern void dn_dummy_reset(void); #ifdef CONFIG_HEARTBEAT static void dn_heartbeat(int on); @@ -156,7 +155,6 @@ void __init config_apollo(void) arch_gettimeoffset = dn_gettimeoffset; mach_max_dma_address = 0xffffffff; mach_hwclk = dn_dummy_hwclk; /* */ - mach_set_clock_mmss = dn_dummy_set_clock_mmss; /* */ mach_reset = dn_dummy_reset; /* */ #ifdef CONFIG_HEARTBEAT mach_heartbeat = dn_heartbeat; @@ -240,12 +238,6 @@ int dn_dummy_hwclk(int op, struct rtc_time *t) { } -int dn_dummy_set_clock_mmss(unsigned long nowtime) -{ - pr_info("set_clock_mmss\n"); - return 0; -} - void dn_dummy_reset(void) { dn_serial_print("The end !\n"); diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c index 565c6f06ab0b..bd96702a1ad0 100644 --- a/arch/m68k/atari/config.c +++ b/arch/m68k/atari/config.c @@ -81,9 +81,6 @@ extern void atari_sched_init(irq_handler_t); extern u32 atari_gettimeoffset(void); extern int atari_mste_hwclk (int, struct rtc_time *); extern int atari_tt_hwclk (int, struct rtc_time *); -extern int atari_mste_set_clock_mmss (unsigned long); -extern int atari_tt_set_clock_mmss (unsigned long); - /* ++roman: This is a more elaborate test for an SCC chip, since the plain * Medusa board generates DTACK at the SCC's standard addresses, but a SCC @@ -362,13 +359,11 @@ void __init config_atari(void) ATARIHW_SET(TT_CLK); pr_cont(" TT_CLK"); mach_hwclk = atari_tt_hwclk; - mach_set_clock_mmss = atari_tt_set_clock_mmss; } if (hwreg_present(&mste_rtc.sec_ones)) { ATARIHW_SET(MSTE_CLK); pr_cont(" MSTE_CLK"); mach_hwclk = atari_mste_hwclk; - mach_set_clock_mmss = atari_mste_set_clock_mmss; } if (!MACH_IS_MEDUSA && hwreg_present(&dma_wd.fdc_speed) && hwreg_write(&dma_wd.fdc_speed, 0)) { diff --git a/arch/m68k/atari/time.c b/arch/m68k/atari/time.c index c549b48174ec..9cca64286464 100644 --- a/arch/m68k/atari/time.c +++ b/arch/m68k/atari/time.c @@ -285,69 +285,6 @@ int atari_tt_hwclk( int op, struct rtc_time *t ) return( 0 ); } - -int atari_mste_set_clock_mmss (unsigned long nowtime) -{ - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - struct MSTE_RTC val; - unsigned char rtc_minutes; - - mste_read(&val); - rtc_minutes= val.min_ones + val.min_tens * 10; - if ((rtc_minutes < real_minutes - ? real_minutes - rtc_minutes - : rtc_minutes - real_minutes) < 30) - { - val.sec_ones = real_seconds % 10; - val.sec_tens = real_seconds / 10; - val.min_ones = real_minutes % 10; - val.min_tens = real_minutes / 10; - mste_write(&val); - } - else - return -1; - return 0; -} - -int atari_tt_set_clock_mmss (unsigned long nowtime) -{ - int retval = 0; - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - unsigned char save_control, save_freq_select, rtc_minutes; - - save_control = RTC_READ (RTC_CONTROL); /* tell the clock it's being set */ - RTC_WRITE (RTC_CONTROL, save_control | RTC_SET); - - save_freq_select = RTC_READ (RTC_FREQ_SELECT); /* stop and reset prescaler */ - RTC_WRITE (RTC_FREQ_SELECT, save_freq_select | RTC_DIV_RESET2); - - rtc_minutes = RTC_READ (RTC_MINUTES); - if (!(save_control & RTC_DM_BINARY)) - rtc_minutes = bcd2bin(rtc_minutes); - - /* Since we're only adjusting minutes and seconds, don't interfere - with hour overflow. This avoids messing with unknown time zones - but requires your RTC not to be off by more than 30 minutes. */ - if ((rtc_minutes < real_minutes - ? real_minutes - rtc_minutes - : rtc_minutes - real_minutes) < 30) - { - if (!(save_control & RTC_DM_BINARY)) - { - real_seconds = bin2bcd(real_seconds); - real_minutes = bin2bcd(real_minutes); - } - RTC_WRITE (RTC_SECONDS, real_seconds); - RTC_WRITE (RTC_MINUTES, real_minutes); - } - else - retval = -1; - - RTC_WRITE (RTC_FREQ_SELECT, save_freq_select); - RTC_WRITE (RTC_CONTROL, save_control); - return retval; -} - /* * Local variables: * c-indent-level: 4 diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c index 2cfff4765040..143ee9fa3893 100644 --- a/arch/m68k/bvme6000/config.c +++ b/arch/m68k/bvme6000/config.c @@ -41,7 +41,6 @@ static void bvme6000_get_model(char *model); extern void bvme6000_sched_init(irq_handler_t handler); extern u32 bvme6000_gettimeoffset(void); extern int bvme6000_hwclk (int, struct rtc_time *); -extern int bvme6000_set_clock_mmss (unsigned long); extern void bvme6000_reset (void); void bvme6000_set_vectors (void); @@ -113,7 +112,6 @@ void __init config_bvme6000(void) mach_init_IRQ = bvme6000_init_IRQ; arch_gettimeoffset = bvme6000_gettimeoffset; mach_hwclk = bvme6000_hwclk; - mach_set_clock_mmss = bvme6000_set_clock_mmss; mach_reset = bvme6000_reset; mach_get_model = bvme6000_get_model; @@ -305,46 +303,3 @@ int bvme6000_hwclk(int op, struct rtc_time *t) return 0; } - -/* - * Set the minutes and seconds from seconds value 'nowtime'. Fail if - * clock is out by > 30 minutes. Logic lifted from atari code. - * Algorithm is to wait for the 10ms register to change, and then to - * wait a short while, and then set it. - */ - -int bvme6000_set_clock_mmss (unsigned long nowtime) -{ - int retval = 0; - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - unsigned char rtc_minutes, rtc_tenms; - volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE; - unsigned char msr = rtc->msr & 0xc0; - unsigned long flags; - volatile int i; - - rtc->msr = 0; /* Ensure clock accessible */ - rtc_minutes = bcd2bin (rtc->bcd_min); - - if ((rtc_minutes < real_minutes - ? real_minutes - rtc_minutes - : rtc_minutes - real_minutes) < 30) - { - local_irq_save(flags); - rtc_tenms = rtc->bcd_tenms; - while (rtc_tenms == rtc->bcd_tenms) - ; - for (i = 0; i < 1000; i++) - ; - rtc->bcd_min = bin2bcd(real_minutes); - rtc->bcd_sec = bin2bcd(real_seconds); - local_irq_restore(flags); - } - else - retval = -1; - - rtc->msr = msr; - - return retval; -} - diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index a874e54404d1..1d5483f6e457 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -52,6 +52,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -98,18 +99,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -122,6 +119,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -200,7 +198,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -231,7 +228,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -260,7 +256,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -356,6 +352,7 @@ CONFIG_A2091_SCSI=y CONFIG_GVP11_SCSI=y CONFIG_SCSI_A4000T=y CONFIG_SCSI_ZORRO7XX=y +CONFIG_SCSI_ZORRO_ESP=y CONFIG_MD=y CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m @@ -363,6 +360,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -402,8 +400,8 @@ CONFIG_A2065=y CONFIG_ARIADNE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CIRRUS is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -412,8 +410,10 @@ CONFIG_ARIADNE=y # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set +CONFIG_XSURF100=y CONFIG_HYDRA=y CONFIG_APNE=y CONFIG_ZORRO8390=y @@ -426,9 +426,9 @@ CONFIG_ZORRO8390=y # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -478,6 +478,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -499,7 +500,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -600,6 +601,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -622,6 +624,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -657,6 +664,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 8ce39e23aa42..52a0af127951 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -381,14 +378,15 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -400,9 +398,9 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -440,6 +438,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -458,7 +457,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -559,6 +558,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -581,6 +581,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -616,6 +621,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 346c4e75edf8..b3103e51268a 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -391,14 +388,15 @@ CONFIG_VETH=m CONFIG_ATARILANCE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set CONFIG_NE2000=y @@ -411,9 +409,9 @@ CONFIG_NE2000=y CONFIG_SMC91X=y # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -480,7 +478,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -581,6 +579,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -603,6 +602,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -638,6 +642,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index fca9c7aa71a3..fb7d651a4cab 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -380,14 +377,15 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set CONFIG_BVME6000_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -399,9 +397,9 @@ CONFIG_BVME6000_NET=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -433,6 +431,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index f9eab174915c..6b37f5537c39 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -382,14 +379,15 @@ CONFIG_VETH=m CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -401,9 +399,9 @@ CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -443,6 +441,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -460,7 +459,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -561,6 +560,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -583,6 +583,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -618,6 +623,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index b52e597899eb..930cc2965a11 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -49,6 +49,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -95,18 +96,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -119,6 +116,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -197,7 +195,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -228,7 +225,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -257,7 +253,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -398,8 +395,8 @@ CONFIG_VETH=m CONFIG_MACMACE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set CONFIG_MAC89x0=y # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -407,6 +404,7 @@ CONFIG_MAC89x0=y # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set CONFIG_MACSONIC=y # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -420,9 +418,9 @@ CONFIG_MAC8390=y # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -465,6 +463,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -482,7 +481,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -583,6 +582,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -605,6 +605,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -640,6 +645,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 2a84eeec5b02..e7dd25300127 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -59,6 +59,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -105,18 +106,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -129,6 +126,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -207,7 +205,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -238,7 +235,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -267,7 +263,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -311,6 +306,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -373,6 +369,7 @@ CONFIG_A2091_SCSI=y CONFIG_GVP11_SCSI=y CONFIG_SCSI_A4000T=y CONFIG_SCSI_ZORRO7XX=y +CONFIG_SCSI_ZORRO_ESP=y CONFIG_ATARI_SCSI=y CONFIG_MAC_SCSI=y CONFIG_SCSI_MAC_ESP=y @@ -387,6 +384,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -438,8 +436,8 @@ CONFIG_SUN3LANCE=y CONFIG_MACMACE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set CONFIG_MAC89x0=y # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -449,9 +447,11 @@ CONFIG_BVME6000_NET=y CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set CONFIG_MACSONIC=y # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set +CONFIG_XSURF100=y CONFIG_HYDRA=y CONFIG_MAC8390=y CONFIG_NE2000=y @@ -466,9 +466,9 @@ CONFIG_ZORRO8390=y CONFIG_SMC91X=y # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m @@ -533,6 +533,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -562,7 +563,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -663,6 +664,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -685,6 +687,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -720,6 +727,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 476e69994340..b383327fd77a 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -47,6 +47,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -93,18 +94,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -117,6 +114,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -195,7 +193,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -226,7 +223,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -255,7 +251,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -296,6 +291,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -343,6 +339,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -380,14 +377,15 @@ CONFIG_VETH=m CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -399,9 +397,9 @@ CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -433,6 +431,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 1477cda9146e..9783d3deb9e9 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -380,14 +377,15 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -399,9 +397,9 @@ CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -433,6 +431,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index b3a543dc48a0..a35d10ee10cb 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -350,6 +346,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -388,8 +385,8 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CIRRUS is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -398,6 +395,7 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set CONFIG_NE2000=y @@ -410,9 +408,9 @@ CONFIG_NE2000=y # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m @@ -455,6 +453,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -473,7 +472,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -574,6 +573,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -596,6 +596,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -631,6 +636,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index d543ed5dfa96..573bf922d448 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -193,7 +191,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -224,7 +221,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -385,6 +382,7 @@ CONFIG_SUN3LANCE=y CONFIG_SUN3_82586=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -397,9 +395,9 @@ CONFIG_SUN3_82586=y # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_SUN is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -435,6 +433,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -574,6 +574,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -609,6 +614,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index a67e54246023..efb27a7fcc55 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -193,7 +191,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -224,7 +221,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -378,14 +375,15 @@ CONFIG_VETH=m CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -397,9 +395,9 @@ CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -435,6 +433,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -575,6 +575,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -610,6 +615,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 4d8d68c4e3dd..a4b8d3331a9e 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,6 +1,7 @@ generic-y += barrier.h generic-y += compat.h generic-y += device.h +generic-y += dma-mapping.h generic-y += emergency-restart.h generic-y += exec.h generic-y += extable.h diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h index e993e2860ee1..47228b0d4163 100644 --- a/arch/m68k/include/asm/atomic.h +++ b/arch/m68k/include/asm/atomic.h @@ -126,11 +126,13 @@ static inline void atomic_inc(atomic_t *v) { __asm__ __volatile__("addql #1,%0" : "+m" (*v)); } +#define atomic_inc atomic_inc static inline void atomic_dec(atomic_t *v) { __asm__ __volatile__("subql #1,%0" : "+m" (*v)); } +#define atomic_dec atomic_dec static inline int atomic_dec_and_test(atomic_t *v) { @@ -138,6 +140,7 @@ static inline int atomic_dec_and_test(atomic_t *v) __asm__ __volatile__("subql #1,%1; seq %0" : "=d" (c), "+m" (*v)); return c != 0; } +#define atomic_dec_and_test atomic_dec_and_test static inline int atomic_dec_and_test_lt(atomic_t *v) { @@ -155,6 +158,7 @@ static inline int atomic_inc_and_test(atomic_t *v) __asm__ __volatile__("addql #1,%1; seq %0" : "=d" (c), "+m" (*v)); return c != 0; } +#define atomic_inc_and_test atomic_inc_and_test #ifdef CONFIG_RMW_INSNS @@ -190,9 +194,6 @@ static inline int atomic_xchg(atomic_t *v, int new) #endif /* !CONFIG_RMW_INSNS */ -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - static inline int atomic_sub_and_test(int i, atomic_t *v) { char c; @@ -201,6 +202,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v) : ASM_DI (i)); return c != 0; } +#define atomic_sub_and_test atomic_sub_and_test static inline int atomic_add_negative(int i, atomic_t *v) { @@ -210,20 +212,6 @@ static inline int atomic_add_negative(int i, atomic_t *v) : ASM_DI (i)); return c != 0; } - -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} +#define atomic_add_negative atomic_add_negative #endif /* __ARCH_M68K_ATOMIC __ */ diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h index 93b47b1f6fb4..d979f38af751 100644 --- a/arch/m68k/include/asm/bitops.h +++ b/arch/m68k/include/asm/bitops.h @@ -454,7 +454,7 @@ static inline unsigned long ffz(unsigned long word) */ #if (defined(__mcfisaaplus__) || defined(__mcfisac__)) && \ !defined(CONFIG_M68000) && !defined(CONFIG_MCPU32) -static inline int __ffs(int x) +static inline unsigned long __ffs(unsigned long x) { __asm__ __volatile__ ("bitrev %0; ff1 %0" : "=d" (x) @@ -493,7 +493,11 @@ static inline int ffs(int x) : "dm" (x & -x)); return 32 - cnt; } -#define __ffs(x) (ffs(x) - 1) + +static inline unsigned long __ffs(unsigned long x) +{ + return ffs(x) - 1; +} /* * fls: find last bit set. @@ -515,12 +519,16 @@ static inline int __fls(int x) #endif +/* Simple test-and-set bit locks */ +#define test_and_set_bit_lock test_and_set_bit +#define clear_bit_unlock clear_bit +#define __clear_bit_unlock clear_bit_unlock + #include <asm-generic/bitops/ext2-atomic.h> #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/fls64.h> #include <asm-generic/bitops/sched.h> #include <asm-generic/bitops/hweight.h> -#include <asm-generic/bitops/lock.h> #endif /* __KERNEL__ */ #endif /* _M68K_BITOPS_H */ diff --git a/arch/m68k/include/asm/dma-mapping.h b/arch/m68k/include/asm/dma-mapping.h deleted file mode 100644 index e3722ed04fbb..000000000000 --- a/arch/m68k/include/asm/dma-mapping.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _M68K_DMA_MAPPING_H -#define _M68K_DMA_MAPPING_H - -extern const struct dma_map_ops m68k_dma_ops; - -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) -{ - return &m68k_dma_ops; -} - -#endif /* _M68K_DMA_MAPPING_H */ diff --git a/arch/m68k/include/asm/io.h b/arch/m68k/include/asm/io.h index ca2849afb087..aabe6420ead2 100644 --- a/arch/m68k/include/asm/io.h +++ b/arch/m68k/include/asm/io.h @@ -1,6 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _M68K_IO_H +#define _M68K_IO_H + #if defined(__uClinux__) || defined(CONFIG_COLDFIRE) #include <asm/io_no.h> #else #include <asm/io_mm.h> #endif + +#include <asm-generic/io.h> + +#endif /* _M68K_IO_H */ diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h index fe485f4f5fac..782b78f8a048 100644 --- a/arch/m68k/include/asm/io_mm.h +++ b/arch/m68k/include/asm/io_mm.h @@ -16,13 +16,11 @@ * isa_readX(),isa_writeX() are for ISA memory */ -#ifndef _IO_H -#define _IO_H +#ifndef _M68K_IO_MM_H +#define _M68K_IO_MM_H #ifdef __KERNEL__ -#define ARCH_HAS_IOREMAP_WT - #include <linux/compiler.h> #include <asm/raw_io.h> #include <asm/virtconvert.h> @@ -369,40 +367,6 @@ static inline void isa_delay(void) #define writew(val, addr) out_le16((addr), (val)) #endif /* CONFIG_ATARI_ROM_ISA */ -#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA) -/* - * We need to define dummy functions for GENERIC_IOMAP support. - */ -#define inb(port) 0xff -#define inb_p(port) 0xff -#define outb(val,port) ((void)0) -#define outb_p(val,port) ((void)0) -#define inw(port) 0xffff -#define inw_p(port) 0xffff -#define outw(val,port) ((void)0) -#define outw_p(val,port) ((void)0) -#define inl(port) 0xffffffffUL -#define inl_p(port) 0xffffffffUL -#define outl(val,port) ((void)0) -#define outl_p(val,port) ((void)0) - -#define insb(port,buf,nr) ((void)0) -#define outsb(port,buf,nr) ((void)0) -#define insw(port,buf,nr) ((void)0) -#define outsw(port,buf,nr) ((void)0) -#define insl(port,buf,nr) ((void)0) -#define outsl(port,buf,nr) ((void)0) - -/* - * These should be valid on any ioremap()ed region - */ -#define readb(addr) in_8(addr) -#define writeb(val,addr) out_8((addr),(val)) -#define readw(addr) in_le16(addr) -#define writew(val,addr) out_le16((addr),(val)) - -#endif /* !CONFIG_ISA && !CONFIG_ATARI_ROM_ISA */ - #define readl(addr) in_le32(addr) #define writel(val,addr) out_le32((addr),(val)) @@ -444,4 +408,4 @@ static inline void isa_delay(void) #define writew_relaxed(b, addr) writew(b, addr) #define writel_relaxed(b, addr) writel(b, addr) -#endif /* _IO_H */ +#endif /* _M68K_IO_MM_H */ diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h index 83a0a6d449f4..0498192e1d98 100644 --- a/arch/m68k/include/asm/io_no.h +++ b/arch/m68k/include/asm/io_no.h @@ -131,19 +131,7 @@ static inline void writel(u32 value, volatile void __iomem *addr) #define PCI_SPACE_LIMIT PCI_IO_MASK #endif /* CONFIG_PCI */ -/* - * These are defined in kmap.h as static inline functions. To maintain - * previous behavior we put these define guards here so io_mm.h doesn't - * see them. - */ -#ifdef CONFIG_MMU -#define memset_io memset_io -#define memcpy_fromio memcpy_fromio -#define memcpy_toio memcpy_toio -#endif - #include <asm/kmap.h> #include <asm/virtconvert.h> -#include <asm-generic/io.h> #endif /* _M68KNOMMU_IO_H */ diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h index 84b8333db8ad..aac7f045f7f0 100644 --- a/arch/m68k/include/asm/kmap.h +++ b/arch/m68k/include/asm/kmap.h @@ -4,6 +4,8 @@ #ifdef CONFIG_MMU +#define ARCH_HAS_IOREMAP_WT + /* Values for nocacheflag and cmode */ #define IOMAP_FULL_CACHING 0 #define IOMAP_NOCACHE_SER 1 @@ -16,6 +18,7 @@ */ extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag); +#define iounmap iounmap extern void iounmap(void __iomem *addr); extern void __iounmap(void *addr, unsigned long size); @@ -33,31 +36,35 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, } #define ioremap_uc ioremap_nocache +#define ioremap_wt ioremap_wt static inline void __iomem *ioremap_wt(unsigned long physaddr, unsigned long size) { return __ioremap(physaddr, size, IOMAP_WRITETHROUGH); } -#define ioremap_fillcache ioremap_fullcache +#define ioremap_fullcache ioremap_fullcache static inline void __iomem *ioremap_fullcache(unsigned long physaddr, unsigned long size) { return __ioremap(physaddr, size, IOMAP_FULL_CACHING); } +#define memset_io memset_io static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count) { __builtin_memset((void __force *) addr, val, count); } +#define memcpy_fromio memcpy_fromio static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, int count) { __builtin_memcpy(dst, (void __force *) src, count); } +#define memcpy_toio memcpy_toio static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int count) { diff --git a/arch/m68k/include/asm/machdep.h b/arch/m68k/include/asm/machdep.h index 1605da48ebf2..49bd3266b4b1 100644 --- a/arch/m68k/include/asm/machdep.h +++ b/arch/m68k/include/asm/machdep.h @@ -22,7 +22,6 @@ extern int (*mach_hwclk)(int, struct rtc_time*); extern unsigned int (*mach_get_ss)(void); extern int (*mach_get_rtc_pll)(struct rtc_pll_info *); extern int (*mach_set_rtc_pll)(struct rtc_pll_info *); -extern int (*mach_set_clock_mmss)(unsigned long); extern void (*mach_reset)( void ); extern void (*mach_halt)( void ); extern void (*mach_power_off)( void ); diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h index 9b840c03ebb7..08cee11180e6 100644 --- a/arch/m68k/include/asm/macintosh.h +++ b/arch/m68k/include/asm/macintosh.h @@ -57,7 +57,6 @@ struct mac_model #define MAC_SCSI_IIFX 5 #define MAC_SCSI_DUO 6 #define MAC_SCSI_LC 7 -#define MAC_SCSI_LATE 8 #define MAC_IDE_NONE 0 #define MAC_IDE_QUADRA 1 diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h index e644c4daf540..6bbe52025de3 100644 --- a/arch/m68k/include/asm/page_no.h +++ b/arch/m68k/include/asm/page_no.h @@ -18,7 +18,7 @@ extern unsigned long memory_end; #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE #define __pa(vaddr) ((unsigned long)(vaddr)) -#define __va(paddr) ((void *)(paddr)) +#define __va(paddr) ((void *)((unsigned long)(paddr))) #define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) #define pfn_to_virt(pfn) __va((pfn) << PAGE_SHIFT) diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c index 463572c4943f..e99993c57d6b 100644 --- a/arch/m68k/kernel/dma.c +++ b/arch/m68k/kernel/dma.c @@ -6,7 +6,7 @@ #undef DEBUG -#include <linux/dma-mapping.h> +#include <linux/dma-noncoherent.h> #include <linux/device.h> #include <linux/kernel.h> #include <linux/platform_device.h> @@ -19,7 +19,7 @@ #if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE) -static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t flag, unsigned long attrs) { struct page *page, **map; @@ -62,7 +62,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, return addr; } -static void m68k_dma_free(struct device *dev, size_t size, void *addr, +void arch_dma_free(struct device *dev, size_t size, void *addr, dma_addr_t handle, unsigned long attrs) { pr_debug("dma_free_coherent: %p, %x\n", addr, handle); @@ -73,8 +73,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *addr, #include <asm/cacheflush.h> -static void *m68k_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) { void *ret; @@ -89,7 +89,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, return ret; } -static void m68k_dma_free(struct device *dev, size_t size, void *vaddr, +void arch_dma_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { free_pages((unsigned long)vaddr, get_order(size)); @@ -97,8 +97,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *vaddr, #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */ -static void m68k_dma_sync_single_for_device(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(struct device *dev, phys_addr_t handle, + size_t size, enum dma_data_direction dir) { switch (dir) { case DMA_BIDIRECTIONAL: @@ -115,58 +115,6 @@ static void m68k_dma_sync_single_for_device(struct device *dev, } } -static void m68k_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sglist, int nents, enum dma_data_direction dir) -{ - int i; - struct scatterlist *sg; - - for_each_sg(sglist, sg, nents, i) { - dma_sync_single_for_device(dev, sg->dma_address, sg->length, - dir); - } -} - -static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t handle = page_to_phys(page) + offset; - - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_sync_single_for_device(dev, handle, size, dir); - - return handle; -} - -static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - int i; - struct scatterlist *sg; - - for_each_sg(sglist, sg, nents, i) { - sg->dma_address = sg_phys(sg); - - if (attrs & DMA_ATTR_SKIP_CPU_SYNC) - continue; - - dma_sync_single_for_device(dev, sg->dma_address, sg->length, - dir); - } - return nents; -} - -const struct dma_map_ops m68k_dma_ops = { - .alloc = m68k_dma_alloc, - .free = m68k_dma_free, - .map_page = m68k_dma_map_page, - .map_sg = m68k_dma_map_sg, - .sync_single_for_device = m68k_dma_sync_single_for_device, - .sync_sg_for_device = m68k_dma_sync_sg_for_device, -}; -EXPORT_SYMBOL(m68k_dma_ops); - void arch_setup_pdev_archdata(struct platform_device *pdev) { if (pdev->dev.coherent_dma_mask == DMA_MASK_NONE && diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index f35e3ebd6331..5d3596c180f9 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/module.h> @@ -88,7 +89,6 @@ void (*mach_get_hardware_list) (struct seq_file *m); /* machine dependent timer functions */ int (*mach_hwclk) (int, struct rtc_time*); EXPORT_SYMBOL(mach_hwclk); -int (*mach_set_clock_mmss) (unsigned long); unsigned int (*mach_get_ss)(void); int (*mach_get_rtc_pll)(struct rtc_pll_info *); int (*mach_set_rtc_pll)(struct rtc_pll_info *); @@ -165,6 +165,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record) be32_to_cpu(m->addr); m68k_memory[m68k_num_memory].size = be32_to_cpu(m->size); + memblock_add(m68k_memory[m68k_num_memory].addr, + m68k_memory[m68k_num_memory].size); m68k_num_memory++; } else pr_warn("%s: too many memory chunks\n", @@ -224,10 +226,6 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record) void __init setup_arch(char **cmdline_p) { -#ifndef CONFIG_SUN3 - int i; -#endif - /* The bootinfo is located right after the kernel */ if (!CPU_IS_COLDFIRE) m68k_parse_bootinfo((const struct bi_record *)_end); @@ -356,14 +354,9 @@ void __init setup_arch(char **cmdline_p) #endif #ifndef CONFIG_SUN3 - for (i = 1; i < m68k_num_memory; i++) - free_bootmem_node(NODE_DATA(i), m68k_memory[i].addr, - m68k_memory[i].size); #ifdef CONFIG_BLK_DEV_INITRD if (m68k_ramdisk.size) { - reserve_bootmem_node(__virt_to_node(phys_to_virt(m68k_ramdisk.addr)), - m68k_ramdisk.addr, m68k_ramdisk.size, - BOOTMEM_DEFAULT); + memblock_reserve(m68k_ramdisk.addr, m68k_ramdisk.size); initrd_start = (unsigned long)phys_to_virt(m68k_ramdisk.addr); initrd_end = initrd_start + m68k_ramdisk.size; pr_info("initrd: %08lx - %08lx\n", initrd_start, initrd_end); diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index a98af1018201..cfd5475bfc31 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -28,6 +28,7 @@ #include <linux/errno.h> #include <linux/string.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/initrd.h> @@ -51,7 +52,6 @@ char __initdata command_line[COMMAND_LINE_SIZE]; /* machine dependent timer functions */ void (*mach_sched_init)(irq_handler_t handler) __initdata = NULL; -int (*mach_set_clock_mmss)(unsigned long); int (*mach_hwclk) (int, struct rtc_time*); /* machine dependent reboot functions */ @@ -86,8 +86,6 @@ void (*mach_power_off)(void); void __init setup_arch(char **cmdline_p) { - int bootmap_size; - memory_start = PAGE_ALIGN(_ramstart); memory_end = _ramend; @@ -142,6 +140,8 @@ void __init setup_arch(char **cmdline_p) pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ", __bss_stop, memory_start, memory_start, memory_end); + memblock_add(memory_start, memory_end - memory_start); + /* Keep a copy of command line */ *cmdline_p = &command_line[0]; memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); @@ -158,23 +158,10 @@ void __init setup_arch(char **cmdline_p) min_low_pfn = PFN_DOWN(memory_start); max_pfn = max_low_pfn = PFN_DOWN(memory_end); - bootmap_size = init_bootmem_node( - NODE_DATA(0), - min_low_pfn, /* map goes here */ - PFN_DOWN(PAGE_OFFSET), - max_pfn); - /* - * Free the usable memory, we have to make sure we do not free - * the bootmem bitmap so we then reserve it after freeing it :-) - */ - free_bootmem(memory_start, memory_end - memory_start); - reserve_bootmem(memory_start, bootmap_size, BOOTMEM_DEFAULT); - #if defined(CONFIG_UBOOT) && defined(CONFIG_BLK_DEV_INITRD) if ((initrd_start > 0) && (initrd_start < initrd_end) && (initrd_end < memory_end)) - reserve_bootmem(initrd_start, initrd_end - initrd_start, - BOOTMEM_DEFAULT); + memblock_reserve(initrd_start, initrd_end - initrd_start); #endif /* if defined(CONFIG_BLK_DEV_INITRD) */ /* diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index e522307db47c..b02d7254b73a 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -57,7 +57,6 @@ static unsigned long mac_orig_videoaddr; /* Mac specific timer functions */ extern u32 mac_gettimeoffset(void); extern int mac_hwclk(int, struct rtc_time *); -extern int mac_set_clock_mmss(unsigned long); extern void iop_preinit(void); extern void iop_init(void); extern void via_init(void); @@ -158,7 +157,6 @@ void __init config_mac(void) mach_get_model = mac_get_model; arch_gettimeoffset = mac_gettimeoffset; mach_hwclk = mac_hwclk; - mach_set_clock_mmss = mac_set_clock_mmss; mach_reset = mac_reset; mach_halt = mac_poweroff; mach_power_off = mac_poweroff; @@ -709,7 +707,7 @@ static struct mac_model mac_data_table[] = { .name = "PowerBook 520", .adb_type = MAC_ADB_PB2, .via_type = MAC_VIA_QUADRA, - .scsi_type = MAC_SCSI_LATE, + .scsi_type = MAC_SCSI_OLD, .scc_type = MAC_SCC_QUADRA, .ether_type = MAC_ETHER_SONIC, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -943,18 +941,6 @@ static const struct resource mac_scsi_old_rsrc[] __initconst = { }, }; -static const struct resource mac_scsi_late_rsrc[] __initconst = { - { - .flags = IORESOURCE_IRQ, - .start = IRQ_MAC_SCSI, - .end = IRQ_MAC_SCSI, - }, { - .flags = IORESOURCE_MEM, - .start = 0x50010000, - .end = 0x50011FFF, - }, -}; - static const struct resource mac_scsi_ccl_rsrc[] __initconst = { { .flags = IORESOURCE_IRQ, @@ -1064,11 +1050,6 @@ int __init mac_platform_init(void) platform_device_register_simple("mac_scsi", 0, mac_scsi_old_rsrc, ARRAY_SIZE(mac_scsi_old_rsrc)); break; - case MAC_SCSI_LATE: - /* XXX PDMA support for PowerBook 500 series needs testing */ - platform_device_register_simple("mac_scsi", 0, - mac_scsi_late_rsrc, ARRAY_SIZE(mac_scsi_late_rsrc)); - break; case MAC_SCSI_LC: /* Addresses from Mac LC data in Designing Cards & Drivers 3ed. * Also from the Developer Notes for Classic II, LC III, diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index c68054361615..19e9d8eef1f2 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -26,33 +26,38 @@ #include <asm/machdep.h> -/* Offset between Unix time (1970-based) and Mac time (1904-based) */ +/* + * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU + * times wrap in 2040. If we need to handle later times, the read_time functions + * need to be changed to interpret wrapped times as post-2040. + */ #define RTC_OFFSET 2082844800 static void (*rom_reset)(void); #ifdef CONFIG_ADB_CUDA -static long cuda_read_time(void) +static time64_t cuda_read_time(void) { struct adb_request req; - long time; + time64_t time; if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0) return 0; while (!req.complete) cuda_poll(); - time = (req.reply[3] << 24) | (req.reply[4] << 16) | - (req.reply[5] << 8) | req.reply[6]; + time = (u32)((req.reply[3] << 24) | (req.reply[4] << 16) | + (req.reply[5] << 8) | req.reply[6]); + return time - RTC_OFFSET; } -static void cuda_write_time(long data) +static void cuda_write_time(time64_t time) { struct adb_request req; + u32 data = lower_32_bits(time + RTC_OFFSET); - data += RTC_OFFSET; if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME, (data >> 24) & 0xFF, (data >> 16) & 0xFF, (data >> 8) & 0xFF, data & 0xFF) < 0) @@ -86,26 +91,27 @@ static void cuda_write_pram(int offset, __u8 data) #endif /* CONFIG_ADB_CUDA */ #ifdef CONFIG_ADB_PMU68K -static long pmu_read_time(void) +static time64_t pmu_read_time(void) { struct adb_request req; - long time; + time64_t time; if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0) return 0; while (!req.complete) pmu_poll(); - time = (req.reply[1] << 24) | (req.reply[2] << 16) | - (req.reply[3] << 8) | req.reply[4]; + time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) | + (req.reply[3] << 8) | req.reply[4]); + return time - RTC_OFFSET; } -static void pmu_write_time(long data) +static void pmu_write_time(time64_t time) { struct adb_request req; + u32 data = lower_32_bits(time + RTC_OFFSET); - data += RTC_OFFSET; if (pmu_request(&req, NULL, 5, PMU_SET_RTC, (data >> 24) & 0xFF, (data >> 16) & 0xFF, (data >> 8) & 0xFF, data & 0xFF) < 0) @@ -245,11 +251,11 @@ static void via_write_pram(int offset, __u8 data) * is basically any machine with Mac II-style ADB. */ -static long via_read_time(void) +static time64_t via_read_time(void) { union { __u8 cdata[4]; - long idata; + __u32 idata; } result, last_result; int count = 1; @@ -270,7 +276,7 @@ static long via_read_time(void) via_pram_command(0x8D, &result.cdata[0]); if (result.idata == last_result.idata) - return result.idata - RTC_OFFSET; + return (time64_t)result.idata - RTC_OFFSET; if (++count > 10) break; @@ -278,8 +284,8 @@ static long via_read_time(void) last_result.idata = result.idata; } - pr_err("via_read_time: failed to read a stable value; got 0x%08lx then 0x%08lx\n", - last_result.idata, result.idata); + pr_err("%s: failed to read a stable value; got 0x%08x then 0x%08x\n", + __func__, last_result.idata, result.idata); return 0; } @@ -291,11 +297,11 @@ static long via_read_time(void) * is basically any machine with Mac II-style ADB. */ -static void via_write_time(long time) +static void via_write_time(time64_t time) { union { __u8 cdata[4]; - long idata; + __u32 idata; } data; __u8 temp; @@ -304,7 +310,7 @@ static void via_write_time(long time) temp = 0x55; via_pram_command(0x35, &temp); - data.idata = time + RTC_OFFSET; + data.idata = lower_32_bits(time + RTC_OFFSET); via_pram_command(0x01, &data.cdata[3]); via_pram_command(0x05, &data.cdata[2]); via_pram_command(0x09, &data.cdata[1]); @@ -585,12 +591,15 @@ void mac_reset(void) * This function translates seconds since 1970 into a proper date. * * Algorithm cribbed from glibc2.1, __offtime(). + * + * This is roughly same as rtc_time64_to_tm(), which we should probably + * use here, but it's only available when CONFIG_RTC_LIB is enabled. */ #define SECS_PER_MINUTE (60) #define SECS_PER_HOUR (SECS_PER_MINUTE * 60) #define SECS_PER_DAY (SECS_PER_HOUR * 24) -static void unmktime(unsigned long time, long offset, +static void unmktime(time64_t time, long offset, int *yearp, int *monp, int *dayp, int *hourp, int *minp, int *secp) { @@ -602,11 +611,10 @@ static void unmktime(unsigned long time, long offset, /* Leap years. */ { 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 } }; - long int days, rem, y, wday, yday; + int days, rem, y, wday, yday; const unsigned short int *ip; - days = time / SECS_PER_DAY; - rem = time % SECS_PER_DAY; + days = div_u64_rem(time, SECS_PER_DAY, &rem); rem += offset; while (rem < 0) { rem += SECS_PER_DAY; @@ -657,7 +665,7 @@ static void unmktime(unsigned long time, long offset, int mac_hwclk(int op, struct rtc_time *t) { - unsigned long now; + time64_t now; if (!op) { /* read */ switch (macintosh_config->adb_type) { @@ -693,8 +701,8 @@ int mac_hwclk(int op, struct rtc_time *t) __func__, t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, t->tm_hour, t->tm_min, t->tm_sec); - now = mktime(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, - t->tm_hour, t->tm_min, t->tm_sec); + now = mktime64(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, + t->tm_hour, t->tm_min, t->tm_sec); switch (macintosh_config->adb_type) { case MAC_ADB_IOP: @@ -719,19 +727,3 @@ int mac_hwclk(int op, struct rtc_time *t) } return 0; } - -/* - * Set minutes/seconds in the hardware clock - */ - -int mac_set_clock_mmss (unsigned long nowtime) -{ - struct rtc_time now; - - mac_hwclk(0, &now); - now.tm_sec = nowtime % 60; - now.tm_min = (nowtime / 60) % 60; - mac_hwclk(1, &now); - - return 0; -} diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 8827b7f91402..38e2b272c220 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -71,7 +71,6 @@ void __init m68k_setup_node(int node) pg_data_table[i] = pg_data_map + node; } #endif - pg_data_map[node].bdata = bootmem_node_data + node; node_set_online(node); } diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 2925d795d71a..70dde040779b 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/string.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/page.h> @@ -153,31 +154,31 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word) void __init cf_bootmem_alloc(void) { - unsigned long start_pfn; unsigned long memstart; /* _rambase and _ramend will be naturally page aligned */ m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; + memblock_add(m68k_memory[0].addr, m68k_memory[0].size); + /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); /* page numbers */ memstart = PAGE_ALIGN(_ramstart); min_low_pfn = PFN_DOWN(_rambase); - start_pfn = PFN_DOWN(memstart); max_pfn = max_low_pfn = PFN_DOWN(_ramend); high_memory = (void *)_ramend; + /* Reserve kernel text/data/bss */ + memblock_reserve(memstart, memstart - _rambase); + m68k_virt_to_node_shift = fls(_ramend - 1) - 6; module_fixup(NULL, __start_fixup, __stop_fixup); - /* setup bootmem data */ + /* setup node data */ m68k_setup_node(0); - memstart += init_bootmem_node(NODE_DATA(0), start_pfn, - min_low_pfn, max_low_pfn); - free_bootmem_node(NODE_DATA(0), memstart, _ramend - memstart); } /* diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index e490ecc7842c..4e17ecb5928a 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -19,6 +19,7 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/gfp.h> #include <asm/setup.h> @@ -208,7 +209,7 @@ void __init paging_init(void) { unsigned long zones_size[MAX_NR_ZONES] = { 0, }; unsigned long min_addr, max_addr; - unsigned long addr, size, end; + unsigned long addr; int i; #ifdef DEBUG @@ -253,34 +254,20 @@ void __init paging_init(void) min_low_pfn = availmem >> PAGE_SHIFT; max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT; - for (i = 0; i < m68k_num_memory; i++) { - addr = m68k_memory[i].addr; - end = addr + m68k_memory[i].size; - m68k_setup_node(i); - availmem = PAGE_ALIGN(availmem); - availmem += init_bootmem_node(NODE_DATA(i), - availmem >> PAGE_SHIFT, - addr >> PAGE_SHIFT, - end >> PAGE_SHIFT); - } + /* Reserve kernel text/data/bss and the memory allocated in head.S */ + memblock_reserve(m68k_memory[0].addr, availmem - m68k_memory[0].addr); /* * Map the physical memory available into the kernel virtual - * address space. First initialize the bootmem allocator with - * the memory we already mapped, so map_node() has something - * to allocate. + * address space. Make sure memblock will not try to allocate + * pages beyond the memory we already mapped in head.S */ - addr = m68k_memory[0].addr; - size = m68k_memory[0].size; - free_bootmem_node(NODE_DATA(0), availmem, - min(m68k_init_mapped_size, size) - (availmem - addr)); - map_node(0); - if (size > m68k_init_mapped_size) - free_bootmem_node(NODE_DATA(0), addr + m68k_init_mapped_size, - size - m68k_init_mapped_size); - - for (i = 1; i < m68k_num_memory; i++) + memblock_set_bottom_up(true); + + for (i = 0; i < m68k_num_memory; i++) { + m68k_setup_node(i); map_node(i); + } flush_tlb_all(); diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c index f8a710fd84cd..adea549d240e 100644 --- a/arch/m68k/mvme147/config.c +++ b/arch/m68k/mvme147/config.c @@ -40,7 +40,6 @@ static void mvme147_get_model(char *model); extern void mvme147_sched_init(irq_handler_t handler); extern u32 mvme147_gettimeoffset(void); extern int mvme147_hwclk (int, struct rtc_time *); -extern int mvme147_set_clock_mmss (unsigned long); extern void mvme147_reset (void); @@ -92,7 +91,6 @@ void __init config_mvme147(void) mach_init_IRQ = mvme147_init_IRQ; arch_gettimeoffset = mvme147_gettimeoffset; mach_hwclk = mvme147_hwclk; - mach_set_clock_mmss = mvme147_set_clock_mmss; mach_reset = mvme147_reset; mach_get_model = mvme147_get_model; @@ -164,8 +162,3 @@ int mvme147_hwclk(int op, struct rtc_time *t) } return 0; } - -int mvme147_set_clock_mmss (unsigned long nowtime) -{ - return 0; -} diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c index 4ffd9ef98de4..6ee36a5b528d 100644 --- a/arch/m68k/mvme16x/config.c +++ b/arch/m68k/mvme16x/config.c @@ -46,7 +46,6 @@ static void mvme16x_get_model(char *model); extern void mvme16x_sched_init(irq_handler_t handler); extern u32 mvme16x_gettimeoffset(void); extern int mvme16x_hwclk (int, struct rtc_time *); -extern int mvme16x_set_clock_mmss (unsigned long); extern void mvme16x_reset (void); int bcd2int (unsigned char b); @@ -280,7 +279,6 @@ void __init config_mvme16x(void) mach_init_IRQ = mvme16x_init_IRQ; arch_gettimeoffset = mvme16x_gettimeoffset; mach_hwclk = mvme16x_hwclk; - mach_set_clock_mmss = mvme16x_set_clock_mmss; mach_reset = mvme16x_reset; mach_get_model = mvme16x_get_model; mach_get_hardware_list = mvme16x_get_hardware_list; @@ -411,9 +409,3 @@ int mvme16x_hwclk(int op, struct rtc_time *t) } return 0; } - -int mvme16x_set_clock_mmss (unsigned long nowtime) -{ - return 0; -} - diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index 71c0867ecf20..96810d91da2b 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -43,7 +43,6 @@ extern void q40_sched_init(irq_handler_t handler); static u32 q40_gettimeoffset(void); static int q40_hwclk(int, struct rtc_time *); static unsigned int q40_get_ss(void); -static int q40_set_clock_mmss(unsigned long); static int q40_get_rtc_pll(struct rtc_pll_info *pll); static int q40_set_rtc_pll(struct rtc_pll_info *pll); @@ -175,7 +174,6 @@ void __init config_q40(void) mach_get_ss = q40_get_ss; mach_get_rtc_pll = q40_get_rtc_pll; mach_set_rtc_pll = q40_set_rtc_pll; - mach_set_clock_mmss = q40_set_clock_mmss; mach_reset = q40_reset; mach_get_model = q40_get_model; @@ -267,34 +265,6 @@ static unsigned int q40_get_ss(void) return bcd2bin(Q40_RTC_SECS); } -/* - * Set the minutes and seconds from seconds value 'nowtime'. Fail if - * clock is out by > 30 minutes. Logic lifted from atari code. - */ - -static int q40_set_clock_mmss(unsigned long nowtime) -{ - int retval = 0; - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - - int rtc_minutes; - - rtc_minutes = bcd2bin(Q40_RTC_MINS); - - if ((rtc_minutes < real_minutes ? - real_minutes - rtc_minutes : - rtc_minutes - real_minutes) < 30) { - Q40_RTC_CTRL |= Q40_RTC_WRITE; - Q40_RTC_MINS = bin2bcd(real_minutes); - Q40_RTC_SECS = bin2bcd(real_seconds); - Q40_RTC_CTRL &= ~(Q40_RTC_WRITE); - } else - retval = -1; - - return retval; -} - - /* get and set PLL calibration of RTC clock */ #define Q40_RTC_PLL_MASK ((1<<5)-1) #define Q40_RTC_PLL_SIGN (1<<5) diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c index 1d28d380e8cc..79a2bb857906 100644 --- a/arch/m68k/sun3/config.c +++ b/arch/m68k/sun3/config.c @@ -123,10 +123,6 @@ static void __init sun3_bootmem_alloc(unsigned long memory_start, availmem = memory_start; m68k_setup_node(0); - availmem += init_bootmem(start_page, num_pages); - availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK; - - free_bootmem(__pa(availmem), memory_end - (availmem)); } diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c index 10a405d593df..c782b10ddf50 100644 --- a/arch/mips/ath79/common.c +++ b/arch/mips/ath79/common.c @@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init); void ath79_ddr_wb_flush(u32 reg) { - void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg; + void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4); /* Flush the DDR write buffer. */ __raw_writel(0x1, flush_reg); diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 8c9cbf13d32a..6054d49e608e 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -212,12 +212,6 @@ static int __init bcm47xx_cpu_fixes(void) */ if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706) cpu_wait = NULL; - - /* - * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail" - * Enable ExternalSync for sync instruction to take effect - */ - set_c0_config7(MIPS_CONF7_ES); break; #endif } diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 0ab176bdb8e8..79be687de4ab 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -274,97 +274,12 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - -/* - * atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -/* - * atomic_dec_and_test - decrement by 1 and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) - /* * atomic_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic_t */ #define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v) -/* - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc(v) atomic_add(1, (v)) - -/* - * atomic_dec - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec(v) atomic_sub(1, (v)) - -/* - * atomic_add_negative - add and test if negative - * @v: pointer of type atomic_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0) - #ifdef CONFIG_64BIT #define ATOMIC64_INIT(i) { (i) } @@ -620,99 +535,12 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v) ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), (new))) -/** - * atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns true iff @v was not @u. - */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - -/* - * atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0) - -/* - * atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - -/* - * atomic64_dec_and_test - decrement by 1 and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) - /* * atomic64_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic64_t */ #define atomic64_dec_if_positive(v) atomic64_sub_if_positive(1, v) -/* - * atomic64_inc - increment atomic variable - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1. - */ -#define atomic64_inc(v) atomic64_add(1, (v)) - -/* - * atomic64_dec - decrement and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1. - */ -#define atomic64_dec(v) atomic64_sub(1, (v)) - -/* - * atomic64_add_negative - add and test if negative - * @v: pointer of type atomic64_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0) - #endif /* CONFIG_64BIT */ #endif /* _ASM_ATOMIC_H */ diff --git a/arch/mips/include/asm/kprobes.h b/arch/mips/include/asm/kprobes.h index ad1a99948f27..a72dfbf1babb 100644 --- a/arch/mips/include/asm/kprobes.h +++ b/arch/mips/include/asm/kprobes.h @@ -68,16 +68,6 @@ struct prev_kprobe { unsigned long saved_epc; }; -#define MAX_JPROBES_STACK_SIZE 128 -#define MAX_JPROBES_STACK_ADDR \ - (((unsigned long)current_thread_info()) + THREAD_SIZE - 32 - sizeof(struct pt_regs)) - -#define MIN_JPROBES_STACK_SIZE(ADDR) \ - ((((ADDR) + MAX_JPROBES_STACK_SIZE) > MAX_JPROBES_STACK_ADDR) \ - ? MAX_JPROBES_STACK_ADDR - (ADDR) \ - : MAX_JPROBES_STACK_SIZE) - - #define SKIP_DELAYSLOT 0x0001 /* per-cpu kprobe control block */ @@ -86,12 +76,9 @@ struct kprobe_ctlblk { unsigned long kprobe_old_SR; unsigned long kprobe_saved_SR; unsigned long kprobe_saved_epc; - unsigned long jprobe_saved_sp; - struct pt_regs jprobe_saved_regs; /* Per-thread fields, used while emulating branches */ unsigned long flags; unsigned long target_epc; - u8 jprobes_stack[MAX_JPROBES_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 0bc270806ec5..ae461d91cd1f 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -681,8 +681,6 @@ #define MIPS_CONF7_WII (_ULCAST_(1) << 31) #define MIPS_CONF7_RPS (_ULCAST_(1) << 2) -/* ExternalSync */ -#define MIPS_CONF7_ES (_ULCAST_(1) << 8) #define MIPS_CONF7_IAR (_ULCAST_(1) << 10) #define MIPS_CONF7_AR (_ULCAST_(1) << 16) @@ -2767,7 +2765,6 @@ __BUILD_SET_C0(status) __BUILD_SET_C0(cause) __BUILD_SET_C0(config) __BUILD_SET_C0(config5) -__BUILD_SET_C0(config7) __BUILD_SET_C0(intcontrol) __BUILD_SET_C0(intctl) __BUILD_SET_C0(srsmap) diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c index f5c8bce70db2..54cd675c5d1d 100644 --- a/arch/mips/kernel/kprobes.c +++ b/arch/mips/kernel/kprobes.c @@ -326,19 +326,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) preempt_enable_no_resched(); } return 1; - } else { - if (addr->word != breakpoint_insn.word) { - /* - * The breakpoint instruction was removed by - * another cpu right after we hit, no further - * handling of this interrupt is appropriate - */ - ret = 1; - goto no_kprobe; - } - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) - goto ss_probe; + } else if (addr->word != breakpoint_insn.word) { + /* + * The breakpoint instruction was removed by + * another cpu right after we hit, no further + * handling of this interrupt is appropriate + */ + ret = 1; } goto no_kprobe; } @@ -364,10 +358,11 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) if (p->pre_handler && p->pre_handler(p, regs)) { /* handler has already set things up, so skip ss setup */ + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; } -ss_probe: prepare_singlestep(p, regs, kcb); if (kcb->flags & SKIP_DELAYSLOT) { kcb->kprobe_status = KPROBE_HIT_SSDONE; @@ -468,51 +463,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - kcb->jprobe_saved_sp = regs->regs[29]; - - memcpy(kcb->jprobes_stack, (void *)kcb->jprobe_saved_sp, - MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp)); - - regs->cp0_epc = (unsigned long)(jp->entry); - - return 1; -} - -/* Defined in the inline asm below. */ -void jprobe_return_end(void); - -void __kprobes jprobe_return(void) -{ - /* Assembler quirk necessitates this '0,code' business. */ - asm volatile( - "break 0,%0\n\t" - ".globl jprobe_return_end\n" - "jprobe_return_end:\n" - : : "n" (BRK_KPROBE_BP) : "memory"); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (regs->cp0_epc >= (unsigned long)jprobe_return && - regs->cp0_epc <= (unsigned long)jprobe_return_end) { - *regs = kcb->jprobe_saved_regs; - memcpy((void *)kcb->jprobe_saved_sp, kcb->jprobes_stack, - MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp)); - preempt_enable_no_resched(); - - return 1; - } - return 0; -} - /* * Function return probe trampoline: * - init_kprobes() establishes a probepoint here @@ -595,9 +545,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_assert(ri, orig_ret_address, trampoline_address); instruction_pointer(regs) = orig_ret_address; - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 7cd76f93a438..f7ea8e21656b 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -515,7 +515,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, dvcpu->arch.wait = 0; if (swq_has_sleeper(&dvcpu->wq)) - swake_up(&dvcpu->wq); + swake_up_one(&dvcpu->wq); return 0; } @@ -1204,7 +1204,7 @@ static void kvm_mips_comparecount_func(unsigned long data) vcpu->arch.wait = 0; if (swq_has_sleeper(&vcpu->wq)) - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); } /* low level hrtimer wake routine */ diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 9632436d74d7..c2e94cf5ecda 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -54,5 +54,5 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, phys_addr_t size = resource_size(rsrc); *start = fixup_bigphys_addr(rsrc->start, size); - *end = rsrc->start + size; + *end = rsrc->start + size - 1; } diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 6aed974276d8..34f7222c5efe 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -12,17 +12,17 @@ config NDS32 select CLONE_BACKWARDS select COMMON_CLK select DMA_NONCOHERENT_OPS - select GENERIC_ASHLDI3 - select GENERIC_ASHRDI3 - select GENERIC_LSHRDI3 - select GENERIC_CMPDI2 - select GENERIC_MULDI3 - select GENERIC_UCMPDI2 select GENERIC_ATOMIC64 select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS select GENERIC_IRQ_CHIP select GENERIC_IRQ_SHOW + select GENERIC_LIB_ASHLDI3 + select GENERIC_LIB_ASHRDI3 + select GENERIC_LIB_CMPDI2 + select GENERIC_LIB_LSHRDI3 + select GENERIC_LIB_MULDI3 + select GENERIC_LIB_UCMPDI2 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile index 513bb2e9baf9..031c676821ff 100644 --- a/arch/nds32/Makefile +++ b/arch/nds32/Makefile @@ -34,10 +34,12 @@ ifdef CONFIG_CPU_LITTLE_ENDIAN KBUILD_CFLAGS += $(call cc-option, -EL) KBUILD_AFLAGS += $(call cc-option, -EL) LDFLAGS += $(call cc-option, -EL) +CHECKFLAGS += -D__NDS32_EL__ else KBUILD_CFLAGS += $(call cc-option, -EB) KBUILD_AFLAGS += $(call cc-option, -EB) LDFLAGS += $(call cc-option, -EB) +CHECKFLAGS += -D__NDS32_EB__ endif boot := arch/nds32/boot diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index 10b48f0d8e85..8b26198d51bb 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -8,6 +8,8 @@ #define PG_dcache_dirty PG_arch_1 +void flush_icache_range(unsigned long start, unsigned long end); +void flush_icache_page(struct vm_area_struct *vma, struct page *page); #ifdef CONFIG_CPU_CACHE_ALIASING void flush_cache_mm(struct mm_struct *mm); void flush_cache_dup_mm(struct mm_struct *mm); @@ -34,13 +36,16 @@ void flush_anon_page(struct vm_area_struct *vma, void flush_kernel_dcache_page(struct page *page); void flush_kernel_vmap_range(void *addr, int size); void invalidate_kernel_vmap_range(void *addr, int size); -void flush_icache_range(unsigned long start, unsigned long end); -void flush_icache_page(struct vm_area_struct *vma, struct page *page); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&(mapping)->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages) #else #include <asm-generic/cacheflush.h> +#undef flush_icache_range +#undef flush_icache_page +#undef flush_icache_user_range +void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, + unsigned long addr, int len); #endif #endif /* __NDS32_CACHEFLUSH_H__ */ diff --git a/arch/nds32/include/asm/futex.h b/arch/nds32/include/asm/futex.h index eab5e84bd991..cb6cb91cfdf8 100644 --- a/arch/nds32/include/asm/futex.h +++ b/arch/nds32/include/asm/futex.h @@ -16,7 +16,7 @@ " .popsection\n" \ " .pushsection .fixup,\"ax\"\n" \ "4: move %0, " err_reg "\n" \ - " j 3b\n" \ + " b 3b\n" \ " .popsection" #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg) \ diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c index 2f5b2ccebe47..63a1a5ef5219 100644 --- a/arch/nds32/kernel/setup.c +++ b/arch/nds32/kernel/setup.c @@ -278,7 +278,8 @@ static void __init setup_memory(void) void __init setup_arch(char **cmdline_p) { - early_init_devtree( __dtb_start); + early_init_devtree(__atags_pointer ? \ + phys_to_virt(__atags_pointer) : __dtb_start); setup_cpuinfo(); diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c index ce8fd34497bf..254703653b6f 100644 --- a/arch/nds32/mm/cacheflush.c +++ b/arch/nds32/mm/cacheflush.c @@ -13,7 +13,39 @@ extern struct cache_info L1_cache_info[2]; -#ifndef CONFIG_CPU_CACHE_ALIASING +void flush_icache_range(unsigned long start, unsigned long end) +{ + unsigned long line_size, flags; + line_size = L1_cache_info[DCACHE].line_size; + start = start & ~(line_size - 1); + end = (end + line_size - 1) & ~(line_size - 1); + local_irq_save(flags); + cpu_cache_wbinval_range(start, end, 1); + local_irq_restore(flags); +} +EXPORT_SYMBOL(flush_icache_range); + +void flush_icache_page(struct vm_area_struct *vma, struct page *page) +{ + unsigned long flags; + unsigned long kaddr; + local_irq_save(flags); + kaddr = (unsigned long)kmap_atomic(page); + cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC); + kunmap_atomic((void *)kaddr); + local_irq_restore(flags); +} +EXPORT_SYMBOL(flush_icache_page); + +void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, + unsigned long addr, int len) +{ + unsigned long kaddr; + kaddr = (unsigned long)kmap_atomic(page) + (addr & ~PAGE_MASK); + flush_icache_range(kaddr, kaddr + len); + kunmap_atomic((void *)kaddr); +} + void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t * pte) { @@ -35,19 +67,15 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, if ((test_and_clear_bit(PG_dcache_dirty, &page->flags)) || (vma->vm_flags & VM_EXEC)) { - - if (!PageHighMem(page)) { - cpu_cache_wbinval_page((unsigned long) - page_address(page), - vma->vm_flags & VM_EXEC); - } else { - unsigned long kaddr = (unsigned long)kmap_atomic(page); - cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC); - kunmap_atomic((void *)kaddr); - } + unsigned long kaddr; + local_irq_save(flags); + kaddr = (unsigned long)kmap_atomic(page); + cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC); + kunmap_atomic((void *)kaddr); + local_irq_restore(flags); } } -#else +#ifdef CONFIG_CPU_CACHE_ALIASING extern pte_t va_present(struct mm_struct *mm, unsigned long addr); static inline unsigned long aliasing(unsigned long addr, unsigned long page) @@ -317,52 +345,4 @@ void invalidate_kernel_vmap_range(void *addr, int size) local_irq_restore(flags); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); - -void flush_icache_range(unsigned long start, unsigned long end) -{ - unsigned long line_size, flags; - line_size = L1_cache_info[DCACHE].line_size; - start = start & ~(line_size - 1); - end = (end + line_size - 1) & ~(line_size - 1); - local_irq_save(flags); - cpu_cache_wbinval_range(start, end, 1); - local_irq_restore(flags); -} -EXPORT_SYMBOL(flush_icache_range); - -void flush_icache_page(struct vm_area_struct *vma, struct page *page) -{ - unsigned long flags; - local_irq_save(flags); - cpu_cache_wbinval_page((unsigned long)page_address(page), - vma->vm_flags & VM_EXEC); - local_irq_restore(flags); -} - -void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, - pte_t * pte) -{ - struct page *page; - unsigned long flags; - unsigned long pfn = pte_pfn(*pte); - - if (!pfn_valid(pfn)) - return; - - if (vma->vm_mm == current->active_mm) { - local_irq_save(flags); - __nds32__mtsr_dsb(addr, NDS32_SR_TLB_VPN); - __nds32__tlbop_rwr(*pte); - __nds32__isb(); - local_irq_restore(flags); - } - - page = pfn_to_page(pfn); - if (test_and_clear_bit(PG_dcache_dirty, &page->flags) || - (vma->vm_flags & VM_EXEC)) { - local_irq_save(flags); - cpu_dcache_wbinval_page((unsigned long)page_address(page)); - local_irq_restore(flags); - } -} #endif diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index 9ecad05bfc73..dfb6a79ba7ff 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -27,7 +27,6 @@ config OPENRISC select GENERIC_STRNLEN_USER select GENERIC_SMP_IDLE_THREAD select MODULES_USE_ELF_RELA - select MULTI_IRQ_HANDLER select HAVE_DEBUG_STACKOVERFLOW select OR1K_PIC select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1 @@ -36,6 +35,7 @@ config OPENRISC select ARCH_USE_QUEUED_RWLOCKS select OMPIC if SMP select ARCH_WANT_FRAME_POINTERS + select GENERIC_IRQ_MULTI_HANDLER config CPU_BIG_ENDIAN def_bool y @@ -69,9 +69,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config MULTI_IRQ_HANDLER - def_bool y - source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/openrisc/include/asm/atomic.h b/arch/openrisc/include/asm/atomic.h index 146e1660f00e..b589fac39b92 100644 --- a/arch/openrisc/include/asm/atomic.h +++ b/arch/openrisc/include/asm/atomic.h @@ -100,7 +100,7 @@ ATOMIC_OP(xor) * * This is often used through atomic_inc_not_zero() */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int old, tmp; @@ -119,7 +119,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) return old; } -#define __atomic_add_unless __atomic_add_unless +#define atomic_fetch_add_unless atomic_fetch_add_unless #include <asm-generic/atomic.h> diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h index d29f7db53906..f9cd43a39d72 100644 --- a/arch/openrisc/include/asm/cmpxchg.h +++ b/arch/openrisc/include/asm/cmpxchg.h @@ -16,8 +16,9 @@ #ifndef __ASM_OPENRISC_CMPXCHG_H #define __ASM_OPENRISC_CMPXCHG_H +#include <linux/bits.h> +#include <linux/compiler.h> #include <linux/types.h> -#include <linux/bitops.h> #define __HAVE_ARCH_CMPXCHG 1 diff --git a/arch/openrisc/include/asm/irq.h b/arch/openrisc/include/asm/irq.h index d9eee0a2b7b4..eb612b1865d2 100644 --- a/arch/openrisc/include/asm/irq.h +++ b/arch/openrisc/include/asm/irq.h @@ -24,6 +24,4 @@ #define NO_IRQ (-1) -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); - #endif /* __ASM_OPENRISC_IRQ_H__ */ diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c index 35e478a93116..5f9445effaf8 100644 --- a/arch/openrisc/kernel/irq.c +++ b/arch/openrisc/kernel/irq.c @@ -41,13 +41,6 @@ void __init init_IRQ(void) irqchip_init(); } -static void (*handle_arch_irq)(struct pt_regs *); - -void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) -{ - handle_arch_irq = handle_irq; -} - void __irq_entry do_IRQ(struct pt_regs *regs) { handle_arch_irq(regs); diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 17526bebcbd2..e7705dde953f 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -11,7 +11,6 @@ config PARISC select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_WANTS_UBSAN_NO_NULL select ARCH_SUPPORTS_MEMORY_FAILURE select RTC_CLASS select RTC_DRV_GENERIC @@ -195,7 +194,7 @@ config PREFETCH config MLONGCALLS bool "Enable the -mlong-calls compiler option for big kernels" - def_bool y if (!MODULES) + default y depends on PA8X00 help If you configure the kernel to include many drivers built-in instead diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 88bae6676c9b..118953d41763 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -77,30 +77,6 @@ static __inline__ int atomic_read(const atomic_t *v) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define ATOMIC_OP(op, c_op) \ static __inline__ void atomic_##op(int i, atomic_t *v) \ { \ @@ -160,28 +136,6 @@ ATOMIC_OPS(xor, ^=) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_inc(v) (atomic_add( 1,(v))) -#define atomic_dec(v) (atomic_add( -1,(v))) - -#define atomic_inc_return(v) (atomic_add_return( 1,(v))) -#define atomic_dec_return(v) (atomic_add_return( -1,(v))) - -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0) - #define ATOMIC_INIT(i) { (i) } #ifdef CONFIG_64BIT @@ -264,72 +218,11 @@ atomic64_read(const atomic64_t *v) return READ_ONCE((v)->counter); } -#define atomic64_inc(v) (atomic64_add( 1,(v))) -#define atomic64_dec(v) (atomic64_add( -1,(v))) - -#define atomic64_inc_return(v) (atomic64_add_return( 1,(v))) -#define atomic64_dec_return(v) (atomic64_add_return( -1,(v))) - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i),(v)) == 0) - /* exported interface */ #define atomic64_cmpxchg(v, o, n) \ ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -/* - * atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - * - * The function returns the old value of *v minus 1, even if - * the atomic variable, v, was not decremented. - */ -static inline long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - #endif /* !CONFIG_64BIT */ diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h new file mode 100644 index 000000000000..dbaaca84f27f --- /dev/null +++ b/arch/parisc/include/asm/barrier.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_BARRIER_H +#define __ASM_BARRIER_H + +#ifndef __ASSEMBLY__ + +/* The synchronize caches instruction executes as a nop on systems in + which all memory references are performed in order. */ +#define synchronize_caches() __asm__ __volatile__ ("sync" : : : "memory") + +#if defined(CONFIG_SMP) +#define mb() do { synchronize_caches(); } while (0) +#define rmb() mb() +#define wmb() mb() +#define dma_rmb() mb() +#define dma_wmb() mb() +#else +#define mb() barrier() +#define rmb() barrier() +#define wmb() barrier() +#define dma_rmb() barrier() +#define dma_wmb() barrier() +#endif + +#define __smp_mb() mb() +#define __smp_rmb() mb() +#define __smp_wmb() mb() + +#include <asm-generic/barrier.h> + +#endif /* !__ASSEMBLY__ */ +#endif /* __ASM_BARRIER_H */ diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index e95207c0565e..1b4732e20137 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -482,6 +482,8 @@ .macro tlb_unlock0 spc,tmp #ifdef CONFIG_SMP or,COND(=) %r0,\spc,%r0 + sync + or,COND(=) %r0,\spc,%r0 stw \spc,0(\tmp) #endif .endm diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index 22e6374ece44..97451e67d35b 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -353,6 +353,7 @@ ENDPROC_CFI(flush_data_cache_local) .macro tlb_unlock la,flags,tmp #ifdef CONFIG_SMP ldi 1,\tmp + sync stw \tmp,0(\la) mtsm \flags #endif diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index e775f80ae28c..4886a6db42e9 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -633,6 +633,7 @@ cas_action: sub,<> %r28, %r25, %r0 2: stw,ma %r24, 0(%r26) /* Free lock */ + sync stw,ma %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG /* Clear thread register indicator */ @@ -647,6 +648,7 @@ cas_action: 3: /* Error occurred on load or store */ /* Free lock */ + sync stw %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG stw %r0, 4(%sr2,%r20) @@ -848,6 +850,7 @@ cas2_action: cas2_end: /* Free lock */ + sync stw,ma %r20, 0(%sr2,%r20) /* Enable interrupts */ ssm PSW_SM_I, %r0 @@ -858,6 +861,7 @@ cas2_end: 22: /* Error occurred on load or store */ /* Free lock */ + sync stw %r20, 0(%sr2,%r20) ssm PSW_SM_I, %r0 ldo 1(%r0),%r28 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 2ea575cb3401..fb96206de317 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -243,6 +243,7 @@ endif cpu-as-$(CONFIG_4xx) += -Wa,-m405 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) cpu-as-$(CONFIG_E200) += -Wa,-me200 +cpu-as-$(CONFIG_E500) += -Wa,-me500 cpu-as-$(CONFIG_PPC_BOOK3S_64) += -Wa,-mpower4 cpu-as-$(CONFIG_PPC_E500MC) += $(call as-option,-Wa$(comma)-me500mc) diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 682b3e6a1e21..963abf8bf1c0 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -18,18 +18,11 @@ * a "bne-" instruction at the end, so an isync is enough as a acquire barrier * on the platform without lwsync. */ -#define __atomic_op_acquire(op, args...) \ -({ \ - typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory"); \ - __ret; \ -}) - -#define __atomic_op_release(op, args...) \ -({ \ - __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory"); \ - op##_relaxed(args); \ -}) +#define __atomic_acquire_fence() \ + __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory") + +#define __atomic_release_fence() \ + __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory") static __inline__ int atomic_read(const atomic_t *v) { @@ -129,8 +122,6 @@ ATOMIC_OPS(xor, xor) #undef ATOMIC_OP_RETURN_RELAXED #undef ATOMIC_OP -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - static __inline__ void atomic_inc(atomic_t *v) { int t; @@ -145,6 +136,7 @@ static __inline__ void atomic_inc(atomic_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic_inc atomic_inc static __inline__ int atomic_inc_return_relaxed(atomic_t *v) { @@ -163,16 +155,6 @@ static __inline__ int atomic_inc_return_relaxed(atomic_t *v) return t; } -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - static __inline__ void atomic_dec(atomic_t *v) { int t; @@ -187,6 +169,7 @@ static __inline__ void atomic_dec(atomic_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic_dec atomic_dec static __inline__ int atomic_dec_return_relaxed(atomic_t *v) { @@ -218,7 +201,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v) #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -226,13 +209,13 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int t; __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER -"1: lwarx %0,0,%1 # __atomic_add_unless\n\ +"1: lwarx %0,0,%1 # atomic_fetch_add_unless\n\ cmpw 0,%0,%3 \n\ beq 2f \n\ add %0,%2,%0 \n" @@ -248,6 +231,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) return t; } +#define atomic_fetch_add_unless atomic_fetch_add_unless /** * atomic_inc_not_zero - increment unless the number is zero @@ -280,9 +264,6 @@ static __inline__ int atomic_inc_not_zero(atomic_t *v) } #define atomic_inc_not_zero(v) atomic_inc_not_zero((v)) -#define atomic_sub_and_test(a, v) (atomic_sub_return((a), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return((v)) == 0) - /* * Atomically test *v and decrement if it is greater than 0. * The function returns the old value of *v minus 1, even if @@ -412,8 +393,6 @@ ATOMIC64_OPS(xor, xor) #undef ATOMIC64_OP_RETURN_RELAXED #undef ATOMIC64_OP -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - static __inline__ void atomic64_inc(atomic64_t *v) { long t; @@ -427,6 +406,7 @@ static __inline__ void atomic64_inc(atomic64_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic64_inc atomic64_inc static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v) { @@ -444,16 +424,6 @@ static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v) return t; } -/* - * atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - static __inline__ void atomic64_dec(atomic64_t *v) { long t; @@ -467,6 +437,7 @@ static __inline__ void atomic64_dec(atomic64_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic64_dec atomic64_dec static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v) { @@ -487,9 +458,6 @@ static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v) #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) - /* * Atomically test *v and decrement if it is greater than 0. * The function returns the old value of *v minus 1. @@ -513,6 +481,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) return t; } +#define atomic64_dec_if_positive atomic64_dec_if_positive #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic64_cmpxchg_relaxed(v, o, n) \ @@ -524,7 +493,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) #define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) /** - * atomic64_add_unless - add unless the number is a given value + * atomic64_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -532,13 +501,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) +static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u) { long t; __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER -"1: ldarx %0,0,%1 # __atomic_add_unless\n\ +"1: ldarx %0,0,%1 # atomic64_fetch_add_unless\n\ cmpd 0,%0,%3 \n\ beq 2f \n\ add %0,%2,%0 \n" @@ -551,8 +520,9 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) : "r" (&v->counter), "r" (a), "r" (u) : "cc", "memory"); - return t != u; + return t; } +#define atomic64_fetch_add_unless atomic64_fetch_add_unless /** * atomic_inc64_not_zero - increment unless the number is zero @@ -582,6 +552,7 @@ static __inline__ int atomic64_inc_not_zero(atomic64_t *v) return t1 != 0; } +#define atomic64_inc_not_zero(v) atomic64_inc_not_zero((v)) #endif /* __powerpc64__ */ diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 8e7b09703ca4..27d6e3c8fde9 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -52,6 +52,7 @@ struct arch_hw_breakpoint { #include <asm/reg.h> #include <asm/debug.h> +struct perf_event_attr; struct perf_event; struct pmu; struct perf_sample_data; @@ -60,8 +61,10 @@ struct perf_sample_data; extern int hw_breakpoint_slots(int type); extern int arch_bp_generic_fields(int type, int *gen_bp_type); -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); int arch_install_hw_breakpoint(struct perf_event *bp); diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 9f3be5c8a4a3..785c464b6588 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -88,7 +88,6 @@ struct prev_kprobe { struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_saved_msr; - struct pt_regs jprobe_saved_regs; struct prev_kprobe prev_kprobe; }; @@ -103,17 +102,6 @@ extern int kprobe_exceptions_notify(struct notifier_block *self, extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_handler(struct pt_regs *regs); extern int kprobe_post_handler(struct pt_regs *regs); -#ifdef CONFIG_KPROBES_ON_FTRACE -extern int __is_active_jprobe(unsigned long addr); -extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb); -#else -static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - return 0; -} -#endif #else static inline int kprobe_handler(struct pt_regs *regs) { return 0; } static inline int kprobe_post_handler(struct pt_regs *regs) { return 0; } diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 896efa559996..b2f89b621b15 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm( extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries); extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa); + unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa); + unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem); #endif @@ -143,24 +143,33 @@ static inline void mm_context_remove_copro(struct mm_struct *mm) { int c; - c = atomic_dec_if_positive(&mm->context.copros); - - /* Detect imbalance between add and remove */ - WARN_ON(c < 0); - /* - * Need to broadcast a global flush of the full mm before - * decrementing active_cpus count, as the next TLBI may be - * local and the nMMU and/or PSL need to be cleaned up. - * Should be rare enough so that it's acceptable. + * When removing the last copro, we need to broadcast a global + * flush of the full mm, as the next TLBI may be local and the + * nMMU and/or PSL need to be cleaned up. + * + * Both the 'copros' and 'active_cpus' counts are looked at in + * flush_all_mm() to determine the scope (local/global) of the + * TLBIs, so we need to flush first before decrementing + * 'copros'. If this API is used by several callers for the + * same context, it can lead to over-flushing. It's hopefully + * not common enough to be a problem. * * Skip on hash, as we don't know how to do the proper flush * for the time being. Invalidations will remain global if - * used on hash. + * used on hash. Note that we can't drop 'copros' either, as + * it could make some invalidations local with no flush + * in-between. */ - if (c == 0 && radix_enabled()) { + if (radix_enabled()) { flush_all_mm(mm); - dec_mm_active_cpus(mm); + + c = atomic_dec_if_positive(&mm->context.copros); + /* Detect imbalance between add and remove */ + WARN_ON(c < 0); + + if (c == 0) + dec_mm_active_cpus(mm); } } #else diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 80547dad37da..fec8a6773119 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -119,11 +119,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp) /* * Check for virtual address in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - - return is_kernel_addr(info->address); + return is_kernel_addr(hw->address); } int arch_bp_generic_fields(int type, int *gen_bp_type) @@ -141,30 +139,31 @@ int arch_bp_generic_fields(int type, int *gen_bp_type) /* * Validate the arch-specific HW Breakpoint register settings */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { int ret = -EINVAL, length_max; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); if (!bp) return ret; - info->type = HW_BRK_TYPE_TRANSLATE; - if (bp->attr.bp_type & HW_BREAKPOINT_R) - info->type |= HW_BRK_TYPE_READ; - if (bp->attr.bp_type & HW_BREAKPOINT_W) - info->type |= HW_BRK_TYPE_WRITE; - if (info->type == HW_BRK_TYPE_TRANSLATE) + hw->type = HW_BRK_TYPE_TRANSLATE; + if (attr->bp_type & HW_BREAKPOINT_R) + hw->type |= HW_BRK_TYPE_READ; + if (attr->bp_type & HW_BREAKPOINT_W) + hw->type |= HW_BRK_TYPE_WRITE; + if (hw->type == HW_BRK_TYPE_TRANSLATE) /* must set alteast read or write */ return ret; - if (!(bp->attr.exclude_user)) - info->type |= HW_BRK_TYPE_USER; - if (!(bp->attr.exclude_kernel)) - info->type |= HW_BRK_TYPE_KERNEL; - if (!(bp->attr.exclude_hv)) - info->type |= HW_BRK_TYPE_HYP; - info->address = bp->attr.bp_addr; - info->len = bp->attr.bp_len; + if (!attr->exclude_user) + hw->type |= HW_BRK_TYPE_USER; + if (!attr->exclude_kernel) + hw->type |= HW_BRK_TYPE_KERNEL; + if (!attr->exclude_hv) + hw->type |= HW_BRK_TYPE_HYP; + hw->address = attr->bp_addr; + hw->len = attr->bp_len; /* * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8) @@ -178,12 +177,12 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) if (cpu_has_feature(CPU_FTR_DAWR)) { length_max = 512 ; /* 64 doublewords */ /* DAWR region can't cross 512 boundary */ - if ((bp->attr.bp_addr >> 9) != - ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 9)) + if ((attr->bp_addr >> 9) != + ((attr->bp_addr + attr->bp_len - 1) >> 9)) return -EINVAL; } - if (info->len > - (length_max - (info->address & HW_BREAKPOINT_ALIGN))) + if (hw->len > + (length_max - (hw->address & HW_BREAKPOINT_ALIGN))) return -EINVAL; return 0; } diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index e734f6e45abc..689306118b48 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -144,7 +144,9 @@ power9_restore_additional_sprs: mtspr SPRN_MMCR1, r4 ld r3, STOP_MMCR2(r13) + ld r4, PACA_SPRG_VDSO(r13) mtspr SPRN_MMCR2, r3 + mtspr SPRN_SPRG3, r4 blr /* diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c index 7a1f99f1b47f..e4a49c051325 100644 --- a/arch/powerpc/kernel/kprobes-ftrace.c +++ b/arch/powerpc/kernel/kprobes-ftrace.c @@ -25,50 +25,6 @@ #include <linux/preempt.h> #include <linux/ftrace.h> -/* - * This is called from ftrace code after invoking registered handlers to - * disambiguate regs->nip changes done by jprobes and livepatch. We check if - * there is an active jprobe at the provided address (mcount location). - */ -int __is_active_jprobe(unsigned long addr) -{ - if (!preemptible()) { - struct kprobe *p = raw_cpu_read(current_kprobe); - return (p && (unsigned long)p->addr == addr) ? 1 : 0; - } - - return 0; -} - -static nokprobe_inline -int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb, unsigned long orig_nip) -{ - /* - * Emulate singlestep (and also recover regs->nip) - * as if there is a nop - */ - regs->nip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; - if (unlikely(p->post_handler)) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - p->post_handler(p, regs, 0); - } - __this_cpu_write(current_kprobe, NULL); - if (orig_nip) - regs->nip = orig_nip; - return 1; -} - -int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - if (kprobe_ftrace(p)) - return __skip_singlestep(p, regs, kcb, 0); - else - return 0; -} -NOKPROBE_SYMBOL(skip_singlestep); - /* Ftrace callback handler for kprobes */ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, struct ftrace_ops *ops, struct pt_regs *regs) @@ -76,18 +32,14 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, struct kprobe *p; struct kprobe_ctlblk *kcb; - preempt_disable(); - p = get_kprobe((kprobe_opcode_t *)nip); if (unlikely(!p) || kprobe_disabled(p)) - goto end; + return; kcb = get_kprobe_ctlblk(); if (kprobe_running()) { kprobes_inc_nmissed_count(p); } else { - unsigned long orig_nip = regs->nip; - /* * On powerpc, NIP is *before* this instruction for the * pre handler @@ -96,19 +48,23 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (!p->pre_handler || !p->pre_handler(p, regs)) - __skip_singlestep(p, regs, kcb, orig_nip); - else { + if (!p->pre_handler || !p->pre_handler(p, regs)) { /* - * If pre_handler returns !0, it sets regs->nip and - * resets current kprobe. In this case, we should not - * re-enable preemption. + * Emulate singlestep (and also recover regs->nip) + * as if there is a nop */ - return; + regs->nip += MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } } + /* + * If pre_handler returns !0, it changes regs->nip. We have to + * skip emulating post_handler. + */ + __this_cpu_write(current_kprobe, NULL); } -end: - preempt_enable_no_resched(); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index e4c5bf33970b..5c60bb0f927f 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -317,25 +317,17 @@ int kprobe_handler(struct pt_regs *regs) } prepare_singlestep(p, regs); return 1; - } else { - if (*addr != BREAKPOINT_INSTRUCTION) { - /* If trap variant, then it belongs not to us */ - kprobe_opcode_t cur_insn = *addr; - if (is_trap(cur_insn)) - goto no_kprobe; - /* The breakpoint instruction was removed by - * another cpu right after we hit, no further - * handling of this interrupt is appropriate - */ - ret = 1; + } else if (*addr != BREAKPOINT_INSTRUCTION) { + /* If trap variant, then it belongs not to us */ + kprobe_opcode_t cur_insn = *addr; + + if (is_trap(cur_insn)) goto no_kprobe; - } - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - if (!skip_singlestep(p, regs, kcb)) - goto ss_probe; - ret = 1; - } + /* The breakpoint instruction was removed by + * another cpu right after we hit, no further + * handling of this interrupt is appropriate + */ + ret = 1; } goto no_kprobe; } @@ -350,7 +342,7 @@ int kprobe_handler(struct pt_regs *regs) */ kprobe_opcode_t cur_insn = *addr; if (is_trap(cur_insn)) - goto no_kprobe; + goto no_kprobe; /* * The breakpoint instruction was removed right * after we hit it. Another cpu has removed @@ -366,11 +358,13 @@ int kprobe_handler(struct pt_regs *regs) kcb->kprobe_status = KPROBE_HIT_ACTIVE; set_current_kprobe(p, regs, kcb); - if (p->pre_handler && p->pre_handler(p, regs)) - /* handler has already set things up, so skip ss setup */ + if (p->pre_handler && p->pre_handler(p, regs)) { + /* handler changed execution path, so skip ss setup */ + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: if (p->ainsn.boostable >= 0) { ret = try_to_emulate(p, regs); @@ -611,60 +605,6 @@ unsigned long arch_deref_entry_point(void *entry) } NOKPROBE_SYMBOL(arch_deref_entry_point); -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); - - /* setup return addr to the jprobe handler routine */ - regs->nip = arch_deref_entry_point(jp->entry); -#ifdef PPC64_ELF_ABI_v2 - regs->gpr[12] = (unsigned long)jp->entry; -#elif defined(PPC64_ELF_ABI_v1) - regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc); -#endif - - /* - * jprobes use jprobe_return() which skips the normal return - * path of the function, and this messes up the accounting of the - * function graph tracer. - * - * Pause function graph tracing while performing the jprobe function. - */ - pause_graph_tracing(); - - return 1; -} -NOKPROBE_SYMBOL(setjmp_pre_handler); - -void __used jprobe_return(void) -{ - asm volatile("jprobe_return_trap:\n" - "trap\n" - ::: "memory"); -} -NOKPROBE_SYMBOL(jprobe_return); - -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (regs->nip != ppc_kallsyms_lookup_name("jprobe_return_trap")) { - pr_debug("longjmp_break_handler NIP (0x%lx) does not match jprobe_return_trap (0x%lx)\n", - regs->nip, ppc_kallsyms_lookup_name("jprobe_return_trap")); - return 0; - } - - memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); - /* It's OK to start function graph tracing again */ - unpause_graph_tracing(); - preempt_enable_no_resched(); - return 1; -} -NOKPROBE_SYMBOL(longjmp_break_handler); - static struct kprobe trampoline_p = { .addr = (kprobe_opcode_t *) &kretprobe_trampoline, .pre_handler = trampoline_probe_handler diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index fe9733ffffaa..471aac313b89 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -42,6 +42,8 @@ #include <asm/ppc-pci.h> #include <asm/eeh.h> +#include "../../../drivers/pci/pci.h" + /* hose_spinlock protects accesses to the the phb_bitmap. */ static DEFINE_SPINLOCK(hose_spinlock); LIST_HEAD(hose_list); @@ -1014,7 +1016,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus) /* Cardbus can call us to add new devices to a bus, so ignore * those who are already fully discovered */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pcibios_setup_device(dev); diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index 9a5b5a513604..32476a6e4e9c 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -104,39 +104,13 @@ ftrace_regs_call: bl ftrace_stub nop - /* Load the possibly modified NIP */ - ld r15, _NIP(r1) - + /* Load ctr with the possibly modified NIP */ + ld r3, _NIP(r1) + mtctr r3 #ifdef CONFIG_LIVEPATCH - cmpd r14, r15 /* has NIP been altered? */ + cmpd r14, r3 /* has NIP been altered? */ #endif -#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE) - /* NIP has not been altered, skip over further checks */ - beq 1f - - /* Check if there is an active jprobe on us */ - subi r3, r14, 4 - bl __is_active_jprobe - nop - - /* - * If r3 == 1, then this is a kprobe/jprobe. - * else, this is livepatched function. - * - * The conditional branch for livepatch_handler below will use the - * result of this comparison. For kprobe/jprobe, we just need to branch to - * the new NIP, not call livepatch_handler. The branch below is bne, so we - * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want - * CR0[EQ] = (r3 == 1). - */ - cmpdi r3, 1 -1: -#endif - - /* Load CTR with the possibly modified NIP */ - mtctr r15 - /* Restore gprs */ REST_GPR(0,r1) REST_10GPRS(2,r1) @@ -154,10 +128,7 @@ ftrace_regs_call: addi r1, r1, SWITCH_FRAME_SIZE #ifdef CONFIG_LIVEPATCH - /* - * Based on the cmpd or cmpdi above, if the NIP was altered and we're - * not on a kprobe/jprobe, then handle livepatch. - */ + /* Based on the cmpd above, if the NIP was altered handle livepatch */ bne- livepatch_handler #endif diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index d066e37551ec..8c456fa691a5 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, /* This only handles v2 IOMMU type, v1 is handled via ioctl() */ return H_TOO_HARD; - if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa))) + if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa))) return H_HARDWARE; if (mm_iommu_mapped_inc(mem)) diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 925fc316a104..5b298f5a1a14 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -279,7 +279,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (!mem) return H_TOO_HARD; - if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa))) + if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift, + &hpa))) return H_HARDWARE; pua = (void *) vmalloc_to_phys(pua); @@ -469,7 +470,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K); if (mem) - prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0; + prereg = mm_iommu_ua_to_hpa_rm(mem, ua, + IOMMU_PAGE_SHIFT_4K, &tces) == 0; } if (!prereg) { diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index de686b340f4a..ee4a8854985e 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -216,7 +216,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) wqp = kvm_arch_vcpu_wq(vcpu); if (swq_has_sleeper(wqp)) { - swake_up(wqp); + swake_up_one(wqp); ++vcpu->stat.halt_wakeup; } @@ -3188,7 +3188,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) } } - prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE); if (kvmppc_vcore_check_block(vc)) { finish_swait(&vc->wq, &wait); @@ -3311,7 +3311,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - swake_up(&vc->wq); + swake_up_one(&vc->wq); } } diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index abb43646927a..a4ca57612558 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -19,6 +19,7 @@ #include <linux/hugetlb.h> #include <linux/swap.h> #include <asm/mmu_context.h> +#include <asm/pte-walk.h> static DEFINE_MUTEX(mem_list_mutex); @@ -27,6 +28,7 @@ struct mm_iommu_table_group_mem_t { struct rcu_head rcu; unsigned long used; atomic64_t mapped; + unsigned int pageshift; u64 ua; /* userspace address */ u64 entries; /* number of entries in hpas[] */ u64 *hpas; /* vmalloc'ed */ @@ -125,6 +127,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, { struct mm_iommu_table_group_mem_t *mem; long i, j, ret = 0, locked_entries = 0; + unsigned int pageshift; + unsigned long flags; struct page *page = NULL; mutex_lock(&mem_list_mutex); @@ -159,6 +163,12 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, goto unlock_exit; } + /* + * For a starting point for a maximum page size calculation + * we use @ua and @entries natural alignment to allow IOMMU pages + * smaller than huge pages but still bigger than PAGE_SIZE. + */ + mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT)); mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0]))); if (!mem->hpas) { kfree(mem); @@ -199,6 +209,23 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, } } populate: + pageshift = PAGE_SHIFT; + if (PageCompound(page)) { + pte_t *pte; + struct page *head = compound_head(page); + unsigned int compshift = compound_order(head); + + local_irq_save(flags); /* disables as well */ + pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift); + local_irq_restore(flags); + + /* Double check it is still the same pinned page */ + if (pte && pte_page(*pte) == head && + pageshift == compshift) + pageshift = max_t(unsigned int, pageshift, + PAGE_SHIFT); + } + mem->pageshift = min(mem->pageshift, pageshift); mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; } @@ -349,7 +376,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, EXPORT_SYMBOL_GPL(mm_iommu_find); long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa) + unsigned long ua, unsigned int pageshift, unsigned long *hpa) { const long entry = (ua - mem->ua) >> PAGE_SHIFT; u64 *va = &mem->hpas[entry]; @@ -357,6 +384,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, if (entry >= mem->entries) return -EFAULT; + if (pageshift > mem->pageshift) + return -EFAULT; + *hpa = *va | (ua & ~PAGE_MASK); return 0; @@ -364,7 +394,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa); long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa) + unsigned long ua, unsigned int pageshift, unsigned long *hpa) { const long entry = (ua - mem->ua) >> PAGE_SHIFT; void *va = &mem->hpas[entry]; @@ -373,6 +403,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, if (entry >= mem->entries) return -EFAULT; + if (pageshift > mem->pageshift) + return -EFAULT; + pa = (void *) vmalloc_to_phys(va); if (!pa) return -EFAULT; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 380cbf9a40d9..c0a9bcd28356 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -286,6 +286,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u64 imm64; u8 *func; u32 true_cond; + u32 tmp_idx; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -637,11 +638,7 @@ emit_clear: case BPF_STX | BPF_XADD | BPF_W: /* Get EA into TMP_REG_1 */ PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); - /* error if EA is not word-aligned */ - PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_JMP(exit_addr); + tmp_idx = ctx->idx * 4; /* load value from memory into TMP_REG_2 */ PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); /* add value from src_reg into this */ @@ -649,32 +646,16 @@ emit_clear: /* store result back */ PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); /* we're done if this succeeded */ - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4)); - /* otherwise, let's try once more */ - PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - /* exit if the store was not successful */ - PPC_LI(b2p[BPF_REG_0], 0); - PPC_BCC(COND_NE, exit_addr); + PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* *(u64 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_DW: PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); - /* error if EA is not doubleword-aligned */ - PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4)); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_JMP(exit_addr); - PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4)); + tmp_idx = ctx->idx * 4; PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_BCC(COND_NE, exit_addr); + PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 3f66fcf8ad99..19d8ab49d1bd 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1469,7 +1469,7 @@ static int collect_events(struct perf_event *group, int max_count, } /* - * Add a event to the PMU. + * Add an event to the PMU. * If all events are not already frozen, then we disable and * re-enable the PMU in order to get hw_perf_enable to do the * actual work of reconfiguring the PMU. @@ -1548,7 +1548,7 @@ nocheck: } /* - * Remove a event from the PMU. + * Remove an event from the PMU. */ static void power_pmu_del(struct perf_event *event, int ef_flags) { @@ -1742,7 +1742,7 @@ static int power_pmu_commit_txn(struct pmu *pmu) /* * Return 1 if we might be able to put event on a limited PMC, * or 0 if not. - * A event can only go on a limited PMC if it counts something + * An event can only go on a limited PMC if it counts something * that a limited PMC can count, doesn't require interrupts, and * doesn't exclude any processor mode. */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 5bd0eb6681bc..70b2e1e0f23c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -46,6 +46,7 @@ #include "powernv.h" #include "pci.h" +#include "../../../../drivers/pci/pci.h" #define PNV_IODA1_M64_NUM 16 /* Number of M64 BARs */ #define PNV_IODA1_M64_SEGS 8 /* Segments per M64 BAR */ @@ -3138,7 +3139,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) struct pci_dn *pdn; int mul, total_vfs; - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; pdn = pci_get_pdn(pdev); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 139f0af6c3d9..8a4868a3964b 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -71,6 +71,7 @@ #include <asm/security_features.h> #include "pseries.h" +#include "../../../../drivers/pci/pci.h" int CMO_PrPSP = -1; int CMO_SecPSP = -1; @@ -664,7 +665,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev) const int *indexes; struct device_node *dn = pci_device_to_OF_node(pdev); - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; /*Firmware must support open sriov otherwise dont configure*/ indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 47166ad2a669..196978733e64 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2734,7 +2734,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr, { int nr, dotted; unsigned long first_adr; - unsigned long inst, last_inst = 0; + unsigned int inst, last_inst = 0; unsigned char val[4]; dotted = 0; @@ -2758,7 +2758,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr, dotted = 0; last_inst = inst; if (praddr) - printf(REG" %.8lx", adr, inst); + printf(REG" %.8x", adr, inst); printf("\t"); dump_func(inst, adr); printf("\n"); diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index 855115ace98c..c452359c9cb8 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -25,18 +25,11 @@ #define ATOMIC_INIT(i) { (i) } -#define __atomic_op_acquire(op, args...) \ -({ \ - typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory"); \ - __ret; \ -}) - -#define __atomic_op_release(op, args...) \ -({ \ - __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); \ - op##_relaxed(args); \ -}) +#define __atomic_acquire_fence() \ + __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory") + +#define __atomic_release_fence() \ + __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); static __always_inline int atomic_read(const atomic_t *v) { @@ -209,130 +202,8 @@ ATOMIC_OPS(xor, xor, i) #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN -/* - * The extra atomic operations that are constructed from one of the core - * AMO-based operations above (aside from sub, which is easier to fit above). - * These are required to perform a full barrier, but they're OK this way - * because atomic_*_return is also required to perform a full barrier. - * - */ -#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix) \ -static __always_inline \ -bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_##func_op##_return(i, v) comp_op I; \ -} - -#ifdef CONFIG_GENERIC_ATOMIC64 -#define ATOMIC_OPS(op, func_op, comp_op, I) \ - ATOMIC_OP(op, func_op, comp_op, I, int, ) -#else -#define ATOMIC_OPS(op, func_op, comp_op, I) \ - ATOMIC_OP(op, func_op, comp_op, I, int, ) \ - ATOMIC_OP(op, func_op, comp_op, I, long, 64) -#endif - -ATOMIC_OPS(add_and_test, add, ==, 0) -ATOMIC_OPS(sub_and_test, sub, ==, 0) -ATOMIC_OPS(add_negative, add, <, 0) - -#undef ATOMIC_OP -#undef ATOMIC_OPS - -#define ATOMIC_OP(op, func_op, I, c_type, prefix) \ -static __always_inline \ -void atomic##prefix##_##op(atomic##prefix##_t *v) \ -{ \ - atomic##prefix##_##func_op(I, v); \ -} - -#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix) \ -static __always_inline \ -c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##func_op##_relaxed(I, v); \ -} \ -static __always_inline \ -c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##func_op(I, v); \ -} - -#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix) \ -static __always_inline \ -c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##op##_relaxed(v) c_op I; \ -} \ -static __always_inline \ -c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##op(v) c_op I; \ -} - -#ifdef CONFIG_GENERIC_ATOMIC64 -#define ATOMIC_OPS(op, asm_op, c_op, I) \ - ATOMIC_OP( op, asm_op, I, int, ) \ - ATOMIC_FETCH_OP( op, asm_op, I, int, ) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) -#else -#define ATOMIC_OPS(op, asm_op, c_op, I) \ - ATOMIC_OP( op, asm_op, I, int, ) \ - ATOMIC_FETCH_OP( op, asm_op, I, int, ) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) \ - ATOMIC_OP( op, asm_op, I, long, 64) \ - ATOMIC_FETCH_OP( op, asm_op, I, long, 64) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64) -#endif - -ATOMIC_OPS(inc, add, +, 1) -ATOMIC_OPS(dec, add, +, -1) - -#define atomic_inc_return_relaxed atomic_inc_return_relaxed -#define atomic_dec_return_relaxed atomic_dec_return_relaxed -#define atomic_inc_return atomic_inc_return -#define atomic_dec_return atomic_dec_return - -#define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed -#define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed -#define atomic_fetch_inc atomic_fetch_inc -#define atomic_fetch_dec atomic_fetch_dec - -#ifndef CONFIG_GENERIC_ATOMIC64 -#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed -#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed -#define atomic64_inc_return atomic64_inc_return -#define atomic64_dec_return atomic64_dec_return - -#define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed -#define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed -#define atomic64_fetch_inc atomic64_fetch_inc -#define atomic64_fetch_dec atomic64_fetch_dec -#endif - -#undef ATOMIC_OPS -#undef ATOMIC_OP -#undef ATOMIC_FETCH_OP -#undef ATOMIC_OP_RETURN - -#define ATOMIC_OP(op, func_op, comp_op, I, prefix) \ -static __always_inline \ -bool atomic##prefix##_##op(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_##func_op##_return(v) comp_op I; \ -} - -ATOMIC_OP(inc_and_test, inc, ==, 0, ) -ATOMIC_OP(dec_and_test, dec, ==, 0, ) -#ifndef CONFIG_GENERIC_ATOMIC64 -ATOMIC_OP(inc_and_test, inc, ==, 0, 64) -ATOMIC_OP(dec_and_test, dec, ==, 0, 64) -#endif - -#undef ATOMIC_OP - /* This is required to provide a full barrier on success. */ -static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) +static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int prev, rc; @@ -349,9 +220,10 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) : "memory"); return prev; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #ifndef CONFIG_GENERIC_ATOMIC64 -static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u) +static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u) { long prev, rc; @@ -368,27 +240,7 @@ static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u) : "memory"); return prev; } - -static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - return __atomic64_add_unless(v, a, u) != u; -} -#endif - -/* - * The extra atomic operations that are constructed from one of the core - * LR/SC-based operations above. - */ -static __always_inline int atomic_inc_not_zero(atomic_t *v) -{ - return __atomic_add_unless(v, 1, 0); -} - -#ifndef CONFIG_GENERIC_ATOMIC64 -static __always_inline long atomic64_inc_not_zero(atomic64_t *v) -{ - return atomic64_add_unless(v, 1, 0); -} +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e44bb2b2873e..4fe5b2affa23 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -106,7 +106,6 @@ config S390 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANTS_DYNAMIC_TASK_STRUCT - select ARCH_WANTS_UBSAN_NO_NULL select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS2 @@ -140,7 +139,7 @@ config S390 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if FUTEX - select HAVE_GCC_PLUGINS + select HAVE_GCC_PLUGINS if BROKEN select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 4b55532f15c4..fd20ab5d4cf7 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -55,17 +55,9 @@ static inline void atomic_add(int i, atomic_t *v) __atomic_add(i, &v->counter); } -#define atomic_add_negative(_i, _v) (atomic_add_return(_i, _v) < 0) -#define atomic_inc(_v) atomic_add(1, _v) -#define atomic_inc_return(_v) atomic_add_return(1, _v) -#define atomic_inc_and_test(_v) (atomic_add_return(1, _v) == 0) #define atomic_sub(_i, _v) atomic_add(-(int)(_i), _v) #define atomic_sub_return(_i, _v) atomic_add_return(-(int)(_i), _v) #define atomic_fetch_sub(_i, _v) atomic_fetch_add(-(int)(_i), _v) -#define atomic_sub_and_test(_i, _v) (atomic_sub_return(_i, _v) == 0) -#define atomic_dec(_v) atomic_sub(1, _v) -#define atomic_dec_return(_v) atomic_sub_return(1, _v) -#define atomic_dec_and_test(_v) (atomic_sub_return(1, _v) == 0) #define ATOMIC_OPS(op) \ static inline void atomic_##op(int i, atomic_t *v) \ @@ -90,21 +82,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return __atomic_cmpxchg(&v->counter, old, new); } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == u)) - break; - old = atomic_cmpxchg(v, c, c + a); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define ATOMIC64_INIT(i) { (i) } static inline long atomic64_read(const atomic64_t *v) @@ -168,50 +145,8 @@ ATOMIC64_OPS(xor) #undef ATOMIC64_OPS -static inline int atomic64_add_unless(atomic64_t *v, long i, long u) -{ - long c, old; - - c = atomic64_read(v); - for (;;) { - if (unlikely(c == u)) - break; - old = atomic64_cmpxchg(v, c, c + i); - if (likely(old == c)) - break; - c = old; - } - return c != u; -} - -static inline long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - -#define atomic64_add_negative(_i, _v) (atomic64_add_return(_i, _v) < 0) -#define atomic64_inc(_v) atomic64_add(1, _v) -#define atomic64_inc_return(_v) atomic64_add_return(1, _v) -#define atomic64_inc_and_test(_v) (atomic64_add_return(1, _v) == 0) #define atomic64_sub_return(_i, _v) atomic64_add_return(-(long)(_i), _v) #define atomic64_fetch_sub(_i, _v) atomic64_fetch_add(-(long)(_i), _v) #define atomic64_sub(_i, _v) atomic64_add(-(long)(_i), _v) -#define atomic64_sub_and_test(_i, _v) (atomic64_sub_return(_i, _v) == 0) -#define atomic64_dec(_v) atomic64_sub(1, _v) -#define atomic64_dec_return(_v) atomic64_sub_return(1, _v) -#define atomic64_dec_and_test(_v) (atomic64_sub_return(1, _v) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) #endif /* __ARCH_S390_ATOMIC__ */ diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index 13de80cf741c..b106aa29bf55 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -68,8 +68,6 @@ struct kprobe_ctlblk { unsigned long kprobe_saved_imask; unsigned long kprobe_saved_ctl[3]; struct prev_kprobe prev_kprobe; - struct pt_regs jprobe_saved_regs; - kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; }; void arch_remove_kprobe(struct kprobe *p); diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 60f60afa645c..7c0a095e9c5f 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -321,38 +321,20 @@ static int kprobe_handler(struct pt_regs *regs) * If we have no pre-handler or it returned 0, we * continue with single stepping. If we have a * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry - * for jprobe processing, so get out doing nothing - * more here. + * for changing execution path, so get out doing + * nothing more here. */ push_kprobe(kcb, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) + if (p->pre_handler && p->pre_handler(p, regs)) { + pop_kprobe(kcb); + preempt_enable_no_resched(); return 1; + } kcb->kprobe_status = KPROBE_HIT_SS; } enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn); return 1; - } else if (kprobe_running()) { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - /* - * Continuation after the jprobe completed and - * caused the jprobe_return trap. The jprobe - * break_handler "returns" to the original - * function that still has the kprobe breakpoint - * installed. We continue with single stepping. - */ - kcb->kprobe_status = KPROBE_HIT_SS; - enable_singlestep(kcb, regs, - (unsigned long) p->ainsn.insn); - return 1; - } /* else: - * No kprobe at this address and the current kprobe - * has no break handler (no jprobe!). The kernel just - * exploded, let the standard trap handler pick up the - * pieces. - */ } /* else: * No kprobe at this address and no active kprobe. The trap has * not been caused by a kprobe breakpoint. The race of breakpoint @@ -452,9 +434,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) regs->psw.addr = orig_ret_address; - pop_kprobe(get_kprobe_ctlblk()); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); @@ -661,60 +641,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, } NOKPROBE_SYMBOL(kprobe_exceptions_notify); -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long stack; - - memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); - - /* setup return addr to the jprobe handler routine */ - regs->psw.addr = (unsigned long) jp->entry; - regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); - - /* r15 is the stack pointer */ - stack = (unsigned long) regs->gprs[15]; - - memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack)); - - /* - * jprobes use jprobe_return() which skips the normal return - * path of the function, and this messes up the accounting of the - * function graph tracer to get messed up. - * - * Pause function graph tracing while performing the jprobe function. - */ - pause_graph_tracing(); - return 1; -} -NOKPROBE_SYMBOL(setjmp_pre_handler); - -void jprobe_return(void) -{ - asm volatile(".word 0x0002"); -} -NOKPROBE_SYMBOL(jprobe_return); - -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long stack; - - /* It's OK to start function graph tracing again */ - unpause_graph_tracing(); - - stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15]; - - /* Put the regs back */ - memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); - /* put the stack back */ - memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack)); - preempt_enable_no_resched(); - return 1; -} -NOKPROBE_SYMBOL(longjmp_break_handler); - static struct kprobe trampoline = { .addr = (kprobe_opcode_t *) &kretprobe_trampoline, .pre_handler = trampoline_probe_handler diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index daa09f89ca2d..fcb55b02990e 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1145,7 +1145,7 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) * yield-candidate. */ vcpu->preempted = true; - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); vcpu->stat.halt_wakeup++; } /* diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h index 0fd0099f43cc..f37b95a80232 100644 --- a/arch/sh/include/asm/atomic.h +++ b/arch/sh/include/asm/atomic.h @@ -32,44 +32,9 @@ #include <asm/atomic-irq.h> #endif -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) - -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) - #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - - return c; -} - #endif /* CONFIG_CPU_J2 */ #endif /* __ASM_SH_ATOMIC_H */ diff --git a/arch/sh/include/asm/cmpxchg-xchg.h b/arch/sh/include/asm/cmpxchg-xchg.h index 1e881f5db659..593a9704782b 100644 --- a/arch/sh/include/asm/cmpxchg-xchg.h +++ b/arch/sh/include/asm/cmpxchg-xchg.h @@ -8,7 +8,8 @@ * This work is licensed under the terms of the GNU GPL, version 2. See the * file "COPYING" in the main directory of this archive for more details. */ -#include <linux/bitops.h> +#include <linux/bits.h> +#include <linux/compiler.h> #include <asm/byteorder.h> /* diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h index 7431c172c0cb..199d17b765f2 100644 --- a/arch/sh/include/asm/hw_breakpoint.h +++ b/arch/sh/include/asm/hw_breakpoint.h @@ -10,7 +10,6 @@ #include <linux/types.h> struct arch_hw_breakpoint { - char *name; /* Contains name of the symbol to set bkpt */ unsigned long address; u16 len; u16 type; @@ -41,6 +40,7 @@ struct sh_ubc { struct clk *clk; /* optional interface clock / MSTP bit */ }; +struct perf_event_attr; struct perf_event; struct task_struct; struct pmu; @@ -54,8 +54,10 @@ static inline int hw_breakpoint_slots(int type) } /* arch/sh/kernel/hw_breakpoint.c */ -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h index 85d8bcaa8493..6171682f7798 100644 --- a/arch/sh/include/asm/kprobes.h +++ b/arch/sh/include/asm/kprobes.h @@ -27,7 +27,6 @@ struct kprobe; void arch_remove_kprobe(struct kprobe *); void kretprobe_trampoline(void); -void jprobe_return_end(void); /* Architecture specific copy of original instruction*/ struct arch_specific_insn { @@ -43,9 +42,6 @@ struct prev_kprobe { /* per-cpu kprobe control block */ struct kprobe_ctlblk { unsigned long kprobe_status; - unsigned long jprobe_saved_r15; - struct pt_regs jprobe_saved_regs; - kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c index 8648ed05ccf0..d9ff3b42da7c 100644 --- a/arch/sh/kernel/hw_breakpoint.c +++ b/arch/sh/kernel/hw_breakpoint.c @@ -124,14 +124,13 @@ static int get_hbp_len(u16 hbp_len) /* * Check for virtual address in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = get_hbp_len(info->len); + va = hw->address; + len = get_hbp_len(hw->len); return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -174,40 +173,40 @@ int arch_bp_generic_fields(int sh_len, int sh_type, return 0; } -static int arch_build_bp_info(struct perf_event *bp) +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - - info->address = bp->attr.bp_addr; + hw->address = attr->bp_addr; /* Len */ - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->len = SH_BREAKPOINT_LEN_1; + hw->len = SH_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->len = SH_BREAKPOINT_LEN_2; + hw->len = SH_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_4: - info->len = SH_BREAKPOINT_LEN_4; + hw->len = SH_BREAKPOINT_LEN_4; break; case HW_BREAKPOINT_LEN_8: - info->len = SH_BREAKPOINT_LEN_8; + hw->len = SH_BREAKPOINT_LEN_8; break; default: return -EINVAL; } /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_R: - info->type = SH_BREAKPOINT_READ; + hw->type = SH_BREAKPOINT_READ; break; case HW_BREAKPOINT_W: - info->type = SH_BREAKPOINT_WRITE; + hw->type = SH_BREAKPOINT_WRITE; break; case HW_BREAKPOINT_W | HW_BREAKPOINT_R: - info->type = SH_BREAKPOINT_RW; + hw->type = SH_BREAKPOINT_RW; break; default: return -EINVAL; @@ -219,19 +218,20 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); unsigned int align; int ret; - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; ret = -EINVAL; - switch (info->len) { + switch (hw->len) { case SH_BREAKPOINT_LEN_1: align = 0; break; @@ -249,17 +249,10 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) } /* - * For kernel-addresses, either the address or symbol name can be - * specified. - */ - if (info->name) - info->address = (unsigned long)kallsyms_lookup_name(info->name); - - /* * Check that the low-order bits of the address are appropriate * for the alignment implied by len. */ - if (info->address & align) + if (hw->address & align) return -EINVAL; return 0; @@ -346,7 +339,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) perf_bp_event(bp, args->regs); /* Deliver the signal to userspace */ - if (!arch_check_bp_in_kernelspace(bp)) { + if (!arch_check_bp_in_kernelspace(&bp->hw.info)) { force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)NULL, current); } diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index 52a5e11247d1..241e903dd3ee 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -248,11 +248,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_REENTER; return 1; - } else { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - goto ss_probe; - } } goto no_kprobe; } @@ -277,11 +272,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) set_current_kprobe(p, regs, kcb); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) + if (p->pre_handler && p->pre_handler(p, regs)) { /* handler has already set things up, so skip ss setup */ + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; return 1; @@ -358,8 +355,6 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) regs->pc = orig_ret_address; kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); @@ -508,14 +503,8 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, if (post_kprobe_handler(args->regs)) ret = NOTIFY_STOP; } else { - if (kprobe_handler(args->regs)) { + if (kprobe_handler(args->regs)) ret = NOTIFY_STOP; - } else { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && - p->break_handler(p, args->regs)) - ret = NOTIFY_STOP; - } } } } @@ -523,57 +512,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - unsigned long addr; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - kcb->jprobe_saved_r15 = regs->regs[15]; - addr = kcb->jprobe_saved_r15; - - /* - * TBD: As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. - */ - memcpy(kcb->jprobes_stack, (kprobe_opcode_t *) addr, - MIN_STACK_SIZE(addr)); - - regs->pc = (unsigned long)(jp->entry); - - return 1; -} - -void __kprobes jprobe_return(void) -{ - asm volatile ("trapa #0x3a\n\t" "jprobe_return_end:\n\t" "nop\n\t"); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long stack_addr = kcb->jprobe_saved_r15; - u8 *addr = (u8 *)regs->pc; - - if ((addr >= (u8 *)jprobe_return) && - (addr <= (u8 *)jprobe_return_end)) { - *regs = kcb->jprobe_saved_regs; - - memcpy((kprobe_opcode_t *)stack_addr, kcb->jprobes_stack, - MIN_STACK_SIZE(stack_addr)); - - kcb->kprobe_status = KPROBE_HIT_SS; - preempt_enable_no_resched(); - return 1; - } - - return 0; -} - static struct kprobe trampoline_p = { .addr = (kprobe_opcode_t *)&kretprobe_trampoline, .pre_handler = trampoline_probe_handler diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index ac67828da201..410b263ef5c8 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -13,6 +13,7 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += module.h +generic-y += msi.h generic-y += preempt.h generic-y += rwsem.h generic-y += serial.h diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index d13ce517f4b9..94c930f0bc62 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -27,17 +27,17 @@ int atomic_fetch_or(int, atomic_t *); int atomic_fetch_xor(int, atomic_t *); int atomic_cmpxchg(atomic_t *, int, int); int atomic_xchg(atomic_t *, int); -int __atomic_add_unless(atomic_t *, int, int); +int atomic_fetch_add_unless(atomic_t *, int, int); void atomic_set(atomic_t *, int); +#define atomic_fetch_add_unless atomic_fetch_add_unless + #define atomic_set_release(v, i) atomic_set((v), (i)) #define atomic_read(v) READ_ONCE((v)->counter) #define atomic_add(i, v) ((void)atomic_add_return( (int)(i), (v))) #define atomic_sub(i, v) ((void)atomic_add_return(-(int)(i), (v))) -#define atomic_inc(v) ((void)atomic_add_return( 1, (v))) -#define atomic_dec(v) ((void)atomic_add_return( -1, (v))) #define atomic_and(i, v) ((void)atomic_fetch_and((i), (v))) #define atomic_or(i, v) ((void)atomic_fetch_or((i), (v))) @@ -46,22 +46,4 @@ void atomic_set(atomic_t *, int); #define atomic_sub_return(i, v) (atomic_add_return(-(int)(i), (v))) #define atomic_fetch_sub(i, v) (atomic_fetch_add (-(int)(i), (v))) -#define atomic_inc_return(v) (atomic_add_return( 1, (v))) -#define atomic_dec_return(v) (atomic_add_return( -1, (v))) - -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - #endif /* !(__ARCH_SPARC_ATOMIC__) */ diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index 28db058d471b..6963482c81d8 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -50,38 +50,6 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_dec_return(v) atomic_sub_return(1, v) -#define atomic64_dec_return(v) atomic64_sub_return(1, v) - -#define atomic_inc_return(v) atomic_add_return(1, v) -#define atomic64_inc_return(v) atomic64_add_return(1, v) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) -#define atomic64_sub_and_test(i, v) (atomic64_sub_return(i, v) == 0) - -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, v) == 0) - -#define atomic_inc(v) atomic_add(1, v) -#define atomic64_inc(v) atomic64_add(1, v) - -#define atomic_dec(v) atomic_sub(1, v) -#define atomic64_dec(v) atomic64_sub(1, v) - -#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0) -#define atomic64_add_negative(i, v) (atomic64_add_return(i, v) < 0) - #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) static inline int atomic_xchg(atomic_t *v, int new) @@ -89,42 +57,11 @@ static inline int atomic_xchg(atomic_t *v, int new) return xchg(&v->counter, new); } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define atomic64_cmpxchg(v, o, n) \ ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static inline long atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - long atomic64_dec_if_positive(atomic64_t *v); +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif /* !(__ARCH_SPARC64_ATOMIC__) */ diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h index 3704490b4488..bfcaa6326c20 100644 --- a/arch/sparc/include/asm/kprobes.h +++ b/arch/sparc/include/asm/kprobes.h @@ -44,7 +44,6 @@ struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_orig_tnpc; unsigned long kprobe_orig_tstate_pil; - struct pt_regs jprobe_saved_regs; struct prev_kprobe prev_kprobe; }; diff --git a/arch/sparc/include/asm/msi.h b/arch/sparc/include/asm/msi.h deleted file mode 100644 index 3c17c1074431..000000000000 --- a/arch/sparc/include/asm/msi.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * msi.h: Defines specific to the MBus - Sbus - Interface. - * - * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) - * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be) - */ - -#ifndef _SPARC_MSI_H -#define _SPARC_MSI_H - -/* - * Locations of MSI Registers. - */ -#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */ - -/* - * Useful bits in the MSI Registers. - */ -#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */ - - -static inline void msi_set_sync(void) -{ - __asm__ __volatile__ ("lda [%0] %1, %%g3\n\t" - "andn %%g3, %2, %%g3\n\t" - "sta %%g3, [%0] %1\n\t" : : - "r" (MSI_MBUS_ARBEN), - "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3"); -} - -#endif /* !(_SPARC_MSI_H) */ diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c index ab4ba4347941..dfbca2470536 100644 --- a/arch/sparc/kernel/kprobes.c +++ b/arch/sparc/kernel/kprobes.c @@ -147,18 +147,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) kcb->kprobe_status = KPROBE_REENTER; prepare_singlestep(p, regs, kcb); return 1; - } else { - if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) { + } else if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) { /* The breakpoint instruction was removed by * another cpu right after we hit, no further * handling of this interrupt is appropriate */ - ret = 1; - goto no_kprobe; - } - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) - goto ss_probe; + ret = 1; } goto no_kprobe; } @@ -181,10 +175,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) set_current_kprobe(p, regs, kcb); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) + if (p->pre_handler && p->pre_handler(p, regs)) { + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: prepare_singlestep(p, regs, kcb); kcb->kprobe_status = KPROBE_HIT_SS; return 1; @@ -441,53 +437,6 @@ out: exception_exit(prev_state); } -/* Jprobes support. */ -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - memcpy(&(kcb->jprobe_saved_regs), regs, sizeof(*regs)); - - regs->tpc = (unsigned long) jp->entry; - regs->tnpc = ((unsigned long) jp->entry) + 0x4UL; - regs->tstate |= TSTATE_PIL; - - return 1; -} - -void __kprobes jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - register unsigned long orig_fp asm("g1"); - - orig_fp = kcb->jprobe_saved_regs.u_regs[UREG_FP]; - __asm__ __volatile__("\n" -"1: cmp %%sp, %0\n\t" - "blu,a,pt %%xcc, 1b\n\t" - " restore\n\t" - ".globl jprobe_return_trap_instruction\n" -"jprobe_return_trap_instruction:\n\t" - "ta 0x70" - : /* no outputs */ - : "r" (orig_fp)); -} - -extern void jprobe_return_trap_instruction(void); - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - u32 *addr = (u32 *) regs->tpc; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (addr == (u32 *) jprobe_return_trap_instruction) { - memcpy(regs, &(kcb->jprobe_saved_regs), sizeof(*regs)); - preempt_enable_no_resched(); - return 1; - } - return 0; -} - /* The value stored in the return address register is actually 2 * instructions before where the callee will return to. * Sequences usually look something like this @@ -562,9 +511,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, regs->tpc = orig_ret_address; regs->tnpc = orig_ret_address + 4; - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 2ef8cfa9677e..f0eba72aa1ad 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -814,7 +814,7 @@ static void __init get_tick_patch(void) } } -static void init_tick_ops(struct sparc64_tick_ops *ops) +static void __init init_tick_ops(struct sparc64_tick_ops *ops) { unsigned long freq, quotient, tick; diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index 465a901a0ada..281fa634bb1a 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -95,7 +95,7 @@ int atomic_cmpxchg(atomic_t *v, int old, int new) } EXPORT_SYMBOL(atomic_cmpxchg); -int __atomic_add_unless(atomic_t *v, int a, int u) +int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int ret; unsigned long flags; @@ -107,7 +107,7 @@ int __atomic_add_unless(atomic_t *v, int a, int u) spin_unlock_irqrestore(ATOMIC_HASH(v), flags); return ret; } -EXPORT_SYMBOL(__atomic_add_unless); +EXPORT_SYMBOL(atomic_fetch_add_unless); /* Atomic operations are already serializing */ void atomic_set(atomic_t *v, int i) diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index 1d70c3f6d986..be9cb0065179 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -37,7 +37,6 @@ #include <asm/mbus.h> #include <asm/page.h> #include <asm/asi.h> -#include <asm/msi.h> #include <asm/smp.h> #include <asm/io.h> @@ -116,6 +115,25 @@ static inline void srmmu_ctxd_set(ctxd_t *ctxp, pgd_t *pgdp) set_pte((pte_t *)ctxp, pte); } +/* + * Locations of MSI Registers. + */ +#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */ + +/* + * Useful bits in the MSI Registers. + */ +#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */ + +static void msi_set_sync(void) +{ + __asm__ __volatile__ ("lda [%0] %1, %%g3\n\t" + "andn %%g3, %2, %%g3\n\t" + "sta %%g3, [%0] %1\n\t" : : + "r" (MSI_MBUS_ARBEN), + "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3"); +} + void pmd_set(pmd_t *pmdp, pte_t *ptep) { unsigned long ptp; /* Physical address, shifted right by 4 */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f1dbb4ee19d7..6d4774f203d0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -63,7 +63,7 @@ config X86 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 - select ARCH_HAS_UACCESS_MCSAFE if X86_64 + select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE select ARCH_HAS_SET_MEMORY select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX @@ -180,7 +180,7 @@ config X86 select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RELIABLE_STACKTRACE if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION + select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR select HAVE_STACK_VALIDATION if X86_64 select HAVE_RSEQ diff --git a/arch/x86/Makefile b/arch/x86/Makefile index a08e82856563..7e3c07d6ad42 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -80,11 +80,6 @@ ifeq ($(CONFIG_X86_32),y) # alignment instructions. KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4)) - # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use - # a lot more stack due to the lack of sharing of stacklots: - KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0400, \ - $(call cc-option,-fno-unit-at-a-time)) - # CPU-specific tuning. Anything which can be shared with UML should go here. include arch/x86/Makefile_32.cpu KBUILD_CFLAGS += $(cflags-y) diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h index 0d41d68131cc..2e1382486e91 100644 --- a/arch/x86/boot/bitops.h +++ b/arch/x86/boot/bitops.h @@ -17,6 +17,7 @@ #define _LINUX_BITOPS_H /* Inhibit inclusion of <linux/bitops.h> */ #include <linux/types.h> +#include <asm/asm.h> static inline bool constant_test_bit(int nr, const void *addr) { @@ -28,7 +29,7 @@ static inline bool variable_test_bit(int nr, const void *addr) bool v; const u32 *p = (const u32 *)addr; - asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr)); + asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr)); return v; } diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index fa42f895fdde..169c2feda14a 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -106,9 +106,13 @@ define cmd_check_data_rel done endef +# We need to run two commands under "if_changed", so merge them into a +# single invocation. +quiet_cmd_check-and-link-vmlinux = LD $@ + cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld) + $(obj)/vmlinux: $(vmlinux-objs-y) FORCE - $(call if_changed,check_data_rel) - $(call if_changed,ld) + $(call if_changed,check-and-link-vmlinux) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index e98522ea6f09..1458b1700fc7 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -34,74 +34,13 @@ static void setup_boot_services##bits(struct efi_config *c) \ \ table = (typeof(table))sys_table; \ \ - c->runtime_services = table->runtime; \ - c->boot_services = table->boottime; \ - c->text_output = table->con_out; \ + c->runtime_services = table->runtime; \ + c->boot_services = table->boottime; \ + c->text_output = table->con_out; \ } BOOT_SERVICES(32); BOOT_SERVICES(64); -static inline efi_status_t __open_volume32(void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_32_t *image = __image; - efi_file_handle_32_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - unsigned long func; - - status = efi_call_early(handle_protocol, handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to handle fs_proto\n"); - return status; - } - - func = (unsigned long)io->open_volume; - status = efi_early->call(func, io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to open volume\n"); - - *__fh = fh; - return status; -} - -static inline efi_status_t __open_volume64(void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_64_t *image = __image; - efi_file_handle_64_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - unsigned long func; - - status = efi_call_early(handle_protocol, handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to handle fs_proto\n"); - return status; - } - - func = (unsigned long)io->open_volume; - status = efi_early->call(func, io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to open volume\n"); - - *__fh = fh; - return status; -} - -efi_status_t -efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) -{ - if (efi_early->is64) - return __open_volume64(__image, __fh); - - return __open_volume32(__image, __fh); -} - void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) { efi_call_proto(efi_simple_text_output_protocol, output_string, @@ -109,7 +48,7 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) } static efi_status_t -__setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) +preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) { struct pci_setup_rom *rom = NULL; efi_status_t status; @@ -134,16 +73,16 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for rom\n"); + efi_printk(sys_table, "Failed to allocate memory for 'rom'\n"); return status; } memset(rom, 0, sizeof(*rom)); - rom->data.type = SETUP_PCI; - rom->data.len = size - sizeof(struct setup_data); - rom->data.next = 0; - rom->pcilen = pci->romsize; + rom->data.type = SETUP_PCI; + rom->data.len = size - sizeof(struct setup_data); + rom->data.next = 0; + rom->pcilen = pci->romsize; *__rom = rom; status = efi_call_proto(efi_pci_io_protocol, pci.read, pci, @@ -179,96 +118,6 @@ free_struct: return status; } -static void -setup_efi_pci32(struct boot_params *params, void **pci_handle, - unsigned long size) -{ - efi_pci_io_protocol_t *pci = NULL; - efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; - u32 *handles = (u32 *)(unsigned long)pci_handle; - efi_status_t status; - unsigned long nr_pci; - struct setup_data *data; - int i; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - nr_pci = size / sizeof(u32); - for (i = 0; i < nr_pci; i++) { - struct pci_setup_rom *rom = NULL; - u32 h = handles[i]; - - status = efi_call_early(handle_protocol, h, - &pci_proto, (void **)&pci); - - if (status != EFI_SUCCESS) - continue; - - if (!pci) - continue; - - status = __setup_efi_pci(pci, &rom); - if (status != EFI_SUCCESS) - continue; - - if (data) - data->next = (unsigned long)rom; - else - params->hdr.setup_data = (unsigned long)rom; - - data = (struct setup_data *)rom; - - } -} - -static void -setup_efi_pci64(struct boot_params *params, void **pci_handle, - unsigned long size) -{ - efi_pci_io_protocol_t *pci = NULL; - efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; - u64 *handles = (u64 *)(unsigned long)pci_handle; - efi_status_t status; - unsigned long nr_pci; - struct setup_data *data; - int i; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - nr_pci = size / sizeof(u64); - for (i = 0; i < nr_pci; i++) { - struct pci_setup_rom *rom = NULL; - u64 h = handles[i]; - - status = efi_call_early(handle_protocol, h, - &pci_proto, (void **)&pci); - - if (status != EFI_SUCCESS) - continue; - - if (!pci) - continue; - - status = __setup_efi_pci(pci, &rom); - if (status != EFI_SUCCESS) - continue; - - if (data) - data->next = (unsigned long)rom; - else - params->hdr.setup_data = (unsigned long)rom; - - data = (struct setup_data *)rom; - - } -} - /* * There's no way to return an informative status from this function, * because any analysis (and printing of error messages) needs to be @@ -284,6 +133,9 @@ static void setup_efi_pci(struct boot_params *params) void **pci_handle = NULL; efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; unsigned long size = 0; + unsigned long nr_pci; + struct setup_data *data; + int i; status = efi_call_early(locate_handle, EFI_LOCATE_BY_PROTOCOL, @@ -295,7 +147,7 @@ static void setup_efi_pci(struct boot_params *params) size, (void **)&pci_handle); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for pci_handle\n"); + efi_printk(sys_table, "Failed to allocate memory for 'pci_handle'\n"); return; } @@ -307,10 +159,34 @@ static void setup_efi_pci(struct boot_params *params) if (status != EFI_SUCCESS) goto free_handle; - if (efi_early->is64) - setup_efi_pci64(params, pci_handle, size); - else - setup_efi_pci32(params, pci_handle, size); + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + nr_pci = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32)); + for (i = 0; i < nr_pci; i++) { + efi_pci_io_protocol_t *pci = NULL; + struct pci_setup_rom *rom; + + status = efi_call_early(handle_protocol, + efi_is_64bit() ? ((u64 *)pci_handle)[i] + : ((u32 *)pci_handle)[i], + &pci_proto, (void **)&pci); + if (status != EFI_SUCCESS || !pci) + continue; + + status = preserve_pci_rom_image(pci, &rom); + if (status != EFI_SUCCESS) + continue; + + if (data) + data->next = (unsigned long)rom; + else + params->hdr.setup_data = (unsigned long)rom; + + data = (struct setup_data *)rom; + } free_handle: efi_call_early(free_pool, pci_handle); @@ -341,8 +217,7 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size + sizeof(struct setup_data), &new); if (status != EFI_SUCCESS) { - efi_printk(sys_table, - "Failed to alloc mem for properties\n"); + efi_printk(sys_table, "Failed to allocate memory for 'properties'\n"); return; } @@ -358,9 +233,9 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) new->next = 0; data = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data; - if (!data) + if (!data) { boot_params->hdr.setup_data = (unsigned long)new; - else { + } else { while (data->next) data = (struct setup_data *)(unsigned long)data->next; data->next = (unsigned long)new; @@ -380,81 +255,55 @@ static void setup_quirks(struct boot_params *boot_params) } } +/* + * See if we have Universal Graphics Adapter (UGA) protocol + */ static efi_status_t -setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height) +setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) { - struct efi_uga_draw_protocol *uga = NULL, *first_uga; - efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; + efi_status_t status; + u32 width, height; + void **uga_handle = NULL; + efi_uga_draw_protocol_t *uga = NULL, *first_uga; unsigned long nr_ugas; - u32 *handles = (u32 *)uga_handle; - efi_status_t status = EFI_INVALID_PARAMETER; int i; - first_uga = NULL; - nr_ugas = size / sizeof(u32); - for (i = 0; i < nr_ugas; i++) { - efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; - u32 w, h, depth, refresh; - void *pciio; - u32 handle = handles[i]; - - status = efi_call_early(handle_protocol, handle, - &uga_proto, (void **)&uga); - if (status != EFI_SUCCESS) - continue; - - efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); - - status = efi_early->call((unsigned long)uga->get_mode, uga, - &w, &h, &depth, &refresh); - if (status == EFI_SUCCESS && (!first_uga || pciio)) { - *width = w; - *height = h; - - /* - * Once we've found a UGA supporting PCIIO, - * don't bother looking any further. - */ - if (pciio) - break; - - first_uga = uga; - } - } + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + size, (void **)&uga_handle); + if (status != EFI_SUCCESS) + return status; - return status; -} + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + uga_proto, NULL, &size, uga_handle); + if (status != EFI_SUCCESS) + goto free_handle; -static efi_status_t -setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) -{ - struct efi_uga_draw_protocol *uga = NULL, *first_uga; - efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; - unsigned long nr_ugas; - u64 *handles = (u64 *)uga_handle; - efi_status_t status = EFI_INVALID_PARAMETER; - int i; + height = 0; + width = 0; first_uga = NULL; - nr_ugas = size / sizeof(u64); + nr_ugas = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32)); for (i = 0; i < nr_ugas; i++) { efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; u32 w, h, depth, refresh; void *pciio; - u64 handle = handles[i]; + unsigned long handle = efi_is_64bit() ? ((u64 *)uga_handle)[i] + : ((u32 *)uga_handle)[i]; status = efi_call_early(handle_protocol, handle, - &uga_proto, (void **)&uga); + uga_proto, (void **)&uga); if (status != EFI_SUCCESS) continue; + pciio = NULL; efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); - status = efi_early->call((unsigned long)uga->get_mode, uga, - &w, &h, &depth, &refresh); + status = efi_call_proto(efi_uga_draw_protocol, get_mode, uga, + &w, &h, &depth, &refresh); if (status == EFI_SUCCESS && (!first_uga || pciio)) { - *width = w; - *height = h; + width = w; + height = h; /* * Once we've found a UGA supporting PCIIO, @@ -467,59 +316,28 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) } } - return status; -} - -/* - * See if we have Universal Graphics Adapter (UGA) protocol - */ -static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto, - unsigned long size) -{ - efi_status_t status; - u32 width, height; - void **uga_handle = NULL; - - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size, (void **)&uga_handle); - if (status != EFI_SUCCESS) - return status; - - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - uga_proto, NULL, &size, uga_handle); - if (status != EFI_SUCCESS) - goto free_handle; - - height = 0; - width = 0; - - if (efi_early->is64) - status = setup_uga64(uga_handle, size, &width, &height); - else - status = setup_uga32(uga_handle, size, &width, &height); - if (!width && !height) goto free_handle; /* EFI framebuffer */ - si->orig_video_isVGA = VIDEO_TYPE_EFI; + si->orig_video_isVGA = VIDEO_TYPE_EFI; - si->lfb_depth = 32; - si->lfb_width = width; - si->lfb_height = height; + si->lfb_depth = 32; + si->lfb_width = width; + si->lfb_height = height; - si->red_size = 8; - si->red_pos = 16; - si->green_size = 8; - si->green_pos = 8; - si->blue_size = 8; - si->blue_pos = 0; - si->rsvd_size = 8; - si->rsvd_pos = 24; + si->red_size = 8; + si->red_pos = 16; + si->green_size = 8; + si->green_pos = 8; + si->blue_size = 8; + si->blue_pos = 0; + si->rsvd_size = 8; + si->rsvd_pos = 24; free_handle: efi_call_early(free_pool, uga_handle); + return status; } @@ -586,7 +404,7 @@ struct boot_params *make_boot_params(struct efi_config *c) if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) return NULL; - if (efi_early->is64) + if (efi_is_64bit()) setup_boot_services64(efi_early); else setup_boot_services32(efi_early); @@ -601,7 +419,7 @@ struct boot_params *make_boot_params(struct efi_config *c) status = efi_low_alloc(sys_table, 0x4000, 1, (unsigned long *)&boot_params); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc lowmem for boot params\n"); + efi_printk(sys_table, "Failed to allocate lowmem for boot params\n"); return NULL; } @@ -617,9 +435,9 @@ struct boot_params *make_boot_params(struct efi_config *c) * Fill out some of the header fields ourselves because the * EFI firmware loader doesn't load the first sector. */ - hdr->root_flags = 1; - hdr->vid_mode = 0xffff; - hdr->boot_flag = 0xAA55; + hdr->root_flags = 1; + hdr->vid_mode = 0xffff; + hdr->boot_flag = 0xAA55; hdr->type_of_loader = 0x21; @@ -627,6 +445,7 @@ struct boot_params *make_boot_params(struct efi_config *c) cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); if (!cmdline_ptr) goto fail; + hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; /* Fill in upper bits of command line address, NOP on 32 bit */ boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32; @@ -663,10 +482,12 @@ struct boot_params *make_boot_params(struct efi_config *c) boot_params->ext_ramdisk_size = (u64)ramdisk_size >> 32; return boot_params; + fail2: efi_free(sys_table, options_size, hdr->cmd_line_ptr); fail: efi_free(sys_table, 0x4000, (unsigned long)boot_params); + return NULL; } @@ -678,7 +499,7 @@ static void add_e820ext(struct boot_params *params, unsigned long size; e820ext->type = SETUP_E820_EXT; - e820ext->len = nr_entries * sizeof(struct boot_e820_entry); + e820ext->len = nr_entries * sizeof(struct boot_e820_entry); e820ext->next = 0; data = (struct setup_data *)(unsigned long)params->hdr.setup_data; @@ -692,8 +513,8 @@ static void add_e820ext(struct boot_params *params, params->hdr.setup_data = (unsigned long)e820ext; } -static efi_status_t setup_e820(struct boot_params *params, - struct setup_data *e820ext, u32 e820ext_size) +static efi_status_t +setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_size) { struct boot_e820_entry *entry = params->e820_table; struct efi_info *efi = ¶ms->efi_info; @@ -814,11 +635,10 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, } struct exit_boot_struct { - struct boot_params *boot_params; - struct efi_info *efi; - struct setup_data *e820ext; - __u32 e820ext_size; - bool is64; + struct boot_params *boot_params; + struct efi_info *efi; + struct setup_data *e820ext; + __u32 e820ext_size; }; static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, @@ -845,25 +665,25 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, first = false; } - signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE; + signature = efi_is_64bit() ? EFI64_LOADER_SIGNATURE + : EFI32_LOADER_SIGNATURE; memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32)); - p->efi->efi_systab = (unsigned long)sys_table_arg; - p->efi->efi_memdesc_size = *map->desc_size; - p->efi->efi_memdesc_version = *map->desc_ver; - p->efi->efi_memmap = (unsigned long)*map->map; - p->efi->efi_memmap_size = *map->map_size; + p->efi->efi_systab = (unsigned long)sys_table_arg; + p->efi->efi_memdesc_size = *map->desc_size; + p->efi->efi_memdesc_version = *map->desc_ver; + p->efi->efi_memmap = (unsigned long)*map->map; + p->efi->efi_memmap_size = *map->map_size; #ifdef CONFIG_X86_64 - p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32; - p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32; + p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32; + p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32; #endif return EFI_SUCCESS; } -static efi_status_t exit_boot(struct boot_params *boot_params, - void *handle, bool is64) +static efi_status_t exit_boot(struct boot_params *boot_params, void *handle) { unsigned long map_sz, key, desc_size, buff_size; efi_memory_desc_t *mem_map; @@ -874,17 +694,16 @@ static efi_status_t exit_boot(struct boot_params *boot_params, struct efi_boot_memmap map; struct exit_boot_struct priv; - map.map = &mem_map; - map.map_size = &map_sz; - map.desc_size = &desc_size; - map.desc_ver = &desc_version; - map.key_ptr = &key; - map.buff_size = &buff_size; - priv.boot_params = boot_params; - priv.efi = &boot_params->efi_info; - priv.e820ext = NULL; - priv.e820ext_size = 0; - priv.is64 = is64; + map.map = &mem_map; + map.map_size = &map_sz; + map.desc_size = &desc_size; + map.desc_ver = &desc_version; + map.key_ptr = &key; + map.buff_size = &buff_size; + priv.boot_params = boot_params; + priv.efi = &boot_params->efi_info; + priv.e820ext = NULL; + priv.e820ext_size = 0; /* Might as well exit boot services now */ status = efi_exit_boot_services(sys_table, handle, &map, &priv, @@ -892,10 +711,11 @@ static efi_status_t exit_boot(struct boot_params *boot_params, if (status != EFI_SUCCESS) return status; - e820ext = priv.e820ext; - e820ext_size = priv.e820ext_size; + e820ext = priv.e820ext; + e820ext_size = priv.e820ext_size; + /* Historic? */ - boot_params->alt_mem_k = 32 * 1024; + boot_params->alt_mem_k = 32 * 1024; status = setup_e820(boot_params, e820ext, e820ext_size); if (status != EFI_SUCCESS) @@ -908,8 +728,8 @@ static efi_status_t exit_boot(struct boot_params *boot_params, * On success we return a pointer to a boot_params structure, and NULL * on failure. */ -struct boot_params *efi_main(struct efi_config *c, - struct boot_params *boot_params) +struct boot_params * +efi_main(struct efi_config *c, struct boot_params *boot_params) { struct desc_ptr *gdt = NULL; efi_loaded_image_t *image; @@ -918,13 +738,11 @@ struct boot_params *efi_main(struct efi_config *c, struct desc_struct *desc; void *handle; efi_system_table_t *_table; - bool is64; efi_early = c; _table = (efi_system_table_t *)(unsigned long)efi_early->table; handle = (void *)(unsigned long)efi_early->image_handle; - is64 = efi_early->is64; sys_table = _table; @@ -932,7 +750,7 @@ struct boot_params *efi_main(struct efi_config *c, if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) goto fail; - if (is64) + if (efi_is_64bit()) setup_boot_services64(efi_early); else setup_boot_services32(efi_early); @@ -957,7 +775,7 @@ struct boot_params *efi_main(struct efi_config *c, status = efi_call_early(allocate_pool, EFI_LOADER_DATA, sizeof(*gdt), (void **)&gdt); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for gdt structure\n"); + efi_printk(sys_table, "Failed to allocate memory for 'gdt' structure\n"); goto fail; } @@ -965,7 +783,7 @@ struct boot_params *efi_main(struct efi_config *c, status = efi_low_alloc(sys_table, gdt->size, 8, (unsigned long *)&gdt->address); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for gdt\n"); + efi_printk(sys_table, "Failed to allocate memory for 'gdt'\n"); goto fail; } @@ -988,7 +806,7 @@ struct boot_params *efi_main(struct efi_config *c, hdr->code32_start = bzimage_addr; } - status = exit_boot(boot_params, handle, is64); + status = exit_boot(boot_params, handle); if (status != EFI_SUCCESS) { efi_printk(sys_table, "exit_boot() failed!\n"); goto fail; @@ -1002,19 +820,20 @@ struct boot_params *efi_main(struct efi_config *c, if (IS_ENABLED(CONFIG_X86_64)) { /* __KERNEL32_CS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + desc++; } else { /* Second entry is unused on 32-bit */ @@ -1022,15 +841,16 @@ struct boot_params *efi_main(struct efi_config *c, } /* __KERNEL_CS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0xf; + desc->avl = 0; + if (IS_ENABLED(CONFIG_X86_64)) { desc->l = 1; desc->d = 0; @@ -1038,41 +858,41 @@ struct boot_params *efi_main(struct efi_config *c, desc->l = 0; desc->d = SEG_OP_SIZE_32BIT; } - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; desc++; /* __KERNEL_DS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; desc++; if (IS_ENABLED(CONFIG_X86_64)) { /* Task segment value */ - desc->limit0 = 0x0000; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_TSS; - desc->s = 0; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0x0; - desc->avl = 0; - desc->l = 0; - desc->d = 0; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->limit0 = 0x0000; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_TSS; + desc->s = 0; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0x0; + desc->avl = 0; + desc->l = 0; + desc->d = 0; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; desc++; } @@ -1082,5 +902,6 @@ struct boot_params *efi_main(struct efi_config *c, return boot_params; fail: efi_printk(sys_table, "efi_main() failed!\n"); + return NULL; } diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index e799dc5c6448..8297387c4676 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -12,22 +12,22 @@ #define DESC_TYPE_CODE_DATA (1 << 0) -struct efi_uga_draw_protocol_32 { +typedef struct { u32 get_mode; u32 set_mode; u32 blt; -}; +} efi_uga_draw_protocol_32_t; -struct efi_uga_draw_protocol_64 { +typedef struct { u64 get_mode; u64 set_mode; u64 blt; -}; +} efi_uga_draw_protocol_64_t; -struct efi_uga_draw_protocol { +typedef struct { void *get_mode; void *set_mode; void *blt; -}; +} efi_uga_draw_protocol_t; #endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index b87a7582853d..302517929932 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -102,7 +102,7 @@ static bool memmap_too_large; /* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */ -unsigned long long mem_limit = ULLONG_MAX; +static unsigned long long mem_limit = ULLONG_MAX; enum mem_avoid_index { @@ -215,7 +215,36 @@ static void mem_avoid_memmap(char *str) memmap_too_large = true; } -static int handle_mem_memmap(void) +/* Store the number of 1GB huge pages which users specified: */ +static unsigned long max_gb_huge_pages; + +static void parse_gb_huge_pages(char *param, char *val) +{ + static bool gbpage_sz; + char *p; + + if (!strcmp(param, "hugepagesz")) { + p = val; + if (memparse(p, &p) != PUD_SIZE) { + gbpage_sz = false; + return; + } + + if (gbpage_sz) + warn("Repeatedly set hugeTLB page size of 1G!\n"); + gbpage_sz = true; + return; + } + + if (!strcmp(param, "hugepages") && gbpage_sz) { + p = val; + max_gb_huge_pages = simple_strtoull(p, &p, 0); + return; + } +} + + +static int handle_mem_options(void) { char *args = (char *)get_cmd_line_ptr(); size_t len = strlen((char *)args); @@ -223,7 +252,8 @@ static int handle_mem_memmap(void) char *param, *val; u64 mem_size; - if (!strstr(args, "memmap=") && !strstr(args, "mem=")) + if (!strstr(args, "memmap=") && !strstr(args, "mem=") && + !strstr(args, "hugepages")) return 0; tmp_cmdline = malloc(len + 1); @@ -248,6 +278,8 @@ static int handle_mem_memmap(void) if (!strcmp(param, "memmap")) { mem_avoid_memmap(val); + } else if (strstr(param, "hugepages")) { + parse_gb_huge_pages(param, val); } else if (!strcmp(param, "mem")) { char *p = val; @@ -387,7 +419,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* We don't need to set a mapping for setup_data. */ /* Mark the memmap regions we need to avoid */ - handle_mem_memmap(); + handle_mem_options(); #ifdef CONFIG_X86_VERBOSE_BOOTUP /* Make sure video RAM can be used. */ @@ -466,6 +498,60 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size) } } +/* + * Skip as many 1GB huge pages as possible in the passed region + * according to the number which users specified: + */ +static void +process_gb_huge_pages(struct mem_vector *region, unsigned long image_size) +{ + unsigned long addr, size = 0; + struct mem_vector tmp; + int i = 0; + + if (!max_gb_huge_pages) { + store_slot_info(region, image_size); + return; + } + + addr = ALIGN(region->start, PUD_SIZE); + /* Did we raise the address above the passed in memory entry? */ + if (addr < region->start + region->size) + size = region->size - (addr - region->start); + + /* Check how many 1GB huge pages can be filtered out: */ + while (size > PUD_SIZE && max_gb_huge_pages) { + size -= PUD_SIZE; + max_gb_huge_pages--; + i++; + } + + /* No good 1GB huge pages found: */ + if (!i) { + store_slot_info(region, image_size); + return; + } + + /* + * Skip those 'i'*1GB good huge pages, and continue checking and + * processing the remaining head or tail part of the passed region + * if available. + */ + + if (addr >= region->start + image_size) { + tmp.start = region->start; + tmp.size = addr - region->start; + store_slot_info(&tmp, image_size); + } + + size = region->size - (addr - region->start) - i * PUD_SIZE; + if (size >= image_size) { + tmp.start = addr + i * PUD_SIZE; + tmp.size = size; + store_slot_info(&tmp, image_size); + } +} + static unsigned long slots_fetch_random(void) { unsigned long slot; @@ -546,7 +632,7 @@ static void process_mem_region(struct mem_vector *entry, /* If nothing overlaps, store the region and return. */ if (!mem_avoid_overlap(®ion, &overlap)) { - store_slot_info(®ion, image_size); + process_gb_huge_pages(®ion, image_size); return; } @@ -556,7 +642,7 @@ static void process_mem_region(struct mem_vector *entry, beginning.start = region.start; beginning.size = overlap.start - region.start; - store_slot_info(&beginning, image_size); + process_gb_huge_pages(&beginning, image_size); } /* Return if overlap extends to or past end of region. */ diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 8c5107545251..9e2157371491 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,3 +1,4 @@ +#include <asm/e820/types.h> #include <asm/processor.h> #include "pgtable.h" #include "../string.h" @@ -34,10 +35,62 @@ unsigned long *trampoline_32bit __section(.data); extern struct boot_params *boot_params; int cmdline_find_option_bool(const char *option); +static unsigned long find_trampoline_placement(void) +{ + unsigned long bios_start, ebda_start; + unsigned long trampoline_start; + struct boot_e820_entry *entry; + int i; + + /* + * Find a suitable spot for the trampoline. + * This code is based on reserve_bios_regions(). + */ + + ebda_start = *(unsigned short *)0x40e << 4; + bios_start = *(unsigned short *)0x413 << 10; + + if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) + bios_start = BIOS_START_MAX; + + if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) + bios_start = ebda_start; + + bios_start = round_down(bios_start, PAGE_SIZE); + + /* Find the first usable memory region under bios_start. */ + for (i = boot_params->e820_entries - 1; i >= 0; i--) { + entry = &boot_params->e820_table[i]; + + /* Skip all entries above bios_start. */ + if (bios_start <= entry->addr) + continue; + + /* Skip non-RAM entries. */ + if (entry->type != E820_TYPE_RAM) + continue; + + /* Adjust bios_start to the end of the entry if needed. */ + if (bios_start > entry->addr + entry->size) + bios_start = entry->addr + entry->size; + + /* Keep bios_start page-aligned. */ + bios_start = round_down(bios_start, PAGE_SIZE); + + /* Skip the entry if it's too small. */ + if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr) + continue; + + break; + } + + /* Place the trampoline just below the end of low memory */ + return bios_start - TRAMPOLINE_32BIT_SIZE; +} + struct paging_config paging_prepare(void *rmode) { struct paging_config paging_config = {}; - unsigned long bios_start, ebda_start; /* Initialize boot_params. Required for cmdline_find_option_bool(). */ boot_params = rmode; @@ -61,23 +114,7 @@ struct paging_config paging_prepare(void *rmode) paging_config.l5_required = 1; } - /* - * Find a suitable spot for the trampoline. - * This code is based on reserve_bios_regions(). - */ - - ebda_start = *(unsigned short *)0x40e << 4; - bios_start = *(unsigned short *)0x413 << 10; - - if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) - bios_start = BIOS_START_MAX; - - if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) - bios_start = ebda_start; - - /* Place the trampoline just below the end of low memory, aligned to 4k */ - paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE; - paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE); + paging_config.trampoline_start = find_trampoline_placement(); trampoline_32bit = (unsigned long *)paging_config.trampoline_start; diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 16f49123d747..c4428a176973 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -13,6 +13,7 @@ */ #include <linux/types.h> +#include <asm/asm.h> #include "ctype.h" #include "string.h" @@ -28,8 +29,8 @@ int memcmp(const void *s1, const void *s2, size_t len) { bool diff; - asm("repe; cmpsb; setnz %0" - : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len)); + asm("repe; cmpsb" CC_SET(nz) + : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len)); return diff; } diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S index 717bf0776421..5f7e43d4f64a 100644 --- a/arch/x86/crypto/aegis128-aesni-asm.S +++ b/arch/x86/crypto/aegis128-aesni-asm.S @@ -75,7 +75,7 @@ * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG, MSG mov LEN, %r8 diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index 5de7c0d46edf..acd11b3bf639 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis128_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis128_aesni_alg, diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S index 4eda2b8db9e1..491dd61c845c 100644 --- a/arch/x86/crypto/aegis128l-aesni-asm.S +++ b/arch/x86/crypto/aegis128l-aesni-asm.S @@ -66,7 +66,7 @@ * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG0, MSG0 pxor MSG1, MSG1 diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c index 876e4866e633..2071c3d1ae07 100644 --- a/arch/x86/crypto/aegis128l-aesni-glue.c +++ b/arch/x86/crypto/aegis128l-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128l_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis128l_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis128l_aesni_alg, diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S index 32aae8397268..8870c7c5d9a4 100644 --- a/arch/x86/crypto/aegis256-aesni-asm.S +++ b/arch/x86/crypto/aegis256-aesni-asm.S @@ -59,7 +59,7 @@ * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG, MSG mov LEN, %r8 diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c index 2b5dd3af8f4d..b5f2a8fd5a71 100644 --- a/arch/x86/crypto/aegis256-aesni-glue.c +++ b/arch/x86/crypto/aegis256-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis256_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis256_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis256_aesni_alg, diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index e762ef417562..9bd139569b41 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -258,7 +258,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff .macro GCM_INIT Iv SUBKEY AAD AADLEN mov \AADLEN, %r11 mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length - xor %r11, %r11 + xor %r11d, %r11d mov %r11, InLen(%arg2) # ctx_data.in_length = 0 mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0 mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0 @@ -286,7 +286,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff movdqu HashKey(%arg2), %xmm13 add %arg5, InLen(%arg2) - xor %r11, %r11 # initialise the data pointer offset as zero + xor %r11d, %r11d # initialise the data pointer offset as zero PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation sub %r11, %arg5 # sub partial block data used @@ -702,7 +702,7 @@ _no_extra_mask_1_\@: # GHASH computation for the last <16 Byte block GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 - xor %rax,%rax + xor %eax, %eax mov %rax, PBlockLen(%arg2) jmp _dec_done_\@ @@ -737,7 +737,7 @@ _no_extra_mask_2_\@: # GHASH computation for the last <16 Byte block GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 - xor %rax,%rax + xor %eax, %eax mov %rax, PBlockLen(%arg2) jmp _encode_done_\@ diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index faecb1518bf8..1985ea0b551b 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -463,7 +463,7 @@ _get_AAD_rest_final\@: _get_AAD_done\@: # initialize the data pointer offset as zero - xor %r11, %r11 + xor %r11d, %r11d # start AES for num_initial_blocks blocks mov arg5, %rax # rax = *Y0 @@ -1770,7 +1770,7 @@ _get_AAD_rest_final\@: _get_AAD_done\@: # initialize the data pointer offset as zero - xor %r11, %r11 + xor %r11d, %r11d # start AES for num_initial_blocks blocks mov arg5, %rax # rax = *Y0 diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S index 07653d4582a6..de182c460f82 100644 --- a/arch/x86/crypto/morus1280-avx2-asm.S +++ b/arch/x86/crypto/morus1280-avx2-asm.S @@ -113,7 +113,7 @@ ENDPROC(__morus1280_update_zero) * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d vpxor MSG, MSG, MSG mov %rcx, %r8 diff --git a/arch/x86/crypto/morus1280-avx2-glue.c b/arch/x86/crypto/morus1280-avx2-glue.c index f111f36d26dc..6634907d6ccd 100644 --- a/arch/x86/crypto/morus1280-avx2-glue.c +++ b/arch/x86/crypto/morus1280-avx2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_avx2_final(void *state, void *tag_xor, MORUS1280_DECLARE_ALGS(avx2, "morus1280-avx2", 400); -static const struct x86_cpu_id avx2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AVX2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, avx2_cpu_id); - static int __init crypto_morus1280_avx2_module_init(void) { - if (!x86_match_cpu(avx2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_AVX2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus1280_avx2_algs, diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S index bd1aa1b60869..da5d2905db60 100644 --- a/arch/x86/crypto/morus1280-sse2-asm.S +++ b/arch/x86/crypto/morus1280-sse2-asm.S @@ -235,7 +235,7 @@ ENDPROC(__morus1280_update_zero) * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG_LO, MSG_LO pxor MSG_HI, MSG_HI diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c index 839270aa713c..95cf857d2cbb 100644 --- a/arch/x86/crypto/morus1280-sse2-glue.c +++ b/arch/x86/crypto/morus1280-sse2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_sse2_final(void *state, void *tag_xor, MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350); -static const struct x86_cpu_id sse2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id); - static int __init crypto_morus1280_sse2_module_init(void) { - if (!x86_match_cpu(sse2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus1280_sse2_algs, diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S index efa02816d921..414db480250e 100644 --- a/arch/x86/crypto/morus640-sse2-asm.S +++ b/arch/x86/crypto/morus640-sse2-asm.S @@ -113,7 +113,7 @@ ENDPROC(__morus640_update_zero) * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG, MSG mov %rcx, %r8 diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c index 26b47e2db8d2..615fb7bc9a32 100644 --- a/arch/x86/crypto/morus640-sse2-glue.c +++ b/arch/x86/crypto/morus640-sse2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus640_sse2_final(void *state, void *tag_xor, MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400); -static const struct x86_cpu_id sse2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id); - static int __init crypto_morus640_sse2_module_init(void) { - if (!x86_match_cpu(sse2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus640_sse2_algs, diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index 6204bd53528c..613d0bfc3d84 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -96,7 +96,7 @@ # cleanup workspace mov $8, %ecx mov %rsp, %rdi - xor %rax, %rax + xor %eax, %eax rep stosq mov %rbp, %rsp # deallocate workspace diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 73a522d53b53..957dfb693ecc 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -92,7 +92,7 @@ END(native_usergs_sysret64) .endm .macro TRACE_IRQS_IRETQ_DEBUG - bt $9, EFLAGS(%rsp) /* interrupts off? */ + btl $9, EFLAGS(%rsp) /* interrupts off? */ jnc 1f TRACE_IRQS_ON_DEBUG 1: @@ -408,6 +408,7 @@ ENTRY(ret_from_fork) 1: /* kernel thread */ + UNWIND_HINT_EMPTY movq %r12, %rdi CALL_NOSPEC %rbx /* @@ -701,7 +702,7 @@ retint_kernel: #ifdef CONFIG_PREEMPT /* Interrupts are off */ /* Check if we need preemption */ - bt $9, EFLAGS(%rsp) /* were interrupts off? */ + btl $9, EFLAGS(%rsp) /* were interrupts off? */ jnc 1f 0: cmpl $0, PER_CPU_VAR(__preempt_count) jnz 1f @@ -981,7 +982,7 @@ ENTRY(\sym) call \do_sym - jmp error_exit /* %ebx: no swapgs flag */ + jmp error_exit .endif END(\sym) .endm @@ -1222,7 +1223,6 @@ END(paranoid_exit) /* * Save all registers in pt_regs, and switch GS if needed. - * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) UNWIND_HINT_FUNC @@ -1269,7 +1269,6 @@ ENTRY(error_entry) * for these here too. */ .Lerror_kernelspace: - incl %ebx leaq native_irq_return_iret(%rip), %rcx cmpq %rcx, RIP+8(%rsp) je .Lerror_bad_iret @@ -1303,28 +1302,20 @@ ENTRY(error_entry) /* * Pretend that the exception came from user mode: set up pt_regs - * as if we faulted immediately after IRET and clear EBX so that - * error_exit knows that we will be returning to user mode. + * as if we faulted immediately after IRET. */ mov %rsp, %rdi call fixup_bad_iret mov %rax, %rsp - decl %ebx jmp .Lerror_entry_from_usermode_after_swapgs END(error_entry) - -/* - * On entry, EBX is a "return to kernel mode" flag: - * 1: already in kernel mode, don't need SWAPGS - * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode - */ ENTRY(error_exit) UNWIND_HINT_REGS DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - testl %ebx, %ebx - jnz retint_kernel + testb $3, CS(%rsp) + jz retint_kernel jmp retint_user END(error_exit) diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 261802b1cc50..b9ed1aa53a26 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -58,9 +58,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(src hostprogs-y += vdso2c quiet_cmd_vdso2c = VDSO2C $@ -define cmd_vdso2c - $(obj)/vdso2c $< $(<:%.dbg=%) $@ -endef + cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE $(call if_changed,vdso2c) diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 4b98101209a1..d50bb4dc0650 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -579,7 +579,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) { struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); struct perf_event *event = pcpu->event; - struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event *hwc; struct perf_sample_data data; struct perf_raw_record raw; struct pt_regs regs; @@ -602,6 +602,10 @@ fail: return 0; } + if (WARN_ON_ONCE(!event)) + goto fail; + + hwc = &event->hw; msr = hwc->config_base; buf = ibs_data.regs; rdmsrl(msr, *buf); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 707b2a96e516..035c37481f57 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2041,15 +2041,15 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); cpuc->intel_cp_status &= ~(1ull << hwc->idx); + if (unlikely(event->attr.precise_ip)) + intel_pmu_pebs_disable(event); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_disable_fixed(hwc); return; } x86_pmu_disable_event(event); - - if (unlikely(event->attr.precise_ip)) - intel_pmu_pebs_disable(event); } static void intel_pmu_del_event(struct perf_event *event) @@ -2068,17 +2068,19 @@ static void intel_pmu_read_event(struct perf_event *event) x86_perf_event_update(event); } -static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) +static void intel_pmu_enable_fixed(struct perf_event *event) { + struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx - INTEL_PMC_IDX_FIXED; - u64 ctrl_val, bits, mask; + u64 ctrl_val, mask, bits = 0; /* - * Enable IRQ generation (0x8), + * Enable IRQ generation (0x8), if not PEBS, * and enable ring-3 counting (0x2) and ring-0 counting (0x1) * if requested: */ - bits = 0x8ULL; + if (!event->attr.precise_ip) + bits |= 0x8; if (hwc->config & ARCH_PERFMON_EVENTSEL_USR) bits |= 0x2; if (hwc->config & ARCH_PERFMON_EVENTSEL_OS) @@ -2120,14 +2122,14 @@ static void intel_pmu_enable_event(struct perf_event *event) if (unlikely(event_is_checkpointed(event))) cpuc->intel_cp_status |= (1ull << hwc->idx); + if (unlikely(event->attr.precise_ip)) + intel_pmu_pebs_enable(event); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { - intel_pmu_enable_fixed(hwc); + intel_pmu_enable_fixed(event); return; } - if (unlikely(event->attr.precise_ip)) - intel_pmu_pebs_enable(event); - __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } @@ -2280,7 +2282,10 @@ again: * counters from the GLOBAL_STATUS mask and we always process PEBS * events via drain_pebs(). */ - status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK); + if (x86_pmu.flags & PMU_FL_PEBS_ALL) + status &= ~cpuc->pebs_enabled; + else + status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK); /* * PEBS overflow sets bit 62 in the global status register @@ -2997,6 +3002,9 @@ static int intel_pmu_hw_config(struct perf_event *event) } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); + + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY; } if (needs_branch_stack(event)) { @@ -4069,7 +4077,6 @@ __init int intel_pmu_init(void) intel_pmu_lbr_init_skl(); x86_pmu.event_constraints = intel_slm_event_constraints; - x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints; x86_pmu.extra_regs = intel_glm_extra_regs; /* * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS @@ -4079,6 +4086,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_prec_dist = true; x86_pmu.lbr_pt_coexist = true; x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_PEBS_ALL; x86_pmu.get_event_constraints = glp_get_event_constraints; x86_pmu.cpu_events = glm_events_attrs; /* Goldmont Plus has 4-wide pipeline */ diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8a10a045b57b..b7b01d762d32 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -408,9 +408,11 @@ static int alloc_bts_buffer(int cpu) ds->bts_buffer_base = (unsigned long) cea; ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL); ds->bts_index = ds->bts_buffer_base; - max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE); - ds->bts_absolute_maximum = ds->bts_buffer_base + max; - ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16); + max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE; + ds->bts_absolute_maximum = ds->bts_buffer_base + + max * BTS_RECORD_SIZE; + ds->bts_interrupt_threshold = ds->bts_absolute_maximum - + (max / 16) * BTS_RECORD_SIZE; return 0; } @@ -711,12 +713,6 @@ struct event_constraint intel_glm_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -struct event_constraint intel_glp_pebs_event_constraints[] = { - /* Allow all events as PEBS with no flags */ - INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), - EVENT_CONSTRAINT_END -}; - struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ @@ -869,6 +865,13 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) } } + /* + * Extended PEBS support + * Makes the PEBS code search the normal constraints. + */ + if (x86_pmu.flags & PMU_FL_PEBS_ALL) + return NULL; + return &emptyconstraint; } @@ -894,10 +897,16 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) { struct debug_store *ds = cpuc->ds; u64 threshold; + int reserved; + + if (x86_pmu.flags & PMU_FL_PEBS_ALL) + reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed; + else + reserved = x86_pmu.max_pebs_events; if (cpuc->n_pebs == cpuc->n_large_pebs) { threshold = ds->pebs_absolute_maximum - - x86_pmu.max_pebs_events * x86_pmu.pebs_record_size; + reserved * x86_pmu.pebs_record_size; } else { threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; } @@ -961,7 +970,11 @@ void intel_pmu_pebs_enable(struct perf_event *event) * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD. */ if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { - ds->pebs_event_reset[hwc->idx] = + unsigned int idx = hwc->idx; + + if (idx >= INTEL_PMC_IDX_FIXED) + idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED); + ds->pebs_event_reset[idx] = (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; } else { ds->pebs_event_reset[hwc->idx] = 0; @@ -1184,16 +1197,20 @@ static void setup_pebs_sample_data(struct perf_event *event, } /* + * We must however always use iregs for the unwinder to stay sane; the + * record BP,SP,IP can point into thin air when the record is from a + * previous PMI context or an (I)RET happend between the record and + * PMI. + */ + if (sample_type & PERF_SAMPLE_CALLCHAIN) + data->callchain = perf_callchain(event, iregs); + + /* * We use the interrupt regs as a base because the PEBS record does not * contain a full regs set, specifically it seems to lack segment * descriptors, which get used by things like user_mode(). * * In the simple case fix up only the IP for PERF_SAMPLE_IP. - * - * We must however always use BP,SP from iregs for the unwinder to stay - * sane; the record BP,SP can point into thin air when the record is - * from a previous PMI context or an (I)RET happend between the record - * and PMI. */ *regs = *iregs; @@ -1212,15 +1229,8 @@ static void setup_pebs_sample_data(struct perf_event *event, regs->si = pebs->si; regs->di = pebs->di; - /* - * Per the above; only set BP,SP if we don't need callchains. - * - * XXX: does this make sense? - */ - if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) { - regs->bp = pebs->bp; - regs->sp = pebs->sp; - } + regs->bp = pebs->bp; + regs->sp = pebs->sp; #ifndef CONFIG_X86_32 regs->r8 = pebs->r8; @@ -1482,9 +1492,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) struct debug_store *ds = cpuc->ds; struct perf_event *event; void *base, *at, *top; - short counts[MAX_PEBS_EVENTS] = {}; - short error[MAX_PEBS_EVENTS] = {}; - int bit, i; + short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + int bit, i, size; + u64 mask; if (!x86_pmu.pebs_active) return; @@ -1494,6 +1505,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) ds->pebs_index = ds->pebs_buffer_base; + mask = (1ULL << x86_pmu.max_pebs_events) - 1; + size = x86_pmu.max_pebs_events; + if (x86_pmu.flags & PMU_FL_PEBS_ALL) { + mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED; + size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed; + } + if (unlikely(base >= top)) { /* * The drain_pebs() could be called twice in a short period @@ -1503,7 +1521,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * update the event->count for this case. */ for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, - x86_pmu.max_pebs_events) { + size) { event = cpuc->events[bit]; if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) intel_pmu_save_and_restart_reload(event, 0); @@ -1516,12 +1534,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) u64 pebs_status; pebs_status = p->status & cpuc->pebs_enabled; - pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; + pebs_status &= mask; /* PEBS v3 has more accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) { for_each_set_bit(bit, (unsigned long *)&pebs_status, - x86_pmu.max_pebs_events) + size) counts[bit]++; continue; @@ -1569,7 +1587,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) counts[bit]++; } - for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) { + for (bit = 0; bit < size; bit++) { if ((counts[bit] == 0) && (error[bit] == 0)) continue; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index cf372b90557e..f3e006bed9a7 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -216,6 +216,8 @@ static void intel_pmu_lbr_reset_64(void) void intel_pmu_lbr_reset(void) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + if (!x86_pmu.lbr_nr) return; @@ -223,6 +225,9 @@ void intel_pmu_lbr_reset(void) intel_pmu_lbr_reset_32(); else intel_pmu_lbr_reset_64(); + + cpuc->last_task_ctx = NULL; + cpuc->last_log_id = 0; } /* @@ -334,6 +339,7 @@ static inline u64 rdlbr_to(unsigned int idx) static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; unsigned lbr_idx, mask; u64 tos; @@ -344,9 +350,21 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) return; } - mask = x86_pmu.lbr_nr - 1; tos = task_ctx->tos; - for (i = 0; i < tos; i++) { + /* + * Does not restore the LBR registers, if + * - No one else touched them, and + * - Did not enter C6 + */ + if ((task_ctx == cpuc->last_task_ctx) && + (task_ctx->log_id == cpuc->last_log_id) && + rdlbr_from(tos)) { + task_ctx->lbr_stack_state = LBR_NONE; + return; + } + + mask = x86_pmu.lbr_nr - 1; + for (i = 0; i < task_ctx->valid_lbrs; i++) { lbr_idx = (tos - i) & mask; wrlbr_from(lbr_idx, task_ctx->lbr_from[i]); wrlbr_to (lbr_idx, task_ctx->lbr_to[i]); @@ -354,14 +372,24 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + + for (; i < x86_pmu.lbr_nr; i++) { + lbr_idx = (tos - i) & mask; + wrlbr_from(lbr_idx, 0); + wrlbr_to(lbr_idx, 0); + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0); + } + wrmsrl(x86_pmu.lbr_tos, tos); task_ctx->lbr_stack_state = LBR_NONE; } static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); unsigned lbr_idx, mask; - u64 tos; + u64 tos, from; int i; if (task_ctx->lbr_callstack_users == 0) { @@ -371,15 +399,22 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) mask = x86_pmu.lbr_nr - 1; tos = intel_pmu_lbr_tos(); - for (i = 0; i < tos; i++) { + for (i = 0; i < x86_pmu.lbr_nr; i++) { lbr_idx = (tos - i) & mask; - task_ctx->lbr_from[i] = rdlbr_from(lbr_idx); + from = rdlbr_from(lbr_idx); + if (!from) + break; + task_ctx->lbr_from[i] = from; task_ctx->lbr_to[i] = rdlbr_to(lbr_idx); if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + task_ctx->valid_lbrs = i; task_ctx->tos = tos; task_ctx->lbr_stack_state = LBR_VALID; + + cpuc->last_task_ctx = task_ctx; + cpuc->last_log_id = ++task_ctx->log_id; } void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) @@ -531,7 +566,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) */ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { - bool need_info = false; + bool need_info = false, call_stack = false; unsigned long mask = x86_pmu.lbr_nr - 1; int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); @@ -542,7 +577,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) if (cpuc->lbr_sel) { need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO); if (cpuc->lbr_sel->config & LBR_CALL_STACK) - num = tos; + call_stack = true; } for (i = 0; i < num; i++) { @@ -555,6 +590,13 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) from = rdlbr_from(lbr_idx); to = rdlbr_to(lbr_idx); + /* + * Read LBR call stack entries + * until invalid entry (0s) is detected. + */ + if (call_stack && !from) + break; + if (lbr_format == LBR_FORMAT_INFO && need_info) { u64 info; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index c9e1e0bef3c3..e17ab885b1e9 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -28,7 +28,7 @@ #define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff) #define UNCORE_PCI_DEV_IDX(data) (data & 0xff) #define UNCORE_EXTRA_PCI_DEV 0xff -#define UNCORE_EXTRA_PCI_DEV_MAX 3 +#define UNCORE_EXTRA_PCI_DEV_MAX 4 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 87dc0263a2e1..51d7c117e3c7 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void) enum { SNBEP_PCI_QPI_PORT0_FILTER, SNBEP_PCI_QPI_PORT1_FILTER, + BDX_PCI_QPI_PORT2_FILTER, HSWEP_PCI_PCU_3, }; @@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { }, { /* QPI Port 0 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), }, { /* QPI Port 1 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), }, { /* QPI Port 2 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + BDX_PCI_QPI_PORT2_FILTER), }, { /* PCU.3 (for Capability registers) */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0), diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 9f3711470ec1..156286335351 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -163,6 +163,7 @@ struct intel_excl_cntrs { unsigned core_id; /* per-core: core id */ }; +struct x86_perf_task_context; #define MAX_LBR_ENTRIES 32 enum { @@ -214,6 +215,8 @@ struct cpu_hw_events { struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; struct er_account *lbr_sel; u64 br_sel; + struct x86_perf_task_context *last_task_ctx; + int last_log_id; /* * Intel host/guest exclude bits @@ -648,8 +651,10 @@ struct x86_perf_task_context { u64 lbr_to[MAX_LBR_ENTRIES]; u64 lbr_info[MAX_LBR_ENTRIES]; int tos; + int valid_lbrs; int lbr_callstack_users; int lbr_stack_state; + int log_id; }; #define x86_add_quirk(func_) \ @@ -668,6 +673,7 @@ do { \ #define PMU_FL_HAS_RSP_1 0x2 /* has 2 equivalent offcore_rsp regs */ #define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */ #define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ +#define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 402338365651..5b0f613428c2 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -31,6 +31,8 @@ #include <asm/mshyperv.h> #include <asm/apic.h> +#include <asm/trace/hyperv.h> + static struct apic orig_apic; static u64 hv_apic_icr_read(void) @@ -99,6 +101,9 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) int nr_bank = 0; int ret = 1; + if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return false; + local_irq_save(flags); arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); @@ -130,10 +135,10 @@ ipi_mask_ex_done: static bool __send_ipi_mask(const struct cpumask *mask, int vector) { int cur_cpu, vcpu; - struct ipi_arg_non_ex **arg; - struct ipi_arg_non_ex *ipi_arg; + struct ipi_arg_non_ex ipi_arg; int ret = 1; - unsigned long flags; + + trace_hyperv_send_ipi_mask(mask, vector); if (cpumask_empty(mask)) return true; @@ -144,40 +149,43 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector) if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) return false; - if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - return __send_ipi_mask_ex(mask, vector); - - local_irq_save(flags); - arg = (struct ipi_arg_non_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); - - ipi_arg = *arg; - if (unlikely(!ipi_arg)) - goto ipi_mask_done; - - ipi_arg->vector = vector; - ipi_arg->reserved = 0; - ipi_arg->cpu_mask = 0; + /* + * From the supplied CPU set we need to figure out if we can get away + * with cheaper HVCALL_SEND_IPI hypercall. This is possible when the + * highest VP number in the set is < 64. As VP numbers are usually in + * ascending order and match Linux CPU ids, here is an optimization: + * we check the VP number for the highest bit in the supplied set first + * so we can quickly find out if using HVCALL_SEND_IPI_EX hypercall is + * a must. We will also check all VP numbers when walking the supplied + * CPU set to remain correct in all cases. + */ + if (hv_cpu_number_to_vp_number(cpumask_last(mask)) >= 64) + goto do_ex_hypercall; + + ipi_arg.vector = vector; + ipi_arg.cpu_mask = 0; for_each_cpu(cur_cpu, mask) { vcpu = hv_cpu_number_to_vp_number(cur_cpu); if (vcpu == VP_INVAL) - goto ipi_mask_done; + return false; /* * This particular version of the IPI hypercall can * only target upto 64 CPUs. */ if (vcpu >= 64) - goto ipi_mask_done; + goto do_ex_hypercall; - __set_bit(vcpu, (unsigned long *)&ipi_arg->cpu_mask); + __set_bit(vcpu, (unsigned long *)&ipi_arg.cpu_mask); } - ret = hv_do_hypercall(HVCALL_SEND_IPI, ipi_arg, NULL); - -ipi_mask_done: - local_irq_restore(flags); + ret = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector, + ipi_arg.cpu_mask); return ((ret == 0) ? true : false); + +do_ex_hypercall: + return __send_ipi_mask_ex(mask, vector); } static bool __send_ipi_one(int cpu, int vector) @@ -233,10 +241,7 @@ static void hv_send_ipi_self(int vector) void __init hv_apic_init(void) { if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) { - if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - pr_info("Hyper-V: Using ext hypercalls for IPI\n"); - else - pr_info("Hyper-V: Using IPI hypercalls\n"); + pr_info("Hyper-V: Using IPI hypercalls\n"); /* * Set the IPI entry points. */ diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index de27615c51ea..1147e1fed7ff 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -16,6 +16,8 @@ /* Each gva in gva_list encodes up to 4096 pages to flush */ #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) +static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, + const struct flush_tlb_info *info); /* * Fills in gva_list starting from offset. Returns the number of items added. @@ -93,10 +95,29 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, if (cpumask_equal(cpus, cpu_present_mask)) { flush->flags |= HV_FLUSH_ALL_PROCESSORS; } else { + /* + * From the supplied CPU set we need to figure out if we can get + * away with cheaper HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE} + * hypercalls. This is possible when the highest VP number in + * the set is < 64. As VP numbers are usually in ascending order + * and match Linux CPU ids, here is an optimization: we check + * the VP number for the highest bit in the supplied set first + * so we can quickly find out if using *_EX hypercalls is a + * must. We will also check all VP numbers when walking the + * supplied CPU set to remain correct in all cases. + */ + if (hv_cpu_number_to_vp_number(cpumask_last(cpus)) >= 64) + goto do_ex_hypercall; + for_each_cpu(cpu, cpus) { vcpu = hv_cpu_number_to_vp_number(cpu); - if (vcpu >= 64) + if (vcpu == VP_INVAL) { + local_irq_restore(flags); goto do_native; + } + + if (vcpu >= 64) + goto do_ex_hypercall; __set_bit(vcpu, (unsigned long *) &flush->processor_mask); @@ -123,7 +144,12 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST, gva_n, 0, flush, NULL); } + goto check_status; + +do_ex_hypercall: + status = hyperv_flush_tlb_others_ex(cpus, info); +check_status: local_irq_restore(flags); if (!(status & HV_HYPERCALL_RESULT_MASK)) @@ -132,35 +158,22 @@ do_native: native_flush_tlb_others(cpus, info); } -static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, - const struct flush_tlb_info *info) +static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, + const struct flush_tlb_info *info) { int nr_bank = 0, max_gvas, gva_n; struct hv_tlb_flush_ex **flush_pcpu; struct hv_tlb_flush_ex *flush; - u64 status = U64_MAX; - unsigned long flags; + u64 status; - trace_hyperv_mmu_flush_tlb_others(cpus, info); - - if (!hv_hypercall_pg) - goto do_native; - - if (cpumask_empty(cpus)) - return; - - local_irq_save(flags); + if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return U64_MAX; flush_pcpu = (struct hv_tlb_flush_ex **) this_cpu_ptr(hyperv_pcpu_input_arg); flush = *flush_pcpu; - if (unlikely(!flush)) { - local_irq_restore(flags); - goto do_native; - } - if (info->mm) { /* * AddressSpace argument must match the CR3 with PCID bits @@ -176,15 +189,10 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->hv_vp_set.valid_bank_mask = 0; - if (!cpumask_equal(cpus, cpu_present_mask)) { - flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; - nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus); - } - - if (!nr_bank) { - flush->hv_vp_set.format = HV_GENERIC_SET_ALL; - flush->flags |= HV_FLUSH_ALL_PROCESSORS; - } + flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus); + if (nr_bank < 0) + return U64_MAX; /* * We can flush not more than max_gvas with one hypercall. Flush the @@ -213,12 +221,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, gva_n, nr_bank, flush, NULL); } - local_irq_restore(flags); - - if (!(status & HV_HYPERCALL_RESULT_MASK)) - return; -do_native: - native_flush_tlb_others(cpus, info); + return status; } void hyperv_setup_mmu_ops(void) @@ -226,11 +229,6 @@ void hyperv_setup_mmu_ops(void) if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED)) return; - if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) { - pr_info("Using hypercall for remote TLB flush\n"); - pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others; - } else { - pr_info("Using ext hypercall for remote TLB flush\n"); - pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex; - } + pr_info("Using hypercall for remote TLB flush\n"); + pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others; } diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index c356098b6fb9..4d4015ddcf26 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -7,8 +7,6 @@ #ifndef _ASM_X86_MACH_DEFAULT_APM_H #define _ASM_X86_MACH_DEFAULT_APM_H -#include <asm/nospec-branch.h> - #ifdef APM_ZERO_SEGS # define APM_DO_ZERO_SEGS \ "pushl %%ds\n\t" \ @@ -34,7 +32,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ - firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -47,7 +44,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, "=S" (*esi) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); - firmware_restrict_branch_speculation_end(); } static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, @@ -60,7 +56,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ - firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -73,7 +68,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, "=S" (si) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); - firmware_restrict_branch_speculation_end(); return error; } diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 0db6bec95489..b143717b92b3 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -80,6 +80,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ +#define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); @@ -91,6 +92,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" @@ -103,6 +105,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic_dec arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" @@ -117,6 +120,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ +#define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); @@ -130,6 +134,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ +#define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); @@ -144,6 +149,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ +#define arch_atomic_add_negative arch_atomic_add_negative static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); @@ -173,9 +179,6 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) return arch_atomic_add_return(-i, v); } -#define arch_atomic_inc_return(v) (arch_atomic_add_return(1, v)) -#define arch_atomic_dec_return(v) (arch_atomic_sub_return(1, v)) - static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return xadd(&v->counter, i); @@ -199,7 +202,7 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n static inline int arch_atomic_xchg(atomic_t *v, int new) { - return xchg(&v->counter, new); + return arch_xchg(&v->counter, new); } static inline void arch_atomic_and(int i, atomic_t *v) @@ -253,27 +256,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v) return val; } -/** - * __arch_atomic_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns the old value of @v. - */ -static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); - - return c; -} - #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 92212bf0484f..ef959f02d070 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -158,6 +158,7 @@ static inline long long arch_atomic64_inc_return(atomic64_t *v) "S" (v) : "memory", "ecx"); return a; } +#define arch_atomic64_inc_return arch_atomic64_inc_return static inline long long arch_atomic64_dec_return(atomic64_t *v) { @@ -166,6 +167,7 @@ static inline long long arch_atomic64_dec_return(atomic64_t *v) "S" (v) : "memory", "ecx"); return a; } +#define arch_atomic64_dec_return arch_atomic64_dec_return /** * arch_atomic64_add - add integer to atomic64 variable @@ -198,25 +200,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) } /** - * arch_atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer to type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v) -{ - return arch_atomic64_sub_return(i, v) == 0; -} - -/** * arch_atomic64_inc - increment atomic64 variable * @v: pointer to type atomic64_t * * Atomically increments @v by 1. */ +#define arch_atomic64_inc arch_atomic64_inc static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, @@ -229,6 +218,7 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic64_dec arch_atomic64_dec static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, @@ -236,46 +226,6 @@ static inline void arch_atomic64_dec(atomic64_t *v) } /** - * arch_atomic64_dec_and_test - decrement and test - * @v: pointer to type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static inline int arch_atomic64_dec_and_test(atomic64_t *v) -{ - return arch_atomic64_dec_return(v) == 0; -} - -/** - * atomic64_inc_and_test - increment and test - * @v: pointer to type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static inline int arch_atomic64_inc_and_test(atomic64_t *v) -{ - return arch_atomic64_inc_return(v) == 0; -} - -/** - * arch_atomic64_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer to type atomic64_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static inline int arch_atomic64_add_negative(long long i, atomic64_t *v) -{ - return arch_atomic64_add_return(i, v) < 0; -} - -/** * arch_atomic64_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... @@ -295,7 +245,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, return (int)a; } - +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; @@ -304,6 +254,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) return r; } +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 6106b59d3260..4343d9b4f30e 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -71,6 +71,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); @@ -82,6 +83,7 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" @@ -95,6 +97,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic64_dec arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" @@ -110,6 +113,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); @@ -123,6 +127,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); @@ -137,6 +142,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ +#define arch_atomic64_add_negative arch_atomic64_add_negative static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); @@ -169,9 +175,6 @@ static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v) return xadd(&v->counter, -i); } -#define arch_atomic64_inc_return(v) (arch_atomic64_add_return(1, (v))) -#define arch_atomic64_dec_return(v) (arch_atomic64_sub_return(1, (v))) - static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new) { return arch_cmpxchg(&v->counter, old, new); @@ -185,46 +188,7 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, l static inline long arch_atomic64_xchg(atomic64_t *v, long new) { - return xchg(&v->counter, new); -} - -/** - * arch_atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u) -{ - s64 c = arch_atomic64_read(v); - do { - if (unlikely(c == u)) - return false; - } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); - return true; -} - -#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0) - -/* - * arch_atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - * - * The function returns the old value of *v minus 1, even if - * the atomic variable, v, was not decremented. - */ -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) -{ - s64 dec, c = arch_atomic64_read(v); - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); - return dec; + return arch_xchg(&v->counter, new); } static inline void arch_atomic64_and(long i, atomic64_t *v) diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index e3efd8a06066..a55d79b233d3 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -75,7 +75,7 @@ extern void __add_wrong_size(void) * use "asm volatile" and "memory" clobbers to prevent gcc from moving * information around. */ -#define xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") +#define arch_xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") /* * Atomic compare and exchange. Compare OLD with MEM, if identical, diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index bfca3b346c74..072e5459fe2f 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -10,13 +10,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) #define arch_cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg((ptr), (o), (n)); \ + arch_cmpxchg((ptr), (o), (n)); \ }) #define arch_cmpxchg64_local(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg_local((ptr), (o), (n)); \ + arch_cmpxchg_local((ptr), (o), (n)); \ }) #define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 5701f5cecd31..7fff98fa5855 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -229,7 +229,7 @@ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ - +#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index f59c39835a5a..a1f0e90d0818 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -49,11 +49,14 @@ static inline int hw_breakpoint_slots(int type) return HBP_NUM; } +struct perf_event_attr; struct perf_event; struct pmu; -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h index 62a9f4966b42..ae26df1c2789 100644 --- a/arch/x86/include/asm/intel_ds.h +++ b/arch/x86/include/asm/intel_ds.h @@ -8,6 +8,7 @@ /* The maximal number of PEBS events: */ #define MAX_PEBS_EVENTS 8 +#define MAX_FIXED_PEBS_EVENTS 3 /* * A debug store configuration. @@ -23,7 +24,7 @@ struct debug_store { u64 pebs_index; u64 pebs_absolute_maximum; u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; + u64 pebs_event_reset[MAX_PEBS_EVENTS + MAX_FIXED_PEBS_EVENTS]; } __aligned(PAGE_SIZE); DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 367d99cff426..c8cec1b39b88 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -78,7 +78,7 @@ struct arch_specific_insn { * boostable = true: This instruction has been boosted: we have * added a relative jump after the instruction copy in insn, * so no single-step and fixup are needed (unless there's - * a post_handler or break_handler). + * a post_handler). */ bool boostable; bool if_modifier; @@ -111,9 +111,6 @@ struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_old_flags; unsigned long kprobe_saved_flags; - unsigned long *jprobe_saved_sp; - struct pt_regs jprobe_saved_regs; - kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 5a7375ed5f7c..19886fef1dfc 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -194,6 +194,40 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) return hv_status; } +/* Fast hypercall with 16 bytes of input */ +static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) +{ + u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT; + +#ifdef CONFIG_X86_64 + { + __asm__ __volatile__("mov %4, %%r8\n" + CALL_NOSPEC + : "=a" (hv_status), ASM_CALL_CONSTRAINT, + "+c" (control), "+d" (input1) + : "r" (input2), + THUNK_TARGET(hv_hypercall_pg) + : "cc", "r8", "r9", "r10", "r11"); + } +#else + { + u32 input1_hi = upper_32_bits(input1); + u32 input1_lo = lower_32_bits(input1); + u32 input2_hi = upper_32_bits(input2); + u32 input2_lo = lower_32_bits(input2); + + __asm__ __volatile__ (CALL_NOSPEC + : "=A"(hv_status), + "+c"(input1_lo), ASM_CALL_CONSTRAINT + : "A" (control), "b" (input1_hi), + "D"(input2_hi), "S"(input2_lo), + THUNK_TARGET(hv_hypercall_pg) + : "cc"); + } +#endif + return hv_status; +} + /* * Rep hypercalls. Callers of this functions are supposed to ensure that * rep_count and varhead_size comply with Hyper-V hypercall definition. diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h index 9c9dc579bd7d..46f516dd80ce 100644 --- a/arch/x86/include/asm/orc_types.h +++ b/arch/x86/include/asm/orc_types.h @@ -88,6 +88,7 @@ struct orc_entry { unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; + unsigned end:1; } __packed; /* @@ -101,6 +102,7 @@ struct unwind_hint { s16 sp_offset; u8 sp_reg; u8 type; + u8 end; }; #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a06b07399d17..e9202a0de8f0 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -450,9 +450,10 @@ do { \ bool __ret; \ typeof(pcp1) __o1 = (o1), __n1 = (n1); \ typeof(pcp2) __o2 = (o2), __n2 = (n2); \ - asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t" \ - : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \ - : "b" (__n1), "c" (__n2), "a" (__o1)); \ + asm volatile("cmpxchg8b "__percpu_arg(1) \ + CC_SET(z) \ + : CC_OUT(z) (__ret), "+m" (pcp1), "+m" (pcp2), "+a" (__o1), "+d" (__o2) \ + : "b" (__n1), "c" (__n2)); \ __ret; \ }) diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 9ef5ee03d2d7..159622ee0674 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -43,7 +43,7 @@ asm (".pushsection .text;" "push %rdx;" "mov $0x1,%eax;" "xor %edx,%edx;" - "lock cmpxchg %dl,(%rdi);" + LOCK_PREFIX "cmpxchg %dl,(%rdi);" "cmp $0x1,%al;" "jne .slowpath;" "pop %rdx;" diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 4cf11d88d3b3..19b90521954c 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -5,6 +5,7 @@ * PaX/grsecurity. */ #include <linux/refcount.h> +#include <asm/bug.h> /* * This is the first portion of the refcount error handling, which lives in diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h index 4253bca99989..9c0d4b588e3f 100644 --- a/arch/x86/include/asm/trace/hyperv.h +++ b/arch/x86/include/asm/trace/hyperv.h @@ -28,6 +28,21 @@ TRACE_EVENT(hyperv_mmu_flush_tlb_others, __entry->addr, __entry->end) ); +TRACE_EVENT(hyperv_send_ipi_mask, + TP_PROTO(const struct cpumask *cpus, + int vector), + TP_ARGS(cpus, vector), + TP_STRUCT__entry( + __field(unsigned int, ncpus) + __field(int, vector) + ), + TP_fast_assign(__entry->ncpus = cpumask_weight(cpus); + __entry->vector = vector; + ), + TP_printk("ncpus %d vector %x", + __entry->ncpus, __entry->vector) + ); + #endif /* CONFIG_HYPERV */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 62acb613114b..a9d637bc301d 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -52,7 +52,12 @@ copy_to_user_mcsafe(void *to, const void *from, unsigned len) unsigned long ret; __uaccess_begin(); - ret = memcpy_mcsafe(to, from, len); + /* + * Note, __memcpy_mcsafe() is explicitly used since it can + * handle exceptions / faults. memcpy_mcsafe() may fall back to + * memcpy() which lacks this handling. + */ + ret = __memcpy_mcsafe(to, from, len); __uaccess_end(); return ret; } diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index bae46fc6b9de..0bcdb1279361 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -26,7 +26,7 @@ * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL +.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0 #ifdef CONFIG_STACK_VALIDATION .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints @@ -35,12 +35,14 @@ .short \sp_offset .byte \sp_reg .byte \type + .byte \end + .balign 4 .popsection #endif .endm .macro UNWIND_HINT_EMPTY - UNWIND_HINT sp_reg=ORC_REG_UNDEFINED + UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1 .endm .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0 @@ -86,19 +88,21 @@ #else /* !__ASSEMBLY__ */ -#define UNWIND_HINT(sp_reg, sp_offset, type) \ +#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ ".long 987b - .\n\t" \ - ".short " __stringify(sp_offset) "\n\t" \ + ".short " __stringify(sp_offset) "\n\t" \ ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ + ".byte " __stringify(end) "\n\t" \ + ".balign 4 \n\t" \ ".popsection\n\t" -#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE) +#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0) -#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE) +#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0) #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2aabd4cb0e3f..07fa222f0c52 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -573,6 +573,9 @@ static u32 skx_deadline_rev(void) case 0x04: return 0x02000014; } + if (boot_cpu_data.x86_stepping > 4) + return 0; + return ~0U; } @@ -937,7 +940,7 @@ static int __init calibrate_APIC_clock(void) if (levt->features & CLOCK_EVT_FEAT_DUMMY) { pr_warning("APIC timer disabled due to verification failure\n"); - return -1; + return -1; } return 0; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 35aaee4fc028..0954315842c0 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -218,7 +218,8 @@ static int reserve_irq_vector(struct irq_data *irqd) return 0; } -static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest) +static int +assign_vector_locked(struct irq_data *irqd, const struct cpumask *dest) { struct apic_chip_data *apicd = apic_chip_data(irqd); bool resvd = apicd->has_reserved; @@ -245,22 +246,12 @@ static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest) return -EBUSY; vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu); - if (vector > 0) - apic_update_vector(irqd, vector, cpu); trace_vector_alloc(irqd->irq, vector, resvd, vector); - return vector; -} - -static int assign_vector_locked(struct irq_data *irqd, - const struct cpumask *dest) -{ - struct apic_chip_data *apicd = apic_chip_data(irqd); - int vector = allocate_vector(irqd, dest); - if (vector < 0) return vector; + apic_update_vector(irqd, vector, cpu); + apic_update_irq_cfg(irqd, vector, cpu); - apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu); return 0; } @@ -433,7 +424,7 @@ static int activate_managed(struct irq_data *irqd) pr_err("Managed startup irq %u, no vector available\n", irqd->irq); } - return ret; + return ret; } static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d492752f79e1..391f358ebb4c 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -394,10 +394,10 @@ extern int uv_hub_info_version(void) EXPORT_SYMBOL(uv_hub_info_version); /* Default UV memory block size is 2GB */ -static unsigned long mem_block_size = (2UL << 30); +static unsigned long mem_block_size __initdata = (2UL << 30); /* Kernel parameter to specify UV mem block size */ -static int parse_mem_block_size(char *ptr) +static int __init parse_mem_block_size(char *ptr) { unsigned long size = memparse(ptr, NULL); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 5d0de79fdab0..ec00d1ff5098 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -240,6 +240,7 @@ #include <asm/olpc.h> #include <asm/paravirt.h> #include <asm/reboot.h> +#include <asm/nospec-branch.h> #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT) extern int (*console_blank_hook)(int); @@ -614,11 +615,13 @@ static long __apm_bios_call(void *_call) gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); + firmware_restrict_branch_speculation_start(); APM_DO_SAVE_SEGS; apm_bios_call_asm(call->func, call->ebx, call->ecx, &call->eax, &call->ebx, &call->ecx, &call->edx, &call->esi); APM_DO_RESTORE_SEGS; + firmware_restrict_branch_speculation_end(); apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); @@ -690,10 +693,12 @@ static long __apm_bios_call_simple(void *_call) gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); + firmware_restrict_branch_speculation_start(); APM_DO_SAVE_SEGS; error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx, &call->eax); APM_DO_RESTORE_SEGS; + firmware_restrict_branch_speculation_end(); apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 7a40196967cb..347137e80bf5 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -35,7 +35,9 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o -obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o +obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o +obj-$(CONFIG_INTEL_RDT) += intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o +CFLAGS_intel_rdt_pseudo_lock.o = -I$(src) obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index eb75564f2d25..c050cd6066af 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -465,14 +465,17 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) #define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 #define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 #define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 +#define x86_VMX_FEATURE_EPT_CAP_AD 0x00200000 u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; + u32 msr_vpid_cap, msr_ept_cap; clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW); clear_cpu_cap(c, X86_FEATURE_VNMI); clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); clear_cpu_cap(c, X86_FEATURE_EPT); clear_cpu_cap(c, X86_FEATURE_VPID); + clear_cpu_cap(c, X86_FEATURE_EPT_AD); rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); msr_ctl = vmx_msr_high | vmx_msr_low; @@ -487,8 +490,13 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) + if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) { set_cpu_cap(c, X86_FEATURE_EPT); + rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, + msr_ept_cap, msr_vpid_cap); + if (msr_ept_cap & x86_VMX_FEATURE_EPT_CAP_AD) + set_cpu_cap(c, X86_FEATURE_EPT_AD); + } if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) set_cpu_cap(c, X86_FEATURE_VPID); } diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index ec4754f81cbd..abb71ac70443 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -859,6 +859,8 @@ static __init bool get_rdt_resources(void) return (rdt_mon_capable || rdt_alloc_capable); } +static enum cpuhp_state rdt_online; + static int __init intel_rdt_late_init(void) { struct rdt_resource *r; @@ -880,6 +882,7 @@ static int __init intel_rdt_late_init(void) cpuhp_remove_state(state); return ret; } + rdt_online = state; for_each_alloc_capable_rdt_resource(r) pr_info("Intel RDT %s allocation detected\n", r->name); @@ -891,3 +894,11 @@ static int __init intel_rdt_late_init(void) } late_initcall(intel_rdt_late_init); + +static void __exit intel_rdt_exit(void) +{ + cpuhp_remove_state(rdt_online); + rdtgroup_exit(); +} + +__exitcall(intel_rdt_exit); diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 39752825e376..4e588f36228f 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -81,6 +81,34 @@ enum rdt_group_type { }; /** + * enum rdtgrp_mode - Mode of a RDT resource group + * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations + * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed + * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking + * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations + * allowed AND the allocations are Cache Pseudo-Locked + * + * The mode of a resource group enables control over the allowed overlap + * between allocations associated with different resource groups (classes + * of service). User is able to modify the mode of a resource group by + * writing to the "mode" resctrl file associated with the resource group. + * + * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by + * writing the appropriate text to the "mode" file. A resource group enters + * "pseudo-locked" mode after the schemata is written while the resource + * group is in "pseudo-locksetup" mode. + */ +enum rdtgrp_mode { + RDT_MODE_SHAREABLE = 0, + RDT_MODE_EXCLUSIVE, + RDT_MODE_PSEUDO_LOCKSETUP, + RDT_MODE_PSEUDO_LOCKED, + + /* Must be last */ + RDT_NUM_MODES, +}; + +/** * struct mongroup - store mon group's data in resctrl fs. * @mon_data_kn kernlfs node for the mon_data directory * @parent: parent rdtgrp @@ -95,6 +123,43 @@ struct mongroup { }; /** + * struct pseudo_lock_region - pseudo-lock region information + * @r: RDT resource to which this pseudo-locked region + * belongs + * @d: RDT domain to which this pseudo-locked region + * belongs + * @cbm: bitmask of the pseudo-locked region + * @lock_thread_wq: waitqueue used to wait on the pseudo-locking thread + * completion + * @thread_done: variable used by waitqueue to test if pseudo-locking + * thread completed + * @cpu: core associated with the cache on which the setup code + * will be run + * @line_size: size of the cache lines + * @size: size of pseudo-locked region in bytes + * @kmem: the kernel memory associated with pseudo-locked region + * @minor: minor number of character device associated with this + * region + * @debugfs_dir: pointer to this region's directory in the debugfs + * filesystem + * @pm_reqs: Power management QoS requests related to this region + */ +struct pseudo_lock_region { + struct rdt_resource *r; + struct rdt_domain *d; + u32 cbm; + wait_queue_head_t lock_thread_wq; + int thread_done; + int cpu; + unsigned int line_size; + unsigned int size; + void *kmem; + unsigned int minor; + struct dentry *debugfs_dir; + struct list_head pm_reqs; +}; + +/** * struct rdtgroup - store rdtgroup's data in resctrl file system. * @kn: kernfs node * @rdtgroup_list: linked list for all rdtgroups @@ -106,16 +171,20 @@ struct mongroup { * @type: indicates type of this rdtgroup - either * monitor only or ctrl_mon group * @mon: mongroup related data + * @mode: mode of resource group + * @plr: pseudo-locked region */ struct rdtgroup { - struct kernfs_node *kn; - struct list_head rdtgroup_list; - u32 closid; - struct cpumask cpu_mask; - int flags; - atomic_t waitcount; - enum rdt_group_type type; - struct mongroup mon; + struct kernfs_node *kn; + struct list_head rdtgroup_list; + u32 closid; + struct cpumask cpu_mask; + int flags; + atomic_t waitcount; + enum rdt_group_type type; + struct mongroup mon; + enum rdtgrp_mode mode; + struct pseudo_lock_region *plr; }; /* rdtgroup.flags */ @@ -148,6 +217,7 @@ extern struct list_head rdt_all_groups; extern int max_name_width, max_data_width; int __init rdtgroup_init(void); +void __exit rdtgroup_exit(void); /** * struct rftype - describe each file in the resctrl file system @@ -216,22 +286,24 @@ struct mbm_state { * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps * @new_ctrl: new ctrl value to be loaded * @have_new_ctrl: did user provide new_ctrl for this domain + * @plr: pseudo-locked region (if any) associated with domain */ struct rdt_domain { - struct list_head list; - int id; - struct cpumask cpu_mask; - unsigned long *rmid_busy_llc; - struct mbm_state *mbm_total; - struct mbm_state *mbm_local; - struct delayed_work mbm_over; - struct delayed_work cqm_limbo; - int mbm_work_cpu; - int cqm_work_cpu; - u32 *ctrl_val; - u32 *mbps_val; - u32 new_ctrl; - bool have_new_ctrl; + struct list_head list; + int id; + struct cpumask cpu_mask; + unsigned long *rmid_busy_llc; + struct mbm_state *mbm_total; + struct mbm_state *mbm_local; + struct delayed_work mbm_over; + struct delayed_work cqm_limbo; + int mbm_work_cpu; + int cqm_work_cpu; + u32 *ctrl_val; + u32 *mbps_val; + u32 new_ctrl; + bool have_new_ctrl; + struct pseudo_lock_region *plr; }; /** @@ -351,7 +423,7 @@ struct rdt_resource { struct rdt_cache cache; struct rdt_membw membw; const char *format_str; - int (*parse_ctrlval) (char *buf, struct rdt_resource *r, + int (*parse_ctrlval) (void *data, struct rdt_resource *r, struct rdt_domain *d); struct list_head evt_list; int num_rmid; @@ -359,8 +431,8 @@ struct rdt_resource { unsigned long fflags; }; -int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d); +int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -368,7 +440,7 @@ extern struct rdt_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); -int __init rdtgroup_init(void); +extern struct dentry *debugfs_resctrl; enum { RDT_RESOURCE_L3, @@ -439,13 +511,32 @@ void rdt_last_cmd_printf(const char *fmt, ...); void rdt_ctrl_update(void *arg); struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); void rdtgroup_kn_unlock(struct kernfs_node *kn); +int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name); +int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, + umode_t mask); struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, struct list_head **pos); ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + u32 _cbm, int closid, bool exclusive); +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, + u32 cbm); +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); +int rdtgroup_tasks_assigned(struct rdtgroup *r); +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm); +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d); +int rdt_pseudo_lock_init(void); +void rdt_pseudo_lock_release(void); +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); +int update_domains(struct rdt_resource *r, int closid); +void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 116d57b248d3..af358ca05160 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -64,9 +64,10 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d) { unsigned long data; + char *buf = _buf; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); @@ -87,7 +88,7 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). * Additionally Haswell requires at least two bits set. */ -static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) +static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) { unsigned long first_bit, zero_bit, val; unsigned int cbm_len = r->cache.cbm_len; @@ -122,22 +123,64 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } +struct rdt_cbm_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + /* * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) { - unsigned long data; + struct rdt_cbm_parse_data *data = _data; + struct rdtgroup *rdtgrp = data->rdtgrp; + u32 cbm_val; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; } - if(!cbm_validate(buf, &data, r)) + /* + * Cannot set up more than one pseudo-locked region in a cache + * hierarchy. + */ + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + rdtgroup_pseudo_locked_in_hierarchy(d)) { + rdt_last_cmd_printf("pseudo-locked region in hierarchy\n"); return -EINVAL; - d->new_ctrl = data; + } + + if (!cbm_validate(data->buf, &cbm_val, r)) + return -EINVAL; + + if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE || + rdtgrp->mode == RDT_MODE_SHAREABLE) && + rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) { + rdt_last_cmd_printf("CBM overlaps with pseudo-locked region\n"); + return -EINVAL; + } + + /* + * The CBM may not overlap with the CBM of another closid if + * either is exclusive. + */ + if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) { + rdt_last_cmd_printf("overlaps with exclusive group\n"); + return -EINVAL; + } + + if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) { + if (rdtgrp->mode == RDT_MODE_EXCLUSIVE || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + rdt_last_cmd_printf("overlaps with other group\n"); + return -EINVAL; + } + } + + d->new_ctrl = cbm_val; d->have_new_ctrl = true; return 0; @@ -149,8 +192,10 @@ int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) * separated by ";". The "id" is in decimal, and must match one of * the "id"s for this resource. */ -static int parse_line(char *line, struct rdt_resource *r) +static int parse_line(char *line, struct rdt_resource *r, + struct rdtgroup *rdtgrp) { + struct rdt_cbm_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; unsigned long dom_id; @@ -167,15 +212,32 @@ next: dom = strim(dom); list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { - if (r->parse_ctrlval(dom, r, d)) + data.buf = dom; + data.rdtgrp = rdtgrp; + if (r->parse_ctrlval(&data, r, d)) return -EINVAL; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * In pseudo-locking setup mode and just + * parsed a valid CBM that should be + * pseudo-locked. Only one locked region per + * resource group and domain so just do + * the required initialization for single + * region and return. + */ + rdtgrp->plr->r = r; + rdtgrp->plr->d = d; + rdtgrp->plr->cbm = d->new_ctrl; + d->plr = rdtgrp->plr; + return 0; + } goto next; } } return -EINVAL; } -static int update_domains(struct rdt_resource *r, int closid) +int update_domains(struct rdt_resource *r, int closid) { struct msr_param msr_param; cpumask_var_t cpu_mask; @@ -220,13 +282,14 @@ done: return 0; } -static int rdtgroup_parse_resource(char *resname, char *tok, int closid) +static int rdtgroup_parse_resource(char *resname, char *tok, + struct rdtgroup *rdtgrp) { struct rdt_resource *r; for_each_alloc_enabled_rdt_resource(r) { - if (!strcmp(resname, r->name) && closid < r->num_closid) - return parse_line(tok, r); + if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid) + return parse_line(tok, r, rdtgrp); } rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname); return -EINVAL; @@ -239,7 +302,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, struct rdt_domain *dom; struct rdt_resource *r; char *tok, *resname; - int closid, ret = 0; + int ret = 0; /* Valid input requires a trailing newline */ if (nbytes == 0 || buf[nbytes - 1] != '\n') @@ -253,7 +316,15 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, } rdt_last_cmd_clear(); - closid = rdtgrp->closid; + /* + * No changes to pseudo-locked region allowed. It has to be removed + * and re-created instead. + */ + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + ret = -EINVAL; + rdt_last_cmd_puts("resource group is pseudo-locked\n"); + goto out; + } for_each_alloc_enabled_rdt_resource(r) { list_for_each_entry(dom, &r->domains, list) @@ -272,17 +343,27 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, ret = -EINVAL; goto out; } - ret = rdtgroup_parse_resource(resname, tok, closid); + ret = rdtgroup_parse_resource(resname, tok, rdtgrp); if (ret) goto out; } for_each_alloc_enabled_rdt_resource(r) { - ret = update_domains(r, closid); + ret = update_domains(r, rdtgrp->closid); if (ret) goto out; } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * If pseudo-locking fails we keep the resource group in + * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service + * active and updated for just the domain the pseudo-locked + * region was requested for. + */ + ret = rdtgroup_pseudo_lock_create(rdtgrp); + } + out: rdtgroup_kn_unlock(of->kn); return ret ?: nbytes; @@ -318,10 +399,18 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - closid = rdtgrp->closid; - for_each_alloc_enabled_rdt_resource(r) { - if (closid < r->num_closid) - show_doms(s, r, closid); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + for_each_alloc_enabled_rdt_resource(r) + seq_printf(s, "%s:uninitialized\n", r->name); + } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name, + rdtgrp->plr->d->id, rdtgrp->plr->cbm); + } else { + closid = rdtgrp->closid; + for_each_alloc_enabled_rdt_resource(r) { + if (closid < r->num_closid) + show_doms(s, r, closid); + } } } else { ret = -ENOENT; diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c new file mode 100644 index 000000000000..40f3903ae5d9 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -0,0 +1,1522 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Resource Director Technology (RDT) + * + * Pseudo-locking support built on top of Cache Allocation Technology (CAT) + * + * Copyright (C) 2018 Intel Corporation + * + * Author: Reinette Chatre <reinette.chatre@intel.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cacheinfo.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/debugfs.h> +#include <linux/kthread.h> +#include <linux/mman.h> +#include <linux/pm_qos.h> +#include <linux/slab.h> +#include <linux/uaccess.h> + +#include <asm/cacheflush.h> +#include <asm/intel-family.h> +#include <asm/intel_rdt_sched.h> +#include <asm/perf_event.h> + +#include "intel_rdt.h" + +#define CREATE_TRACE_POINTS +#include "intel_rdt_pseudo_lock_event.h" + +/* + * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware + * prefetcher state. Details about this register can be found in the MSR + * tables for specific platforms found in Intel's SDM. + */ +#define MSR_MISC_FEATURE_CONTROL 0x000001a4 + +/* + * The bits needed to disable hardware prefetching varies based on the + * platform. During initialization we will discover which bits to use. + */ +static u64 prefetch_disable_bits; + +/* + * Major number assigned to and shared by all devices exposing + * pseudo-locked regions. + */ +static unsigned int pseudo_lock_major; +static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0); +static struct class *pseudo_lock_class; + +/** + * get_prefetch_disable_bits - prefetch disable bits of supported platforms + * + * Capture the list of platforms that have been validated to support + * pseudo-locking. This includes testing to ensure pseudo-locked regions + * with low cache miss rates can be created under variety of load conditions + * as well as that these pseudo-locked regions can maintain their low cache + * miss rates under variety of load conditions for significant lengths of time. + * + * After a platform has been validated to support pseudo-locking its + * hardware prefetch disable bits are included here as they are documented + * in the SDM. + * + * When adding a platform here also add support for its cache events to + * measure_cycles_perf_fn() + * + * Return: + * If platform is supported, the bits to disable hardware prefetchers, 0 + * if platform is not supported. + */ +static u64 get_prefetch_disable_bits(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return 0; + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_BROADWELL_X: + /* + * SDM defines bits of MSR_MISC_FEATURE_CONTROL register + * as: + * 0 L2 Hardware Prefetcher Disable (R/W) + * 1 L2 Adjacent Cache Line Prefetcher Disable (R/W) + * 2 DCU Hardware Prefetcher Disable (R/W) + * 3 DCU IP Prefetcher Disable (R/W) + * 63:4 Reserved + */ + return 0xF; + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_GEMINI_LAKE: + /* + * SDM defines bits of MSR_MISC_FEATURE_CONTROL register + * as: + * 0 L2 Hardware Prefetcher Disable (R/W) + * 1 Reserved + * 2 DCU Hardware Prefetcher Disable (R/W) + * 63:3 Reserved + */ + return 0x5; + } + + return 0; +} + +/* + * Helper to write 64bit value to MSR without tracing. Used when + * use of the cache should be restricted and use of registers used + * for local variables avoided. + */ +static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val) +{ + __wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32)); +} + +/** + * pseudo_lock_minor_get - Obtain available minor number + * @minor: Pointer to where new minor number will be stored + * + * A bitmask is used to track available minor numbers. Here the next free + * minor number is marked as unavailable and returned. + * + * Return: 0 on success, <0 on failure. + */ +static int pseudo_lock_minor_get(unsigned int *minor) +{ + unsigned long first_bit; + + first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS); + + if (first_bit == MINORBITS) + return -ENOSPC; + + __clear_bit(first_bit, &pseudo_lock_minor_avail); + *minor = first_bit; + + return 0; +} + +/** + * pseudo_lock_minor_release - Return minor number to available + * @minor: The minor number made available + */ +static void pseudo_lock_minor_release(unsigned int minor) +{ + __set_bit(minor, &pseudo_lock_minor_avail); +} + +/** + * region_find_by_minor - Locate a pseudo-lock region by inode minor number + * @minor: The minor number of the device representing pseudo-locked region + * + * When the character device is accessed we need to determine which + * pseudo-locked region it belongs to. This is done by matching the minor + * number of the device to the pseudo-locked region it belongs. + * + * Minor numbers are assigned at the time a pseudo-locked region is associated + * with a cache instance. + * + * Return: On success return pointer to resource group owning the pseudo-locked + * region, NULL on failure. + */ +static struct rdtgroup *region_find_by_minor(unsigned int minor) +{ + struct rdtgroup *rdtgrp, *rdtgrp_match = NULL; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->plr && rdtgrp->plr->minor == minor) { + rdtgrp_match = rdtgrp; + break; + } + } + return rdtgrp_match; +} + +/** + * pseudo_lock_pm_req - A power management QoS request list entry + * @list: Entry within the @pm_reqs list for a pseudo-locked region + * @req: PM QoS request + */ +struct pseudo_lock_pm_req { + struct list_head list; + struct dev_pm_qos_request req; +}; + +static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr) +{ + struct pseudo_lock_pm_req *pm_req, *next; + + list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) { + dev_pm_qos_remove_request(&pm_req->req); + list_del(&pm_req->list); + kfree(pm_req); + } +} + +/** + * pseudo_lock_cstates_constrain - Restrict cores from entering C6 + * + * To prevent the cache from being affected by power management entering + * C6 has to be avoided. This is accomplished by requesting a latency + * requirement lower than lowest C6 exit latency of all supported + * platforms as found in the cpuidle state tables in the intel_idle driver. + * At this time it is possible to do so with a single latency requirement + * for all supported platforms. + * + * Since Goldmont is supported, which is affected by X86_BUG_MONITOR, + * the ACPI latencies need to be considered while keeping in mind that C2 + * may be set to map to deeper sleep states. In this case the latency + * requirement needs to prevent entering C2 also. + */ +static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr) +{ + struct pseudo_lock_pm_req *pm_req; + int cpu; + int ret; + + for_each_cpu(cpu, &plr->d->cpu_mask) { + pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL); + if (!pm_req) { + rdt_last_cmd_puts("fail allocating mem for PM QoS\n"); + ret = -ENOMEM; + goto out_err; + } + ret = dev_pm_qos_add_request(get_cpu_device(cpu), + &pm_req->req, + DEV_PM_QOS_RESUME_LATENCY, + 30); + if (ret < 0) { + rdt_last_cmd_printf("fail to add latency req cpu%d\n", + cpu); + kfree(pm_req); + ret = -1; + goto out_err; + } + list_add(&pm_req->list, &plr->pm_reqs); + } + + return 0; + +out_err: + pseudo_lock_cstates_relax(plr); + return ret; +} + +/** + * pseudo_lock_region_clear - Reset pseudo-lock region data + * @plr: pseudo-lock region + * + * All content of the pseudo-locked region is reset - any memory allocated + * freed. + * + * Return: void + */ +static void pseudo_lock_region_clear(struct pseudo_lock_region *plr) +{ + plr->size = 0; + plr->line_size = 0; + kfree(plr->kmem); + plr->kmem = NULL; + plr->r = NULL; + if (plr->d) + plr->d->plr = NULL; + plr->d = NULL; + plr->cbm = 0; + plr->debugfs_dir = NULL; +} + +/** + * pseudo_lock_region_init - Initialize pseudo-lock region information + * @plr: pseudo-lock region + * + * Called after user provided a schemata to be pseudo-locked. From the + * schemata the &struct pseudo_lock_region is on entry already initialized + * with the resource, domain, and capacity bitmask. Here the information + * required for pseudo-locking is deduced from this data and &struct + * pseudo_lock_region initialized further. This information includes: + * - size in bytes of the region to be pseudo-locked + * - cache line size to know the stride with which data needs to be accessed + * to be pseudo-locked + * - a cpu associated with the cache instance on which the pseudo-locking + * flow can be executed + * + * Return: 0 on success, <0 on failure. Descriptive error will be written + * to last_cmd_status buffer. + */ +static int pseudo_lock_region_init(struct pseudo_lock_region *plr) +{ + struct cpu_cacheinfo *ci; + int ret; + int i; + + /* Pick the first cpu we find that is associated with the cache. */ + plr->cpu = cpumask_first(&plr->d->cpu_mask); + + if (!cpu_online(plr->cpu)) { + rdt_last_cmd_printf("cpu %u associated with cache not online\n", + plr->cpu); + ret = -ENODEV; + goto out_region; + } + + ci = get_cpu_cacheinfo(plr->cpu); + + plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm); + + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == plr->r->cache_level) { + plr->line_size = ci->info_list[i].coherency_line_size; + return 0; + } + } + + ret = -1; + rdt_last_cmd_puts("unable to determine cache line size\n"); +out_region: + pseudo_lock_region_clear(plr); + return ret; +} + +/** + * pseudo_lock_init - Initialize a pseudo-lock region + * @rdtgrp: resource group to which new pseudo-locked region will belong + * + * A pseudo-locked region is associated with a resource group. When this + * association is created the pseudo-locked region is initialized. The + * details of the pseudo-locked region are not known at this time so only + * allocation is done and association established. + * + * Return: 0 on success, <0 on failure + */ +static int pseudo_lock_init(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr; + + plr = kzalloc(sizeof(*plr), GFP_KERNEL); + if (!plr) + return -ENOMEM; + + init_waitqueue_head(&plr->lock_thread_wq); + INIT_LIST_HEAD(&plr->pm_reqs); + rdtgrp->plr = plr; + return 0; +} + +/** + * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked + * @plr: pseudo-lock region + * + * Initialize the details required to set up the pseudo-locked region and + * allocate the contiguous memory that will be pseudo-locked to the cache. + * + * Return: 0 on success, <0 on failure. Descriptive error will be written + * to last_cmd_status buffer. + */ +static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr) +{ + int ret; + + ret = pseudo_lock_region_init(plr); + if (ret < 0) + return ret; + + /* + * We do not yet support contiguous regions larger than + * KMALLOC_MAX_SIZE. + */ + if (plr->size > KMALLOC_MAX_SIZE) { + rdt_last_cmd_puts("requested region exceeds maximum size\n"); + ret = -E2BIG; + goto out_region; + } + + plr->kmem = kzalloc(plr->size, GFP_KERNEL); + if (!plr->kmem) { + rdt_last_cmd_puts("unable to allocate memory\n"); + ret = -ENOMEM; + goto out_region; + } + + ret = 0; + goto out; +out_region: + pseudo_lock_region_clear(plr); +out: + return ret; +} + +/** + * pseudo_lock_free - Free a pseudo-locked region + * @rdtgrp: resource group to which pseudo-locked region belonged + * + * The pseudo-locked region's resources have already been released, or not + * yet created at this point. Now it can be freed and disassociated from the + * resource group. + * + * Return: void + */ +static void pseudo_lock_free(struct rdtgroup *rdtgrp) +{ + pseudo_lock_region_clear(rdtgrp->plr); + kfree(rdtgrp->plr); + rdtgrp->plr = NULL; +} + +/** + * pseudo_lock_fn - Load kernel memory into cache + * @_rdtgrp: resource group to which pseudo-lock region belongs + * + * This is the core pseudo-locking flow. + * + * First we ensure that the kernel memory cannot be found in the cache. + * Then, while taking care that there will be as little interference as + * possible, the memory to be loaded is accessed while core is running + * with class of service set to the bitmask of the pseudo-locked region. + * After this is complete no future CAT allocations will be allowed to + * overlap with this bitmask. + * + * Local register variables are utilized to ensure that the memory region + * to be locked is the only memory access made during the critical locking + * loop. + * + * Return: 0. Waiter on waitqueue will be woken on completion. + */ +static int pseudo_lock_fn(void *_rdtgrp) +{ + struct rdtgroup *rdtgrp = _rdtgrp; + struct pseudo_lock_region *plr = rdtgrp->plr; + u32 rmid_p, closid_p; + unsigned long i; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use a regular + * variable to ensure we always use a valid pointer, but the cost + * is that this variable will enter the cache through evicting the + * memory we are trying to lock into the cache. Thus expect lower + * pseudo-locking success rate when KASAN is active. + */ + unsigned int line_size; + unsigned int size; + void *mem_r; +#else + register unsigned int line_size asm("esi"); + register unsigned int size asm("edi"); +#ifdef CONFIG_X86_64 + register void *mem_r asm("rbx"); +#else + register void *mem_r asm("ebx"); +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KASAN */ + + /* + * Make sure none of the allocated memory is cached. If it is we + * will get a cache hit in below loop from outside of pseudo-locked + * region. + * wbinvd (as opposed to clflush/clflushopt) is required to + * increase likelihood that allocated cache portion will be filled + * with associated memory. + */ + native_wbinvd(); + + /* + * Always called with interrupts enabled. By disabling interrupts + * ensure that we will not be preempted during this critical section. + */ + local_irq_disable(); + + /* + * Call wrmsr and rdmsr as directly as possible to avoid tracing + * clobbering local register variables or affecting cache accesses. + * + * Disable the hardware prefetcher so that when the end of the memory + * being pseudo-locked is reached the hardware will not read beyond + * the buffer and evict pseudo-locked memory read earlier from the + * cache. + */ + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + closid_p = this_cpu_read(pqr_state.cur_closid); + rmid_p = this_cpu_read(pqr_state.cur_rmid); + mem_r = plr->kmem; + size = plr->size; + line_size = plr->line_size; + /* + * Critical section begin: start by writing the closid associated + * with the capacity bitmask of the cache region being + * pseudo-locked followed by reading of kernel memory to load it + * into the cache. + */ + __wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid); + /* + * Cache was flushed earlier. Now access kernel memory to read it + * into cache region associated with just activated plr->closid. + * Loop over data twice: + * - In first loop the cache region is shared with the page walker + * as it populates the paging structure caches (including TLB). + * - In the second loop the paging structure caches are used and + * cache region is populated with the memory being referenced. + */ + for (i = 0; i < size; i += PAGE_SIZE) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + for (i = 0; i < size; i += line_size) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Critical section end: restore closid with capacity bitmask that + * does not overlap with pseudo-locked region. + */ + __wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p); + + /* Re-enable the hardware prefetcher(s) */ + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/** + * rdtgroup_monitor_in_progress - Test if monitoring in progress + * @r: resource group being queried + * + * Return: 1 if monitor groups have been created for this resource + * group, 0 otherwise. + */ +static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp) +{ + return !list_empty(&rdtgrp->mon.crdtgrp_list); +} + +/** + * rdtgroup_locksetup_user_restrict - Restrict user access to group + * @rdtgrp: resource group needing access restricted + * + * A resource group used for cache pseudo-locking cannot have cpus or tasks + * assigned to it. This is communicated to the user by restricting access + * to all the files that can be used to make such changes. + * + * Permissions restored with rdtgroup_locksetup_user_restore() + * + * Return: 0 on success, <0 on failure. If a failure occurs during the + * restriction of access an attempt will be made to restore permissions but + * the state of the mode of these files will be uncertain when a failure + * occurs. + */ +static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp) +{ + int ret; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks"); + if (ret) + return ret; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus"); + if (ret) + goto err_tasks; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list"); + if (ret) + goto err_cpus; + + if (rdt_mon_capable) { + ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups"); + if (ret) + goto err_cpus_list; + } + + ret = 0; + goto out; + +err_cpus_list: + rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777); +err_cpus: + rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777); +err_tasks: + rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777); +out: + return ret; +} + +/** + * rdtgroup_locksetup_user_restore - Restore user access to group + * @rdtgrp: resource group needing access restored + * + * Restore all file access previously removed using + * rdtgroup_locksetup_user_restrict() + * + * Return: 0 on success, <0 on failure. If a failure occurs during the + * restoration of access an attempt will be made to restrict permissions + * again but the state of the mode of these files will be uncertain when + * a failure occurs. + */ +static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp) +{ + int ret; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777); + if (ret) + return ret; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777); + if (ret) + goto err_tasks; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777); + if (ret) + goto err_cpus; + + if (rdt_mon_capable) { + ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777); + if (ret) + goto err_cpus_list; + } + + ret = 0; + goto out; + +err_cpus_list: + rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list"); +err_cpus: + rdtgroup_kn_mode_restrict(rdtgrp, "cpus"); +err_tasks: + rdtgroup_kn_mode_restrict(rdtgrp, "tasks"); +out: + return ret; +} + +/** + * rdtgroup_locksetup_enter - Resource group enters locksetup mode + * @rdtgrp: resource group requested to enter locksetup mode + * + * A resource group enters locksetup mode to reflect that it would be used + * to represent a pseudo-locked region and is in the process of being set + * up to do so. A resource group used for a pseudo-locked region would + * lose the closid associated with it so we cannot allow it to have any + * tasks or cpus assigned nor permit tasks or cpus to be assigned in the + * future. Monitoring of a pseudo-locked region is not allowed either. + * + * The above and more restrictions on a pseudo-locked region are checked + * for and enforced before the resource group enters the locksetup mode. + * + * Returns: 0 if the resource group successfully entered locksetup mode, <0 + * on failure. On failure the last_cmd_status buffer is updated with text to + * communicate details of failure to the user. + */ +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) +{ + int ret; + + /* + * The default resource group can neither be removed nor lose the + * default closid associated with it. + */ + if (rdtgrp == &rdtgroup_default) { + rdt_last_cmd_puts("cannot pseudo-lock default group\n"); + return -EINVAL; + } + + /* + * Cache Pseudo-locking not supported when CDP is enabled. + * + * Some things to consider if you would like to enable this + * support (using L3 CDP as example): + * - When CDP is enabled two separate resources are exposed, + * L3DATA and L3CODE, but they are actually on the same cache. + * The implication for pseudo-locking is that if a + * pseudo-locked region is created on a domain of one + * resource (eg. L3CODE), then a pseudo-locked region cannot + * be created on that same domain of the other resource + * (eg. L3DATA). This is because the creation of a + * pseudo-locked region involves a call to wbinvd that will + * affect all cache allocations on particular domain. + * - Considering the previous, it may be possible to only + * expose one of the CDP resources to pseudo-locking and + * hide the other. For example, we could consider to only + * expose L3DATA and since the L3 cache is unified it is + * still possible to place instructions there are execute it. + * - If only one region is exposed to pseudo-locking we should + * still keep in mind that availability of a portion of cache + * for pseudo-locking should take into account both resources. + * Similarly, if a pseudo-locked region is created in one + * resource, the portion of cache used by it should be made + * unavailable to all future allocations from both resources. + */ + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled || + rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) { + rdt_last_cmd_puts("CDP enabled\n"); + return -EINVAL; + } + + /* + * Not knowing the bits to disable prefetching implies that this + * platform does not support Cache Pseudo-Locking. + */ + prefetch_disable_bits = get_prefetch_disable_bits(); + if (prefetch_disable_bits == 0) { + rdt_last_cmd_puts("pseudo-locking not supported\n"); + return -EINVAL; + } + + if (rdtgroup_monitor_in_progress(rdtgrp)) { + rdt_last_cmd_puts("monitoring in progress\n"); + return -EINVAL; + } + + if (rdtgroup_tasks_assigned(rdtgrp)) { + rdt_last_cmd_puts("tasks assigned to resource group\n"); + return -EINVAL; + } + + if (!cpumask_empty(&rdtgrp->cpu_mask)) { + rdt_last_cmd_puts("CPUs assigned to resource group\n"); + return -EINVAL; + } + + if (rdtgroup_locksetup_user_restrict(rdtgrp)) { + rdt_last_cmd_puts("unable to modify resctrl permissions\n"); + return -EIO; + } + + ret = pseudo_lock_init(rdtgrp); + if (ret) { + rdt_last_cmd_puts("unable to init pseudo-lock region\n"); + goto out_release; + } + + /* + * If this system is capable of monitoring a rmid would have been + * allocated when the control group was created. This is not needed + * anymore when this group would be used for pseudo-locking. This + * is safe to call on platforms not capable of monitoring. + */ + free_rmid(rdtgrp->mon.rmid); + + ret = 0; + goto out; + +out_release: + rdtgroup_locksetup_user_restore(rdtgrp); +out: + return ret; +} + +/** + * rdtgroup_locksetup_exit - resource group exist locksetup mode + * @rdtgrp: resource group + * + * When a resource group exits locksetup mode the earlier restrictions are + * lifted. + * + * Return: 0 on success, <0 on failure + */ +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) +{ + int ret; + + if (rdt_mon_capable) { + ret = alloc_rmid(); + if (ret < 0) { + rdt_last_cmd_puts("out of RMIDs\n"); + return ret; + } + rdtgrp->mon.rmid = ret; + } + + ret = rdtgroup_locksetup_user_restore(rdtgrp); + if (ret) { + free_rmid(rdtgrp->mon.rmid); + return ret; + } + + pseudo_lock_free(rdtgrp); + return 0; +} + +/** + * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked + * @d: RDT domain + * @_cbm: CBM to test + * + * @d represents a cache instance and @_cbm a capacity bitmask that is + * considered for it. Determine if @_cbm overlaps with any existing + * pseudo-locked region on @d. + * + * Return: true if @_cbm overlaps with pseudo-locked region on @d, false + * otherwise. + */ +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm) +{ + unsigned long *cbm = (unsigned long *)&_cbm; + unsigned long *cbm_b; + unsigned int cbm_len; + + if (d->plr) { + cbm_len = d->plr->r->cache.cbm_len; + cbm_b = (unsigned long *)&d->plr->cbm; + if (bitmap_intersects(cbm, cbm_b, cbm_len)) + return true; + } + return false; +} + +/** + * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy + * @d: RDT domain under test + * + * The setup of a pseudo-locked region affects all cache instances within + * the hierarchy of the region. It is thus essential to know if any + * pseudo-locked regions exist within a cache hierarchy to prevent any + * attempts to create new pseudo-locked regions in the same hierarchy. + * + * Return: true if a pseudo-locked region exists in the hierarchy of @d or + * if it is not possible to test due to memory allocation issue, + * false otherwise. + */ +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) +{ + cpumask_var_t cpu_with_psl; + struct rdt_resource *r; + struct rdt_domain *d_i; + bool ret = false; + + if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL)) + return true; + + /* + * First determine which cpus have pseudo-locked regions + * associated with them. + */ + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d_i, &r->domains, list) { + if (d_i->plr) + cpumask_or(cpu_with_psl, cpu_with_psl, + &d_i->cpu_mask); + } + } + + /* + * Next test if new pseudo-locked region would intersect with + * existing region. + */ + if (cpumask_intersects(&d->cpu_mask, cpu_with_psl)) + ret = true; + + free_cpumask_var(cpu_with_psl); + return ret; +} + +/** + * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory + * @_plr: pseudo-lock region to measure + * + * There is no deterministic way to test if a memory region is cached. One + * way is to measure how long it takes to read the memory, the speed of + * access is a good way to learn how close to the cpu the data was. Even + * more, if the prefetcher is disabled and the memory is read at a stride + * of half the cache line, then a cache miss will be easy to spot since the + * read of the first half would be significantly slower than the read of + * the second half. + * + * Return: 0. Waiter on waitqueue will be woken on completion. + */ +static int measure_cycles_lat_fn(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + unsigned long i; + u64 start, end; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use a regular + * variable to ensure we always use a valid pointer to access memory. + * The cost is that accessing this pointer, which could be in + * cache, will be included in the measurement of memory read latency. + */ + void *mem_r; +#else +#ifdef CONFIG_X86_64 + register void *mem_r asm("rbx"); +#else + register void *mem_r asm("ebx"); +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KASAN */ + + local_irq_disable(); + /* + * The wrmsr call may be reordered with the assignment below it. + * Call wrmsr as directly as possible to avoid tracing clobbering + * local register variable used for memory pointer. + */ + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + mem_r = plr->kmem; + /* + * Dummy execute of the time measurement to load the needed + * instructions into the L1 instruction cache. + */ + start = rdtsc_ordered(); + for (i = 0; i < plr->size; i += 32) { + start = rdtsc_ordered(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + end = rdtsc_ordered(); + trace_pseudo_lock_mem_latency((u32)(end - start)); + } + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +static int measure_cycles_perf_fn(void *_plr) +{ + unsigned long long l3_hits = 0, l3_miss = 0; + u64 l3_hit_bits = 0, l3_miss_bits = 0; + struct pseudo_lock_region *plr = _plr; + unsigned long long l2_hits, l2_miss; + u64 l2_hit_bits, l2_miss_bits; + unsigned long i; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use regular variables + * at the cost of including cache access latency to these variables + * in the measurements. + */ + unsigned int line_size; + unsigned int size; + void *mem_r; +#else + register unsigned int line_size asm("esi"); + register unsigned int size asm("edi"); +#ifdef CONFIG_X86_64 + register void *mem_r asm("rbx"); +#else + register void *mem_r asm("ebx"); +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KASAN */ + + /* + * Non-architectural event for the Goldmont Microarchitecture + * from Intel x86 Architecture Software Developer Manual (SDM): + * MEM_LOAD_UOPS_RETIRED D1H (event number) + * Umask values: + * L1_HIT 01H + * L2_HIT 02H + * L1_MISS 08H + * L2_MISS 10H + * + * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event + * has two "no fix" errata associated with it: BDM35 and BDM100. On + * this platform we use the following events instead: + * L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/) + * REFERENCES FFH + * MISS 3FH + * LONGEST_LAT_CACHE 2EH (Documented in SDM) + * REFERENCE 4FH + * MISS 41H + */ + + /* + * Start by setting flags for IA32_PERFEVTSELx: + * OS (Operating system mode) 0x2 + * INT (APIC interrupt enable) 0x10 + * EN (Enable counter) 0x40 + * + * Then add the Umask value and event number to select performance + * event. + */ + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_GEMINI_LAKE: + l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1; + l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1; + break; + case INTEL_FAM6_BROADWELL_X: + /* On BDW the l2_hit_bits count references, not hits */ + l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24; + l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24; + /* On BDW the l3_hit_bits count references, not hits */ + l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e; + l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e; + break; + default: + goto out; + } + + local_irq_disable(); + /* + * Call wrmsr direcly to avoid the local register variables from + * being overwritten due to reordering of their assignment with + * the wrmsr calls. + */ + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + /* Disable events and reset counters */ + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0); + if (l3_hit_bits > 0) { + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0); + } + /* Set and enable the L2 counters */ + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits); + if (l3_hit_bits > 0) { + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, + l3_hit_bits); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, + l3_miss_bits); + } + mem_r = plr->kmem; + size = plr->size; + line_size = plr->line_size; + for (i = 0; i < size; i += line_size) { + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Call wrmsr directly (no tracing) to not influence + * the cache access counters as they are disabled. + */ + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, + l2_hit_bits & ~(0x40ULL << 16)); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, + l2_miss_bits & ~(0x40ULL << 16)); + if (l3_hit_bits > 0) { + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, + l3_hit_bits & ~(0x40ULL << 16)); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, + l3_miss_bits & ~(0x40ULL << 16)); + } + l2_hits = native_read_pmc(0); + l2_miss = native_read_pmc(1); + if (l3_hit_bits > 0) { + l3_hits = native_read_pmc(2); + l3_miss = native_read_pmc(3); + } + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + /* + * On BDW we count references and misses, need to adjust. Sometimes + * the "hits" counter is a bit more than the references, for + * example, x references but x + 1 hits. To not report invalid + * hit values in this case we treat that as misses eaqual to + * references. + */ + if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) + l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss); + trace_pseudo_lock_l2(l2_hits, l2_miss); + if (l3_hit_bits > 0) { + if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) + l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss); + trace_pseudo_lock_l3(l3_hits, l3_miss); + } + +out: + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/** + * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region + * + * The measurement of latency to access a pseudo-locked region should be + * done from a cpu that is associated with that pseudo-locked region. + * Determine which cpu is associated with this region and start a thread on + * that cpu to perform the measurement, wait for that thread to complete. + * + * Return: 0 on success, <0 on failure + */ +static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + struct task_struct *thread; + unsigned int cpu; + int ret = -1; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + if (rdtgrp->flags & RDT_DELETED) { + ret = -ENODEV; + goto out; + } + + plr->thread_done = 0; + cpu = cpumask_first(&plr->d->cpu_mask); + if (!cpu_online(cpu)) { + ret = -ENODEV; + goto out; + } + + if (sel == 1) + thread = kthread_create_on_node(measure_cycles_lat_fn, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else if (sel == 2) + thread = kthread_create_on_node(measure_cycles_perf_fn, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else + goto out; + + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + goto out; + } + kthread_bind(thread, cpu); + wake_up_process(thread); + + ret = wait_event_interruptible(plr->lock_thread_wq, + plr->thread_done == 1); + if (ret < 0) + goto out; + + ret = 0; + +out: + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + return ret; +} + +static ssize_t pseudo_lock_measure_trigger(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct rdtgroup *rdtgrp = file->private_data; + size_t buf_size; + char buf[32]; + int ret; + int sel; + + buf_size = min(count, (sizeof(buf) - 1)); + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + ret = kstrtoint(buf, 10, &sel); + if (ret == 0) { + if (sel != 1) + return -EINVAL; + ret = debugfs_file_get(file->f_path.dentry); + if (ret) + return ret; + ret = pseudo_lock_measure_cycles(rdtgrp, sel); + if (ret == 0) + ret = count; + debugfs_file_put(file->f_path.dentry); + } + + return ret; +} + +static const struct file_operations pseudo_measure_fops = { + .write = pseudo_lock_measure_trigger, + .open = simple_open, + .llseek = default_llseek, +}; + +/** + * rdtgroup_pseudo_lock_create - Create a pseudo-locked region + * @rdtgrp: resource group to which pseudo-lock region belongs + * + * Called when a resource group in the pseudo-locksetup mode receives a + * valid schemata that should be pseudo-locked. Since the resource group is + * in pseudo-locksetup mode the &struct pseudo_lock_region has already been + * allocated and initialized with the essential information. If a failure + * occurs the resource group remains in the pseudo-locksetup mode with the + * &struct pseudo_lock_region associated with it, but cleared from all + * information and ready for the user to re-attempt pseudo-locking by + * writing the schemata again. + * + * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0 + * on failure. Descriptive error will be written to last_cmd_status buffer. + */ +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + struct task_struct *thread; + unsigned int new_minor; + struct device *dev; + int ret; + + ret = pseudo_lock_region_alloc(plr); + if (ret < 0) + return ret; + + ret = pseudo_lock_cstates_constrain(plr); + if (ret < 0) { + ret = -EINVAL; + goto out_region; + } + + plr->thread_done = 0; + + thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp, + cpu_to_node(plr->cpu), + "pseudo_lock/%u", plr->cpu); + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + rdt_last_cmd_printf("locking thread returned error %d\n", ret); + goto out_cstates; + } + + kthread_bind(thread, plr->cpu); + wake_up_process(thread); + + ret = wait_event_interruptible(plr->lock_thread_wq, + plr->thread_done == 1); + if (ret < 0) { + /* + * If the thread does not get on the CPU for whatever + * reason and the process which sets up the region is + * interrupted then this will leave the thread in runnable + * state and once it gets on the CPU it will derefence + * the cleared, but not freed, plr struct resulting in an + * empty pseudo-locking loop. + */ + rdt_last_cmd_puts("locking thread interrupted\n"); + goto out_cstates; + } + + ret = pseudo_lock_minor_get(&new_minor); + if (ret < 0) { + rdt_last_cmd_puts("unable to obtain a new minor number\n"); + goto out_cstates; + } + + /* + * Unlock access but do not release the reference. The + * pseudo-locked region will still be here on return. + * + * The mutex has to be released temporarily to avoid a potential + * deadlock with the mm->mmap_sem semaphore which is obtained in + * the device_create() and debugfs_create_dir() callpath below + * as well as before the mmap() callback is called. + */ + mutex_unlock(&rdtgroup_mutex); + + if (!IS_ERR_OR_NULL(debugfs_resctrl)) { + plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name, + debugfs_resctrl); + if (!IS_ERR_OR_NULL(plr->debugfs_dir)) + debugfs_create_file("pseudo_lock_measure", 0200, + plr->debugfs_dir, rdtgrp, + &pseudo_measure_fops); + } + + dev = device_create(pseudo_lock_class, NULL, + MKDEV(pseudo_lock_major, new_minor), + rdtgrp, "%s", rdtgrp->kn->name); + + mutex_lock(&rdtgroup_mutex); + + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + rdt_last_cmd_printf("failed to create character device: %d\n", + ret); + goto out_debugfs; + } + + /* We released the mutex - check if group was removed while we did so */ + if (rdtgrp->flags & RDT_DELETED) { + ret = -ENODEV; + goto out_device; + } + + plr->minor = new_minor; + + rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED; + closid_free(rdtgrp->closid); + rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444); + rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444); + + ret = 0; + goto out; + +out_device: + device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor)); +out_debugfs: + debugfs_remove_recursive(plr->debugfs_dir); + pseudo_lock_minor_release(new_minor); +out_cstates: + pseudo_lock_cstates_relax(plr); +out_region: + pseudo_lock_region_clear(plr); +out: + return ret; +} + +/** + * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region + * @rdtgrp: resource group to which the pseudo-locked region belongs + * + * The removal of a pseudo-locked region can be initiated when the resource + * group is removed from user space via a "rmdir" from userspace or the + * unmount of the resctrl filesystem. On removal the resource group does + * not go back to pseudo-locksetup mode before it is removed, instead it is + * removed directly. There is thus assymmetry with the creation where the + * &struct pseudo_lock_region is removed here while it was not created in + * rdtgroup_pseudo_lock_create(). + * + * Return: void + */ +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * Default group cannot be a pseudo-locked region so we can + * free closid here. + */ + closid_free(rdtgrp->closid); + goto free; + } + + pseudo_lock_cstates_relax(plr); + debugfs_remove_recursive(rdtgrp->plr->debugfs_dir); + device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor)); + pseudo_lock_minor_release(plr->minor); + +free: + pseudo_lock_free(rdtgrp); +} + +static int pseudo_lock_dev_open(struct inode *inode, struct file *filp) +{ + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + + rdtgrp = region_find_by_minor(iminor(inode)); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + filp->private_data = rdtgrp; + atomic_inc(&rdtgrp->waitcount); + /* Perform a non-seekable open - llseek is not supported */ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); + + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static int pseudo_lock_dev_release(struct inode *inode, struct file *filp) +{ + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + rdtgrp = filp->private_data; + WARN_ON(!rdtgrp); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + filp->private_data = NULL; + atomic_dec(&rdtgrp->waitcount); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static int pseudo_lock_dev_mremap(struct vm_area_struct *area) +{ + /* Not supported */ + return -EINVAL; +} + +static const struct vm_operations_struct pseudo_mmap_ops = { + .mremap = pseudo_lock_dev_mremap, +}; + +static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) +{ + unsigned long vsize = vma->vm_end - vma->vm_start; + unsigned long off = vma->vm_pgoff << PAGE_SHIFT; + struct pseudo_lock_region *plr; + struct rdtgroup *rdtgrp; + unsigned long physical; + unsigned long psize; + + mutex_lock(&rdtgroup_mutex); + + rdtgrp = filp->private_data; + WARN_ON(!rdtgrp); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + plr = rdtgrp->plr; + + /* + * Task is required to run with affinity to the cpus associated + * with the pseudo-locked region. If this is not the case the task + * may be scheduled elsewhere and invalidate entries in the + * pseudo-locked region. + */ + if (!cpumask_subset(¤t->cpus_allowed, &plr->d->cpu_mask)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } + + physical = __pa(plr->kmem) >> PAGE_SHIFT; + psize = plr->size - off; + + if (off > plr->size) { + mutex_unlock(&rdtgroup_mutex); + return -ENOSPC; + } + + /* + * Ensure changes are carried directly to the memory being mapped, + * do not allow copy-on-write mapping. + */ + if (!(vma->vm_flags & VM_SHARED)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } + + if (vsize > psize) { + mutex_unlock(&rdtgroup_mutex); + return -ENOSPC; + } + + memset(plr->kmem + off, 0, vsize); + + if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff, + vsize, vma->vm_page_prot)) { + mutex_unlock(&rdtgroup_mutex); + return -EAGAIN; + } + vma->vm_ops = &pseudo_mmap_ops; + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static const struct file_operations pseudo_lock_dev_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = NULL, + .write = NULL, + .open = pseudo_lock_dev_open, + .release = pseudo_lock_dev_release, + .mmap = pseudo_lock_dev_mmap, +}; + +static char *pseudo_lock_devnode(struct device *dev, umode_t *mode) +{ + struct rdtgroup *rdtgrp; + + rdtgrp = dev_get_drvdata(dev); + if (mode) + *mode = 0600; + return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name); +} + +int rdt_pseudo_lock_init(void) +{ + int ret; + + ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops); + if (ret < 0) + return ret; + + pseudo_lock_major = ret; + + pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock"); + if (IS_ERR(pseudo_lock_class)) { + ret = PTR_ERR(pseudo_lock_class); + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + return ret; + } + + pseudo_lock_class->devnode = pseudo_lock_devnode; + return 0; +} + +void rdt_pseudo_lock_release(void) +{ + class_destroy(pseudo_lock_class); + pseudo_lock_class = NULL; + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + pseudo_lock_major = 0; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h new file mode 100644 index 000000000000..2c041e6d9f05 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM resctrl + +#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PSEUDO_LOCK_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(pseudo_lock_mem_latency, + TP_PROTO(u32 latency), + TP_ARGS(latency), + TP_STRUCT__entry(__field(u32, latency)), + TP_fast_assign(__entry->latency = latency), + TP_printk("latency=%u", __entry->latency) + ); + +TRACE_EVENT(pseudo_lock_l2, + TP_PROTO(u64 l2_hits, u64 l2_miss), + TP_ARGS(l2_hits, l2_miss), + TP_STRUCT__entry(__field(u64, l2_hits) + __field(u64, l2_miss)), + TP_fast_assign(__entry->l2_hits = l2_hits; + __entry->l2_miss = l2_miss;), + TP_printk("hits=%llu miss=%llu", + __entry->l2_hits, __entry->l2_miss)); + +TRACE_EVENT(pseudo_lock_l3, + TP_PROTO(u64 l3_hits, u64 l3_miss), + TP_ARGS(l3_hits, l3_miss), + TP_STRUCT__entry(__field(u64, l3_hits) + __field(u64, l3_miss)), + TP_fast_assign(__entry->l3_hits = l3_hits; + __entry->l3_miss = l3_miss;), + TP_printk("hits=%llu miss=%llu", + __entry->l3_hits, __entry->l3_miss)); + +#endif /* _TRACE_PSEUDO_LOCK_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event +#include <trace/define_trace.h> diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 749856a2e736..d6d7ea7349d0 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -20,7 +20,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/cacheinfo.h> #include <linux/cpu.h> +#include <linux/debugfs.h> #include <linux/fs.h> #include <linux/sysfs.h> #include <linux/kernfs.h> @@ -55,6 +57,8 @@ static struct kernfs_node *kn_mondata; static struct seq_buf last_cmd_status; static char last_cmd_status_buf[512]; +struct dentry *debugfs_resctrl; + void rdt_last_cmd_clear(void) { lockdep_assert_held(&rdtgroup_mutex); @@ -121,11 +125,65 @@ static int closid_alloc(void) return closid; } -static void closid_free(int closid) +void closid_free(int closid) { closid_free_map |= 1 << closid; } +/** + * closid_allocated - test if provided closid is in use + * @closid: closid to be tested + * + * Return: true if @closid is currently associated with a resource group, + * false if @closid is free + */ +static bool closid_allocated(unsigned int closid) +{ + return (closid_free_map & (1 << closid)) == 0; +} + +/** + * rdtgroup_mode_by_closid - Return mode of resource group with closid + * @closid: closid if the resource group + * + * Each resource group is associated with a @closid. Here the mode + * of a resource group can be queried by searching for it using its closid. + * + * Return: mode as &enum rdtgrp_mode of resource group with closid @closid + */ +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid) +{ + struct rdtgroup *rdtgrp; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->closid == closid) + return rdtgrp->mode; + } + + return RDT_NUM_MODES; +} + +static const char * const rdt_mode_str[] = { + [RDT_MODE_SHAREABLE] = "shareable", + [RDT_MODE_EXCLUSIVE] = "exclusive", + [RDT_MODE_PSEUDO_LOCKSETUP] = "pseudo-locksetup", + [RDT_MODE_PSEUDO_LOCKED] = "pseudo-locked", +}; + +/** + * rdtgroup_mode_str - Return the string representation of mode + * @mode: the resource group mode as &enum rdtgroup_mode + * + * Return: string representation of valid mode, "unknown" otherwise + */ +static const char *rdtgroup_mode_str(enum rdtgrp_mode mode) +{ + if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES) + return "unknown"; + + return rdt_mode_str[mode]; +} + /* set uid and gid of rdtgroup dirs and files to that of the creator */ static int rdtgroup_kn_set_ugid(struct kernfs_node *kn) { @@ -207,8 +265,12 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", - cpumask_pr_args(&rdtgrp->cpu_mask)); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", + cpumask_pr_args(&rdtgrp->plr->d->cpu_mask)); + else + seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", + cpumask_pr_args(&rdtgrp->cpu_mask)); } else { ret = -ENOENT; } @@ -394,6 +456,13 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, goto unlock; } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto unlock; + } + if (is_cpu_list(of)) ret = cpulist_parse(buf, newmask); else @@ -509,6 +578,32 @@ static int __rdtgroup_move_task(struct task_struct *tsk, return ret; } +/** + * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group + * @r: Resource group + * + * Return: 1 if tasks have been assigned to @r, 0 otherwise + */ +int rdtgroup_tasks_assigned(struct rdtgroup *r) +{ + struct task_struct *p, *t; + int ret = 0; + + lockdep_assert_held(&rdtgroup_mutex); + + rcu_read_lock(); + for_each_process_thread(p, t) { + if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) || + (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) { + ret = 1; + break; + } + } + rcu_read_unlock(); + + return ret; +} + static int rdtgroup_task_write_permission(struct task_struct *task, struct kernfs_open_file *of) { @@ -570,13 +665,22 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } rdt_last_cmd_clear(); - if (rdtgrp) - ret = rdtgroup_move_task(pid, rdtgrp, of); - else - ret = -ENOENT; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto unlock; + } + ret = rdtgroup_move_task(pid, rdtgrp, of); + +unlock: rdtgroup_kn_unlock(of->kn); return ret ?: nbytes; @@ -662,6 +766,94 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of, return 0; } +/** + * rdt_bit_usage_show - Display current usage of resources + * + * A domain is a shared resource that can now be allocated differently. Here + * we display the current regions of the domain as an annotated bitmask. + * For each domain of this resource its allocation bitmask + * is annotated as below to indicate the current usage of the corresponding bit: + * 0 - currently unused + * X - currently available for sharing and used by software and hardware + * H - currently used by hardware only but available for software use + * S - currently used and shareable by software only + * E - currently used exclusively by one resource group + * P - currently pseudo-locked by one resource group + */ +static int rdt_bit_usage_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + u32 sw_shareable = 0, hw_shareable = 0; + u32 exclusive = 0, pseudo_locked = 0; + struct rdt_domain *dom; + int i, hwb, swb, excl, psl; + enum rdtgrp_mode mode; + bool sep = false; + u32 *ctrl; + + mutex_lock(&rdtgroup_mutex); + hw_shareable = r->cache.shareable_bits; + list_for_each_entry(dom, &r->domains, list) { + if (sep) + seq_putc(seq, ';'); + ctrl = dom->ctrl_val; + sw_shareable = 0; + exclusive = 0; + seq_printf(seq, "%d=", dom->id); + for (i = 0; i < r->num_closid; i++, ctrl++) { + if (!closid_allocated(i)) + continue; + mode = rdtgroup_mode_by_closid(i); + switch (mode) { + case RDT_MODE_SHAREABLE: + sw_shareable |= *ctrl; + break; + case RDT_MODE_EXCLUSIVE: + exclusive |= *ctrl; + break; + case RDT_MODE_PSEUDO_LOCKSETUP: + /* + * RDT_MODE_PSEUDO_LOCKSETUP is possible + * here but not included since the CBM + * associated with this CLOSID in this mode + * is not initialized and no task or cpu can be + * assigned this CLOSID. + */ + break; + case RDT_MODE_PSEUDO_LOCKED: + case RDT_NUM_MODES: + WARN(1, + "invalid mode for closid %d\n", i); + break; + } + } + for (i = r->cache.cbm_len - 1; i >= 0; i--) { + pseudo_locked = dom->plr ? dom->plr->cbm : 0; + hwb = test_bit(i, (unsigned long *)&hw_shareable); + swb = test_bit(i, (unsigned long *)&sw_shareable); + excl = test_bit(i, (unsigned long *)&exclusive); + psl = test_bit(i, (unsigned long *)&pseudo_locked); + if (hwb && swb) + seq_putc(seq, 'X'); + else if (hwb && !swb) + seq_putc(seq, 'H'); + else if (!hwb && swb) + seq_putc(seq, 'S'); + else if (excl) + seq_putc(seq, 'E'); + else if (psl) + seq_putc(seq, 'P'); + else /* Unused bits remain */ + seq_putc(seq, '0'); + } + sep = true; + } + seq_putc(seq, '\n'); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -740,6 +932,269 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, return nbytes; } +/* + * rdtgroup_mode_show - Display mode of this resource group + */ +static int rdtgroup_mode_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode)); + + rdtgroup_kn_unlock(of->kn); + return 0; +} + +/** + * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other + * @r: Resource to which domain instance @d belongs. + * @d: The domain instance for which @closid is being tested. + * @cbm: Capacity bitmask being tested. + * @closid: Intended closid for @cbm. + * @exclusive: Only check if overlaps with exclusive resource groups + * + * Checks if provided @cbm intended to be used for @closid on domain + * @d overlaps with any other closids or other hardware usage associated + * with this domain. If @exclusive is true then only overlaps with + * resource groups in exclusive mode will be considered. If @exclusive + * is false then overlaps with any resource group or hardware entities + * will be considered. + * + * Return: false if CBM does not overlap, true if it does. + */ +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + u32 _cbm, int closid, bool exclusive) +{ + unsigned long *cbm = (unsigned long *)&_cbm; + unsigned long *ctrl_b; + enum rdtgrp_mode mode; + u32 *ctrl; + int i; + + /* Check for any overlap with regions used by hardware directly */ + if (!exclusive) { + if (bitmap_intersects(cbm, + (unsigned long *)&r->cache.shareable_bits, + r->cache.cbm_len)) + return true; + } + + /* Check for overlap with other resource groups */ + ctrl = d->ctrl_val; + for (i = 0; i < r->num_closid; i++, ctrl++) { + ctrl_b = (unsigned long *)ctrl; + mode = rdtgroup_mode_by_closid(i); + if (closid_allocated(i) && i != closid && + mode != RDT_MODE_PSEUDO_LOCKSETUP) { + if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) { + if (exclusive) { + if (mode == RDT_MODE_EXCLUSIVE) + return true; + continue; + } + return true; + } + } + } + + return false; +} + +/** + * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive + * + * An exclusive resource group implies that there should be no sharing of + * its allocated resources. At the time this group is considered to be + * exclusive this test can determine if its current schemata supports this + * setting by testing for overlap with all other resource groups. + * + * Return: true if resource group can be exclusive, false if there is overlap + * with allocations of other resource groups and thus this resource group + * cannot be exclusive. + */ +static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) +{ + int closid = rdtgrp->closid; + struct rdt_resource *r; + struct rdt_domain *d; + + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d, &r->domains, list) { + if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], + rdtgrp->closid, false)) + return false; + } + } + + return true; +} + +/** + * rdtgroup_mode_write - Modify the resource group's mode + * + */ +static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + enum rdtgrp_mode mode; + int ret = 0; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + buf[nbytes - 1] = '\0'; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + rdt_last_cmd_clear(); + + mode = rdtgrp->mode; + + if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) || + (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) || + (!strcmp(buf, "pseudo-locksetup") && + mode == RDT_MODE_PSEUDO_LOCKSETUP) || + (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED)) + goto out; + + if (mode == RDT_MODE_PSEUDO_LOCKED) { + rdt_last_cmd_printf("cannot change pseudo-locked group\n"); + ret = -EINVAL; + goto out; + } + + if (!strcmp(buf, "shareable")) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = rdtgroup_locksetup_exit(rdtgrp); + if (ret) + goto out; + } + rdtgrp->mode = RDT_MODE_SHAREABLE; + } else if (!strcmp(buf, "exclusive")) { + if (!rdtgroup_mode_test_exclusive(rdtgrp)) { + rdt_last_cmd_printf("schemata overlaps\n"); + ret = -EINVAL; + goto out; + } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = rdtgroup_locksetup_exit(rdtgrp); + if (ret) + goto out; + } + rdtgrp->mode = RDT_MODE_EXCLUSIVE; + } else if (!strcmp(buf, "pseudo-locksetup")) { + ret = rdtgroup_locksetup_enter(rdtgrp); + if (ret) + goto out; + rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP; + } else { + rdt_last_cmd_printf("unknown/unsupported mode\n"); + ret = -EINVAL; + } + +out: + rdtgroup_kn_unlock(of->kn); + return ret ?: nbytes; +} + +/** + * rdtgroup_cbm_to_size - Translate CBM to size in bytes + * @r: RDT resource to which @d belongs. + * @d: RDT domain instance. + * @cbm: bitmask for which the size should be computed. + * + * The bitmask provided associated with the RDT domain instance @d will be + * translated into how many bytes it represents. The size in bytes is + * computed by first dividing the total cache size by the CBM length to + * determine how many bytes each bit in the bitmask represents. The result + * is multiplied with the number of bits set in the bitmask. + */ +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, + struct rdt_domain *d, u32 cbm) +{ + struct cpu_cacheinfo *ci; + unsigned int size = 0; + int num_b, i; + + num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len); + ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask)); + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == r->cache_level) { + size = ci->info_list[i].size / r->cache.cbm_len * num_b; + break; + } + } + + return size; +} + +/** + * rdtgroup_size_show - Display size in bytes of allocated regions + * + * The "size" file mirrors the layout of the "schemata" file, printing the + * size in bytes of each region instead of the capacity bitmask. + * + */ +static int rdtgroup_size_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + struct rdt_domain *d; + unsigned int size; + bool sep = false; + u32 cbm; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name); + size = rdtgroup_cbm_to_size(rdtgrp->plr->r, + rdtgrp->plr->d, + rdtgrp->plr->cbm); + seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + goto out; + } + + for_each_alloc_enabled_rdt_resource(r) { + seq_printf(s, "%*s:", max_name_width, r->name); + list_for_each_entry(d, &r->domains, list) { + if (sep) + seq_putc(s, ';'); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + size = 0; + } else { + cbm = d->ctrl_val[rdtgrp->closid]; + size = rdtgroup_cbm_to_size(r, d, cbm); + } + seq_printf(s, "%d=%u", d->id, size); + sep = true; + } + seq_putc(s, '\n'); + } + +out: + rdtgroup_kn_unlock(of->kn); + + return 0; +} + /* rdtgroup information files for one cache resource. */ static struct rftype res_common_files[] = { { @@ -792,6 +1247,13 @@ static struct rftype res_common_files[] = { .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, { + .name = "bit_usage", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_bit_usage_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { .name = "min_bandwidth", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, @@ -853,6 +1315,22 @@ static struct rftype res_common_files[] = { .seq_show = rdtgroup_schemata_show, .fflags = RF_CTRL_BASE, }, + { + .name = "mode", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_mode_write, + .seq_show = rdtgroup_mode_show, + .fflags = RF_CTRL_BASE, + }, + { + .name = "size", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_size_show, + .fflags = RF_CTRL_BASE, + }, + }; static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) @@ -883,6 +1361,103 @@ error: return ret; } +/** + * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file + * @r: The resource group with which the file is associated. + * @name: Name of the file + * + * The permissions of named resctrl file, directory, or link are modified + * to not allow read, write, or execute by any user. + * + * WARNING: This function is intended to communicate to the user that the + * resctrl file has been locked down - that it is not relevant to the + * particular state the system finds itself in. It should not be relied + * on to protect from user access because after the file's permissions + * are restricted the user can still change the permissions using chmod + * from the command line. + * + * Return: 0 on success, <0 on failure. + */ +int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name) +{ + struct iattr iattr = {.ia_valid = ATTR_MODE,}; + struct kernfs_node *kn; + int ret = 0; + + kn = kernfs_find_and_get_ns(r->kn, name, NULL); + if (!kn) + return -ENOENT; + + switch (kernfs_type(kn)) { + case KERNFS_DIR: + iattr.ia_mode = S_IFDIR; + break; + case KERNFS_FILE: + iattr.ia_mode = S_IFREG; + break; + case KERNFS_LINK: + iattr.ia_mode = S_IFLNK; + break; + } + + ret = kernfs_setattr(kn, &iattr); + kernfs_put(kn); + return ret; +} + +/** + * rdtgroup_kn_mode_restore - Restore user access to named resctrl file + * @r: The resource group with which the file is associated. + * @name: Name of the file + * @mask: Mask of permissions that should be restored + * + * Restore the permissions of the named file. If @name is a directory the + * permissions of its parent will be used. + * + * Return: 0 on success, <0 on failure. + */ +int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, + umode_t mask) +{ + struct iattr iattr = {.ia_valid = ATTR_MODE,}; + struct kernfs_node *kn, *parent; + struct rftype *rfts, *rft; + int ret, len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + for (rft = rfts; rft < rfts + len; rft++) { + if (!strcmp(rft->name, name)) + iattr.ia_mode = rft->mode & mask; + } + + kn = kernfs_find_and_get_ns(r->kn, name, NULL); + if (!kn) + return -ENOENT; + + switch (kernfs_type(kn)) { + case KERNFS_DIR: + parent = kernfs_get_parent(kn); + if (parent) { + iattr.ia_mode |= parent->mode; + kernfs_put(parent); + } + iattr.ia_mode |= S_IFDIR; + break; + case KERNFS_FILE: + iattr.ia_mode |= S_IFREG; + break; + case KERNFS_LINK: + iattr.ia_mode |= S_IFLNK; + break; + } + + ret = kernfs_setattr(kn, &iattr); + kernfs_put(kn); + return ret; +} + static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, unsigned long fflags) { @@ -1224,6 +1799,9 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) if (atomic_dec_and_test(&rdtgrp->waitcount) && (rdtgrp->flags & RDT_DELETED)) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); kernfs_unbreak_active_protection(kn); kernfs_put(rdtgrp->kn); kfree(rdtgrp); @@ -1289,10 +1867,16 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, rdtgroup_default.mon.mon_data_kn = kn_mondata; } + ret = rdt_pseudo_lock_init(); + if (ret) { + dentry = ERR_PTR(ret); + goto out_mondata; + } + dentry = kernfs_mount(fs_type, flags, rdt_root, RDTGROUP_SUPER_MAGIC, NULL); if (IS_ERR(dentry)) - goto out_mondata; + goto out_psl; if (rdt_alloc_capable) static_branch_enable_cpuslocked(&rdt_alloc_enable_key); @@ -1310,6 +1894,8 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, goto out; +out_psl: + rdt_pseudo_lock_release(); out_mondata: if (rdt_mon_capable) kernfs_remove(kn_mondata); @@ -1447,6 +2033,10 @@ static void rmdir_all_sub(void) if (rdtgrp == &rdtgroup_default) continue; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); + /* * Give any CPUs back to the default group. We cannot copy * cpu_online_mask because a CPU might have executed the @@ -1483,6 +2073,8 @@ static void rdt_kill_sb(struct super_block *sb) reset_all_ctrls(r); cdp_disable_all(); rmdir_all_sub(); + rdt_pseudo_lock_release(); + rdtgroup_default.mode = RDT_MODE_SHAREABLE; static_branch_disable_cpuslocked(&rdt_alloc_enable_key); static_branch_disable_cpuslocked(&rdt_mon_enable_key); static_branch_disable_cpuslocked(&rdt_enable_key); @@ -1682,6 +2274,114 @@ out_destroy: return ret; } +/** + * cbm_ensure_valid - Enforce validity on provided CBM + * @_val: Candidate CBM + * @r: RDT resource to which the CBM belongs + * + * The provided CBM represents all cache portions available for use. This + * may be represented by a bitmap that does not consist of contiguous ones + * and thus be an invalid CBM. + * Here the provided CBM is forced to be a valid CBM by only considering + * the first set of contiguous bits as valid and clearing all bits. + * The intention here is to provide a valid default CBM with which a new + * resource group is initialized. The user can follow this with a + * modification to the CBM if the default does not satisfy the + * requirements. + */ +static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r) +{ + /* + * Convert the u32 _val to an unsigned long required by all the bit + * operations within this function. No more than 32 bits of this + * converted value can be accessed because all bit operations are + * additionally provided with cbm_len that is initialized during + * hardware enumeration using five bits from the EAX register and + * thus never can exceed 32 bits. + */ + unsigned long *val = (unsigned long *)_val; + unsigned int cbm_len = r->cache.cbm_len; + unsigned long first_bit, zero_bit; + + if (*val == 0) + return; + + first_bit = find_first_bit(val, cbm_len); + zero_bit = find_next_zero_bit(val, cbm_len, first_bit); + + /* Clear any remaining bits to ensure contiguous region */ + bitmap_clear(val, zero_bit, cbm_len - zero_bit); +} + +/** + * rdtgroup_init_alloc - Initialize the new RDT group's allocations + * + * A new RDT group is being created on an allocation capable (CAT) + * supporting system. Set this group up to start off with all usable + * allocations. That is, all shareable and unused bits. + * + * All-zero CBM is invalid. If there are no more shareable bits available + * on any domain then the entire allocation will fail. + */ +static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) +{ + u32 used_b = 0, unused_b = 0; + u32 closid = rdtgrp->closid; + struct rdt_resource *r; + enum rdtgrp_mode mode; + struct rdt_domain *d; + int i, ret; + u32 *ctrl; + + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d, &r->domains, list) { + d->have_new_ctrl = false; + d->new_ctrl = r->cache.shareable_bits; + used_b = r->cache.shareable_bits; + ctrl = d->ctrl_val; + for (i = 0; i < r->num_closid; i++, ctrl++) { + if (closid_allocated(i) && i != closid) { + mode = rdtgroup_mode_by_closid(i); + if (mode == RDT_MODE_PSEUDO_LOCKSETUP) + break; + used_b |= *ctrl; + if (mode == RDT_MODE_SHAREABLE) + d->new_ctrl |= *ctrl; + } + } + if (d->plr && d->plr->cbm > 0) + used_b |= d->plr->cbm; + unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1); + unused_b &= BIT_MASK(r->cache.cbm_len) - 1; + d->new_ctrl |= unused_b; + /* + * Force the initial CBM to be valid, user can + * modify the CBM based on system availability. + */ + cbm_ensure_valid(&d->new_ctrl, r); + if (bitmap_weight((unsigned long *) &d->new_ctrl, + r->cache.cbm_len) < + r->cache.min_cbm_bits) { + rdt_last_cmd_printf("no space on %s:%d\n", + r->name, d->id); + return -ENOSPC; + } + d->have_new_ctrl = true; + } + } + + for_each_alloc_enabled_rdt_resource(r) { + ret = update_domains(r, rdtgrp->closid); + if (ret < 0) { + rdt_last_cmd_puts("failed to initialize allocations\n"); + return ret; + } + rdtgrp->mode = RDT_MODE_SHAREABLE; + } + + return 0; +} + static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, struct kernfs_node *prgrp_kn, const char *name, umode_t mode, @@ -1700,6 +2400,14 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_unlock; } + if (rtype == RDTMON_GROUP && + (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto out_unlock; + } + /* allocate the rdtgroup. */ rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); if (!rdtgrp) { @@ -1840,6 +2548,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = 0; rdtgrp->closid = closid; + ret = rdtgroup_init_alloc(rdtgrp); + if (ret < 0) + goto out_id_free; + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); if (rdt_mon_capable) { @@ -1850,15 +2562,16 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); if (ret) { rdt_last_cmd_puts("kernfs subdir error\n"); - goto out_id_free; + goto out_del_list; } } goto out_unlock; +out_del_list: + list_del(&rdtgrp->rdtgroup_list); out_id_free: closid_free(closid); - list_del(&rdtgrp->rdtgroup_list); out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); out_unlock: @@ -1945,6 +2658,21 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, return 0; } +static int rdtgroup_ctrl_remove(struct kernfs_node *kn, + struct rdtgroup *rdtgrp) +{ + rdtgrp->flags = RDT_DELETED; + list_del(&rdtgrp->rdtgroup_list); + + /* + * one extra hold on this, will drop when we kfree(rdtgrp) + * in rdtgroup_kn_unlock() + */ + kernfs_get(kn); + kernfs_remove(rdtgrp->kn); + return 0; +} + static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) { @@ -1970,7 +2698,6 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); update_closid_rmid(tmpmask, NULL); - rdtgrp->flags = RDT_DELETED; closid_free(rdtgrp->closid); free_rmid(rdtgrp->mon.rmid); @@ -1979,14 +2706,7 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, */ free_all_child_rdtgrp(rdtgrp); - list_del(&rdtgrp->rdtgroup_list); - - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); - kernfs_remove(rdtgrp->kn); + rdtgroup_ctrl_remove(kn, rdtgrp); return 0; } @@ -2014,13 +2734,19 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) * If the rdtgroup is a mon group and parent directory * is a valid "mon_groups" directory, remove the mon group. */ - if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) - ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); - else if (rdtgrp->type == RDTMON_GROUP && - is_mon_groups(parent_kn, kn->name)) + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + ret = rdtgroup_ctrl_remove(kn, rdtgrp); + } else { + ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); + } + } else if (rdtgrp->type == RDTMON_GROUP && + is_mon_groups(parent_kn, kn->name)) { ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask); - else + } else { ret = -EPERM; + } out: rdtgroup_kn_unlock(kn); @@ -2046,7 +2772,8 @@ static int __init rdtgroup_setup_root(void) int ret; rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, - KERNFS_ROOT_CREATE_DEACTIVATED, + KERNFS_ROOT_CREATE_DEACTIVATED | + KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, &rdtgroup_default); if (IS_ERR(rdt_root)) return PTR_ERR(rdt_root); @@ -2102,6 +2829,29 @@ int __init rdtgroup_init(void) if (ret) goto cleanup_mountpoint; + /* + * Adding the resctrl debugfs directory here may not be ideal since + * it would let the resctrl debugfs directory appear on the debugfs + * filesystem before the resctrl filesystem is mounted. + * It may also be ok since that would enable debugging of RDT before + * resctrl is mounted. + * The reason why the debugfs directory is created here and not in + * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and + * during the debugfs directory creation also &sb->s_type->i_mutex_key + * (the lockdep class of inode->i_rwsem). Other filesystem + * interactions (eg. SyS_getdents) have the lock ordering: + * &sb->s_type->i_mutex_key --> &mm->mmap_sem + * During mmap(), called with &mm->mmap_sem, the rdtgroup_mutex + * is taken, thus creating dependency: + * &mm->mmap_sem --> rdtgroup_mutex for the latter that can cause + * issues considering the other two lock dependencies. + * By creating the debugfs directory here we avoid a dependency + * that may cause deadlock (even though file operations cannot + * occur until the filesystem is mounted, but I do not know how to + * tell lockdep that). + */ + debugfs_resctrl = debugfs_create_dir("resctrl", NULL); + return 0; cleanup_mountpoint: @@ -2111,3 +2861,11 @@ cleanup_root: return ret; } + +void __exit rdtgroup_exit(void) +{ + debugfs_remove_recursive(debugfs_resctrl); + unregister_filesystem(&rdt_fs_type); + sysfs_remove_mount_point(fs_kobj, "resctrl"); + kernfs_destroy_root(rdt_root); +} diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index c102ad51025e..4b767284b7f5 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -123,8 +123,8 @@ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - /* We hope get_seconds stays lockless */ - m->time = get_seconds(); + /* need the internal __ version to avoid deadlocks */ + m->time = __ktime_get_real_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; m->cpuid = cpuid_eax(1); m->socketid = cpu_data(m->extcpu).phys_proc_id; @@ -1104,6 +1104,101 @@ static void mce_unmap_kpfn(unsigned long pfn) } #endif + +/* + * Cases where we avoid rendezvous handler timeout: + * 1) If this CPU is offline. + * + * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to + * skip those CPUs which remain looping in the 1st kernel - see + * crash_nmi_callback(). + * + * Note: there still is a small window between kexec-ing and the new, + * kdump kernel establishing a new #MC handler where a broadcasted MCE + * might not get handled properly. + */ +static bool __mc_check_crashing_cpu(int cpu) +{ + if (cpu_is_offline(cpu) || + (crashing_cpu != -1 && crashing_cpu != cpu)) { + u64 mcgstatus; + + mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (mcgstatus & MCG_STATUS_RIPV) { + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + return true; + } + } + return false; +} + +static void __mc_scan_banks(struct mce *m, struct mce *final, + unsigned long *toclear, unsigned long *valid_banks, + int no_way_out, int *worst) +{ + struct mca_config *cfg = &mca_cfg; + int severity, i; + + for (i = 0; i < cfg->banks; i++) { + __clear_bit(i, toclear); + if (!test_bit(i, valid_banks)) + continue; + + if (!mce_banks[i].ctl) + continue; + + m->misc = 0; + m->addr = 0; + m->bank = i; + + m->status = mce_rdmsrl(msr_ops.status(i)); + if (!(m->status & MCI_STATUS_VAL)) + continue; + + /* + * Corrected or non-signaled errors are handled by + * machine_check_poll(). Leave them alone, unless this panics. + */ + if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && + !no_way_out) + continue; + + /* Set taint even when machine check was not enabled. */ + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + + severity = mce_severity(m, cfg->tolerant, NULL, true); + + /* + * When machine check was for corrected/deferred handler don't + * touch, unless we're panicking. + */ + if ((severity == MCE_KEEP_SEVERITY || + severity == MCE_UCNA_SEVERITY) && !no_way_out) + continue; + + __set_bit(i, toclear); + + /* Machine check event was not enabled. Clear, but ignore. */ + if (severity == MCE_NO_SEVERITY) + continue; + + mce_read_aux(m, i); + + /* assuming valid severity level != 0 */ + m->severity = severity; + + mce_log(m); + + if (severity > *worst) { + *final = *m; + *worst = severity; + } + } + + /* mce_clear_state will clear *final, save locally for use later */ + *m = *final; +} + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. @@ -1118,68 +1213,45 @@ static void mce_unmap_kpfn(unsigned long pfn) */ void do_machine_check(struct pt_regs *regs, long error_code) { + DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); + DECLARE_BITMAP(toclear, MAX_NR_BANKS); struct mca_config *cfg = &mca_cfg; + int cpu = smp_processor_id(); + char *msg = "Unknown"; struct mce m, *final; - int i; int worst = 0; - int severity; /* * Establish sequential order between the CPUs entering the machine * check handler. */ int order = -1; + /* * If no_way_out gets set, there is no safe way to recover from this * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. */ int no_way_out = 0; + /* * If kill_it gets set, there might be a way to recover from this * error. */ int kill_it = 0; - DECLARE_BITMAP(toclear, MAX_NR_BANKS); - DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); - char *msg = "Unknown"; /* * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES * on Intel. */ int lmce = 1; - int cpu = smp_processor_id(); - - /* - * Cases where we avoid rendezvous handler timeout: - * 1) If this CPU is offline. - * - * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to - * skip those CPUs which remain looping in the 1st kernel - see - * crash_nmi_callback(). - * - * Note: there still is a small window between kexec-ing and the new, - * kdump kernel establishing a new #MC handler where a broadcasted MCE - * might not get handled properly. - */ - if (cpu_is_offline(cpu) || - (crashing_cpu != -1 && crashing_cpu != cpu)) { - u64 mcgstatus; - mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); - if (mcgstatus & MCG_STATUS_RIPV) { - mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); - return; - } - } + if (__mc_check_crashing_cpu(cpu)) + return; ist_enter(regs); this_cpu_inc(mce_exception_count); - if (!cfg->banks) - goto out; - mce_gather_info(&m, regs); m.tsc = rdtsc(); @@ -1220,67 +1292,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) order = mce_start(&no_way_out); } - for (i = 0; i < cfg->banks; i++) { - __clear_bit(i, toclear); - if (!test_bit(i, valid_banks)) - continue; - if (!mce_banks[i].ctl) - continue; - - m.misc = 0; - m.addr = 0; - m.bank = i; - - m.status = mce_rdmsrl(msr_ops.status(i)); - if ((m.status & MCI_STATUS_VAL) == 0) - continue; - - /* - * Non uncorrected or non signaled errors are handled by - * machine_check_poll. Leave them alone, unless this panics. - */ - if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && - !no_way_out) - continue; - - /* - * Set taint even when machine check was not enabled. - */ - add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - - severity = mce_severity(&m, cfg->tolerant, NULL, true); - - /* - * When machine check was for corrected/deferred handler don't - * touch, unless we're panicing. - */ - if ((severity == MCE_KEEP_SEVERITY || - severity == MCE_UCNA_SEVERITY) && !no_way_out) - continue; - __set_bit(i, toclear); - if (severity == MCE_NO_SEVERITY) { - /* - * Machine check event was not enabled. Clear, but - * ignore. - */ - continue; - } - - mce_read_aux(&m, i); - - /* assuming valid severity level != 0 */ - m.severity = severity; - - mce_log(&m); - - if (severity > worst) { - *final = m; - worst = severity; - } - } - - /* mce_clear_state will clear *final, save locally for use later */ - m = *final; + __mc_scan_banks(&m, final, toclear, valid_banks, no_way_out, &worst); if (!no_way_out) mce_clear_state(toclear); @@ -1319,7 +1331,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) if (worst > 0) mce_report_event(regs); mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); -out: + sync_core(); if (worst != MCE_AR_SEVERITY && !kill_it) @@ -2165,9 +2177,6 @@ static ssize_t store_int_with_restart(struct device *s, if (check_interval == old_check_interval) return ret; - if (check_interval < 1) - check_interval = 1; - mutex_lock(&mce_sysfs_mutex); mce_restart(); mutex_unlock(&mce_sysfs_mutex); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 666a284116ac..9c8652974f8e 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -22,8 +22,6 @@ #include <asm/stacktrace.h> #include <asm/unwind.h> -#define OPCODE_BUFSIZE 64 - int panic_on_unrecovered_nmi; int panic_on_io_nmi; static int die_counter; @@ -93,26 +91,18 @@ static void printk_stack_address(unsigned long address, int reliable, */ void show_opcodes(u8 *rip, const char *loglvl) { - unsigned int code_prologue = OPCODE_BUFSIZE * 2 / 3; +#define PROLOGUE_SIZE 42 +#define EPILOGUE_SIZE 21 +#define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE) u8 opcodes[OPCODE_BUFSIZE]; - u8 *ip; - int i; - - printk("%sCode: ", loglvl); - - ip = (u8 *)rip - code_prologue; - if (probe_kernel_read(opcodes, ip, OPCODE_BUFSIZE)) { - pr_cont("Bad RIP value.\n"); - return; - } - for (i = 0; i < OPCODE_BUFSIZE; i++, ip++) { - if (ip == rip) - pr_cont("<%02x> ", opcodes[i]); - else - pr_cont("%02x ", opcodes[i]); + if (probe_kernel_read(opcodes, rip - PROLOGUE_SIZE, OPCODE_BUFSIZE)) { + printk("%sCode: Bad RIP value.\n", loglvl); + } else { + printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" + __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, + opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1); } - pr_cont("\n"); } void show_ip(struct pt_regs *regs, const char *loglvl) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 8344dd2f310a..15ebc2fc166e 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -235,7 +235,7 @@ ENTRY(secondary_startup_64) * address given in m16:64. */ pushq $.Lafter_lret # put return address on stack for unwinder - xorq %rbp, %rbp # clear frame pointer + xorl %ebp, %ebp # clear frame pointer movq initial_code(%rip), %rax pushq $__KERNEL_CS # set correct cs pushq %rax # target address in negative space diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 8771766d46b6..34a5c1715148 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -169,28 +169,29 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) set_dr_addr_mask(0, i); } -/* - * Check for virtual address in kernel space. - */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +static int arch_bp_generic_len(int x86_len) { - unsigned int len; - unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - - va = info->address; - len = bp->attr.bp_len; - - /* - * We don't need to worry about va + len - 1 overflowing: - * we already require that va is aligned to a multiple of len. - */ - return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX); + switch (x86_len) { + case X86_BREAKPOINT_LEN_1: + return HW_BREAKPOINT_LEN_1; + case X86_BREAKPOINT_LEN_2: + return HW_BREAKPOINT_LEN_2; + case X86_BREAKPOINT_LEN_4: + return HW_BREAKPOINT_LEN_4; +#ifdef CONFIG_X86_64 + case X86_BREAKPOINT_LEN_8: + return HW_BREAKPOINT_LEN_8; +#endif + default: + return -EINVAL; + } } int arch_bp_generic_fields(int x86_len, int x86_type, int *gen_len, int *gen_type) { + int len; + /* Type */ switch (x86_type) { case X86_BREAKPOINT_EXECUTE: @@ -211,42 +212,47 @@ int arch_bp_generic_fields(int x86_len, int x86_type, } /* Len */ - switch (x86_len) { - case X86_BREAKPOINT_LEN_1: - *gen_len = HW_BREAKPOINT_LEN_1; - break; - case X86_BREAKPOINT_LEN_2: - *gen_len = HW_BREAKPOINT_LEN_2; - break; - case X86_BREAKPOINT_LEN_4: - *gen_len = HW_BREAKPOINT_LEN_4; - break; -#ifdef CONFIG_X86_64 - case X86_BREAKPOINT_LEN_8: - *gen_len = HW_BREAKPOINT_LEN_8; - break; -#endif - default: + len = arch_bp_generic_len(x86_len); + if (len < 0) return -EINVAL; - } + *gen_len = len; return 0; } - -static int arch_build_bp_info(struct perf_event *bp) +/* + * Check for virtual address in kernel space. + */ +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); + unsigned long va; + int len; - info->address = bp->attr.bp_addr; + va = hw->address; + len = arch_bp_generic_len(hw->len); + WARN_ON_ONCE(len < 0); + + /* + * We don't need to worry about va + len - 1 overflowing: + * we already require that va is aligned to a multiple of len. + */ + return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX); +} + +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) +{ + hw->address = attr->bp_addr; + hw->mask = 0; /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_W: - info->type = X86_BREAKPOINT_WRITE; + hw->type = X86_BREAKPOINT_WRITE; break; case HW_BREAKPOINT_W | HW_BREAKPOINT_R: - info->type = X86_BREAKPOINT_RW; + hw->type = X86_BREAKPOINT_RW; break; case HW_BREAKPOINT_X: /* @@ -254,23 +260,23 @@ static int arch_build_bp_info(struct perf_event *bp) * acceptable for kprobes. On non-kprobes kernels, we don't * allow kernel breakpoints at all. */ - if (bp->attr.bp_addr >= TASK_SIZE_MAX) { + if (attr->bp_addr >= TASK_SIZE_MAX) { #ifdef CONFIG_KPROBES - if (within_kprobe_blacklist(bp->attr.bp_addr)) + if (within_kprobe_blacklist(attr->bp_addr)) return -EINVAL; #else return -EINVAL; #endif } - info->type = X86_BREAKPOINT_EXECUTE; + hw->type = X86_BREAKPOINT_EXECUTE; /* * x86 inst breakpoints need to have a specific undefined len. * But we still need to check userspace is not trying to setup * an unsupported length, to get a range breakpoint for example. */ - if (bp->attr.bp_len == sizeof(long)) { - info->len = X86_BREAKPOINT_LEN_X; + if (attr->bp_len == sizeof(long)) { + hw->len = X86_BREAKPOINT_LEN_X; return 0; } default: @@ -278,28 +284,26 @@ static int arch_build_bp_info(struct perf_event *bp) } /* Len */ - info->mask = 0; - - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->len = X86_BREAKPOINT_LEN_1; + hw->len = X86_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->len = X86_BREAKPOINT_LEN_2; + hw->len = X86_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_4: - info->len = X86_BREAKPOINT_LEN_4; + hw->len = X86_BREAKPOINT_LEN_4; break; #ifdef CONFIG_X86_64 case HW_BREAKPOINT_LEN_8: - info->len = X86_BREAKPOINT_LEN_8; + hw->len = X86_BREAKPOINT_LEN_8; break; #endif default: /* AMD range breakpoint */ - if (!is_power_of_2(bp->attr.bp_len)) + if (!is_power_of_2(attr->bp_len)) return -EINVAL; - if (bp->attr.bp_addr & (bp->attr.bp_len - 1)) + if (attr->bp_addr & (attr->bp_len - 1)) return -EINVAL; if (!boot_cpu_has(X86_FEATURE_BPEXT)) @@ -312,8 +316,8 @@ static int arch_build_bp_info(struct perf_event *bp) * breakpoints, then we'll have to check for kprobe-blacklisted * addresses anywhere in the range. */ - info->mask = bp->attr.bp_len - 1; - info->len = X86_BREAKPOINT_LEN_1; + hw->mask = attr->bp_len - 1; + hw->len = X86_BREAKPOINT_LEN_1; } return 0; @@ -322,22 +326,23 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); unsigned int align; int ret; - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; - switch (info->len) { + switch (hw->len) { case X86_BREAKPOINT_LEN_1: align = 0; - if (info->mask) - align = info->mask; + if (hw->mask) + align = hw->mask; break; case X86_BREAKPOINT_LEN_2: align = 1; @@ -358,7 +363,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * Check that the low-order bits of the address are appropriate * for the alignment implied by len. */ - if (info->address & align) + if (hw->address & align) return -EINVAL; return 0; diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index ae38dccf0c8f..2b949f4fd4d8 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -105,14 +105,4 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig } #endif -#ifdef CONFIG_KPROBES_ON_FTRACE -extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb); -#else -static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - return 0; -} -#endif #endif diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6f4d42377fe5..b0d1e81c96bb 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -66,8 +66,6 @@ #include "common.h" -void jprobe_return_end(void); - DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -395,8 +393,6 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) - (u8 *) real; if ((s64) (s32) newdisp != newdisp) { pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); - pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", - src, real, insn->displacement.value); return 0; } disp = (u8 *) dest + insn_offset_displacement(insn); @@ -596,7 +592,6 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, * stepping. */ regs->ip = (unsigned long)p->ainsn.insn; - preempt_enable_no_resched(); return; } #endif @@ -640,8 +635,7 @@ static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs, * Raise a BUG or we'll continue in an endless reentering loop * and eventually a stack overflow. */ - printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n", - p->addr); + pr_err("Unrecoverable kprobe detected.\n"); dump_kprobe(p); BUG(); default: @@ -669,12 +663,10 @@ int kprobe_int3_handler(struct pt_regs *regs) addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t)); /* - * We don't want to be preempted for the entire - * duration of kprobe processing. We conditionally - * re-enable preemption at the end of this function, - * and also in reenter_kprobe() and setup_singlestep(). + * We don't want to be preempted for the entire duration of kprobe + * processing. Since int3 and debug trap disables irqs and we clear + * IF while singlestepping, it must be no preemptible. */ - preempt_disable(); kcb = get_kprobe_ctlblk(); p = get_kprobe(addr); @@ -690,13 +682,14 @@ int kprobe_int3_handler(struct pt_regs *regs) /* * If we have no pre-handler or it returned 0, we * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry - * for jprobe processing, so get out doing nothing - * more here. + * pre-handler and it returned non-zero, that means + * user handler setup registers to exit to another + * instruction, we must skip the single stepping. */ if (!p->pre_handler || !p->pre_handler(p, regs)) setup_singlestep(p, regs, kcb, 0); + else + reset_current_kprobe(); return 1; } } else if (*addr != BREAKPOINT_INSTRUCTION) { @@ -710,18 +703,9 @@ int kprobe_int3_handler(struct pt_regs *regs) * the original instruction. */ regs->ip = (unsigned long)addr; - preempt_enable_no_resched(); return 1; - } else if (kprobe_running()) { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - if (!skip_singlestep(p, regs, kcb)) - setup_singlestep(p, regs, kcb, 0); - return 1; - } } /* else: not a kprobe fault; let the kernel handle it */ - preempt_enable_no_resched(); return 0; } NOKPROBE_SYMBOL(kprobe_int3_handler); @@ -972,8 +956,6 @@ int kprobe_debug_handler(struct pt_regs *regs) } reset_current_kprobe(); out: - preempt_enable_no_resched(); - /* * if somebody else is singlestepping across a probe point, flags * will have TF set, in which case, continue the remaining processing @@ -1020,7 +1002,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) restore_previous_kprobe(kcb); else reset_current_kprobe(); - preempt_enable_no_resched(); } else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE || kcb->kprobe_status == KPROBE_HIT_SSDONE) { /* @@ -1083,93 +1064,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, } NOKPROBE_SYMBOL(kprobe_exceptions_notify); -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - unsigned long addr; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - kcb->jprobe_saved_sp = stack_addr(regs); - addr = (unsigned long)(kcb->jprobe_saved_sp); - - /* - * As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. - * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy - * raw stack chunk with redzones: - */ - __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr)); - regs->ip = (unsigned long)(jp->entry); - - /* - * jprobes use jprobe_return() which skips the normal return - * path of the function, and this messes up the accounting of the - * function graph tracer to get messed up. - * - * Pause function graph tracing while performing the jprobe function. - */ - pause_graph_tracing(); - return 1; -} -NOKPROBE_SYMBOL(setjmp_pre_handler); - -void jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - /* Unpoison stack redzones in the frames we are going to jump over. */ - kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp); - - asm volatile ( -#ifdef CONFIG_X86_64 - " xchg %%rbx,%%rsp \n" -#else - " xchgl %%ebx,%%esp \n" -#endif - " int3 \n" - " .globl jprobe_return_end\n" - " jprobe_return_end: \n" - " nop \n"::"b" - (kcb->jprobe_saved_sp):"memory"); -} -NOKPROBE_SYMBOL(jprobe_return); -NOKPROBE_SYMBOL(jprobe_return_end); - -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - u8 *addr = (u8 *) (regs->ip - 1); - struct jprobe *jp = container_of(p, struct jprobe, kp); - void *saved_sp = kcb->jprobe_saved_sp; - - if ((addr > (u8 *) jprobe_return) && - (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != saved_sp) { - struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; - printk(KERN_ERR - "current sp %p does not match saved sp %p\n", - stack_addr(regs), saved_sp); - printk(KERN_ERR "Saved registers for jprobe %p\n", jp); - show_regs(saved_regs); - printk(KERN_ERR "Current registers\n"); - show_regs(regs); - BUG(); - } - /* It's OK to start function graph tracing again */ - unpause_graph_tracing(); - *regs = kcb->jprobe_saved_regs; - __memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp)); - preempt_enable_no_resched(); - return 1; - } - return 0; -} -NOKPROBE_SYMBOL(longjmp_break_handler); - bool arch_within_kprobe_blacklist(unsigned long addr) { bool is_in_entry_trampoline_section = false; diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 8dc0161cec8f..ef819e19650b 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -25,36 +25,6 @@ #include "common.h" -static nokprobe_inline -void __skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb, unsigned long orig_ip) -{ - /* - * Emulate singlestep (and also recover regs->ip) - * as if there is a 5byte nop - */ - regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; - if (unlikely(p->post_handler)) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - p->post_handler(p, regs, 0); - } - __this_cpu_write(current_kprobe, NULL); - if (orig_ip) - regs->ip = orig_ip; -} - -int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - if (kprobe_ftrace(p)) { - __skip_singlestep(p, regs, kcb, 0); - preempt_enable_no_resched(); - return 1; - } - return 0; -} -NOKPROBE_SYMBOL(skip_singlestep); - /* Ftrace callback handler for kprobes -- called under preepmt disabed */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *regs) @@ -75,18 +45,25 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ regs->ip = ip + sizeof(kprobe_opcode_t); - /* To emulate trap based kprobes, preempt_disable here */ - preempt_disable(); __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; if (!p->pre_handler || !p->pre_handler(p, regs)) { - __skip_singlestep(p, regs, kcb, orig_ip); - preempt_enable_no_resched(); + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + regs->ip = orig_ip; } /* - * If pre_handler returns !0, it sets regs->ip and - * resets current kprobe, and keep preempt count +1. + * If pre_handler returns !0, it changes regs->ip. We have to + * skip emulating post_handler. */ + __this_cpu_write(current_kprobe, NULL); } } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 203d398802a3..eaf02f2e7300 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -491,7 +491,6 @@ int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; if (!reenter) reset_current_kprobe(); - preempt_enable_no_resched(); return 1; } return 0; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 5b2300b818af..a37bda38d205 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -154,7 +154,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) for (;;) { if (!n.halted) - prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE); if (hlist_unhashed(&n.link)) break; @@ -188,7 +188,7 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n) if (n->halted) smp_send_reschedule(n->cpu); else if (swq_has_sleeper(&n->wq)) - swake_up(&n->wq); + swake_up_one(&n->wq); } static void apf_task_wake_all(void) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index bf8d1eb7fca3..3b8e7c13c614 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -138,6 +138,7 @@ static unsigned long kvm_get_tsc_khz(void) src = &hv_clock[cpu].pvti; tsc_khz = pvclock_tsc_khz(src); put_cpu(); + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); return tsc_khz; } @@ -319,6 +320,8 @@ void __init kvmclock_init(void) printk(KERN_INFO "kvm-clock: Using msrs %x and %x", msr_kvm_system_time, msr_kvm_wall_clock); + pvclock_set_pvti_cpu0_va(hv_clock); + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); @@ -366,14 +369,11 @@ int __init kvm_setup_vsyscall_timeinfo(void) vcpu_time = &hv_clock[cpu].pvti; flags = pvclock_read_flags(vcpu_time); - if (!(flags & PVCLOCK_TSC_STABLE_BIT)) { - put_cpu(); - return 1; - } - - pvclock_set_pvti_cpu0_va(hv_clock); put_cpu(); + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) + return 1; + kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; #endif return 0; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 9edadabf04f6..9cb98f7b07c9 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -20,7 +20,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax"); #if defined(CONFIG_PARAVIRT_SPINLOCKS) DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)"); -DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax"); +DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax"); #endif unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c index 4dfd90a75e63..2e9006c1e240 100644 --- a/arch/x86/kernel/pci-iommu_table.c +++ b/arch/x86/kernel/pci-iommu_table.c @@ -60,7 +60,7 @@ void __init check_iommu_entries(struct iommu_table_entry *start, printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n", p->detect, q->detect); /* Heavy handed way..*/ - x->depend = 0; + x->depend = NULL; } } diff --git a/arch/x86/kernel/pcspeaker.c b/arch/x86/kernel/pcspeaker.c index da5190a1ea16..4a710ffffd9a 100644 --- a/arch/x86/kernel/pcspeaker.c +++ b/arch/x86/kernel/pcspeaker.c @@ -9,6 +9,6 @@ static __init int add_pcspkr(void) pd = platform_device_register_simple("pcspkr", -1, NULL, 0); - return IS_ERR(pd) ? PTR_ERR(pd) : 0; + return PTR_ERR_OR_ZERO(pd); } device_initcall(add_pcspkr); diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 093f2ea5dd56..7627455047c2 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -81,16 +81,6 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk); #ifdef CONFIG_HAVE_RELIABLE_STACKTRACE -#define STACKTRACE_DUMP_ONCE(task) ({ \ - static bool __section(.data.unlikely) __dumped; \ - \ - if (!__dumped) { \ - __dumped = true; \ - WARN_ON(1); \ - show_stack(task, NULL); \ - } \ -}) - static int __always_inline __save_stack_trace_reliable(struct stack_trace *trace, struct task_struct *task) @@ -99,30 +89,25 @@ __save_stack_trace_reliable(struct stack_trace *trace, struct pt_regs *regs; unsigned long addr; - for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state); + for (unwind_start(&state, task, NULL, NULL); + !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) { regs = unwind_get_entry_regs(&state, NULL); if (regs) { + /* Success path for user tasks */ + if (user_mode(regs)) + goto success; + /* * Kernel mode registers on the stack indicate an * in-kernel interrupt or exception (e.g., preemption * or a page fault), which can make frame pointers * unreliable. */ - if (!user_mode(regs)) - return -EINVAL; - /* - * The last frame contains the user mode syscall - * pt_regs. Skip it and finish the unwind. - */ - unwind_next_frame(&state); - if (!unwind_done(&state)) { - STACKTRACE_DUMP_ONCE(task); + if (IS_ENABLED(CONFIG_FRAME_POINTER)) return -EINVAL; - } - break; } addr = unwind_get_return_address(&state); @@ -132,21 +117,22 @@ __save_stack_trace_reliable(struct stack_trace *trace, * generated code which __kernel_text_address() doesn't know * about. */ - if (!addr) { - STACKTRACE_DUMP_ONCE(task); + if (!addr) return -EINVAL; - } if (save_stack_address(trace, addr, false)) return -EINVAL; } /* Check for stack corruption */ - if (unwind_error(&state)) { - STACKTRACE_DUMP_ONCE(task); + if (unwind_error(&state)) + return -EINVAL; + + /* Success path for non-user tasks, i.e. kthreads and idle tasks */ + if (!(task->flags & (PF_KTHREAD | PF_IDLE))) return -EINVAL; - } +success: if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index feb28fee6cea..26038eacf74a 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -198,7 +198,7 @@ static int orc_sort_cmp(const void *_a, const void *_b) * whitelisted .o files which didn't get objtool generation. */ orc_a = cur_orc_table + (a - cur_orc_ip_table); - return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1; + return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1; } #ifdef CONFIG_MODULES @@ -352,7 +352,7 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip, prev_sp = state->sp; + unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -363,9 +363,9 @@ bool unwind_next_frame(struct unwind_state *state) /* Don't let modules unload while we're reading their ORC data. */ preempt_disable(); - /* Have we reached the end? */ + /* End-of-stack check for user tasks: */ if (state->regs && user_mode(state->regs)) - goto done; + goto the_end; /* * Find the orc_entry associated with the text address. @@ -374,9 +374,16 @@ bool unwind_next_frame(struct unwind_state *state) * calls and calls to noreturn functions. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); - if (!orc || orc->sp_reg == ORC_REG_UNDEFINED) - goto done; - orig_ip = state->ip; + if (!orc) + goto err; + + /* End-of-stack check for kernel threads: */ + if (orc->sp_reg == ORC_REG_UNDEFINED) { + if (!orc->end) + goto err; + + goto the_end; + } /* Find the previous frame's stack: */ switch (orc->sp_reg) { @@ -402,7 +409,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg R10 at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->r10; break; @@ -411,7 +418,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg R13 at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->r13; break; @@ -420,7 +427,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg DI at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->di; break; @@ -429,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg DX at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->dx; break; @@ -437,12 +444,12 @@ bool unwind_next_frame(struct unwind_state *state) default: orc_warn("unknown SP base reg %d for ip %pB\n", orc->sp_reg, (void *)state->ip); - goto done; + goto err; } if (indirect) { if (!deref_stack_reg(state, sp, &sp)) - goto done; + goto err; } /* Find IP, SP and possibly regs: */ @@ -451,7 +458,7 @@ bool unwind_next_frame(struct unwind_state *state) ip_p = sp - sizeof(long); if (!deref_stack_reg(state, ip_p, &state->ip)) - goto done; + goto err; state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, state->ip, (void *)ip_p); @@ -465,7 +472,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); - goto done; + goto err; } state->regs = (struct pt_regs *)sp; @@ -477,7 +484,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference iret registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); - goto done; + goto err; } state->regs = (void *)sp - IRET_FRAME_OFFSET; @@ -500,18 +507,18 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_PREV_SP: if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp)) - goto done; + goto err; break; case ORC_REG_BP: if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp)) - goto done; + goto err; break; default: orc_warn("unknown BP base reg %d for ip %pB\n", orc->bp_reg, (void *)orig_ip); - goto done; + goto err; } /* Prevent a recursive loop due to bad ORC data: */ @@ -520,13 +527,16 @@ bool unwind_next_frame(struct unwind_state *state) state->sp <= prev_sp) { orc_warn("stack going in the wrong direction? ip=%pB\n", (void *)orig_ip); - goto done; + goto err; } preempt_enable(); return true; -done: +err: + state->error = true; + +the_end: preempt_enable(); state->stack_info.type = STACK_TYPE_UNKNOWN; return false; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 92fd433c50b9..1bbec387d289 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -85,7 +85,7 @@ config KVM_AMD_SEV def_bool y bool "AMD Secure Encrypted Virtualization (SEV) support" depends on KVM_AMD && X86_64 - depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP + depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) ---help--- Provides support for launching Encrypted VMs on AMD processors. diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index b5cd8465d44f..d536d457517b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1379,7 +1379,7 @@ static void apic_timer_expired(struct kvm_lapic *apic) * using swait_active() is safe. */ if (swait_active(q)) - swake_up(q); + swake_up_one(q); if (apic_lvtt_tscdeadline(apic)) ktimer->expired_tscdeadline = ktimer->tscdeadline; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d594690d8b95..6b8f11521c41 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -890,7 +890,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - page = (void *)__get_free_page(GFP_KERNEL); + page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT); if (!page) return -ENOMEM; cache->objects[cache->nobjs++] = page; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1689f433f3a0..5d8e317c2b04 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2571,6 +2571,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); + unsigned long fs_base, kernel_gs_base; #endif int i; @@ -2586,12 +2587,20 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel; #ifdef CONFIG_X86_64 - save_fsgs_for_kvm(); - vmx->host_state.fs_sel = current->thread.fsindex; - vmx->host_state.gs_sel = current->thread.gsindex; -#else - savesegment(fs, vmx->host_state.fs_sel); - savesegment(gs, vmx->host_state.gs_sel); + if (likely(is_64bit_mm(current->mm))) { + save_fsgs_for_kvm(); + vmx->host_state.fs_sel = current->thread.fsindex; + vmx->host_state.gs_sel = current->thread.gsindex; + fs_base = current->thread.fsbase; + kernel_gs_base = current->thread.gsbase; + } else { +#endif + savesegment(fs, vmx->host_state.fs_sel); + savesegment(gs, vmx->host_state.gs_sel); +#ifdef CONFIG_X86_64 + fs_base = read_msr(MSR_FS_BASE); + kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); + } #endif if (!(vmx->host_state.fs_sel & 7)) { vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel); @@ -2611,10 +2620,10 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) savesegment(ds, vmx->host_state.ds_sel); savesegment(es, vmx->host_state.es_sel); - vmcs_writel(HOST_FS_BASE, current->thread.fsbase); + vmcs_writel(HOST_FS_BASE, fs_base); vmcs_writel(HOST_GS_BASE, cpu_kernelmode_gs_base(cpu)); - vmx->msr_host_kernel_gs_base = current->thread.gsbase; + vmx->msr_host_kernel_gs_base = kernel_gs_base; if (is_long_mode(&vmx->vcpu)) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else @@ -4322,11 +4331,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) vmcs_conf->order = get_order(vmcs_conf->size); vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; - /* KVM supports Enlightened VMCS v1 only */ - if (static_branch_unlikely(&enable_evmcs)) - vmcs_conf->revision_id = KVM_EVMCS_VERSION; - else - vmcs_conf->revision_id = vmx_msr_low; + vmcs_conf->revision_id = vmx_msr_low; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; @@ -4396,7 +4401,13 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) return NULL; vmcs = page_address(pages); memset(vmcs, 0, vmcs_config.size); - vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */ + + /* KVM supports Enlightened VMCS v1 only */ + if (static_branch_unlikely(&enable_evmcs)) + vmcs->revision_id = KVM_EVMCS_VERSION; + else + vmcs->revision_id = vmcs_config.revision_id; + return vmcs; } @@ -4564,6 +4575,19 @@ static __init int alloc_kvm_area(void) return -ENOMEM; } + /* + * When eVMCS is enabled, alloc_vmcs_cpu() sets + * vmcs->revision_id to KVM_EVMCS_VERSION instead of + * revision_id reported by MSR_IA32_VMX_BASIC. + * + * However, even though not explictly documented by + * TLFS, VMXArea passed as VMXON argument should + * still be marked with revision_id reported by + * physical CPU. + */ + if (static_branch_unlikely(&enable_evmcs)) + vmcs->revision_id = vmcs_config.revision_id; + per_cpu(vmxarea, cpu) = vmcs; } return 0; @@ -7869,6 +7893,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + vmx->nested.vpid02 = allocate_vpid(); + vmx->nested.vmxon = true; return 0; @@ -8456,21 +8482,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) /* Emulate the VMPTRST instruction */ static int handle_vmptrst(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - gva_t vmcs_gva; + unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION); + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr; struct x86_exception e; + gva_t gva; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, true, &vmcs_gva)) + if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva)) return 1; /* *_system ok, nested_vmx_check_permission has verified cpl=0 */ - if (kvm_write_guest_virt_system(vcpu, vmcs_gva, - (void *)&to_vmx(vcpu)->nested.current_vmptr, - sizeof(u64), &e)) { + if (kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr, + sizeof(gpa_t), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } @@ -10346,11 +10371,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto free_vmcs; } - if (nested) { + if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, kvm_vcpu_apicv_active(&vmx->vcpu)); - vmx->nested.vpid02 = allocate_vpid(); - } vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; @@ -10367,7 +10390,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return &vmx->vcpu; free_vmcs: - free_vpid(vmx->nested.vpid02); free_loaded_vmcs(vmx->loaded_vmcs); free_msrs: kfree(vmx->guest_msrs); @@ -11753,7 +11775,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u32 msr_entry_idx; u32 exit_qual; int r; @@ -11775,10 +11796,10 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu) nested_get_vmcs12_pages(vcpu, vmcs12); r = EXIT_REASON_MSR_LOAD_FAIL; - msr_entry_idx = nested_vmx_load_msr(vcpu, - vmcs12->vm_entry_msr_load_addr, - vmcs12->vm_entry_msr_load_count); - if (msr_entry_idx) + exit_qual = nested_vmx_load_msr(vcpu, + vmcs12->vm_entry_msr_load_addr, + vmcs12->vm_entry_msr_load_count); + if (exit_qual) goto fail; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0046aa70205a..2b812b3c5088 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1097,6 +1097,7 @@ static u32 msr_based_features[] = { MSR_F10H_DECFG, MSR_IA32_UCODE_REV, + MSR_IA32_ARCH_CAPABILITIES, }; static unsigned int num_msr_based_features; @@ -1105,7 +1106,8 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { case MSR_IA32_UCODE_REV: - rdmsrl(msr->index, msr->data); + case MSR_IA32_ARCH_CAPABILITIES: + rdmsrl_safe(msr->index, &msr->data); break; default: if (kvm_x86_ops->get_msr_feature(msr)) diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 298ef1479240..3b24dc05251c 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -256,7 +256,7 @@ ENTRY(__memcpy_mcsafe) /* Copy successful. Return zero */ .L_done_memcpy_trap: - xorq %rax, %rax + xorl %eax, %eax ret ENDPROC(__memcpy_mcsafe) EXPORT_SYMBOL_GPL(__memcpy_mcsafe) diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 34a2a3bfde9c..b54d52a2d00a 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -61,7 +61,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei, eb->nid = nid; if (emu_nid_to_phys[nid] == NUMA_NO_NODE) - emu_nid_to_phys[nid] = nid; + emu_nid_to_phys[nid] = pb->nid; pb->start += size; if (pb->start >= pb->end) { @@ -198,40 +198,73 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) return end; } +static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes) +{ + unsigned long max_pfn = PHYS_PFN(max_addr); + unsigned long base_pfn = PHYS_PFN(base); + unsigned long hole_pfns = PHYS_PFN(hole); + + return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes); +} + /* * Sets up fake nodes of `size' interleaved over physical nodes ranging from * `addr' to `max_addr'. * * Returns zero on success or negative on error. */ -static int __init split_nodes_size_interleave(struct numa_meminfo *ei, +static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei, struct numa_meminfo *pi, - u64 addr, u64 max_addr, u64 size) + u64 addr, u64 max_addr, u64 size, + int nr_nodes, struct numa_memblk *pblk, + int nid) { nodemask_t physnode_mask = numa_nodes_parsed; + int i, ret, uniform = 0; u64 min_size; - int nid = 0; - int i, ret; - if (!size) + if ((!size && !nr_nodes) || (nr_nodes && !pblk)) return -1; + /* - * The limit on emulated nodes is MAX_NUMNODES, so the size per node is - * increased accordingly if the requested size is too small. This - * creates a uniform distribution of node sizes across the entire - * machine (but not necessarily over physical nodes). + * In the 'uniform' case split the passed in physical node by + * nr_nodes, in the non-uniform case, ignore the passed in + * physical block and try to create nodes of at least size + * @size. + * + * In the uniform case, split the nodes strictly by physical + * capacity, i.e. ignore holes. In the non-uniform case account + * for holes and treat @size as a minimum floor. */ - min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES; - min_size = max(min_size, FAKE_NODE_MIN_SIZE); - if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size) - min_size = (min_size + FAKE_NODE_MIN_SIZE) & - FAKE_NODE_MIN_HASH_MASK; + if (!nr_nodes) + nr_nodes = MAX_NUMNODES; + else { + nodes_clear(physnode_mask); + node_set(pblk->nid, physnode_mask); + uniform = 1; + } + + if (uniform) { + min_size = uniform_size(max_addr, addr, 0, nr_nodes); + size = min_size; + } else { + /* + * The limit on emulated nodes is MAX_NUMNODES, so the + * size per node is increased accordingly if the + * requested size is too small. This creates a uniform + * distribution of node sizes across the entire machine + * (but not necessarily over physical nodes). + */ + min_size = uniform_size(max_addr, addr, + mem_hole_size(addr, max_addr), nr_nodes); + } + min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE); if (size < min_size) { pr_err("Fake node size %LuMB too small, increasing to %LuMB\n", size >> 20, min_size >> 20); size = min_size; } - size &= FAKE_NODE_MIN_HASH_MASK; + size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE); /* * Fill physical nodes with fake nodes of size until there is no memory @@ -248,10 +281,14 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, node_clear(i, physnode_mask); continue; } + start = pi->blk[phys_blk].start; limit = pi->blk[phys_blk].end; - end = find_end_of_node(start, limit, size); + if (uniform) + end = start + size; + else + end = find_end_of_node(start, limit, size); /* * If there won't be at least FAKE_NODE_MIN_SIZE of * non-reserved memory in ZONE_DMA32 for the next node, @@ -266,7 +303,8 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, * next node, this one must extend to the end of the * physical node. */ - if (limit - end - mem_hole_size(end, limit) < size) + if ((limit - end - mem_hole_size(end, limit) < size) + && !uniform) end = limit; ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES, @@ -276,7 +314,15 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, return ret; } } - return 0; + return nid; +} + +static int __init split_nodes_size_interleave(struct numa_meminfo *ei, + struct numa_meminfo *pi, + u64 addr, u64 max_addr, u64 size) +{ + return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size, + 0, NULL, NUMA_NO_NODE); } int __init setup_emu2phys_nid(int *dfl_phys_nid) @@ -346,7 +392,28 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) * the fixed node size. Otherwise, if it is just a single number N, * split the system RAM into N fake nodes. */ - if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) { + if (strchr(emu_cmdline, 'U')) { + nodemask_t physnode_mask = numa_nodes_parsed; + unsigned long n; + int nid = 0; + + n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); + ret = -1; + for_each_node_mask(i, physnode_mask) { + ret = split_nodes_size_interleave_uniform(&ei, &pi, + pi.blk[i].start, pi.blk[i].end, 0, + n, &pi.blk[i], nid); + if (ret < 0) + break; + if (ret < n) { + pr_info("%s: phys: %d only got %d of %ld nodes, failing\n", + __func__, i, ret, n); + ret = -1; + break; + } + nid = ret; + } + } else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) { u64 size; size = memparse(emu_cmdline, &emu_cmdline); diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 55799873ebe5..8f6cc71e0848 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1441,8 +1441,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth) /* sub esp,STACK_SIZE */ EMIT2_off32(0x81, 0xEC, STACK_SIZE); - /* sub ebp,SCRATCH_SIZE+4+12*/ - EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16); + /* sub ebp,SCRATCH_SIZE+12*/ + EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 12); /* xor ebx,ebx */ EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX)); @@ -1475,8 +1475,8 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) /* mov edx,dword ptr [ebp+off]*/ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1])); - /* add ebp,SCRATCH_SIZE+4+12*/ - EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16); + /* add ebp,SCRATCH_SIZE+12*/ + EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 12); /* mov ebx,dword ptr [ebp-12]*/ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 77873ce700ae..ee5d08f25ce4 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -417,7 +417,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va) if (!(md->attribute & EFI_MEMORY_WB)) flags |= _PAGE_PCD; - if (sev_active()) + if (sev_active() && md->type != EFI_MEMORY_MAPPED_IO) flags |= _PAGE_ENC; pfn = md->phys_addr >> PAGE_SHIFT; @@ -636,6 +636,8 @@ void efi_switch_mm(struct mm_struct *mm) #ifdef CONFIG_EFI_MIXED extern efi_status_t efi64_thunk(u32, ...); +static DEFINE_SPINLOCK(efi_runtime_lock); + #define runtime_service32(func) \ ({ \ u32 table = (u32)(unsigned long)efi.systab; \ @@ -657,17 +659,14 @@ extern efi_status_t efi64_thunk(u32, ...); #define efi_thunk(f, ...) \ ({ \ efi_status_t __s; \ - unsigned long __flags; \ u32 __func; \ \ - local_irq_save(__flags); \ arch_efi_call_virt_setup(); \ \ __func = runtime_service32(f); \ __s = efi64_thunk(__func, __VA_ARGS__); \ \ arch_efi_call_virt_teardown(); \ - local_irq_restore(__flags); \ \ __s; \ }) @@ -702,14 +701,17 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc) { efi_status_t status; u32 phys_tm, phys_tc; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_tm = virt_to_phys_or_null(tm); phys_tc = virt_to_phys_or_null(tc); status = efi_thunk(get_time, phys_tm, phys_tc); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -719,13 +721,16 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm) { efi_status_t status; u32 phys_tm; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_tm = virt_to_phys_or_null(tm); status = efi_thunk(set_time, phys_tm); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -737,8 +742,10 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, { efi_status_t status; u32 phys_enabled, phys_pending, phys_tm; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_enabled = virt_to_phys_or_null(enabled); phys_pending = virt_to_phys_or_null(pending); @@ -747,6 +754,7 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, status = efi_thunk(get_wakeup_time, phys_enabled, phys_pending, phys_tm); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -757,13 +765,16 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) { efi_status_t status; u32 phys_tm; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_tm = virt_to_phys_or_null(tm); status = efi_thunk(set_wakeup_time, enabled, phys_tm); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -781,6 +792,9 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, efi_status_t status; u32 phys_name, phys_vendor, phys_attr; u32 phys_data_size, phys_data; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_data_size = virt_to_phys_or_null(data_size); phys_vendor = virt_to_phys_or_null(vendor); @@ -791,6 +805,8 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, status = efi_thunk(get_variable, phys_name, phys_vendor, phys_attr, phys_data_size, phys_data); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -800,6 +816,34 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, { u32 phys_name, phys_vendor, phys_data; efi_status_t status; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); + + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); + phys_vendor = virt_to_phys_or_null(vendor); + phys_data = virt_to_phys_or_null_size(data, data_size); + + /* If data_size is > sizeof(u32) we've got problems */ + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); + + spin_unlock_irqrestore(&efi_runtime_lock, flags); + + return status; +} + +static efi_status_t +efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, + void *data) +{ + u32 phys_name, phys_vendor, phys_data; + efi_status_t status; + unsigned long flags; + + if (!spin_trylock_irqsave(&efi_runtime_lock, flags)) + return EFI_NOT_READY; phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); phys_vendor = virt_to_phys_or_null(vendor); @@ -809,6 +853,8 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, status = efi_thunk(set_variable, phys_name, phys_vendor, attr, data_size, phys_data); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -819,6 +865,9 @@ efi_thunk_get_next_variable(unsigned long *name_size, { efi_status_t status; u32 phys_name_size, phys_name, phys_vendor; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_name_size = virt_to_phys_or_null(name_size); phys_vendor = virt_to_phys_or_null(vendor); @@ -827,6 +876,8 @@ efi_thunk_get_next_variable(unsigned long *name_size, status = efi_thunk(get_next_variable, phys_name_size, phys_name, phys_vendor); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -835,10 +886,15 @@ efi_thunk_get_next_high_mono_count(u32 *count) { efi_status_t status; u32 phys_count; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_count = virt_to_phys_or_null(count); status = efi_thunk(get_next_high_mono_count, phys_count); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -847,10 +903,15 @@ efi_thunk_reset_system(int reset_type, efi_status_t status, unsigned long data_size, efi_char16_t *data) { u32 phys_data; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_data = virt_to_phys_or_null_size(data, data_size); efi_thunk(reset_system, reset_type, status, data_size, phys_data); + + spin_unlock_irqrestore(&efi_runtime_lock, flags); } static efi_status_t @@ -872,10 +933,40 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space, { efi_status_t status; u32 phys_storage, phys_remaining, phys_max; + unsigned long flags; + + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + spin_lock_irqsave(&efi_runtime_lock, flags); + + phys_storage = virt_to_phys_or_null(storage_space); + phys_remaining = virt_to_phys_or_null(remaining_space); + phys_max = virt_to_phys_or_null(max_variable_size); + + status = efi_thunk(query_variable_info, attr, phys_storage, + phys_remaining, phys_max); + + spin_unlock_irqrestore(&efi_runtime_lock, flags); + + return status; +} + +static efi_status_t +efi_thunk_query_variable_info_nonblocking(u32 attr, u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) +{ + efi_status_t status; + u32 phys_storage, phys_remaining, phys_max; + unsigned long flags; if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) return EFI_UNSUPPORTED; + if (!spin_trylock_irqsave(&efi_runtime_lock, flags)) + return EFI_NOT_READY; + phys_storage = virt_to_phys_or_null(storage_space); phys_remaining = virt_to_phys_or_null(remaining_space); phys_max = virt_to_phys_or_null(max_variable_size); @@ -883,6 +974,8 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space, status = efi_thunk(query_variable_info, attr, phys_storage, phys_remaining, phys_max); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -908,9 +1001,11 @@ void efi_thunk_runtime_setup(void) efi.get_variable = efi_thunk_get_variable; efi.get_next_variable = efi_thunk_get_next_variable; efi.set_variable = efi_thunk_set_variable; + efi.set_variable_nonblocking = efi_thunk_set_variable_nonblocking; efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count; efi.reset_system = efi_thunk_reset_system; efi.query_variable_info = efi_thunk_query_variable_info; + efi.query_variable_info_nonblocking = efi_thunk_query_variable_info_nonblocking; efi.update_capsule = efi_thunk_update_capsule; efi.query_capsule_caps = efi_thunk_query_capsule_caps; } diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 36c1f8b9f7e0..844d31cb8a0c 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -105,12 +105,11 @@ early_param("efi_no_storage_paranoia", setup_storage_paranoia); */ void efi_delete_dummy_variable(void) { - efi.set_variable((efi_char16_t *)efi_dummy_name, - &EFI_DUMMY_GUID, - EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS, - 0, NULL); + efi.set_variable_nonblocking((efi_char16_t *)efi_dummy_name, + &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, 0, NULL); } /* @@ -249,7 +248,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) int num_entries; void *new; - if (efi_mem_desc_lookup(addr, &md)) { + if (efi_mem_desc_lookup(addr, &md) || + md.type != EFI_BOOT_SERVICES_DATA) { pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr); return; } diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c index 7c3077e58fa0..f0e920fb98ad 100644 --- a/arch/x86/platform/olpc/olpc.c +++ b/arch/x86/platform/olpc/olpc.c @@ -311,10 +311,8 @@ static int __init add_xo1_platform_devices(void) return PTR_ERR(pdev); pdev = platform_device_register_simple("olpc-xo1", -1, NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - return 0; + return PTR_ERR_OR_ZERO(pdev); } static int olpc_xo1_ec_probe(struct platform_device *pdev) diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index ca446da48fd2..e26dfad507c8 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1607,8 +1607,6 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr, *tunables[cnt].tunp = val; continue; } - if (q == p) - break; } return 0; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index ce8da3a0412c..fd369a6e9ff8 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -137,7 +137,7 @@ ENTRY(restore_registers) /* Saved in save_processor_state. */ lgdt saved_context_gdt_desc(%rax) - xorq %rax, %rax + xorl %eax, %eax /* tell the hibernation core that we've just restored the memory */ movq %rax, in_suspend(%rip) diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index 744afdc18cf3..56c44d865f7b 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -16,7 +16,7 @@ static int __init gate_vma_init(void) if (!FIXADDR_USER_START) return 0; - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/arch/x86/um/vdso/.gitignore b/arch/x86/um/vdso/.gitignore index 9cac6d072199..f8b69d84238e 100644 --- a/arch/x86/um/vdso/.gitignore +++ b/arch/x86/um/vdso/.gitignore @@ -1,2 +1 @@ -vdso-syms.lds vdso.lds diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index b2d6967262b2..822ccdba93ad 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -53,22 +53,6 @@ $(vobjs): KBUILD_CFLAGS += $(CFL) CFLAGS_REMOVE_vdso-note.o = -pg -fprofile-arcs -ftest-coverage CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage -targets += vdso-syms.lds -extra-$(VDSO64-y) += vdso-syms.lds - -# -# Match symbols in the DSO that look like VDSO*; produce a file of constants. -# -sed-vdsosym := -e 's/^00*/0/' \ - -e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p' -quiet_cmd_vdsosym = VDSOSYM $@ -define cmd_vdsosym - $(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ -endef - -$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE - $(call if_changed,vdsosym) - # # The DSO images are built using a special linker script. # diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h index e7a23f2a519a..7de0149e1cf7 100644 --- a/arch/xtensa/include/asm/atomic.h +++ b/arch/xtensa/include/asm/atomic.h @@ -197,107 +197,9 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -/** - * atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0) - -/** - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc(v) atomic_add(1,(v)) - -/** - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc_return(v) atomic_add_return(1,(v)) - -/** - * atomic_dec - decrement atomic variable - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec(v) atomic_sub(1,(v)) - -/** - * atomic_dec_return - decrement atomic variable - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec_return(v) atomic_sub_return(1,(v)) - -/** - * atomic_dec_and_test - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic_dec_and_test(v) (atomic_sub_return(1,(v)) == 0) - -/** - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_add_return(1,(v)) == 0) - -/** - * atomic_add_negative - add and test if negative - * @v: pointer of type atomic_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic_add_negative(i,v) (atomic_add_return((i),(v)) < 0) - #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #endif /* __KERNEL__ */ #endif /* _XTENSA_ATOMIC_H */ diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h index dbe3053b284a..9f119c1ca0b5 100644 --- a/arch/xtensa/include/asm/hw_breakpoint.h +++ b/arch/xtensa/include/asm/hw_breakpoint.h @@ -30,13 +30,16 @@ struct arch_hw_breakpoint { u16 type; }; +struct perf_event_attr; struct perf_event; struct pt_regs; struct task_struct; int hw_breakpoint_slots(int type); -int arch_check_bp_in_kernelspace(struct perf_event *bp); -int arch_validate_hwbkpt_settings(struct perf_event *bp); +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c index b35656ab7dbd..c2e387c19cda 100644 --- a/arch/xtensa/kernel/hw_breakpoint.c +++ b/arch/xtensa/kernel/hw_breakpoint.c @@ -33,14 +33,13 @@ int hw_breakpoint_slots(int type) } } -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = bp->attr.bp_len; + va = hw->address; + len = hw->len; return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -48,50 +47,41 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) /* * Construct an arch_hw_breakpoint from a perf_event. */ -static int arch_build_bp_info(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_X: - info->type = XTENSA_BREAKPOINT_EXECUTE; + hw->type = XTENSA_BREAKPOINT_EXECUTE; break; case HW_BREAKPOINT_R: - info->type = XTENSA_BREAKPOINT_LOAD; + hw->type = XTENSA_BREAKPOINT_LOAD; break; case HW_BREAKPOINT_W: - info->type = XTENSA_BREAKPOINT_STORE; + hw->type = XTENSA_BREAKPOINT_STORE; break; case HW_BREAKPOINT_RW: - info->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE; + hw->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE; break; default: return -EINVAL; } /* Len */ - info->len = bp->attr.bp_len; - if (info->len < 1 || info->len > 64 || !is_power_of_2(info->len)) + hw->len = attr->bp_len; + if (hw->len < 1 || hw->len > 64 || !is_power_of_2(hw->len)) return -EINVAL; /* Address */ - info->address = bp->attr.bp_addr; - if (info->address & (info->len - 1)) + hw->address = attr->bp_addr; + if (hw->address & (hw->len - 1)) return -EINVAL; return 0; } -int arch_validate_hwbkpt_settings(struct perf_event *bp) -{ - int ret; - - /* Build the arch_hw_breakpoint. */ - ret = arch_build_bp_info(bp); - return ret; -} - int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data) { diff --git a/block/bio.c b/block/bio.c index 67eff5eddc49..047c5dca6d90 100644 --- a/block/bio.c +++ b/block/bio.c @@ -903,25 +903,27 @@ int bio_add_page(struct bio *bio, struct page *page, EXPORT_SYMBOL(bio_add_page); /** - * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * - * Pins as many pages from *iter and appends them to @bio's bvec array. The + * Pins pages from *iter and appends them to @bio's bvec array. The * pages will have to be released using put_page() when done. + * For multi-segment *iter, this function only adds pages from the + * the next non-empty segment of the iov iterator. */ -int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { - unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; + unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; - size_t offset, diff; + size_t offset; ssize_t size; size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; - nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE; + idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE; /* * Deep magic below: We need to walk the pinned pages backwards @@ -934,21 +936,46 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) bio->bi_iter.bi_size += size; bio->bi_vcnt += nr_pages; - diff = (nr_pages * PAGE_SIZE - offset) - size; - while (nr_pages--) { - bv[nr_pages].bv_page = pages[nr_pages]; - bv[nr_pages].bv_len = PAGE_SIZE; - bv[nr_pages].bv_offset = 0; + while (idx--) { + bv[idx].bv_page = pages[idx]; + bv[idx].bv_len = PAGE_SIZE; + bv[idx].bv_offset = 0; } bv[0].bv_offset += offset; bv[0].bv_len -= offset; - if (diff) - bv[bio->bi_vcnt - 1].bv_len -= diff; + bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size; iov_iter_advance(iter, size); return 0; } + +/** + * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * @bio: bio to add pages to + * @iter: iov iterator describing the region to be mapped + * + * Pins pages from *iter and appends them to @bio's bvec array. The + * pages will have to be released using put_page() when done. + * The function tries, but does not guarantee, to pin as many pages as + * fit into the bio, or are requested in *iter, whatever is smaller. + * If MM encounters an error pinning the requested pages, it stops. + * Error is returned only if 0 pages could be pinned. + */ +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +{ + unsigned short orig_vcnt = bio->bi_vcnt; + + do { + int ret = __bio_iov_iter_get_pages(bio, iter); + + if (unlikely(ret)) + return bio->bi_vcnt > orig_vcnt ? 0 : ret; + + } while (iov_iter_count(iter) && !bio_full(bio)); + + return 0; +} EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); static void submit_bio_wait_endio(struct bio *bio) @@ -1866,6 +1893,7 @@ struct bio *bio_split(struct bio *bio, int sectors, bio_integrity_trim(split); bio_advance(bio, split->bi_iter.bi_size); + bio->bi_iter.bi_done = 0; if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); diff --git a/block/blk-core.c b/block/blk-core.c index f84a9b7b6f5a..ee33590f54eb 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2155,11 +2155,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) if (part->policy && op_is_write(bio_op(bio))) { char b[BDEVNAME_SIZE]; - printk(KERN_ERR + WARN_ONCE(1, "generic_make_request: Trying to write " "to read-only block-device %s (partno %d)\n", bio_devname(bio, b), part->partno); - return true; + /* Older lvm-tools actually trigger this */ + return false; } return false; diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 09b2ee6694fb..3de0836163c2 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -271,7 +271,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * test and set the bit before assining ->rqs[]. */ rq = tags->rqs[bitnr]; - if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) + if (rq && blk_mq_request_started(rq)) iter_data->fn(rq, iter_data->data, reserved); return true; diff --git a/block/blk-mq.c b/block/blk-mq.c index 95919268564b..654b0dc7e001 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -558,10 +558,8 @@ static void __blk_mq_complete_request(struct request *rq) bool shared = false; int cpu; - if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) != - MQ_RQ_IN_FLIGHT) + if (!blk_mq_mark_complete(rq)) return; - if (rq->internal_tag != -1) blk_mq_sched_completed_request(rq); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 314c52c967e5..c166f424871c 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1155,8 +1155,10 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags, /* make one iovec available as scatterlist */ err = af_alg_make_sg(&rsgl->sgl, &msg->msg_iter, seglen); - if (err < 0) + if (err < 0) { + rsgl->sg_num_bytes = 0; return err; + } /* chain the new scatterlist with previous one */ if (areq->last_rsgl) diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index f8fecfec5df9..9706613eecf9 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -879,6 +879,7 @@ static void acpi_lpss_dismiss(struct device *dev) #define LPSS_GPIODEF0_DMA_LLP BIT(13) static DEFINE_MUTEX(lpss_iosf_mutex); +static bool lpss_iosf_d3_entered; static void lpss_iosf_enter_d3_state(void) { @@ -921,6 +922,9 @@ static void lpss_iosf_enter_d3_state(void) iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE, LPSS_IOSF_GPIODEF0, value1, mask1); + + lpss_iosf_d3_entered = true; + exit: mutex_unlock(&lpss_iosf_mutex); } @@ -935,6 +939,11 @@ static void lpss_iosf_exit_d3_state(void) mutex_lock(&lpss_iosf_mutex); + if (!lpss_iosf_d3_entered) + goto exit; + + lpss_iosf_d3_entered = false; + iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE, LPSS_IOSF_GPIODEF0, value1, mask1); @@ -944,13 +953,13 @@ static void lpss_iosf_exit_d3_state(void) iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO1, MBI_CFG_WRITE, LPSS_IOSF_PMCSR, value2, mask2); +exit: mutex_unlock(&lpss_iosf_mutex); } -static int acpi_lpss_suspend(struct device *dev, bool runtime) +static int acpi_lpss_suspend(struct device *dev, bool wakeup) { struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); - bool wakeup = runtime || device_may_wakeup(dev); int ret; if (pdata->dev_desc->flags & LPSS_SAVE_CTX) @@ -963,14 +972,14 @@ static int acpi_lpss_suspend(struct device *dev, bool runtime) * wrong status for devices being about to be powered off. See * lpss_iosf_enter_d3_state() for further information. */ - if ((runtime || !pm_suspend_via_firmware()) && + if (acpi_target_system_state() == ACPI_STATE_S0 && lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) lpss_iosf_enter_d3_state(); return ret; } -static int acpi_lpss_resume(struct device *dev, bool runtime) +static int acpi_lpss_resume(struct device *dev) { struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); int ret; @@ -979,8 +988,7 @@ static int acpi_lpss_resume(struct device *dev, bool runtime) * This call is kept first to be in symmetry with * acpi_lpss_runtime_suspend() one. */ - if ((runtime || !pm_resume_via_firmware()) && - lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) + if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) lpss_iosf_exit_d3_state(); ret = acpi_dev_resume(dev); @@ -1004,12 +1012,12 @@ static int acpi_lpss_suspend_late(struct device *dev) return 0; ret = pm_generic_suspend_late(dev); - return ret ? ret : acpi_lpss_suspend(dev, false); + return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev)); } static int acpi_lpss_resume_early(struct device *dev) { - int ret = acpi_lpss_resume(dev, false); + int ret = acpi_lpss_resume(dev); return ret ? ret : pm_generic_resume_early(dev); } @@ -1024,7 +1032,7 @@ static int acpi_lpss_runtime_suspend(struct device *dev) static int acpi_lpss_runtime_resume(struct device *dev) { - int ret = acpi_lpss_resume(dev, true); + int ret = acpi_lpss_resume(dev); return ret ? ret : pm_generic_runtime_resume(dev); } diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c index bc5f05906bd1..44f35ab3347d 100644 --- a/drivers/acpi/acpica/psloop.c +++ b/drivers/acpi/acpica/psloop.c @@ -497,6 +497,18 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state) status = acpi_ps_create_op(walk_state, aml_op_start, &op); if (ACPI_FAILURE(status)) { + /* + * ACPI_PARSE_MODULE_LEVEL means that we are loading a table by + * executing it as a control method. However, if we encounter + * an error while loading the table, we need to keep trying to + * load the table rather than aborting the table load. Set the + * status to AE_OK to proceed with the table load. + */ + if ((walk_state-> + parse_flags & ACPI_PARSE_MODULE_LEVEL) + && status == AE_ALREADY_EXISTS) { + status = AE_OK; + } if (status == AE_CTRL_PARSE_CONTINUE) { continue; } @@ -694,6 +706,25 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state) acpi_ps_next_parse_state(walk_state, op, status); if (status == AE_CTRL_PENDING) { status = AE_OK; + } else + if ((walk_state-> + parse_flags & ACPI_PARSE_MODULE_LEVEL) + && status != AE_CTRL_TRANSFER + && ACPI_FAILURE(status)) { + /* + * ACPI_PARSE_MODULE_LEVEL flag means that we are currently + * loading a table by executing it as a control method. + * However, if we encounter an error while loading the table, + * we need to keep trying to load the table rather than + * aborting the table load (setting the status to AE_OK + * continues the table load). If we get a failure at this + * point, it means that the dispatcher got an error while + * processing Op (most likely an AML operand error) or a + * control method was called from module level and the + * dispatcher returned AE_CTRL_TRANSFER. In the latter case, + * leave the status alone, there's nothing wrong with it. + */ + status = AE_OK; } } diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 442a9e24f439..917f77f4cb55 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -2042,7 +2042,7 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = { .ident = "Thinkpad X1 Carbon 6th", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "20KGS3JF01"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "Thinkpad X1 Carbon 6th"), }, }, { }, diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 1435d7281c66..6ebcd65d64b6 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -434,14 +434,6 @@ re_probe: goto probe_failed; } - /* - * Ensure devices are listed in devices_kset in correct order - * It's important to move Dev to the end of devices_kset before - * calling .probe, because it could be recursive and parent Dev - * should always go first - */ - devices_kset_move_last(dev); - if (dev->bus->probe) { ret = dev->bus->probe(dev); if (ret) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 74a05561b620..3fb95c8d9fd8 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -112,12 +112,16 @@ struct nbd_device { struct task_struct *task_setup; }; +#define NBD_CMD_REQUEUED 1 + struct nbd_cmd { struct nbd_device *nbd; + struct mutex lock; int index; int cookie; - struct completion send_complete; blk_status_t status; + unsigned long flags; + u32 cmd_cookie; }; #if IS_ENABLED(CONFIG_DEBUG_FS) @@ -146,6 +150,35 @@ static inline struct device *nbd_to_dev(struct nbd_device *nbd) return disk_to_dev(nbd->disk); } +static void nbd_requeue_cmd(struct nbd_cmd *cmd) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + + if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags)) + blk_mq_requeue_request(req, true); +} + +#define NBD_COOKIE_BITS 32 + +static u64 nbd_cmd_handle(struct nbd_cmd *cmd) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + u32 tag = blk_mq_unique_tag(req); + u64 cookie = cmd->cmd_cookie; + + return (cookie << NBD_COOKIE_BITS) | tag; +} + +static u32 nbd_handle_to_tag(u64 handle) +{ + return (u32)handle; +} + +static u32 nbd_handle_to_cookie(u64 handle) +{ + return (u32)(handle >> NBD_COOKIE_BITS); +} + static const char *nbdcmd_to_ascii(int cmd) { switch (cmd) { @@ -319,6 +352,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, } config = nbd->config; + if (!mutex_trylock(&cmd->lock)) + return BLK_EH_RESET_TIMER; + if (config->num_connections > 1) { dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out, retrying (%d/%d alive)\n", @@ -343,7 +379,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); } - blk_mq_requeue_request(req, true); + mutex_unlock(&cmd->lock); + nbd_requeue_cmd(cmd); nbd_config_put(nbd); return BLK_EH_DONE; } @@ -353,6 +390,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, } set_bit(NBD_TIMEDOUT, &config->runtime_flags); cmd->status = BLK_STS_IOERR; + mutex_unlock(&cmd->lock); sock_shutdown(nbd); nbd_config_put(nbd); done: @@ -430,9 +468,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) struct iov_iter from; unsigned long size = blk_rq_bytes(req); struct bio *bio; + u64 handle; u32 type; u32 nbd_cmd_flags = 0; - u32 tag = blk_mq_unique_tag(req); int sent = nsock->sent, skip = 0; iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); @@ -474,6 +512,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) goto send_pages; } iov_iter_advance(&from, sent); + } else { + cmd->cmd_cookie++; } cmd->index = index; cmd->cookie = nsock->cookie; @@ -482,7 +522,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); request.len = htonl(size); } - memcpy(request.handle, &tag, sizeof(tag)); + handle = nbd_cmd_handle(cmd); + memcpy(request.handle, &handle, sizeof(handle)); dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n", req, nbdcmd_to_ascii(type), @@ -500,6 +541,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->pending = req; nsock->sent = sent; } + set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), @@ -541,6 +583,7 @@ send_pages: */ nsock->pending = req; nsock->sent = sent; + set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), @@ -573,10 +616,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) struct nbd_reply reply; struct nbd_cmd *cmd; struct request *req = NULL; + u64 handle; u16 hwq; u32 tag; struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)}; struct iov_iter to; + int ret = 0; reply.magic = 0; iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply)); @@ -594,8 +639,8 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) return ERR_PTR(-EPROTO); } - memcpy(&tag, reply.handle, sizeof(u32)); - + memcpy(&handle, reply.handle, sizeof(handle)); + tag = nbd_handle_to_tag(handle); hwq = blk_mq_unique_tag_to_hwq(tag); if (hwq < nbd->tag_set.nr_hw_queues) req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq], @@ -606,11 +651,25 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) return ERR_PTR(-ENOENT); } cmd = blk_mq_rq_to_pdu(req); + + mutex_lock(&cmd->lock); + if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) { + dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n", + req, cmd->cmd_cookie, nbd_handle_to_cookie(handle)); + ret = -ENOENT; + goto out; + } + if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) { + dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n", + req); + ret = -ENOENT; + goto out; + } if (ntohl(reply.error)) { dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n", ntohl(reply.error)); cmd->status = BLK_STS_IOERR; - return cmd; + goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req); @@ -635,18 +694,18 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) if (nbd_disconnected(config) || config->num_connections <= 1) { cmd->status = BLK_STS_IOERR; - return cmd; + goto out; } - return ERR_PTR(-EIO); + ret = -EIO; + goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n", req, bvec.bv_len); } - } else { - /* See the comment in nbd_queue_rq. */ - wait_for_completion(&cmd->send_complete); } - return cmd; +out: + mutex_unlock(&cmd->lock); + return ret ? ERR_PTR(ret) : cmd; } static void recv_work(struct work_struct *work) @@ -805,7 +864,7 @@ again: */ blk_mq_start_request(req); if (unlikely(nsock->pending && nsock->pending != req)) { - blk_mq_requeue_request(req, true); + nbd_requeue_cmd(cmd); ret = 0; goto out; } @@ -818,7 +877,7 @@ again: dev_err_ratelimited(disk_to_dev(nbd->disk), "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); - blk_mq_requeue_request(req, true); + nbd_requeue_cmd(cmd); ret = 0; } out: @@ -842,7 +901,8 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * that the server is misbehaving (or there was an error) before we're * done sending everything over the wire. */ - init_completion(&cmd->send_complete); + mutex_lock(&cmd->lock); + clear_bit(NBD_CMD_REQUEUED, &cmd->flags); /* We can be called directly from the user space process, which means we * could possibly have signals pending so our sendmsg will fail. In @@ -854,7 +914,7 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, ret = BLK_STS_IOERR; else if (!ret) ret = BLK_STS_OK; - complete(&cmd->send_complete); + mutex_unlock(&cmd->lock); return ret; } @@ -1460,6 +1520,8 @@ static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq, { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq); cmd->nbd = set->driver_data; + cmd->flags = 0; + mutex_init(&cmd->lock); return 0; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index fa0729c1e776..d81c653b9bf6 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -61,7 +61,7 @@ static int atomic_inc_return_safe(atomic_t *v) { unsigned int counter; - counter = (unsigned int)__atomic_add_unless(v, 1, 0); + counter = (unsigned int)atomic_fetch_add_unless(v, 1, 0); if (counter <= (unsigned int)INT_MAX) return (int)counter; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 7436b2d27fa3..a390c6d4f72d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -298,7 +298,8 @@ static void reset_bdev(struct zram *zram) zram->backing_dev = NULL; zram->old_block_size = 0; zram->bdev = NULL; - + zram->disk->queue->backing_dev_info->capabilities |= + BDI_CAP_SYNCHRONOUS_IO; kvfree(zram->bitmap); zram->bitmap = NULL; } @@ -400,6 +401,18 @@ static ssize_t backing_dev_store(struct device *dev, zram->backing_dev = backing_dev; zram->bitmap = bitmap; zram->nr_pages = nr_pages; + /* + * With writeback feature, zram does asynchronous IO so it's no longer + * synchronous device so let's remove synchronous io flag. Othewise, + * upper layer(e.g., swap) could wait IO completion rather than + * (submit and return), which will cause system sluggish. + * Furthermore, when the IO function returns(e.g., swap_readpage), + * upper layer expects IO was done so it could deallocate the page + * freely but in fact, IO is going on so finally could cause + * use-after-free when the IO is really done. + */ + zram->disk->queue->backing_dev_info->capabilities &= + ~BDI_CAP_SYNCHRONOUS_IO; up_write(&zram->init_lock); pr_info("setup backing device %s\n", file_name); diff --git a/drivers/char/agp/alpha-agp.c b/drivers/char/agp/alpha-agp.c index 53fe633df1e8..c9bf2c219841 100644 --- a/drivers/char/agp/alpha-agp.c +++ b/drivers/char/agp/alpha-agp.c @@ -11,7 +11,7 @@ #include "agp.h" -static int alpha_core_agp_vm_fault(struct vm_fault *vmf) +static vm_fault_t alpha_core_agp_vm_fault(struct vm_fault *vmf) { alpha_agp_info *agp = agp_bridge->dev_private_data; dma_addr_t dma_addr; diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index e50c29c97ca7..c69e39fdd02b 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -156,7 +156,7 @@ static u64 amd64_configure(struct pci_dev *hammer, u64 gatt_table) /* Address to map to */ pci_read_config_dword(hammer, AMD64_GARTAPERTUREBASE, &tmp); - aperturebase = tmp << 25; + aperturebase = (u64)tmp << 25; aper_base = (aperturebase & PCI_BASE_ADDRESS_MEM_MASK); enable_gart_translation(hammer, gatt_table); @@ -277,7 +277,7 @@ static int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp, u16 cap) pci_read_config_dword(nb, AMD64_GARTAPERTURECTL, &nb_order); nb_order = (nb_order >> 1) & 7; pci_read_config_dword(nb, AMD64_GARTAPERTUREBASE, &nb_base); - nb_aper = nb_base << 25; + nb_aper = (u64)nb_base << 25; /* Northbridge seems to contain crap. Try the AGP bridge. */ diff --git a/drivers/char/mem.c b/drivers/char/mem.c index ffeb60d3434c..df66a9dd0aae 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -708,6 +708,7 @@ static int mmap_zero(struct file *file, struct vm_area_struct *vma) #endif if (vma->vm_flags & VM_SHARED) return shmem_zero_setup(vma); + vma_set_anonymous(vma); return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index cd888d4ee605..bd449ad52442 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1895,14 +1895,22 @@ static int write_pool(struct entropy_store *r, const char __user *buffer, size_t count) { size_t bytes; - __u32 buf[16]; + __u32 t, buf[16]; const char __user *p = buffer; while (count > 0) { + int b, i = 0; + bytes = min(count, sizeof(buf)); if (copy_from_user(&buf, p, bytes)) return -EFAULT; + for (b = bytes ; b > 0 ; b -= sizeof(__u32), i++) { + if (!arch_get_random_int(&t)) + break; + buf[i] ^= t; + } + count -= bytes; p += bytes; diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c index 38b366b00c57..7b70a074095d 100644 --- a/drivers/clk/clk-aspeed.c +++ b/drivers/clk/clk-aspeed.c @@ -24,7 +24,7 @@ #define ASPEED_MPLL_PARAM 0x20 #define ASPEED_HPLL_PARAM 0x24 #define AST2500_HPLL_BYPASS_EN BIT(20) -#define AST2400_HPLL_STRAPPED BIT(18) +#define AST2400_HPLL_PROGRAMMED BIT(18) #define AST2400_HPLL_BYPASS_EN BIT(17) #define ASPEED_MISC_CTRL 0x2c #define UART_DIV13_EN BIT(12) @@ -91,8 +91,8 @@ static const struct aspeed_gate_data aspeed_gates[] = { [ASPEED_CLK_GATE_GCLK] = { 1, 7, "gclk-gate", NULL, 0 }, /* 2D engine */ [ASPEED_CLK_GATE_MCLK] = { 2, -1, "mclk-gate", "mpll", CLK_IS_CRITICAL }, /* SDRAM */ [ASPEED_CLK_GATE_VCLK] = { 3, 6, "vclk-gate", NULL, 0 }, /* Video Capture */ - [ASPEED_CLK_GATE_BCLK] = { 4, 8, "bclk-gate", "bclk", 0 }, /* PCIe/PCI */ - [ASPEED_CLK_GATE_DCLK] = { 5, -1, "dclk-gate", NULL, 0 }, /* DAC */ + [ASPEED_CLK_GATE_BCLK] = { 4, 8, "bclk-gate", "bclk", CLK_IS_CRITICAL }, /* PCIe/PCI */ + [ASPEED_CLK_GATE_DCLK] = { 5, -1, "dclk-gate", NULL, CLK_IS_CRITICAL }, /* DAC */ [ASPEED_CLK_GATE_REFCLK] = { 6, -1, "refclk-gate", "clkin", CLK_IS_CRITICAL }, [ASPEED_CLK_GATE_USBPORT2CLK] = { 7, 3, "usb-port2-gate", NULL, 0 }, /* USB2.0 Host port 2 */ [ASPEED_CLK_GATE_LCLK] = { 8, 5, "lclk-gate", NULL, 0 }, /* LPC */ @@ -212,9 +212,22 @@ static int aspeed_clk_is_enabled(struct clk_hw *hw) { struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw); u32 clk = BIT(gate->clock_idx); + u32 rst = BIT(gate->reset_idx); u32 enval = (gate->flags & CLK_GATE_SET_TO_DISABLE) ? 0 : clk; u32 reg; + /* + * If the IP is in reset, treat the clock as not enabled, + * this happens with some clocks such as the USB one when + * coming from cold reset. Without this, aspeed_clk_enable() + * will fail to lift the reset. + */ + if (gate->reset_idx >= 0) { + regmap_read(gate->map, ASPEED_RESET_CTRL, ®); + if (reg & rst) + return 0; + } + regmap_read(gate->map, ASPEED_CLK_STOP_CTRL, ®); return ((reg & clk) == enval) ? 1 : 0; @@ -565,29 +578,45 @@ builtin_platform_driver(aspeed_clk_driver); static void __init aspeed_ast2400_cc(struct regmap *map) { struct clk_hw *hw; - u32 val, freq, div; + u32 val, div, clkin, hpll; + const u16 hpll_rates[][4] = { + {384, 360, 336, 408}, + {400, 375, 350, 425}, + }; + int rate; /* * CLKIN is the crystal oscillator, 24, 48 or 25MHz selected by * strapping */ regmap_read(map, ASPEED_STRAP, &val); - if (val & CLKIN_25MHZ_EN) - freq = 25000000; - else if (val & AST2400_CLK_SOURCE_SEL) - freq = 48000000; - else - freq = 24000000; - hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, freq); - pr_debug("clkin @%u MHz\n", freq / 1000000); + rate = (val >> 8) & 3; + if (val & CLKIN_25MHZ_EN) { + clkin = 25000000; + hpll = hpll_rates[1][rate]; + } else if (val & AST2400_CLK_SOURCE_SEL) { + clkin = 48000000; + hpll = hpll_rates[0][rate]; + } else { + clkin = 24000000; + hpll = hpll_rates[0][rate]; + } + hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, clkin); + pr_debug("clkin @%u MHz\n", clkin / 1000000); /* * High-speed PLL clock derived from the crystal. This the CPU clock, - * and we assume that it is enabled + * and we assume that it is enabled. It can be configured through the + * HPLL_PARAM register, or set to a specified frequency by strapping. */ regmap_read(map, ASPEED_HPLL_PARAM, &val); - WARN(val & AST2400_HPLL_STRAPPED, "hpll is strapped not configured"); - aspeed_clk_data->hws[ASPEED_CLK_HPLL] = aspeed_ast2400_calc_pll("hpll", val); + if (val & AST2400_HPLL_PROGRAMMED) + hw = aspeed_ast2400_calc_pll("hpll", val); + else + hw = clk_hw_register_fixed_rate(NULL, "hpll", "clkin", 0, + hpll * 1000000); + + aspeed_clk_data->hws[ASPEED_CLK_HPLL] = hw; /* * Strap bits 11:10 define the CPU/AHB clock frequency ratio (aka HCLK) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 9760b526ca31..e2ed078abd90 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -24,7 +24,6 @@ #include <linux/pm_runtime.h> #include <linux/sched.h> #include <linux/clkdev.h> -#include <linux/stringify.h> #include "clk.h" @@ -2559,7 +2558,7 @@ static const struct { unsigned long flag; const char *name; } clk_flags[] = { -#define ENTRY(f) { f, __stringify(f) } +#define ENTRY(f) { f, #f } ENTRY(CLK_SET_RATE_GATE), ENTRY(CLK_SET_PARENT_GATE), ENTRY(CLK_SET_RATE_PARENT), diff --git a/drivers/clk/meson/clk-audio-divider.c b/drivers/clk/meson/clk-audio-divider.c index 58f546e04807..e4cf96ba704e 100644 --- a/drivers/clk/meson/clk-audio-divider.c +++ b/drivers/clk/meson/clk-audio-divider.c @@ -51,7 +51,7 @@ static unsigned long audio_divider_recalc_rate(struct clk_hw *hw, struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk); unsigned long divider; - divider = meson_parm_read(clk->map, &adiv->div); + divider = meson_parm_read(clk->map, &adiv->div) + 1; return DIV_ROUND_UP_ULL((u64)parent_rate, divider); } diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 240658404367..177fffb9ebef 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -498,6 +498,7 @@ static struct clk_regmap gxbb_fclk_div2 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div2_div" }, .num_parents = 1, + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c index 6860bd5a37c5..44e4e27eddad 100644 --- a/drivers/clk/mvebu/armada-37xx-periph.c +++ b/drivers/clk/mvebu/armada-37xx-periph.c @@ -35,6 +35,7 @@ #define CLK_SEL 0x10 #define CLK_DIS 0x14 +#define ARMADA_37XX_DVFS_LOAD_1 1 #define LOAD_LEVEL_NR 4 #define ARMADA_37XX_NB_L0L1 0x18 @@ -507,6 +508,40 @@ static long clk_pm_cpu_round_rate(struct clk_hw *hw, unsigned long rate, return -EINVAL; } +/* + * Switching the CPU from the L2 or L3 frequencies (300 and 200 Mhz + * respectively) to L0 frequency (1.2 Ghz) requires a significant + * amount of time to let VDD stabilize to the appropriate + * voltage. This amount of time is large enough that it cannot be + * covered by the hardware countdown register. Due to this, the CPU + * might start operating at L0 before the voltage is stabilized, + * leading to CPU stalls. + * + * To work around this problem, we prevent switching directly from the + * L2/L3 frequencies to the L0 frequency, and instead switch to the L1 + * frequency in-between. The sequence therefore becomes: + * 1. First switch from L2/L3(200/300MHz) to L1(600MHZ) + * 2. Sleep 20ms for stabling VDD voltage + * 3. Then switch from L1(600MHZ) to L0(1200Mhz). + */ +static void clk_pm_cpu_set_rate_wa(unsigned long rate, struct regmap *base) +{ + unsigned int cur_level; + + if (rate != 1200 * 1000 * 1000) + return; + + regmap_read(base, ARMADA_37XX_NB_CPU_LOAD, &cur_level); + cur_level &= ARMADA_37XX_NB_CPU_LOAD_MASK; + if (cur_level <= ARMADA_37XX_DVFS_LOAD_1) + return; + + regmap_update_bits(base, ARMADA_37XX_NB_CPU_LOAD, + ARMADA_37XX_NB_CPU_LOAD_MASK, + ARMADA_37XX_DVFS_LOAD_1); + msleep(20); +} + static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { @@ -537,6 +572,9 @@ static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate, */ reg = ARMADA_37XX_NB_CPU_LOAD; mask = ARMADA_37XX_NB_CPU_LOAD_MASK; + + clk_pm_cpu_set_rate_wa(rate, base); + regmap_update_bits(base, reg, mask, load_level); return rate; diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c index 9f35b3fe1d97..ff8d66fd94e6 100644 --- a/drivers/clk/qcom/gcc-msm8996.c +++ b/drivers/clk/qcom/gcc-msm8996.c @@ -2781,6 +2781,7 @@ static struct clk_branch gcc_ufs_rx_cfg_clk = { static struct clk_branch gcc_ufs_tx_symbol_0_clk = { .halt_reg = 0x75018, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x75018, .enable_mask = BIT(0), diff --git a/drivers/clk/qcom/mmcc-msm8996.c b/drivers/clk/qcom/mmcc-msm8996.c index 1a25ee4f3658..4b20d1b67a1b 100644 --- a/drivers/clk/qcom/mmcc-msm8996.c +++ b/drivers/clk/qcom/mmcc-msm8996.c @@ -2910,6 +2910,7 @@ static struct gdsc mmagic_bimc_gdsc = { .name = "mmagic_bimc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = ALWAYS_ON, }; static struct gdsc mmagic_video_gdsc = { diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index 00caf37e52f9..c070cc7992e9 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -49,7 +49,7 @@ obj-$(CONFIG_CLKSRC_SAMSUNG_PWM) += samsung_pwm_timer.o obj-$(CONFIG_FSL_FTM_TIMER) += fsl_ftm_timer.o obj-$(CONFIG_VF_PIT_TIMER) += vf_pit_timer.o obj-$(CONFIG_CLKSRC_QCOM) += qcom-timer.o -obj-$(CONFIG_MTK_TIMER) += mtk_timer.o +obj-$(CONFIG_MTK_TIMER) += timer-mediatek.o obj-$(CONFIG_CLKSRC_PISTACHIO) += time-pistachio.o obj-$(CONFIG_CLKSRC_TI_32K) += timer-ti-32k.o obj-$(CONFIG_CLKSRC_NPS) += timer-nps.o diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c deleted file mode 100644 index f9b724fd9950..000000000000 --- a/drivers/clocksource/mtk_timer.c +++ /dev/null @@ -1,268 +0,0 @@ -/* - * Mediatek SoCs General-Purpose Timer handling. - * - * Copyright (C) 2014 Matthias Brugger - * - * Matthias Brugger <matthias.bgg@gmail.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/clk.h> -#include <linux/clockchips.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/irqreturn.h> -#include <linux/of.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> -#include <linux/sched_clock.h> -#include <linux/slab.h> - -#define GPT_IRQ_EN_REG 0x00 -#define GPT_IRQ_ENABLE(val) BIT((val) - 1) -#define GPT_IRQ_ACK_REG 0x08 -#define GPT_IRQ_ACK(val) BIT((val) - 1) - -#define TIMER_CTRL_REG(val) (0x10 * (val)) -#define TIMER_CTRL_OP(val) (((val) & 0x3) << 4) -#define TIMER_CTRL_OP_ONESHOT (0) -#define TIMER_CTRL_OP_REPEAT (1) -#define TIMER_CTRL_OP_FREERUN (3) -#define TIMER_CTRL_CLEAR (2) -#define TIMER_CTRL_ENABLE (1) -#define TIMER_CTRL_DISABLE (0) - -#define TIMER_CLK_REG(val) (0x04 + (0x10 * (val))) -#define TIMER_CLK_SRC(val) (((val) & 0x1) << 4) -#define TIMER_CLK_SRC_SYS13M (0) -#define TIMER_CLK_SRC_RTC32K (1) -#define TIMER_CLK_DIV1 (0x0) -#define TIMER_CLK_DIV2 (0x1) - -#define TIMER_CNT_REG(val) (0x08 + (0x10 * (val))) -#define TIMER_CMP_REG(val) (0x0C + (0x10 * (val))) - -#define GPT_CLK_EVT 1 -#define GPT_CLK_SRC 2 - -struct mtk_clock_event_device { - void __iomem *gpt_base; - u32 ticks_per_jiffy; - struct clock_event_device dev; -}; - -static void __iomem *gpt_sched_reg __read_mostly; - -static u64 notrace mtk_read_sched_clock(void) -{ - return readl_relaxed(gpt_sched_reg); -} - -static inline struct mtk_clock_event_device *to_mtk_clk( - struct clock_event_device *c) -{ - return container_of(c, struct mtk_clock_event_device, dev); -} - -static void mtk_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer) -{ - u32 val; - - val = readl(evt->gpt_base + TIMER_CTRL_REG(timer)); - writel(val & ~TIMER_CTRL_ENABLE, evt->gpt_base + - TIMER_CTRL_REG(timer)); -} - -static void mtk_clkevt_time_setup(struct mtk_clock_event_device *evt, - unsigned long delay, u8 timer) -{ - writel(delay, evt->gpt_base + TIMER_CMP_REG(timer)); -} - -static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt, - bool periodic, u8 timer) -{ - u32 val; - - /* Acknowledge interrupt */ - writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG); - - val = readl(evt->gpt_base + TIMER_CTRL_REG(timer)); - - /* Clear 2 bit timer operation mode field */ - val &= ~TIMER_CTRL_OP(0x3); - - if (periodic) - val |= TIMER_CTRL_OP(TIMER_CTRL_OP_REPEAT); - else - val |= TIMER_CTRL_OP(TIMER_CTRL_OP_ONESHOT); - - writel(val | TIMER_CTRL_ENABLE | TIMER_CTRL_CLEAR, - evt->gpt_base + TIMER_CTRL_REG(timer)); -} - -static int mtk_clkevt_shutdown(struct clock_event_device *clk) -{ - mtk_clkevt_time_stop(to_mtk_clk(clk), GPT_CLK_EVT); - return 0; -} - -static int mtk_clkevt_set_periodic(struct clock_event_device *clk) -{ - struct mtk_clock_event_device *evt = to_mtk_clk(clk); - - mtk_clkevt_time_stop(evt, GPT_CLK_EVT); - mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT); - mtk_clkevt_time_start(evt, true, GPT_CLK_EVT); - return 0; -} - -static int mtk_clkevt_next_event(unsigned long event, - struct clock_event_device *clk) -{ - struct mtk_clock_event_device *evt = to_mtk_clk(clk); - - mtk_clkevt_time_stop(evt, GPT_CLK_EVT); - mtk_clkevt_time_setup(evt, event, GPT_CLK_EVT); - mtk_clkevt_time_start(evt, false, GPT_CLK_EVT); - - return 0; -} - -static irqreturn_t mtk_timer_interrupt(int irq, void *dev_id) -{ - struct mtk_clock_event_device *evt = dev_id; - - /* Acknowledge timer0 irq */ - writel(GPT_IRQ_ACK(GPT_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG); - evt->dev.event_handler(&evt->dev); - - return IRQ_HANDLED; -} - -static void -__init mtk_timer_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option) -{ - writel(TIMER_CTRL_CLEAR | TIMER_CTRL_DISABLE, - evt->gpt_base + TIMER_CTRL_REG(timer)); - - writel(TIMER_CLK_SRC(TIMER_CLK_SRC_SYS13M) | TIMER_CLK_DIV1, - evt->gpt_base + TIMER_CLK_REG(timer)); - - writel(0x0, evt->gpt_base + TIMER_CMP_REG(timer)); - - writel(TIMER_CTRL_OP(option) | TIMER_CTRL_ENABLE, - evt->gpt_base + TIMER_CTRL_REG(timer)); -} - -static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer) -{ - u32 val; - - /* Disable all interrupts */ - writel(0x0, evt->gpt_base + GPT_IRQ_EN_REG); - - /* Acknowledge all spurious pending interrupts */ - writel(0x3f, evt->gpt_base + GPT_IRQ_ACK_REG); - - val = readl(evt->gpt_base + GPT_IRQ_EN_REG); - writel(val | GPT_IRQ_ENABLE(timer), - evt->gpt_base + GPT_IRQ_EN_REG); -} - -static int __init mtk_timer_init(struct device_node *node) -{ - struct mtk_clock_event_device *evt; - struct resource res; - unsigned long rate = 0; - struct clk *clk; - - evt = kzalloc(sizeof(*evt), GFP_KERNEL); - if (!evt) - return -ENOMEM; - - evt->dev.name = "mtk_tick"; - evt->dev.rating = 300; - evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; - evt->dev.set_state_shutdown = mtk_clkevt_shutdown; - evt->dev.set_state_periodic = mtk_clkevt_set_periodic; - evt->dev.set_state_oneshot = mtk_clkevt_shutdown; - evt->dev.tick_resume = mtk_clkevt_shutdown; - evt->dev.set_next_event = mtk_clkevt_next_event; - evt->dev.cpumask = cpu_possible_mask; - - evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer"); - if (IS_ERR(evt->gpt_base)) { - pr_err("Can't get resource\n"); - goto err_kzalloc; - } - - evt->dev.irq = irq_of_parse_and_map(node, 0); - if (evt->dev.irq <= 0) { - pr_err("Can't parse IRQ\n"); - goto err_mem; - } - - clk = of_clk_get(node, 0); - if (IS_ERR(clk)) { - pr_err("Can't get timer clock\n"); - goto err_irq; - } - - if (clk_prepare_enable(clk)) { - pr_err("Can't prepare clock\n"); - goto err_clk_put; - } - rate = clk_get_rate(clk); - - if (request_irq(evt->dev.irq, mtk_timer_interrupt, - IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) { - pr_err("failed to setup irq %d\n", evt->dev.irq); - goto err_clk_disable; - } - - evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ); - - /* Configure clock source */ - mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN); - clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC), - node->name, rate, 300, 32, clocksource_mmio_readl_up); - gpt_sched_reg = evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC); - sched_clock_register(mtk_read_sched_clock, 32, rate); - - /* Configure clock event */ - mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT); - clockevents_config_and_register(&evt->dev, rate, 0x3, - 0xffffffff); - - mtk_timer_enable_irq(evt, GPT_CLK_EVT); - - return 0; - -err_clk_disable: - clk_disable_unprepare(clk); -err_clk_put: - clk_put(clk); -err_irq: - irq_dispose_mapping(evt->dev.irq); -err_mem: - iounmap(evt->gpt_base); - of_address_to_resource(node, 0, &res); - release_mem_region(res.start, resource_size(&res)); -err_kzalloc: - kfree(evt); - - return -EINVAL; -} -TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init); diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c index c337a8100a7b..dabf0a103567 100644 --- a/drivers/clocksource/tegra20_timer.c +++ b/drivers/clocksource/tegra20_timer.c @@ -230,7 +230,7 @@ static int __init tegra20_init_timer(struct device_node *np) return ret; } - tegra_clockevent.cpumask = cpu_all_mask; + tegra_clockevent.cpumask = cpu_possible_mask; tegra_clockevent.irq = tegra_timer_irq.irq; clockevents_config_and_register(&tegra_clockevent, 1000000, 0x1, 0x1fffffff); diff --git a/drivers/clocksource/timer-atcpit100.c b/drivers/clocksource/timer-atcpit100.c index 5e23d7b4a722..b4bd2f5b801d 100644 --- a/drivers/clocksource/timer-atcpit100.c +++ b/drivers/clocksource/timer-atcpit100.c @@ -185,7 +185,7 @@ static struct timer_of to = { .set_state_oneshot = atcpit100_clkevt_set_oneshot, .tick_resume = atcpit100_clkevt_shutdown, .set_next_event = atcpit100_clkevt_next_event, - .cpumask = cpu_all_mask, + .cpumask = cpu_possible_mask, }, .of_irq = { diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c index 0eee03250cfc..f5b2eda30bf3 100644 --- a/drivers/clocksource/timer-keystone.c +++ b/drivers/clocksource/timer-keystone.c @@ -211,7 +211,7 @@ static int __init keystone_timer_init(struct device_node *np) event_dev->set_state_shutdown = keystone_shutdown; event_dev->set_state_periodic = keystone_set_periodic; event_dev->set_state_oneshot = keystone_shutdown; - event_dev->cpumask = cpu_all_mask; + event_dev->cpumask = cpu_possible_mask; event_dev->owner = THIS_MODULE; event_dev->name = TIMER_NAME; event_dev->irq = irq; diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c new file mode 100644 index 000000000000..eb10321f8517 --- /dev/null +++ b/drivers/clocksource/timer-mediatek.c @@ -0,0 +1,328 @@ +/* + * Mediatek SoCs General-Purpose Timer handling. + * + * Copyright (C) 2014 Matthias Brugger + * + * Matthias Brugger <matthias.bgg@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/clockchips.h> +#include <linux/clocksource.h> +#include <linux/interrupt.h> +#include <linux/irqreturn.h> +#include <linux/sched_clock.h> +#include <linux/slab.h> +#include "timer-of.h" + +#define TIMER_CLK_EVT (1) +#define TIMER_CLK_SRC (2) + +#define TIMER_SYNC_TICKS (3) + +/* gpt */ +#define GPT_IRQ_EN_REG 0x00 +#define GPT_IRQ_ENABLE(val) BIT((val) - 1) +#define GPT_IRQ_ACK_REG 0x08 +#define GPT_IRQ_ACK(val) BIT((val) - 1) + +#define GPT_CTRL_REG(val) (0x10 * (val)) +#define GPT_CTRL_OP(val) (((val) & 0x3) << 4) +#define GPT_CTRL_OP_ONESHOT (0) +#define GPT_CTRL_OP_REPEAT (1) +#define GPT_CTRL_OP_FREERUN (3) +#define GPT_CTRL_CLEAR (2) +#define GPT_CTRL_ENABLE (1) +#define GPT_CTRL_DISABLE (0) + +#define GPT_CLK_REG(val) (0x04 + (0x10 * (val))) +#define GPT_CLK_SRC(val) (((val) & 0x1) << 4) +#define GPT_CLK_SRC_SYS13M (0) +#define GPT_CLK_SRC_RTC32K (1) +#define GPT_CLK_DIV1 (0x0) +#define GPT_CLK_DIV2 (0x1) + +#define GPT_CNT_REG(val) (0x08 + (0x10 * (val))) +#define GPT_CMP_REG(val) (0x0C + (0x10 * (val))) + +/* system timer */ +#define SYST_BASE (0x40) + +#define SYST_CON (SYST_BASE + 0x0) +#define SYST_VAL (SYST_BASE + 0x4) + +#define SYST_CON_REG(to) (timer_of_base(to) + SYST_CON) +#define SYST_VAL_REG(to) (timer_of_base(to) + SYST_VAL) + +/* + * SYST_CON_EN: Clock enable. Shall be set to + * - Start timer countdown. + * - Allow timeout ticks being updated. + * - Allow changing interrupt functions. + * + * SYST_CON_IRQ_EN: Set to allow interrupt. + * + * SYST_CON_IRQ_CLR: Set to clear interrupt. + */ +#define SYST_CON_EN BIT(0) +#define SYST_CON_IRQ_EN BIT(1) +#define SYST_CON_IRQ_CLR BIT(4) + +static void __iomem *gpt_sched_reg __read_mostly; + +static void mtk_syst_ack_irq(struct timer_of *to) +{ + /* Clear and disable interrupt */ + writel(SYST_CON_IRQ_CLR | SYST_CON_EN, SYST_CON_REG(to)); +} + +static irqreturn_t mtk_syst_handler(int irq, void *dev_id) +{ + struct clock_event_device *clkevt = dev_id; + struct timer_of *to = to_timer_of(clkevt); + + mtk_syst_ack_irq(to); + clkevt->event_handler(clkevt); + + return IRQ_HANDLED; +} + +static int mtk_syst_clkevt_next_event(unsigned long ticks, + struct clock_event_device *clkevt) +{ + struct timer_of *to = to_timer_of(clkevt); + + /* Enable clock to allow timeout tick update later */ + writel(SYST_CON_EN, SYST_CON_REG(to)); + + /* + * Write new timeout ticks. Timer shall start countdown + * after timeout ticks are updated. + */ + writel(ticks, SYST_VAL_REG(to)); + + /* Enable interrupt */ + writel(SYST_CON_EN | SYST_CON_IRQ_EN, SYST_CON_REG(to)); + + return 0; +} + +static int mtk_syst_clkevt_shutdown(struct clock_event_device *clkevt) +{ + /* Disable timer */ + writel(0, SYST_CON_REG(to_timer_of(clkevt))); + + return 0; +} + +static int mtk_syst_clkevt_resume(struct clock_event_device *clkevt) +{ + return mtk_syst_clkevt_shutdown(clkevt); +} + +static int mtk_syst_clkevt_oneshot(struct clock_event_device *clkevt) +{ + return 0; +} + +static u64 notrace mtk_gpt_read_sched_clock(void) +{ + return readl_relaxed(gpt_sched_reg); +} + +static void mtk_gpt_clkevt_time_stop(struct timer_of *to, u8 timer) +{ + u32 val; + + val = readl(timer_of_base(to) + GPT_CTRL_REG(timer)); + writel(val & ~GPT_CTRL_ENABLE, timer_of_base(to) + + GPT_CTRL_REG(timer)); +} + +static void mtk_gpt_clkevt_time_setup(struct timer_of *to, + unsigned long delay, u8 timer) +{ + writel(delay, timer_of_base(to) + GPT_CMP_REG(timer)); +} + +static void mtk_gpt_clkevt_time_start(struct timer_of *to, + bool periodic, u8 timer) +{ + u32 val; + + /* Acknowledge interrupt */ + writel(GPT_IRQ_ACK(timer), timer_of_base(to) + GPT_IRQ_ACK_REG); + + val = readl(timer_of_base(to) + GPT_CTRL_REG(timer)); + + /* Clear 2 bit timer operation mode field */ + val &= ~GPT_CTRL_OP(0x3); + + if (periodic) + val |= GPT_CTRL_OP(GPT_CTRL_OP_REPEAT); + else + val |= GPT_CTRL_OP(GPT_CTRL_OP_ONESHOT); + + writel(val | GPT_CTRL_ENABLE | GPT_CTRL_CLEAR, + timer_of_base(to) + GPT_CTRL_REG(timer)); +} + +static int mtk_gpt_clkevt_shutdown(struct clock_event_device *clk) +{ + mtk_gpt_clkevt_time_stop(to_timer_of(clk), TIMER_CLK_EVT); + + return 0; +} + +static int mtk_gpt_clkevt_set_periodic(struct clock_event_device *clk) +{ + struct timer_of *to = to_timer_of(clk); + + mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT); + mtk_gpt_clkevt_time_setup(to, to->of_clk.period, TIMER_CLK_EVT); + mtk_gpt_clkevt_time_start(to, true, TIMER_CLK_EVT); + + return 0; +} + +static int mtk_gpt_clkevt_next_event(unsigned long event, + struct clock_event_device *clk) +{ + struct timer_of *to = to_timer_of(clk); + + mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT); + mtk_gpt_clkevt_time_setup(to, event, TIMER_CLK_EVT); + mtk_gpt_clkevt_time_start(to, false, TIMER_CLK_EVT); + + return 0; +} + +static irqreturn_t mtk_gpt_interrupt(int irq, void *dev_id) +{ + struct clock_event_device *clkevt = (struct clock_event_device *)dev_id; + struct timer_of *to = to_timer_of(clkevt); + + /* Acknowledge timer0 irq */ + writel(GPT_IRQ_ACK(TIMER_CLK_EVT), timer_of_base(to) + GPT_IRQ_ACK_REG); + clkevt->event_handler(clkevt); + + return IRQ_HANDLED; +} + +static void +__init mtk_gpt_setup(struct timer_of *to, u8 timer, u8 option) +{ + writel(GPT_CTRL_CLEAR | GPT_CTRL_DISABLE, + timer_of_base(to) + GPT_CTRL_REG(timer)); + + writel(GPT_CLK_SRC(GPT_CLK_SRC_SYS13M) | GPT_CLK_DIV1, + timer_of_base(to) + GPT_CLK_REG(timer)); + + writel(0x0, timer_of_base(to) + GPT_CMP_REG(timer)); + + writel(GPT_CTRL_OP(option) | GPT_CTRL_ENABLE, + timer_of_base(to) + GPT_CTRL_REG(timer)); +} + +static void mtk_gpt_enable_irq(struct timer_of *to, u8 timer) +{ + u32 val; + + /* Disable all interrupts */ + writel(0x0, timer_of_base(to) + GPT_IRQ_EN_REG); + + /* Acknowledge all spurious pending interrupts */ + writel(0x3f, timer_of_base(to) + GPT_IRQ_ACK_REG); + + val = readl(timer_of_base(to) + GPT_IRQ_EN_REG); + writel(val | GPT_IRQ_ENABLE(timer), + timer_of_base(to) + GPT_IRQ_EN_REG); +} + +static struct timer_of to = { + .flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK, + + .clkevt = { + .name = "mtk-clkevt", + .rating = 300, + .cpumask = cpu_possible_mask, + }, + + .of_irq = { + .flags = IRQF_TIMER | IRQF_IRQPOLL, + }, +}; + +static int __init mtk_syst_init(struct device_node *node) +{ + int ret; + + to.clkevt.features = CLOCK_EVT_FEAT_DYNIRQ | CLOCK_EVT_FEAT_ONESHOT; + to.clkevt.set_state_shutdown = mtk_syst_clkevt_shutdown; + to.clkevt.set_state_oneshot = mtk_syst_clkevt_oneshot; + to.clkevt.tick_resume = mtk_syst_clkevt_resume; + to.clkevt.set_next_event = mtk_syst_clkevt_next_event; + to.of_irq.handler = mtk_syst_handler; + + ret = timer_of_init(node, &to); + if (ret) + goto err; + + clockevents_config_and_register(&to.clkevt, timer_of_rate(&to), + TIMER_SYNC_TICKS, 0xffffffff); + + return 0; +err: + timer_of_cleanup(&to); + return ret; +} + +static int __init mtk_gpt_init(struct device_node *node) +{ + int ret; + + to.clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; + to.clkevt.set_state_shutdown = mtk_gpt_clkevt_shutdown; + to.clkevt.set_state_periodic = mtk_gpt_clkevt_set_periodic; + to.clkevt.set_state_oneshot = mtk_gpt_clkevt_shutdown; + to.clkevt.tick_resume = mtk_gpt_clkevt_shutdown; + to.clkevt.set_next_event = mtk_gpt_clkevt_next_event; + to.of_irq.handler = mtk_gpt_interrupt; + + ret = timer_of_init(node, &to); + if (ret) + goto err; + + /* Configure clock source */ + mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN); + clocksource_mmio_init(timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC), + node->name, timer_of_rate(&to), 300, 32, + clocksource_mmio_readl_up); + gpt_sched_reg = timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC); + sched_clock_register(mtk_gpt_read_sched_clock, 32, timer_of_rate(&to)); + + /* Configure clock event */ + mtk_gpt_setup(&to, TIMER_CLK_EVT, GPT_CTRL_OP_REPEAT); + clockevents_config_and_register(&to.clkevt, timer_of_rate(&to), + TIMER_SYNC_TICKS, 0xffffffff); + + mtk_gpt_enable_irq(&to, TIMER_CLK_EVT); + + return 0; +err: + timer_of_cleanup(&to); + return ret; +} +TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init); +TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init); diff --git a/drivers/clocksource/timer-sprd.c b/drivers/clocksource/timer-sprd.c index ef9ebeafb3ed..430cb99d8d79 100644 --- a/drivers/clocksource/timer-sprd.c +++ b/drivers/clocksource/timer-sprd.c @@ -156,4 +156,54 @@ static int __init sprd_timer_init(struct device_node *np) return 0; } +static struct timer_of suspend_to = { + .flags = TIMER_OF_BASE | TIMER_OF_CLOCK, +}; + +static u64 sprd_suspend_timer_read(struct clocksource *cs) +{ + return ~(u64)readl_relaxed(timer_of_base(&suspend_to) + + TIMER_VALUE_SHDW_LO) & cs->mask; +} + +static int sprd_suspend_timer_enable(struct clocksource *cs) +{ + sprd_timer_update_counter(timer_of_base(&suspend_to), + TIMER_VALUE_LO_MASK); + sprd_timer_enable(timer_of_base(&suspend_to), TIMER_CTL_PERIOD_MODE); + + return 0; +} + +static void sprd_suspend_timer_disable(struct clocksource *cs) +{ + sprd_timer_disable(timer_of_base(&suspend_to)); +} + +static struct clocksource suspend_clocksource = { + .name = "sprd_suspend_timer", + .rating = 200, + .read = sprd_suspend_timer_read, + .enable = sprd_suspend_timer_enable, + .disable = sprd_suspend_timer_disable, + .mask = CLOCKSOURCE_MASK(32), + .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_SUSPEND_NONSTOP, +}; + +static int __init sprd_suspend_timer_init(struct device_node *np) +{ + int ret; + + ret = timer_of_init(np, &suspend_to); + if (ret) + return ret; + + clocksource_register_hz(&suspend_clocksource, + timer_of_rate(&suspend_to)); + + return 0; +} + TIMER_OF_DECLARE(sc9860_timer, "sprd,sc9860-timer", sprd_timer_init); +TIMER_OF_DECLARE(sc9860_persistent_timer, "sprd,sc9860-suspend-timer", + sprd_suspend_timer_init); diff --git a/drivers/clocksource/timer-ti-32k.c b/drivers/clocksource/timer-ti-32k.c index 880a861ab3c8..29e2e1a78a43 100644 --- a/drivers/clocksource/timer-ti-32k.c +++ b/drivers/clocksource/timer-ti-32k.c @@ -78,8 +78,7 @@ static struct ti_32k ti_32k_timer = { .rating = 250, .read = ti_32k_read_cycles, .mask = CLOCKSOURCE_MASK(32), - .flags = CLOCK_SOURCE_IS_CONTINUOUS | - CLOCK_SOURCE_SUSPEND_NONSTOP, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, }, }; diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c index a6a0338eea77..f74689334f7c 100644 --- a/drivers/clocksource/zevio-timer.c +++ b/drivers/clocksource/zevio-timer.c @@ -162,7 +162,7 @@ static int __init zevio_timer_add(struct device_node *node) timer->clkevt.set_state_oneshot = zevio_timer_set_oneshot; timer->clkevt.tick_resume = zevio_timer_set_oneshot; timer->clkevt.rating = 200; - timer->clkevt.cpumask = cpu_all_mask; + timer->clkevt.cpumask = cpu_possible_mask; timer->clkevt.features = CLOCK_EVT_FEAT_ONESHOT; timer->clkevt.irq = irqnr; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index ece120da3353..d4ed0022b0dd 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -311,12 +311,20 @@ static DEFINE_MUTEX(intel_pstate_limits_lock); #ifdef CONFIG_ACPI -static bool intel_pstate_get_ppc_enable_status(void) +static bool intel_pstate_acpi_pm_profile_server(void) { if (acpi_gbl_FADT.preferred_profile == PM_ENTERPRISE_SERVER || acpi_gbl_FADT.preferred_profile == PM_PERFORMANCE_SERVER) return true; + return false; +} + +static bool intel_pstate_get_ppc_enable_status(void) +{ + if (intel_pstate_acpi_pm_profile_server()) + return true; + return acpi_ppc; } @@ -459,6 +467,11 @@ static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *pol static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) { } + +static inline bool intel_pstate_acpi_pm_profile_server(void) +{ + return false; +} #endif static inline void update_turbo_state(void) @@ -1841,7 +1854,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum) intel_pstate_hwp_enable(cpu); id = x86_match_cpu(intel_pstate_hwp_boost_ids); - if (id) + if (id && intel_pstate_acpi_pm_profile_server()) hwp_boost = true; } @@ -2394,6 +2407,18 @@ static bool __init intel_pstate_no_acpi_pss(void) return true; } +static bool __init intel_pstate_no_acpi_pcch(void) +{ + acpi_status status; + acpi_handle handle; + + status = acpi_get_handle(NULL, "\\_SB", &handle); + if (ACPI_FAILURE(status)) + return true; + + return !acpi_has_method(handle, "PCCH"); +} + static bool __init intel_pstate_has_acpi_ppc(void) { int i; @@ -2453,7 +2478,10 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void) switch (plat_info[idx].data) { case PSS: - return intel_pstate_no_acpi_pss(); + if (!intel_pstate_no_acpi_pss()) + return false; + + return intel_pstate_no_acpi_pcch(); case PPC: return intel_pstate_has_acpi_ppc() && !force_load; } diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 3f0ce2ae35ee..0c56c9759672 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -580,6 +580,10 @@ static int __init pcc_cpufreq_init(void) { int ret; + /* Skip initialization if another cpufreq driver is there. */ + if (cpufreq_get_current_driver()) + return 0; + if (acpi_disabled) return 0; diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c index 29389accf3e9..efc9a7ae4857 100644 --- a/drivers/cpufreq/qcom-cpufreq-kryo.c +++ b/drivers/cpufreq/qcom-cpufreq-kryo.c @@ -183,6 +183,7 @@ static struct platform_driver qcom_cpufreq_kryo_driver = { static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = { { .compatible = "qcom,apq8096", }, { .compatible = "qcom,msm8996", }, + {} }; /* diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 1c6cbda56afe..09d823d36d3a 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -266,6 +266,8 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key, return; } + count -= initial; + if (initial) asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */ : "+S"(input), "+D"(output) @@ -273,7 +275,7 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key, asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */ : "+S"(input), "+D"(output) - : "d"(control_word), "b"(key), "c"(count - initial)); + : "d"(control_word), "b"(key), "c"(count)); } static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key, @@ -284,6 +286,8 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key, if (count < cbc_fetch_blocks) return cbc_crypt(input, output, key, iv, control_word, count); + count -= initial; + if (initial) asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */ : "+S" (input), "+D" (output), "+a" (iv) @@ -291,7 +295,7 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key, asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */ : "+S" (input), "+D" (output), "+a" (iv) - : "d" (control_word), "b" (key), "c" (count-initial)); + : "d" (control_word), "b" (key), "c" (count)); return iv; } diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 781a4a337557..d8e159feb573 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -87,6 +87,18 @@ config EFI_RUNTIME_WRAPPERS config EFI_ARMSTUB bool +config EFI_ARMSTUB_DTB_LOADER + bool "Enable the DTB loader" + depends on EFI_ARMSTUB + help + Select this config option to add support for the dtb= command + line parameter, allowing a device tree blob to be loaded into + memory from the EFI System Partition by the stub. + + The device tree is typically provided by the platform or by + the bootloader, so this option is mostly for development + purposes only. + config EFI_BOOTLOADER_CONTROL tristate "EFI Bootloader Control" depends on EFI_VARS diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 3bf0dca378a6..a7902fccdcfa 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -48,8 +48,21 @@ u64 cper_next_record_id(void) { static atomic64_t seq; - if (!atomic64_read(&seq)) - atomic64_set(&seq, ((u64)get_seconds()) << 32); + if (!atomic64_read(&seq)) { + time64_t time = ktime_get_real_seconds(); + + /* + * This code is unlikely to still be needed in year 2106, + * but just in case, let's use a few more bits for timestamps + * after y2038 to be sure they keep increasing monotonically + * for the next few hundred years... + */ + if (time < 0x80000000) + atomic64_set(&seq, (ktime_get_real_seconds()) << 32); + else + atomic64_set(&seq, 0x8000000000000000ull | + ktime_get_real_seconds() << 24); + } return atomic64_inc_return(&seq); } @@ -459,7 +472,7 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata else goto err_section_too_small; #if defined(CONFIG_ARM64) || defined(CONFIG_ARM) - } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_ARM)) { + } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { struct cper_sec_proc_arm *arm_err = acpi_hest_get_payload(gdata); printk("%ssection_type: ARM processor error\n", newpfx); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 7f0b19410a95..2a29dd9c986d 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -85,6 +85,8 @@ struct mm_struct efi_mm = { .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0}, }; +struct workqueue_struct *efi_rts_wq; + static bool disable_runtime; static int __init setup_noefi(char *arg) { @@ -338,6 +340,18 @@ static int __init efisubsys_init(void) if (!efi_enabled(EFI_BOOT)) return 0; + /* + * Since we process only one efi_runtime_service() at a time, an + * ordered workqueue (which creates only one execution context) + * should suffice all our needs. + */ + efi_rts_wq = alloc_ordered_workqueue("efi_rts_wq", 0); + if (!efi_rts_wq) { + pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return 0; + } + /* We register the efi directory at /sys/firmware/efi */ efi_kobj = kobject_create_and_add("efi", firmware_kobj); if (!efi_kobj) { @@ -389,7 +403,7 @@ subsys_initcall(efisubsys_init); * and if so, populate the supplied memory descriptor with the appropriate * data. */ -int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) +int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) { efi_memory_desc_t *md; @@ -407,12 +421,6 @@ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) u64 size; u64 end; - if (!(md->attribute & EFI_MEMORY_RUNTIME) && - md->type != EFI_BOOT_SERVICES_DATA && - md->type != EFI_RUNTIME_SERVICES_DATA) { - continue; - } - size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; if (phys_addr >= md->phys_addr && phys_addr < end) { diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c index 1ab80e06e7c5..5d06bd247d07 100644 --- a/drivers/firmware/efi/esrt.c +++ b/drivers/firmware/efi/esrt.c @@ -250,7 +250,10 @@ void __init efi_esrt_init(void) return; rc = efi_mem_desc_lookup(efi.esrt, &md); - if (rc < 0) { + if (rc < 0 || + (!(md.attribute & EFI_MEMORY_RUNTIME) && + md.type != EFI_BOOT_SERVICES_DATA && + md.type != EFI_RUNTIME_SERVICES_DATA)) { pr_warn("ESRT header is not in the memory map.\n"); return; } @@ -326,7 +329,8 @@ void __init efi_esrt_init(void) end = esrt_data + size; pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end); - efi_mem_reserve(esrt_data, esrt_data_size); + if (md.type == EFI_BOOT_SERVICES_DATA) + efi_mem_reserve(esrt_data, esrt_data_size); pr_debug("esrt-init: loaded.\n"); } diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index 01a9d78ee415..6920033de6d4 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -40,31 +40,6 @@ static u64 virtmap_base = EFI_RT_VIRTUAL_BASE; -efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, - void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_t *image = __image; - efi_file_handle_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - - status = sys_table_arg->boottime->handle_protocol(handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to handle fs_proto\n"); - return status; - } - - status = io->open_volume(io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table_arg, "Failed to open volume\n"); - - *__fh = fh; - return status; -} - void efi_char16_printk(efi_system_table_t *sys_table_arg, efi_char16_t *str) { @@ -202,9 +177,10 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, * 'dtb=' unless UEFI Secure Boot is disabled. We assume that secure * boot is enabled if we can't determine its state. */ - if (secure_boot != efi_secureboot_mode_disabled && - strstr(cmdline_ptr, "dtb=")) { - pr_efi(sys_table, "Ignoring DTB from command line.\n"); + if (!IS_ENABLED(CONFIG_EFI_ARMSTUB_DTB_LOADER) || + secure_boot != efi_secureboot_mode_disabled) { + if (strstr(cmdline_ptr, "dtb=")) + pr_efi(sys_table, "Ignoring DTB from command line.\n"); } else { status = handle_cmdline_files(sys_table, image, cmdline_ptr, "dtb=", diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 50a9cab5a834..e94975f4655b 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -413,6 +413,34 @@ static efi_status_t efi_file_close(void *handle) return efi_call_proto(efi_file_handle, close, handle); } +static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, + efi_loaded_image_t *image, + efi_file_handle_t **__fh) +{ + efi_file_io_interface_t *io; + efi_file_handle_t *fh; + efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; + efi_status_t status; + void *handle = (void *)(unsigned long)efi_table_attr(efi_loaded_image, + device_handle, + image); + + status = efi_call_early(handle_protocol, handle, + &fs_proto, (void **)&io); + if (status != EFI_SUCCESS) { + efi_printk(sys_table_arg, "Failed to handle fs_proto\n"); + return status; + } + + status = efi_call_proto(efi_file_io_interface, open_volume, io, &fh); + if (status != EFI_SUCCESS) + efi_printk(sys_table_arg, "Failed to open volume\n"); + else + *__fh = fh; + + return status; +} + /* * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi= * option, e.g. efi=nochunk. @@ -563,8 +591,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, /* Only open the volume once. */ if (!i) { - status = efi_open_volume(sys_table_arg, image, - (void **)&fh); + status = efi_open_volume(sys_table_arg, image, &fh); if (status != EFI_SUCCESS) goto free_files; } diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index f59564b72ddc..32799cf039ef 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -36,9 +36,6 @@ extern int __pure is_quiet(void); void efi_char16_printk(efi_system_table_t *, efi_char16_t *); -efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image, - void **__fh); - unsigned long get_dram_base(efi_system_table_t *sys_table_arg); efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index ae54870b2788..aa66cbf23512 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -1,6 +1,15 @@ /* * runtime-wrappers.c - Runtime Services function call wrappers * + * Implementation summary: + * ----------------------- + * 1. When user/kernel thread requests to execute efi_runtime_service(), + * enqueue work to efi_rts_wq. + * 2. Caller thread waits for completion until the work is finished + * because it's dependent on the return status and execution of + * efi_runtime_service(). + * For instance, get_variable() and get_next_variable(). + * * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> * * Split off from arch/x86/platform/efi/efi.c @@ -22,6 +31,9 @@ #include <linux/mutex.h> #include <linux/semaphore.h> #include <linux/stringify.h> +#include <linux/workqueue.h> +#include <linux/completion.h> + #include <asm/efi.h> /* @@ -33,6 +45,76 @@ #define __efi_call_virt(f, args...) \ __efi_call_virt_pointer(efi.systab->runtime, f, args) +/* efi_runtime_service() function identifiers */ +enum efi_rts_ids { + GET_TIME, + SET_TIME, + GET_WAKEUP_TIME, + SET_WAKEUP_TIME, + GET_VARIABLE, + GET_NEXT_VARIABLE, + SET_VARIABLE, + QUERY_VARIABLE_INFO, + GET_NEXT_HIGH_MONO_COUNT, + UPDATE_CAPSULE, + QUERY_CAPSULE_CAPS, +}; + +/* + * efi_runtime_work: Details of EFI Runtime Service work + * @arg<1-5>: EFI Runtime Service function arguments + * @status: Status of executing EFI Runtime Service + * @efi_rts_id: EFI Runtime Service function identifier + * @efi_rts_comp: Struct used for handling completions + */ +struct efi_runtime_work { + void *arg1; + void *arg2; + void *arg3; + void *arg4; + void *arg5; + efi_status_t status; + struct work_struct work; + enum efi_rts_ids efi_rts_id; + struct completion efi_rts_comp; +}; + +/* + * efi_queue_work: Queue efi_runtime_service() and wait until it's done + * @rts: efi_runtime_service() function identifier + * @rts_arg<1-5>: efi_runtime_service() function arguments + * + * Accesses to efi_runtime_services() are serialized by a binary + * semaphore (efi_runtime_lock) and caller waits until the work is + * finished, hence _only_ one work is queued at a time and the caller + * thread waits for completion. + */ +#define efi_queue_work(_rts, _arg1, _arg2, _arg3, _arg4, _arg5) \ +({ \ + struct efi_runtime_work efi_rts_work; \ + efi_rts_work.status = EFI_ABORTED; \ + \ + init_completion(&efi_rts_work.efi_rts_comp); \ + INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts); \ + efi_rts_work.arg1 = _arg1; \ + efi_rts_work.arg2 = _arg2; \ + efi_rts_work.arg3 = _arg3; \ + efi_rts_work.arg4 = _arg4; \ + efi_rts_work.arg5 = _arg5; \ + efi_rts_work.efi_rts_id = _rts; \ + \ + /* \ + * queue_work() returns 0 if work was already on queue, \ + * _ideally_ this should never happen. \ + */ \ + if (queue_work(efi_rts_wq, &efi_rts_work.work)) \ + wait_for_completion(&efi_rts_work.efi_rts_comp); \ + else \ + pr_err("Failed to queue work to efi_rts_wq.\n"); \ + \ + efi_rts_work.status; \ +}) + void efi_call_virt_check_flags(unsigned long flags, const char *call) { unsigned long cur_flags, mismatch; @@ -90,13 +172,98 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call) */ static DEFINE_SEMAPHORE(efi_runtime_lock); +/* + * Calls the appropriate efi_runtime_service() with the appropriate + * arguments. + * + * Semantics followed by efi_call_rts() to understand efi_runtime_work: + * 1. If argument was a pointer, recast it from void pointer to original + * pointer type. + * 2. If argument was a value, recast it from void pointer to original + * pointer type and dereference it. + */ +static void efi_call_rts(struct work_struct *work) +{ + struct efi_runtime_work *efi_rts_work; + void *arg1, *arg2, *arg3, *arg4, *arg5; + efi_status_t status = EFI_NOT_FOUND; + + efi_rts_work = container_of(work, struct efi_runtime_work, work); + arg1 = efi_rts_work->arg1; + arg2 = efi_rts_work->arg2; + arg3 = efi_rts_work->arg3; + arg4 = efi_rts_work->arg4; + arg5 = efi_rts_work->arg5; + + switch (efi_rts_work->efi_rts_id) { + case GET_TIME: + status = efi_call_virt(get_time, (efi_time_t *)arg1, + (efi_time_cap_t *)arg2); + break; + case SET_TIME: + status = efi_call_virt(set_time, (efi_time_t *)arg1); + break; + case GET_WAKEUP_TIME: + status = efi_call_virt(get_wakeup_time, (efi_bool_t *)arg1, + (efi_bool_t *)arg2, (efi_time_t *)arg3); + break; + case SET_WAKEUP_TIME: + status = efi_call_virt(set_wakeup_time, *(efi_bool_t *)arg1, + (efi_time_t *)arg2); + break; + case GET_VARIABLE: + status = efi_call_virt(get_variable, (efi_char16_t *)arg1, + (efi_guid_t *)arg2, (u32 *)arg3, + (unsigned long *)arg4, (void *)arg5); + break; + case GET_NEXT_VARIABLE: + status = efi_call_virt(get_next_variable, (unsigned long *)arg1, + (efi_char16_t *)arg2, + (efi_guid_t *)arg3); + break; + case SET_VARIABLE: + status = efi_call_virt(set_variable, (efi_char16_t *)arg1, + (efi_guid_t *)arg2, *(u32 *)arg3, + *(unsigned long *)arg4, (void *)arg5); + break; + case QUERY_VARIABLE_INFO: + status = efi_call_virt(query_variable_info, *(u32 *)arg1, + (u64 *)arg2, (u64 *)arg3, (u64 *)arg4); + break; + case GET_NEXT_HIGH_MONO_COUNT: + status = efi_call_virt(get_next_high_mono_count, (u32 *)arg1); + break; + case UPDATE_CAPSULE: + status = efi_call_virt(update_capsule, + (efi_capsule_header_t **)arg1, + *(unsigned long *)arg2, + *(unsigned long *)arg3); + break; + case QUERY_CAPSULE_CAPS: + status = efi_call_virt(query_capsule_caps, + (efi_capsule_header_t **)arg1, + *(unsigned long *)arg2, (u64 *)arg3, + (int *)arg4); + break; + default: + /* + * Ideally, we should never reach here because a caller of this + * function should have put the right efi_runtime_service() + * function identifier into efi_rts_work->efi_rts_id + */ + pr_err("Requested executing invalid EFI Runtime Service.\n"); + } + efi_rts_work->status = status; + complete(&efi_rts_work->efi_rts_comp); +} + static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { efi_status_t status; if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_time, tm, tc); + status = efi_queue_work(GET_TIME, tm, tc, NULL, NULL, NULL); up(&efi_runtime_lock); return status; } @@ -107,7 +274,7 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm) if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(set_time, tm); + status = efi_queue_work(SET_TIME, tm, NULL, NULL, NULL, NULL); up(&efi_runtime_lock); return status; } @@ -120,7 +287,8 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_wakeup_time, enabled, pending, tm); + status = efi_queue_work(GET_WAKEUP_TIME, enabled, pending, tm, NULL, + NULL); up(&efi_runtime_lock); return status; } @@ -131,7 +299,8 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(set_wakeup_time, enabled, tm); + status = efi_queue_work(SET_WAKEUP_TIME, &enabled, tm, NULL, NULL, + NULL); up(&efi_runtime_lock); return status; } @@ -146,8 +315,8 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_variable, name, vendor, attr, data_size, - data); + status = efi_queue_work(GET_VARIABLE, name, vendor, attr, data_size, + data); up(&efi_runtime_lock); return status; } @@ -160,7 +329,8 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_next_variable, name_size, name, vendor); + status = efi_queue_work(GET_NEXT_VARIABLE, name_size, name, vendor, + NULL, NULL); up(&efi_runtime_lock); return status; } @@ -175,8 +345,8 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(set_variable, name, vendor, attr, data_size, - data); + status = efi_queue_work(SET_VARIABLE, name, vendor, &attr, &data_size, + data); up(&efi_runtime_lock); return status; } @@ -210,8 +380,8 @@ static efi_status_t virt_efi_query_variable_info(u32 attr, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(query_variable_info, attr, storage_space, - remaining_space, max_variable_size); + status = efi_queue_work(QUERY_VARIABLE_INFO, &attr, storage_space, + remaining_space, max_variable_size, NULL); up(&efi_runtime_lock); return status; } @@ -242,7 +412,8 @@ static efi_status_t virt_efi_get_next_high_mono_count(u32 *count) if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_next_high_mono_count, count); + status = efi_queue_work(GET_NEXT_HIGH_MONO_COUNT, count, NULL, NULL, + NULL, NULL); up(&efi_runtime_lock); return status; } @@ -272,7 +443,8 @@ static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(update_capsule, capsules, count, sg_list); + status = efi_queue_work(UPDATE_CAPSULE, capsules, &count, &sg_list, + NULL, NULL); up(&efi_runtime_lock); return status; } @@ -289,8 +461,8 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(query_capsule_caps, capsules, count, max_size, - reset_type); + status = efi_queue_work(QUERY_CAPSULE_CAPS, capsules, &count, + max_size, reset_type, NULL); up(&efi_runtime_lock); return status; } diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c index d3cf9502e7e7..58faeb1cef63 100644 --- a/drivers/gpio/gpio-uniphier.c +++ b/drivers/gpio/gpio-uniphier.c @@ -181,7 +181,11 @@ static int uniphier_gpio_to_irq(struct gpio_chip *chip, unsigned int offset) fwspec.fwnode = of_node_to_fwnode(chip->parent->of_node); fwspec.param_count = 2; fwspec.param[0] = offset - UNIPHIER_GPIO_IRQ_OFFSET; - fwspec.param[1] = IRQ_TYPE_NONE; + /* + * IRQ_TYPE_NONE is rejected by the parent irq domain. Set LEVEL_HIGH + * temporarily. Anyway, ->irq_set_type() will override it later. + */ + fwspec.param[1] = IRQ_TYPE_LEVEL_HIGH; return irq_create_fwspec_mapping(&fwspec); } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index e2232cbcec8b..addd9fecc198 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -25,6 +25,7 @@ struct acpi_gpio_event { struct list_head node; + struct list_head initial_sync_list; acpi_handle handle; unsigned int pin; unsigned int irq; @@ -50,6 +51,9 @@ struct acpi_gpio_chip { struct list_head events; }; +static LIST_HEAD(acpi_gpio_initial_sync_list); +static DEFINE_MUTEX(acpi_gpio_initial_sync_list_lock); + static int acpi_gpiochip_find(struct gpio_chip *gc, void *data) { if (!gc->parent) @@ -85,6 +89,21 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin) return gpiochip_get_desc(chip, pin); } +static void acpi_gpio_add_to_initial_sync_list(struct acpi_gpio_event *event) +{ + mutex_lock(&acpi_gpio_initial_sync_list_lock); + list_add(&event->initial_sync_list, &acpi_gpio_initial_sync_list); + mutex_unlock(&acpi_gpio_initial_sync_list_lock); +} + +static void acpi_gpio_del_from_initial_sync_list(struct acpi_gpio_event *event) +{ + mutex_lock(&acpi_gpio_initial_sync_list_lock); + if (!list_empty(&event->initial_sync_list)) + list_del_init(&event->initial_sync_list); + mutex_unlock(&acpi_gpio_initial_sync_list_lock); +} + static irqreturn_t acpi_gpio_irq_handler(int irq, void *data) { struct acpi_gpio_event *event = data; @@ -136,7 +155,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, irq_handler_t handler = NULL; struct gpio_desc *desc; unsigned long irqflags; - int ret, pin, irq; + int ret, pin, irq, value; if (!acpi_gpio_get_irq_resource(ares, &agpio)) return AE_OK; @@ -167,6 +186,8 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, gpiod_direction_input(desc); + value = gpiod_get_value(desc); + ret = gpiochip_lock_as_irq(chip, pin); if (ret) { dev_err(chip->parent, "Failed to lock GPIO as interrupt\n"); @@ -208,6 +229,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, event->irq = irq; event->pin = pin; event->desc = desc; + INIT_LIST_HEAD(&event->initial_sync_list); ret = request_threaded_irq(event->irq, NULL, handler, irqflags, "ACPI:Event", event); @@ -222,6 +244,18 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, enable_irq_wake(irq); list_add_tail(&event->node, &acpi_gpio->events); + + /* + * Make sure we trigger the initial state of the IRQ when using RISING + * or FALLING. Note we run the handlers on late_init, the AML code + * may refer to OperationRegions from other (builtin) drivers which + * may be probed after us. + */ + if (handler == acpi_gpio_irq_handler && + (((irqflags & IRQF_TRIGGER_RISING) && value == 1) || + ((irqflags & IRQF_TRIGGER_FALLING) && value == 0))) + acpi_gpio_add_to_initial_sync_list(event); + return AE_OK; fail_free_event: @@ -294,6 +328,8 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) { struct gpio_desc *desc; + acpi_gpio_del_from_initial_sync_list(event); + if (irqd_is_wakeup_set(irq_get_irq_data(event->irq))) disable_irq_wake(event->irq); @@ -1158,3 +1194,21 @@ bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id) return con_id == NULL; } + +/* Sync the initial state of handlers after all builtin drivers have probed */ +static int acpi_gpio_initial_sync(void) +{ + struct acpi_gpio_event *event, *ep; + + mutex_lock(&acpi_gpio_initial_sync_list_lock); + list_for_each_entry_safe(event, ep, &acpi_gpio_initial_sync_list, + initial_sync_list) { + acpi_evaluate_object(event->handle, NULL, NULL, NULL); + list_del_init(&event->initial_sync_list); + } + mutex_unlock(&acpi_gpio_initial_sync_list_lock); + + return 0; +} +/* We must use _sync so that this runs after the first deferred_probe run */ +late_initcall_sync(acpi_gpio_initial_sync); diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 28d968088131..53a14ee8ad6d 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -64,7 +64,8 @@ static void of_gpio_flags_quirks(struct device_node *np, * Note that active low is the default. */ if (IS_ENABLED(CONFIG_REGULATOR) && - (of_device_is_compatible(np, "reg-fixed-voltage") || + (of_device_is_compatible(np, "regulator-fixed") || + of_device_is_compatible(np, "reg-fixed-voltage") || of_device_is_compatible(np, "regulator-gpio"))) { /* * The regulator GPIO handles are specified such that the diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c index f4c474a95875..71efcf38f11b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c @@ -57,6 +57,10 @@ #define ACP_I2S_COMP2_CAP_REG_OFFSET 0xa8 #define ACP_I2S_COMP1_PLAY_REG_OFFSET 0x6c #define ACP_I2S_COMP2_PLAY_REG_OFFSET 0x68 +#define ACP_BT_PLAY_REGS_START 0x14970 +#define ACP_BT_PLAY_REGS_END 0x14a24 +#define ACP_BT_COMP1_REG_OFFSET 0xac +#define ACP_BT_COMP2_REG_OFFSET 0xa8 #define mmACP_PGFSM_RETAIN_REG 0x51c9 #define mmACP_PGFSM_CONFIG_REG 0x51ca @@ -77,7 +81,7 @@ #define ACP_SOFT_RESET_DONE_TIME_OUT_VALUE 0x000000FF #define ACP_TIMEOUT_LOOP 0x000000FF -#define ACP_DEVS 3 +#define ACP_DEVS 4 #define ACP_SRC_ID 162 enum { @@ -316,14 +320,13 @@ static int acp_hw_init(void *handle) if (adev->acp.acp_cell == NULL) return -ENOMEM; - adev->acp.acp_res = kcalloc(4, sizeof(struct resource), GFP_KERNEL); - + adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL); if (adev->acp.acp_res == NULL) { kfree(adev->acp.acp_cell); return -ENOMEM; } - i2s_pdata = kcalloc(2, sizeof(struct i2s_platform_data), GFP_KERNEL); + i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL); if (i2s_pdata == NULL) { kfree(adev->acp.acp_res); kfree(adev->acp.acp_cell); @@ -358,6 +361,20 @@ static int acp_hw_init(void *handle) i2s_pdata[1].i2s_reg_comp1 = ACP_I2S_COMP1_CAP_REG_OFFSET; i2s_pdata[1].i2s_reg_comp2 = ACP_I2S_COMP2_CAP_REG_OFFSET; + i2s_pdata[2].quirks = DW_I2S_QUIRK_COMP_REG_OFFSET; + switch (adev->asic_type) { + case CHIP_STONEY: + i2s_pdata[2].quirks |= DW_I2S_QUIRK_16BIT_IDX_OVERRIDE; + break; + default: + break; + } + + i2s_pdata[2].cap = DWC_I2S_PLAY | DWC_I2S_RECORD; + i2s_pdata[2].snd_rates = SNDRV_PCM_RATE_8000_96000; + i2s_pdata[2].i2s_reg_comp1 = ACP_BT_COMP1_REG_OFFSET; + i2s_pdata[2].i2s_reg_comp2 = ACP_BT_COMP2_REG_OFFSET; + adev->acp.acp_res[0].name = "acp2x_dma"; adev->acp.acp_res[0].flags = IORESOURCE_MEM; adev->acp.acp_res[0].start = acp_base; @@ -373,13 +390,18 @@ static int acp_hw_init(void *handle) adev->acp.acp_res[2].start = acp_base + ACP_I2S_CAP_REGS_START; adev->acp.acp_res[2].end = acp_base + ACP_I2S_CAP_REGS_END; - adev->acp.acp_res[3].name = "acp2x_dma_irq"; - adev->acp.acp_res[3].flags = IORESOURCE_IRQ; - adev->acp.acp_res[3].start = amdgpu_irq_create_mapping(adev, 162); - adev->acp.acp_res[3].end = adev->acp.acp_res[3].start; + adev->acp.acp_res[3].name = "acp2x_dw_bt_i2s_play_cap"; + adev->acp.acp_res[3].flags = IORESOURCE_MEM; + adev->acp.acp_res[3].start = acp_base + ACP_BT_PLAY_REGS_START; + adev->acp.acp_res[3].end = acp_base + ACP_BT_PLAY_REGS_END; + + adev->acp.acp_res[4].name = "acp2x_dma_irq"; + adev->acp.acp_res[4].flags = IORESOURCE_IRQ; + adev->acp.acp_res[4].start = amdgpu_irq_create_mapping(adev, 162); + adev->acp.acp_res[4].end = adev->acp.acp_res[4].start; adev->acp.acp_cell[0].name = "acp_audio_dma"; - adev->acp.acp_cell[0].num_resources = 4; + adev->acp.acp_cell[0].num_resources = 5; adev->acp.acp_cell[0].resources = &adev->acp.acp_res[0]; adev->acp.acp_cell[0].platform_data = &adev->asic_type; adev->acp.acp_cell[0].pdata_size = sizeof(adev->asic_type); @@ -396,6 +418,12 @@ static int acp_hw_init(void *handle) adev->acp.acp_cell[2].platform_data = &i2s_pdata[1]; adev->acp.acp_cell[2].pdata_size = sizeof(struct i2s_platform_data); + adev->acp.acp_cell[3].name = "designware-i2s"; + adev->acp.acp_cell[3].num_resources = 1; + adev->acp.acp_cell[3].resources = &adev->acp.acp_res[3]; + adev->acp.acp_cell[3].platform_data = &i2s_pdata[2]; + adev->acp.acp_cell[3].pdata_size = sizeof(struct i2s_platform_data); + r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell, ACP_DEVS); if (r) @@ -451,7 +479,6 @@ static int acp_hw_init(void *handle) val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET); val &= ~ACP_SOFT_RESET__SoftResetAud_MASK; cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val); - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 9ab89371d9e8..ca8bf1c9a98e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -575,6 +575,7 @@ static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = { { 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX }, { 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX }, { 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX }, + { 0x1002, 0x6900, 0x1025, 0x125A, AMDGPU_PX_QUIRK_FORCE_ATPX }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 82312a7bc6ad..9c85a90be293 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -927,6 +927,10 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev, r = amdgpu_bo_vm_update_pte(p); if (r) return r; + + r = reservation_object_reserve_shared(vm->root.base.bo->tbo.resv); + if (r) + return r; } return amdgpu_cs_sync_rings(p); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 6e5284e6c028..2c5f093e79e3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2747,6 +2747,9 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon) if (r) return r; + /* Make sure IB tests flushed */ + flush_delayed_work(&adev->late_init_work); + /* blat the mode back in */ if (fbcon) { if (!amdgpu_device_has_dc_support(adev)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index edf16b2b957a..fdcb498f6d19 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -107,6 +107,9 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, return; list_add_tail(&base->bo_list, &bo->va); + if (bo->tbo.type == ttm_bo_type_kernel) + list_move(&base->vm_status, &vm->relocated); + if (bo->tbo.resv != vm->root.base.bo->tbo.resv) return; @@ -468,7 +471,6 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev, pt->parent = amdgpu_bo_ref(parent->base.bo); amdgpu_vm_bo_base_init(&entry->base, vm, pt); - list_move(&entry->base.vm_status, &vm->relocated); } if (level < AMDGPU_VM_PTB) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 4304d9e408b8..ace9ad578ca0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -83,22 +83,21 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ? I2C_MOT_TRUE : I2C_MOT_FALSE; enum ddc_result res; - uint32_t read_bytes = msg->size; + ssize_t read_bytes; if (WARN_ON(msg->size > 16)) return -E2BIG; switch (msg->request & ~DP_AUX_I2C_MOT) { case DP_AUX_NATIVE_READ: - res = dal_ddc_service_read_dpcd_data( + read_bytes = dal_ddc_service_read_dpcd_data( TO_DM_AUX(aux)->ddc_service, false, I2C_MOT_UNDEF, msg->address, msg->buffer, - msg->size, - &read_bytes); - break; + msg->size); + return read_bytes; case DP_AUX_NATIVE_WRITE: res = dal_ddc_service_write_dpcd_data( TO_DM_AUX(aux)->ddc_service, @@ -109,15 +108,14 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, msg->size); break; case DP_AUX_I2C_READ: - res = dal_ddc_service_read_dpcd_data( + read_bytes = dal_ddc_service_read_dpcd_data( TO_DM_AUX(aux)->ddc_service, true, mot, msg->address, msg->buffer, - msg->size, - &read_bytes); - break; + msg->size); + return read_bytes; case DP_AUX_I2C_WRITE: res = dal_ddc_service_write_dpcd_data( TO_DM_AUX(aux)->ddc_service, @@ -139,9 +137,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, r == DDC_RESULT_SUCESSFULL); #endif - if (res != DDC_RESULT_SUCESSFULL) - return -EIO; - return read_bytes; + return msg->size; } static enum drm_connector_status diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c index 5a3346124a01..5a2e952c5bea 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c @@ -255,8 +255,9 @@ static void pp_to_dc_clock_levels_with_latency( DC_DECODE_PP_CLOCK_TYPE(dc_clk_type)); for (i = 0; i < clk_level_info->num_levels; i++) { - DRM_DEBUG("DM_PPLIB:\t %d\n", pp_clks->data[i].clocks_in_khz); - clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz; + DRM_DEBUG("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz); + /* translate 10kHz to kHz */ + clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10; clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us; } } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index ae48d603ebd6..49c2face1e7a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -629,14 +629,13 @@ bool dal_ddc_service_query_ddc_data( return ret; } -enum ddc_result dal_ddc_service_read_dpcd_data( +ssize_t dal_ddc_service_read_dpcd_data( struct ddc_service *ddc, bool i2c, enum i2c_mot_mode mot, uint32_t address, uint8_t *data, - uint32_t len, - uint32_t *read) + uint32_t len) { struct aux_payload read_payload = { .i2c_over_aux = i2c, @@ -653,8 +652,6 @@ enum ddc_result dal_ddc_service_read_dpcd_data( .mot = mot }; - *read = 0; - if (len > DEFAULT_AUX_MAX_DATA_SIZE) { BREAK_TO_DEBUGGER(); return DDC_RESULT_FAILED_INVALID_OPERATION; @@ -664,8 +661,7 @@ enum ddc_result dal_ddc_service_read_dpcd_data( ddc->ctx->i2caux, ddc->ddc_pin, &command)) { - *read = command.payloads->length; - return DDC_RESULT_SUCESSFULL; + return (ssize_t)command.payloads->length; } return DDC_RESULT_FAILED_OPERATION; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 7857cb42b3e6..bdd121485cbc 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1767,12 +1767,10 @@ static void dp_test_send_link_training(struct dc_link *link) dp_retrain_link_dp_test(link, &link_settings, false); } -/* TODO hbr2 compliance eye output is unstable +/* TODO Raven hbr2 compliance eye output is unstable * (toggling on and off) with debugger break * This caueses intermittent PHY automation failure * Need to look into the root cause */ -static uint8_t force_tps4_for_cp2520 = 1; - static void dp_test_send_phy_test_pattern(struct dc_link *link) { union phy_test_pattern dpcd_test_pattern; @@ -1832,13 +1830,13 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link) break; case PHY_TEST_PATTERN_CP2520_1: /* CP2520 pattern is unstable, temporarily use TPS4 instead */ - test_pattern = (force_tps4_for_cp2520 == 1) ? + test_pattern = (link->dc->caps.force_dp_tps4_for_cp2520 == 1) ? DP_TEST_PATTERN_TRAINING_PATTERN4 : DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE; break; case PHY_TEST_PATTERN_CP2520_2: /* CP2520 pattern is unstable, temporarily use TPS4 instead */ - test_pattern = (force_tps4_for_cp2520 == 1) ? + test_pattern = (link->dc->caps.force_dp_tps4_for_cp2520 == 1) ? DP_TEST_PATTERN_TRAINING_PATTERN4 : DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE; break; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 9cfde0ccf4e9..53c71296f3dd 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -76,6 +76,7 @@ struct dc_caps { bool is_apu; bool dual_link_dvi; bool post_blend_color_processing; + bool force_dp_tps4_for_cp2520; }; struct dc_dcc_surface_param { diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c index b235a75355b8..bae752332a9f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c @@ -741,6 +741,29 @@ static struct mem_input_funcs dce_mi_funcs = { .mem_input_is_flip_pending = dce_mi_is_flip_pending }; +static struct mem_input_funcs dce112_mi_funcs = { + .mem_input_program_display_marks = dce112_mi_program_display_marks, + .allocate_mem_input = dce_mi_allocate_dmif, + .free_mem_input = dce_mi_free_dmif, + .mem_input_program_surface_flip_and_addr = + dce_mi_program_surface_flip_and_addr, + .mem_input_program_pte_vm = dce_mi_program_pte_vm, + .mem_input_program_surface_config = + dce_mi_program_surface_config, + .mem_input_is_flip_pending = dce_mi_is_flip_pending +}; + +static struct mem_input_funcs dce120_mi_funcs = { + .mem_input_program_display_marks = dce120_mi_program_display_marks, + .allocate_mem_input = dce_mi_allocate_dmif, + .free_mem_input = dce_mi_free_dmif, + .mem_input_program_surface_flip_and_addr = + dce_mi_program_surface_flip_and_addr, + .mem_input_program_pte_vm = dce_mi_program_pte_vm, + .mem_input_program_surface_config = + dce_mi_program_surface_config, + .mem_input_is_flip_pending = dce_mi_is_flip_pending +}; void dce_mem_input_construct( struct dce_mem_input *dce_mi, @@ -769,7 +792,7 @@ void dce112_mem_input_construct( const struct dce_mem_input_mask *mi_mask) { dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask); - dce_mi->base.funcs->mem_input_program_display_marks = dce112_mi_program_display_marks; + dce_mi->base.funcs = &dce112_mi_funcs; } void dce120_mem_input_construct( @@ -781,5 +804,5 @@ void dce120_mem_input_construct( const struct dce_mem_input_mask *mi_mask) { dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask); - dce_mi->base.funcs->mem_input_program_display_marks = dce120_mi_program_display_marks; + dce_mi->base.funcs = &dce120_mi_funcs; } diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c index 38ec0d609297..344dd2e69e7c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c @@ -678,9 +678,22 @@ bool dce100_validate_bandwidth( struct dc *dc, struct dc_state *context) { - /* TODO implement when needed but for now hardcode max value*/ - context->bw.dce.dispclk_khz = 681000; - context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER; + int i; + bool at_least_one_pipe = false; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].stream) + at_least_one_pipe = true; + } + + if (at_least_one_pipe) { + /* TODO implement when needed but for now hardcode max value*/ + context->bw.dce.dispclk_khz = 681000; + context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER; + } else { + context->bw.dce.dispclk_khz = 0; + context->bw.dce.yclk_khz = 0; + } return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index df5cb2d1d164..34dac84066a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -1027,6 +1027,8 @@ static bool construct( dc->caps.max_slave_planes = 1; dc->caps.is_apu = true; dc->caps.post_blend_color_processing = false; + /* Raven DP PHY HBR2 eye diagram pattern is not stable. Use TP4 */ + dc->caps.force_dp_tps4_for_cp2520 = true; if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV) dc->debug = debug_defaults_drv; diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h index 30b3a08b91be..090b7a8dd67b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h @@ -102,14 +102,13 @@ bool dal_ddc_service_query_ddc_data( uint8_t *read_buf, uint32_t read_size); -enum ddc_result dal_ddc_service_read_dpcd_data( +ssize_t dal_ddc_service_read_dpcd_data( struct ddc_service *ddc, bool i2c, enum i2c_mot_mode mot, uint32_t address, uint8_t *data, - uint32_t len, - uint32_t *read); + uint32_t len); enum ddc_result dal_ddc_service_write_dpcd_data( struct ddc_service *ddc, diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c index d644a9bb9078..9f407c48d4f0 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c @@ -381,6 +381,7 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr) uint32_t fw_to_load; int result = 0; struct SMU_DRAMData_TOC *toc; + uint32_t num_entries = 0; if (!hwmgr->reload_fw) { pr_info("skip reloading...\n"); @@ -422,41 +423,41 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr) } toc = (struct SMU_DRAMData_TOC *)smu_data->header; - toc->num_entries = 0; toc->structure_version = 1; PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr, - UCODE_ID_RLC_G, &toc->entry[toc->num_entries++]), + UCODE_ID_RLC_G, &toc->entry[num_entries++]), "Failed to Get Firmware Entry.", return -EINVAL); PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr, - UCODE_ID_CP_CE, &toc->entry[toc->num_entries++]), + UCODE_ID_CP_CE, &toc->entry[num_entries++]), "Failed to Get Firmware Entry.", return -EINVAL); PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr, - UCODE_ID_CP_PFP, &toc->entry[toc->num_entries++]), + UCODE_ID_CP_PFP, &toc->entry[num_entries++]), "Failed to Get Firmware Entry.", return -EINVAL); PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr, - UCODE_ID_CP_ME, &toc->entry[toc->num_entries++]), + UCODE_ID_CP_ME, &toc->entry[num_entries++]), "Failed to Get Firmware Entry.", return -EINVAL); PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr, - UCODE_ID_CP_MEC, &toc->entry[toc->num_entries++]), + UCODE_ID_CP_MEC, &toc->entry[num_entries++]), "Failed to Get Firmware Entry.", return -EINVAL); PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr, - UCODE_ID_CP_MEC_JT1, &toc->entry[toc->num_entries++]), + UCODE_ID_CP_MEC_JT1, &toc->entry[num_entries++]), "Failed to Get Firmware Entry.", return -EINVAL); PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr, - UCODE_ID_CP_MEC_JT2, &toc->entry[toc->num_entries++]), + UCODE_ID_CP_MEC_JT2, &toc->entry[num_entries++]), "Failed to Get Firmware Entry.", return -EINVAL); PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr, - UCODE_ID_SDMA0, &toc->entry[toc->num_entries++]), + UCODE_ID_SDMA0, &toc->entry[num_entries++]), "Failed to Get Firmware Entry.", return -EINVAL); PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr, - UCODE_ID_SDMA1, &toc->entry[toc->num_entries++]), + UCODE_ID_SDMA1, &toc->entry[num_entries++]), "Failed to Get Firmware Entry.", return -EINVAL); if (!hwmgr->not_vf) PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr, - UCODE_ID_MEC_STORAGE, &toc->entry[toc->num_entries++]), + UCODE_ID_MEC_STORAGE, &toc->entry[num_entries++]), "Failed to Get Firmware Entry.", return -EINVAL); + toc->num_entries = num_entries; smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_HI, upper_32_bits(smu_data->header_buffer.mc_addr)); smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_LO, lower_32_bits(smu_data->header_buffer.mc_addr)); diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c index 03eeee11dd5b..42a40daff132 100644 --- a/drivers/gpu/drm/armada/armada_crtc.c +++ b/drivers/gpu/drm/armada/armada_crtc.c @@ -519,8 +519,9 @@ static irqreturn_t armada_drm_irq(int irq, void *arg) u32 v, stat = readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR); /* - * This is rediculous - rather than writing bits to clear, we - * have to set the actual status register value. This is racy. + * Reading the ISR appears to clear bits provided CLEAN_SPU_IRQ_ISR + * is set. Writing has some other effect to acknowledge the IRQ - + * without this, we only get a single IRQ. */ writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR); @@ -1116,16 +1117,22 @@ armada_drm_crtc_set_property(struct drm_crtc *crtc, static int armada_drm_crtc_enable_vblank(struct drm_crtc *crtc) { struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); + unsigned long flags; + spin_lock_irqsave(&dcrtc->irq_lock, flags); armada_drm_crtc_enable_irq(dcrtc, VSYNC_IRQ_ENA); + spin_unlock_irqrestore(&dcrtc->irq_lock, flags); return 0; } static void armada_drm_crtc_disable_vblank(struct drm_crtc *crtc) { struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); + unsigned long flags; + spin_lock_irqsave(&dcrtc->irq_lock, flags); armada_drm_crtc_disable_irq(dcrtc, VSYNC_IRQ_ENA); + spin_unlock_irqrestore(&dcrtc->irq_lock, flags); } static const struct drm_crtc_funcs armada_crtc_funcs = { @@ -1415,6 +1422,7 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev, CFG_PDWN64x66, dcrtc->base + LCD_SPU_SRAM_PARA1); writel_relaxed(0x2032ff81, dcrtc->base + LCD_SPU_DMA_CTRL1); writel_relaxed(dcrtc->irq_ena, dcrtc->base + LCD_SPU_IRQ_ENA); + readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR); writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR); ret = devm_request_irq(dev, irq, armada_drm_irq, 0, "armada_drm_crtc", diff --git a/drivers/gpu/drm/armada/armada_hw.h b/drivers/gpu/drm/armada/armada_hw.h index 27319a8335e2..345dc4d0851e 100644 --- a/drivers/gpu/drm/armada/armada_hw.h +++ b/drivers/gpu/drm/armada/armada_hw.h @@ -160,6 +160,7 @@ enum { CFG_ALPHAM_GRA = 0x1 << 16, CFG_ALPHAM_CFG = 0x2 << 16, CFG_ALPHA_MASK = 0xff << 8, +#define CFG_ALPHA(x) ((x) << 8) CFG_PIXCMD_MASK = 0xff, }; diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c index c391955009d6..afa7ded3ae31 100644 --- a/drivers/gpu/drm/armada/armada_overlay.c +++ b/drivers/gpu/drm/armada/armada_overlay.c @@ -28,6 +28,7 @@ struct armada_ovl_plane_properties { uint16_t contrast; uint16_t saturation; uint32_t colorkey_mode; + uint32_t colorkey_enable; }; struct armada_ovl_plane { @@ -54,11 +55,13 @@ armada_ovl_update_attr(struct armada_ovl_plane_properties *prop, writel_relaxed(0x00002000, dcrtc->base + LCD_SPU_CBSH_HUE); spin_lock_irq(&dcrtc->irq_lock); - armada_updatel(prop->colorkey_mode | CFG_ALPHAM_GRA, - CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK, - dcrtc->base + LCD_SPU_DMA_CTRL1); - - armada_updatel(ADV_GRACOLORKEY, 0, dcrtc->base + LCD_SPU_ADV_REG); + armada_updatel(prop->colorkey_mode, + CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK, + dcrtc->base + LCD_SPU_DMA_CTRL1); + if (dcrtc->variant->has_spu_adv_reg) + armada_updatel(prop->colorkey_enable, + ADV_GRACOLORKEY | ADV_VIDCOLORKEY, + dcrtc->base + LCD_SPU_ADV_REG); spin_unlock_irq(&dcrtc->irq_lock); } @@ -321,8 +324,17 @@ static int armada_ovl_plane_set_property(struct drm_plane *plane, dplane->prop.colorkey_vb |= K2B(val); update_attr = true; } else if (property == priv->colorkey_mode_prop) { - dplane->prop.colorkey_mode &= ~CFG_CKMODE_MASK; - dplane->prop.colorkey_mode |= CFG_CKMODE(val); + if (val == CKMODE_DISABLE) { + dplane->prop.colorkey_mode = + CFG_CKMODE(CKMODE_DISABLE) | + CFG_ALPHAM_CFG | CFG_ALPHA(255); + dplane->prop.colorkey_enable = 0; + } else { + dplane->prop.colorkey_mode = + CFG_CKMODE(val) | + CFG_ALPHAM_GRA | CFG_ALPHA(0); + dplane->prop.colorkey_enable = ADV_GRACOLORKEY; + } update_attr = true; } else if (property == priv->brightness_prop) { dplane->prop.brightness = val - 256; @@ -453,7 +465,9 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs) dplane->prop.colorkey_yr = 0xfefefe00; dplane->prop.colorkey_ug = 0x01010100; dplane->prop.colorkey_vb = 0x01010100; - dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB); + dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB) | + CFG_ALPHAM_GRA | CFG_ALPHA(0); + dplane->prop.colorkey_enable = ADV_GRACOLORKEY; dplane->prop.brightness = 0; dplane->prop.contrast = 0x4000; dplane->prop.saturation = 0x4000; diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 73021b388e12..dd3ff2f2cdce 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -429,6 +429,18 @@ static void adv7511_hpd_work(struct work_struct *work) else status = connector_status_disconnected; + /* + * The bridge resets its registers on unplug. So when we get a plug + * event and we're already supposed to be powered, cycle the bridge to + * restore its state. + */ + if (status == connector_status_connected && + adv7511->connector.status == connector_status_disconnected && + adv7511->powered) { + regcache_mark_dirty(adv7511->regmap); + adv7511_power_on(adv7511); + } + if (adv7511->connector.status != status) { adv7511->connector.status = status; if (status == connector_status_disconnected) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 130da5195f3b..81e32199d3ef 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1510,8 +1510,9 @@ int drm_atomic_helper_async_check(struct drm_device *dev, { struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; - struct drm_plane *plane; - struct drm_plane_state *old_plane_state, *new_plane_state; + struct drm_plane *plane = NULL; + struct drm_plane_state *old_plane_state = NULL; + struct drm_plane_state *new_plane_state = NULL; const struct drm_plane_helper_funcs *funcs; int i, n_planes = 0; @@ -1527,7 +1528,8 @@ int drm_atomic_helper_async_check(struct drm_device *dev, if (n_planes != 1) return -EINVAL; - if (!new_plane_state->crtc) + if (!new_plane_state->crtc || + old_plane_state->crtc != new_plane_state->crtc) return -EINVAL; funcs = plane->helper_private; diff --git a/drivers/gpu/drm/drm_context.c b/drivers/gpu/drm/drm_context.c index 3c4000facb36..f973d287696a 100644 --- a/drivers/gpu/drm/drm_context.c +++ b/drivers/gpu/drm/drm_context.c @@ -372,7 +372,7 @@ int drm_legacy_addctx(struct drm_device *dev, void *data, ctx->handle = drm_legacy_ctxbitmap_next(dev); } DRM_DEBUG("%d\n", ctx->handle); - if (ctx->handle == -1) { + if (ctx->handle < 0) { DRM_DEBUG("Not enough free contexts.\n"); /* Should this return -EBUSY instead? */ return -ENOMEM; diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index 50c73c0a20b9..d638c0fb3418 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -553,24 +553,13 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, /* Clone the lessor file to create a new file for us */ DRM_DEBUG_LEASE("Allocating lease file\n"); - path_get(&lessor_file->f_path); - lessee_file = alloc_file(&lessor_file->f_path, - lessor_file->f_mode, - fops_get(lessor_file->f_inode->i_fop)); - + lessee_file = filp_clone_open(lessor_file); if (IS_ERR(lessee_file)) { ret = PTR_ERR(lessee_file); goto out_lessee; } - /* Initialize the new file for DRM */ - DRM_DEBUG_LEASE("Initializing the file with %p\n", lessee_file->f_op->open); - ret = lessee_file->f_op->open(lessee_file->f_inode, lessee_file); - if (ret) - goto out_lessee_file; - lessee_priv = lessee_file->private_data; - /* Change the file to a master one */ drm_master_put(&lessee_priv->master); lessee_priv->master = lessee; @@ -588,9 +577,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n"); return 0; -out_lessee_file: - fput(lessee_file); - out_lessee: drm_master_put(&lessee); diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index b51c05d03f14..7f562410f9cf 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -862,6 +862,7 @@ static int cmd_reg_handler(struct parser_exec_state *s, { struct intel_vgpu *vgpu = s->vgpu; struct intel_gvt *gvt = vgpu->gvt; + u32 ctx_sr_ctl; if (offset + 4 > gvt->device_info.mmio_size) { gvt_vgpu_err("%s access to (%x) outside of MMIO range\n", @@ -894,6 +895,28 @@ static int cmd_reg_handler(struct parser_exec_state *s, patch_value(s, cmd_ptr(s, index), VGT_PVINFO_PAGE); } + /* TODO + * Right now only scan LRI command on KBL and in inhibit context. + * It's good enough to support initializing mmio by lri command in + * vgpu inhibit context on KBL. + */ + if (IS_KABYLAKE(s->vgpu->gvt->dev_priv) && + intel_gvt_mmio_is_in_ctx(gvt, offset) && + !strncmp(cmd, "lri", 3)) { + intel_gvt_hypervisor_read_gpa(s->vgpu, + s->workload->ring_context_gpa + 12, &ctx_sr_ctl, 4); + /* check inhibit context */ + if (ctx_sr_ctl & 1) { + u32 data = cmd_val(s, index + 1); + + if (intel_gvt_mmio_has_mode_mask(s->vgpu->gvt, offset)) + intel_vgpu_mask_mmio_write(vgpu, + offset, &data, 4); + else + vgpu_vreg(vgpu, offset) = data; + } + } + /* TODO: Update the global mask if this MMIO is a masked-MMIO */ intel_gvt_mmio_set_cmd_accessed(gvt, offset); return 0; diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 05d15a095310..858967daf04b 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -268,6 +268,8 @@ struct intel_gvt_mmio { #define F_CMD_ACCESSED (1 << 5) /* This reg could be accessed by unaligned address */ #define F_UNALIGN (1 << 6) +/* This reg is saved/restored in context */ +#define F_IN_CTX (1 << 7) struct gvt_mmio_block *mmio_block; unsigned int num_mmio_block; @@ -639,6 +641,33 @@ static inline bool intel_gvt_mmio_has_mode_mask( return gvt->mmio.mmio_attribute[offset >> 2] & F_MODE_MASK; } +/** + * intel_gvt_mmio_is_in_ctx - check if a MMIO has in-ctx mask + * @gvt: a GVT device + * @offset: register offset + * + * Returns: + * True if a MMIO has a in-context mask, false if it isn't. + * + */ +static inline bool intel_gvt_mmio_is_in_ctx( + struct intel_gvt *gvt, unsigned int offset) +{ + return gvt->mmio.mmio_attribute[offset >> 2] & F_IN_CTX; +} + +/** + * intel_gvt_mmio_set_in_ctx - mask a MMIO in logical context + * @gvt: a GVT device + * @offset: register offset + * + */ +static inline void intel_gvt_mmio_set_in_ctx( + struct intel_gvt *gvt, unsigned int offset) +{ + gvt->mmio.mmio_attribute[offset >> 2] |= F_IN_CTX; +} + int intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu); void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu); int intel_gvt_debugfs_init(struct intel_gvt *gvt); diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index bcbc47a88a70..8f1caacdc78a 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -3046,6 +3046,30 @@ int intel_vgpu_default_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, } /** + * intel_vgpu_mask_mmio_write - write mask register + * @vgpu: a vGPU + * @offset: access offset + * @p_data: write data buffer + * @bytes: access data length + * + * Returns: + * Zero on success, negative error code if failed. + */ +int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, + void *p_data, unsigned int bytes) +{ + u32 mask, old_vreg; + + old_vreg = vgpu_vreg(vgpu, offset); + write_vreg(vgpu, offset, p_data, bytes); + mask = vgpu_vreg(vgpu, offset) >> 16; + vgpu_vreg(vgpu, offset) = (old_vreg & ~mask) | + (vgpu_vreg(vgpu, offset) & mask); + + return 0; +} + +/** * intel_gvt_in_force_nonpriv_whitelist - if a mmio is in whitelist to be * force-nopriv register * diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h index 71b620875943..dac8c6401e26 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.h +++ b/drivers/gpu/drm/i915/gvt/mmio.h @@ -98,4 +98,6 @@ bool intel_gvt_in_force_nonpriv_whitelist(struct intel_gvt *gvt, int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset, void *pdata, unsigned int bytes, bool is_read); +int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, + void *p_data, unsigned int bytes); #endif diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 0f949554d118..5ca9caf7552a 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -581,7 +581,9 @@ void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt) for (mmio = gvt->engine_mmio_list.mmio; i915_mmio_reg_valid(mmio->reg); mmio++) { - if (mmio->in_context) + if (mmio->in_context) { gvt->engine_mmio_list.ctx_mmio_count[mmio->ring_id]++; + intel_gvt_mmio_set_in_ctx(gvt, mmio->reg.reg); + } } } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 52f3b91d14fd..71e1aa54f774 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -652,6 +652,7 @@ enum intel_sbi_destination { #define QUIRK_BACKLIGHT_PRESENT (1<<3) #define QUIRK_PIN_SWIZZLED_PAGES (1<<5) #define QUIRK_INCREASE_T12_DELAY (1<<6) +#define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7) struct intel_fbdev; struct intel_fbc_work; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 4a02747ac658..c16cb025755e 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1998,10 +1998,38 @@ static void valleyview_pipestat_irq_handler(struct drm_i915_private *dev_priv, static u32 i9xx_hpd_irq_ack(struct drm_i915_private *dev_priv) { - u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT); + u32 hotplug_status = 0, hotplug_status_mask; + int i; + + if (IS_G4X(dev_priv) || + IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) + hotplug_status_mask = HOTPLUG_INT_STATUS_G4X | + DP_AUX_CHANNEL_MASK_INT_STATUS_G4X; + else + hotplug_status_mask = HOTPLUG_INT_STATUS_I915; - if (hotplug_status) + /* + * We absolutely have to clear all the pending interrupt + * bits in PORT_HOTPLUG_STAT. Otherwise the ISR port + * interrupt bit won't have an edge, and the i965/g4x + * edge triggered IIR will not notice that an interrupt + * is still pending. We can't use PORT_HOTPLUG_EN to + * guarantee the edge as the act of toggling the enable + * bits can itself generate a new hotplug interrupt :( + */ + for (i = 0; i < 10; i++) { + u32 tmp = I915_READ(PORT_HOTPLUG_STAT) & hotplug_status_mask; + + if (tmp == 0) + return hotplug_status; + + hotplug_status |= tmp; I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status); + } + + WARN_ONCE(1, + "PORT_HOTPLUG_STAT did not clear (0x%08x)\n", + I915_READ(PORT_HOTPLUG_STAT)); return hotplug_status; } diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index f4a8598a2d39..fed26d6e4e27 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1782,15 +1782,24 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state) I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp); } -void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder) +void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state) { + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; i915_reg_t reg = TRANS_DDI_FUNC_CTL(cpu_transcoder); uint32_t val = I915_READ(reg); val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK | TRANS_DDI_DP_VC_PAYLOAD_ALLOC); val |= TRANS_DDI_PORT_NONE; I915_WRITE(reg, val); + + if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME && + intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) { + DRM_DEBUG_KMS("Quirk Increase DDI disabled time\n"); + /* Quirk time at 100ms for reliable operation */ + msleep(100); + } } int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder, diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 2cc6faa1daa8..dec0d60921bf 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -5809,7 +5809,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state, intel_ddi_set_vc_payload_alloc(intel_crtc->config, false); if (!transcoder_is_dsi(cpu_transcoder)) - intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder); + intel_ddi_disable_transcoder_func(old_crtc_state); if (INTEL_GEN(dev_priv) >= 9) skylake_scaler_disable(intel_crtc); @@ -14646,6 +14646,18 @@ static void quirk_increase_t12_delay(struct drm_device *dev) DRM_INFO("Applying T12 delay quirk\n"); } +/* + * GeminiLake NUC HDMI outputs require additional off time + * this allows the onboard retimer to correctly sync to signal + */ +static void quirk_increase_ddi_disabled_time(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + + dev_priv->quirks |= QUIRK_INCREASE_DDI_DISABLED_TIME; + DRM_INFO("Applying Increase DDI Disabled quirk\n"); +} + struct intel_quirk { int device; int subsystem_vendor; @@ -14732,6 +14744,13 @@ static struct intel_quirk intel_quirks[] = { /* Toshiba Satellite P50-C-18C */ { 0x191B, 0x1179, 0xF840, quirk_increase_t12_delay }, + + /* GeminiLake NUC */ + { 0x3185, 0x8086, 0x2072, quirk_increase_ddi_disabled_time }, + { 0x3184, 0x8086, 0x2072, quirk_increase_ddi_disabled_time }, + /* ASRock ITX*/ + { 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, + { 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, }; static void intel_init_quirks(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0361130500a6..b8eefbffc77d 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1388,8 +1388,7 @@ void hsw_fdi_link_train(struct intel_crtc *crtc, void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port); bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe); void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state); -void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder); +void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state); void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state); void intel_ddi_disable_pipe_clock(const struct intel_crtc_state *crtc_state); struct intel_encoder * diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index 56dd7a9a8e25..dd5312b02a8d 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -612,6 +612,9 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) return PTR_ERR(imx_ldb->regmap); } + /* disable LDB by resetting the control register to POR default */ + regmap_write(imx_ldb->regmap, IOMUXC_GPR2, 0); + imx_ldb->dev = dev; if (of_id) @@ -652,14 +655,14 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) if (ret || i < 0 || i > 1) return -EINVAL; + if (!of_device_is_available(child)) + continue; + if (dual && i > 0) { dev_warn(dev, "dual-channel mode, ignoring second output\n"); continue; } - if (!of_device_is_available(child)) - continue; - channel = &imx_ldb->channel[i]; channel->ldb = imx_ldb; channel->chno = i; diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c index 501d2d290e9c..70dce544984e 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c @@ -55,6 +55,9 @@ nv04_display_create(struct drm_device *dev) nouveau_display(dev)->init = nv04_display_init; nouveau_display(dev)->fini = nv04_display_fini; + /* Pre-nv50 doesn't support atomic, so don't expose the ioctls */ + dev->driver->driver_features &= ~DRIVER_ATOMIC; + nouveau_hw_save_vga_fonts(dev, 1); nv04_crtc_create(dev, 0); diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index b83465ae7c1b..9bae4db84cfb 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -1585,8 +1585,9 @@ nv50_pior_create(struct drm_connector *connector, struct dcb_output *dcbe) *****************************************************************************/ static void -nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 *interlock) +nv50_disp_atomic_commit_core(struct drm_atomic_state *state, u32 *interlock) { + struct nouveau_drm *drm = nouveau_drm(state->dev); struct nv50_disp *disp = nv50_disp(drm->dev); struct nv50_core *core = disp->core; struct nv50_mstm *mstm; @@ -1618,6 +1619,22 @@ nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 *interlock) } static void +nv50_disp_atomic_commit_wndw(struct drm_atomic_state *state, u32 *interlock) +{ + struct drm_plane_state *new_plane_state; + struct drm_plane *plane; + int i; + + for_each_new_plane_in_state(state, plane, new_plane_state, i) { + struct nv50_wndw *wndw = nv50_wndw(plane); + if (interlock[wndw->interlock.type] & wndw->interlock.data) { + if (wndw->func->update) + wndw->func->update(wndw, interlock); + } + } +} + +static void nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) { struct drm_device *dev = state->dev; @@ -1684,7 +1701,8 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) help->disable(encoder); interlock[NV50_DISP_INTERLOCK_CORE] |= 1; if (outp->flush_disable) { - nv50_disp_atomic_commit_core(drm, interlock); + nv50_disp_atomic_commit_wndw(state, interlock); + nv50_disp_atomic_commit_core(state, interlock); memset(interlock, 0x00, sizeof(interlock)); } } @@ -1693,15 +1711,8 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) /* Flush disable. */ if (interlock[NV50_DISP_INTERLOCK_CORE]) { if (atom->flush_disable) { - for_each_new_plane_in_state(state, plane, new_plane_state, i) { - struct nv50_wndw *wndw = nv50_wndw(plane); - if (interlock[wndw->interlock.type] & wndw->interlock.data) { - if (wndw->func->update) - wndw->func->update(wndw, interlock); - } - } - - nv50_disp_atomic_commit_core(drm, interlock); + nv50_disp_atomic_commit_wndw(state, interlock); + nv50_disp_atomic_commit_core(state, interlock); memset(interlock, 0x00, sizeof(interlock)); } } @@ -1762,18 +1773,14 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) } /* Flush update. */ - for_each_new_plane_in_state(state, plane, new_plane_state, i) { - struct nv50_wndw *wndw = nv50_wndw(plane); - if (interlock[wndw->interlock.type] & wndw->interlock.data) { - if (wndw->func->update) - wndw->func->update(wndw, interlock); - } - } + nv50_disp_atomic_commit_wndw(state, interlock); if (interlock[NV50_DISP_INTERLOCK_CORE]) { if (interlock[NV50_DISP_INTERLOCK_BASE] || + interlock[NV50_DISP_INTERLOCK_OVLY] || + interlock[NV50_DISP_INTERLOCK_WNDW] || !atom->state.legacy_cursor_update) - nv50_disp_atomic_commit_core(drm, interlock); + nv50_disp_atomic_commit_core(state, interlock); else disp->core->func->update(disp->core, interlock, false); } @@ -1871,7 +1878,7 @@ nv50_disp_atomic_commit(struct drm_device *dev, nv50_disp_atomic_commit_tail(state); drm_for_each_crtc(crtc, dev) { - if (crtc->state->enable) { + if (crtc->state->active) { if (!drm->have_disp_power_ref) { drm->have_disp_power_ref = true; return 0; @@ -2119,10 +2126,6 @@ nv50_display_destroy(struct drm_device *dev) kfree(disp); } -MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)"); -static int nouveau_atomic = 0; -module_param_named(atomic, nouveau_atomic, int, 0400); - int nv50_display_create(struct drm_device *dev) { @@ -2147,8 +2150,6 @@ nv50_display_create(struct drm_device *dev) disp->disp = &nouveau_display(dev)->disp; dev->mode_config.funcs = &nv50_disp_func; dev->driver->driver_features |= DRIVER_PREFER_XBGR_30BPP; - if (nouveau_atomic) - dev->driver->driver_features |= DRIVER_ATOMIC; /* small shared memory area we use for notifiers and semaphores */ ret = nouveau_bo_new(&drm->client, 4096, 0x1000, TTM_PL_FLAG_VRAM, diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index debbbf0fd4bd..408b955e5c39 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -267,6 +267,7 @@ nouveau_backlight_init(struct drm_device *dev) struct nouveau_drm *drm = nouveau_drm(dev); struct nvif_device *device = &drm->client.device; struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; INIT_LIST_HEAD(&drm->bl_connectors); @@ -275,7 +276,8 @@ nouveau_backlight_init(struct drm_device *dev) return 0; } - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && connector->connector_type != DRM_MODE_CONNECTOR_eDP) continue; @@ -292,7 +294,7 @@ nouveau_backlight_init(struct drm_device *dev) break; } } - + drm_connector_list_iter_end(&conn_iter); return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 7b557c354307..af68eae4c626 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -1208,14 +1208,19 @@ nouveau_connector_create(struct drm_device *dev, int index) struct nouveau_display *disp = nouveau_display(dev); struct nouveau_connector *nv_connector = NULL; struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; int type, ret = 0; bool dummy; - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { nv_connector = nouveau_connector(connector); - if (nv_connector->index == index) + if (nv_connector->index == index) { + drm_connector_list_iter_end(&conn_iter); return connector; + } } + drm_connector_list_iter_end(&conn_iter); nv_connector = kzalloc(sizeof(*nv_connector), GFP_KERNEL); if (!nv_connector) diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h index a4d1a059bd3d..dc7454e7f19a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.h +++ b/drivers/gpu/drm/nouveau/nouveau_connector.h @@ -33,6 +33,7 @@ #include <drm/drm_encoder.h> #include <drm/drm_dp_helper.h> #include "nouveau_crtc.h" +#include "nouveau_encoder.h" struct nvkm_i2c_port; @@ -60,19 +61,46 @@ static inline struct nouveau_connector *nouveau_connector( return container_of(con, struct nouveau_connector, base); } +static inline bool +nouveau_connector_is_mst(struct drm_connector *connector) +{ + const struct nouveau_encoder *nv_encoder; + const struct drm_encoder *encoder; + + if (connector->connector_type != DRM_MODE_CONNECTOR_DisplayPort) + return false; + + nv_encoder = find_encoder(connector, DCB_OUTPUT_ANY); + if (!nv_encoder) + return false; + + encoder = &nv_encoder->base.base; + return encoder->encoder_type == DRM_MODE_ENCODER_DPMST; +} + +#define nouveau_for_each_non_mst_connector_iter(connector, iter) \ + drm_for_each_connector_iter(connector, iter) \ + for_each_if(!nouveau_connector_is_mst(connector)) + static inline struct nouveau_connector * nouveau_crtc_connector_get(struct nouveau_crtc *nv_crtc) { struct drm_device *dev = nv_crtc->base.dev; struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; + struct nouveau_connector *nv_connector = NULL; struct drm_crtc *crtc = to_drm_crtc(nv_crtc); - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { - if (connector->encoder && connector->encoder->crtc == crtc) - return nouveau_connector(connector); + drm_connector_list_iter_begin(dev, &conn_iter); + nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { + if (connector->encoder && connector->encoder->crtc == crtc) { + nv_connector = nouveau_connector(connector); + break; + } } + drm_connector_list_iter_end(&conn_iter); - return NULL; + return nv_connector; } struct drm_connector * diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 774b429142bc..ec7861457b84 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -404,6 +404,7 @@ nouveau_display_init(struct drm_device *dev) struct nouveau_display *disp = nouveau_display(dev); struct nouveau_drm *drm = nouveau_drm(dev); struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; int ret; ret = disp->init(dev); @@ -411,10 +412,12 @@ nouveau_display_init(struct drm_device *dev) return ret; /* enable hotplug interrupts */ - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { struct nouveau_connector *conn = nouveau_connector(connector); nvif_notify_get(&conn->hpd); } + drm_connector_list_iter_end(&conn_iter); /* enable flip completion events */ nvif_notify_get(&drm->flip); @@ -427,6 +430,7 @@ nouveau_display_fini(struct drm_device *dev, bool suspend) struct nouveau_display *disp = nouveau_display(dev); struct nouveau_drm *drm = nouveau_drm(dev); struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; if (!suspend) { if (drm_drv_uses_atomic_modeset(dev)) @@ -439,10 +443,12 @@ nouveau_display_fini(struct drm_device *dev, bool suspend) nvif_notify_put(&drm->flip); /* disable hotplug interrupts */ - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { struct nouveau_connector *conn = nouveau_connector(connector); nvif_notify_put(&conn->hpd); } + drm_connector_list_iter_end(&conn_iter); drm_kms_helper_poll_disable(dev); disp->fini(dev); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 775443c9af94..f5d3158f0378 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -81,6 +81,10 @@ MODULE_PARM_DESC(modeset, "enable driver (default: auto, " int nouveau_modeset = -1; module_param_named(modeset, nouveau_modeset, int, 0400); +MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)"); +static int nouveau_atomic = 0; +module_param_named(atomic, nouveau_atomic, int, 0400); + MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1)"); static int nouveau_runtime_pm = -1; module_param_named(runpm, nouveau_runtime_pm, int, 0400); @@ -509,6 +513,9 @@ static int nouveau_drm_probe(struct pci_dev *pdev, pci_set_master(pdev); + if (nouveau_atomic) + driver_pci.driver_features |= DRIVER_ATOMIC; + ret = drm_get_pci_dev(pdev, pent, &driver_pci); if (ret) { nvkm_device_del(&device); @@ -874,22 +881,11 @@ nouveau_pmops_runtime_resume(struct device *dev) static int nouveau_pmops_runtime_idle(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct drm_device *drm_dev = pci_get_drvdata(pdev); - struct nouveau_drm *drm = nouveau_drm(drm_dev); - struct drm_crtc *crtc; - if (!nouveau_pmops_runtime()) { pm_runtime_forbid(dev); return -EBUSY; } - list_for_each_entry(crtc, &drm->dev->mode_config.crtc_list, head) { - if (crtc->enabled) { - DRM_DEBUG_DRIVER("failing to power off - crtc active\n"); - return -EBUSY; - } - } pm_runtime_mark_last_busy(dev); pm_runtime_autosuspend(dev); /* we don't want the main rpm_idle to call suspend - we want to autosuspend */ diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 300daee74209..e6ccafcb9c41 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -616,7 +616,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli, struct nouveau_bo *nvbo; uint32_t data; - if (unlikely(r->bo_index > req->nr_buffers)) { + if (unlikely(r->bo_index >= req->nr_buffers)) { NV_PRINTK(err, cli, "reloc bo index invalid\n"); ret = -EINVAL; break; @@ -626,7 +626,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli, if (b->presumed.valid) continue; - if (unlikely(r->reloc_bo_index > req->nr_buffers)) { + if (unlikely(r->reloc_bo_index >= req->nr_buffers)) { NV_PRINTK(err, cli, "reloc container bo index invalid\n"); ret = -EINVAL; break; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c index 73b5d46104bd..434d2fc5bb1c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c @@ -140,6 +140,9 @@ nvkm_fb_init(struct nvkm_subdev *subdev) if (fb->func->init) fb->func->init(fb); + if (fb->func->init_remapper) + fb->func->init_remapper(fb); + if (fb->func->init_page) { ret = fb->func->init_page(fb); if (WARN_ON(ret)) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c index dffe1f5e1071..8205ce436b3e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c @@ -37,6 +37,14 @@ gp100_fb_init_unkn(struct nvkm_fb *base) } void +gp100_fb_init_remapper(struct nvkm_fb *fb) +{ + struct nvkm_device *device = fb->subdev.device; + /* Disable address remapper. */ + nvkm_mask(device, 0x100c14, 0x00040000, 0x00000000); +} + +void gp100_fb_init(struct nvkm_fb *base) { struct gf100_fb *fb = gf100_fb(base); @@ -56,6 +64,7 @@ gp100_fb = { .dtor = gf100_fb_dtor, .oneinit = gf100_fb_oneinit, .init = gp100_fb_init, + .init_remapper = gp100_fb_init_remapper, .init_page = gm200_fb_init_page, .init_unkn = gp100_fb_init_unkn, .ram_new = gp100_ram_new, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c index b84b9861ef26..b4d74e815674 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c @@ -31,6 +31,7 @@ gp102_fb = { .dtor = gf100_fb_dtor, .oneinit = gf100_fb_oneinit, .init = gp100_fb_init, + .init_remapper = gp100_fb_init_remapper, .init_page = gm200_fb_init_page, .ram_new = gp100_ram_new, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h index 2857f31466bf..1e4ad61c19e1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h @@ -11,6 +11,7 @@ struct nvkm_fb_func { u32 (*tags)(struct nvkm_fb *); int (*oneinit)(struct nvkm_fb *); void (*init)(struct nvkm_fb *); + void (*init_remapper)(struct nvkm_fb *); int (*init_page)(struct nvkm_fb *); void (*init_unkn)(struct nvkm_fb *); void (*intr)(struct nvkm_fb *); @@ -69,5 +70,6 @@ int gf100_fb_init_page(struct nvkm_fb *); int gm200_fb_init_page(struct nvkm_fb *); +void gp100_fb_init_remapper(struct nvkm_fb *); void gp100_fb_init_unkn(struct nvkm_fb *); #endif diff --git a/drivers/gpu/drm/sun4i/Makefile b/drivers/gpu/drm/sun4i/Makefile index 2589f4acd5ae..9c81301d0eed 100644 --- a/drivers/gpu/drm/sun4i/Makefile +++ b/drivers/gpu/drm/sun4i/Makefile @@ -32,7 +32,10 @@ obj-$(CONFIG_DRM_SUN4I) += sun4i-tcon.o obj-$(CONFIG_DRM_SUN4I) += sun4i_tv.o obj-$(CONFIG_DRM_SUN4I) += sun6i_drc.o -obj-$(CONFIG_DRM_SUN4I_BACKEND) += sun4i-backend.o sun4i-frontend.o +obj-$(CONFIG_DRM_SUN4I_BACKEND) += sun4i-backend.o +ifdef CONFIG_DRM_SUN4I_BACKEND +obj-$(CONFIG_DRM_SUN4I) += sun4i-frontend.o +endif obj-$(CONFIG_DRM_SUN4I_HDMI) += sun4i-drm-hdmi.o obj-$(CONFIG_DRM_SUN6I_DSI) += sun6i-dsi.o obj-$(CONFIG_DRM_SUN8I_DW_HDMI) += sun8i-drm-hdmi.o diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 776c1513e582..a2bd5876c633 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -398,7 +398,7 @@ int tegra_drm_submit(struct tegra_drm_context *context, * unaligned offset is malformed and cause commands stream * corruption on the buffer address relocation. */ - if (offset & 3 || offset >= obj->gem.size) { + if (offset & 3 || offset > obj->gem.size) { err = -EINVAL; goto fail; } diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 1d34619eb3fe..a951ec75d01f 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -320,6 +320,9 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) vc4_state->x_scaling[0] = VC4_SCALING_TPZ; if (vc4_state->y_scaling[0] == VC4_SCALING_NONE) vc4_state->y_scaling[0] = VC4_SCALING_TPZ; + } else { + vc4_state->x_scaling[1] = VC4_SCALING_NONE; + vc4_state->y_scaling[1] = VC4_SCALING_NONE; } vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE && diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index f1d5f76e9c33..d88073e7d22d 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -218,6 +218,9 @@ static int host1x_probe(struct platform_device *pdev) return err; } + if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) + goto skip_iommu; + host->group = iommu_group_get(&pdev->dev); if (host->group) { struct iommu_domain_geometry *geometry; diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index e2f4a4d93d20..527a1cddb14f 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -569,7 +569,8 @@ void host1x_job_unpin(struct host1x_job *job) for (i = 0; i < job->num_unpins; i++) { struct host1x_job_unpin_data *unpin = &job->unpins[i]; - if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && host->domain) { + if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && + unpin->size && host->domain) { iommu_unmap(host->domain, job->addr_phys[i], unpin->size); free_iova(&host->iova, diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c index caa05b0702e1..5450a2db1219 100644 --- a/drivers/gpu/ipu-v3/ipu-csi.c +++ b/drivers/gpu/ipu-v3/ipu-csi.c @@ -339,7 +339,8 @@ static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg, break; case V4L2_MBUS_BT656: csicfg->ext_vsync = 0; - if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field)) + if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field) || + mbus_fmt->field == V4L2_FIELD_ALTERNATE) csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_INTERLACED; else csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE; diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c index 75d6ab177055..7379043711df 100644 --- a/drivers/i2c/busses/i2c-davinci.c +++ b/drivers/i2c/busses/i2c-davinci.c @@ -237,12 +237,16 @@ static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev) /* * It's not always possible to have 1 to 2 ratio when d=7, so fall back * to minimal possible clkh in this case. + * + * Note: + * CLKH is not allowed to be 0, in this case I2C clock is not generated + * at all */ - if (clk >= clkl + d) { + if (clk > clkl + d) { clkh = clk - clkl - d; clkl -= d; } else { - clkh = 0; + clkh = 1; clkl = clk - (d << 1); } diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 0207e194f84b..498c5e891649 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -368,6 +368,7 @@ static int i2c_imx_dma_xfer(struct imx_i2c_struct *i2c_imx, goto err_desc; } + reinit_completion(&dma->cmd_complete); txdesc->callback = i2c_imx_dma_callback; txdesc->callback_param = i2c_imx; if (dma_submit_error(dmaengine_submit(txdesc))) { @@ -622,7 +623,6 @@ static int i2c_imx_dma_write(struct imx_i2c_struct *i2c_imx, * The first byte must be transmitted by the CPU. */ imx_i2c_write_reg(i2c_8bit_addr_from_msg(msgs), i2c_imx, IMX_I2C_I2DR); - reinit_completion(&i2c_imx->dma->cmd_complete); time_left = wait_for_completion_timeout( &i2c_imx->dma->cmd_complete, msecs_to_jiffies(DMA_TIMEOUT)); @@ -681,7 +681,6 @@ static int i2c_imx_dma_read(struct imx_i2c_struct *i2c_imx, if (result) return result; - reinit_completion(&i2c_imx->dma->cmd_complete); time_left = wait_for_completion_timeout( &i2c_imx->dma->cmd_complete, msecs_to_jiffies(DMA_TIMEOUT)); @@ -1010,7 +1009,7 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx, i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl, "gpio"); rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN); - rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH); + rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN); if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER || PTR_ERR(rinfo->scl_gpiod) == -EPROBE_DEFER) { diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index 5e310efd9446..3c1c817f6968 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -32,6 +32,7 @@ #include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/reset.h> #include <linux/slab.h> /* register offsets */ @@ -111,8 +112,9 @@ #define ID_ARBLOST (1 << 3) #define ID_NACK (1 << 4) /* persistent flags */ +#define ID_P_NO_RXDMA (1 << 30) /* HW forbids RXDMA sometimes */ #define ID_P_PM_BLOCKED (1 << 31) -#define ID_P_MASK ID_P_PM_BLOCKED +#define ID_P_MASK (ID_P_PM_BLOCKED | ID_P_NO_RXDMA) enum rcar_i2c_type { I2C_RCAR_GEN1, @@ -141,6 +143,8 @@ struct rcar_i2c_priv { struct dma_chan *dma_rx; struct scatterlist sg; enum dma_data_direction dma_direction; + + struct reset_control *rstc; }; #define rcar_i2c_priv_to_dev(p) ((p)->adap.dev.parent) @@ -370,6 +374,11 @@ static void rcar_i2c_dma_unmap(struct rcar_i2c_priv *priv) dma_unmap_single(chan->device->dev, sg_dma_address(&priv->sg), sg_dma_len(&priv->sg), priv->dma_direction); + /* Gen3 can only do one RXDMA per transfer and we just completed it */ + if (priv->devtype == I2C_RCAR_GEN3 && + priv->dma_direction == DMA_FROM_DEVICE) + priv->flags |= ID_P_NO_RXDMA; + priv->dma_direction = DMA_NONE; } @@ -407,8 +416,9 @@ static void rcar_i2c_dma(struct rcar_i2c_priv *priv) unsigned char *buf; int len; - /* Do not use DMA if it's not available or for messages < 8 bytes */ - if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE)) + /* Do various checks to see if DMA is feasible at all */ + if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE) || + (read && priv->flags & ID_P_NO_RXDMA)) return; if (read) { @@ -739,6 +749,25 @@ static void rcar_i2c_release_dma(struct rcar_i2c_priv *priv) } } +/* I2C is a special case, we need to poll the status of a reset */ +static int rcar_i2c_do_reset(struct rcar_i2c_priv *priv) +{ + int i, ret; + + ret = reset_control_reset(priv->rstc); + if (ret) + return ret; + + for (i = 0; i < LOOP_TIMEOUT; i++) { + ret = reset_control_status(priv->rstc); + if (ret == 0) + return 0; + udelay(1); + } + + return -ETIMEDOUT; +} + static int rcar_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) @@ -750,6 +779,16 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap, pm_runtime_get_sync(dev); + /* Gen3 needs a reset before allowing RXDMA once */ + if (priv->devtype == I2C_RCAR_GEN3) { + priv->flags |= ID_P_NO_RXDMA; + if (!IS_ERR(priv->rstc)) { + ret = rcar_i2c_do_reset(priv); + if (ret == 0) + priv->flags &= ~ID_P_NO_RXDMA; + } + } + rcar_i2c_init(priv); ret = rcar_i2c_bus_barrier(priv); @@ -920,6 +959,15 @@ static int rcar_i2c_probe(struct platform_device *pdev) if (ret < 0) goto out_pm_put; + if (priv->devtype == I2C_RCAR_GEN3) { + priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (!IS_ERR(priv->rstc)) { + ret = reset_control_status(priv->rstc); + if (ret < 0) + priv->rstc = ERR_PTR(-ENOTSUPP); + } + } + /* Stay always active when multi-master to keep arbitration working */ if (of_property_read_bool(dev->of_node, "multi-master")) priv->flags |= ID_P_PM_BLOCKED; diff --git a/drivers/i2c/busses/i2c-xlp9xx.c b/drivers/i2c/busses/i2c-xlp9xx.c index 1f41a4f89c08..8a873975cf12 100644 --- a/drivers/i2c/busses/i2c-xlp9xx.c +++ b/drivers/i2c/busses/i2c-xlp9xx.c @@ -191,28 +191,43 @@ static void xlp9xx_i2c_drain_rx_fifo(struct xlp9xx_i2c_dev *priv) if (priv->len_recv) { /* read length byte */ rlen = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO); + + /* + * We expect at least 2 interrupts for I2C_M_RECV_LEN + * transactions. The length is updated during the first + * interrupt, and the buffer contents are only copied + * during subsequent interrupts. If in case the interrupts + * get merged we would complete the transaction without + * copying out the bytes from RX fifo. To avoid this now we + * drain the fifo as and when data is available. + * We drained the rlen byte already, decrement total length + * by one. + */ + + len--; if (rlen > I2C_SMBUS_BLOCK_MAX || rlen == 0) { rlen = 0; /*abort transfer */ priv->msg_buf_remaining = 0; priv->msg_len = 0; - } else { - *buf++ = rlen; - if (priv->client_pec) - ++rlen; /* account for error check byte */ - /* update remaining bytes and message length */ - priv->msg_buf_remaining = rlen; - priv->msg_len = rlen + 1; + xlp9xx_i2c_update_rlen(priv); + return; } + + *buf++ = rlen; + if (priv->client_pec) + ++rlen; /* account for error check byte */ + /* update remaining bytes and message length */ + priv->msg_buf_remaining = rlen; + priv->msg_len = rlen + 1; xlp9xx_i2c_update_rlen(priv); priv->len_recv = false; - } else { - len = min(priv->msg_buf_remaining, len); - for (i = 0; i < len; i++, buf++) - *buf = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO); - - priv->msg_buf_remaining -= len; } + len = min(priv->msg_buf_remaining, len); + for (i = 0; i < len; i++, buf++) + *buf = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO); + + priv->msg_buf_remaining -= len; priv->msg_buf = buf; if (priv->msg_buf_remaining) diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 301285c54603..15c95aaa484c 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -624,7 +624,7 @@ static int i2c_check_addr_busy(struct i2c_adapter *adapter, int addr) static void i2c_adapter_lock_bus(struct i2c_adapter *adapter, unsigned int flags) { - rt_mutex_lock(&adapter->bus_lock); + rt_mutex_lock_nested(&adapter->bus_lock, i2c_adapter_depth(adapter)); } /** diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c index 300ab4b672e4..29646aa6132e 100644 --- a/drivers/i2c/i2c-mux.c +++ b/drivers/i2c/i2c-mux.c @@ -144,7 +144,7 @@ static void i2c_mux_lock_bus(struct i2c_adapter *adapter, unsigned int flags) struct i2c_mux_priv *priv = adapter->algo_data; struct i2c_adapter *parent = priv->muxc->parent; - rt_mutex_lock(&parent->mux_lock); + rt_mutex_lock_nested(&parent->mux_lock, i2c_adapter_depth(adapter)); if (!(flags & I2C_LOCK_ROOT_ADAPTER)) return; i2c_lock_bus(parent, flags); @@ -181,7 +181,7 @@ static void i2c_parent_lock_bus(struct i2c_adapter *adapter, struct i2c_mux_priv *priv = adapter->algo_data; struct i2c_adapter *parent = priv->muxc->parent; - rt_mutex_lock(&parent->mux_lock); + rt_mutex_lock_nested(&parent->mux_lock, i2c_adapter_depth(adapter)); i2c_lock_bus(parent, flags); } diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index a6e904973ba8..475910ffbcb6 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -121,7 +121,7 @@ static int uverbs_try_lock_object(struct ib_uobject *uobj, bool exclusive) * this lock. */ if (!exclusive) - return __atomic_add_unless(&uobj->usecnt, 1, -1) == -1 ? + return atomic_fetch_add_unless(&uobj->usecnt, 1, -1) == -1 ? -EBUSY : 0; /* lock is either WRITE or DESTROY - should be exclusive */ diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index cc06e8404e9b..583d3a10b940 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1984,15 +1984,64 @@ static int modify_qp(struct ib_uverbs_file *file, goto release_qp; } - if ((cmd->base.attr_mask & IB_QP_AV) && - !rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) { - ret = -EINVAL; - goto release_qp; + if ((cmd->base.attr_mask & IB_QP_AV)) { + if (!rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) { + ret = -EINVAL; + goto release_qp; + } + + if (cmd->base.attr_mask & IB_QP_STATE && + cmd->base.qp_state == IB_QPS_RTR) { + /* We are in INIT->RTR TRANSITION (if we are not, + * this transition will be rejected in subsequent checks). + * In the INIT->RTR transition, we cannot have IB_QP_PORT set, + * but the IB_QP_STATE flag is required. + * + * Since kernel 3.14 (commit dbf727de7440), the uverbs driver, + * when IB_QP_AV is set, has required inclusion of a valid + * port number in the primary AV. (AVs are created and handled + * differently for infiniband and ethernet (RoCE) ports). + * + * Check the port number included in the primary AV against + * the port number in the qp struct, which was set (and saved) + * in the RST->INIT transition. + */ + if (cmd->base.dest.port_num != qp->real_qp->port) { + ret = -EINVAL; + goto release_qp; + } + } else { + /* We are in SQD->SQD. (If we are not, this transition will + * be rejected later in the verbs layer checks). + * Check for both IB_QP_PORT and IB_QP_AV, these can be set + * together in the SQD->SQD transition. + * + * If only IP_QP_AV was set, add in IB_QP_PORT as well (the + * verbs layer driver does not track primary port changes + * resulting from path migration. Thus, in SQD, if the primary + * AV is modified, the primary port should also be modified). + * + * Note that in this transition, the IB_QP_STATE flag + * is not allowed. + */ + if (((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT)) + == (IB_QP_AV | IB_QP_PORT)) && + cmd->base.port_num != cmd->base.dest.port_num) { + ret = -EINVAL; + goto release_qp; + } + if ((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT)) + == IB_QP_AV) { + cmd->base.attr_mask |= IB_QP_PORT; + cmd->base.port_num = cmd->base.dest.port_num; + } + } } if ((cmd->base.attr_mask & IB_QP_ALT_PATH) && (!rdma_is_port_valid(qp->device, cmd->base.alt_port_num) || - !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num))) { + !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num) || + cmd->base.alt_port_num != cmd->base.alt_dest.port_num)) { ret = -EINVAL; goto release_qp; } diff --git a/drivers/input/keyboard/hilkbd.c b/drivers/input/keyboard/hilkbd.c index a4e404aaf64b..5c7afdec192c 100644 --- a/drivers/input/keyboard/hilkbd.c +++ b/drivers/input/keyboard/hilkbd.c @@ -57,8 +57,8 @@ MODULE_LICENSE("GPL v2"); #define HIL_DATA 0x1 #define HIL_CMD 0x3 #define HIL_IRQ 2 - #define hil_readb(p) readb(p) - #define hil_writeb(v,p) writeb((v),(p)) + #define hil_readb(p) readb((const volatile void __iomem *)(p)) + #define hil_writeb(v, p) writeb((v), (volatile void __iomem *)(p)) #else #error "HIL is not supported on this platform" diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 1f9cd7d8b7ad..f5ae24865355 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1346,6 +1346,8 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0611", 0 }, { "ELAN0612", 0 }, { "ELAN0618", 0 }, + { "ELAN061D", 0 }, + { "ELAN0622", 0 }, { "ELAN1000", 0 }, { } }; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index b353d494ad40..136f6e7bf797 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -527,6 +527,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"), }, }, + { + /* Lenovo LaVie Z */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"), + }, + }, { } }; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index b344a883f116..115ff26e9ced 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -484,14 +484,37 @@ static int dmar_forcedac; static int intel_iommu_strict; static int intel_iommu_superpage = 1; static int intel_iommu_ecs = 1; +static int intel_iommu_pasid28; static int iommu_identity_mapping; #define IDENTMAP_ALL 1 #define IDENTMAP_GFX 2 #define IDENTMAP_AZALIA 4 -#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap)) -#define pasid_enabled(iommu) (ecs_enabled(iommu) && ecap_pasid(iommu->ecap)) +/* Broadwell and Skylake have broken ECS support — normal so-called "second + * level" translation of DMA requests-without-PASID doesn't actually happen + * unless you also set the NESTE bit in an extended context-entry. Which of + * course means that SVM doesn't work because it's trying to do nested + * translation of the physical addresses it finds in the process page tables, + * through the IOVA->phys mapping found in the "second level" page tables. + * + * The VT-d specification was retroactively changed to change the definition + * of the capability bits and pretend that Broadwell/Skylake never happened... + * but unfortunately the wrong bit was changed. It's ECS which is broken, but + * for some reason it was the PASID capability bit which was redefined (from + * bit 28 on BDW/SKL to bit 40 in future). + * + * So our test for ECS needs to eschew those implementations which set the old + * PASID capabiity bit 28, since those are the ones on which ECS is broken. + * Unless we are working around the 'pasid28' limitations, that is, by putting + * the device into passthrough mode for normal DMA and thus masking the bug. + */ +#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \ + (intel_iommu_pasid28 || !ecap_broken_pasid(iommu->ecap))) +/* PASID support is thus enabled if ECS is enabled and *either* of the old + * or new capability bits are set. */ +#define pasid_enabled(iommu) (ecs_enabled(iommu) && \ + (ecap_pasid(iommu->ecap) || ecap_broken_pasid(iommu->ecap))) int intel_iommu_gfx_mapped; EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped); @@ -554,6 +577,11 @@ static int __init intel_iommu_setup(char *str) printk(KERN_INFO "Intel-IOMMU: disable extended context table support\n"); intel_iommu_ecs = 0; + } else if (!strncmp(str, "pasid28", 7)) { + printk(KERN_INFO + "Intel-IOMMU: enable pre-production PASID support\n"); + intel_iommu_pasid28 = 1; + iommu_identity_mapping |= IDENTMAP_GFX; } else if (!strncmp(str, "tboot_noforce", 13)) { printk(KERN_INFO "Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n"); diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index e9233db16e03..d564d21245c5 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -8,7 +8,7 @@ config ARM_GIC bool select IRQ_DOMAIN select IRQ_DOMAIN_HIERARCHY - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_EFFECTIVE_AFF_MASK config ARM_GIC_PM @@ -34,7 +34,7 @@ config GIC_NON_BANKED config ARM_GIC_V3 bool select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select IRQ_DOMAIN_HIERARCHY select PARTITION_PERCPU select GENERIC_IRQ_EFFECTIVE_AFF_MASK @@ -66,7 +66,7 @@ config ARM_NVIC config ARM_VIC bool select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER config ARM_VIC_NR int @@ -93,14 +93,14 @@ config ATMEL_AIC_IRQ bool select GENERIC_IRQ_CHIP select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select SPARSE_IRQ config ATMEL_AIC5_IRQ bool select GENERIC_IRQ_CHIP select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select SPARSE_IRQ config I8259 @@ -137,7 +137,7 @@ config DW_APB_ICTL config FARADAY_FTINTC010 bool select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select SPARSE_IRQ config HISILICON_IRQ_MBIGEN @@ -162,7 +162,7 @@ config CLPS711X_IRQCHIP bool depends on ARCH_CLPS711X select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select SPARSE_IRQ default y @@ -181,7 +181,7 @@ config OMAP_IRQCHIP config ORION_IRQCHIP bool select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER config PIC32_EVIC bool diff --git a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c index 4eca5c763766..606efa64adff 100644 --- a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c @@ -45,6 +45,9 @@ static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain, */ info->scratchpad[0].ul = mc_bus_dev->icid; msi_info = msi_get_domain_info(msi_domain->parent); + + /* Allocate at least 32 MSIs, and always as a power of 2 */ + nvec = max_t(int, 32, roundup_pow_of_two(nvec)); return msi_info->ops->msi_prepare(msi_domain->parent, dev, nvec, info); } diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c index 25a98de5cfb2..8d6d009d1d58 100644 --- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c @@ -66,7 +66,7 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev, { struct pci_dev *pdev, *alias_dev; struct msi_domain_info *msi_info; - int alias_count = 0; + int alias_count = 0, minnvec = 1; if (!dev_is_pci(dev)) return -EINVAL; @@ -86,8 +86,18 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev, /* ITS specific DeviceID, as the core ITS ignores dev. */ info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev); - return msi_info->ops->msi_prepare(domain->parent, - dev, max(nvec, alias_count), info); + /* + * Always allocate a power of 2, and special case device 0 for + * broken systems where the DevID is not wired (and all devices + * appear as DevID 0). For that reason, we generously allocate a + * minimum of 32 MSIs for DevID 0. If you want more because all + * your devices are aliasing to DevID 0, consider fixing your HW. + */ + nvec = max(nvec, alias_count); + if (!info->scratchpad[0].ul) + minnvec = 32; + nvec = max_t(int, minnvec, roundup_pow_of_two(nvec)); + return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info); } static struct msi_domain_ops its_pci_msi_ops = { diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c index 8881a053c173..7b8e87b493fe 100644 --- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c @@ -73,6 +73,8 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev, /* ITS specific DeviceID, as the core ITS ignores dev. */ info->scratchpad[0].ul = dev_id; + /* Allocate at least 32 MSIs, and always as a power of 2 */ + nvec = max_t(int, 32, roundup_pow_of_two(nvec)); return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info); } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index d7842d312d3e..316a57530f6d 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -23,6 +23,8 @@ #include <linux/dma-iommu.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> +#include <linux/list.h> +#include <linux/list_sort.h> #include <linux/log2.h> #include <linux/mm.h> #include <linux/msi.h> @@ -160,7 +162,7 @@ static struct { } vpe_proxy; static LIST_HEAD(its_nodes); -static DEFINE_SPINLOCK(its_lock); +static DEFINE_RAW_SPINLOCK(its_lock); static struct rdists *gic_rdists; static struct irq_domain *its_parent; @@ -1421,112 +1423,176 @@ static struct irq_chip its_irq_chip = { .irq_set_vcpu_affinity = its_irq_set_vcpu_affinity, }; + /* * How we allocate LPIs: * - * The GIC has id_bits bits for interrupt identifiers. From there, we - * must subtract 8192 which are reserved for SGIs/PPIs/SPIs. Then, as - * we allocate LPIs by chunks of 32, we can shift the whole thing by 5 - * bits to the right. + * lpi_range_list contains ranges of LPIs that are to available to + * allocate from. To allocate LPIs, just pick the first range that + * fits the required allocation, and reduce it by the required + * amount. Once empty, remove the range from the list. + * + * To free a range of LPIs, add a free range to the list, sort it and + * merge the result if the new range happens to be adjacent to an + * already free block. * - * This gives us (((1UL << id_bits) - 8192) >> 5) possible allocations. + * The consequence of the above is that allocation is cost is low, but + * freeing is expensive. We assumes that freeing rarely occurs. */ -#define IRQS_PER_CHUNK_SHIFT 5 -#define IRQS_PER_CHUNK (1UL << IRQS_PER_CHUNK_SHIFT) -#define ITS_MAX_LPI_NRBITS 16 /* 64K LPIs */ -static unsigned long *lpi_bitmap; -static u32 lpi_chunks; -static DEFINE_SPINLOCK(lpi_lock); +static DEFINE_MUTEX(lpi_range_lock); +static LIST_HEAD(lpi_range_list); + +struct lpi_range { + struct list_head entry; + u32 base_id; + u32 span; +}; -static int its_lpi_to_chunk(int lpi) +static struct lpi_range *mk_lpi_range(u32 base, u32 span) { - return (lpi - 8192) >> IRQS_PER_CHUNK_SHIFT; + struct lpi_range *range; + + range = kzalloc(sizeof(*range), GFP_KERNEL); + if (range) { + INIT_LIST_HEAD(&range->entry); + range->base_id = base; + range->span = span; + } + + return range; } -static int its_chunk_to_lpi(int chunk) +static int lpi_range_cmp(void *priv, struct list_head *a, struct list_head *b) { - return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192; + struct lpi_range *ra, *rb; + + ra = container_of(a, struct lpi_range, entry); + rb = container_of(b, struct lpi_range, entry); + + return rb->base_id - ra->base_id; } -static int __init its_lpi_init(u32 id_bits) +static void merge_lpi_ranges(void) { - lpi_chunks = its_lpi_to_chunk(1UL << id_bits); + struct lpi_range *range, *tmp; - lpi_bitmap = kcalloc(BITS_TO_LONGS(lpi_chunks), sizeof(long), - GFP_KERNEL); - if (!lpi_bitmap) { - lpi_chunks = 0; - return -ENOMEM; + list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) { + if (!list_is_last(&range->entry, &lpi_range_list) && + (tmp->base_id == (range->base_id + range->span))) { + tmp->base_id = range->base_id; + tmp->span += range->span; + list_del(&range->entry); + kfree(range); + } } +} - pr_info("ITS: Allocated %d chunks for LPIs\n", (int)lpi_chunks); - return 0; +static int alloc_lpi_range(u32 nr_lpis, u32 *base) +{ + struct lpi_range *range, *tmp; + int err = -ENOSPC; + + mutex_lock(&lpi_range_lock); + + list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) { + if (range->span >= nr_lpis) { + *base = range->base_id; + range->base_id += nr_lpis; + range->span -= nr_lpis; + + if (range->span == 0) { + list_del(&range->entry); + kfree(range); + } + + err = 0; + break; + } + } + + mutex_unlock(&lpi_range_lock); + + pr_debug("ITS: alloc %u:%u\n", *base, nr_lpis); + return err; } -static unsigned long *its_lpi_alloc_chunks(int nr_irqs, int *base, int *nr_ids) +static int free_lpi_range(u32 base, u32 nr_lpis) { - unsigned long *bitmap = NULL; - int chunk_id; - int nr_chunks; - int i; + struct lpi_range *new; + int err = 0; + + mutex_lock(&lpi_range_lock); + + new = mk_lpi_range(base, nr_lpis); + if (!new) { + err = -ENOMEM; + goto out; + } + + list_add(&new->entry, &lpi_range_list); + list_sort(NULL, &lpi_range_list, lpi_range_cmp); + merge_lpi_ranges(); +out: + mutex_unlock(&lpi_range_lock); + return err; +} + +static int __init its_lpi_init(u32 id_bits) +{ + u32 lpis = (1UL << id_bits) - 8192; + u32 numlpis; + int err; + + numlpis = 1UL << GICD_TYPER_NUM_LPIS(gic_rdists->gicd_typer); + + if (numlpis > 2 && !WARN_ON(numlpis > lpis)) { + lpis = numlpis; + pr_info("ITS: Using hypervisor restricted LPI range [%u]\n", + lpis); + } - nr_chunks = DIV_ROUND_UP(nr_irqs, IRQS_PER_CHUNK); + /* + * Initializing the allocator is just the same as freeing the + * full range of LPIs. + */ + err = free_lpi_range(8192, lpis); + pr_debug("ITS: Allocator initialized for %u LPIs\n", lpis); + return err; +} - spin_lock(&lpi_lock); +static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids) +{ + unsigned long *bitmap = NULL; + int err = 0; do { - chunk_id = bitmap_find_next_zero_area(lpi_bitmap, lpi_chunks, - 0, nr_chunks, 0); - if (chunk_id < lpi_chunks) + err = alloc_lpi_range(nr_irqs, base); + if (!err) break; - nr_chunks--; - } while (nr_chunks > 0); + nr_irqs /= 2; + } while (nr_irqs > 0); - if (!nr_chunks) + if (err) goto out; - bitmap = kcalloc(BITS_TO_LONGS(nr_chunks * IRQS_PER_CHUNK), - sizeof(long), - GFP_ATOMIC); + bitmap = kcalloc(BITS_TO_LONGS(nr_irqs), sizeof (long), GFP_ATOMIC); if (!bitmap) goto out; - for (i = 0; i < nr_chunks; i++) - set_bit(chunk_id + i, lpi_bitmap); - - *base = its_chunk_to_lpi(chunk_id); - *nr_ids = nr_chunks * IRQS_PER_CHUNK; + *nr_ids = nr_irqs; out: - spin_unlock(&lpi_lock); - if (!bitmap) *base = *nr_ids = 0; return bitmap; } -static void its_lpi_free_chunks(unsigned long *bitmap, int base, int nr_ids) +static void its_lpi_free(unsigned long *bitmap, u32 base, u32 nr_ids) { - int lpi; - - spin_lock(&lpi_lock); - - for (lpi = base; lpi < (base + nr_ids); lpi += IRQS_PER_CHUNK) { - int chunk = its_lpi_to_chunk(lpi); - - BUG_ON(chunk > lpi_chunks); - if (test_bit(chunk, lpi_bitmap)) { - clear_bit(chunk, lpi_bitmap); - } else { - pr_err("Bad LPI chunk %d\n", chunk); - } - } - - spin_unlock(&lpi_lock); - + WARN_ON(free_lpi_range(base, nr_ids)); kfree(bitmap); } @@ -1559,7 +1625,7 @@ static int __init its_alloc_lpi_tables(void) { phys_addr_t paddr; - lpi_id_bits = min_t(u32, gic_rdists->id_bits, ITS_MAX_LPI_NRBITS); + lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer); gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT); if (!gic_rdists->prop_page) { pr_err("Failed to allocate PROPBASE\n"); @@ -1997,12 +2063,12 @@ static void its_cpu_init_collections(void) { struct its_node *its; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_for_each_entry(its, &its_nodes, entry) its_cpu_init_collection(its); - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); } static struct its_device *its_find_device(struct its_node *its, u32 dev_id) @@ -2134,17 +2200,20 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, if (!its_alloc_device_table(its, dev_id)) return NULL; + if (WARN_ON(!is_power_of_2(nvecs))) + nvecs = roundup_pow_of_two(nvecs); + dev = kzalloc(sizeof(*dev), GFP_KERNEL); /* - * We allocate at least one chunk worth of LPIs bet device, - * and thus that many ITEs. The device may require less though. + * Even if the device wants a single LPI, the ITT must be + * sized as a power of two (and you need at least one bit...). */ - nr_ites = max(IRQS_PER_CHUNK, roundup_pow_of_two(nvecs)); + nr_ites = max(2, nvecs); sz = nr_ites * its->ite_size; sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1; itt = kzalloc(sz, GFP_KERNEL); if (alloc_lpis) { - lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis); + lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis); if (lpi_map) col_map = kcalloc(nr_lpis, sizeof(*col_map), GFP_KERNEL); @@ -2379,9 +2448,9 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, /* If all interrupts have been freed, start mopping the floor */ if (bitmap_empty(its_dev->event_map.lpi_map, its_dev->event_map.nr_lpis)) { - its_lpi_free_chunks(its_dev->event_map.lpi_map, - its_dev->event_map.lpi_base, - its_dev->event_map.nr_lpis); + its_lpi_free(its_dev->event_map.lpi_map, + its_dev->event_map.lpi_base, + its_dev->event_map.nr_lpis); kfree(its_dev->event_map.col_map); /* Unmap device/itt */ @@ -2780,7 +2849,7 @@ static void its_vpe_irq_domain_free(struct irq_domain *domain, } if (bitmap_empty(vm->db_bitmap, vm->nr_db_lpis)) { - its_lpi_free_chunks(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis); + its_lpi_free(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis); its_free_prop_table(vm->vprop_page); } } @@ -2795,18 +2864,18 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq BUG_ON(!vm); - bitmap = its_lpi_alloc_chunks(nr_irqs, &base, &nr_ids); + bitmap = its_lpi_alloc(roundup_pow_of_two(nr_irqs), &base, &nr_ids); if (!bitmap) return -ENOMEM; if (nr_ids < nr_irqs) { - its_lpi_free_chunks(bitmap, base, nr_ids); + its_lpi_free(bitmap, base, nr_ids); return -ENOMEM; } vprop_page = its_allocate_prop_table(GFP_KERNEL); if (!vprop_page) { - its_lpi_free_chunks(bitmap, base, nr_ids); + its_lpi_free(bitmap, base, nr_ids); return -ENOMEM; } @@ -2833,7 +2902,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq if (i > 0) its_vpe_irq_domain_free(domain, virq, i - 1); - its_lpi_free_chunks(bitmap, base, nr_ids); + its_lpi_free(bitmap, base, nr_ids); its_free_prop_table(vprop_page); } @@ -3070,7 +3139,7 @@ static int its_save_disable(void) struct its_node *its; int err = 0; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_for_each_entry(its, &its_nodes, entry) { void __iomem *base; @@ -3102,7 +3171,7 @@ err: writel_relaxed(its->ctlr_save, base + GITS_CTLR); } } - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); return err; } @@ -3112,7 +3181,7 @@ static void its_restore_enable(void) struct its_node *its; int ret; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_for_each_entry(its, &its_nodes, entry) { void __iomem *base; int i; @@ -3164,7 +3233,7 @@ static void its_restore_enable(void) GITS_TYPER_HCC(gic_read_typer(base + GITS_TYPER))) its_cpu_init_collection(its); } - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); } static struct syscore_ops its_syscore_ops = { @@ -3398,9 +3467,9 @@ static int __init its_probe_one(struct resource *res, if (err) goto out_free_tables; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_add(&its->entry, &its_nodes); - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); return 0; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 76ea56d779a1..e214181b77b7 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -877,7 +877,7 @@ static struct irq_chip gic_eoimode1_chip = { .flags = IRQCHIP_SET_TYPE_MASKED, }; -#define GIC_ID_NR (1U << gic_data.rdists.id_bits) +#define GIC_ID_NR (1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer)) static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) @@ -1091,7 +1091,7 @@ static int __init gic_init_bases(void __iomem *dist_base, * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI) */ typer = readl_relaxed(gic_data.dist_base + GICD_TYPER); - gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer); + gic_data.rdists.gicd_typer = typer; gic_irqs = GICD_TYPER_IRQS(typer); if (gic_irqs > 1020) gic_irqs = 1020; diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c index fc5953dea509..2ff08986b536 100644 --- a/drivers/irqchip/irq-ingenic.c +++ b/drivers/irqchip/irq-ingenic.c @@ -165,6 +165,7 @@ static int __init intc_1chip_of_init(struct device_node *node, return ingenic_intc_of_init(node, 1); } IRQCHIP_DECLARE(jz4740_intc, "ingenic,jz4740-intc", intc_1chip_of_init); +IRQCHIP_DECLARE(jz4725b_intc, "ingenic,jz4725b-intc", intc_1chip_of_init); static int __init intc_2chip_of_init(struct device_node *node, struct device_node *parent) diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index 3a7e8905a97e..3df527fcf4e1 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -159,6 +159,7 @@ static const struct stm32_exti_bank *stm32mp1_exti_banks[] = { }; static const struct stm32_desc_irq stm32mp1_desc_irq[] = { + { .exti = 0, .irq_parent = 6 }, { .exti = 1, .irq_parent = 7 }, { .exti = 2, .irq_parent = 8 }, { .exti = 3, .irq_parent = 9 }, diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 07ea6a48aac6..87107c995cb5 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -136,6 +136,7 @@ struct dm_writecache { struct dm_target *ti; struct dm_dev *dev; struct dm_dev *ssd_dev; + sector_t start_sector; void *memory_map; uint64_t memory_map_size; size_t metadata_sectors; @@ -293,6 +294,10 @@ static int persistent_memory_claim(struct dm_writecache *wc) } dax_read_unlock(id); + + wc->memory_map += (size_t)wc->start_sector << SECTOR_SHIFT; + wc->memory_map_size -= (size_t)wc->start_sector << SECTOR_SHIFT; + return 0; err3: kvfree(pages); @@ -311,7 +316,7 @@ static int persistent_memory_claim(struct dm_writecache *wc) static void persistent_memory_release(struct dm_writecache *wc) { if (wc->memory_vmapped) - vunmap(wc->memory_map); + vunmap(wc->memory_map - ((size_t)wc->start_sector << SECTOR_SHIFT)); } static struct page *persistent_memory_page(void *addr) @@ -359,7 +364,7 @@ static void *memory_data(struct dm_writecache *wc, struct wc_entry *e) static sector_t cache_sector(struct dm_writecache *wc, struct wc_entry *e) { - return wc->metadata_sectors + + return wc->start_sector + wc->metadata_sectors + ((sector_t)e->index << (wc->block_size_bits - SECTOR_SHIFT)); } @@ -471,6 +476,7 @@ static void ssd_commit_flushed(struct dm_writecache *wc) if (unlikely(region.sector + region.count > wc->metadata_sectors)) region.count = wc->metadata_sectors - region.sector; + region.sector += wc->start_sector; atomic_inc(&endio.count); req.bi_op = REQ_OP_WRITE; req.bi_op_flags = REQ_SYNC; @@ -1946,14 +1952,6 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) } wc->memory_map_size = i_size_read(wc->ssd_dev->bdev->bd_inode); - if (WC_MODE_PMEM(wc)) { - r = persistent_memory_claim(wc); - if (r) { - ti->error = "Unable to map persistent memory for cache"; - goto bad; - } - } - /* * Parse the cache block size */ @@ -1982,7 +1980,16 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) while (opt_params) { string = dm_shift_arg(&as), opt_params--; - if (!strcasecmp(string, "high_watermark") && opt_params >= 1) { + if (!strcasecmp(string, "start_sector") && opt_params >= 1) { + unsigned long long start_sector; + string = dm_shift_arg(&as), opt_params--; + if (sscanf(string, "%llu%c", &start_sector, &dummy) != 1) + goto invalid_optional; + wc->start_sector = start_sector; + if (wc->start_sector != start_sector || + wc->start_sector >= wc->memory_map_size >> SECTOR_SHIFT) + goto invalid_optional; + } else if (!strcasecmp(string, "high_watermark") && opt_params >= 1) { string = dm_shift_arg(&as), opt_params--; if (sscanf(string, "%d%c", &high_wm_percent, &dummy) != 1) goto invalid_optional; @@ -2039,12 +2046,20 @@ invalid_optional: goto bad; } - if (!WC_MODE_PMEM(wc)) { + if (WC_MODE_PMEM(wc)) { + r = persistent_memory_claim(wc); + if (r) { + ti->error = "Unable to map persistent memory for cache"; + goto bad; + } + } else { struct dm_io_region region; struct dm_io_request req; size_t n_blocks, n_metadata_blocks; uint64_t n_bitmap_bits; + wc->memory_map_size -= (uint64_t)wc->start_sector << SECTOR_SHIFT; + bio_list_init(&wc->flush_list); wc->flush_thread = kthread_create(writecache_flush_thread, wc, "dm_writecache_flush"); if (IS_ERR(wc->flush_thread)) { @@ -2097,7 +2112,7 @@ invalid_optional: } region.bdev = wc->ssd_dev->bdev; - region.sector = 0; + region.sector = wc->start_sector; region.count = wc->metadata_sectors; req.bi_op = REQ_OP_READ; req.bi_op_flags = REQ_SYNC; @@ -2265,7 +2280,7 @@ static void writecache_status(struct dm_target *ti, status_type_t type, static struct target_type writecache_target = { .name = "writecache", - .version = {1, 0, 0}, + .version = {1, 1, 0}, .module = THIS_MODULE, .ctr = writecache_ctr, .dtr = writecache_dtr, diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c index edb35a5c57ea..a99fc0ced7a7 100644 --- a/drivers/media/platform/vsp1/vsp1_drm.c +++ b/drivers/media/platform/vsp1/vsp1_drm.c @@ -728,9 +728,6 @@ EXPORT_SYMBOL_GPL(vsp1_du_setup_lif); */ void vsp1_du_atomic_begin(struct device *dev, unsigned int pipe_index) { - struct vsp1_device *vsp1 = dev_get_drvdata(dev); - - mutex_lock(&vsp1->drm->lock); } EXPORT_SYMBOL_GPL(vsp1_du_atomic_begin); @@ -846,6 +843,7 @@ void vsp1_du_atomic_flush(struct device *dev, unsigned int pipe_index, drm_pipe->crc = cfg->crc; + mutex_lock(&vsp1->drm->lock); vsp1_du_pipeline_setup_inputs(vsp1, pipe); vsp1_du_pipeline_configure(pipe); mutex_unlock(&vsp1->drm->lock); diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fcfab6635f9c..81b150e5dfdb 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -174,6 +174,7 @@ static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog) rcu_assign_pointer(raw->progs, new_array); bpf_prog_array_free(old_array); + bpf_prog_put(prog); unlock: mutex_unlock(&ir_raw_handler_lock); return ret; diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c index 2e0066b1a31c..e7948908e78c 100644 --- a/drivers/media/rc/rc-ir-raw.c +++ b/drivers/media/rc/rc-ir-raw.c @@ -30,13 +30,13 @@ static int ir_raw_event_thread(void *data) while (kfifo_out(&raw->kfifo, &ev, 1)) { if (is_timing_event(ev)) { if (ev.duration == 0) - dev_err(&dev->dev, "nonsensical timing event of duration 0"); + dev_warn_once(&dev->dev, "nonsensical timing event of duration 0"); if (is_timing_event(raw->prev_ev) && !is_transition(&ev, &raw->prev_ev)) - dev_err(&dev->dev, "two consecutive events of type %s", - TO_STR(ev.pulse)); + dev_warn_once(&dev->dev, "two consecutive events of type %s", + TO_STR(ev.pulse)); if (raw->prev_ev.reset && ev.pulse == 0) - dev_err(&dev->dev, "timing event after reset should be pulse"); + dev_warn_once(&dev->dev, "timing event after reset should be pulse"); } list_for_each_entry(handler, &ir_raw_handler_list, list) if (dev->enabled_protocols & diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 2e222d9ee01f..ca68e1d2b2f9 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -679,6 +679,14 @@ static void ir_timer_repeat(struct timer_list *t) spin_unlock_irqrestore(&dev->keylock, flags); } +static unsigned int repeat_period(int protocol) +{ + if (protocol >= ARRAY_SIZE(protocols)) + return 100; + + return protocols[protocol].repeat_period; +} + /** * rc_repeat() - signals that a key is still pressed * @dev: the struct rc_dev descriptor of the device @@ -691,7 +699,7 @@ void rc_repeat(struct rc_dev *dev) { unsigned long flags; unsigned int timeout = nsecs_to_jiffies(dev->timeout) + - msecs_to_jiffies(protocols[dev->last_protocol].repeat_period); + msecs_to_jiffies(repeat_period(dev->last_protocol)); struct lirc_scancode sc = { .scancode = dev->last_scancode, .rc_proto = dev->last_protocol, .keycode = dev->keypressed ? dev->last_keycode : KEY_RESERVED, @@ -803,7 +811,7 @@ void rc_keydown(struct rc_dev *dev, enum rc_proto protocol, u32 scancode, if (dev->keypressed) { dev->keyup_jiffies = jiffies + nsecs_to_jiffies(dev->timeout) + - msecs_to_jiffies(protocols[protocol].repeat_period); + msecs_to_jiffies(repeat_period(protocol)); mod_timer(&dev->timer_keyup, dev->keyup_jiffies); } spin_unlock_irqrestore(&dev->keylock, flags); diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c index 753b1a698fc4..6b16946f9b05 100644 --- a/drivers/misc/cxl/api.c +++ b/drivers/misc/cxl/api.c @@ -103,15 +103,15 @@ static struct file *cxl_getfile(const char *name, d_instantiate(path.dentry, inode); file = alloc_file(&path, OPEN_FMODE(flags), fops); - if (IS_ERR(file)) - goto err_dput; + if (IS_ERR(file)) { + path_put(&path); + goto err_fs; + } file->f_flags = flags & (O_ACCMODE | O_NONBLOCK); file->private_data = priv; return file; -err_dput: - path_put(&path); err_inode: iput(inode); err_fs: diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c index 75f781c11e89..de4e6e5bf304 100644 --- a/drivers/mmc/host/mxcmmc.c +++ b/drivers/mmc/host/mxcmmc.c @@ -293,9 +293,10 @@ static void mxcmci_swap_buffers(struct mmc_data *data) int i; for_each_sg(data->sg, sg, data->sg_len, i) { - void *buf = kmap_atomic(sg_page(sg) + sg->offset; + void *buf = kmap_atomic(sg_page(sg) + sg->offset); buffer_swap32(buf, sg->length); kunmap_atomic(buf); + } } #else static inline void mxcmci_swap_buffers(struct mmc_data *data) {} diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 63e3844c5bec..217b790d22ed 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1717,6 +1717,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_upper_unlink; } + bond->nest_level = dev_get_nest_level(bond_dev) + 1; + /* If the mode uses primary, then the following is handled by * bond_change_active_slave(). */ @@ -1764,7 +1766,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); - bond->nest_level = dev_get_nest_level(bond_dev); netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n", slave_dev->name, @@ -3415,6 +3416,13 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } +static int bond_get_nest_level(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + + return bond->nest_level; +} + static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3423,7 +3431,7 @@ static void bond_get_stats(struct net_device *bond_dev, struct list_head *iter; struct slave *slave; - spin_lock(&bond->stats_lock); + spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev)); memcpy(stats, &bond->bond_stats, sizeof(*stats)); rcu_read_lock(); @@ -4227,6 +4235,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_neigh_setup = bond_neigh_setup, .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, + .ndo_get_lock_subclass = bond_get_nest_level, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = bond_netpoll_setup, .ndo_netpoll_cleanup = bond_netpoll_cleanup, @@ -4725,6 +4734,7 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; + bond->nest_level = SINGLE_DEPTH_NESTING; netdev_lockdep_set_classes(bond_dev); list_add_tail(&bond->bond_list, &bn->dev_list); diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 98663c50ded0..4d5d01cb8141 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -743,15 +743,20 @@ const struct bond_option *bond_opt_get(unsigned int option) static int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) { - if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) { - netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n", - newval->string); - /* disable arp monitoring */ - bond->params.arp_interval = 0; - /* set miimon to default value */ - bond->params.miimon = BOND_DEFAULT_MIIMON; - netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n", - bond->params.miimon); + if (!bond_mode_uses_arp(newval->value)) { + if (bond->params.arp_interval) { + netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n", + newval->string); + /* disable arp monitoring */ + bond->params.arp_interval = 0; + } + + if (!bond->params.miimon) { + /* set miimon to default value */ + bond->params.miimon = BOND_DEFAULT_MIIMON; + netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n", + bond->params.miimon); + } } if (newval->value == BOND_MODE_ALB) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index b397a33f3d32..9b449400376b 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -634,10 +634,12 @@ static int m_can_clk_start(struct m_can_priv *priv) int err; err = pm_runtime_get_sync(priv->device); - if (err) + if (err < 0) { pm_runtime_put_noidle(priv->device); + return err; + } - return err; + return 0; } static void m_can_clk_stop(struct m_can_priv *priv) @@ -1109,7 +1111,8 @@ static void m_can_chip_config(struct net_device *dev) } else { /* Version 3.1.x or 3.2.x */ - cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE); + cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE | + CCCR_NISO); /* Only 3.2.x has NISO Bit implemented */ if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) @@ -1642,8 +1645,6 @@ static int m_can_plat_probe(struct platform_device *pdev) priv->can.clock.freq = clk_get_rate(cclk); priv->mram_base = mram_addr; - m_can_of_parse_mram(priv, mram_config_vals); - platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev); @@ -1666,6 +1667,8 @@ static int m_can_plat_probe(struct platform_device *pdev) goto clk_disable; } + m_can_of_parse_mram(priv, mram_config_vals); + devm_can_led_init(dev); of_can_transceiver(dev); @@ -1687,8 +1690,6 @@ failed_ret: return ret; } -/* TODO: runtime PM with power down or sleep mode */ - static __maybe_unused int m_can_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); @@ -1715,8 +1716,6 @@ static __maybe_unused int m_can_resume(struct device *dev) pinctrl_pm_select_default_state(dev); - m_can_init_ram(priv); - priv->can.state = CAN_STATE_ERROR_ACTIVE; if (netif_running(ndev)) { @@ -1726,6 +1725,7 @@ static __maybe_unused int m_can_resume(struct device *dev) if (ret) return ret; + m_can_init_ram(priv); m_can_start(ndev); netif_device_attach(ndev); netif_start_queue(ndev); diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c index c7427bdd3a4b..2949a381a94d 100644 --- a/drivers/net/can/mscan/mpc5xxx_can.c +++ b/drivers/net/can/mscan/mpc5xxx_can.c @@ -86,6 +86,11 @@ static u32 mpc52xx_can_get_clock(struct platform_device *ofdev, return 0; } cdm = of_iomap(np_cdm, 0); + if (!cdm) { + of_node_put(np_cdm); + dev_err(&ofdev->dev, "can't map clock node!\n"); + return 0; + } if (in_8(&cdm->ipb_clk_sel) & 0x1) freq *= 2; diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index b9e28578bc7b..455a3797a200 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -58,6 +58,10 @@ MODULE_LICENSE("GPL v2"); #define PCIEFD_REG_SYS_VER1 0x0040 /* version reg #1 */ #define PCIEFD_REG_SYS_VER2 0x0044 /* version reg #2 */ +#define PCIEFD_FW_VERSION(x, y, z) (((u32)(x) << 24) | \ + ((u32)(y) << 16) | \ + ((u32)(z) << 8)) + /* System Control Registers Bits */ #define PCIEFD_SYS_CTL_TS_RST 0x00000001 /* timestamp clock */ #define PCIEFD_SYS_CTL_CLK_EN 0x00000002 /* system clock */ @@ -782,6 +786,21 @@ static int peak_pciefd_probe(struct pci_dev *pdev, "%ux CAN-FD PCAN-PCIe FPGA v%u.%u.%u:\n", can_count, hw_ver_major, hw_ver_minor, hw_ver_sub); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + /* FW < v3.3.0 DMA logic doesn't handle correctly the mix of 32-bit and + * 64-bit logical addresses: this workaround forces usage of 32-bit + * DMA addresses only when such a fw is detected. + */ + if (PCIEFD_FW_VERSION(hw_ver_major, hw_ver_minor, hw_ver_sub) < + PCIEFD_FW_VERSION(3, 3, 0)) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + dev_warn(&pdev->dev, + "warning: can't set DMA mask %llxh (err %d)\n", + DMA_BIT_MASK(32), err); + } +#endif + /* stop system clock */ pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_CLK_EN, PCIEFD_REG_SYS_CTL_CLR); diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 12ff0020ecd6..b7dfd4109d24 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -1072,6 +1072,7 @@ static void ems_usb_disconnect(struct usb_interface *intf) usb_free_urb(dev->intr_urb); kfree(dev->intr_in_buffer); + kfree(dev->tx_msg_buffer); } } diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 89aec07c225f..5a24039733ef 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -2,6 +2,7 @@ * * Copyright (C) 2012 - 2014 Xilinx, Inc. * Copyright (C) 2009 PetaLogix. All rights reserved. + * Copyright (C) 2017 Sandvik Mining and Construction Oy * * Description: * This driver is developed for Axi CAN IP and for Zynq CANPS Controller. @@ -25,8 +26,10 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/of.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/skbuff.h> +#include <linux/spinlock.h> #include <linux/string.h> #include <linux/types.h> #include <linux/can/dev.h> @@ -101,7 +104,7 @@ enum xcan_reg { #define XCAN_INTR_ALL (XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\ XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \ XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \ - XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK) + XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK) /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */ #define XCAN_BTR_SJW_SHIFT 7 /* Synchronous jump width */ @@ -118,6 +121,7 @@ enum xcan_reg { /** * struct xcan_priv - This definition define CAN driver instance * @can: CAN private data structure. + * @tx_lock: Lock for synchronizing TX interrupt handling * @tx_head: Tx CAN packets ready to send on the queue * @tx_tail: Tx CAN packets successfully sended on the queue * @tx_max: Maximum number packets the driver can send @@ -132,6 +136,7 @@ enum xcan_reg { */ struct xcan_priv { struct can_priv can; + spinlock_t tx_lock; unsigned int tx_head; unsigned int tx_tail; unsigned int tx_max; @@ -159,6 +164,11 @@ static const struct can_bittiming_const xcan_bittiming_const = { .brp_inc = 1, }; +#define XCAN_CAP_WATERMARK 0x0001 +struct xcan_devtype_data { + unsigned int caps; +}; + /** * xcan_write_reg_le - Write a value to the device register little endian * @priv: Driver private data structure @@ -238,6 +248,10 @@ static int set_reset_mode(struct net_device *ndev) usleep_range(500, 10000); } + /* reset clears FIFOs */ + priv->tx_head = 0; + priv->tx_tail = 0; + return 0; } @@ -392,6 +406,7 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct net_device_stats *stats = &ndev->stats; struct can_frame *cf = (struct can_frame *)skb->data; u32 id, dlc, data[2] = {0, 0}; + unsigned long flags; if (can_dropped_invalid_skb(ndev, skb)) return NETDEV_TX_OK; @@ -439,6 +454,9 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) data[1] = be32_to_cpup((__be32 *)(cf->data + 4)); can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max); + + spin_lock_irqsave(&priv->tx_lock, flags); + priv->tx_head++; /* Write the Frame to Xilinx CAN TX FIFO */ @@ -454,10 +472,16 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) stats->tx_bytes += cf->can_dlc; } + /* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */ + if (priv->tx_max > 1) + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXFEMP_MASK); + /* Check if the TX buffer is full */ if ((priv->tx_head - priv->tx_tail) == priv->tx_max) netif_stop_queue(ndev); + spin_unlock_irqrestore(&priv->tx_lock, flags); + return NETDEV_TX_OK; } @@ -530,6 +554,123 @@ static int xcan_rx(struct net_device *ndev) } /** + * xcan_current_error_state - Get current error state from HW + * @ndev: Pointer to net_device structure + * + * Checks the current CAN error state from the HW. Note that this + * only checks for ERROR_PASSIVE and ERROR_WARNING. + * + * Return: + * ERROR_PASSIVE or ERROR_WARNING if either is active, ERROR_ACTIVE + * otherwise. + */ +static enum can_state xcan_current_error_state(struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + u32 status = priv->read_reg(priv, XCAN_SR_OFFSET); + + if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) + return CAN_STATE_ERROR_PASSIVE; + else if (status & XCAN_SR_ERRWRN_MASK) + return CAN_STATE_ERROR_WARNING; + else + return CAN_STATE_ERROR_ACTIVE; +} + +/** + * xcan_set_error_state - Set new CAN error state + * @ndev: Pointer to net_device structure + * @new_state: The new CAN state to be set + * @cf: Error frame to be populated or NULL + * + * Set new CAN error state for the device, updating statistics and + * populating the error frame if given. + */ +static void xcan_set_error_state(struct net_device *ndev, + enum can_state new_state, + struct can_frame *cf) +{ + struct xcan_priv *priv = netdev_priv(ndev); + u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET); + u32 txerr = ecr & XCAN_ECR_TEC_MASK; + u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT; + + priv->can.state = new_state; + + if (cf) { + cf->can_id |= CAN_ERR_CRTL; + cf->data[6] = txerr; + cf->data[7] = rxerr; + } + + switch (new_state) { + case CAN_STATE_ERROR_PASSIVE: + priv->can.can_stats.error_passive++; + if (cf) + cf->data[1] = (rxerr > 127) ? + CAN_ERR_CRTL_RX_PASSIVE : + CAN_ERR_CRTL_TX_PASSIVE; + break; + case CAN_STATE_ERROR_WARNING: + priv->can.can_stats.error_warning++; + if (cf) + cf->data[1] |= (txerr > rxerr) ? + CAN_ERR_CRTL_TX_WARNING : + CAN_ERR_CRTL_RX_WARNING; + break; + case CAN_STATE_ERROR_ACTIVE: + if (cf) + cf->data[1] |= CAN_ERR_CRTL_ACTIVE; + break; + default: + /* non-ERROR states are handled elsewhere */ + WARN_ON(1); + break; + } +} + +/** + * xcan_update_error_state_after_rxtx - Update CAN error state after RX/TX + * @ndev: Pointer to net_device structure + * + * If the device is in a ERROR-WARNING or ERROR-PASSIVE state, check if + * the performed RX/TX has caused it to drop to a lesser state and set + * the interface state accordingly. + */ +static void xcan_update_error_state_after_rxtx(struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + enum can_state old_state = priv->can.state; + enum can_state new_state; + + /* changing error state due to successful frame RX/TX can only + * occur from these states + */ + if (old_state != CAN_STATE_ERROR_WARNING && + old_state != CAN_STATE_ERROR_PASSIVE) + return; + + new_state = xcan_current_error_state(ndev); + + if (new_state != old_state) { + struct sk_buff *skb; + struct can_frame *cf; + + skb = alloc_can_err_skb(ndev, &cf); + + xcan_set_error_state(ndev, new_state, skb ? cf : NULL); + + if (skb) { + struct net_device_stats *stats = &ndev->stats; + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); + } + } +} + +/** * xcan_err_interrupt - error frame Isr * @ndev: net_device pointer * @isr: interrupt status register value @@ -544,16 +685,12 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) struct net_device_stats *stats = &ndev->stats; struct can_frame *cf; struct sk_buff *skb; - u32 err_status, status, txerr = 0, rxerr = 0; + u32 err_status; skb = alloc_can_err_skb(ndev, &cf); err_status = priv->read_reg(priv, XCAN_ESR_OFFSET); priv->write_reg(priv, XCAN_ESR_OFFSET, err_status); - txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK; - rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) & - XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT); - status = priv->read_reg(priv, XCAN_SR_OFFSET); if (isr & XCAN_IXR_BSOFF_MASK) { priv->can.state = CAN_STATE_BUS_OFF; @@ -563,28 +700,10 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) can_bus_off(ndev); if (skb) cf->can_id |= CAN_ERR_BUSOFF; - } else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - priv->can.can_stats.error_passive++; - if (skb) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] = (rxerr > 127) ? - CAN_ERR_CRTL_RX_PASSIVE : - CAN_ERR_CRTL_TX_PASSIVE; - cf->data[6] = txerr; - cf->data[7] = rxerr; - } - } else if (status & XCAN_SR_ERRWRN_MASK) { - priv->can.state = CAN_STATE_ERROR_WARNING; - priv->can.can_stats.error_warning++; - if (skb) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] |= (txerr > rxerr) ? - CAN_ERR_CRTL_TX_WARNING : - CAN_ERR_CRTL_RX_WARNING; - cf->data[6] = txerr; - cf->data[7] = rxerr; - } + } else { + enum can_state new_state = xcan_current_error_state(ndev); + + xcan_set_error_state(ndev, new_state, skb ? cf : NULL); } /* Check for Arbitration lost interrupt */ @@ -600,7 +719,6 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) if (isr & XCAN_IXR_RXOFLW_MASK) { stats->rx_over_errors++; stats->rx_errors++; - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); if (skb) { cf->can_id |= CAN_ERR_CRTL; cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW; @@ -709,26 +827,20 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota) isr = priv->read_reg(priv, XCAN_ISR_OFFSET); while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) { - if (isr & XCAN_IXR_RXOK_MASK) { - priv->write_reg(priv, XCAN_ICR_OFFSET, - XCAN_IXR_RXOK_MASK); - work_done += xcan_rx(ndev); - } else { - priv->write_reg(priv, XCAN_ICR_OFFSET, - XCAN_IXR_RXNEMP_MASK); - break; - } + work_done += xcan_rx(ndev); priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK); isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } - if (work_done) + if (work_done) { can_led_event(ndev, CAN_LED_EVENT_RX); + xcan_update_error_state_after_rxtx(ndev); + } if (work_done < quota) { napi_complete_done(napi, work_done); ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK); + ier |= XCAN_IXR_RXNEMP_MASK; priv->write_reg(priv, XCAN_IER_OFFSET, ier); } return work_done; @@ -743,18 +855,71 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr) { struct xcan_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; + unsigned int frames_in_fifo; + int frames_sent = 1; /* TXOK => at least 1 frame was sent */ + unsigned long flags; + int retries = 0; + + /* Synchronize with xmit as we need to know the exact number + * of frames in the FIFO to stay in sync due to the TXFEMP + * handling. + * This also prevents a race between netif_wake_queue() and + * netif_stop_queue(). + */ + spin_lock_irqsave(&priv->tx_lock, flags); + + frames_in_fifo = priv->tx_head - priv->tx_tail; + + if (WARN_ON_ONCE(frames_in_fifo == 0)) { + /* clear TXOK anyway to avoid getting back here */ + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + spin_unlock_irqrestore(&priv->tx_lock, flags); + return; + } + + /* Check if 2 frames were sent (TXOK only means that at least 1 + * frame was sent). + */ + if (frames_in_fifo > 1) { + WARN_ON(frames_in_fifo > priv->tx_max); + + /* Synchronize TXOK and isr so that after the loop: + * (1) isr variable is up-to-date at least up to TXOK clear + * time. This avoids us clearing a TXOK of a second frame + * but not noticing that the FIFO is now empty and thus + * marking only a single frame as sent. + * (2) No TXOK is left. Having one could mean leaving a + * stray TXOK as we might process the associated frame + * via TXFEMP handling as we read TXFEMP *after* TXOK + * clear to satisfy (1). + */ + while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) { + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + isr = priv->read_reg(priv, XCAN_ISR_OFFSET); + } - while ((priv->tx_head - priv->tx_tail > 0) && - (isr & XCAN_IXR_TXOK_MASK)) { + if (isr & XCAN_IXR_TXFEMP_MASK) { + /* nothing in FIFO anymore */ + frames_sent = frames_in_fifo; + } + } else { + /* single frame in fifo, just clear TXOK */ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + } + + while (frames_sent--) { can_get_echo_skb(ndev, priv->tx_tail % priv->tx_max); priv->tx_tail++; stats->tx_packets++; - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } - can_led_event(ndev, CAN_LED_EVENT_TX); + netif_wake_queue(ndev); + + spin_unlock_irqrestore(&priv->tx_lock, flags); + + can_led_event(ndev, CAN_LED_EVENT_TX); + xcan_update_error_state_after_rxtx(ndev); } /** @@ -773,6 +938,7 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) struct net_device *ndev = (struct net_device *)dev_id; struct xcan_priv *priv = netdev_priv(ndev); u32 isr, ier; + u32 isr_errors; /* Get the interrupt status from Xilinx CAN */ isr = priv->read_reg(priv, XCAN_ISR_OFFSET); @@ -791,18 +957,17 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) xcan_tx_interrupt(ndev, isr); /* Check for the type of error interrupt and Processing it */ - if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | - XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) { - priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK | - XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK | - XCAN_IXR_ARBLST_MASK)); + isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | + XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK); + if (isr_errors) { + priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors); xcan_err_interrupt(ndev, isr); } /* Check for the type of receive interrupt and Processing it */ - if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) { + if (isr & XCAN_IXR_RXNEMP_MASK) { ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK); + ier &= ~XCAN_IXR_RXNEMP_MASK; priv->write_reg(priv, XCAN_IER_OFFSET, ier); napi_schedule(&priv->napi); } @@ -819,13 +984,9 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) static void xcan_chip_stop(struct net_device *ndev) { struct xcan_priv *priv = netdev_priv(ndev); - u32 ier; /* Disable interrupts and leave the can in configuration mode */ - ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier &= ~XCAN_INTR_ALL; - priv->write_reg(priv, XCAN_IER_OFFSET, ier); - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); + set_reset_mode(ndev); priv->can.state = CAN_STATE_STOPPED; } @@ -958,10 +1119,15 @@ static const struct net_device_ops xcan_netdev_ops = { */ static int __maybe_unused xcan_suspend(struct device *dev) { - if (!device_may_wakeup(dev)) - return pm_runtime_force_suspend(dev); + struct net_device *ndev = dev_get_drvdata(dev); - return 0; + if (netif_running(ndev)) { + netif_stop_queue(ndev); + netif_device_detach(ndev); + xcan_chip_stop(ndev); + } + + return pm_runtime_force_suspend(dev); } /** @@ -973,11 +1139,27 @@ static int __maybe_unused xcan_suspend(struct device *dev) */ static int __maybe_unused xcan_resume(struct device *dev) { - if (!device_may_wakeup(dev)) - return pm_runtime_force_resume(dev); + struct net_device *ndev = dev_get_drvdata(dev); + int ret; - return 0; + ret = pm_runtime_force_resume(dev); + if (ret) { + dev_err(dev, "pm_runtime_force_resume failed on resume\n"); + return ret; + } + + if (netif_running(ndev)) { + ret = xcan_chip_start(ndev); + if (ret) { + dev_err(dev, "xcan_chip_start failed on resume\n"); + return ret; + } + + netif_device_attach(ndev); + netif_start_queue(ndev); + } + return 0; } /** @@ -992,14 +1174,6 @@ static int __maybe_unused xcan_runtime_suspend(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct xcan_priv *priv = netdev_priv(ndev); - if (netif_running(ndev)) { - netif_stop_queue(ndev); - netif_device_detach(ndev); - } - - priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK); - priv->can.state = CAN_STATE_SLEEPING; - clk_disable_unprepare(priv->bus_clk); clk_disable_unprepare(priv->can_clk); @@ -1018,7 +1192,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct xcan_priv *priv = netdev_priv(ndev); int ret; - u32 isr, status; ret = clk_prepare_enable(priv->bus_clk); if (ret) { @@ -1032,27 +1205,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev) return ret; } - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); - status = priv->read_reg(priv, XCAN_SR_OFFSET); - - if (netif_running(ndev)) { - if (isr & XCAN_IXR_BSOFF_MASK) { - priv->can.state = CAN_STATE_BUS_OFF; - priv->write_reg(priv, XCAN_SRR_OFFSET, - XCAN_SRR_RESET_MASK); - } else if ((status & XCAN_SR_ESTAT_MASK) == - XCAN_SR_ESTAT_MASK) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - } else if (status & XCAN_SR_ERRWRN_MASK) { - priv->can.state = CAN_STATE_ERROR_WARNING; - } else { - priv->can.state = CAN_STATE_ERROR_ACTIVE; - } - netif_device_attach(ndev); - netif_start_queue(ndev); - } - return 0; } @@ -1061,6 +1213,18 @@ static const struct dev_pm_ops xcan_dev_pm_ops = { SET_RUNTIME_PM_OPS(xcan_runtime_suspend, xcan_runtime_resume, NULL) }; +static const struct xcan_devtype_data xcan_zynq_data = { + .caps = XCAN_CAP_WATERMARK, +}; + +/* Match table for OF platform binding */ +static const struct of_device_id xcan_of_match[] = { + { .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data }, + { .compatible = "xlnx,axi-can-1.00.a", }, + { /* end of list */ }, +}; +MODULE_DEVICE_TABLE(of, xcan_of_match); + /** * xcan_probe - Platform registration call * @pdev: Handle to the platform device structure @@ -1075,8 +1239,10 @@ static int xcan_probe(struct platform_device *pdev) struct resource *res; /* IO mem resources */ struct net_device *ndev; struct xcan_priv *priv; + const struct of_device_id *of_id; + int caps = 0; void __iomem *addr; - int ret, rx_max, tx_max; + int ret, rx_max, tx_max, tx_fifo_depth; /* Get the virtual base address for the device */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1086,7 +1252,8 @@ static int xcan_probe(struct platform_device *pdev) goto err; } - ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max); + ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", + &tx_fifo_depth); if (ret < 0) goto err; @@ -1094,6 +1261,30 @@ static int xcan_probe(struct platform_device *pdev) if (ret < 0) goto err; + of_id = of_match_device(xcan_of_match, &pdev->dev); + if (of_id) { + const struct xcan_devtype_data *devtype_data = of_id->data; + + if (devtype_data) + caps = devtype_data->caps; + } + + /* There is no way to directly figure out how many frames have been + * sent when the TXOK interrupt is processed. If watermark programming + * is supported, we can have 2 frames in the FIFO and use TXFEMP + * to determine if 1 or 2 frames have been sent. + * Theoretically we should be able to use TXFWMEMP to determine up + * to 3 frames, but it seems that after putting a second frame in the + * FIFO, with watermark at 2 frames, it can happen that TXFWMEMP (less + * than 2 frames in FIFO) is set anyway with no TXOK (a frame was + * sent), which is not a sensible state - possibly TXFWMEMP is not + * completely synchronized with the rest of the bits? + */ + if (caps & XCAN_CAP_WATERMARK) + tx_max = min(tx_fifo_depth, 2); + else + tx_max = 1; + /* Create a CAN device instance */ ndev = alloc_candev(sizeof(struct xcan_priv), tx_max); if (!ndev) @@ -1108,6 +1299,7 @@ static int xcan_probe(struct platform_device *pdev) CAN_CTRLMODE_BERR_REPORTING; priv->reg_base = addr; priv->tx_max = tx_max; + spin_lock_init(&priv->tx_lock); /* Get IRQ for the device */ ndev->irq = platform_get_irq(pdev, 0); @@ -1172,9 +1364,9 @@ static int xcan_probe(struct platform_device *pdev) pm_runtime_put(&pdev->dev); - netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n", + netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n", priv->reg_base, ndev->irq, priv->can.clock.freq, - priv->tx_max); + tx_fifo_depth, priv->tx_max); return 0; @@ -1208,14 +1400,6 @@ static int xcan_remove(struct platform_device *pdev) return 0; } -/* Match table for OF platform binding */ -static const struct of_device_id xcan_of_match[] = { - { .compatible = "xlnx,zynq-can-1.0", }, - { .compatible = "xlnx,axi-can-1.00.a", }, - { /* end of list */ }, -}; -MODULE_DEVICE_TABLE(of, xcan_of_match); - static struct platform_driver xcan_driver = { .probe = xcan_probe, .remove = xcan_remove, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 437cd6eb4faa..bb28c701381a 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -343,6 +343,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = { .xlate = irq_domain_xlate_twocell, }; +/* To be called with reg_lock held */ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip) { int irq, virq; @@ -362,9 +363,15 @@ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip) static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) { - mv88e6xxx_g1_irq_free_common(chip); - + /* + * free_irq must be called without reg_lock taken because the irq + * handler takes this lock, too. + */ free_irq(chip->irq, chip); + + mutex_lock(&chip->reg_lock); + mv88e6xxx_g1_irq_free_common(chip); + mutex_unlock(&chip->reg_lock); } static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip) @@ -469,10 +476,12 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip) static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip) { - mv88e6xxx_g1_irq_free_common(chip); - kthread_cancel_delayed_work_sync(&chip->irq_poll_work); kthread_destroy_worker(chip->kworker); + + mutex_lock(&chip->reg_lock); + mv88e6xxx_g1_irq_free_common(chip); + mutex_unlock(&chip->reg_lock); } int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask) @@ -2608,7 +2617,6 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .rmu_disable = mv88e6085_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .serdes_power = mv88e6341_serdes_power, }; static const struct mv88e6xxx_ops mv88e6095_ops = { @@ -2774,6 +2782,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .serdes_power = mv88e6341_serdes_power, .gpio_ops = &mv88e6352_gpio_ops, }; @@ -2951,7 +2960,6 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .serdes_power = mv88e6341_serdes_power, }; static const struct mv88e6xxx_ops mv88e6176_ops = { @@ -3327,6 +3335,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .serdes_power = mv88e6341_serdes_power, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, }; @@ -4506,12 +4515,10 @@ out_g2_irq: if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); out_g1_irq: - mutex_lock(&chip->reg_lock); if (chip->irq > 0) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); - mutex_unlock(&chip->reg_lock); out: if (pdata) dev_put(pdata->netdev); @@ -4539,12 +4546,10 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); - mutex_lock(&chip->reg_lock); if (chip->irq > 0) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); - mutex_unlock(&chip->reg_lock); } static const struct of_device_id mv88e6xxx_of_match[] = { diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig index 5b7658bcf020..5c3ef9fc8207 100644 --- a/drivers/net/ethernet/3com/Kconfig +++ b/drivers/net/ethernet/3com/Kconfig @@ -32,7 +32,7 @@ config EL3 config 3C515 tristate "3c515 ISA \"Fast EtherLink\"" - depends on ISA && ISA_DMA_API + depends on ISA && ISA_DMA_API && !PPC32 ---help--- If you have a 3Com ISA EtherLink XL "Corkscrew" 3c515 Fast Ethernet network card, say Y here. diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c index b6d735bf8011..342ae08ec3c2 100644 --- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -153,9 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count, static void dayna_block_output(struct net_device *dev, int count, const unsigned char *buf, int start_page); -#define memcpy_fromio(a, b, c) memcpy((a), (void *)(b), (c)) -#define memcpy_toio(a, b, c) memcpy((void *)(a), (b), (c)) - #define memcmp_withio(a, b, c) memcmp((a), (void *)(b), (c)) /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */ @@ -239,7 +236,7 @@ static enum mac8390_access mac8390_testio(unsigned long membase) unsigned long outdata = 0xA5A0B5B0; unsigned long indata = 0x00000000; /* Try writing 32 bits */ - memcpy_toio(membase, &outdata, 4); + memcpy_toio((void __iomem *)membase, &outdata, 4); /* Now compare them */ if (memcmp_withio(&outdata, membase, 4) == 0) return ACCESS_32; @@ -711,7 +708,7 @@ static void sane_get_8390_hdr(struct net_device *dev, struct e8390_pkt_hdr *hdr, int ring_page) { unsigned long hdr_start = (ring_page - WD_START_PG)<<8; - memcpy_fromio(hdr, dev->mem_start + hdr_start, 4); + memcpy_fromio(hdr, (void __iomem *)dev->mem_start + hdr_start, 4); /* Fix endianness */ hdr->count = swab16(hdr->count); } @@ -725,13 +722,16 @@ static void sane_block_input(struct net_device *dev, int count, if (xfer_start + count > ei_status.rmem_end) { /* We must wrap the input move. */ int semi_count = ei_status.rmem_end - xfer_start; - memcpy_fromio(skb->data, dev->mem_start + xfer_base, + memcpy_fromio(skb->data, + (void __iomem *)dev->mem_start + xfer_base, semi_count); count -= semi_count; - memcpy_fromio(skb->data + semi_count, ei_status.rmem_start, - count); + memcpy_fromio(skb->data + semi_count, + (void __iomem *)ei_status.rmem_start, count); } else { - memcpy_fromio(skb->data, dev->mem_start + xfer_base, count); + memcpy_fromio(skb->data, + (void __iomem *)dev->mem_start + xfer_base, + count); } } @@ -740,7 +740,7 @@ static void sane_block_output(struct net_device *dev, int count, { long shmem = (start_page - WD_START_PG)<<8; - memcpy_toio(dev->mem_start + shmem, buf, count); + memcpy_toio((void __iomem *)dev->mem_start + shmem, buf, count); } /* dayna block input/output */ diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 1b9d3130af4d..17f12c18d225 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -333,6 +333,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr)); + io_sq->dma_addr_bits = ena_dev->dma_addr_bits; io_sq->desc_entry_size = (io_sq->direction == ENA_COM_IO_QUEUE_DIRECTION_TX) ? sizeof(struct ena_eth_io_tx_desc) : diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index f273af136fc7..9e5cf5583c87 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -44,7 +44,7 @@ config AMD8111_ETH config LANCE tristate "AMD LANCE and PCnet (AT1500 and NE2100) support" - depends on ISA && ISA_DMA_API && !ARM + depends on ISA && ISA_DMA_API && !ARM && !PPC32 ---help--- If you have a network (Ethernet) card of this type, say Y here. Some LinkSys cards are of this type. @@ -138,7 +138,7 @@ config PCMCIA_NMCLAN config NI65 tristate "NI6510 support" - depends on ISA && ISA_DMA_API && !ARM + depends on ISA && ISA_DMA_API && !ARM && !PPC32 ---help--- If you have a network (Ethernet) card of this type, say Y here. diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 4b5d625de8f0..8a3a60bb2688 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -1111,14 +1111,14 @@ static void xgbe_phy_adjust_link(struct xgbe_prv_data *pdata) if (pdata->tx_pause != pdata->phy.tx_pause) { new_state = 1; - pdata->hw_if.config_tx_flow_control(pdata); pdata->tx_pause = pdata->phy.tx_pause; + pdata->hw_if.config_tx_flow_control(pdata); } if (pdata->rx_pause != pdata->phy.rx_pause) { new_state = 1; - pdata->hw_if.config_rx_flow_control(pdata); pdata->rx_pause = pdata->phy.rx_pause; + pdata->hw_if.config_rx_flow_control(pdata); } /* Speed support */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h index fc7383106946..91eb8910b1c9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h @@ -63,8 +63,6 @@ #define AQ_CFG_NAPI_WEIGHT 64U -#define AQ_CFG_MULTICAST_ADDRESS_MAX 32U - /*#define AQ_CFG_MAC_ADDR_PERMANENT {0x30, 0x0E, 0xE3, 0x12, 0x34, 0x56}*/ #define AQ_NIC_FC_OFF 0U diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index a2d416b24ffc..2c6ebd91a9f2 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -98,6 +98,8 @@ struct aq_stats_s { #define AQ_HW_MEDIA_TYPE_TP 1U #define AQ_HW_MEDIA_TYPE_FIBRE 2U +#define AQ_HW_MULTICAST_ADDRESS_MAX 32U + struct aq_hw_s { atomic_t flags; u8 rbl_enabled:1; @@ -177,7 +179,7 @@ struct aq_hw_ops { unsigned int packet_filter); int (*hw_multicast_list_set)(struct aq_hw_s *self, - u8 ar_mac[AQ_CFG_MULTICAST_ADDRESS_MAX] + u8 ar_mac[AQ_HW_MULTICAST_ADDRESS_MAX] [ETH_ALEN], u32 count); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index ba5fe8c4125d..e3ae29e523f0 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -135,17 +135,10 @@ err_exit: static void aq_ndev_set_multicast_settings(struct net_device *ndev) { struct aq_nic_s *aq_nic = netdev_priv(ndev); - int err = 0; - err = aq_nic_set_packet_filter(aq_nic, ndev->flags); - if (err < 0) - return; + aq_nic_set_packet_filter(aq_nic, ndev->flags); - if (netdev_mc_count(ndev)) { - err = aq_nic_set_multicast_list(aq_nic, ndev); - if (err < 0) - return; - } + aq_nic_set_multicast_list(aq_nic, ndev); } static const struct net_device_ops aq_ndev_ops = { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 1a1a6380c128..7a22d0257e04 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -563,34 +563,41 @@ err_exit: int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) { + unsigned int packet_filter = self->packet_filter; struct netdev_hw_addr *ha = NULL; unsigned int i = 0U; - self->mc_list.count = 0U; - - netdev_for_each_mc_addr(ha, ndev) { - ether_addr_copy(self->mc_list.ar[i++], ha->addr); - ++self->mc_list.count; + self->mc_list.count = 0; + if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) { + packet_filter |= IFF_PROMISC; + } else { + netdev_for_each_uc_addr(ha, ndev) { + ether_addr_copy(self->mc_list.ar[i++], ha->addr); - if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX) - break; + if (i >= AQ_HW_MULTICAST_ADDRESS_MAX) + break; + } } - if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX) { - /* Number of filters is too big: atlantic does not support this. - * Force all multi filter to support this. - * With this we disable all UC filters and setup "all pass" - * multicast mask - */ - self->packet_filter |= IFF_ALLMULTI; - self->aq_nic_cfg.mc_list_count = 0; - return self->aq_hw_ops->hw_packet_filter_set(self->aq_hw, - self->packet_filter); + if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) { + packet_filter |= IFF_ALLMULTI; } else { - return self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, - self->mc_list.ar, - self->mc_list.count); + netdev_for_each_mc_addr(ha, ndev) { + ether_addr_copy(self->mc_list.ar[i++], ha->addr); + + if (i >= AQ_HW_MULTICAST_ADDRESS_MAX) + break; + } + } + + if (i > 0 && i < AQ_HW_MULTICAST_ADDRESS_MAX) { + packet_filter |= IFF_MULTICAST; + self->mc_list.count = i; + self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, + self->mc_list.ar, + self->mc_list.count); } + return aq_nic_set_packet_filter(self, packet_filter); } int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index faa533a0ec47..fecfc401f95d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -75,7 +75,7 @@ struct aq_nic_s { struct aq_hw_link_status_s link_status; struct { u32 count; - u8 ar[AQ_CFG_MULTICAST_ADDRESS_MAX][ETH_ALEN]; + u8 ar[AQ_HW_MULTICAST_ADDRESS_MAX][ETH_ALEN]; } mc_list; struct pci_dev *pdev; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 67e2f9fb9402..8cc6abadc03b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -765,7 +765,7 @@ static int hw_atl_a0_hw_packet_filter_set(struct aq_hw_s *self, static int hw_atl_a0_hw_multicast_list_set(struct aq_hw_s *self, u8 ar_mac - [AQ_CFG_MULTICAST_ADDRESS_MAX] + [AQ_HW_MULTICAST_ADDRESS_MAX] [ETH_ALEN], u32 count) { diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 819f6bcf9b4e..3bdab972420b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -762,7 +762,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, hw_atl_rpfl2promiscuous_mode_en_set(self, IS_FILTER_ENABLED(IFF_PROMISC)); hw_atl_rpfl2multicast_flr_en_set(self, - IS_FILTER_ENABLED(IFF_MULTICAST), 0); + IS_FILTER_ENABLED(IFF_ALLMULTI), 0); hw_atl_rpfl2_accept_all_mc_packets_set(self, IS_FILTER_ENABLED(IFF_ALLMULTI)); @@ -784,7 +784,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self, u8 ar_mac - [AQ_CFG_MULTICAST_ADDRESS_MAX] + [AQ_HW_MULTICAST_ADDRESS_MAX] [ETH_ALEN], u32 count) { @@ -812,7 +812,7 @@ static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self, hw_atl_rpfl2_uc_flr_en_set(self, (self->aq_nic_cfg->is_mc_list_enabled), - HW_ATL_B0_MAC_MIN + i); + HW_ATL_B0_MAC_MIN + i); } err = aq_hw_err_from_flags(self); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 94270f654b3b..7087b88550db 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -1686,6 +1686,7 @@ static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter) skb = build_skb(page_address(page) + adapter->rx_page_offset, adapter->rx_frag_size); if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); adapter->rx_page_offset += adapter->rx_frag_size; if (adapter->rx_page_offset >= PAGE_SIZE) adapter->rx_page = NULL; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index d5fca2e5a9bc..a1f60f89e059 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1946,8 +1946,8 @@ static int bcm_sysport_open(struct net_device *dev) if (!priv->is_lite) priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD); else - priv->crc_fwd = !!(gib_readl(priv, GIB_CONTROL) & - GIB_FCS_STRIP); + priv->crc_fwd = !((gib_readl(priv, GIB_CONTROL) & + GIB_FCS_STRIP) >> GIB_FCS_STRIP_SHIFT); phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link, 0, priv->phy_interface); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index d6e5d0cbf3a3..cf440b91fd04 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -278,7 +278,8 @@ struct bcm_rsb { #define GIB_GTX_CLK_EXT_CLK (0 << GIB_GTX_CLK_SEL_SHIFT) #define GIB_GTX_CLK_125MHZ (1 << GIB_GTX_CLK_SEL_SHIFT) #define GIB_GTX_CLK_250MHZ (2 << GIB_GTX_CLK_SEL_SHIFT) -#define GIB_FCS_STRIP (1 << 6) +#define GIB_FCS_STRIP_SHIFT 6 +#define GIB_FCS_STRIP (1 << GIB_FCS_STRIP_SHIFT) #define GIB_LCL_LOOP_EN (1 << 7) #define GIB_LCL_LOOP_TXEN (1 << 8) #define GIB_RMT_LOOP_EN (1 << 9) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index da18aa239acb..a4a90b6cdb46 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -3388,14 +3388,18 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info) DP(BNX2X_MSG_ETHTOOL, "rss re-configured, UDP 4-tupple %s\n", udp_rss_requested ? "enabled" : "disabled"); - return bnx2x_rss(bp, &bp->rss_conf_obj, false, true); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_rss(bp, &bp->rss_conf_obj, false, + true); } else if ((info->flow_type == UDP_V6_FLOW) && (bp->rss_conf_obj.udp_rss_v6 != udp_rss_requested)) { bp->rss_conf_obj.udp_rss_v6 = udp_rss_requested; DP(BNX2X_MSG_ETHTOOL, "rss re-configured, UDP 4-tupple %s\n", udp_rss_requested ? "enabled" : "disabled"); - return bnx2x_rss(bp, &bp->rss_conf_obj, false, true); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_rss(bp, &bp->rss_conf_obj, false, + true); } return 0; @@ -3509,7 +3513,10 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir, bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id; } - return bnx2x_config_rss_eth(bp, false); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_config_rss_eth(bp, false); + + return 0; } /** diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 176fc9f4d7de..4394c1162be4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5712,7 +5712,9 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) } vnic->uc_filter_count = 1; - vnic->rx_mask = CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; + vnic->rx_mask = 0; + if (bp->dev->flags & IFF_BROADCAST) + vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; if ((bp->dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp)) vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS; @@ -5917,7 +5919,7 @@ unsigned int bnxt_get_max_func_irqs(struct bnxt *bp) return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_cp_rings); } -void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs) +static void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs) { bp->hw_resc.max_irqs = max_irqs; } @@ -6888,7 +6890,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) rc = bnxt_request_irq(bp); if (rc) { netdev_err(bp->dev, "bnxt_request_irq err: %x\n", rc); - goto open_err; + goto open_err_irq; } } @@ -6928,6 +6930,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) open_err: bnxt_debug_dev_exit(bp); bnxt_disable_napi(bp); + +open_err_irq: bnxt_del_napi(bp); open_err_free_mem: @@ -7214,13 +7218,16 @@ static void bnxt_set_rx_mode(struct net_device *dev) mask &= ~(CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS | CFA_L2_SET_RX_MASK_REQ_MASK_MCAST | - CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST); + CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST | + CFA_L2_SET_RX_MASK_REQ_MASK_BCAST); if ((dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp)) mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS; uc_update = bnxt_uc_list_updated(bp); + if (dev->flags & IFF_BROADCAST) + mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; if (dev->flags & IFF_ALLMULTI) { mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST; vnic->mc_list_count = 0; @@ -8502,11 +8509,11 @@ int bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, bool shared) int rx, tx, cp; _bnxt_get_max_rings(bp, &rx, &tx, &cp); + *max_rx = rx; + *max_tx = tx; if (!rx || !tx || !cp) return -ENOMEM; - *max_rx = rx; - *max_tx = tx; return bnxt_trim_rings(bp, max_rx, max_tx, cp, shared); } @@ -8520,8 +8527,11 @@ static int bnxt_get_dflt_rings(struct bnxt *bp, int *max_rx, int *max_tx, /* Not enough rings, try disabling agg rings. */ bp->flags &= ~BNXT_FLAG_AGG_RINGS; rc = bnxt_get_max_rings(bp, max_rx, max_tx, shared); - if (rc) + if (rc) { + /* set BNXT_FLAG_AGG_RINGS back for consistency */ + bp->flags |= BNXT_FLAG_AGG_RINGS; return rc; + } bp->flags |= BNXT_FLAG_NO_AGG_RINGS; bp->dev->hw_features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW); bp->dev->features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 9b14eb610b9f..91575ef97c8c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1470,7 +1470,6 @@ void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max); unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp); void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max); unsigned int bnxt_get_max_func_irqs(struct bnxt *bp); -void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max); int bnxt_get_avail_msix(struct bnxt *bp, int num); int bnxt_reserve_rings(struct bnxt *bp); void bnxt_tx_disable(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 795f45024c20..491bd40a254d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -27,6 +27,15 @@ #define BNXT_FID_INVALID 0xffff #define VLAN_TCI(vid, prio) ((vid) | ((prio) << VLAN_PRIO_SHIFT)) +#define is_vlan_pcp_wildcarded(vlan_tci_mask) \ + ((ntohs(vlan_tci_mask) & VLAN_PRIO_MASK) == 0x0000) +#define is_vlan_pcp_exactmatch(vlan_tci_mask) \ + ((ntohs(vlan_tci_mask) & VLAN_PRIO_MASK) == VLAN_PRIO_MASK) +#define is_vlan_pcp_zero(vlan_tci) \ + ((ntohs(vlan_tci) & VLAN_PRIO_MASK) == 0x0000) +#define is_vid_exactmatch(vlan_tci_mask) \ + ((ntohs(vlan_tci_mask) & VLAN_VID_MASK) == VLAN_VID_MASK) + /* Return the dst fid of the func for flow forwarding * For PFs: src_fid is the fid of the PF * For VF-reps: src_fid the fid of the VF @@ -389,6 +398,21 @@ static bool is_exactmatch(void *mask, int len) return true; } +static bool is_vlan_tci_allowed(__be16 vlan_tci_mask, + __be16 vlan_tci) +{ + /* VLAN priority must be either exactly zero or fully wildcarded and + * VLAN id must be exact match. + */ + if (is_vid_exactmatch(vlan_tci_mask) && + ((is_vlan_pcp_exactmatch(vlan_tci_mask) && + is_vlan_pcp_zero(vlan_tci)) || + is_vlan_pcp_wildcarded(vlan_tci_mask))) + return true; + + return false; +} + static bool bits_set(void *key, int len) { const u8 *p = key; @@ -803,9 +827,9 @@ static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow) /* Currently VLAN fields cannot be partial wildcard */ if (bits_set(&flow->l2_key.inner_vlan_tci, sizeof(flow->l2_key.inner_vlan_tci)) && - !is_exactmatch(&flow->l2_mask.inner_vlan_tci, - sizeof(flow->l2_mask.inner_vlan_tci))) { - netdev_info(bp->dev, "Wildcard match unsupported for VLAN TCI\n"); + !is_vlan_tci_allowed(flow->l2_mask.inner_vlan_tci, + flow->l2_key.inner_vlan_tci)) { + netdev_info(bp->dev, "Unsupported VLAN TCI\n"); return false; } if (bits_set(&flow->l2_key.inner_vlan_tpid, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 347e4f946eb2..840f6e505f73 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -169,7 +169,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, edev->ulp_tbl[ulp_id].msix_requested = avail_msix; } bnxt_fill_msix_vecs(bp, ent); - bnxt_set_max_func_irqs(bp, bnxt_get_max_func_irqs(bp) - avail_msix); bnxt_set_max_func_cp_rings(bp, max_cp_rings - avail_msix); edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED; return avail_msix; @@ -192,7 +191,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id) msix_requested = edev->ulp_tbl[ulp_id].msix_requested; bnxt_set_max_func_cp_rings(bp, max_cp_rings + msix_requested); edev->ulp_tbl[ulp_id].msix_requested = 0; - bnxt_set_max_func_irqs(bp, bnxt_get_max_func_irqs(bp) + msix_requested); edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED; if (netif_running(dev)) { bnxt_close_nic(bp, true, false); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 3be87efdc93d..aa1374d0af93 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6,11 +6,15 @@ * Copyright (C) 2004 Sun Microsystems Inc. * Copyright (C) 2005-2016 Broadcom Corporation. * Copyright (C) 2016-2017 Broadcom Limited. + * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom" + * refers to Broadcom Inc. and/or its subsidiaries. * * Firmware is: * Derived from proprietary unpublished source code, * Copyright (C) 2000-2016 Broadcom Corporation. * Copyright (C) 2016-2017 Broadcom Ltd. + * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom" + * refers to Broadcom Inc. and/or its subsidiaries. * * Permission is hereby granted for the distribution of this firmware * data in hexadecimal or equivalent format, provided this copyright @@ -9290,6 +9294,15 @@ static int tg3_chip_reset(struct tg3 *tp) tg3_restore_clk(tp); + /* Increase the core clock speed to fix tx timeout issue for 5762 + * with 100Mbps link speed. + */ + if (tg3_asic_rev(tp) == ASIC_REV_5762) { + val = tr32(TG3_CPMU_CLCK_ORIDE_ENABLE); + tw32(TG3_CPMU_CLCK_ORIDE_ENABLE, val | + TG3_CPMU_MAC_ORIDE_ENABLE); + } + /* Reprobe ASF enable state. */ tg3_flag_clear(tp, ENABLE_ASF); tp->phy_flags &= ~(TG3_PHYFLG_1G_ON_VAUX_OK | diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index 1d61aa3efda1..a772a33b685c 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -7,6 +7,8 @@ * Copyright (C) 2004 Sun Microsystems Inc. * Copyright (C) 2007-2016 Broadcom Corporation. * Copyright (C) 2016-2017 Broadcom Limited. + * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom" + * refers to Broadcom Inc. and/or its subsidiaries. */ #ifndef _T3_H diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 86659823b259..3d45f4c92cf6 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -166,6 +166,7 @@ #define GEM_DCFG6 0x0294 /* Design Config 6 */ #define GEM_DCFG7 0x0298 /* Design Config 7 */ #define GEM_DCFG8 0x029C /* Design Config 8 */ +#define GEM_DCFG10 0x02A4 /* Design Config 10 */ #define GEM_TXBDCTRL 0x04cc /* TX Buffer Descriptor control register */ #define GEM_RXBDCTRL 0x04d0 /* RX Buffer Descriptor control register */ @@ -490,6 +491,12 @@ #define GEM_SCR2CMP_OFFSET 0 #define GEM_SCR2CMP_SIZE 8 +/* Bitfields in DCFG10 */ +#define GEM_TXBD_RDBUFF_OFFSET 12 +#define GEM_TXBD_RDBUFF_SIZE 4 +#define GEM_RXBD_RDBUFF_OFFSET 8 +#define GEM_RXBD_RDBUFF_SIZE 4 + /* Bitfields in TISUBN */ #define GEM_SUBNSINCR_OFFSET 0 #define GEM_SUBNSINCR_SIZE 16 @@ -635,6 +642,7 @@ #define MACB_CAPS_USRIO_DISABLED 0x00000010 #define MACB_CAPS_JUMBO 0x00000020 #define MACB_CAPS_GEM_HAS_PTP 0x00000040 +#define MACB_CAPS_BD_RD_PREFETCH 0x00000080 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 @@ -1203,6 +1211,9 @@ struct macb { unsigned int max_tuples; struct tasklet_struct hresp_err_tasklet; + + int rx_bd_rd_prefetch; + int tx_bd_rd_prefetch; }; #ifdef CONFIG_MACB_USE_HWSTAMP diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 96cc03a6d942..a6c911bb5ce2 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1811,23 +1811,25 @@ static void macb_free_consistent(struct macb *bp) { struct macb_queue *queue; unsigned int q; + int size; - queue = &bp->queues[0]; bp->macbgem_ops.mog_free_rx_buffers(bp); - if (queue->rx_ring) { - dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES(bp), - queue->rx_ring, queue->rx_ring_dma); - queue->rx_ring = NULL; - } for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { kfree(queue->tx_skb); queue->tx_skb = NULL; if (queue->tx_ring) { - dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES(bp), + size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch; + dma_free_coherent(&bp->pdev->dev, size, queue->tx_ring, queue->tx_ring_dma); queue->tx_ring = NULL; } + if (queue->rx_ring) { + size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch; + dma_free_coherent(&bp->pdev->dev, size, + queue->rx_ring, queue->rx_ring_dma); + queue->rx_ring = NULL; + } } } @@ -1874,7 +1876,7 @@ static int macb_alloc_consistent(struct macb *bp) int size; for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - size = TX_RING_BYTES(bp); + size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch; queue->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size, &queue->tx_ring_dma, GFP_KERNEL); @@ -1890,7 +1892,7 @@ static int macb_alloc_consistent(struct macb *bp) if (!queue->tx_skb) goto out_err; - size = RX_RING_BYTES(bp); + size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch; queue->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size, &queue->rx_ring_dma, GFP_KERNEL); if (!queue->rx_ring) @@ -3797,7 +3799,7 @@ static const struct macb_config np4_config = { static const struct macb_config zynqmp_config = { .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO | - MACB_CAPS_GEM_HAS_PTP, + MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, @@ -3858,7 +3860,7 @@ static int macb_probe(struct platform_device *pdev) void __iomem *mem; const char *mac; struct macb *bp; - int err; + int err, val; regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); mem = devm_ioremap_resource(&pdev->dev, regs); @@ -3947,6 +3949,18 @@ static int macb_probe(struct platform_device *pdev) else dev->max_mtu = ETH_DATA_LEN; + if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) { + val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10)); + if (val) + bp->rx_bd_rd_prefetch = (2 << (val - 1)) * + macb_dma_desc_get_size(bp); + + val = GEM_BFEXT(TXBD_RDBUFF, gem_readl(bp, DCFG10)); + if (val) + bp->tx_bd_rd_prefetch = (2 << (val - 1)) * + macb_dma_desc_get_size(bp); + } + mac = of_get_mac_address(np); if (mac) { ether_addr_copy(bp->dev->dev_addr, mac); diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 043e3c11c42b..92d88c5f76fb 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -15,7 +15,7 @@ if NET_VENDOR_CAVIUM config THUNDER_NIC_PF tristate "Thunder Physical function driver" - depends on 64BIT + depends on 64BIT && PCI select THUNDER_NIC_BGX ---help--- This driver supports Thunder's NIC physical function. @@ -28,13 +28,13 @@ config THUNDER_NIC_PF config THUNDER_NIC_VF tristate "Thunder Virtual function driver" imply CAVIUM_PTP - depends on 64BIT + depends on 64BIT && PCI ---help--- This driver supports Thunder's NIC virtual function config THUNDER_NIC_BGX tristate "Thunder MAC interface driver (BGX)" - depends on 64BIT + depends on 64BIT && PCI select PHYLIB select MDIO_THUNDER select THUNDER_NIC_RGX @@ -44,7 +44,7 @@ config THUNDER_NIC_BGX config THUNDER_NIC_RGX tristate "Thunder MAC interface driver (RGX)" - depends on 64BIT + depends on 64BIT && PCI select PHYLIB select MDIO_THUNDER ---help--- @@ -53,7 +53,7 @@ config THUNDER_NIC_RGX config CAVIUM_PTP tristate "Cavium PTP coprocessor as PTP clock" - depends on 64BIT + depends on 64BIT && PCI imply PTP_1588_CLOCK default y ---help--- @@ -65,7 +65,7 @@ config CAVIUM_PTP config LIQUIDIO tristate "Cavium LiquidIO support" - depends on 64BIT + depends on 64BIT && PCI depends on MAY_USE_DEVLINK imply PTP_1588_CLOCK select FW_LOADER diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 8a815bb57177..7e8454d3b1ad 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -91,6 +91,9 @@ static int octeon_console_debug_enabled(u32 console) */ #define LIO_SYNC_OCTEON_TIME_INTERVAL_MS 60000 +/* time to wait for possible in-flight requests in milliseconds */ +#define WAIT_INFLIGHT_REQUEST msecs_to_jiffies(1000) + struct lio_trusted_vf_ctx { struct completion complete; int status; @@ -259,7 +262,7 @@ static inline void pcierror_quiesce_device(struct octeon_device *oct) force_io_queues_off(oct); /* To allow for in-flight requests */ - schedule_timeout_uninterruptible(100); + schedule_timeout_uninterruptible(WAIT_INFLIGHT_REQUEST); if (wait_for_pending_requests(oct)) dev_err(&oct->pci_dev->dev, "There were pending requests\n"); diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 3f6afb54a5eb..bb43ddb7539e 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -643,13 +643,21 @@ static int octeon_mgmt_set_mac_address(struct net_device *netdev, void *addr) static int octeon_mgmt_change_mtu(struct net_device *netdev, int new_mtu) { struct octeon_mgmt *p = netdev_priv(netdev); - int size_without_fcs = new_mtu + OCTEON_MGMT_RX_HEADROOM; + int max_packet = new_mtu + ETH_HLEN + ETH_FCS_LEN; netdev->mtu = new_mtu; - cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_MAX, size_without_fcs); + /* HW lifts the limit if the frame is VLAN tagged + * (+4 bytes per each tag, up to two tags) + */ + cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_MAX, max_packet); + /* Set the hardware to truncate packets larger than the MTU. The jabber + * register must be set to a multiple of 8 bytes, so round up. JABBER is + * an unconditional limit, so we need to account for two possible VLAN + * tags. + */ cvmx_write_csr(p->agl + AGL_GMX_RX_JABBER, - (size_without_fcs + 7) & 0xfff8); + (max_packet + 7 + VLAN_HLEN * 2) & 0xfff8); return 0; } diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 5d08d2aeb172..e337da6ba2a4 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1083,6 +1083,8 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid) lmac->dmacs_count = (RX_DMAC_COUNT / bgx->lmac_count); lmac->dmacs = kcalloc(lmac->dmacs_count, sizeof(*lmac->dmacs), GFP_KERNEL); + if (!lmac->dmacs) + return -ENOMEM; /* Enable lmac */ bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 7b795edd9d3a..a19172dbe6be 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -51,6 +51,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/nospec.h> #include "common.h" #include "cxgb3_ioctl.h" @@ -2268,6 +2269,7 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (t.qset_idx >= nqsets) return -EINVAL; + t.qset_idx = array_index_nospec(t.qset_idx, nqsets); q = &adapter->params.sge.qset[q1 + t.qset_idx]; t.rspq_size = q->rspq_size; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 00fc5f1afb1d..7dddb9e748b8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1038,10 +1038,8 @@ static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb, OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, qid_filterid)); req->local_port = cpu_to_be16(f->fs.val.lport); req->peer_port = cpu_to_be16(f->fs.val.fport); - req->local_ip = f->fs.val.lip[0] | f->fs.val.lip[1] << 8 | - f->fs.val.lip[2] << 16 | f->fs.val.lip[3] << 24; - req->peer_ip = f->fs.val.fip[0] | f->fs.val.fip[1] << 8 | - f->fs.val.fip[2] << 16 | f->fs.val.fip[3] << 24; + memcpy(&req->local_ip, f->fs.val.lip, 4); + memcpy(&req->peer_ip, f->fs.val.fip, 4); req->opt0 = cpu_to_be64(NAGLE_V(f->fs.newvlan == VLAN_REMOVE || f->fs.newvlan == VLAN_REWRITE) | DELACK_V(f->fs.hitcnts) | diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index bc03c175a3cd..a8926e97935e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3072,6 +3072,7 @@ static void cxgb_del_udp_tunnel(struct net_device *netdev, adapter->geneve_port = 0; t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, 0); + break; default: return; } @@ -3157,6 +3158,7 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev, t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, GENEVE_V(be16_to_cpu(ti->port)) | GENEVE_EN_F); + break; default: return; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 974a868a4824..3720c3e11ebb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -8702,7 +8702,7 @@ static int t4_get_flash_params(struct adapter *adap) }; unsigned int part, manufacturer; - unsigned int density, size; + unsigned int density, size = 0; u32 flashid = 0; int ret; @@ -8772,11 +8772,6 @@ static int t4_get_flash_params(struct adapter *adap) case 0x22: /* 256MB */ size = 1 << 28; break; - - default: - dev_err(adap->pdev_dev, "Micron Flash Part has bad size, ID = %#x, Density code = %#x\n", - flashid, density); - return -EINVAL; } break; } @@ -8792,10 +8787,6 @@ static int t4_get_flash_params(struct adapter *adap) case 0x17: /* 64MB */ size = 1 << 26; break; - default: - dev_err(adap->pdev_dev, "ISSI Flash Part has bad size, ID = %#x, Density code = %#x\n", - flashid, density); - return -EINVAL; } break; } @@ -8811,10 +8802,6 @@ static int t4_get_flash_params(struct adapter *adap) case 0x18: /* 16MB */ size = 1 << 24; break; - default: - dev_err(adap->pdev_dev, "Macronix Flash Part has bad size, ID = %#x, Density code = %#x\n", - flashid, density); - return -EINVAL; } break; } @@ -8830,17 +8817,21 @@ static int t4_get_flash_params(struct adapter *adap) case 0x18: /* 16MB */ size = 1 << 24; break; - default: - dev_err(adap->pdev_dev, "Winbond Flash Part has bad size, ID = %#x, Density code = %#x\n", - flashid, density); - return -EINVAL; } break; } - default: - dev_err(adap->pdev_dev, "Unsupported Flash Part, ID = %#x\n", - flashid); - return -EINVAL; + } + + /* If we didn't recognize the FLASH part, that's no real issue: the + * Hardware/Software contract says that Hardware will _*ALWAYS*_ + * use a FLASH part which is at least 4MB in size and has 64KB + * sectors. The unrecognized FLASH part is likely to be much larger + * than 4MB, but that's all we really need. + */ + if (size == 0) { + dev_warn(adap->pdev_dev, "Unknown Flash Part, ID = %#x, assuming 4MB\n", + flashid); + size = 1 << 22; } /* Store decoded Flash size and fall through into vetting code. */ diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig index 5ab912937aff..ec0b545197e2 100644 --- a/drivers/net/ethernet/cirrus/Kconfig +++ b/drivers/net/ethernet/cirrus/Kconfig @@ -19,6 +19,7 @@ if NET_VENDOR_CIRRUS config CS89x0 tristate "CS89x0 support" depends on ISA || EISA || ARM + depends on !PPC32 ---help--- Support for CS89x0 chipset based Ethernet cards. If you have a network (Ethernet) card of this type, say Y and read the file diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 90c645b8538e..60641e202534 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -2047,28 +2047,42 @@ static int enic_stop(struct net_device *netdev) return 0; } +static int _enic_change_mtu(struct net_device *netdev, int new_mtu) +{ + bool running = netif_running(netdev); + int err = 0; + + ASSERT_RTNL(); + if (running) { + err = enic_stop(netdev); + if (err) + return err; + } + + netdev->mtu = new_mtu; + + if (running) { + err = enic_open(netdev); + if (err) + return err; + } + + return 0; +} + static int enic_change_mtu(struct net_device *netdev, int new_mtu) { struct enic *enic = netdev_priv(netdev); - int running = netif_running(netdev); if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic)) return -EOPNOTSUPP; - if (running) - enic_stop(netdev); - - netdev->mtu = new_mtu; - if (netdev->mtu > enic->port_mtu) netdev_warn(netdev, - "interface MTU (%d) set higher than port MTU (%d)\n", - netdev->mtu, enic->port_mtu); + "interface MTU (%d) set higher than port MTU (%d)\n", + netdev->mtu, enic->port_mtu); - if (running) - enic_open(netdev); - - return 0; + return _enic_change_mtu(netdev, new_mtu); } static void enic_change_mtu_work(struct work_struct *work) @@ -2076,47 +2090,9 @@ static void enic_change_mtu_work(struct work_struct *work) struct enic *enic = container_of(work, struct enic, change_mtu_work); struct net_device *netdev = enic->netdev; int new_mtu = vnic_dev_mtu(enic->vdev); - int err; - unsigned int i; - - new_mtu = max_t(int, ENIC_MIN_MTU, min_t(int, ENIC_MAX_MTU, new_mtu)); rtnl_lock(); - - /* Stop RQ */ - del_timer_sync(&enic->notify_timer); - - for (i = 0; i < enic->rq_count; i++) - napi_disable(&enic->napi[i]); - - vnic_intr_mask(&enic->intr[0]); - enic_synchronize_irqs(enic); - err = vnic_rq_disable(&enic->rq[0]); - if (err) { - rtnl_unlock(); - netdev_err(netdev, "Unable to disable RQ.\n"); - return; - } - vnic_rq_clean(&enic->rq[0], enic_free_rq_buf); - vnic_cq_clean(&enic->cq[0]); - vnic_intr_clean(&enic->intr[0]); - - /* Fill RQ with new_mtu-sized buffers */ - netdev->mtu = new_mtu; - vnic_rq_fill(&enic->rq[0], enic_rq_alloc_buf); - /* Need at least one buffer on ring to get going */ - if (vnic_rq_desc_used(&enic->rq[0]) == 0) { - rtnl_unlock(); - netdev_err(netdev, "Unable to alloc receive buffers.\n"); - return; - } - - /* Start RQ */ - vnic_rq_enable(&enic->rq[0]); - napi_enable(&enic->napi[0]); - vnic_intr_unmask(&enic->intr[0]); - enic_notify_timer_start(enic); - + (void)_enic_change_mtu(netdev, new_mtu); rtnl_unlock(); netdev_info(netdev, "interface MTU set as %d\n", netdev->mtu); @@ -2916,7 +2892,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ enic->port_mtu = enic->config.mtu; - (void)enic_change_mtu(netdev, enic->port_mtu); err = enic_set_mac_addr(netdev, enic->mac_addr); if (err) { @@ -3006,6 +2981,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* MTU range: 68 - 9000 */ netdev->min_mtu = ENIC_MIN_MTU; netdev->max_mtu = ENIC_MAX_MTU; + netdev->mtu = enic->port_mtu; err = register_netdev(netdev); if (err) { diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 5b122728dcb4..09e9da10b786 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -983,6 +983,7 @@ static int nic_dev_init(struct pci_dev *pdev) hinic_hwdev_cb_register(nic_dev->hwdev, HINIC_MGMT_MSG_CMD_LINK_STATUS, nic_dev, link_status_event_handler); + SET_NETDEV_DEV(netdev, &pdev->dev); err = register_netdev(netdev); if (err) { dev_err(&pdev->dev, "Failed to register netdev\n"); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index 9128858479c4..2353ec829c04 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -229,6 +229,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) txq->txq_stats.tx_busy++; u64_stats_update_end(&txq->txq_stats.syncp); err = NETDEV_TX_BUSY; + wqe_size = 0; goto flush_skbs; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index d0e196bff081..ffe7acbeaa22 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -329,7 +329,8 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, return; failure: - dev_info(dev, "replenish pools failure\n"); + if (lpar_rc != H_PARAMETER && lpar_rc != H_CLOSED) + dev_err_ratelimited(dev, "rx: replenish packet buffer failed\n"); pool->free_map[pool->next_free] = index; pool->rx_buff[index].skb = NULL; @@ -1617,7 +1618,8 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) &tx_crq); } if (lpar_rc != H_SUCCESS) { - dev_err(dev, "tx failed with code %ld\n", lpar_rc); + if (lpar_rc != H_CLOSED && lpar_rc != H_PARAMETER) + dev_err_ratelimited(dev, "tx: send failed\n"); dev_kfree_skb_any(skb); tx_buff->skb = NULL; @@ -1825,8 +1827,8 @@ static int do_reset(struct ibmvnic_adapter *adapter, rc = ibmvnic_login(netdev); if (rc) { - adapter->state = VNIC_PROBED; - return 0; + adapter->state = reset_state; + return rc; } if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM || @@ -3204,6 +3206,25 @@ static union ibmvnic_crq *ibmvnic_next_crq(struct ibmvnic_adapter *adapter) return crq; } +static void print_subcrq_error(struct device *dev, int rc, const char *func) +{ + switch (rc) { + case H_PARAMETER: + dev_warn_ratelimited(dev, + "%s failed: Send request is malformed or adapter failover pending. (rc=%d)\n", + func, rc); + break; + case H_CLOSED: + dev_warn_ratelimited(dev, + "%s failed: Backing queue closed. Adapter is down or failover pending. (rc=%d)\n", + func, rc); + break; + default: + dev_err_ratelimited(dev, "%s failed: (rc=%d)\n", func, rc); + break; + } +} + static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle, union sub_crq *sub_crq) { @@ -3230,11 +3251,8 @@ static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle, cpu_to_be64(u64_crq[2]), cpu_to_be64(u64_crq[3])); - if (rc) { - if (rc == H_CLOSED) - dev_warn(dev, "CRQ Queue closed\n"); - dev_err(dev, "Send error (rc=%d)\n", rc); - } + if (rc) + print_subcrq_error(dev, rc, __func__); return rc; } @@ -3252,11 +3270,8 @@ static int send_subcrq_indirect(struct ibmvnic_adapter *adapter, cpu_to_be64(remote_handle), ioba, num_entries); - if (rc) { - if (rc == H_CLOSED) - dev_warn(dev, "CRQ Queue closed\n"); - dev_err(dev, "Send (indirect) error (rc=%d)\n", rc); - } + if (rc) + print_subcrq_error(dev, rc, __func__); return rc; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 3f5c350716bb..0bd1294ba517 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -1871,7 +1871,12 @@ s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq, if (enable_addr != 0) rar_high |= IXGBE_RAH_AV; + /* Record lower 32 bits of MAC address and then make + * sure that write is flushed to hardware before writing + * the upper 16 bits and setting the valid bit. + */ IXGBE_WRITE_REG(hw, IXGBE_RAL(index), rar_low); + IXGBE_WRITE_FLUSH(hw); IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high); return 0; @@ -1903,8 +1908,13 @@ s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index) rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(index)); rar_high &= ~(0x0000FFFF | IXGBE_RAH_AV); - IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0); + /* Clear the address valid bit and upper 16 bits of the address + * before clearing the lower bits. This way we aren't updating + * a live filter. + */ IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high); + IXGBE_WRITE_FLUSH(hw); + IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0); /* clear VMDq pool/queue selection for this RAR */ hw->mac.ops.clear_vmdq(hw, index, IXGBE_CLEAR_VMDQ_ALL); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index c116f459945d..da4322e4daed 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -839,7 +839,7 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, } itd->sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; - if (unlikely(itd->sa_idx > IXGBE_IPSEC_MAX_SA_COUNT)) { + if (unlikely(itd->sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT)) { netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n", __func__, itd->sa_idx, xs->xso.offload_handle); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 9f54ccbddea7..3360f7b9ee73 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -474,10 +474,10 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, { const struct mlx4_en_frag_info *frag_info = priv->frag_info; unsigned int truesize = 0; + bool release = true; int nr, frag_size; struct page *page; dma_addr_t dma; - bool release; /* Collect used fragments while replacing them in the HW descriptors */ for (nr = 0;; frags++) { @@ -500,7 +500,11 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, release = page_count(page) != 1 || page_is_pfmemalloc(page) || page_to_nid(page) != numa_mem_id(); - } else { + } else if (!priv->rx_headroom) { + /* rx_headroom for non XDP setup is always 0. + * When XDP is set, the above condition will + * guarantee page is always released. + */ u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES); frags->page_offset += sz_align; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 7b1b5ac986d0..31bd56727022 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2958,7 +2958,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, u32 srqn = qp_get_srqn(qpc) & 0xffffff; int use_srq = (qp_get_srqn(qpc) >> 24) & 1; struct res_srq *srq; - int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff; + int local_qpn = vhcr->in_modifier & 0xffffff; err = adjust_qp_sched_queue(dev, slave, qpc, inbox); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c index 323ffe8bf7e4..456f30007ad6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c @@ -123,7 +123,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, int i; buf->size = size; - buf->npages = 1 << get_order(size); + buf->npages = DIV_ROUND_UP(size, PAGE_SIZE); buf->page_shift = PAGE_SHIFT; buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index eb9eb7aa953a..405236cf0b04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -858,8 +858,6 @@ struct mlx5e_profile { mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe; } rx_handlers; - void (*netdev_registered_init)(struct mlx5e_priv *priv); - void (*netdev_registered_remove)(struct mlx5e_priv *priv); int max_tc; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 75e4308ba786..d258bb679271 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -381,14 +381,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv) HLIST_HEAD(del_list); spin_lock_bh(&priv->fs.arfs.arfs_lock); mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) { - if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) - break; if (!work_pending(&arfs_rule->arfs_work) && rps_may_expire_flow(priv->netdev, arfs_rule->rxq, arfs_rule->flow_id, arfs_rule->filter_id)) { hlist_del_init(&arfs_rule->hlist); hlist_add_head(&arfs_rule->hlist, &del_list); + if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) + break; } } spin_unlock_bh(&priv->fs.arfs.arfs_lock); @@ -711,6 +711,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, skb->protocol != htons(ETH_P_IPV6)) return -EPROTONOSUPPORT; + if (skb->encapsulation) + return -EPROTONOSUPPORT; + arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol); if (!arfs_t) return -EPROTONOSUPPORT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 0a52f31fef37..722998d68564 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -275,7 +275,8 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) } static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, - struct ieee_ets *ets) + struct ieee_ets *ets, + bool zero_sum_allowed) { bool have_ets_tc = false; int bw_sum = 0; @@ -300,8 +301,9 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, } if (have_ets_tc && bw_sum != 100) { - netdev_err(netdev, - "Failed to validate ETS: BW sum is illegal\n"); + if (bw_sum || (!bw_sum && !zero_sum_allowed)) + netdev_err(netdev, + "Failed to validate ETS: BW sum is illegal\n"); return -EINVAL; } return 0; @@ -316,7 +318,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev, if (!MLX5_CAP_GEN(priv->mdev, ets)) return -EOPNOTSUPP; - err = mlx5e_dbcnl_validate_ets(netdev, ets); + err = mlx5e_dbcnl_validate_ets(netdev, ets, false); if (err) return err; @@ -441,16 +443,12 @@ static int mlx5e_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app) bool is_new; int err; - if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP) - return -EINVAL; - - if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager)) - return -EINVAL; - - if (!MLX5_DSCP_SUPPORTED(priv->mdev)) - return -EINVAL; + if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) || + !MLX5_DSCP_SUPPORTED(priv->mdev)) + return -EOPNOTSUPP; - if (app->protocol >= MLX5E_MAX_DSCP) + if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) || + (app->protocol >= MLX5E_MAX_DSCP)) return -EINVAL; /* Save the old entry info */ @@ -498,16 +496,12 @@ static int mlx5e_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app) struct mlx5e_priv *priv = netdev_priv(dev); int err; - if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP) - return -EINVAL; - - if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager)) - return -EINVAL; - - if (!MLX5_DSCP_SUPPORTED(priv->mdev)) - return -EINVAL; + if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) || + !MLX5_DSCP_SUPPORTED(priv->mdev)) + return -EOPNOTSUPP; - if (app->protocol >= MLX5E_MAX_DSCP) + if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) || + (app->protocol >= MLX5E_MAX_DSCP)) return -EINVAL; /* Skip if no dscp app entry */ @@ -642,12 +636,9 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev) ets.prio_tc[i]); } - err = mlx5e_dbcnl_validate_ets(netdev, &ets); - if (err) { - netdev_err(netdev, - "%s, Failed to validate ETS: %d\n", __func__, err); + err = mlx5e_dbcnl_validate_ets(netdev, &ets, true); + if (err) goto out; - } err = mlx5e_dcbnl_ieee_setets_core(priv, &ets); if (err) { @@ -1147,7 +1138,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state) { int err; - err = mlx5_set_trust_state(priv->mdev, trust_state); + err = mlx5_set_trust_state(priv->mdev, trust_state); if (err) return err; priv->dcbx_dp.trust_state = trust_state; @@ -1173,6 +1164,8 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; int err; + priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_PCP; + if (!MLX5_DSCP_SUPPORTED(mdev)) return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dae4156a710d..c592678ab5f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3712,7 +3712,8 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, if (!reset) { params->sw_mtu = new_mtu; - set_mtu_cb(priv); + if (set_mtu_cb) + set_mtu_cb(priv); netdev->mtu = params->sw_mtu; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 0edf4751a8ba..dfbcda0d0e08 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1957,6 +1957,10 @@ static bool actions_match_supported(struct mlx5e_priv *priv, else actions = flow->nic_attr->action; + if (flow->flags & MLX5E_TC_FLOW_EGRESS && + !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)) + return false; + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) return modify_header_match_supported(&parse_attr->spec, exts); @@ -1966,15 +1970,15 @@ static bool actions_match_supported(struct mlx5e_priv *priv, static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) { struct mlx5_core_dev *fmdev, *pmdev; - u16 func_id, peer_id; + u64 fsystem_guid, psystem_guid; fmdev = priv->mdev; pmdev = peer_priv->mdev; - func_id = (u16)((fmdev->pdev->bus->number << 8) | PCI_SLOT(fmdev->pdev->devfn)); - peer_id = (u16)((pmdev->pdev->bus->number << 8) | PCI_SLOT(pmdev->pdev->devfn)); + mlx5_query_nic_vport_system_image_guid(fmdev, &fsystem_guid); + mlx5_query_nic_vport_system_image_guid(pmdev, &psystem_guid); - return (func_id == peer_id); + return (fsystem_guid == psystem_guid); } static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index b79d74860a30..40dba9e8af92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1696,7 +1696,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) int vport_num; int err; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; esw_info(dev, @@ -1765,7 +1765,7 @@ abort: void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) { - if (!esw || !MLX5_VPORT_MANAGER(esw->dev)) + if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev)) return; esw_info(esw->dev, "cleanup\n"); @@ -2216,6 +2216,6 @@ free_out: u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw) { - return esw->mode; + return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE; } EXPORT_SYMBOL_GPL(mlx5_eswitch_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index f1a86cea86a0..6ddb2565884d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1887,7 +1887,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { if (!fwd_next_prio_supported(ft)) return ERR_PTR(-EOPNOTSUPP); - if (dest) + if (dest_num) return ERR_PTR(-EINVAL); mutex_lock(&root->chain_lock); next_ft = find_next_chained_ft(prio); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index af3bb2f7a504..b7c21eb21a21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -76,6 +76,7 @@ void mlx5i_init(struct mlx5_core_dev *mdev, void *ppriv) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); + u16 max_mtu; /* priv init */ priv->mdev = mdev; @@ -84,6 +85,9 @@ void mlx5i_init(struct mlx5_core_dev *mdev, priv->ppriv = ppriv; mutex_init(&priv->state_lock); + mlx5_query_port_max_mtu(mdev, &max_mtu, 1); + netdev->mtu = max_mtu; + mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev), netdev->mtu); mlx5i_build_nic_params(mdev, &priv->channels.params); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 1e062e6b2587..3f767cde4c1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -488,6 +488,7 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev, void mlx5_init_clock(struct mlx5_core_dev *mdev) { struct mlx5_clock *clock = &mdev->clock; + u64 overflow_cycles; u64 ns; u64 frac = 0; u32 dev_freq; @@ -511,10 +512,17 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev) /* Calculate period in seconds to call the overflow watchdog - to make * sure counter is checked at least once every wrap around. + * The period is calculated as the minimum between max HW cycles count + * (The clock source mask) and max amount of cycles that can be + * multiplied by clock multiplier where the result doesn't exceed + * 64bits. */ - ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask, + overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult); + overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1); + + ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles, frac, &frac); - do_div(ns, NSEC_PER_SEC / 2 / HZ); + do_div(ns, NSEC_PER_SEC / HZ); clock->overflow_period = ns; mdev->clock_info_page = alloc_page(GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index b97bb72b4db4..86478a6b99c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -113,35 +113,45 @@ err_db_free: return err; } -static void mlx5e_qp_set_frag_buf(struct mlx5_frag_buf *buf, - struct mlx5_wq_qp *qp) +static void mlx5_qp_set_frag_buf(struct mlx5_frag_buf *buf, + struct mlx5_wq_qp *qp) { + struct mlx5_frag_buf_ctrl *sq_fbc; struct mlx5_frag_buf *rqb, *sqb; - rqb = &qp->rq.fbc.frag_buf; + rqb = &qp->rq.fbc.frag_buf; *rqb = *buf; rqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); - rqb->npages = 1 << get_order(rqb->size); + rqb->npages = DIV_ROUND_UP(rqb->size, PAGE_SIZE); - sqb = &qp->sq.fbc.frag_buf; - *sqb = *buf; - sqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); - sqb->npages = 1 << get_order(sqb->size); + sq_fbc = &qp->sq.fbc; + sqb = &sq_fbc->frag_buf; + *sqb = *buf; + sqb->size = mlx5_wq_cyc_get_byte_size(&qp->sq); + sqb->npages = DIV_ROUND_UP(sqb->size, PAGE_SIZE); sqb->frags += rqb->npages; /* first part is for the rq */ + if (sq_fbc->strides_offset) + sqb->frags--; } int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) { + u32 sq_strides_offset; int err; mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4, MLX5_GET(qpc, qpc, log_rq_size), &wq->rq.fbc); - mlx5_fill_fbc(ilog2(MLX5_SEND_WQE_BB), - MLX5_GET(qpc, qpc, log_sq_size), - &wq->sq.fbc); + + sq_strides_offset = + ((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB; + + mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB), + MLX5_GET(qpc, qpc, log_sq_size), + sq_strides_offset, + &wq->sq.fbc); err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -156,7 +166,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, goto err_db_free; } - mlx5e_qp_set_frag_buf(&wq_ctrl->buf, wq); + mlx5_qp_set_frag_buf(&wq_ctrl->buf, wq); wq->rq.db = &wq_ctrl->db.db[MLX5_RCV_DBR]; wq->sq.db = &wq_ctrl->db.db[MLX5_SND_DBR]; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index 3c0d882ba183..f6f6a568d66a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -327,12 +327,16 @@ static void mlxsw_afa_resource_add(struct mlxsw_afa_block *block, list_add(&resource->list, &block->resource_list); } +static void mlxsw_afa_resource_del(struct mlxsw_afa_resource *resource) +{ + list_del(&resource->list); +} + static void mlxsw_afa_resources_destroy(struct mlxsw_afa_block *block) { struct mlxsw_afa_resource *resource, *tmp; list_for_each_entry_safe(resource, tmp, &block->resource_list, list) { - list_del(&resource->list); resource->destructor(block, resource); } } @@ -530,6 +534,7 @@ static void mlxsw_afa_fwd_entry_ref_destroy(struct mlxsw_afa_block *block, struct mlxsw_afa_fwd_entry_ref *fwd_entry_ref) { + mlxsw_afa_resource_del(&fwd_entry_ref->resource); mlxsw_afa_fwd_entry_put(block->afa, fwd_entry_ref->fwd_entry); kfree(fwd_entry_ref); } @@ -579,6 +584,7 @@ static void mlxsw_afa_counter_destroy(struct mlxsw_afa_block *block, struct mlxsw_afa_counter *counter) { + mlxsw_afa_resource_del(&counter->resource); block->afa->ops->counter_index_put(block->afa->ops_priv, counter->counter_index); kfree(counter); @@ -626,8 +632,8 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block, char *oneact; char *actions; - if (WARN_ON(block->finished)) - return NULL; + if (block->finished) + return ERR_PTR(-EINVAL); if (block->cur_act_index + action_size > block->afa->max_acts_per_set) { struct mlxsw_afa_set *set; @@ -637,7 +643,7 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block, */ set = mlxsw_afa_set_create(false); if (!set) - return NULL; + return ERR_PTR(-ENOBUFS); set->prev = block->cur_set; block->cur_act_index = 0; block->cur_set->next = set; @@ -724,8 +730,8 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, MLXSW_AFA_VLAN_CODE, MLXSW_AFA_VLAN_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP, MLXSW_AFA_VLAN_CMD_SET_OUTER, vid, MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp, @@ -806,8 +812,8 @@ int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block) MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, 0); return 0; @@ -820,8 +826,8 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id) MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, trap_id); @@ -836,8 +842,8 @@ int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, trap_id); @@ -856,6 +862,7 @@ static void mlxsw_afa_mirror_destroy(struct mlxsw_afa_block *block, struct mlxsw_afa_mirror *mirror) { + mlxsw_afa_resource_del(&mirror->resource); block->afa->ops->mirror_del(block->afa->ops_priv, mirror->local_in_port, mirror->span_id, @@ -908,8 +915,8 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block, char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, 0); mlxsw_afa_trapdisc_mirror_pack(act, true, mirror_agent); @@ -996,8 +1003,8 @@ int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, act = mlxsw_afa_block_append_action(block, MLXSW_AFA_FORWARD_CODE, MLXSW_AFA_FORWARD_SIZE); - if (!act) { - err = -ENOBUFS; + if (IS_ERR(act)) { + err = PTR_ERR(act); goto err_append_action; } mlxsw_afa_forward_pack(act, MLXSW_AFA_FORWARD_TYPE_PBS, @@ -1052,8 +1059,8 @@ int mlxsw_afa_block_append_allocated_counter(struct mlxsw_afa_block *block, { char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_POLCNT_CODE, MLXSW_AFA_POLCNT_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES, counter_index); return 0; @@ -1123,8 +1130,8 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid) char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_VIRFWD_CODE, MLXSW_AFA_VIRFWD_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid); return 0; } @@ -1193,8 +1200,8 @@ int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block, char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_MCROUTER_CODE, MLXSW_AFA_MCROUTER_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_mcrouter_pack(act, MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP, expected_irif, min_mtu, rmid_valid, kvdl_index); return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 6aaaf3d9ba31..77b2adb29341 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -4756,6 +4756,12 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6) kfree(mlxsw_sp_rt6); } +static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt) +{ + /* RTF_CACHE routes are ignored */ + return (rt->fib6_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY; +} + static struct fib6_info * mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry) { @@ -4765,11 +4771,11 @@ mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry) static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, - const struct fib6_info *nrt, bool append) + const struct fib6_info *nrt, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry; - if (!append) + if (!mlxsw_sp_fib6_rt_can_mp(nrt) || replace) return NULL; list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { @@ -4784,7 +4790,8 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, break; if (rt->fib6_metric < nrt->fib6_metric) continue; - if (rt->fib6_metric == nrt->fib6_metric) + if (rt->fib6_metric == nrt->fib6_metric && + mlxsw_sp_fib6_rt_can_mp(rt)) return fib6_entry; if (rt->fib6_metric > nrt->fib6_metric) break; @@ -5163,7 +5170,7 @@ static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node, const struct fib6_info *nrt, bool replace) { - struct mlxsw_sp_fib6_entry *fib6_entry; + struct mlxsw_sp_fib6_entry *fib6_entry, *fallback = NULL; list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); @@ -5172,13 +5179,18 @@ mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node, continue; if (rt->fib6_table->tb6_id != nrt->fib6_table->tb6_id) break; - if (replace && rt->fib6_metric == nrt->fib6_metric) - return fib6_entry; + if (replace && rt->fib6_metric == nrt->fib6_metric) { + if (mlxsw_sp_fib6_rt_can_mp(rt) == + mlxsw_sp_fib6_rt_can_mp(nrt)) + return fib6_entry; + if (mlxsw_sp_fib6_rt_can_mp(nrt)) + fallback = fallback ?: fib6_entry; + } if (rt->fib6_metric > nrt->fib6_metric) - return fib6_entry; + return fallback ?: fib6_entry; } - return NULL; + return fallback; } static int @@ -5304,8 +5316,7 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, - struct fib6_info *rt, bool replace, - bool append) + struct fib6_info *rt, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; @@ -5331,7 +5342,7 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, /* Before creating a new entry, try to append route to an existing * multipath entry. */ - fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, append); + fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, replace); if (fib6_entry) { err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt); if (err) @@ -5339,14 +5350,6 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, return 0; } - /* We received an append event, yet did not find any route to - * append to. - */ - if (WARN_ON(append)) { - err = -EINVAL; - goto err_fib6_entry_append; - } - fib6_entry = mlxsw_sp_fib6_entry_create(mlxsw_sp, fib_node, rt); if (IS_ERR(fib6_entry)) { err = PTR_ERR(fib6_entry); @@ -5364,7 +5367,6 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, err_fib6_node_entry_link: mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry); err_fib6_entry_create: -err_fib6_entry_append: err_fib6_entry_nexthop_add: mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); return err; @@ -5715,7 +5717,7 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) struct mlxsw_sp_fib_event_work *fib_work = container_of(work, struct mlxsw_sp_fib_event_work, work); struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; - bool replace, append; + bool replace; int err; rtnl_lock(); @@ -5726,10 +5728,8 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) case FIB_EVENT_ENTRY_APPEND: /* fall through */ case FIB_EVENT_ENTRY_ADD: replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE; - append = fib_work->event == FIB_EVENT_ENTRY_APPEND; err = mlxsw_sp_router_fib6_add(mlxsw_sp, - fib_work->fen6_info.rt, replace, - append); + fib_work->fen6_info.rt, replace); if (err) mlxsw_sp_router_fib_abort(mlxsw_sp); mlxsw_sp_rt6_release(fib_work->fen6_info.rt); diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index 1decf3a1cad3..e57d23746585 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -80,7 +80,7 @@ nfp_flower_repr_get_type_and_port(struct nfp_app *app, u32 port_id, u8 *port) return NFP_REPR_TYPE_VF; } - return NFP_FLOWER_CMSG_PORT_TYPE_UNSPEC; + return __NFP_REPR_TYPE_MAX; } static struct net_device * @@ -91,6 +91,8 @@ nfp_flower_repr_get(struct nfp_app *app, u32 port_id) u8 port = 0; repr_type = nfp_flower_repr_get_type_and_port(app, port_id, &port); + if (repr_type > NFP_REPR_TYPE_MAX) + return NULL; reprs = rcu_dereference(app->reprs[repr_type]); if (!reprs) diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 78afe75129ab..382bb93cb090 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -317,7 +317,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, payload.dst_ipv4 = flow->daddr; /* If entry has expired send dst IP with all other fields 0. */ - if (!(neigh->nud_state & NUD_VALID)) { + if (!(neigh->nud_state & NUD_VALID) || neigh->dead) { nfp_tun_del_route_from_cache(app, payload.dst_ipv4); /* Trigger ARP to verify invalid neighbour state. */ neigh_event_send(neigh, NULL); diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 00db3401b898..1dfaccd151f0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -502,6 +502,7 @@ enum BAR_ID { struct qed_nvm_image_info { u32 num_images; struct bist_nvm_image_att *image_att; + bool valid; }; #define DRV_MODULE_VERSION \ diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index a14e48489029..4340c4c90bcb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -6723,7 +6723,7 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, format_idx = header & MFW_TRACE_EVENTID_MASK; /* Skip message if its index doesn't exist in the meta data */ - if (format_idx > s_mcp_trace_meta.formats_num) { + if (format_idx >= s_mcp_trace_meta.formats_num) { u8 format_size = (u8)((header & MFW_TRACE_PRM_SIZE_MASK) >> MFW_TRACE_PRM_SIZE_SHIFT); diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 99973e10b179..5ede6408649d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -665,7 +665,7 @@ qed_sp_update_mcast_bin(struct qed_hwfn *p_hwfn, p_ramrod->common.update_approx_mcast_flg = 1; for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) { - u32 *p_bins = (u32 *)p_params->bins; + u32 *p_bins = p_params->bins; p_ramrod->approx_mcast.bins[i] = cpu_to_le32(p_bins[i]); } @@ -1476,8 +1476,8 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn, enum spq_mode comp_mode, struct qed_spq_comp_cb *p_comp_data) { - unsigned long bins[ETH_MULTICAST_MAC_BINS_IN_REGS]; struct vport_update_ramrod_data *p_ramrod = NULL; + u32 bins[ETH_MULTICAST_MAC_BINS_IN_REGS]; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; u8 abs_vport_id = 0; @@ -1513,26 +1513,25 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn, /* explicitly clear out the entire vector */ memset(&p_ramrod->approx_mcast.bins, 0, sizeof(p_ramrod->approx_mcast.bins)); - memset(bins, 0, sizeof(unsigned long) * - ETH_MULTICAST_MAC_BINS_IN_REGS); + memset(bins, 0, sizeof(bins)); /* filter ADD op is explicit set op and it removes * any existing filters for the vport */ if (p_filter_cmd->opcode == QED_FILTER_ADD) { for (i = 0; i < p_filter_cmd->num_mc_addrs; i++) { - u32 bit; + u32 bit, nbits; bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]); - __set_bit(bit, bins); + nbits = sizeof(u32) * BITS_PER_BYTE; + bins[bit / nbits] |= 1 << (bit % nbits); } /* Convert to correct endianity */ for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) { struct vport_update_ramrod_mcast *p_ramrod_bins; - u32 *p_bins = (u32 *)bins; p_ramrod_bins = &p_ramrod->approx_mcast; - p_ramrod_bins->bins[i] = cpu_to_le32(p_bins[i]); + p_ramrod_bins->bins[i] = cpu_to_le32(bins[i]); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index 806a8da257e9..8d80f1095d17 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -215,7 +215,7 @@ struct qed_sp_vport_update_params { u8 anti_spoofing_en; u8 update_accept_any_vlan_flg; u8 accept_any_vlan; - unsigned long bins[8]; + u32 bins[8]; struct qed_rss_params *rss_params; struct qed_filter_accept_flags accept_flags; struct qed_sge_tpa_params *sge_tpa_params; diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 0cbc74d6ca8b..758a9a5127fa 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -371,7 +371,7 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev, goto err2; } - DP_INFO(cdev, "qed_probe completed successffuly\n"); + DP_INFO(cdev, "qed_probe completed successfully\n"); return cdev; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 4e0b443c9519..cdd645024a32 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -592,6 +592,9 @@ int qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn, *o_mcp_resp = mb_params.mcp_resp; *o_mcp_param = mb_params.mcp_param; + /* nvm_info needs to be updated */ + p_hwfn->nvm_info.valid = false; + return 0; } @@ -1208,6 +1211,7 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn, break; default: p_link->speed = 0; + p_link->link_up = 0; } if (p_link->link_up && p_link->speed) @@ -1305,9 +1309,15 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up) phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0; phy_cfg.adv_speed = params->speed.advertised_speeds; phy_cfg.loopback_mode = params->loopback_mode; - if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) { - if (params->eee.enable) - phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED; + + /* There are MFWs that share this capability regardless of whether + * this is feasible or not. And given that at the very least adv_caps + * would be set internally by qed, we want to make sure LFA would + * still work. + */ + if ((p_hwfn->mcp_info->capabilities & + FW_MB_PARAM_FEATURE_SUPPORT_EEE) && params->eee.enable) { + phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED; if (params->eee.tx_lpi_enable) phy_cfg.eee_cfg |= EEE_CFG_TX_LPI; if (params->eee.adv_caps & QED_EEE_1G_ADV) @@ -2555,11 +2565,14 @@ int qed_mcp_bist_nvm_get_image_att(struct qed_hwfn *p_hwfn, int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn) { - struct qed_nvm_image_info *nvm_info = &p_hwfn->nvm_info; + struct qed_nvm_image_info nvm_info; struct qed_ptt *p_ptt; int rc; u32 i; + if (p_hwfn->nvm_info.valid) + return 0; + p_ptt = qed_ptt_acquire(p_hwfn); if (!p_ptt) { DP_ERR(p_hwfn, "failed to acquire ptt\n"); @@ -2567,29 +2580,29 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn) } /* Acquire from MFW the amount of available images */ - nvm_info->num_images = 0; + nvm_info.num_images = 0; rc = qed_mcp_bist_nvm_get_num_images(p_hwfn, - p_ptt, &nvm_info->num_images); + p_ptt, &nvm_info.num_images); if (rc == -EOPNOTSUPP) { DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n"); goto out; - } else if (rc || !nvm_info->num_images) { + } else if (rc || !nvm_info.num_images) { DP_ERR(p_hwfn, "Failed getting number of images\n"); goto err0; } - nvm_info->image_att = kmalloc_array(nvm_info->num_images, - sizeof(struct bist_nvm_image_att), - GFP_KERNEL); - if (!nvm_info->image_att) { + nvm_info.image_att = kmalloc_array(nvm_info.num_images, + sizeof(struct bist_nvm_image_att), + GFP_KERNEL); + if (!nvm_info.image_att) { rc = -ENOMEM; goto err0; } /* Iterate over images and get their attributes */ - for (i = 0; i < nvm_info->num_images; i++) { + for (i = 0; i < nvm_info.num_images; i++) { rc = qed_mcp_bist_nvm_get_image_att(p_hwfn, p_ptt, - &nvm_info->image_att[i], i); + &nvm_info.image_att[i], i); if (rc) { DP_ERR(p_hwfn, "Failed getting image index %d attributes\n", i); @@ -2597,14 +2610,22 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn) } DP_VERBOSE(p_hwfn, QED_MSG_SP, "image index %d, size %x\n", i, - nvm_info->image_att[i].len); + nvm_info.image_att[i].len); } out: + /* Update hwfn's nvm_info */ + if (nvm_info.num_images) { + p_hwfn->nvm_info.num_images = nvm_info.num_images; + kfree(p_hwfn->nvm_info.image_att); + p_hwfn->nvm_info.image_att = nvm_info.image_att; + p_hwfn->nvm_info.valid = true; + } + qed_ptt_release(p_hwfn, p_ptt); return 0; err1: - kfree(nvm_info->image_att); + kfree(nvm_info.image_att); err0: qed_ptt_release(p_hwfn, p_ptt); return rc; @@ -2641,6 +2662,7 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, return -EINVAL; } + qed_mcp_nvm_info_populate(p_hwfn); for (i = 0; i < p_hwfn->nvm_info.num_images; i++) if (type == p_hwfn->nvm_info.image_att[i].image_type) break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index fd59cf45f4be..26e918d7f2f9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -2831,7 +2831,7 @@ qed_iov_vp_update_mcast_bin_param(struct qed_hwfn *p_hwfn, p_data->update_approx_mcast_flg = 1; memcpy(p_data->bins, p_mcast_tlv->bins, - sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS); + sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS); *tlvs_mask |= 1 << QED_IOV_VP_UPDATE_MCAST; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 2d7fcd6a0777..be6ddde1a104 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -1126,7 +1126,7 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, resp_size += sizeof(struct pfvf_def_resp_tlv); memcpy(p_mcast_tlv->bins, p_params->bins, - sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS); + sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS); } update_rx = p_params->accept_flags.update_rx_mode_config; @@ -1272,7 +1272,7 @@ void qed_vf_pf_filter_mcast(struct qed_hwfn *p_hwfn, u32 bit; bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]); - __set_bit(bit, sp_params.bins); + sp_params.bins[bit / 32] |= 1 << (bit % 32); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h index 4f05d5eb3cf5..033409db86ae 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.h +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h @@ -392,7 +392,12 @@ struct vfpf_vport_update_mcast_bin_tlv { struct channel_tlv tl; u8 padding[4]; - u64 bins[8]; + /* There are only 256 approx bins, and in HSI they're divided into + * 32-bit values. As old VFs used to set-bit to the values on its side, + * the upper half of the array is never expected to contain any data. + */ + u64 bins[4]; + u64 obsolete_bins[4]; }; struct vfpf_vport_update_accept_param_tlv { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index 891f03a7a33d..8d7b9bb910f2 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -1128,6 +1128,8 @@ static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp, struct qlcnic_adapter *adapter = dev_get_drvdata(dev); ret = kstrtoul(buf, 16, &data); + if (ret) + return ret; switch (data) { case QLC_83XX_FLASH_SECTOR_ERASE_CMD: diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 5803cd6db406..206f0266463e 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -658,7 +658,7 @@ qcaspi_netdev_open(struct net_device *dev) return ret; } - netif_start_queue(qca->net_dev); + /* SPI thread takes care of TX queue */ return 0; } @@ -760,6 +760,9 @@ qcaspi_netdev_tx_timeout(struct net_device *dev) qca->net_dev->stats.tx_errors++; /* Trigger tx queue flush and QCA7000 reset */ qca->sync = QCASPI_SYNC_UNKNOWN; + + if (qca->spi_thread) + wake_up_process(qca->spi_thread); } static int @@ -878,22 +881,22 @@ qca_spi_probe(struct spi_device *spi) if ((qcaspi_clkspeed < QCASPI_CLK_SPEED_MIN) || (qcaspi_clkspeed > QCASPI_CLK_SPEED_MAX)) { - dev_info(&spi->dev, "Invalid clkspeed: %d\n", - qcaspi_clkspeed); + dev_err(&spi->dev, "Invalid clkspeed: %d\n", + qcaspi_clkspeed); return -EINVAL; } if ((qcaspi_burst_len < QCASPI_BURST_LEN_MIN) || (qcaspi_burst_len > QCASPI_BURST_LEN_MAX)) { - dev_info(&spi->dev, "Invalid burst len: %d\n", - qcaspi_burst_len); + dev_err(&spi->dev, "Invalid burst len: %d\n", + qcaspi_burst_len); return -EINVAL; } if ((qcaspi_pluggable < QCASPI_PLUGGABLE_MIN) || (qcaspi_pluggable > QCASPI_PLUGGABLE_MAX)) { - dev_info(&spi->dev, "Invalid pluggable: %d\n", - qcaspi_pluggable); + dev_err(&spi->dev, "Invalid pluggable: %d\n", + qcaspi_pluggable); return -EINVAL; } @@ -955,8 +958,8 @@ qca_spi_probe(struct spi_device *spi) } if (register_netdev(qcaspi_devs)) { - dev_info(&spi->dev, "Unable to register net device %s\n", - qcaspi_devs->name); + dev_err(&spi->dev, "Unable to register net device %s\n", + qcaspi_devs->name); free_netdev(qcaspi_devs); return -EFAULT; } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index f4cae2be0fda..eaedc11ed686 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -7734,8 +7734,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return rc; } - /* override BIOS settings, use userspace tools to enable WOL */ - __rtl8169_set_wol(tp, 0); + tp->saved_wolopts = __rtl8169_get_wol(tp); if (rtl_tbi_enabled(tp)) { tp->set_speed = rtl8169_set_speed_tbi; @@ -7789,6 +7788,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_HW_VLAN_CTAG_RX; dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | NETIF_F_HIGHDMA; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; tp->cp_cmd |= RxChkSum | RxVlan; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 68f122140966..0d811c02ff34 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -980,6 +980,13 @@ static void ravb_adjust_link(struct net_device *ndev) struct ravb_private *priv = netdev_priv(ndev); struct phy_device *phydev = ndev->phydev; bool new_state = false; + unsigned long flags; + + spin_lock_irqsave(&priv->lock, flags); + + /* Disable TX and RX right over here, if E-MAC change is ignored */ + if (priv->no_avb_link) + ravb_rcv_snd_disable(ndev); if (phydev->link) { if (phydev->duplex != priv->duplex) { @@ -997,18 +1004,21 @@ static void ravb_adjust_link(struct net_device *ndev) ravb_modify(ndev, ECMR, ECMR_TXF, 0); new_state = true; priv->link = phydev->link; - if (priv->no_avb_link) - ravb_rcv_snd_enable(ndev); } } else if (priv->link) { new_state = true; priv->link = 0; priv->speed = 0; priv->duplex = -1; - if (priv->no_avb_link) - ravb_rcv_snd_disable(ndev); } + /* Enable TX and RX right over here, if E-MAC change is ignored */ + if (priv->no_avb_link && phydev->link) + ravb_rcv_snd_enable(ndev); + + mmiowb(); + spin_unlock_irqrestore(&priv->lock, flags); + if (new_state && netif_msg_link(priv)) phy_print_status(phydev); } @@ -1096,75 +1106,6 @@ static int ravb_phy_start(struct net_device *ndev) return 0; } -static int ravb_get_link_ksettings(struct net_device *ndev, - struct ethtool_link_ksettings *cmd) -{ - struct ravb_private *priv = netdev_priv(ndev); - unsigned long flags; - - if (!ndev->phydev) - return -ENODEV; - - spin_lock_irqsave(&priv->lock, flags); - phy_ethtool_ksettings_get(ndev->phydev, cmd); - spin_unlock_irqrestore(&priv->lock, flags); - - return 0; -} - -static int ravb_set_link_ksettings(struct net_device *ndev, - const struct ethtool_link_ksettings *cmd) -{ - struct ravb_private *priv = netdev_priv(ndev); - unsigned long flags; - int error; - - if (!ndev->phydev) - return -ENODEV; - - spin_lock_irqsave(&priv->lock, flags); - - /* Disable TX and RX */ - ravb_rcv_snd_disable(ndev); - - error = phy_ethtool_ksettings_set(ndev->phydev, cmd); - if (error) - goto error_exit; - - if (cmd->base.duplex == DUPLEX_FULL) - priv->duplex = 1; - else - priv->duplex = 0; - - ravb_set_duplex(ndev); - -error_exit: - mdelay(1); - - /* Enable TX and RX */ - ravb_rcv_snd_enable(ndev); - - mmiowb(); - spin_unlock_irqrestore(&priv->lock, flags); - - return error; -} - -static int ravb_nway_reset(struct net_device *ndev) -{ - struct ravb_private *priv = netdev_priv(ndev); - int error = -ENODEV; - unsigned long flags; - - if (ndev->phydev) { - spin_lock_irqsave(&priv->lock, flags); - error = phy_start_aneg(ndev->phydev); - spin_unlock_irqrestore(&priv->lock, flags); - } - - return error; -} - static u32 ravb_get_msglevel(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); @@ -1377,7 +1318,7 @@ static int ravb_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) } static const struct ethtool_ops ravb_ethtool_ops = { - .nway_reset = ravb_nway_reset, + .nway_reset = phy_ethtool_nway_reset, .get_msglevel = ravb_get_msglevel, .set_msglevel = ravb_set_msglevel, .get_link = ethtool_op_get_link, @@ -1387,8 +1328,8 @@ static const struct ethtool_ops ravb_ethtool_ops = { .get_ringparam = ravb_get_ringparam, .set_ringparam = ravb_set_ringparam, .get_ts_info = ravb_get_ts_info, - .get_link_ksettings = ravb_get_link_ksettings, - .set_link_ksettings = ravb_set_link_ksettings, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_wol = ravb_get_wol, .set_wol = ravb_set_wol, }; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index e9007b613f17..5614fd231bbe 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1927,8 +1927,15 @@ static void sh_eth_adjust_link(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); struct phy_device *phydev = ndev->phydev; + unsigned long flags; int new_state = 0; + spin_lock_irqsave(&mdp->lock, flags); + + /* Disable TX and RX right over here, if E-MAC change is ignored */ + if (mdp->cd->no_psr || mdp->no_ether_link) + sh_eth_rcv_snd_disable(ndev); + if (phydev->link) { if (phydev->duplex != mdp->duplex) { new_state = 1; @@ -1947,18 +1954,21 @@ static void sh_eth_adjust_link(struct net_device *ndev) sh_eth_modify(ndev, ECMR, ECMR_TXF, 0); new_state = 1; mdp->link = phydev->link; - if (mdp->cd->no_psr || mdp->no_ether_link) - sh_eth_rcv_snd_enable(ndev); } } else if (mdp->link) { new_state = 1; mdp->link = 0; mdp->speed = 0; mdp->duplex = -1; - if (mdp->cd->no_psr || mdp->no_ether_link) - sh_eth_rcv_snd_disable(ndev); } + /* Enable TX and RX right over here, if E-MAC change is ignored */ + if ((mdp->cd->no_psr || mdp->no_ether_link) && phydev->link) + sh_eth_rcv_snd_enable(ndev); + + mmiowb(); + spin_unlock_irqrestore(&mdp->lock, flags); + if (new_state && netif_msg_link(mdp)) phy_print_status(phydev); } @@ -2030,60 +2040,6 @@ static int sh_eth_phy_start(struct net_device *ndev) return 0; } -static int sh_eth_get_link_ksettings(struct net_device *ndev, - struct ethtool_link_ksettings *cmd) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - unsigned long flags; - - if (!ndev->phydev) - return -ENODEV; - - spin_lock_irqsave(&mdp->lock, flags); - phy_ethtool_ksettings_get(ndev->phydev, cmd); - spin_unlock_irqrestore(&mdp->lock, flags); - - return 0; -} - -static int sh_eth_set_link_ksettings(struct net_device *ndev, - const struct ethtool_link_ksettings *cmd) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - unsigned long flags; - int ret; - - if (!ndev->phydev) - return -ENODEV; - - spin_lock_irqsave(&mdp->lock, flags); - - /* disable tx and rx */ - sh_eth_rcv_snd_disable(ndev); - - ret = phy_ethtool_ksettings_set(ndev->phydev, cmd); - if (ret) - goto error_exit; - - if (cmd->base.duplex == DUPLEX_FULL) - mdp->duplex = 1; - else - mdp->duplex = 0; - - if (mdp->cd->set_duplex) - mdp->cd->set_duplex(ndev); - -error_exit: - mdelay(1); - - /* enable tx and rx */ - sh_eth_rcv_snd_enable(ndev); - - spin_unlock_irqrestore(&mdp->lock, flags); - - return ret; -} - /* If it is ever necessary to increase SH_ETH_REG_DUMP_MAX_REGS, the * version must be bumped as well. Just adding registers up to that * limit is fine, as long as the existing register indices don't @@ -2263,22 +2219,6 @@ static void sh_eth_get_regs(struct net_device *ndev, struct ethtool_regs *regs, pm_runtime_put_sync(&mdp->pdev->dev); } -static int sh_eth_nway_reset(struct net_device *ndev) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - unsigned long flags; - int ret; - - if (!ndev->phydev) - return -ENODEV; - - spin_lock_irqsave(&mdp->lock, flags); - ret = phy_start_aneg(ndev->phydev); - spin_unlock_irqrestore(&mdp->lock, flags); - - return ret; -} - static u32 sh_eth_get_msglevel(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); @@ -2429,7 +2369,7 @@ static int sh_eth_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) static const struct ethtool_ops sh_eth_ethtool_ops = { .get_regs_len = sh_eth_get_regs_len, .get_regs = sh_eth_get_regs, - .nway_reset = sh_eth_nway_reset, + .nway_reset = phy_ethtool_nway_reset, .get_msglevel = sh_eth_get_msglevel, .set_msglevel = sh_eth_set_msglevel, .get_link = ethtool_op_get_link, @@ -2438,8 +2378,8 @@ static const struct ethtool_ops sh_eth_ethtool_ops = { .get_sset_count = sh_eth_get_sset_count, .get_ringparam = sh_eth_get_ringparam, .set_ringparam = sh_eth_set_ringparam, - .get_link_ksettings = sh_eth_get_link_ksettings, - .set_link_ksettings = sh_eth_set_link_ksettings, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_wol = sh_eth_get_wol, .set_wol = sh_eth_set_wol, }; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 23f0785c0573..7eeac3d6cfe8 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -4288,9 +4288,9 @@ static int efx_ef10_filter_pri(struct efx_ef10_filter_table *table, return -EPROTONOSUPPORT; } -static s32 efx_ef10_filter_insert(struct efx_nic *efx, - struct efx_filter_spec *spec, - bool replace_equal) +static s32 efx_ef10_filter_insert_locked(struct efx_nic *efx, + struct efx_filter_spec *spec, + bool replace_equal) { DECLARE_BITMAP(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT); struct efx_ef10_nic_data *nic_data = efx->nic_data; @@ -4307,7 +4307,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx, bool is_mc_recip; s32 rc; - down_read(&efx->filter_sem); + WARN_ON(!rwsem_is_locked(&efx->filter_sem)); table = efx->filter_state; down_write(&table->lock); @@ -4498,10 +4498,22 @@ out_unlock: if (rss_locked) mutex_unlock(&efx->rss_lock); up_write(&table->lock); - up_read(&efx->filter_sem); return rc; } +static s32 efx_ef10_filter_insert(struct efx_nic *efx, + struct efx_filter_spec *spec, + bool replace_equal) +{ + s32 ret; + + down_read(&efx->filter_sem); + ret = efx_ef10_filter_insert_locked(efx, spec, replace_equal); + up_read(&efx->filter_sem); + + return ret; +} + static void efx_ef10_filter_update_rx_scatter(struct efx_nic *efx) { /* no need to do anything here on EF10 */ @@ -5285,7 +5297,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, EFX_WARN_ON_PARANOID(ids[i] != EFX_EF10_FILTER_ID_INVALID); efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); efx_filter_set_eth_local(&spec, vlan->vid, addr_list[i].addr); - rc = efx_ef10_filter_insert(efx, &spec, true); + rc = efx_ef10_filter_insert_locked(efx, &spec, true); if (rc < 0) { if (rollback) { netif_info(efx, drv, efx->net_dev, @@ -5314,7 +5326,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); eth_broadcast_addr(baddr); efx_filter_set_eth_local(&spec, vlan->vid, baddr); - rc = efx_ef10_filter_insert(efx, &spec, true); + rc = efx_ef10_filter_insert_locked(efx, &spec, true); if (rc < 0) { netif_warn(efx, drv, efx->net_dev, "Broadcast filter insert failed rc=%d\n", rc); @@ -5370,7 +5382,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, if (vlan->vid != EFX_FILTER_VID_UNSPEC) efx_filter_set_eth_local(&spec, vlan->vid, NULL); - rc = efx_ef10_filter_insert(efx, &spec, true); + rc = efx_ef10_filter_insert_locked(efx, &spec, true); if (rc < 0) { const char *um = multicast ? "Multicast" : "Unicast"; const char *encap_name = ""; @@ -5430,7 +5442,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, filter_flags, 0); eth_broadcast_addr(baddr); efx_filter_set_eth_local(&spec, vlan->vid, baddr); - rc = efx_ef10_filter_insert(efx, &spec, true); + rc = efx_ef10_filter_insert_locked(efx, &spec, true); if (rc < 0) { netif_warn(efx, drv, efx->net_dev, "Broadcast filter insert failed rc=%d\n", diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 570ec72266f3..ce3a177081a8 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1871,12 +1871,6 @@ static void efx_remove_filters(struct efx_nic *efx) up_write(&efx->filter_sem); } -static void efx_restore_filters(struct efx_nic *efx) -{ - down_read(&efx->filter_sem); - efx->type->filter_table_restore(efx); - up_read(&efx->filter_sem); -} /************************************************************************** * @@ -2688,6 +2682,7 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method) efx_disable_interrupts(efx); mutex_lock(&efx->mac_lock); + down_write(&efx->filter_sem); mutex_lock(&efx->rss_lock); if (efx->port_initialized && method != RESET_TYPE_INVISIBLE && method != RESET_TYPE_DATAPATH) @@ -2745,9 +2740,8 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok) if (efx->type->rx_restore_rss_contexts) efx->type->rx_restore_rss_contexts(efx); mutex_unlock(&efx->rss_lock); - down_read(&efx->filter_sem); - efx_restore_filters(efx); - up_read(&efx->filter_sem); + efx->type->filter_table_restore(efx); + up_write(&efx->filter_sem); if (efx->type->sriov_reset) efx->type->sriov_reset(efx); @@ -2764,6 +2758,7 @@ fail: efx->port_initialized = false; mutex_unlock(&efx->rss_lock); + up_write(&efx->filter_sem); mutex_unlock(&efx->mac_lock); return rc; @@ -3473,7 +3468,9 @@ static int efx_pci_probe_main(struct efx_nic *efx) efx_init_napi(efx); + down_write(&efx->filter_sem); rc = efx->type->init(efx); + up_write(&efx->filter_sem); if (rc) { netif_err(efx, probe, efx->net_dev, "failed to initialise NIC\n"); @@ -3765,7 +3762,9 @@ static int efx_pm_resume(struct device *dev) rc = efx->type->reset(efx, RESET_TYPE_ALL); if (rc) return rc; + down_write(&efx->filter_sem); rc = efx->type->init(efx); + up_write(&efx->filter_sem); if (rc) return rc; rc = efx_pm_thaw(dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 2e6e2a96b4f2..f9a61f90cfbc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -37,7 +37,7 @@ * is done in the "stmmac files" */ -/* struct emac_variant - Descrive dwmac-sun8i hardware variant +/* struct emac_variant - Describe dwmac-sun8i hardware variant * @default_syscon_value: The default value of the EMAC register in syscon * This value is used for disabling properly EMAC * and used as a good starting value in case of the diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 60f59abab009..ef6a8d39db2f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -53,7 +53,7 @@ #include "dwmac1000.h" #include "hwif.h" -#define STMMAC_ALIGN(x) L1_CACHE_ALIGN(x) +#define STMMAC_ALIGN(x) __ALIGN_KERNEL(x, SMP_CACHE_BYTES) #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) /* Module parameters */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 8d375e51a526..6a393b16a1fc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -257,7 +257,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev, return -ENOMEM; /* Enable pci device */ - ret = pcim_enable_device(pdev); + ret = pci_enable_device(pdev); if (ret) { dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__); @@ -300,9 +300,45 @@ static int stmmac_pci_probe(struct pci_dev *pdev, static void stmmac_pci_remove(struct pci_dev *pdev) { stmmac_dvr_remove(&pdev->dev); + pci_disable_device(pdev); } -static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_suspend, stmmac_resume); +static int stmmac_pci_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + ret = stmmac_suspend(dev); + if (ret) + return ret; + + ret = pci_save_state(pdev); + if (ret) + return ret; + + pci_disable_device(pdev); + pci_wake_from_d3(pdev, true); + return 0; +} + +static int stmmac_pci_resume(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + pci_restore_state(pdev); + pci_set_power_state(pdev, PCI_D0); + + ret = pci_enable_device(pdev); + if (ret) + return ret; + + pci_set_master(pdev); + + return stmmac_resume(dev); +} + +static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_pci_suspend, stmmac_pci_resume); /* synthetic ID, no official vendor */ #define PCI_VENDOR_ID_STMMAC 0x700 diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 6d141f3931eb..72da77b94ecd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -94,7 +94,6 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries) /** * stmmac_axi_setup - parse DT parameters for programming the AXI register * @pdev: platform device - * @priv: driver private struct. * Description: * if required, from device-tree the AXI internal register can be tuned * by using platform parameters. diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 358edab9e72e..3e34cb8ac1d3 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2086,14 +2086,16 @@ static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev, int i; for (i = 0; i < cpsw->data.slaves; i++) { - if (vid == cpsw->slaves[i].port_vlan) - return -EINVAL; + if (vid == cpsw->slaves[i].port_vlan) { + ret = -EINVAL; + goto err; + } } } dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid); ret = cpsw_add_vlan_ale_entry(priv, vid); - +err: pm_runtime_put(cpsw->dev); return ret; } @@ -2119,22 +2121,17 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, for (i = 0; i < cpsw->data.slaves; i++) { if (vid == cpsw->slaves[i].port_vlan) - return -EINVAL; + goto err; } } dev_info(priv->dev, "removing vlanid %d from vlan filter\n", vid); ret = cpsw_ale_del_vlan(cpsw->ale, vid, 0); - if (ret != 0) - return ret; - - ret = cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, - HOST_PORT_NUM, ALE_VLAN, vid); - if (ret != 0) - return ret; - - ret = cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, - 0, ALE_VLAN, vid); + ret |= cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, + HOST_PORT_NUM, ALE_VLAN, vid); + ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, + 0, ALE_VLAN, vid); +err: pm_runtime_put(cpsw->dev); return ret; } diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 93dc05c194d3..5766225a4ce1 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -394,7 +394,7 @@ int cpsw_ale_del_mcast(struct cpsw_ale *ale, u8 *addr, int port_mask, idx = cpsw_ale_match_addr(ale, addr, (flags & ALE_VLAN) ? vid : 0); if (idx < 0) - return -EINVAL; + return -ENOENT; cpsw_ale_read(ale, idx, ale_entry); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c index 16c3bfbe1992..757a3b37ae8a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c @@ -218,6 +218,7 @@ issue: ret = of_mdiobus_register(bus, np1); if (ret) { mdiobus_free(bus); + lp->mii_bus = NULL; return ret; } return 0; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 8e9d0ee1572b..31c3d77b4733 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1274,6 +1274,7 @@ int netvsc_poll(struct napi_struct *napi, int budget) struct hv_device *device = netvsc_channel_to_device(channel); struct net_device *ndev = hv_get_drvdata(device); int work_done = 0; + int ret; /* If starting a new interval */ if (!nvchan->desc) @@ -1285,16 +1286,18 @@ int netvsc_poll(struct napi_struct *napi, int budget) nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc); } - /* If send of pending receive completions suceeded - * and did not exhaust NAPI budget this time - * and not doing busy poll + /* Send any pending receive completions */ + ret = send_recv_completions(ndev, net_device, nvchan); + + /* If it did not exhaust NAPI budget this time + * and not doing busy poll * then re-enable host interrupts - * and reschedule if ring is not empty. + * and reschedule if ring is not empty + * or sending receive completion failed. */ - if (send_recv_completions(ndev, net_device, nvchan) == 0 && - work_done < budget && + if (work_done < budget && napi_complete_done(napi, work_done) && - hv_end_read(&channel->inbound) && + (ret || hv_end_read(&channel->inbound)) && napi_schedule_prep(napi)) { hv_begin_read(&channel->inbound); __napi_schedule(napi); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 9b4e3c3787e5..408ece27131c 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1338,6 +1338,7 @@ out: /* setting up multiple channels failed */ net_device->max_chn = 1; net_device->num_chn = 1; + return 0; err_dev_remv: rndis_filter_device_remove(dev, net_device); diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index 64f1b1e77bc0..23a52b9293f3 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -275,6 +275,8 @@ struct adf7242_local { struct spi_message stat_msg; struct spi_transfer stat_xfer; struct dentry *debugfs_root; + struct delayed_work work; + struct workqueue_struct *wqueue; unsigned long flags; int tx_stat; bool promiscuous; @@ -575,10 +577,26 @@ static int adf7242_cmd_rx(struct adf7242_local *lp) /* Wait until the ACK is sent */ adf7242_wait_status(lp, RC_STATUS_PHY_RDY, RC_STATUS_MASK, __LINE__); adf7242_clear_irqstat(lp); + mod_delayed_work(lp->wqueue, &lp->work, msecs_to_jiffies(400)); return adf7242_cmd(lp, CMD_RC_RX); } +static void adf7242_rx_cal_work(struct work_struct *work) +{ + struct adf7242_local *lp = + container_of(work, struct adf7242_local, work.work); + + /* Reissuing RC_RX every 400ms - to adjust for offset + * drift in receiver (datasheet page 61, OCL section) + */ + + if (!test_bit(FLAG_XMIT, &lp->flags)) { + adf7242_cmd(lp, CMD_RC_PHY_RDY); + adf7242_cmd_rx(lp); + } +} + static int adf7242_set_txpower(struct ieee802154_hw *hw, int mbm) { struct adf7242_local *lp = hw->priv; @@ -686,7 +704,7 @@ static int adf7242_start(struct ieee802154_hw *hw) enable_irq(lp->spi->irq); set_bit(FLAG_START, &lp->flags); - return adf7242_cmd(lp, CMD_RC_RX); + return adf7242_cmd_rx(lp); } static void adf7242_stop(struct ieee802154_hw *hw) @@ -694,6 +712,7 @@ static void adf7242_stop(struct ieee802154_hw *hw) struct adf7242_local *lp = hw->priv; disable_irq(lp->spi->irq); + cancel_delayed_work_sync(&lp->work); adf7242_cmd(lp, CMD_RC_IDLE); clear_bit(FLAG_START, &lp->flags); adf7242_clear_irqstat(lp); @@ -719,7 +738,10 @@ static int adf7242_channel(struct ieee802154_hw *hw, u8 page, u8 channel) adf7242_write_reg(lp, REG_CH_FREQ1, freq >> 8); adf7242_write_reg(lp, REG_CH_FREQ2, freq >> 16); - return adf7242_cmd(lp, CMD_RC_RX); + if (test_bit(FLAG_START, &lp->flags)) + return adf7242_cmd_rx(lp); + else + return adf7242_cmd(lp, CMD_RC_PHY_RDY); } static int adf7242_set_hw_addr_filt(struct ieee802154_hw *hw, @@ -814,6 +836,7 @@ static int adf7242_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) /* ensure existing instances of the IRQ handler have completed */ disable_irq(lp->spi->irq); set_bit(FLAG_XMIT, &lp->flags); + cancel_delayed_work_sync(&lp->work); reinit_completion(&lp->tx_complete); adf7242_cmd(lp, CMD_RC_PHY_RDY); adf7242_clear_irqstat(lp); @@ -952,6 +975,7 @@ static irqreturn_t adf7242_isr(int irq, void *data) unsigned int xmit; u8 irq1; + mod_delayed_work(lp->wqueue, &lp->work, msecs_to_jiffies(400)); adf7242_read_reg(lp, REG_IRQ1_SRC1, &irq1); if (!(irq1 & (IRQ_RX_PKT_RCVD | IRQ_CSMA_CA))) @@ -1241,6 +1265,9 @@ static int adf7242_probe(struct spi_device *spi) spi_message_add_tail(&lp->stat_xfer, &lp->stat_msg); spi_set_drvdata(spi, lp); + INIT_DELAYED_WORK(&lp->work, adf7242_rx_cal_work); + lp->wqueue = alloc_ordered_workqueue(dev_name(&spi->dev), + WQ_MEM_RECLAIM); ret = adf7242_hw_init(lp); if (ret) @@ -1284,6 +1311,9 @@ static int adf7242_remove(struct spi_device *spi) if (!IS_ERR_OR_NULL(lp->debugfs_root)) debugfs_remove_recursive(lp->debugfs_root); + cancel_delayed_work_sync(&lp->work); + destroy_workqueue(lp->wqueue); + ieee802154_unregister_hw(lp->hw); mutex_destroy(&lp->bmux); ieee802154_free_hw(lp->hw); diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 77abedf0b524..3d9e91579866 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -940,7 +940,7 @@ at86rf230_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) static int at86rf230_ed(struct ieee802154_hw *hw, u8 *level) { - BUG_ON(!level); + WARN_ON(!level); *level = 0xbe; return 0; } @@ -1121,8 +1121,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw, if (changed & IEEE802154_AFILT_SADDR_CHANGED) { u16 addr = le16_to_cpu(filt->short_addr); - dev_vdbg(&lp->spi->dev, - "at86rf230_set_hw_addr_filt called for saddr\n"); + dev_vdbg(&lp->spi->dev, "%s called for saddr\n", __func__); __at86rf230_write(lp, RG_SHORT_ADDR_0, addr); __at86rf230_write(lp, RG_SHORT_ADDR_1, addr >> 8); } @@ -1130,8 +1129,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw, if (changed & IEEE802154_AFILT_PANID_CHANGED) { u16 pan = le16_to_cpu(filt->pan_id); - dev_vdbg(&lp->spi->dev, - "at86rf230_set_hw_addr_filt called for pan id\n"); + dev_vdbg(&lp->spi->dev, "%s called for pan id\n", __func__); __at86rf230_write(lp, RG_PAN_ID_0, pan); __at86rf230_write(lp, RG_PAN_ID_1, pan >> 8); } @@ -1140,15 +1138,13 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw, u8 i, addr[8]; memcpy(addr, &filt->ieee_addr, 8); - dev_vdbg(&lp->spi->dev, - "at86rf230_set_hw_addr_filt called for IEEE addr\n"); + dev_vdbg(&lp->spi->dev, "%s called for IEEE addr\n", __func__); for (i = 0; i < 8; i++) __at86rf230_write(lp, RG_IEEE_ADDR_0 + i, addr[i]); } if (changed & IEEE802154_AFILT_PANC_CHANGED) { - dev_vdbg(&lp->spi->dev, - "at86rf230_set_hw_addr_filt called for panc change\n"); + dev_vdbg(&lp->spi->dev, "%s called for panc change\n", __func__); if (filt->pan_coord) at86rf230_write_subreg(lp, SR_AACK_I_AM_COORD, 1); else @@ -1252,7 +1248,6 @@ at86rf230_set_cca_mode(struct ieee802154_hw *hw, return at86rf230_write_subreg(lp, SR_CCA_MODE, val); } - static int at86rf230_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm) { diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c index 0d673f7682ee..176395e4b7bb 100644 --- a/drivers/net/ieee802154/fakelb.c +++ b/drivers/net/ieee802154/fakelb.c @@ -49,7 +49,7 @@ struct fakelb_phy { static int fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level) { - BUG_ON(!level); + WARN_ON(!level); *level = 0xbe; return 0; diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index de0d7f28a181..e428277781ac 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -15,10 +15,11 @@ */ #include <linux/kernel.h> #include <linux/module.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/spi/spi.h> #include <linux/workqueue.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/skbuff.h> #include <linux/of_gpio.h> #include <linux/regmap.h> diff --git a/drivers/net/netdevsim/devlink.c b/drivers/net/netdevsim/devlink.c index ba663e5af168..5135fc371f01 100644 --- a/drivers/net/netdevsim/devlink.c +++ b/drivers/net/netdevsim/devlink.c @@ -207,6 +207,7 @@ void nsim_devlink_teardown(struct netdevsim *ns) struct net *net = nsim_to_net(ns); bool *reg_devlink = net_generic(net, nsim_devlink_id); + devlink_resources_unregister(ns->devlink, NULL); devlink_unregister(ns->devlink); devlink_free(ns->devlink); ns->devlink = NULL; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index b8f57e9b9379..1cd439bdf608 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -130,8 +130,9 @@ #define MII_88E1318S_PHY_WOL_CTRL_CLEAR_WOL_STATUS BIT(12) #define MII_88E1318S_PHY_WOL_CTRL_MAGIC_PACKET_MATCH_ENABLE BIT(14) -#define MII_88E1121_PHY_LED_CTRL 16 +#define MII_PHY_LED_CTRL 16 #define MII_88E1121_PHY_LED_DEF 0x0030 +#define MII_88E1510_PHY_LED_DEF 0x1177 #define MII_M1011_PHY_STATUS 0x11 #define MII_M1011_PHY_STATUS_1000 0x8000 @@ -632,8 +633,40 @@ error: return err; } +static void marvell_config_led(struct phy_device *phydev) +{ + u16 def_config; + int err; + + switch (MARVELL_PHY_FAMILY_ID(phydev->phy_id)) { + /* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */ + case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1121R): + case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1318S): + def_config = MII_88E1121_PHY_LED_DEF; + break; + /* Default PHY LED config: + * LED[0] .. 1000Mbps Link + * LED[1] .. 100Mbps Link + * LED[2] .. Blink, Activity + */ + case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1510): + def_config = MII_88E1510_PHY_LED_DEF; + break; + default: + return; + } + + err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE, MII_PHY_LED_CTRL, + def_config); + if (err < 0) + pr_warn("Fail to config marvell phy LED.\n"); +} + static int marvell_config_init(struct phy_device *phydev) { + /* Set defalut LED */ + marvell_config_led(phydev); + /* Set registers from marvell,reg-init DT property */ return marvell_of_reg_init(phydev); } @@ -813,21 +846,6 @@ static int m88e1111_config_init(struct phy_device *phydev) return genphy_soft_reset(phydev); } -static int m88e1121_config_init(struct phy_device *phydev) -{ - int err; - - /* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */ - err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE, - MII_88E1121_PHY_LED_CTRL, - MII_88E1121_PHY_LED_DEF); - if (err < 0) - return err; - - /* Set marvell,reg-init configuration from device tree */ - return marvell_config_init(phydev); -} - static int m88e1318_config_init(struct phy_device *phydev) { if (phy_interrupt_is_valid(phydev)) { @@ -841,7 +859,7 @@ static int m88e1318_config_init(struct phy_device *phydev) return err; } - return m88e1121_config_init(phydev); + return marvell_config_init(phydev); } static int m88e1510_config_init(struct phy_device *phydev) @@ -2087,7 +2105,7 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = &m88e1121_probe, - .config_init = &m88e1121_config_init, + .config_init = &marvell_config_init, .config_aneg = &m88e1121_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c index 0831b7142df7..0c5b68e7da51 100644 --- a/drivers/net/phy/mdio-mux-bcm-iproc.c +++ b/drivers/net/phy/mdio-mux-bcm-iproc.c @@ -218,7 +218,7 @@ out: static int mdio_mux_iproc_remove(struct platform_device *pdev) { - struct iproc_mdiomux_desc *md = dev_get_platdata(&pdev->dev); + struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev); mdio_mux_uninit(md->mux_handle); mdiobus_unregister(md->mii_bus); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 537297d2b4b4..6c9b24fe3148 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -514,7 +514,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync) * negotiation may already be done and aneg interrupt may not be * generated. */ - if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) { + if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) { err = phy_aneg_done(phydev); if (err > 0) { trigger = true; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index bd0f339f69fd..b9f5f40a7ac1 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1724,11 +1724,8 @@ EXPORT_SYMBOL(genphy_loopback); static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) { - /* The default values for phydev->supported are provided by the PHY - * driver "features" member, we want to reset to sane defaults first - * before supporting higher speeds. - */ - phydev->supported &= PHY_DEFAULT_FEATURES; + phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES | + PHY_10BT_FEATURES); switch (max_speed) { default: diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index d437f4f5ed52..740655261e5b 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -349,7 +349,6 @@ static int sfp_register_bus(struct sfp_bus *bus) } if (bus->started) bus->socket_ops->start(bus->sfp); - bus->netdev->sfp_bus = bus; bus->registered = true; return 0; } @@ -364,7 +363,6 @@ static void sfp_unregister_bus(struct sfp_bus *bus) if (bus->phydev && ops && ops->disconnect_phy) ops->disconnect_phy(bus->upstream); } - bus->netdev->sfp_bus = NULL; bus->registered = false; } @@ -436,6 +434,14 @@ void sfp_upstream_stop(struct sfp_bus *bus) } EXPORT_SYMBOL_GPL(sfp_upstream_stop); +static void sfp_upstream_clear(struct sfp_bus *bus) +{ + bus->upstream_ops = NULL; + bus->upstream = NULL; + bus->netdev->sfp_bus = NULL; + bus->netdev = NULL; +} + /** * sfp_register_upstream() - Register the neighbouring device * @fwnode: firmware node for the SFP bus @@ -461,9 +467,13 @@ struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode, bus->upstream_ops = ops; bus->upstream = upstream; bus->netdev = ndev; + ndev->sfp_bus = bus; - if (bus->sfp) + if (bus->sfp) { ret = sfp_register_bus(bus); + if (ret) + sfp_upstream_clear(bus); + } rtnl_unlock(); } @@ -488,8 +498,7 @@ void sfp_unregister_upstream(struct sfp_bus *bus) rtnl_lock(); if (bus->sfp) sfp_unregister_bus(bus); - bus->upstream = NULL; - bus->netdev = NULL; + sfp_upstream_clear(bus); rtnl_unlock(); sfp_bus_put(bus); @@ -561,6 +570,13 @@ void sfp_module_remove(struct sfp_bus *bus) } EXPORT_SYMBOL_GPL(sfp_module_remove); +static void sfp_socket_clear(struct sfp_bus *bus) +{ + bus->sfp_dev = NULL; + bus->sfp = NULL; + bus->socket_ops = NULL; +} + struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp, const struct sfp_socket_ops *ops) { @@ -573,8 +589,11 @@ struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp, bus->sfp = sfp; bus->socket_ops = ops; - if (bus->netdev) + if (bus->netdev) { ret = sfp_register_bus(bus); + if (ret) + sfp_socket_clear(bus); + } rtnl_unlock(); } @@ -592,9 +611,7 @@ void sfp_unregister_socket(struct sfp_bus *bus) rtnl_lock(); if (bus->netdev) sfp_unregister_bus(bus); - bus->sfp_dev = NULL; - bus->sfp = NULL; - bus->socket_ops = NULL; + sfp_socket_clear(bus); rtnl_unlock(); sfp_bus_put(bus); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a192a017cc68..f5727baac84a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1688,7 +1688,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, case XDP_TX: get_page(alloc_frag->page); alloc_frag->offset += buflen; - if (tun_xdp_tx(tun->dev, &xdp)) + if (tun_xdp_tx(tun->dev, &xdp) < 0) goto err_redirect; rcu_read_unlock(); local_bh_enable(); diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 3d4f7959dabb..b1b3d8f7e67d 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -642,10 +642,12 @@ static void ax88772_restore_phy(struct usbnet *dev) priv->presvd_phy_advertise); /* Restore BMCR */ + if (priv->presvd_phy_bmcr & BMCR_ANENABLE) + priv->presvd_phy_bmcr |= BMCR_ANRESTART; + asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_BMCR, priv->presvd_phy_bmcr); - mii_nway_restart(&dev->mii); priv->presvd_phy_advertise = 0; priv->presvd_phy_bmcr = 0; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 2e4130746c40..aeca484a75b8 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1242,6 +1242,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) mod_timer(&dev->stat_monitor, jiffies + STAT_UPDATE_TIMER); } + + tasklet_schedule(&dev->bh); } return ret; @@ -3344,6 +3346,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) pkt_cnt = 0; count = 0; length = 0; + spin_lock_irqsave(&tqp->lock, flags); for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) { if (skb_is_gso(skb)) { if (pkt_cnt) { @@ -3352,7 +3355,8 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) } count = 1; length = skb->len - TX_OVERHEAD; - skb2 = skb_dequeue(tqp); + __skb_unlink(skb, tqp); + spin_unlock_irqrestore(&tqp->lock, flags); goto gso_skb; } @@ -3361,6 +3365,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) skb_totallen = skb->len + roundup(skb_totallen, sizeof(u32)); pkt_cnt++; } + spin_unlock_irqrestore(&tqp->lock, flags); /* copy to a single skb */ skb = alloc_skb(skb_totallen, GFP_ATOMIC); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 8fac8e132c5b..cb0cc30c3d6a 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1246,13 +1246,14 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ - {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e */ + {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ {QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)}, /* SIMCom 7100E, 7230E, 7600E ++ */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)}, /* Quectel EP06 Mini PCIe */ diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 5f565bd574da..48ba80a8ca5c 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -681,7 +681,7 @@ static void rtl8150_set_multicast(struct net_device *netdev) (netdev->flags & IFF_ALLMULTI)) { rx_creg &= 0xfffe; rx_creg |= 0x0002; - dev_info(&netdev->dev, "%s: allmulti set\n", netdev->name); + dev_dbg(&netdev->dev, "%s: allmulti set\n", netdev->name); } else { /* ~RX_MULTICAST, ~RX_PROMISCUOUS */ rx_creg &= 0x00fc; diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 7a6a1fe79309..05553d252446 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -82,6 +82,9 @@ static bool turbo_mode = true; module_param(turbo_mode, bool, 0644); MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction"); +static int smsc75xx_link_ok_nopm(struct usbnet *dev); +static int smsc75xx_phy_gig_workaround(struct usbnet *dev); + static int __must_check __smsc75xx_read_reg(struct usbnet *dev, u32 index, u32 *data, int in_pm) { @@ -852,6 +855,9 @@ static int smsc75xx_phy_initialize(struct usbnet *dev) return -EIO; } + /* phy workaround for gig link */ + smsc75xx_phy_gig_workaround(dev); + smsc75xx_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE, ADVERTISE_ALL | ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM); @@ -987,6 +993,62 @@ static int smsc75xx_wait_ready(struct usbnet *dev, int in_pm) return -EIO; } +static int smsc75xx_phy_gig_workaround(struct usbnet *dev) +{ + struct mii_if_info *mii = &dev->mii; + int ret = 0, timeout = 0; + u32 buf, link_up = 0; + + /* Set the phy in Gig loopback */ + smsc75xx_mdio_write(dev->net, mii->phy_id, MII_BMCR, 0x4040); + + /* Wait for the link up */ + do { + link_up = smsc75xx_link_ok_nopm(dev); + usleep_range(10000, 20000); + timeout++; + } while ((!link_up) && (timeout < 1000)); + + if (timeout >= 1000) { + netdev_warn(dev->net, "Timeout waiting for PHY link up\n"); + return -EIO; + } + + /* phy reset */ + ret = smsc75xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) { + netdev_warn(dev->net, "Failed to read PMT_CTL: %d\n", ret); + return ret; + } + + buf |= PMT_CTL_PHY_RST; + + ret = smsc75xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) { + netdev_warn(dev->net, "Failed to write PMT_CTL: %d\n", ret); + return ret; + } + + timeout = 0; + do { + usleep_range(10000, 20000); + ret = smsc75xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) { + netdev_warn(dev->net, "Failed to read PMT_CTL: %d\n", + ret); + return ret; + } + timeout++; + } while ((buf & PMT_CTL_PHY_RST) && (timeout < 100)); + + if (timeout >= 100) { + netdev_warn(dev->net, "timeout waiting for PHY Reset\n"); + return -EIO; + } + + return 0; +} + static int smsc75xx_reset(struct usbnet *dev) { struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 53085c63277b..2b6ec927809e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -586,7 +586,8 @@ static struct sk_buff *receive_small(struct net_device *dev, struct receive_queue *rq, void *buf, void *ctx, unsigned int len, - unsigned int *xdp_xmit) + unsigned int *xdp_xmit, + unsigned int *rbytes) { struct sk_buff *skb; struct bpf_prog *xdp_prog; @@ -601,6 +602,7 @@ static struct sk_buff *receive_small(struct net_device *dev, int err; len -= vi->hdr_len; + *rbytes += len; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); @@ -705,11 +707,13 @@ static struct sk_buff *receive_big(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, void *buf, - unsigned int len) + unsigned int len, + unsigned int *rbytes) { struct page *page = buf; struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE); + *rbytes += len - vi->hdr_len; if (unlikely(!skb)) goto err; @@ -727,7 +731,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, void *buf, void *ctx, unsigned int len, - unsigned int *xdp_xmit) + unsigned int *xdp_xmit, + unsigned int *rbytes) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); @@ -740,6 +745,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, int err; head_skb = NULL; + *rbytes += len - vi->hdr_len; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); @@ -877,6 +883,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, goto err_buf; } + *rbytes += len; page = virt_to_head_page(buf); truesize = mergeable_ctx_to_truesize(ctx); @@ -932,6 +939,7 @@ err_skb: dev->stats.rx_length_errors++; break; } + *rbytes += len; page = virt_to_head_page(buf); put_page(page); } @@ -942,14 +950,13 @@ xdp_xmit: return NULL; } -static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, - void *buf, unsigned int len, void **ctx, - unsigned int *xdp_xmit) +static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, + void *buf, unsigned int len, void **ctx, + unsigned int *xdp_xmit, unsigned int *rbytes) { struct net_device *dev = vi->dev; struct sk_buff *skb; struct virtio_net_hdr_mrg_rxbuf *hdr; - int ret; if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); @@ -961,23 +968,22 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, } else { put_page(virt_to_head_page(buf)); } - return 0; + return; } if (vi->mergeable_rx_bufs) - skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit); + skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, + rbytes); else if (vi->big_packets) - skb = receive_big(dev, vi, rq, buf, len); + skb = receive_big(dev, vi, rq, buf, len, rbytes); else - skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit); + skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, rbytes); if (unlikely(!skb)) - return 0; + return; hdr = skb_vnet_hdr(skb); - ret = skb->len; - if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -994,12 +1000,11 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, ntohs(skb->protocol), skb->len, skb->pkt_type); napi_gro_receive(&rq->napi, skb); - return ret; + return; frame_err: dev->stats.rx_frame_errors++; dev_kfree_skb(skb); - return 0; } /* Unlike mergeable buffers, all buffers are allocated to the @@ -1249,13 +1254,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget, while (received < budget && (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) { - bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit); + receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &bytes); received++; } } else { while (received < budget && (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) { - bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit); + receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &bytes); received++; } } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index f6bb1d54d4bd..e857cb3335f6 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -636,9 +636,62 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); } -/* Add new entry to forwarding table -- assumes lock held */ +static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, + const u8 *mac, __u16 state, + __be32 src_vni, __u8 ndm_flags) +{ + struct vxlan_fdb *f; + + f = kmalloc(sizeof(*f), GFP_ATOMIC); + if (!f) + return NULL; + f->state = state; + f->flags = ndm_flags; + f->updated = f->used = jiffies; + f->vni = src_vni; + INIT_LIST_HEAD(&f->remotes); + memcpy(f->eth_addr, mac, ETH_ALEN); + + return f; +} + static int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, + __u16 state, __be16 port, __be32 src_vni, + __be32 vni, __u32 ifindex, __u8 ndm_flags, + struct vxlan_fdb **fdb) +{ + struct vxlan_rdst *rd = NULL; + struct vxlan_fdb *f; + int rc; + + if (vxlan->cfg.addrmax && + vxlan->addrcnt >= vxlan->cfg.addrmax) + return -ENOSPC; + + netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); + f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags); + if (!f) + return -ENOMEM; + + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + if (rc < 0) { + kfree(f); + return rc; + } + + ++vxlan->addrcnt; + hlist_add_head_rcu(&f->hlist, + vxlan_fdb_head(vxlan, mac, src_vni)); + + *fdb = f; + + return 0; +} + +/* Add new entry to forwarding table -- assumes lock held */ +static int vxlan_fdb_update(struct vxlan_dev *vxlan, + const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u8 ndm_flags) @@ -687,37 +740,17 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, if (!(flags & NLM_F_CREATE)) return -ENOENT; - if (vxlan->cfg.addrmax && - vxlan->addrcnt >= vxlan->cfg.addrmax) - return -ENOSPC; - /* Disallow replace to add a multicast entry */ if ((flags & NLM_F_REPLACE) && (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) return -EOPNOTSUPP; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); - f = kmalloc(sizeof(*f), GFP_ATOMIC); - if (!f) - return -ENOMEM; - - notify = 1; - f->state = state; - f->flags = ndm_flags; - f->updated = f->used = jiffies; - f->vni = src_vni; - INIT_LIST_HEAD(&f->remotes); - memcpy(f->eth_addr, mac, ETH_ALEN); - - rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); - if (rc < 0) { - kfree(f); + rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni, + vni, ifindex, ndm_flags, &f); + if (rc < 0) return rc; - } - - ++vxlan->addrcnt; - hlist_add_head_rcu(&f->hlist, - vxlan_fdb_head(vxlan, mac, src_vni)); + notify = 1; } if (notify) { @@ -741,13 +774,15 @@ static void vxlan_fdb_free(struct rcu_head *head) kfree(f); } -static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f) +static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, + bool do_notify) { netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr); --vxlan->addrcnt; - vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH); + if (do_notify) + vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH); hlist_del_rcu(&f->hlist); call_rcu(&f->rcu, vxlan_fdb_free); @@ -863,7 +898,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EAFNOSUPPORT; spin_lock_bh(&vxlan->hash_lock); - err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags, + err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags); spin_unlock_bh(&vxlan->hash_lock); @@ -897,7 +932,7 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan, goto out; } - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); out: return 0; @@ -1006,7 +1041,7 @@ static bool vxlan_snoop(struct net_device *dev, /* close off race between vxlan_flush and incoming packets */ if (netif_running(dev)) - vxlan_fdb_create(vxlan, src_mac, src_ip, + vxlan_fdb_update(vxlan, src_mac, src_ip, NUD_REACHABLE, NLM_F_EXCL|NLM_F_CREATE, vxlan->cfg.dst_port, @@ -2364,7 +2399,7 @@ static void vxlan_cleanup(struct timer_list *t) "garbage collect %pM\n", f->eth_addr); f->state = NUD_STALE; - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); } else if (time_before(timeout, next_timer)) next_timer = timeout; } @@ -2415,7 +2450,7 @@ static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni) spin_lock_bh(&vxlan->hash_lock); f = __vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f) - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); spin_unlock_bh(&vxlan->hash_lock); } @@ -2469,7 +2504,7 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all) continue; /* the all_zeros_mac entry is deleted at vxlan_uninit */ if (!is_zero_ether_addr(f->eth_addr)) - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); } } spin_unlock_bh(&vxlan->hash_lock); @@ -3160,6 +3195,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_fdb *f = NULL; int err; err = vxlan_dev_configure(net, dev, conf, false, extack); @@ -3173,24 +3209,35 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, err = vxlan_fdb_create(vxlan, all_zeros_mac, &vxlan->default_dst.remote_ip, NUD_REACHABLE | NUD_PERMANENT, - NLM_F_EXCL | NLM_F_CREATE, vxlan->cfg.dst_port, vxlan->default_dst.remote_vni, vxlan->default_dst.remote_vni, vxlan->default_dst.remote_ifindex, - NTF_SELF); + NTF_SELF, &f); if (err) return err; } err = register_netdevice(dev); + if (err) + goto errout; + + err = rtnl_configure_link(dev, NULL); if (err) { - vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni); - return err; + unregister_netdevice(dev); + goto errout; } + /* notify default fdb entry */ + if (f) + vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH); + list_add(&vxlan->next, &vn->vxlan_list); return 0; +errout: + if (f) + vxlan_fdb_destroy(vxlan, f, false); + return err; } static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], @@ -3425,6 +3472,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct vxlan_rdst *dst = &vxlan->default_dst; struct vxlan_rdst old_dst; struct vxlan_config conf; + struct vxlan_fdb *f = NULL; int err; err = vxlan_nl2conf(tb, data, @@ -3453,16 +3501,16 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], err = vxlan_fdb_create(vxlan, all_zeros_mac, &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, - NLM_F_CREATE | NLM_F_APPEND, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, - NTF_SELF); + NTF_SELF, &f); if (err) { spin_unlock_bh(&vxlan->hash_lock); return err; } + vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH); } spin_unlock_bh(&vxlan->hash_lock); } diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c index 90a4ad9a2d08..b3a1b6f5c406 100644 --- a/drivers/net/wan/lmc/lmc_main.c +++ b/drivers/net/wan/lmc/lmc_main.c @@ -1362,7 +1362,7 @@ static irqreturn_t lmc_interrupt (int irq, void *dev_instance) /*fold00*/ case 0x001: printk(KERN_WARNING "%s: Master Abort (naughty)\n", dev->name); break; - case 0x010: + case 0x002: printk(KERN_WARNING "%s: Target Abort (not so naughty)\n", dev->name); break; default: diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index e9c2fb318c03..836e0a47b94a 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -6058,8 +6058,19 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk) ath10k_mac_max_vht_nss(vht_mcs_mask))); if (changed & IEEE80211_RC_BW_CHANGED) { - ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d\n", - sta->addr, bw); + enum wmi_phy_mode mode; + + mode = chan_to_phymode(&def); + ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d phymode %d\n", + sta->addr, bw, mode); + + err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr, + WMI_PEER_PHYMODE, mode); + if (err) { + ath10k_warn(ar, "failed to update STA %pM peer phymode %d: %d\n", + sta->addr, mode, err); + goto exit; + } err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr, WMI_PEER_CHAN_WIDTH, bw); @@ -6100,6 +6111,7 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk) sta->addr); } +exit: mutex_unlock(&ar->conf_mutex); } diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h index b48db54e9865..d68afb65402a 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.h +++ b/drivers/net/wireless/ath/ath10k/wmi.h @@ -6144,6 +6144,7 @@ enum wmi_peer_param { WMI_PEER_NSS = 0x5, WMI_PEER_USE_4ADDR = 0x6, WMI_PEER_DEBUG = 0xa, + WMI_PEER_PHYMODE = 0xd, WMI_PEER_DUMMY_VAR = 0xff, /* dummy parameter for STA PS workaround */ }; diff --git a/drivers/net/wireless/ath/wcn36xx/testmode.c b/drivers/net/wireless/ath/wcn36xx/testmode.c index 1279064a3b71..51a038022c8b 100644 --- a/drivers/net/wireless/ath/wcn36xx/testmode.c +++ b/drivers/net/wireless/ath/wcn36xx/testmode.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (c) 2018, The Linux Foundation. All rights reserved. * * Permission to use, copy, modify, and/or distribute this software for any diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 45928b5b8d97..4fffa6988087 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -1785,7 +1785,8 @@ brcmf_pcie_prepare_fw_request(struct brcmf_pciedev_info *devinfo) fwreq->items[BRCMF_PCIE_FW_CODE].type = BRCMF_FW_TYPE_BINARY; fwreq->items[BRCMF_PCIE_FW_NVRAM].type = BRCMF_FW_TYPE_NVRAM; fwreq->items[BRCMF_PCIE_FW_NVRAM].flags = BRCMF_FW_REQF_OPTIONAL; - fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus); + /* NVRAM reserves PCI domain 0 for Broadcom's SDK faked bus */ + fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus) + 1; fwreq->bus_nr = devinfo->pdev->bus->number; return fwreq; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index c99a191e8d69..a907d7b065fa 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -4296,6 +4296,13 @@ void brcmf_sdio_remove(struct brcmf_sdio *bus) brcmf_dbg(TRACE, "Enter\n"); if (bus) { + /* Stop watchdog task */ + if (bus->watchdog_tsk) { + send_sig(SIGTERM, bus->watchdog_tsk, 1); + kthread_stop(bus->watchdog_tsk); + bus->watchdog_tsk = NULL; + } + /* De-register interrupt handler */ brcmf_sdiod_intr_unregister(bus->sdiodev); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c index e20c30b29c03..c8ea63d02619 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c @@ -178,6 +178,17 @@ const struct iwl_cfg iwl9260_2ac_cfg = { .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, }; +const struct iwl_cfg iwl9260_killer_2ac_cfg = { + .name = "Killer (R) Wireless-AC 1550 Wireless Network Adapter (9260NGW)", + .fw_name_pre = IWL9260A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, +}; + const struct iwl_cfg iwl9270_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9270", .fw_name_pre = IWL9260A_FW_PRE, @@ -267,6 +278,34 @@ const struct iwl_cfg iwl9560_2ac_cfg_soc = { .soc_latency = 5000, }; +const struct iwl_cfg iwl9560_killer_2ac_cfg_soc = { + .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, +}; + +const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc = { + .name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, +}; + const struct iwl_cfg iwl9460_2ac_cfg_shared_clk = { .name = "Intel(R) Dual Band Wireless AC 9460", .fw_name_pre = IWL9000A_FW_PRE, @@ -327,6 +366,36 @@ const struct iwl_cfg iwl9560_2ac_cfg_shared_clk = { .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK }; +const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk = { + .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, + .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK +}; + +const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk = { + .name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, + .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK +}; + MODULE_FIRMWARE(IWL9000A_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL9000B_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL9000RFB_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index c503b26793f6..84a816809723 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -551,6 +551,7 @@ extern const struct iwl_cfg iwl8275_2ac_cfg; extern const struct iwl_cfg iwl4165_2ac_cfg; extern const struct iwl_cfg iwl9160_2ac_cfg; extern const struct iwl_cfg iwl9260_2ac_cfg; +extern const struct iwl_cfg iwl9260_killer_2ac_cfg; extern const struct iwl_cfg iwl9270_2ac_cfg; extern const struct iwl_cfg iwl9460_2ac_cfg; extern const struct iwl_cfg iwl9560_2ac_cfg; @@ -558,10 +559,14 @@ extern const struct iwl_cfg iwl9460_2ac_cfg_soc; extern const struct iwl_cfg iwl9461_2ac_cfg_soc; extern const struct iwl_cfg iwl9462_2ac_cfg_soc; extern const struct iwl_cfg iwl9560_2ac_cfg_soc; +extern const struct iwl_cfg iwl9560_killer_2ac_cfg_soc; +extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc; extern const struct iwl_cfg iwl9460_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9461_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9462_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9560_2ac_cfg_shared_clk; +extern const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk; +extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl22000_2ac_cfg_hr; extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb; extern const struct iwl_cfg iwl22000_2ac_cfg_jf; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 38234bda9017..8520523b91b4 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -545,6 +545,9 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x1210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x1410, iwl9270_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x1420, iwl9460_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x1550, iwl9260_killer_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x1610, iwl9270_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x2034, iwl9560_2ac_cfg_soc)}, @@ -554,6 +557,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0010, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0014, iwl9160_2ac_cfg)}, @@ -578,6 +582,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2720, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2720, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2720, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2720, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_cfg)}, @@ -604,6 +610,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x30DC, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x30DC, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -630,6 +638,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x31DC, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x31DC, 0x1030, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x31DC, 0x1551, iwl9560_killer_s_2ac_cfg_shared_clk)}, + {IWL_PCI_DEVICE(0x31DC, 0x1552, iwl9560_killer_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x2030, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x2034, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x4030, iwl9560_2ac_cfg_shared_clk)}, @@ -656,6 +666,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x34F0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x34F0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x34F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x34F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -682,6 +694,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x3DF0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x3DF0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x3DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -708,6 +722,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x43F0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x43F0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x43F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x43F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -743,6 +759,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x9DF0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x9DF0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x9DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x9DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2010, iwl9460_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2034, iwl9560_2ac_cfg_soc)}, @@ -771,6 +789,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0xA0F0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0xA0F0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -797,6 +817,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0xA370, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0xA370, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0xA370, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA370, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x4030, iwl9560_2ac_cfg_soc)}, diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c index 6e3cf9817730..88f4c89f89ba 100644 --- a/drivers/net/wireless/marvell/mwifiex/usb.c +++ b/drivers/net/wireless/marvell/mwifiex/usb.c @@ -644,11 +644,6 @@ static void mwifiex_usb_disconnect(struct usb_interface *intf) MWIFIEX_FUNC_SHUTDOWN); } - if (adapter->workqueue) - flush_workqueue(adapter->workqueue); - - mwifiex_usb_free(card); - mwifiex_dbg(adapter, FATAL, "%s: removing card\n", __func__); mwifiex_remove_card(adapter); @@ -1356,6 +1351,8 @@ static void mwifiex_unregister_dev(struct mwifiex_adapter *adapter) { struct usb_card_rec *card = (struct usb_card_rec *)adapter->card; + mwifiex_usb_free(card); + mwifiex_usb_cleanup_tx_aggr(adapter); card->adapter = NULL; diff --git a/drivers/net/wireless/mediatek/mt7601u/phy.c b/drivers/net/wireless/mediatek/mt7601u/phy.c index 9d2f9a776ef1..b804abd464ae 100644 --- a/drivers/net/wireless/mediatek/mt7601u/phy.c +++ b/drivers/net/wireless/mediatek/mt7601u/phy.c @@ -986,13 +986,15 @@ static void mt7601u_agc_tune(struct mt7601u_dev *dev) */ spin_lock_bh(&dev->con_mon_lock); avg_rssi = ewma_rssi_read(&dev->avg_rssi); - WARN_ON_ONCE(avg_rssi == 0); + spin_unlock_bh(&dev->con_mon_lock); + if (avg_rssi == 0) + return; + avg_rssi = -avg_rssi; if (avg_rssi <= -70) val -= 0x20; else if (avg_rssi <= -60) val -= 0x10; - spin_unlock_bh(&dev->con_mon_lock); if (val != mt7601u_bbp_rr(dev, 66)) mt7601u_bbp_wr(dev, 66, val); diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c index 220e2b710208..ae0ca8006849 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c @@ -654,8 +654,7 @@ qtnf_disconnect(struct wiphy *wiphy, struct net_device *dev, vif = qtnf_mac_get_base_vif(mac); if (!vif) { pr_err("MAC%u: primary VIF is not configured\n", mac->macid); - ret = -EFAULT; - goto out; + return -EFAULT; } if (vif->wdev.iftype != NL80211_IFTYPE_STATION) { diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index 39c817eddd78..54c9f6ab0c8c 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -484,18 +484,21 @@ static void _rtl_init_deferred_work(struct ieee80211_hw *hw) } -void rtl_deinit_deferred_work(struct ieee80211_hw *hw) +void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq) { struct rtl_priv *rtlpriv = rtl_priv(hw); del_timer_sync(&rtlpriv->works.watchdog_timer); - cancel_delayed_work(&rtlpriv->works.watchdog_wq); - cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); - cancel_delayed_work(&rtlpriv->works.ps_work); - cancel_delayed_work(&rtlpriv->works.ps_rfon_wq); - cancel_delayed_work(&rtlpriv->works.fwevt_wq); - cancel_delayed_work(&rtlpriv->works.c2hcmd_wq); + cancel_delayed_work_sync(&rtlpriv->works.watchdog_wq); + if (ips_wq) + cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); + else + cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq); + cancel_delayed_work_sync(&rtlpriv->works.ps_work); + cancel_delayed_work_sync(&rtlpriv->works.ps_rfon_wq); + cancel_delayed_work_sync(&rtlpriv->works.fwevt_wq); + cancel_delayed_work_sync(&rtlpriv->works.c2hcmd_wq); } EXPORT_SYMBOL_GPL(rtl_deinit_deferred_work); diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h index 912f205779c3..a7ae40eaa3cd 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.h +++ b/drivers/net/wireless/realtek/rtlwifi/base.h @@ -121,7 +121,7 @@ void rtl_init_rfkill(struct ieee80211_hw *hw); void rtl_deinit_rfkill(struct ieee80211_hw *hw); void rtl_watch_dog_timer_callback(struct timer_list *t); -void rtl_deinit_deferred_work(struct ieee80211_hw *hw); +void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq); bool rtl_action_proc(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx); int rtlwifi_rate_mapping(struct ieee80211_hw *hw, bool isht, diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c index cfea57efa7f4..4bf7967590ca 100644 --- a/drivers/net/wireless/realtek/rtlwifi/core.c +++ b/drivers/net/wireless/realtek/rtlwifi/core.c @@ -130,7 +130,6 @@ found_alt: firmware->size); rtlpriv->rtlhal.wowlan_fwsize = firmware->size; } - rtlpriv->rtlhal.fwsize = firmware->size; release_firmware(firmware); } @@ -196,7 +195,7 @@ static void rtl_op_stop(struct ieee80211_hw *hw) /* reset sec info */ rtl_cam_reset_sec_info(hw); - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); } rtlpriv->intf_ops->adapter_stop(hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index ae13bcfb3bf0..5d1fda16fc8c 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -2377,7 +2377,7 @@ void rtl_pci_disconnect(struct pci_dev *pdev) ieee80211_unregister_hw(hw); rtlmac->mac80211_registered = 0; } else { - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); rtlpriv->intf_ops->adapter_stop(hw); } rtlpriv->cfg->ops->disable_interrupt(hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.c b/drivers/net/wireless/realtek/rtlwifi/ps.c index 71af24e2e051..479a4cfc245d 100644 --- a/drivers/net/wireless/realtek/rtlwifi/ps.c +++ b/drivers/net/wireless/realtek/rtlwifi/ps.c @@ -71,7 +71,7 @@ bool rtl_ps_disable_nic(struct ieee80211_hw *hw) struct rtl_priv *rtlpriv = rtl_priv(hw); /*<1> Stop all timer */ - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, true); /*<2> Disable Interrupt */ rtlpriv->cfg->ops->disable_interrupt(hw); @@ -292,7 +292,7 @@ void rtl_ips_nic_on(struct ieee80211_hw *hw) struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); enum rf_pwrstate rtstate; - cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); + cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq); mutex_lock(&rtlpriv->locks.ips_mutex); if (ppsc->inactiveps) { diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index f9faffc498bc..2ac5004d7a40 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -1132,7 +1132,7 @@ void rtl_usb_disconnect(struct usb_interface *intf) ieee80211_unregister_hw(hw); rtlmac->mac80211_registered = 0; } else { - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); rtlpriv->intf_ops->adapter_stop(hw); } /*deinit rfkill */ diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index a57daecf1d57..9dd2ca62d84a 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -87,6 +87,7 @@ struct netfront_cb { /* IRQ name is queue name with "-tx" or "-rx" appended */ #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3) +static DECLARE_WAIT_QUEUE_HEAD(module_load_q); static DECLARE_WAIT_QUEUE_HEAD(module_unload_q); struct netfront_stats { @@ -893,7 +894,6 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, struct sk_buff *skb, struct sk_buff_head *list) { - struct skb_shared_info *shinfo = skb_shinfo(skb); RING_IDX cons = queue->rx.rsp_cons; struct sk_buff *nskb; @@ -902,15 +902,16 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, RING_GET_RESPONSE(&queue->rx, ++cons); skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0]; - if (shinfo->nr_frags == MAX_SKB_FRAGS) { + if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) { unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to; BUG_ON(pull_to <= skb_headlen(skb)); __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } - BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS); + BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS); - skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag), + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + skb_frag_page(nfrag), rx->offset, rx->status, PAGE_SIZE); skb_shinfo(nskb)->nr_frags = 0; @@ -1330,6 +1331,11 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) netif_carrier_off(netdev); xenbus_switch_state(dev, XenbusStateInitialising); + wait_event(module_load_q, + xenbus_read_driver_state(dev->otherend) != + XenbusStateClosed && + xenbus_read_driver_state(dev->otherend) != + XenbusStateUnknown); return netdev; exit: diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c index a59b6c4bb5b8..ad3d17c42e23 100644 --- a/drivers/nubus/bus.c +++ b/drivers/nubus/bus.c @@ -5,6 +5,7 @@ // Copyright (C) 2017 Finn Thain #include <linux/device.h> +#include <linux/dma-mapping.h> #include <linux/list.h> #include <linux/nubus.h> #include <linux/seq_file.h> @@ -93,6 +94,8 @@ int nubus_device_register(struct nubus_board *board) board->dev.release = nubus_device_release; board->dev.bus = &nubus_bus_type; dev_set_name(&board->dev, "slot.%X", board->slot); + board->dev.dma_mask = &board->dev.coherent_dma_mask; + dma_set_mask(&board->dev, DMA_BIT_MASK(32)); return device_register(&board->dev); } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 46df030b2c3f..bf65501e6ed6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -100,6 +100,22 @@ static struct class *nvme_subsys_class; static void nvme_ns_remove(struct nvme_ns *ns); static int nvme_revalidate_disk(struct gendisk *disk); static void nvme_put_subsystem(struct nvme_subsystem *subsys); +static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, + unsigned nsid); + +static void nvme_set_queue_dying(struct nvme_ns *ns) +{ + /* + * Revalidating a dead namespace sets capacity to 0. This will end + * buffered writers dirtying pages that can't be synced. + */ + if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags)) + return; + revalidate_disk(ns->disk); + blk_set_queue_dying(ns->queue); + /* Forcibly unquiesce queues to avoid blocking dispatch */ + blk_mq_unquiesce_queue(ns->queue); +} static void nvme_queue_scan(struct nvme_ctrl *ctrl) { @@ -1044,14 +1060,17 @@ EXPORT_SYMBOL_GPL(nvme_set_queue_count); static void nvme_enable_aen(struct nvme_ctrl *ctrl) { - u32 result; + u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED; int status; - status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, - ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result); + if (!supported_aens) + return; + + status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens, + NULL, 0, &result); if (status) dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n", - ctrl->oaes & NVME_AEN_SUPPORTED); + supported_aens); } static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) @@ -1151,19 +1170,15 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, static void nvme_update_formats(struct nvme_ctrl *ctrl) { - struct nvme_ns *ns, *next; - LIST_HEAD(rm_list); + struct nvme_ns *ns; - down_write(&ctrl->namespaces_rwsem); - list_for_each_entry(ns, &ctrl->namespaces, list) { - if (ns->disk && nvme_revalidate_disk(ns->disk)) { - list_move_tail(&ns->list, &rm_list); - } - } - up_write(&ctrl->namespaces_rwsem); + down_read(&ctrl->namespaces_rwsem); + list_for_each_entry(ns, &ctrl->namespaces, list) + if (ns->disk && nvme_revalidate_disk(ns->disk)) + nvme_set_queue_dying(ns); + up_read(&ctrl->namespaces_rwsem); - list_for_each_entry_safe(ns, next, &rm_list, list) - nvme_ns_remove(ns); + nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL); } static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) @@ -1218,7 +1233,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, effects = nvme_passthru_start(ctrl, ns, cmd.opcode); status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, (void __user *)(uintptr_t)cmd.addr, cmd.data_len, - (void __user *)(uintptr_t)cmd.metadata, cmd.metadata, + (void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len, 0, &cmd.result, timeout); nvme_passthru_end(ctrl, effects); @@ -3138,7 +3153,7 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, down_write(&ctrl->namespaces_rwsem); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) { - if (ns->head->ns_id > nsid) + if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags)) list_move_tail(&ns->list, &rm_list); } up_write(&ctrl->namespaces_rwsem); @@ -3542,19 +3557,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) if (ctrl->admin_q) blk_mq_unquiesce_queue(ctrl->admin_q); - list_for_each_entry(ns, &ctrl->namespaces, list) { - /* - * Revalidating a dead namespace sets capacity to 0. This will - * end buffered writers dirtying pages that can't be synced. - */ - if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags)) - continue; - revalidate_disk(ns->disk); - blk_set_queue_dying(ns->queue); + list_for_each_entry(ns, &ctrl->namespaces, list) + nvme_set_queue_dying(ns); - /* Forcibly unquiesce queues to avoid blocking dispatch */ - blk_mq_unquiesce_queue(ns->queue); - } up_read(&ctrl->namespaces_rwsem); } EXPORT_SYMBOL_GPL(nvme_kill_queues); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 903eb4545e26..f7efe5a58cc7 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -539,14 +539,18 @@ static struct nvmf_transport_ops *nvmf_lookup_transport( /* * For something we're not in a state to send to the device the default action * is to busy it and retry it after the controller state is recovered. However, - * anything marked for failfast or nvme multipath is immediately failed. + * if the controller is deleting or if anything is marked for failfast or + * nvme multipath it is immediately failed. * * Note: commands used to initialize the controller will be marked for failfast. * Note: nvme cli/ioctl commands are marked for failfast. */ -blk_status_t nvmf_fail_nonready_command(struct request *rq) +blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, + struct request *rq) { - if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) + if (ctrl->state != NVME_CTRL_DELETING && + ctrl->state != NVME_CTRL_DEAD && + !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) return BLK_STS_RESOURCE; nvme_req(rq)->status = NVME_SC_ABORT_REQ; return BLK_STS_IOERR; diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index e1818a27aa2d..aa2fdb2a2e8f 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -162,7 +162,8 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops); void nvmf_free_options(struct nvmf_ctrl_options *opts); int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size); bool nvmf_should_reconnect(struct nvme_ctrl *ctrl); -blk_status_t nvmf_fail_nonready_command(struct request *rq); +blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, + struct request *rq); bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq, bool queue_live); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 41d45a1b5c62..9bac912173ba 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2272,7 +2272,7 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx, if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE || !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready)) - return nvmf_fail_nonready_command(rq); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq); ret = nvme_setup_cmd(ns, rq, sqe); if (ret) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ba943f211687..ddd441b1516a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2556,11 +2556,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) quirks |= check_vendor_combination_bug(pdev); - result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, - quirks); - if (result) - goto release_pools; - /* * Double check that our mempool alloc size will cover the biggest * command we support. @@ -2578,6 +2573,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto release_pools; } + result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, + quirks); + if (result) + goto release_mempool; + dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev)); nvme_get_ctrl(&dev->ctrl); @@ -2585,6 +2585,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; + release_mempool: + mempool_destroy(dev->iod_mempool); release_pools: nvme_release_prp_pools(dev); unmap: diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 518c5b09038c..66ec5985c9f3 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1639,7 +1639,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, WARN_ON_ONCE(rq->tag < 0); if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready)) - return nvmf_fail_nonready_command(rq); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq); dev = queue->device->dev; ib_dma_sync_single_for_cpu(dev, sqe->dma, diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index d3f3b3ec4d1a..ebea1373d1b7 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -282,6 +282,7 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item, { struct nvmet_ns *ns = to_nvmet_ns(item); struct nvmet_subsys *subsys = ns->subsys; + size_t len; int ret; mutex_lock(&subsys->lock); @@ -289,10 +290,14 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item, if (ns->enabled) goto out_unlock; - kfree(ns->device_path); + ret = -EINVAL; + len = strcspn(page, "\n"); + if (!len) + goto out_unlock; + kfree(ns->device_path); ret = -ENOMEM; - ns->device_path = kstrndup(page, strcspn(page, "\n"), GFP_KERNEL); + ns->device_path = kstrndup(page, len, GFP_KERNEL); if (!ns->device_path) goto out_unlock; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 74d4b785d2da..9838103f2d62 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -339,7 +339,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns) goto out_unlock; ret = nvmet_bdev_ns_enable(ns); - if (ret) + if (ret == -ENOTBLK) ret = nvmet_file_ns_enable(ns); if (ret) goto out_unlock; diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 408279cb6f2c..29b4b236afd8 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -58,8 +58,8 @@ struct nvmet_fc_ls_iod { struct work_struct work; } __aligned(sizeof(unsigned long long)); +/* desired maximum for a single sequence - if sg list allows it */ #define NVMET_FC_MAX_SEQ_LENGTH (256 * 1024) -#define NVMET_FC_MAX_XFR_SGENTS (NVMET_FC_MAX_SEQ_LENGTH / PAGE_SIZE) enum nvmet_fcp_datadir { NVMET_FCP_NODATA, @@ -74,6 +74,7 @@ struct nvmet_fc_fcp_iod { struct nvme_fc_cmd_iu cmdiubuf; struct nvme_fc_ersp_iu rspiubuf; dma_addr_t rspdma; + struct scatterlist *next_sg; struct scatterlist *data_sg; int data_sg_cnt; u32 offset; @@ -1025,8 +1026,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo, INIT_LIST_HEAD(&newrec->assoc_list); kref_init(&newrec->ref); ida_init(&newrec->assoc_cnt); - newrec->max_sg_cnt = min_t(u32, NVMET_FC_MAX_XFR_SGENTS, - template->max_sgl_segments); + newrec->max_sg_cnt = template->max_sgl_segments; ret = nvmet_fc_alloc_ls_iodlist(newrec); if (ret) { @@ -1722,6 +1722,7 @@ nvmet_fc_alloc_tgt_pgs(struct nvmet_fc_fcp_iod *fod) ((fod->io_dir == NVMET_FCP_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE)); /* note: write from initiator perspective */ + fod->next_sg = fod->data_sg; return 0; @@ -1866,24 +1867,49 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_fcp_iod *fod, u8 op) { struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq; + struct scatterlist *sg = fod->next_sg; unsigned long flags; - u32 tlen; + u32 remaininglen = fod->req.transfer_len - fod->offset; + u32 tlen = 0; int ret; fcpreq->op = op; fcpreq->offset = fod->offset; fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC; - tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE, - (fod->req.transfer_len - fod->offset)); + /* + * for next sequence: + * break at a sg element boundary + * attempt to keep sequence length capped at + * NVMET_FC_MAX_SEQ_LENGTH but allow sequence to + * be longer if a single sg element is larger + * than that amount. This is done to avoid creating + * a new sg list to use for the tgtport api. + */ + fcpreq->sg = sg; + fcpreq->sg_cnt = 0; + while (tlen < remaininglen && + fcpreq->sg_cnt < tgtport->max_sg_cnt && + tlen + sg_dma_len(sg) < NVMET_FC_MAX_SEQ_LENGTH) { + fcpreq->sg_cnt++; + tlen += sg_dma_len(sg); + sg = sg_next(sg); + } + if (tlen < remaininglen && fcpreq->sg_cnt == 0) { + fcpreq->sg_cnt++; + tlen += min_t(u32, sg_dma_len(sg), remaininglen); + sg = sg_next(sg); + } + if (tlen < remaininglen) + fod->next_sg = sg; + else + fod->next_sg = NULL; + fcpreq->transfer_length = tlen; fcpreq->transferred_length = 0; fcpreq->fcp_error = 0; fcpreq->rsplen = 0; - fcpreq->sg = &fod->data_sg[fod->offset / PAGE_SIZE]; - fcpreq->sg_cnt = DIV_ROUND_UP(tlen, PAGE_SIZE); - /* * If the last READDATA request: check if LLDD supports * combined xfr with response. diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index d8d91f04bd7e..ae7586b8be07 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -162,7 +162,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, blk_status_t ret; if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready)) - return nvmf_fail_nonready_command(req); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req); ret = nvme_setup_cmd(ns, req, &iod->cmd); if (ret) diff --git a/drivers/of/base.c b/drivers/of/base.c index 848f549164cd..466e3c8582f0 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -102,7 +102,7 @@ static u32 phandle_cache_mask; * - the phandle lookup overhead reduction provided by the cache * will likely be less */ -static void of_populate_phandle_cache(void) +void of_populate_phandle_cache(void) { unsigned long flags; u32 cache_entries; @@ -134,8 +134,7 @@ out: raw_spin_unlock_irqrestore(&devtree_lock, flags); } -#ifndef CONFIG_MODULES -static int __init of_free_phandle_cache(void) +int of_free_phandle_cache(void) { unsigned long flags; @@ -148,6 +147,7 @@ static int __init of_free_phandle_cache(void) return 0; } +#if !defined(CONFIG_MODULES) late_initcall_sync(of_free_phandle_cache); #endif diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index 891d780c076a..216175d11d3d 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -79,6 +79,8 @@ int of_resolve_phandles(struct device_node *tree); #if defined(CONFIG_OF_OVERLAY) void of_overlay_mutex_lock(void); void of_overlay_mutex_unlock(void); +int of_free_phandle_cache(void); +void of_populate_phandle_cache(void); #else static inline void of_overlay_mutex_lock(void) {}; static inline void of_overlay_mutex_unlock(void) {}; diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 7baa53e5b1d7..eda57ef12fd0 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -804,6 +804,8 @@ static int of_overlay_apply(const void *fdt, struct device_node *tree, goto err_free_overlay_changeset; } + of_populate_phandle_cache(); + ret = __of_changeset_apply_notify(&ovcs->cset); if (ret) pr_err("overlay changeset entry notify error %d\n", ret); @@ -1046,8 +1048,17 @@ int of_overlay_remove(int *ovcs_id) list_del(&ovcs->ovcs_list); + /* + * Disable phandle cache. Avoids race condition that would arise + * from removing cache entry when the associated node is deleted. + */ + of_free_phandle_cache(); + ret_apply = 0; ret = __of_changeset_revert_entries(&ovcs->cset, &ret_apply); + + of_populate_phandle_cache(); + if (ret) { if (ret_apply) devicetree_state_flags |= DTSF_REVERT_FAIL; diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 35b7fc87eac5..5cb40b2518f9 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -330,7 +330,7 @@ void pci_bus_add_device(struct pci_dev *dev) return; } - dev->is_added = 1; + pci_dev_assign_added(dev, true); } EXPORT_SYMBOL_GPL(pci_bus_add_device); @@ -347,14 +347,14 @@ void pci_bus_add_devices(const struct pci_bus *bus) list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip already-added devices */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pci_bus_add_device(dev); } list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip if device attach failed */ - if (!dev->is_added) + if (!pci_dev_is_added(dev)) continue; child = dev->subordinate; if (child) diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 781aa03aeede..29a05759a294 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -363,7 +363,8 @@ int dw_pcie_host_init(struct pcie_port *pp) resource_list_for_each_entry_safe(win, tmp, &bridge->windows) { switch (resource_type(win->res)) { case IORESOURCE_IO: - ret = pci_remap_iospace(win->res, pp->io_base); + ret = devm_pci_remap_iospace(dev, win->res, + pp->io_base); if (ret) { dev_warn(dev, "Error %d: failed to map resource %pR\n", ret, win->res); diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index d3172d5d3d35..0fae816fba39 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -849,7 +849,7 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie) 0, 0xF8000000, 0, lower_32_bits(res->start), OB_PCIE_IO); - err = pci_remap_iospace(res, iobase); + err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", err, res); diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c index 20bb2564a6b3..bf5ece5d9291 100644 --- a/drivers/pci/controller/pci-ftpci100.c +++ b/drivers/pci/controller/pci-ftpci100.c @@ -503,7 +503,7 @@ static int faraday_pci_probe(struct platform_device *pdev) dev_err(dev, "illegal IO mem size\n"); return -EINVAL; } - ret = pci_remap_iospace(io, io_base); + ret = devm_pci_remap_iospace(dev, io, io_base); if (ret) { dev_warn(dev, "error %d: failed to map resource %pR\n", ret, io); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 6cc5036ac83c..f6325f1a89e8 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1073,6 +1073,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_bus *pbus; struct pci_dev *pdev; struct cpumask *dest; + unsigned long flags; struct compose_comp_ctxt comp; struct tran_int_desc *int_desc; struct { @@ -1164,14 +1165,15 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) * the channel callback directly when channel->target_cpu is * the current CPU. When the higher level interrupt code * calls us with interrupt enabled, let's add the - * local_bh_disable()/enable() to avoid race. + * local_irq_save()/restore() to avoid race: + * hv_pci_onchannelcallback() can also run in tasklet. */ - local_bh_disable(); + local_irq_save(flags); if (hbus->hdev->channel->target_cpu == smp_processor_id()) hv_pci_onchannelcallback(hbus); - local_bh_enable(); + local_irq_restore(flags); if (hpdev->state == hv_pcichild_ejecting) { dev_err_once(&hbus->hdev->device, diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c index 68b8bfbdb867..d219404bad92 100644 --- a/drivers/pci/controller/pci-v3-semi.c +++ b/drivers/pci/controller/pci-v3-semi.c @@ -537,7 +537,7 @@ static int v3_pci_setup_resource(struct v3_pci *v3, v3->io_bus_addr = io->start - win->offset; dev_dbg(dev, "I/O window %pR, bus addr %pap\n", io, &v3->io_bus_addr); - ret = pci_remap_iospace(io, io_base); + ret = devm_pci_remap_iospace(dev, io, io_base); if (ret) { dev_warn(dev, "error %d: failed to map resource %pR\n", diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c index 994f32061b32..f59ad2728c0b 100644 --- a/drivers/pci/controller/pci-versatile.c +++ b/drivers/pci/controller/pci-versatile.c @@ -82,7 +82,7 @@ static int versatile_pci_parse_request_of_pci_ranges(struct device *dev, switch (resource_type(res)) { case IORESOURCE_IO: - err = pci_remap_iospace(res, iobase); + err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", err, res); diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c index d854d67e873c..ffda3e8b4742 100644 --- a/drivers/pci/controller/pci-xgene.c +++ b/drivers/pci/controller/pci-xgene.c @@ -423,7 +423,7 @@ static int xgene_pcie_map_ranges(struct xgene_pcie_port *port, case IORESOURCE_IO: xgene_pcie_setup_ob_reg(port, res, OMR3BARL, io_base, res->start - window->offset); - ret = pci_remap_iospace(res, io_base); + ret = devm_pci_remap_iospace(dev, res, io_base); if (ret < 0) return ret; break; diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 0baabe30858f..861dda69f366 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -1109,7 +1109,7 @@ static int mtk_pcie_request_resources(struct mtk_pcie *pcie) if (err < 0) return err; - pci_remap_iospace(&pcie->pio, pcie->io.start); + devm_pci_remap_iospace(dev, &pcie->pio, pcie->io.start); return 0; } diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c index 4d6c20e47bed..cf0aa7cee5b0 100644 --- a/drivers/pci/controller/pcie-mobiveil.c +++ b/drivers/pci/controller/pcie-mobiveil.c @@ -107,7 +107,7 @@ #define CFG_WINDOW_TYPE 0 #define IO_WINDOW_TYPE 1 #define MEM_WINDOW_TYPE 2 -#define IB_WIN_SIZE (256 * 1024 * 1024 * 1024) +#define IB_WIN_SIZE ((u64)256 * 1024 * 1024 * 1024) #define MAX_PIO_WINDOWS 8 /* Parameters for the waiting for link up routine */ diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index bf53fad636a5..825fa24427a3 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -137,25 +137,60 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar) } EXPORT_SYMBOL_GPL(pci_epf_alloc_space); -/** - * pci_epf_unregister_driver() - unregister the PCI EPF driver - * @driver: the PCI EPF driver that has to be unregistered - * - * Invoke to unregister the PCI EPF driver. - */ -void pci_epf_unregister_driver(struct pci_epf_driver *driver) +static void pci_epf_remove_cfs(struct pci_epf_driver *driver) { struct config_group *group, *tmp; + if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS)) + return; + mutex_lock(&pci_epf_mutex); list_for_each_entry_safe(group, tmp, &driver->epf_group, group_entry) pci_ep_cfs_remove_epf_group(group); list_del(&driver->epf_group); mutex_unlock(&pci_epf_mutex); +} + +/** + * pci_epf_unregister_driver() - unregister the PCI EPF driver + * @driver: the PCI EPF driver that has to be unregistered + * + * Invoke to unregister the PCI EPF driver. + */ +void pci_epf_unregister_driver(struct pci_epf_driver *driver) +{ + pci_epf_remove_cfs(driver); driver_unregister(&driver->driver); } EXPORT_SYMBOL_GPL(pci_epf_unregister_driver); +static int pci_epf_add_cfs(struct pci_epf_driver *driver) +{ + struct config_group *group; + const struct pci_epf_device_id *id; + + if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS)) + return 0; + + INIT_LIST_HEAD(&driver->epf_group); + + id = driver->id_table; + while (id->name[0]) { + group = pci_ep_cfs_add_epf_group(id->name); + if (IS_ERR(group)) { + pci_epf_remove_cfs(driver); + return PTR_ERR(group); + } + + mutex_lock(&pci_epf_mutex); + list_add_tail(&group->group_entry, &driver->epf_group); + mutex_unlock(&pci_epf_mutex); + id++; + } + + return 0; +} + /** * __pci_epf_register_driver() - register a new PCI EPF driver * @driver: structure representing PCI EPF driver @@ -167,8 +202,6 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver, struct module *owner) { int ret; - struct config_group *group; - const struct pci_epf_device_id *id; if (!driver->ops) return -EINVAL; @@ -183,16 +216,7 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver, if (ret) return ret; - INIT_LIST_HEAD(&driver->epf_group); - - id = driver->id_table; - while (id->name[0]) { - group = pci_ep_cfs_add_epf_group(id->name); - mutex_lock(&pci_epf_mutex); - list_add_tail(&group->group_entry, &driver->epf_group); - mutex_unlock(&pci_epf_mutex); - id++; - } + pci_epf_add_cfs(driver); return 0; } diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 3a17b290df5d..ef0b1b6ba86f 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -509,7 +509,7 @@ static void enable_slot(struct acpiphp_slot *slot) list_for_each_entry(dev, &bus->devices, bus_list) { /* Assume that newly added devices are powered on already. */ - if (!dev->is_added) + if (!pci_dev_is_added(dev)) dev->current_state = PCI_D0; } diff --git a/drivers/pci/of.c b/drivers/pci/of.c index d088c9147f10..69a60d6ebd73 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -612,7 +612,7 @@ int pci_parse_request_of_pci_ranges(struct device *dev, switch (resource_type(res)) { case IORESOURCE_IO: - err = pci_remap_iospace(res, iobase); + err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", err, res); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 97acba712e4e..316496e99da9 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3579,6 +3579,44 @@ void pci_unmap_iospace(struct resource *res) } EXPORT_SYMBOL(pci_unmap_iospace); +static void devm_pci_unmap_iospace(struct device *dev, void *ptr) +{ + struct resource **res = ptr; + + pci_unmap_iospace(*res); +} + +/** + * devm_pci_remap_iospace - Managed pci_remap_iospace() + * @dev: Generic device to remap IO address for + * @res: Resource describing the I/O space + * @phys_addr: physical address of range to be mapped + * + * Managed pci_remap_iospace(). Map is automatically unmapped on driver + * detach. + */ +int devm_pci_remap_iospace(struct device *dev, const struct resource *res, + phys_addr_t phys_addr) +{ + const struct resource **ptr; + int error; + + ptr = devres_alloc(devm_pci_unmap_iospace, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return -ENOMEM; + + error = pci_remap_iospace(res, phys_addr); + if (error) { + devres_free(ptr); + } else { + *ptr = res; + devres_add(dev, ptr); + } + + return error; +} +EXPORT_SYMBOL(devm_pci_remap_iospace); + /** * devm_pci_remap_cfgspace - Managed pci_remap_cfgspace() * @dev: Generic device to remap IO address for diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 882f1f9596df..08817253c8a2 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -288,6 +288,7 @@ struct pci_sriov { /* pci_dev priv_flags */ #define PCI_DEV_DISCONNECTED 0 +#define PCI_DEV_ADDED 1 static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) { @@ -300,6 +301,16 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) return test_bit(PCI_DEV_DISCONNECTED, &dev->priv_flags); } +static inline void pci_dev_assign_added(struct pci_dev *dev, bool added) +{ + assign_bit(PCI_DEV_ADDED, &dev->priv_flags, added); +} + +static inline bool pci_dev_is_added(const struct pci_dev *dev) +{ + return test_bit(PCI_DEV_ADDED, &dev->priv_flags); +} + #ifdef CONFIG_PCI_ATS void pci_restore_ats_state(struct pci_dev *dev); #else diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index f7ce0cb0b0b7..f02e334beb45 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -295,6 +295,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) parent = udev->subordinate; pci_lock_rescan_remove(); + pci_dev_get(dev); list_for_each_entry_safe_reverse(pdev, temp, &parent->devices, bus_list) { pci_dev_get(pdev); @@ -328,6 +329,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) pci_info(dev, "Device recovery from fatal error failed\n"); } + pci_dev_put(dev); pci_unlock_rescan_remove(); } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ac876e32de4b..611adcd9c169 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2433,13 +2433,13 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) dev = pci_scan_single_device(bus, devfn); if (!dev) return 0; - if (!dev->is_added) + if (!pci_dev_is_added(dev)) nr++; for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) { dev = pci_scan_single_device(bus, devfn + fn); if (dev) { - if (!dev->is_added) + if (!pci_dev_is_added(dev)) nr++; dev->multifunction = 1; } diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 6f072eae4f7a..5e3d0dced2b8 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -19,11 +19,12 @@ static void pci_stop_dev(struct pci_dev *dev) { pci_pme_active(dev, false); - if (dev->is_added) { + if (pci_dev_is_added(dev)) { device_release_driver(&dev->dev); pci_proc_detach_device(dev); pci_remove_sysfs_dev_files(dev); - dev->is_added = 0; + + pci_dev_assign_added(dev, false); } if (dev->bus->self) diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.c b/drivers/phy/broadcom/phy-brcm-usb-init.c index 1b7febc43da9..29d2c3b1913a 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init.c @@ -962,6 +962,10 @@ void brcm_usb_init_xhci(struct brcm_usb_init_params *params) { void __iomem *ctrl = params->ctrl_regs; + USB_CTRL_UNSET(ctrl, USB30_PCTL, PHY3_IDDQ_OVERRIDE); + /* 1 millisecond - for USB clocks to settle down */ + usleep_range(1000, 2000); + if (BRCM_ID(params->family_id) == 0x7366) { /* * The PHY3_SOFT_RESETB bits default to the wrong state. diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index 23705e1a0023..0075fb0bef8c 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -182,13 +182,13 @@ static void phy_mdm6600_status(struct work_struct *work) ddata = container_of(work, struct phy_mdm6600, status_work.work); dev = ddata->dev; - error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_CMD_LINES, + error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_STATUS_LINES, ddata->status_gpios->desc, values); if (error) return; - for (i = 0; i < PHY_MDM6600_NR_CMD_LINES; i++) { + for (i = 0; i < PHY_MDM6600_NR_STATUS_LINES; i++) { val |= values[i] << i; dev_dbg(ddata->dev, "XXX %s: i: %i values[i]: %i val: %i\n", __func__, i, values[i], val); diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-mux.c b/drivers/pinctrl/bcm/pinctrl-nsp-mux.c index 35c17653c694..87618a4e90e4 100644 --- a/drivers/pinctrl/bcm/pinctrl-nsp-mux.c +++ b/drivers/pinctrl/bcm/pinctrl-nsp-mux.c @@ -460,8 +460,8 @@ static int nsp_pinmux_enable(struct pinctrl_dev *pctrl_dev, const struct nsp_pin_function *func; const struct nsp_pin_group *grp; - if (grp_select > pinctrl->num_groups || - func_select > pinctrl->num_functions) + if (grp_select >= pinctrl->num_groups || + func_select >= pinctrl->num_functions) return -EINVAL; func = &pinctrl->functions[func_select]; @@ -577,6 +577,8 @@ static int nsp_pinmux_probe(struct platform_device *pdev) return PTR_ERR(pinctrl->base0); res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!res) + return -EINVAL; pinctrl->base1 = devm_ioremap_nocache(&pdev->dev, res->start, resource_size(res)); if (!pinctrl->base1) { diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7622.c b/drivers/pinctrl/mediatek/pinctrl-mt7622.c index e3f1ab2290fc..4c4740ffeb9c 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt7622.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt7622.c @@ -1424,7 +1424,7 @@ static struct pinctrl_desc mtk_desc = { static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio) { - struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent); + struct mtk_pinctrl *hw = gpiochip_get_data(chip); int value, err; err = mtk_hw_get_value(hw, gpio, PINCTRL_PIN_REG_DI, &value); @@ -1436,7 +1436,7 @@ static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio) static void mtk_gpio_set(struct gpio_chip *chip, unsigned int gpio, int value) { - struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent); + struct mtk_pinctrl *hw = gpiochip_get_data(chip); mtk_hw_set_value(hw, gpio, PINCTRL_PIN_REG_DO, !!value); } @@ -1508,11 +1508,20 @@ static int mtk_build_gpiochip(struct mtk_pinctrl *hw, struct device_node *np) if (ret < 0) return ret; - ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0, - chip->ngpio); - if (ret < 0) { - gpiochip_remove(chip); - return ret; + /* Just for backward compatible for these old pinctrl nodes without + * "gpio-ranges" property. Otherwise, called directly from a + * DeviceTree-supported pinctrl driver is DEPRECATED. + * Please see Section 2.1 of + * Documentation/devicetree/bindings/gpio/gpio.txt on how to + * bind pinctrl and gpio drivers via the "gpio-ranges" property. + */ + if (!of_find_property(np, "gpio-ranges", NULL)) { + ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0, + chip->ngpio); + if (ret < 0) { + gpiochip_remove(chip); + return ret; + } } return 0; @@ -1695,15 +1704,16 @@ static int mtk_pinctrl_probe(struct platform_device *pdev) mtk_desc.custom_conf_items = mtk_conf_items; #endif - hw->pctrl = devm_pinctrl_register(&pdev->dev, &mtk_desc, hw); - if (IS_ERR(hw->pctrl)) - return PTR_ERR(hw->pctrl); + err = devm_pinctrl_register_and_init(&pdev->dev, &mtk_desc, hw, + &hw->pctrl); + if (err) + return err; /* Setup groups descriptions per SoC types */ err = mtk_build_groups(hw); if (err) { dev_err(&pdev->dev, "Failed to build groups\n"); - return 0; + return err; } /* Setup functions descriptions per SoC types */ @@ -1713,17 +1723,25 @@ static int mtk_pinctrl_probe(struct platform_device *pdev) return err; } - err = mtk_build_gpiochip(hw, pdev->dev.of_node); - if (err) { - dev_err(&pdev->dev, "Failed to add gpio_chip\n"); + /* For able to make pinctrl_claim_hogs, we must not enable pinctrl + * until all groups and functions are being added one. + */ + err = pinctrl_enable(hw->pctrl); + if (err) return err; - } err = mtk_build_eint(hw, pdev); if (err) dev_warn(&pdev->dev, "Failed to add EINT, but pinctrl still can work\n"); + /* Build gpiochip should be after pinctrl_enable is done */ + err = mtk_build_gpiochip(hw, pdev->dev.of_node); + if (err) { + dev_err(&pdev->dev, "Failed to add gpio_chip\n"); + return err; + } + platform_set_drvdata(pdev, hw); return 0; diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index a1d7156d0a43..6a1b6058b991 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -536,7 +536,7 @@ static int ingenic_pinmux_gpio_set_direction(struct pinctrl_dev *pctldev, ingenic_config_pin(jzpc, pin, JZ4770_GPIO_PAT1, input); } else { ingenic_config_pin(jzpc, pin, JZ4740_GPIO_SELECT, false); - ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, input); + ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, !input); ingenic_config_pin(jzpc, pin, JZ4740_GPIO_FUNC, false); } diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77970.c b/drivers/pinctrl/sh-pfc/pfc-r8a77970.c index b02caf316711..eeb58b3bbc9a 100644 --- a/drivers/pinctrl/sh-pfc/pfc-r8a77970.c +++ b/drivers/pinctrl/sh-pfc/pfc-r8a77970.c @@ -21,15 +21,13 @@ #include "core.h" #include "sh_pfc.h" -#define CFG_FLAGS SH_PFC_PIN_CFG_DRIVE_STRENGTH - #define CPU_ALL_PORT(fn, sfx) \ - PORT_GP_CFG_22(0, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_28(1, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_17(2, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_17(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_6(4, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_15(5, fn, sfx, CFG_FLAGS) + PORT_GP_CFG_22(0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_28(1, fn, sfx), \ + PORT_GP_CFG_17(2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_6(4, fn, sfx), \ + PORT_GP_15(5, fn, sfx) /* * F_() : just information * FM() : macro for FN_xxx / xxx_MARK diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index f1fa8612db40..06978c14c83b 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -2185,7 +2185,7 @@ static int __init dell_init(void) dell_fill_request(&buffer, token->location, 0, 0, 0); ret = dell_send_request(&buffer, CLASS_TOKEN_READ, SELECT_TOKEN_AC); - if (ret) + if (ret == 0) max_intensity = buffer.output[3]; } diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 547dbdac9d54..01b0e2bb3319 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -89,6 +89,7 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin, case PTP_PF_PHYSYNC: if (chan != 0) return -EINVAL; + break; default: return -EINVAL; } diff --git a/drivers/scsi/cxlflash/main.h b/drivers/scsi/cxlflash/main.h index 2a3977823812..a39be94d110c 100644 --- a/drivers/scsi/cxlflash/main.h +++ b/drivers/scsi/cxlflash/main.h @@ -107,12 +107,12 @@ cxlflash_assign_ops(struct dev_dependent_vals *ddv) { const struct cxlflash_backend_ops *ops = NULL; -#ifdef CONFIG_OCXL +#ifdef CONFIG_OCXL_BASE if (ddv->flags & CXLFLASH_OCXL_DEV) ops = &cxlflash_ocxl_ops; #endif -#ifdef CONFIG_CXL +#ifdef CONFIG_CXL_BASE if (!(ddv->flags & CXLFLASH_OCXL_DEV)) ops = &cxlflash_cxl_ops; #endif diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c index 0a95b5f25380..497a68389461 100644 --- a/drivers/scsi/cxlflash/ocxl_hw.c +++ b/drivers/scsi/cxlflash/ocxl_hw.c @@ -134,15 +134,14 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name, rc = PTR_ERR(file); dev_err(dev, "%s: alloc_file failed rc=%d\n", __func__, rc); - goto err5; + path_put(&path); + goto err3; } file->f_flags = flags & (O_ACCMODE | O_NONBLOCK); file->private_data = priv; out: return file; -err5: - path_put(&path); err4: iput(inode); err3: diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index ea23c8dffc25..ffec695e0bfb 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -754,9 +754,9 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, case ELS_LOGO: if (fip->mode == FIP_MODE_VN2VN) { if (fip->state != FIP_ST_VNMP_UP) - return -EINVAL; + goto drop; if (ntoh24(fh->fh_d_id) == FC_FID_FLOGI) - return -EINVAL; + goto drop; } else { if (fip->state != FIP_ST_ENABLED) return 0; @@ -799,9 +799,9 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, fip->send(fip, skb); return -EINPROGRESS; drop: - kfree_skb(skb); LIBFCOE_FIP_DBG(fip, "drop els_send op %u d_id %x\n", op, ntoh24(fh->fh_d_id)); + kfree_skb(skb); return -EINVAL; } EXPORT_SYMBOL(fcoe_ctlr_els_send); diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 15c7f3b6f35e..58bb70b886d7 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -3440,11 +3440,11 @@ static void hpsa_get_enclosure_info(struct ctlr_info *h, struct ext_report_lun_entry *rle = &rlep->LUN[rle_index]; u16 bmic_device_index = 0; - bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]); - - encl_dev->sas_address = + encl_dev->eli = hpsa_get_enclosure_logical_identifier(h, scsi3addr); + bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]); + if (encl_dev->target == -1 || encl_dev->lun == -1) { rc = IO_OK; goto out; @@ -9697,7 +9697,24 @@ hpsa_sas_get_linkerrors(struct sas_phy *phy) static int hpsa_sas_get_enclosure_identifier(struct sas_rphy *rphy, u64 *identifier) { - *identifier = rphy->identify.sas_address; + struct Scsi_Host *shost = phy_to_shost(rphy); + struct ctlr_info *h; + struct hpsa_scsi_dev_t *sd; + + if (!shost) + return -ENXIO; + + h = shost_to_hba(shost); + + if (!h) + return -ENXIO; + + sd = hpsa_find_device_by_sas_rphy(h, rphy); + if (!sd) + return -ENXIO; + + *identifier = sd->eli; + return 0; } diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h index fb9f5e7f8209..59e023696fff 100644 --- a/drivers/scsi/hpsa.h +++ b/drivers/scsi/hpsa.h @@ -68,6 +68,7 @@ struct hpsa_scsi_dev_t { #define RAID_CTLR_LUNID "\0\0\0\0\0\0\0\0" unsigned char device_id[16]; /* from inquiry pg. 0x83 */ u64 sas_address; + u64 eli; /* from report diags. */ unsigned char vendor[8]; /* bytes 8-15 of inquiry data */ unsigned char model[16]; /* bytes 16-31 of inquiry data */ unsigned char rev; /* byte 2 of inquiry data */ diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 31d31aad3de1..89b1f1af2fd4 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -2164,6 +2164,7 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp) FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n", fc_rport_state(rdata)); + rdata->flags &= ~FC_RP_STARTED; fc_rport_enter_delete(rdata, RPORT_EV_STOP); mutex_unlock(&rdata->rp_mutex); kref_put(&rdata->kref, fc_rport_destroy); diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index d6093838f5f2..c972cc2b3d5b 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -284,11 +284,11 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode) */ if (opcode != ISCSI_OP_SCSI_DATA_OUT) { iscsi_conn_printk(KERN_INFO, conn, - "task [op %x/%x itt " + "task [op %x itt " "0x%x/0x%x] " "rejected.\n", - task->hdr->opcode, opcode, - task->itt, task->hdr_itt); + opcode, task->itt, + task->hdr_itt); return -EACCES; } /* @@ -297,10 +297,10 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode) */ if (conn->session->fast_abort) { iscsi_conn_printk(KERN_INFO, conn, - "task [op %x/%x itt " + "task [op %x itt " "0x%x/0x%x] fast abort.\n", - task->hdr->opcode, opcode, - task->itt, task->hdr_itt); + opcode, task->itt, + task->hdr_itt); return -EACCES; } break; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 569392d0d4c9..e44c91edf92d 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -3343,11 +3343,10 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock) { unsigned long flags; - __u64 data_out = b; spin_lock_irqsave(writeq_lock, flags); - writel((u32)(data_out), addr); - writel((u32)(data_out >> 32), (addr + 4)); + __raw_writel((u32)(b), addr); + __raw_writel((u32)(b >> 32), (addr + 4)); mmiowb(); spin_unlock_irqrestore(writeq_lock, flags); } @@ -3367,7 +3366,8 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr, static inline void _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock) { - writeq(b, addr); + __raw_writeq(b, addr); + mmiowb(); } #else static inline void @@ -5268,7 +5268,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, /* send message 32-bits at a time */ for (i = 0, failed = 0; i < request_bytes/4 && !failed; i++) { - writel((u32)(request[i]), &ioc->chip->Doorbell); + writel(cpu_to_le32(request[i]), &ioc->chip->Doorbell); if ((_base_wait_for_doorbell_ack(ioc, 5))) failed = 1; } @@ -5289,7 +5289,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, } /* read the first two 16-bits, it gives the total length of the reply */ - reply[0] = (u16)(readl(&ioc->chip->Doorbell) + reply[0] = le16_to_cpu(readl(&ioc->chip->Doorbell) & MPI2_DOORBELL_DATA_MASK); writel(0, &ioc->chip->HostInterruptStatus); if ((_base_wait_for_doorbell_int(ioc, 5))) { @@ -5298,7 +5298,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, ioc->name, __LINE__); return -EFAULT; } - reply[1] = (u16)(readl(&ioc->chip->Doorbell) + reply[1] = le16_to_cpu(readl(&ioc->chip->Doorbell) & MPI2_DOORBELL_DATA_MASK); writel(0, &ioc->chip->HostInterruptStatus); @@ -5312,7 +5312,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, if (i >= reply_bytes/2) /* overflow case */ readl(&ioc->chip->Doorbell); else - reply[i] = (u16)(readl(&ioc->chip->Doorbell) + reply[i] = le16_to_cpu(readl(&ioc->chip->Doorbell) & MPI2_DOORBELL_DATA_MASK); writel(0, &ioc->chip->HostInterruptStatus); } diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 90394cef0f41..0a5dd5595dd3 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -3295,6 +3295,11 @@ static int __qedf_probe(struct pci_dev *pdev, int mode) init_completion(&qedf->flogi_compl); + status = qed_ops->common->update_drv_state(qedf->cdev, true); + if (status) + QEDF_ERR(&(qedf->dbg_ctx), + "Failed to send drv state to MFW.\n"); + memset(&link_params, 0, sizeof(struct qed_link_params)); link_params.link_up = true; status = qed_ops->common->set_link(qedf->cdev, &link_params); @@ -3343,6 +3348,7 @@ static int qedf_probe(struct pci_dev *pdev, const struct pci_device_id *id) static void __qedf_remove(struct pci_dev *pdev, int mode) { struct qedf_ctx *qedf; + int rc; if (!pdev) { QEDF_ERR(NULL, "pdev is NULL.\n"); @@ -3437,6 +3443,12 @@ static void __qedf_remove(struct pci_dev *pdev, int mode) qed_ops->common->set_power_state(qedf->cdev, PCI_D0); pci_set_drvdata(pdev, NULL); } + + rc = qed_ops->common->update_drv_state(qedf->cdev, false); + if (rc) + QEDF_ERR(&(qedf->dbg_ctx), + "Failed to send drv state to MFW.\n"); + qed_ops->common->slowpath_stop(qedf->cdev); qed_ops->common->remove(qedf->cdev); diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index cf274a79e77a..cff83b9457f7 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -888,7 +888,7 @@ static void qedi_get_boot_tgt_info(struct nvm_iscsi_block *block, ipv6_en = !!(block->generic.ctrl_flags & NVM_ISCSI_CFG_GEN_IPV6_ENABLED); - snprintf(tgt->iscsi_name, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", + snprintf(tgt->iscsi_name, sizeof(tgt->iscsi_name), "%s\n", block->target[index].target_name.byte); tgt->ipv6_en = ipv6_en; @@ -2273,6 +2273,7 @@ kset_free: static void __qedi_remove(struct pci_dev *pdev, int mode) { struct qedi_ctx *qedi = pci_get_drvdata(pdev); + int rval; if (qedi->tmf_thread) { flush_workqueue(qedi->tmf_thread); @@ -2302,6 +2303,10 @@ static void __qedi_remove(struct pci_dev *pdev, int mode) if (mode == QEDI_MODE_NORMAL) qedi_free_iscsi_pf_param(qedi); + rval = qedi_ops->common->update_drv_state(qedi->cdev, false); + if (rval) + QEDI_ERR(&qedi->dbg_ctx, "Failed to send drv state to MFW\n"); + if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags)) { qedi_ops->common->slowpath_stop(qedi->cdev); qedi_ops->common->remove(qedi->cdev); @@ -2576,6 +2581,12 @@ static int __qedi_probe(struct pci_dev *pdev, int mode) if (qedi_setup_boot_info(qedi)) QEDI_ERR(&qedi->dbg_ctx, "No iSCSI boot target configured\n"); + + rc = qedi_ops->common->update_drv_state(qedi->cdev, true); + if (rc) + QEDI_ERR(&qedi->dbg_ctx, + "Failed to send drv state to MFW\n"); + } return 0; diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 89a4999fa631..c8731568f9c4 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2141,6 +2141,7 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) msleep(1000); qla24xx_disable_vp(vha); + qla2x00_wait_for_sess_deletion(vha); vha->flags.delete_progress = 1; diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 9442e18aef6f..0f94b1d62d3f 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -361,6 +361,8 @@ struct ct_arg { dma_addr_t rsp_dma; u32 req_size; u32 rsp_size; + u32 req_allocated_size; + u32 rsp_allocated_size; void *req; void *rsp; port_id_t id; diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index f68eb6096559..2660a48d918a 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -214,6 +214,7 @@ void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *, int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *); int qla24xx_async_abort_cmd(srb_t *); int qla24xx_post_relogin_work(struct scsi_qla_host *vha); +void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *); /* * Global Functions in qla_mid.c source file. diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 4bc2b66b299f..7a3744006419 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -556,7 +556,7 @@ err2: /* please ignore kernel warning. otherwise, we have mem leak. */ if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; @@ -564,7 +564,7 @@ err2: if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -617,6 +617,7 @@ static int qla_async_rftid(scsi_qla_host_t *vha, port_id_t *d_id) sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xd041, "%s: Failed to allocate ct_sns request.\n", @@ -627,6 +628,7 @@ static int qla_async_rftid(scsi_qla_host_t *vha, port_id_t *d_id) sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xd042, "%s: Failed to allocate ct_sns request.\n", @@ -712,6 +714,7 @@ static int qla_async_rffid(scsi_qla_host_t *vha, port_id_t *d_id, sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xd041, "%s: Failed to allocate ct_sns request.\n", @@ -722,6 +725,7 @@ static int qla_async_rffid(scsi_qla_host_t *vha, port_id_t *d_id, sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xd042, "%s: Failed to allocate ct_sns request.\n", @@ -802,6 +806,7 @@ static int qla_async_rnnid(scsi_qla_host_t *vha, port_id_t *d_id, sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xd041, "%s: Failed to allocate ct_sns request.\n", @@ -812,6 +817,7 @@ static int qla_async_rnnid(scsi_qla_host_t *vha, port_id_t *d_id, sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xd042, "%s: Failed to allocate ct_sns request.\n", @@ -909,6 +915,7 @@ static int qla_async_rsnn_nn(scsi_qla_host_t *vha) sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xd041, "%s: Failed to allocate ct_sns request.\n", @@ -919,6 +926,7 @@ static int qla_async_rsnn_nn(scsi_qla_host_t *vha) sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xd042, "%s: Failed to allocate ct_sns request.\n", @@ -3388,14 +3396,14 @@ void qla24xx_sp_unmap(scsi_qla_host_t *vha, srb_t *sp) { if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -3596,14 +3604,14 @@ static void qla2x00_async_gpnid_sp_done(void *s, int res) /* please ignore kernel warning. otherwise, we have mem leak. */ if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -3654,6 +3662,7 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id) sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xd041, "Failed to allocate ct_sns request.\n"); @@ -3663,6 +3672,7 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id) sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xd042, "Failed to allocate ct_sns request.\n"); @@ -3698,6 +3708,10 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id) return rval; done_free_sp: + spin_lock_irqsave(&vha->hw->vport_slock, flags); + list_del(&sp->elem); + spin_unlock_irqrestore(&vha->hw->vport_slock, flags); + if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), @@ -4142,14 +4156,14 @@ static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res) */ if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -4179,14 +4193,14 @@ static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res) /* please ignore kernel warning. Otherwise, we have mem leak. */ if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -4281,14 +4295,14 @@ static int qla24xx_async_gnnft(scsi_qla_host_t *vha, struct srb *sp, done_free_sp: if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -4349,6 +4363,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp) sp->u.iocb_cmd.u.ctarg.req = dma_zalloc_coherent( &vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xffff, "Failed to allocate ct_sns request.\n"); @@ -4366,6 +4381,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp) sp->u.iocb_cmd.u.ctarg.rsp = dma_zalloc_coherent( &vha->hw->pdev->dev, rspsz, &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xffff, "Failed to allocate ct_sns request.\n"); @@ -4425,14 +4441,14 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp) done_free_sp: if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 7b675243bd16..1b19b954bbae 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -591,12 +591,14 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, conflict_fcport = qla2x00_find_fcport_by_wwpn(vha, e->port_name, 0); - ql_dbg(ql_dbg_disc, vha, 0x20e6, - "%s %d %8phC post del sess\n", - __func__, __LINE__, - conflict_fcport->port_name); - qlt_schedule_sess_for_deletion - (conflict_fcport); + if (conflict_fcport) { + qlt_schedule_sess_for_deletion + (conflict_fcport); + ql_dbg(ql_dbg_disc, vha, 0x20e6, + "%s %d %8phC post del sess\n", + __func__, __LINE__, + conflict_fcport->port_name); + } } /* FW already picked this loop id for another fcport */ @@ -1487,11 +1489,10 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun, wait_for_completion(&tm_iocb->u.tmf.comp); - rval = tm_iocb->u.tmf.comp_status == CS_COMPLETE ? - QLA_SUCCESS : QLA_FUNCTION_FAILED; + rval = tm_iocb->u.tmf.data; - if ((rval != QLA_SUCCESS) || tm_iocb->u.tmf.data) { - ql_dbg(ql_dbg_taskm, vha, 0x8030, + if (rval != QLA_SUCCESS) { + ql_log(ql_log_warn, vha, 0x8030, "TM IOCB failed (%x).\n", rval); } diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index 37ae0f6d8ae5..59fd5a9dfeb8 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -222,6 +222,8 @@ qla2xxx_get_qpair_sp(struct qla_qpair *qpair, fc_port_t *fcport, gfp_t flag) sp->fcport = fcport; sp->iocbs = 1; sp->vha = qpair->vha; + INIT_LIST_HEAD(&sp->elem); + done: if (!sp) QLA_QPAIR_MARK_NOT_BUSY(qpair); diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index a91cca52b5d5..dd93a22fe843 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2130,34 +2130,11 @@ __qla2x00_alloc_iocbs(struct qla_qpair *qpair, srb_t *sp) req_cnt = 1; handle = 0; - if (!sp) - goto skip_cmd_array; - - /* Check for room in outstanding command list. */ - handle = req->current_outstanding_cmd; - for (index = 1; index < req->num_outstanding_cmds; index++) { - handle++; - if (handle == req->num_outstanding_cmds) - handle = 1; - if (!req->outstanding_cmds[handle]) - break; - } - if (index == req->num_outstanding_cmds) { - ql_log(ql_log_warn, vha, 0x700b, - "No room on outstanding cmd array.\n"); - goto queuing_error; - } - - /* Prep command array. */ - req->current_outstanding_cmd = handle; - req->outstanding_cmds[handle] = sp; - sp->handle = handle; - - /* Adjust entry-counts as needed. */ - if (sp->type != SRB_SCSI_CMD) + if (sp && (sp->type != SRB_SCSI_CMD)) { + /* Adjust entry-counts as needed. */ req_cnt = sp->iocbs; + } -skip_cmd_array: /* Check for room on request queue. */ if (req->cnt < req_cnt + 2) { if (qpair->use_shadow_reg) @@ -2183,6 +2160,28 @@ skip_cmd_array: if (req->cnt < req_cnt + 2) goto queuing_error; + if (sp) { + /* Check for room in outstanding command list. */ + handle = req->current_outstanding_cmd; + for (index = 1; index < req->num_outstanding_cmds; index++) { + handle++; + if (handle == req->num_outstanding_cmds) + handle = 1; + if (!req->outstanding_cmds[handle]) + break; + } + if (index == req->num_outstanding_cmds) { + ql_log(ql_log_warn, vha, 0x700b, + "No room on outstanding cmd array.\n"); + goto queuing_error; + } + + /* Prep command array. */ + req->current_outstanding_cmd = handle; + req->outstanding_cmds[handle] = sp; + sp->handle = handle; + } + /* Prep packet */ req->cnt -= req_cnt; pkt = req->ring_ptr; @@ -2195,6 +2194,8 @@ skip_cmd_array: pkt->handle = handle; } + return pkt; + queuing_error: qpair->tgt_counters.num_alloc_iocb_failed++; return pkt; diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 9fa5a2557f2c..7756106d4555 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -631,6 +631,9 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) unsigned long flags; fc_port_t *fcport = NULL; + if (!vha->hw->flags.fw_started) + return; + /* Setup to process RIO completion. */ handle_cnt = 0; if (IS_CNA_CAPABLE(ha)) diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 7e875f575229..f0ec13d48bf3 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -4220,6 +4220,9 @@ qla25xx_init_req_que(struct scsi_qla_host *vha, struct req_que *req) mbx_cmd_t *mcp = &mc; struct qla_hw_data *ha = vha->hw; + if (!ha->flags.fw_started) + return QLA_SUCCESS; + ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d3, "Entered %s.\n", __func__); @@ -4289,6 +4292,9 @@ qla25xx_init_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp) mbx_cmd_t *mcp = &mc; struct qla_hw_data *ha = vha->hw; + if (!ha->flags.fw_started) + return QLA_SUCCESS; + ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d6, "Entered %s.\n", __func__); diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index f6f0a759a7c2..aa727d07b702 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -152,11 +152,18 @@ int qla24xx_disable_vp(scsi_qla_host_t *vha) { unsigned long flags; - int ret; + int ret = QLA_SUCCESS; + fc_port_t *fcport; + + if (vha->hw->flags.fw_started) + ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); - ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); atomic_set(&vha->loop_state, LOOP_DOWN); atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME); + list_for_each_entry(fcport, &vha->vp_fcports, list) + fcport->logout_on_delete = 0; + + qla2x00_mark_all_devices_lost(vha, 0); /* Remove port id from vp target map */ spin_lock_irqsave(&vha->hw->hardware_lock, flags); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index e881fce7477a..1fbd16c8c9a7 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -303,6 +303,7 @@ static void qla2x00_free_device(scsi_qla_host_t *); static int qla2xxx_map_queues(struct Scsi_Host *shost); static void qla2x00_destroy_deferred_work(struct qla_hw_data *); + struct scsi_host_template qla2xxx_driver_template = { .module = THIS_MODULE, .name = QLA2XXX_DRIVER_NAME, @@ -1147,7 +1148,7 @@ static inline int test_fcport_count(scsi_qla_host_t *vha) * qla2x00_wait_for_sess_deletion can only be called from remove_one. * it has dependency on UNLOADING flag to stop device discovery */ -static void +void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha) { qla2x00_mark_all_devices_lost(vha, 0); @@ -3180,6 +3181,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) "req->req_q_in=%p req->req_q_out=%p rsp->rsp_q_in=%p rsp->rsp_q_out=%p.\n", req->req_q_in, req->req_q_out, rsp->rsp_q_in, rsp->rsp_q_out); + ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0); + if (ha->isp_ops->initialize_adapter(base_vha)) { ql_log(ql_log_fatal, base_vha, 0x00d6, "Failed to initialize adapter - Adapter flags %x.\n", @@ -3216,8 +3219,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) host->can_queue, base_vha->req, base_vha->mgmt_svr_loop_id, host->sg_tablesize); - ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0); - if (ha->mqenable) { bool mq = false; bool startit = false; @@ -3603,6 +3604,8 @@ qla2x00_remove_one(struct pci_dev *pdev) base_vha = pci_get_drvdata(pdev); ha = base_vha->hw; + ql_log(ql_log_info, base_vha, 0xb079, + "Removing driver\n"); /* Indicate device removal to prevent future board_disable and wait * until any pending board_disable has completed. */ @@ -3625,6 +3628,21 @@ qla2x00_remove_one(struct pci_dev *pdev) } qla2x00_wait_for_hba_ready(base_vha); + if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha)) { + if (ha->flags.fw_started) + qla2x00_abort_isp_cleanup(base_vha); + } else if (!IS_QLAFX00(ha)) { + if (IS_QLA8031(ha)) { + ql_dbg(ql_dbg_p3p, base_vha, 0xb07e, + "Clearing fcoe driver presence.\n"); + if (qla83xx_clear_drv_presence(base_vha) != QLA_SUCCESS) + ql_dbg(ql_dbg_p3p, base_vha, 0xb079, + "Error while clearing DRV-Presence.\n"); + } + + qla2x00_try_to_stop_firmware(base_vha); + } + qla2x00_wait_for_sess_deletion(base_vha); /* @@ -3648,14 +3666,6 @@ qla2x00_remove_one(struct pci_dev *pdev) qla2x00_delete_all_vps(ha, base_vha); - if (IS_QLA8031(ha)) { - ql_dbg(ql_dbg_p3p, base_vha, 0xb07e, - "Clearing fcoe driver presence.\n"); - if (qla83xx_clear_drv_presence(base_vha) != QLA_SUCCESS) - ql_dbg(ql_dbg_p3p, base_vha, 0xb079, - "Error while clearing DRV-Presence.\n"); - } - qla2x00_abort_all_cmds(base_vha, DID_NO_CONNECT << 16); qla2x00_dfs_remove(base_vha); @@ -3715,24 +3725,6 @@ qla2x00_free_device(scsi_qla_host_t *vha) qla2x00_stop_timer(vha); qla25xx_delete_queues(vha); - - if (ha->flags.fce_enabled) - qla2x00_disable_fce_trace(vha, NULL, NULL); - - if (ha->eft) - qla2x00_disable_eft_trace(vha); - - if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha)) { - if (ha->flags.fw_started) - qla2x00_abort_isp_cleanup(vha); - } else { - if (ha->flags.fw_started) { - /* Stop currently executing firmware. */ - qla2x00_try_to_stop_firmware(vha); - ha->flags.fw_started = 0; - } - } - vha->flags.online = 0; /* turn-off interrupts on the card */ @@ -6028,8 +6020,9 @@ qla2x00_do_dpc(void *data) set_bit(ISP_ABORT_NEEDED, &base_vha->dpc_flags); } - if (test_and_clear_bit(ISP_ABORT_NEEDED, - &base_vha->dpc_flags)) { + if (test_and_clear_bit + (ISP_ABORT_NEEDED, &base_vha->dpc_flags) && + !test_bit(UNLOADING, &base_vha->dpc_flags)) { ql_dbg(ql_dbg_dpc, base_vha, 0x4007, "ISP abort scheduled.\n"); diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c index 04458eb19d38..4499c787165f 100644 --- a/drivers/scsi/qla2xxx/qla_sup.c +++ b/drivers/scsi/qla2xxx/qla_sup.c @@ -1880,6 +1880,9 @@ qla24xx_beacon_off(struct scsi_qla_host *vha) if (IS_P3P_TYPE(ha)) return QLA_SUCCESS; + if (!ha->flags.fw_started) + return QLA_SUCCESS; + ha->beacon_blink_led = 0; if (IS_QLA2031(ha) || IS_QLA27XX(ha)) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 8932ae81a15a..2715cdaa669c 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -296,6 +296,20 @@ enum blk_eh_timer_return scsi_times_out(struct request *req) rtn = host->hostt->eh_timed_out(scmd); if (rtn == BLK_EH_DONE) { + /* + * For blk-mq, we must set the request state to complete now + * before sending the request to the scsi error handler. This + * will prevent a use-after-free in the event the LLD manages + * to complete the request before the error handler finishes + * processing this timed out request. + * + * If the request was already completed, then the LLD beat the + * time out handler from transferring the request to the scsi + * error handler. In that case we can return immediately as no + * further action is required. + */ + if (req->q->mq_ops && !blk_mq_mark_complete(req)) + return rtn; if (scsi_abort_command(scmd) != SUCCESS) { set_host_byte(scmd, DID_TIME_OUT); scsi_eh_scmd_add(scmd); diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index a14fef11776e..2bf3bf73886e 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -391,7 +391,8 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf) * Check that all zones of the device are equal. The last zone can however * be smaller. The zone size must also be a power of two number of LBAs. * - * Returns the zone size in bytes upon success or an error code upon failure. + * Returns the zone size in number of blocks upon success or an error code + * upon failure. */ static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp) { @@ -401,7 +402,7 @@ static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp) unsigned char *rec; unsigned int buf_len; unsigned int list_length; - int ret; + s64 ret; u8 same; /* Get a buffer */ diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index cd2fdac000c9..ba9ba0e04f42 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1741,15 +1741,11 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) * * With scsi-mq enabled, there are a fixed number of preallocated * requests equal in number to shost->can_queue. If all of the - * preallocated requests are already in use, then using GFP_ATOMIC with - * blk_get_request() will return -EWOULDBLOCK, whereas using GFP_KERNEL - * will cause blk_get_request() to sleep until an active command - * completes, freeing up a request. Neither option is ideal, but - * GFP_KERNEL is the better choice to prevent userspace from getting an - * unexpected EWOULDBLOCK. - * - * With scsi-mq disabled, blk_get_request() with GFP_KERNEL usually - * does not sleep except under memory pressure. + * preallocated requests are already in use, then blk_get_request() + * will sleep until an active command completes, freeing up a request. + * Although waiting in an asynchronous interface is less than ideal, we + * do not want to use BLK_MQ_REQ_NOWAIT here because userspace might + * not expect an EWOULDBLOCK from this condition. */ rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0); @@ -2185,6 +2181,7 @@ sg_add_sfp(Sg_device * sdp) write_lock_irqsave(&sdp->sfd_lock, iflags); if (atomic_read(&sdp->detaching)) { write_unlock_irqrestore(&sdp->sfd_lock, iflags); + kfree(sfp); return ERR_PTR(-ENODEV); } list_add_tail(&sfp->sfd_siblings, &sdp->sfds); diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 3f3cb72e0c0c..d0389b20574d 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -523,18 +523,26 @@ static int sr_init_command(struct scsi_cmnd *SCpnt) static int sr_block_open(struct block_device *bdev, fmode_t mode) { struct scsi_cd *cd; + struct scsi_device *sdev; int ret = -ENXIO; + cd = scsi_cd_get(bdev->bd_disk); + if (!cd) + goto out; + + sdev = cd->device; + scsi_autopm_get_device(sdev); check_disk_change(bdev); mutex_lock(&sr_mutex); - cd = scsi_cd_get(bdev->bd_disk); - if (cd) { - ret = cdrom_open(&cd->cdi, bdev, mode); - if (ret) - scsi_cd_put(cd); - } + ret = cdrom_open(&cd->cdi, bdev, mode); mutex_unlock(&sr_mutex); + + scsi_autopm_put_device(sdev); + if (ret) + scsi_cd_put(cd); + +out: return ret; } @@ -562,6 +570,8 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, if (ret) goto out; + scsi_autopm_get_device(sdev); + /* * Send SCSI addressing ioctls directly to mid level, send other * ioctls to cdrom/block level. @@ -570,15 +580,18 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case SCSI_IOCTL_GET_IDLUN: case SCSI_IOCTL_GET_BUS_NUMBER: ret = scsi_ioctl(sdev, cmd, argp); - goto out; + goto put; } ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); if (ret != -ENOSYS) - goto out; + goto put; ret = scsi_ioctl(sdev, cmd, argp); +put: + scsi_autopm_put_device(sdev); + out: mutex_unlock(&sr_mutex); return ret; diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c index 777e5f1e52d1..0cd947f78b5b 100644 --- a/drivers/scsi/vmw_pvscsi.c +++ b/drivers/scsi/vmw_pvscsi.c @@ -561,9 +561,14 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter, (btstat == BTSTAT_SUCCESS || btstat == BTSTAT_LINKED_COMMAND_COMPLETED || btstat == BTSTAT_LINKED_COMMAND_COMPLETED_WITH_FLAG)) { - cmd->result = (DID_OK << 16) | sdstat; - if (sdstat == SAM_STAT_CHECK_CONDITION && cmd->sense_buffer) - cmd->result |= (DRIVER_SENSE << 24); + if (sdstat == SAM_STAT_COMMAND_TERMINATED) { + cmd->result = (DID_RESET << 16); + } else { + cmd->result = (DID_OK << 16) | sdstat; + if (sdstat == SAM_STAT_CHECK_CONDITION && + cmd->sense_buffer) + cmd->result |= (DRIVER_SENSE << 24); + } } else switch (btstat) { case BTSTAT_SUCCESS: diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c index 32f0748fd067..0097a939487f 100644 --- a/drivers/soc/imx/gpc.c +++ b/drivers/soc/imx/gpc.c @@ -27,9 +27,16 @@ #define GPC_PGC_SW2ISO_SHIFT 0x8 #define GPC_PGC_SW_SHIFT 0x0 +#define GPC_PGC_PCI_PDN 0x200 +#define GPC_PGC_PCI_SR 0x20c + #define GPC_PGC_GPU_PDN 0x260 #define GPC_PGC_GPU_PUPSCR 0x264 #define GPC_PGC_GPU_PDNSCR 0x268 +#define GPC_PGC_GPU_SR 0x26c + +#define GPC_PGC_DISP_PDN 0x240 +#define GPC_PGC_DISP_SR 0x24c #define GPU_VPU_PUP_REQ BIT(1) #define GPU_VPU_PDN_REQ BIT(0) @@ -318,10 +325,24 @@ static const struct of_device_id imx_gpc_dt_ids[] = { { } }; +static const struct regmap_range yes_ranges[] = { + regmap_reg_range(GPC_CNTR, GPC_CNTR), + regmap_reg_range(GPC_PGC_PCI_PDN, GPC_PGC_PCI_SR), + regmap_reg_range(GPC_PGC_GPU_PDN, GPC_PGC_GPU_SR), + regmap_reg_range(GPC_PGC_DISP_PDN, GPC_PGC_DISP_SR), +}; + +static const struct regmap_access_table access_table = { + .yes_ranges = yes_ranges, + .n_yes_ranges = ARRAY_SIZE(yes_ranges), +}; + static const struct regmap_config imx_gpc_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, + .rd_table = &access_table, + .wr_table = &access_table, .max_register = 0x2ac, }; diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index a1a0025b59e0..d5d33e12e952 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -402,6 +402,8 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) fput(asma->file); goto out; } + } else { + vma_set_anonymous(vma); } if (vma->vm_file) diff --git a/drivers/staging/ks7010/ks_hostif.c b/drivers/staging/ks7010/ks_hostif.c index 0ecffab52ec2..abdaf7cf8162 100644 --- a/drivers/staging/ks7010/ks_hostif.c +++ b/drivers/staging/ks7010/ks_hostif.c @@ -1842,15 +1842,15 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv) memset(set_address, 0, NIC_MAX_MCAST_LIST * ETH_ALEN); if (dev->flags & IFF_PROMISC) { - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_PROMISC); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_PROMISC); goto spin_unlock; } if ((netdev_mc_count(dev) > NIC_MAX_MCAST_LIST) || (dev->flags & IFF_ALLMULTI)) { - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_MCASTALL); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_MCASTALL); goto spin_unlock; } @@ -1866,8 +1866,8 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv) ETH_ALEN * mc_count); } else { priv->sme_i.sme_flag |= SME_MULTICAST; - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_MCAST); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_MCAST); } spin_unlock: diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c index a3a83424a926..16478fe9e3f8 100644 --- a/drivers/staging/media/omap4iss/iss_video.c +++ b/drivers/staging/media/omap4iss/iss_video.c @@ -11,7 +11,6 @@ * (at your option) any later version. */ -#include <asm/cacheflush.h> #include <linux/clk.h> #include <linux/mm.h> #include <linux/pagemap.h> @@ -24,6 +23,8 @@ #include <media/v4l2-ioctl.h> #include <media/v4l2-mc.h> +#include <asm/cacheflush.h> + #include "iss_video.h" #include "iss.h" diff --git a/drivers/staging/rtl8188eu/Kconfig b/drivers/staging/rtl8188eu/Kconfig index 673fdce25530..ff7832798a77 100644 --- a/drivers/staging/rtl8188eu/Kconfig +++ b/drivers/staging/rtl8188eu/Kconfig @@ -7,7 +7,6 @@ config R8188EU select LIB80211 select LIB80211_CRYPT_WEP select LIB80211_CRYPT_CCMP - select LIB80211_CRYPT_TKIP ---help--- This option adds the Realtek RTL8188EU USB device such as TP-Link TL-WN725N. If built as a module, it will be called r8188eu. diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c index 05936a45eb93..c6857a5be12a 100644 --- a/drivers/staging/rtl8188eu/core/rtw_recv.c +++ b/drivers/staging/rtl8188eu/core/rtw_recv.c @@ -23,7 +23,6 @@ #include <mon.h> #include <wifi.h> #include <linux/vmalloc.h> -#include <net/lib80211.h> #define ETHERNET_HEADER_SIZE 14 /* Ethernet Header Length */ #define LLC_HEADER_SIZE 6 /* LLC Header Length */ @@ -221,20 +220,31 @@ u32 rtw_free_uc_swdec_pending_queue(struct adapter *adapter) static int recvframe_chkmic(struct adapter *adapter, struct recv_frame *precvframe) { - int res = _SUCCESS; - struct rx_pkt_attrib *prxattrib = &precvframe->attrib; - struct sta_info *stainfo = rtw_get_stainfo(&adapter->stapriv, prxattrib->ta); + int i, res = _SUCCESS; + u32 datalen; + u8 miccode[8]; + u8 bmic_err = false, brpt_micerror = true; + u8 *pframe, *payload, *pframemic; + u8 *mickey; + struct sta_info *stainfo; + struct rx_pkt_attrib *prxattrib = &precvframe->attrib; + struct security_priv *psecuritypriv = &adapter->securitypriv; + + struct mlme_ext_priv *pmlmeext = &adapter->mlmeextpriv; + struct mlme_ext_info *pmlmeinfo = &(pmlmeext->mlmext_info); + + stainfo = rtw_get_stainfo(&adapter->stapriv, &prxattrib->ta[0]); if (prxattrib->encrypt == _TKIP_) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: prxattrib->encrypt==_TKIP_\n", __func__)); + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: da=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + __func__, prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2], + prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5])); + + /* calculate mic code */ if (stainfo) { - int key_idx; - const int iv_len = 8, icv_len = 4, key_length = 32; - struct sk_buff *skb = precvframe->pkt; - u8 key[32], iv[8], icv[4], *pframe = skb->data; - void *crypto_private = NULL; - struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip"); - struct security_priv *psecuritypriv = &adapter->securitypriv; - if (IS_MCAST(prxattrib->ra)) { if (!psecuritypriv) { res = _FAIL; @@ -243,58 +253,115 @@ static int recvframe_chkmic(struct adapter *adapter, DBG_88E("\n %s: didn't install group key!!!!!!!!!!\n", __func__); goto exit; } - key_idx = prxattrib->key_index; - memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16); - memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16); + mickey = &psecuritypriv->dot118021XGrprxmickey[prxattrib->key_index].skey[0]; + + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: bcmc key\n", __func__)); } else { - key_idx = 0; - memcpy(key, stainfo->dot118021x_UncstKey.skey, 16); - memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16); + mickey = &stainfo->dot11tkiprxmickey.skey[0]; + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n %s: unicast key\n", __func__)); } - if (!crypto_ops) { - res = _FAIL; - goto exit_lib80211_tkip; - } + /* icv_len included the mic code */ + datalen = precvframe->pkt->len-prxattrib->hdrlen - + prxattrib->iv_len-prxattrib->icv_len-8; + pframe = precvframe->pkt->data; + payload = pframe+prxattrib->hdrlen+prxattrib->iv_len; - memcpy(iv, pframe + prxattrib->hdrlen, iv_len); - memcpy(icv, pframe + skb->len - icv_len, icv_len); - memmove(pframe + iv_len, pframe, prxattrib->hdrlen); + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, ("\n prxattrib->iv_len=%d prxattrib->icv_len=%d\n", prxattrib->iv_len, prxattrib->icv_len)); + rtw_seccalctkipmic(mickey, pframe, payload, datalen, &miccode[0], + (unsigned char)prxattrib->priority); /* care the length of the data */ - skb_pull(skb, iv_len); - skb_trim(skb, skb->len - icv_len); + pframemic = payload+datalen; - crypto_private = crypto_ops->init(key_idx); - if (!crypto_private) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->decrypt_msdu(skb, key_idx, prxattrib->hdrlen, crypto_private)) { - res = _FAIL; - goto exit_lib80211_tkip; + bmic_err = false; + + for (i = 0; i < 8; i++) { + if (miccode[i] != *(pframemic+i)) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("%s: miccode[%d](%02x)!=*(pframemic+%d)(%02x) ", + __func__, i, miccode[i], i, *(pframemic + i))); + bmic_err = true; + } } - memmove(pframe, pframe + iv_len, prxattrib->hdrlen); - skb_push(skb, iv_len); - skb_put(skb, icv_len); + if (bmic_err) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n *(pframemic-8)-*(pframemic-1)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + *(pframemic-8), *(pframemic-7), *(pframemic-6), + *(pframemic-5), *(pframemic-4), *(pframemic-3), + *(pframemic-2), *(pframemic-1))); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n *(pframemic-16)-*(pframemic-9)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + *(pframemic-16), *(pframemic-15), *(pframemic-14), + *(pframemic-13), *(pframemic-12), *(pframemic-11), + *(pframemic-10), *(pframemic-9))); + { + uint i; - memcpy(pframe + prxattrib->hdrlen, iv, iv_len); - memcpy(pframe + skb->len - icv_len, icv, icv_len); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n ======demp packet (len=%d)======\n", + precvframe->pkt->len)); + for (i = 0; i < precvframe->pkt->len; i += 8) { + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x", + *(precvframe->pkt->data+i), + *(precvframe->pkt->data+i+1), + *(precvframe->pkt->data+i+2), + *(precvframe->pkt->data+i+3), + *(precvframe->pkt->data+i+4), + *(precvframe->pkt->data+i+5), + *(precvframe->pkt->data+i+6), + *(precvframe->pkt->data+i+7))); + } + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("\n ====== demp packet end [len=%d]======\n", + precvframe->pkt->len)); + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("\n hrdlen=%d,\n", + prxattrib->hdrlen)); + } -exit_lib80211_tkip: - if (crypto_ops && crypto_private) - crypto_ops->deinit(crypto_private); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("ra=0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x psecuritypriv->binstallGrpkey=%d ", + prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2], + prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5], psecuritypriv->binstallGrpkey)); + + /* double check key_index for some timing issue , */ + /* cannot compare with psecuritypriv->dot118021XGrpKeyid also cause timing issue */ + if ((IS_MCAST(prxattrib->ra) == true) && (prxattrib->key_index != pmlmeinfo->key_index)) + brpt_micerror = false; + + if ((prxattrib->bdecrypted) && (brpt_micerror)) { + rtw_handle_tkip_mic_err(adapter, (u8)IS_MCAST(prxattrib->ra)); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted)); + DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted); + } else { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted)); + DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted); + } + res = _FAIL; + } else { + /* mic checked ok */ + if ((!psecuritypriv->bcheck_grpkey) && (IS_MCAST(prxattrib->ra))) { + psecuritypriv->bcheck_grpkey = true; + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("psecuritypriv->bcheck_grpkey = true")); + } + } } else { RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("%s: rtw_get_stainfo==NULL!!!\n", __func__)); } + + skb_trim(precvframe->pkt, precvframe->pkt->len - 8); } exit: + return res; } diff --git a/drivers/staging/rtl8188eu/core/rtw_security.c b/drivers/staging/rtl8188eu/core/rtw_security.c index bfe0b217e679..67a2490f055e 100644 --- a/drivers/staging/rtl8188eu/core/rtw_security.c +++ b/drivers/staging/rtl8188eu/core/rtw_security.c @@ -650,71 +650,71 @@ u32 rtw_tkip_encrypt(struct adapter *padapter, u8 *pxmitframe) return res; } +/* The hlen isn't include the IV */ u32 rtw_tkip_decrypt(struct adapter *padapter, u8 *precvframe) -{ - struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib; - u32 res = _SUCCESS; +{ /* exclude ICV */ + u16 pnl; + u32 pnh; + u8 rc4key[16]; + u8 ttkey[16]; + u8 crc[4]; + struct arc4context mycontext; + int length; + + u8 *pframe, *payload, *iv, *prwskey; + union pn48 dot11txpn; + struct sta_info *stainfo; + struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib; + struct security_priv *psecuritypriv = &padapter->securitypriv; + u32 res = _SUCCESS; + + + pframe = (unsigned char *)((struct recv_frame *)precvframe)->pkt->data; /* 4 start to decrypt recvframe */ if (prxattrib->encrypt == _TKIP_) { - struct sta_info *stainfo = rtw_get_stainfo(&padapter->stapriv, prxattrib->ta); - + stainfo = rtw_get_stainfo(&padapter->stapriv, &prxattrib->ta[0]); if (stainfo) { - int key_idx; - const int iv_len = 8, icv_len = 4, key_length = 32; - void *crypto_private = NULL; - struct sk_buff *skb = ((struct recv_frame *)precvframe)->pkt; - u8 key[32], iv[8], icv[4], *pframe = skb->data; - struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip"); - struct security_priv *psecuritypriv = &padapter->securitypriv; - if (IS_MCAST(prxattrib->ra)) { if (!psecuritypriv->binstallGrpkey) { res = _FAIL; DBG_88E("%s:rx bc/mc packets, but didn't install group key!!!!!!!!!!\n", __func__); goto exit; } - key_idx = prxattrib->key_index; - memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16); - memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16); + prwskey = psecuritypriv->dot118021XGrpKey[prxattrib->key_index].skey; } else { - key_idx = 0; - memcpy(key, stainfo->dot118021x_UncstKey.skey, 16); - memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16); + RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("%s: stainfo!= NULL!!!\n", __func__)); + prwskey = &stainfo->dot118021x_UncstKey.skey[0]; } - if (!crypto_ops) { - res = _FAIL; - goto exit_lib80211_tkip; - } + iv = pframe+prxattrib->hdrlen; + payload = pframe+prxattrib->iv_len+prxattrib->hdrlen; + length = ((struct recv_frame *)precvframe)->pkt->len-prxattrib->hdrlen-prxattrib->iv_len; - memcpy(iv, pframe + prxattrib->hdrlen, iv_len); - memcpy(icv, pframe + skb->len - icv_len, icv_len); + GET_TKIP_PN(iv, dot11txpn); - crypto_private = crypto_ops->init(key_idx); - if (!crypto_private) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->decrypt_mpdu(skb, prxattrib->hdrlen, crypto_private)) { - res = _FAIL; - goto exit_lib80211_tkip; - } + pnl = (u16)(dot11txpn.val); + pnh = (u32)(dot11txpn.val>>16); - memmove(pframe, pframe + iv_len, prxattrib->hdrlen); - skb_push(skb, iv_len); - skb_put(skb, icv_len); + phase1((u16 *)&ttkey[0], prwskey, &prxattrib->ta[0], pnh); + phase2(&rc4key[0], prwskey, (unsigned short *)&ttkey[0], pnl); - memcpy(pframe + prxattrib->hdrlen, iv, iv_len); - memcpy(pframe + skb->len - icv_len, icv, icv_len); + /* 4 decrypt payload include icv */ -exit_lib80211_tkip: - if (crypto_ops && crypto_private) - crypto_ops->deinit(crypto_private); + arcfour_init(&mycontext, rc4key, 16); + arcfour_encrypt(&mycontext, payload, payload, length); + + *((__le32 *)crc) = getcrc32(payload, length-4); + + if (crc[3] != payload[length-1] || + crc[2] != payload[length-2] || + crc[1] != payload[length-3] || + crc[0] != payload[length-4]) { + RT_TRACE(_module_rtl871x_security_c_, _drv_err_, + ("rtw_wep_decrypt:icv error crc (%4ph)!=payload (%4ph)\n", + &crc, &payload[length-4])); + res = _FAIL; + } } else { RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("rtw_tkip_decrypt: stainfo==NULL!!!\n")); res = _FAIL; diff --git a/drivers/staging/speakup/speakup_soft.c b/drivers/staging/speakup/speakup_soft.c index a61bc41b82d7..947c79532e10 100644 --- a/drivers/staging/speakup/speakup_soft.c +++ b/drivers/staging/speakup/speakup_soft.c @@ -198,11 +198,15 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count, int chars_sent = 0; char __user *cp; char *init; + size_t bytes_per_ch = unicode ? 3 : 1; u16 ch; int empty; unsigned long flags; DEFINE_WAIT(wait); + if (count < bytes_per_ch) + return -EINVAL; + spin_lock_irqsave(&speakup_info.spinlock, flags); while (1) { prepare_to_wait(&speakup_event, &wait, TASK_INTERRUPTIBLE); @@ -228,7 +232,7 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count, init = get_initstring(); /* Keep 3 bytes available for a 16bit UTF-8-encoded character */ - while (chars_sent <= count - 3) { + while (chars_sent <= count - bytes_per_ch) { if (speakup_info.flushing) { speakup_info.flushing = 0; ch = '\x18'; diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c index 514986b57c2d..25eb3891e34b 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_target.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c @@ -652,6 +652,7 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk) struct iscsi_param *param; u32 mrdsl, mbl; u32 max_npdu, max_iso_npdu; + u32 max_iso_payload; if (conn->login->leading_connection) { param = iscsi_find_param_from_key(MAXBURSTLENGTH, @@ -670,8 +671,10 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk) mrdsl = conn_ops->MaxRecvDataSegmentLength; max_npdu = mbl / mrdsl; - max_iso_npdu = CXGBIT_MAX_ISO_PAYLOAD / - (ISCSI_HDR_LEN + mrdsl + + max_iso_payload = rounddown(CXGBIT_MAX_ISO_PAYLOAD, csk->emss); + + max_iso_npdu = max_iso_payload / + (ISCSI_HDR_LEN + mrdsl + cxgbit_digest_len[csk->submode]); csk->max_iso_npdu = min(max_npdu, max_iso_npdu); @@ -741,6 +744,9 @@ static int cxgbit_set_params(struct iscsi_conn *conn) if (conn_ops->MaxRecvDataSegmentLength > cdev->mdsl) conn_ops->MaxRecvDataSegmentLength = cdev->mdsl; + if (cxgbit_set_digest(csk)) + return -1; + if (conn->login->leading_connection) { param = iscsi_find_param_from_key(ERRORRECOVERYLEVEL, conn->param_list); @@ -764,7 +770,7 @@ static int cxgbit_set_params(struct iscsi_conn *conn) if (is_t5(cdev->lldi.adapter_type)) goto enable_ddp; else - goto enable_digest; + return 0; } if (test_bit(CDEV_ISO_ENABLE, &cdev->flags)) { @@ -781,10 +787,6 @@ enable_ddp: } } -enable_digest: - if (cxgbit_set_digest(csk)) - return -1; - return 0; } diff --git a/drivers/usb/chipidea/Kconfig b/drivers/usb/chipidea/Kconfig index 785f0ed037f7..ee34e9046f7e 100644 --- a/drivers/usb/chipidea/Kconfig +++ b/drivers/usb/chipidea/Kconfig @@ -3,6 +3,7 @@ config USB_CHIPIDEA depends on ((USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET)) && HAS_DMA select EXTCON select RESET_CONTROLLER + select USB_ULPI_BUS help Say Y here if your system has a dual role high speed USB controller based on ChipIdea silicon IP. It supports: @@ -38,12 +39,4 @@ config USB_CHIPIDEA_HOST help Say Y here to enable host controller functionality of the ChipIdea driver. - -config USB_CHIPIDEA_ULPI - bool "ChipIdea ULPI PHY support" - depends on USB_ULPI_BUS=y || USB_ULPI_BUS=USB_CHIPIDEA - help - Say Y here if you have a ULPI PHY attached to your ChipIdea - controller. - endif diff --git a/drivers/usb/chipidea/Makefile b/drivers/usb/chipidea/Makefile index e3d5e728fa53..12df94f78f72 100644 --- a/drivers/usb/chipidea/Makefile +++ b/drivers/usb/chipidea/Makefile @@ -1,11 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_USB_CHIPIDEA) += ci_hdrc.o -ci_hdrc-y := core.o otg.o debug.o +ci_hdrc-y := core.o otg.o debug.o ulpi.o ci_hdrc-$(CONFIG_USB_CHIPIDEA_UDC) += udc.o ci_hdrc-$(CONFIG_USB_CHIPIDEA_HOST) += host.o ci_hdrc-$(CONFIG_USB_OTG_FSM) += otg_fsm.o -ci_hdrc-$(CONFIG_USB_CHIPIDEA_ULPI) += ulpi.o # Glue/Bridge layers go here diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h index 0bf244d50544..6a2cc5cd0281 100644 --- a/drivers/usb/chipidea/ci.h +++ b/drivers/usb/chipidea/ci.h @@ -240,10 +240,8 @@ struct ci_hdrc { struct ci_hdrc_platform_data *platdata; int vbus_active; -#ifdef CONFIG_USB_CHIPIDEA_ULPI struct ulpi *ulpi; struct ulpi_ops ulpi_ops; -#endif struct phy *phy; /* old usb_phy interface */ struct usb_phy *usb_phy; @@ -426,15 +424,9 @@ static inline bool ci_otg_is_fsm_mode(struct ci_hdrc *ci) #endif } -#if IS_ENABLED(CONFIG_USB_CHIPIDEA_ULPI) int ci_ulpi_init(struct ci_hdrc *ci); void ci_ulpi_exit(struct ci_hdrc *ci); int ci_ulpi_resume(struct ci_hdrc *ci); -#else -static inline int ci_ulpi_init(struct ci_hdrc *ci) { return 0; } -static inline void ci_ulpi_exit(struct ci_hdrc *ci) { } -static inline int ci_ulpi_resume(struct ci_hdrc *ci) { return 0; } -#endif u32 hw_read_intr_enable(struct ci_hdrc *ci); diff --git a/drivers/usb/chipidea/ulpi.c b/drivers/usb/chipidea/ulpi.c index 6da42dcd2888..dfec07e8ae1d 100644 --- a/drivers/usb/chipidea/ulpi.c +++ b/drivers/usb/chipidea/ulpi.c @@ -95,6 +95,9 @@ int ci_ulpi_resume(struct ci_hdrc *ci) { int cnt = 100000; + if (ci->platdata->phy_mode != USBPHY_INTERFACE_MODE_ULPI) + return 0; + while (cnt-- > 0) { if (hw_read(ci, OP_ULPI_VIEWPORT, ULPI_SYNC_STATE)) return 0; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 998b32d0167e..75c4623ad779 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1831,6 +1831,9 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */ .driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */ }, + { USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */ + .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */ + }, { USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */ .driver_info = CLEAR_HALT_CONDITIONS, diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index fcae521df29b..1fb266809966 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1142,10 +1142,14 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) if (!udev || udev->state == USB_STATE_NOTATTACHED) { /* Tell hub_wq to disconnect the device or - * check for a new connection + * check for a new connection or over current condition. + * Based on USB2.0 Spec Section 11.12.5, + * C_PORT_OVER_CURRENT could be set while + * PORT_OVER_CURRENT is not. So check for any of them. */ if (udev || (portstatus & USB_PORT_STAT_CONNECTION) || - (portstatus & USB_PORT_STAT_OVERCURRENT)) + (portstatus & USB_PORT_STAT_OVERCURRENT) || + (portchange & USB_PORT_STAT_C_OVERCURRENT)) set_bit(port1, hub->change_bits); } else if (portstatus & USB_PORT_STAT_ENABLE) { diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index a0f82cca2d9a..cefc99ae69b2 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -3430,7 +3430,7 @@ static void dwc2_gadget_handle_incomplete_isoc_in(struct dwc2_hsotg *hsotg) for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_in[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DIEPCTL(idx)); @@ -3476,7 +3476,7 @@ static void dwc2_gadget_handle_incomplete_isoc_out(struct dwc2_hsotg *hsotg) for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_out[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx)); @@ -3650,7 +3650,7 @@ irq_retry: for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_out[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx)); diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index b1104be3429c..6e2cdd7b93d4 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -2665,34 +2665,35 @@ static int dwc2_alloc_split_dma_aligned_buf(struct dwc2_hsotg *hsotg, #define DWC2_USB_DMA_ALIGN 4 -struct dma_aligned_buffer { - void *kmalloc_ptr; - void *old_xfer_buffer; - u8 data[0]; -}; - static void dwc2_free_dma_aligned_buffer(struct urb *urb) { - struct dma_aligned_buffer *temp; + void *stored_xfer_buffer; + size_t length; if (!(urb->transfer_flags & URB_ALIGNED_TEMP_BUFFER)) return; - temp = container_of(urb->transfer_buffer, - struct dma_aligned_buffer, data); + /* Restore urb->transfer_buffer from the end of the allocated area */ + memcpy(&stored_xfer_buffer, urb->transfer_buffer + + urb->transfer_buffer_length, sizeof(urb->transfer_buffer)); - if (usb_urb_dir_in(urb)) - memcpy(temp->old_xfer_buffer, temp->data, - urb->transfer_buffer_length); - urb->transfer_buffer = temp->old_xfer_buffer; - kfree(temp->kmalloc_ptr); + if (usb_urb_dir_in(urb)) { + if (usb_pipeisoc(urb->pipe)) + length = urb->transfer_buffer_length; + else + length = urb->actual_length; + + memcpy(stored_xfer_buffer, urb->transfer_buffer, length); + } + kfree(urb->transfer_buffer); + urb->transfer_buffer = stored_xfer_buffer; urb->transfer_flags &= ~URB_ALIGNED_TEMP_BUFFER; } static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags) { - struct dma_aligned_buffer *temp, *kmalloc_ptr; + void *kmalloc_ptr; size_t kmalloc_size; if (urb->num_sgs || urb->sg || @@ -2700,22 +2701,29 @@ static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags) !((uintptr_t)urb->transfer_buffer & (DWC2_USB_DMA_ALIGN - 1))) return 0; - /* Allocate a buffer with enough padding for alignment */ + /* + * Allocate a buffer with enough padding for original transfer_buffer + * pointer. This allocation is guaranteed to be aligned properly for + * DMA + */ kmalloc_size = urb->transfer_buffer_length + - sizeof(struct dma_aligned_buffer) + DWC2_USB_DMA_ALIGN - 1; + sizeof(urb->transfer_buffer); kmalloc_ptr = kmalloc(kmalloc_size, mem_flags); if (!kmalloc_ptr) return -ENOMEM; - /* Position our struct dma_aligned_buffer such that data is aligned */ - temp = PTR_ALIGN(kmalloc_ptr + 1, DWC2_USB_DMA_ALIGN) - 1; - temp->kmalloc_ptr = kmalloc_ptr; - temp->old_xfer_buffer = urb->transfer_buffer; + /* + * Position value of original urb->transfer_buffer pointer to the end + * of allocation for later referencing + */ + memcpy(kmalloc_ptr + urb->transfer_buffer_length, + &urb->transfer_buffer, sizeof(urb->transfer_buffer)); + if (usb_urb_dir_out(urb)) - memcpy(temp->data, urb->transfer_buffer, + memcpy(kmalloc_ptr, urb->transfer_buffer, urb->transfer_buffer_length); - urb->transfer_buffer = temp->data; + urb->transfer_buffer = kmalloc_ptr; urb->transfer_flags |= URB_ALIGNED_TEMP_BUFFER; diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c index ed7f05cf4906..8ce10caf3e19 100644 --- a/drivers/usb/dwc2/hcd_intr.c +++ b/drivers/usb/dwc2/hcd_intr.c @@ -1231,7 +1231,10 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg, * avoid interrupt storms we'll wait before retrying if we've got * several NAKs. If we didn't do this we'd retry directly from the * interrupt handler and could end up quickly getting another - * interrupt (another NAK), which we'd retry. + * interrupt (another NAK), which we'd retry. Note that we do not + * delay retries for IN parts of control requests, as those are expected + * to complete fairly quickly, and if we delay them we risk confusing + * the device and cause it issue STALL. * * Note that in DMA mode software only gets involved to re-send NAKed * transfers for split transactions, so we only need to apply this @@ -1244,7 +1247,9 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg, qtd->error_count = 0; qtd->complete_split = 0; qtd->num_naks++; - qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY; + qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY && + !(chan->ep_type == USB_ENDPOINT_XFER_CONTROL && + chan->ep_is_in); dwc2_halt_channel(hsotg, chan, qtd, DWC2_HC_XFER_NAK); goto handle_nak_done; } diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index c77ff50a88a2..8efde178eef4 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -973,15 +973,12 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, ret = dwc3_ep0_start_trans(dep); } else if (IS_ALIGNED(req->request.length, dep->endpoint.maxpacket) && req->request.length && req->request.zero) { - u32 maxpacket; ret = usb_gadget_map_request_by_dev(dwc->sysdev, &req->request, dep->number); if (ret) return; - maxpacket = dep->endpoint.maxpacket; - /* prepare normal TRB */ dwc3_ep0_prepare_one_trb(dep, req->request.dma, req->request.length, diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index d2fa071c21b1..b8a15840b4ff 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1819,7 +1819,6 @@ unknown: if (cdev->use_os_string && cdev->os_desc_config && (ctrl->bRequestType & USB_TYPE_VENDOR) && ctrl->bRequest == cdev->b_vendor_code) { - struct usb_request *req; struct usb_configuration *os_desc_cfg; u8 *buf; int interface; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 33e2030503fa..3ada83d81bda 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3263,7 +3263,7 @@ static int ffs_func_setup(struct usb_function *f, __ffs_event_add(ffs, FUNCTIONFS_SETUP); spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags); - return USB_GADGET_DELAYED_STATUS; + return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; } static bool ffs_func_req_match(struct usb_function *f, diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index d2dc1f00180b..d582921f7257 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -438,14 +438,14 @@ static struct usb_descriptor_header *hs_audio_desc[] = { }; struct cntrl_cur_lay3 { - __u32 dCUR; + __le32 dCUR; }; struct cntrl_range_lay3 { - __u16 wNumSubRanges; - __u32 dMIN; - __u32 dMAX; - __u32 dRES; + __le16 wNumSubRanges; + __le32 dMIN; + __le32 dMAX; + __le32 dRES; } __packed; static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts, @@ -559,13 +559,13 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc); if (!agdev->out_ep) { dev_err(dev, "%s:%d Error!\n", __func__, __LINE__); - return ret; + return -ENODEV; } agdev->in_ep = usb_ep_autoconfig(gadget, &fs_epin_desc); if (!agdev->in_ep) { dev_err(dev, "%s:%d Error!\n", __func__, __LINE__); - return ret; + return -ENODEV; } agdev->in_ep_maxpsize = max_t(u16, @@ -703,9 +703,9 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr) memset(&c, 0, sizeof(struct cntrl_cur_lay3)); if (entity_id == USB_IN_CLK_ID) - c.dCUR = p_srate; + c.dCUR = cpu_to_le32(p_srate); else if (entity_id == USB_OUT_CLK_ID) - c.dCUR = c_srate; + c.dCUR = cpu_to_le32(c_srate); value = min_t(unsigned, w_length, sizeof c); memcpy(req->buf, &c, value); @@ -742,15 +742,15 @@ in_rq_range(struct usb_function *fn, const struct usb_ctrlrequest *cr) if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) { if (entity_id == USB_IN_CLK_ID) - r.dMIN = p_srate; + r.dMIN = cpu_to_le32(p_srate); else if (entity_id == USB_OUT_CLK_ID) - r.dMIN = c_srate; + r.dMIN = cpu_to_le32(c_srate); else return -EOPNOTSUPP; r.dMAX = r.dMIN; r.dRES = 0; - r.wNumSubRanges = 1; + r.wNumSubRanges = cpu_to_le16(1); value = min_t(unsigned, w_length, sizeof r); memcpy(req->buf, &r, value); diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c index a72295c953bb..fb5ed97572e5 100644 --- a/drivers/usb/gadget/function/u_audio.c +++ b/drivers/usb/gadget/function/u_audio.c @@ -32,9 +32,6 @@ struct uac_req { struct uac_rtd_params { struct snd_uac_chip *uac; /* parent chip */ bool ep_enabled; /* if the ep is enabled */ - /* Size of the ring buffer */ - size_t dma_bytes; - unsigned char *dma_area; struct snd_pcm_substream *ss; @@ -43,8 +40,6 @@ struct uac_rtd_params { void *rbuf; - size_t period_size; - unsigned max_psize; /* MaxPacketSize of endpoint */ struct uac_req *ureq; @@ -84,12 +79,12 @@ static const struct snd_pcm_hardware uac_pcm_hardware = { static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) { unsigned pending; - unsigned long flags; + unsigned long flags, flags2; unsigned int hw_ptr; - bool update_alsa = false; int status = req->status; struct uac_req *ur = req->context; struct snd_pcm_substream *substream; + struct snd_pcm_runtime *runtime; struct uac_rtd_params *prm = ur->pp; struct snd_uac_chip *uac = prm->uac; @@ -111,6 +106,14 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) if (!substream) goto exit; + snd_pcm_stream_lock_irqsave(substream, flags2); + + runtime = substream->runtime; + if (!runtime || !snd_pcm_running(substream)) { + snd_pcm_stream_unlock_irqrestore(substream, flags2); + goto exit; + } + spin_lock_irqsave(&prm->lock, flags); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { @@ -137,43 +140,46 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) req->actual = req->length; } - pending = prm->hw_ptr % prm->period_size; - pending += req->actual; - if (pending >= prm->period_size) - update_alsa = true; - hw_ptr = prm->hw_ptr; - prm->hw_ptr = (prm->hw_ptr + req->actual) % prm->dma_bytes; spin_unlock_irqrestore(&prm->lock, flags); /* Pack USB load in ALSA ring buffer */ - pending = prm->dma_bytes - hw_ptr; + pending = runtime->dma_bytes - hw_ptr; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { if (unlikely(pending < req->actual)) { - memcpy(req->buf, prm->dma_area + hw_ptr, pending); - memcpy(req->buf + pending, prm->dma_area, + memcpy(req->buf, runtime->dma_area + hw_ptr, pending); + memcpy(req->buf + pending, runtime->dma_area, req->actual - pending); } else { - memcpy(req->buf, prm->dma_area + hw_ptr, req->actual); + memcpy(req->buf, runtime->dma_area + hw_ptr, + req->actual); } } else { if (unlikely(pending < req->actual)) { - memcpy(prm->dma_area + hw_ptr, req->buf, pending); - memcpy(prm->dma_area, req->buf + pending, + memcpy(runtime->dma_area + hw_ptr, req->buf, pending); + memcpy(runtime->dma_area, req->buf + pending, req->actual - pending); } else { - memcpy(prm->dma_area + hw_ptr, req->buf, req->actual); + memcpy(runtime->dma_area + hw_ptr, req->buf, + req->actual); } } + spin_lock_irqsave(&prm->lock, flags); + /* update hw_ptr after data is copied to memory */ + prm->hw_ptr = (hw_ptr + req->actual) % runtime->dma_bytes; + hw_ptr = prm->hw_ptr; + spin_unlock_irqrestore(&prm->lock, flags); + snd_pcm_stream_unlock_irqrestore(substream, flags2); + + if ((hw_ptr % snd_pcm_lib_period_bytes(substream)) < req->actual) + snd_pcm_period_elapsed(substream); + exit: if (usb_ep_queue(ep, req, GFP_ATOMIC)) dev_err(uac->card->dev, "%d Error!\n", __LINE__); - - if (update_alsa) - snd_pcm_period_elapsed(substream); } static int uac_pcm_trigger(struct snd_pcm_substream *substream, int cmd) @@ -236,40 +242,12 @@ static snd_pcm_uframes_t uac_pcm_pointer(struct snd_pcm_substream *substream) static int uac_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *hw_params) { - struct snd_uac_chip *uac = snd_pcm_substream_chip(substream); - struct uac_rtd_params *prm; - int err; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - prm = &uac->p_prm; - else - prm = &uac->c_prm; - - err = snd_pcm_lib_malloc_pages(substream, + return snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params)); - if (err >= 0) { - prm->dma_bytes = substream->runtime->dma_bytes; - prm->dma_area = substream->runtime->dma_area; - prm->period_size = params_period_bytes(hw_params); - } - - return err; } static int uac_pcm_hw_free(struct snd_pcm_substream *substream) { - struct snd_uac_chip *uac = snd_pcm_substream_chip(substream); - struct uac_rtd_params *prm; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - prm = &uac->p_prm; - else - prm = &uac->c_prm; - - prm->dma_area = NULL; - prm->dma_bytes = 0; - prm->period_size = 0; - return snd_pcm_lib_free_pages(substream); } @@ -595,15 +573,15 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name, if (err < 0) goto snd_fail; - strcpy(pcm->name, pcm_name); + strlcpy(pcm->name, pcm_name, sizeof(pcm->name)); pcm->private_data = uac; uac->pcm = pcm; snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &uac_pcm_ops); snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &uac_pcm_ops); - strcpy(card->driver, card_name); - strcpy(card->shortname, card_name); + strlcpy(card->driver, card_name, sizeof(card->driver)); + strlcpy(card->shortname, card_name, sizeof(card->shortname)); sprintf(card->longname, "%s %i", card_name, card->dev->id); snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS, diff --git a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c index 20ffb03ff6ac..e2927fb083cf 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c @@ -108,6 +108,13 @@ void ast_vhub_ep0_handle_setup(struct ast_vhub_ep *ep) /* Check our state, cancel pending requests if needed */ if (ep->ep0.state != ep0_state_token) { EPDBG(ep, "wrong state\n"); + ast_vhub_nuke(ep, -EIO); + + /* + * Accept the packet regardless, this seems to happen + * when stalling a SETUP packet that has an OUT data + * phase. + */ ast_vhub_nuke(ep, 0); goto stall; } @@ -212,6 +219,8 @@ static void ast_vhub_ep0_do_send(struct ast_vhub_ep *ep, if (chunk && req->req.buf) memcpy(ep->buf, req->req.buf + req->req.actual, chunk); + vhub_dma_workaround(ep->buf); + /* Remember chunk size and trigger send */ reg = VHUB_EP0_SET_TX_LEN(chunk); writel(reg, ep->ep0.ctlstat); @@ -224,7 +233,7 @@ static void ast_vhub_ep0_rx_prime(struct ast_vhub_ep *ep) EPVDBG(ep, "rx prime\n"); /* Prime endpoint for receiving data */ - writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat + AST_VHUB_EP0_CTRL); + writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat); } static void ast_vhub_ep0_do_receive(struct ast_vhub_ep *ep, struct ast_vhub_req *req, diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c index 80c9feac5147..5939eb1e97f2 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/epn.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c @@ -66,11 +66,16 @@ static void ast_vhub_epn_kick(struct ast_vhub_ep *ep, struct ast_vhub_req *req) if (!req->req.dma) { /* For IN transfers, copy data over first */ - if (ep->epn.is_in) + if (ep->epn.is_in) { memcpy(ep->buf, req->req.buf + act, chunk); + vhub_dma_workaround(ep->buf); + } writel(ep->buf_dma, ep->epn.regs + AST_VHUB_EP_DESC_BASE); - } else + } else { + if (ep->epn.is_in) + vhub_dma_workaround(req->req.buf); writel(req->req.dma + act, ep->epn.regs + AST_VHUB_EP_DESC_BASE); + } /* Start DMA */ req->active = true; @@ -161,6 +166,7 @@ static inline unsigned int ast_vhub_count_free_descs(struct ast_vhub_ep *ep) static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, struct ast_vhub_req *req) { + struct ast_vhub_desc *desc = NULL; unsigned int act = req->act_count; unsigned int len = req->req.length; unsigned int chunk; @@ -177,7 +183,6 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, /* While we can create descriptors */ while (ast_vhub_count_free_descs(ep) && req->last_desc < 0) { - struct ast_vhub_desc *desc; unsigned int d_num; /* Grab next free descriptor */ @@ -227,6 +232,9 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, req->act_count = act = act + chunk; } + if (likely(desc)) + vhub_dma_workaround(desc); + /* Tell HW about new descriptors */ writel(VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next), ep->epn.regs + AST_VHUB_EP_DESC_STATUS); diff --git a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h index 2b040257bc1f..4ed03d33a5a9 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h +++ b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h @@ -462,6 +462,39 @@ enum std_req_rc { #define DDBG(d, fmt, ...) do { } while(0) #endif +static inline void vhub_dma_workaround(void *addr) +{ + /* + * This works around a confirmed HW issue with the Aspeed chip. + * + * The core uses a different bus to memory than the AHB going to + * the USB device controller. Due to the latter having a higher + * priority than the core for arbitration on that bus, it's + * possible for an MMIO to the device, followed by a DMA by the + * device from memory to all be performed and services before + * a previous store to memory gets completed. + * + * This the following scenario can happen: + * + * - Driver writes to a DMA descriptor (Mbus) + * - Driver writes to the MMIO register to start the DMA (AHB) + * - The gadget sees the second write and sends a read of the + * descriptor to the memory controller (Mbus) + * - The gadget hits memory before the descriptor write + * causing it to read an obsolete value. + * + * Thankfully the problem is limited to the USB gadget device, other + * masters in the SoC all have a lower priority than the core, thus + * ensuring that the store by the core arrives first. + * + * The workaround consists of using a dummy read of the memory before + * doing the MMIO writes. This will ensure that the previous writes + * have been "pushed out". + */ + mb(); + (void)__raw_readl((void __iomem *)addr); +} + /* core.c */ void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req, int status); diff --git a/drivers/usb/gadget/udc/r8a66597-udc.c b/drivers/usb/gadget/udc/r8a66597-udc.c index a3ecce62662b..11e25a3f4f1f 100644 --- a/drivers/usb/gadget/udc/r8a66597-udc.c +++ b/drivers/usb/gadget/udc/r8a66597-udc.c @@ -832,11 +832,11 @@ static void init_controller(struct r8a66597 *r8a66597) r8a66597_bset(r8a66597, XCKE, SYSCFG0); - msleep(3); + mdelay(3); r8a66597_bset(r8a66597, PLLC, SYSCFG0); - msleep(1); + mdelay(1); r8a66597_bset(r8a66597, SCKE, SYSCFG0); @@ -1190,7 +1190,7 @@ __acquires(r8a66597->lock) r8a66597->ep0_req->length = 2; /* AV: what happens if we get called again before that gets through? */ spin_unlock(&r8a66597->lock); - r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_KERNEL); + r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_ATOMIC); spin_lock(&r8a66597->lock); } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 2f4850f25e82..68e6132aa8b2 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3051,6 +3051,7 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd, if (!list_empty(&ep->ring->td_list)) { dev_err(&udev->dev, "EP not empty, refuse reset\n"); spin_unlock_irqrestore(&xhci->lock, flags); + xhci_free_command(xhci, cfg_cmd); goto cleanup; } xhci_queue_stop_endpoint(xhci, stop_cmd, udev->slot_id, ep_index, 0); diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c index 900875f326d7..f7c96d209eda 100644 --- a/drivers/usb/phy/phy-fsl-usb.c +++ b/drivers/usb/phy/phy-fsl-usb.c @@ -861,6 +861,7 @@ int usb_otg_start(struct platform_device *pdev) if (pdata->init && pdata->init(pdev) != 0) return -EINVAL; +#ifdef CONFIG_PPC32 if (pdata->big_endian_mmio) { _fsl_readl = _fsl_readl_be; _fsl_writel = _fsl_writel_be; @@ -868,6 +869,7 @@ int usb_otg_start(struct platform_device *pdev) _fsl_readl = _fsl_readl_le; _fsl_writel = _fsl_writel_le; } +#endif /* request irq */ p_otg->irq = platform_get_irq(pdev, 0); @@ -958,7 +960,7 @@ int usb_otg_start(struct platform_device *pdev) /* * state file in sysfs */ -static int show_fsl_usb2_otg_state(struct device *dev, +static ssize_t show_fsl_usb2_otg_state(struct device *dev, struct device_attribute *attr, char *buf) { struct otg_fsm *fsm = &fsl_otg_dev->fsm; diff --git a/drivers/usb/typec/tcpm.c b/drivers/usb/typec/tcpm.c index 150f43668bec..d1d20252bad8 100644 --- a/drivers/usb/typec/tcpm.c +++ b/drivers/usb/typec/tcpm.c @@ -2140,7 +2140,7 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port) * PPS APDO. Again skip the first sink PDO as this will * always be 5V 3A. */ - for (j = i; j < port->nr_snk_pdo; j++) { + for (j = 1; j < port->nr_snk_pdo; j++) { pdo = port->snk_pdo[j]; switch (pdo_type(pdo)) { diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index b423a309a6e0..125b58eff936 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -28,6 +28,7 @@ #include <linux/uaccess.h> #include <linux/vfio.h> #include <linux/vgaarb.h> +#include <linux/nospec.h> #include "vfio_pci_private.h" @@ -727,6 +728,9 @@ static long vfio_pci_ioctl(void *device_data, if (info.index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions) return -EINVAL; + info.index = array_index_nospec(info.index, + VFIO_PCI_NUM_REGIONS + + vdev->num_regions); i = info.index - VFIO_PCI_NUM_REGIONS; diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 759a5bdd40e1..7cd63b0c1a46 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -457,17 +457,17 @@ static void tce_iommu_unuse_page(struct tce_container *container, } static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container, - unsigned long tce, unsigned long size, + unsigned long tce, unsigned long shift, unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem) { long ret = 0; struct mm_iommu_table_group_mem_t *mem; - mem = mm_iommu_lookup(container->mm, tce, size); + mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift); if (!mem) return -EINVAL; - ret = mm_iommu_ua_to_hpa(mem, tce, phpa); + ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa); if (ret) return -EINVAL; @@ -487,7 +487,7 @@ static void tce_iommu_unuse_page_v2(struct tce_container *container, if (!pua) return; - ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl), + ret = tce_iommu_prereg_ua_to_hpa(container, *pua, tbl->it_page_shift, &hpa, &mem); if (ret) pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n", @@ -611,7 +611,7 @@ static long tce_iommu_build_v2(struct tce_container *container, entry + i); ret = tce_iommu_prereg_ua_to_hpa(container, - tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem); + tce, tbl->it_page_shift, &hpa, &mem); if (ret) break; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a502f1af4a21..ed3114556fda 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1560,9 +1560,12 @@ int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled) d->iotlb = niotlb; for (i = 0; i < d->nvqs; ++i) { - mutex_lock(&d->vqs[i]->mutex); - d->vqs[i]->iotlb = niotlb; - mutex_unlock(&d->vqs[i]->mutex); + struct vhost_virtqueue *vq = d->vqs[i]; + + mutex_lock(&vq->mutex); + vq->iotlb = niotlb; + __vhost_vq_meta_reset(vq); + mutex_unlock(&vq->mutex); } vhost_umem_clean(oiotlb); diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 46a4484e3da7..c6f78d27947b 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -20,7 +20,7 @@ #include <drm/drm_connector.h> /* For DRM_MODE_PANEL_ORIENTATION_* */ static bool request_mem_succeeded = false; -static bool nowc = false; +static u64 mem_flags = EFI_MEMORY_WC | EFI_MEMORY_UC; static struct fb_var_screeninfo efifb_defined = { .activate = FB_ACTIVATE_NOW, @@ -68,8 +68,12 @@ static int efifb_setcolreg(unsigned regno, unsigned red, unsigned green, static void efifb_destroy(struct fb_info *info) { - if (info->screen_base) - iounmap(info->screen_base); + if (info->screen_base) { + if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC)) + iounmap(info->screen_base); + else + memunmap(info->screen_base); + } if (request_mem_succeeded) release_mem_region(info->apertures->ranges[0].base, info->apertures->ranges[0].size); @@ -104,7 +108,7 @@ static int efifb_setup(char *options) else if (!strncmp(this_opt, "width:", 6)) screen_info.lfb_width = simple_strtoul(this_opt+6, NULL, 0); else if (!strcmp(this_opt, "nowc")) - nowc = true; + mem_flags &= ~EFI_MEMORY_WC; } } @@ -164,6 +168,7 @@ static int efifb_probe(struct platform_device *dev) unsigned int size_remap; unsigned int size_total; char *option = NULL; + efi_memory_desc_t md; if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled) return -ENODEV; @@ -272,12 +277,35 @@ static int efifb_probe(struct platform_device *dev) info->apertures->ranges[0].base = efifb_fix.smem_start; info->apertures->ranges[0].size = size_remap; - if (nowc) - info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len); - else - info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len); + if (!efi_mem_desc_lookup(efifb_fix.smem_start, &md)) { + if ((efifb_fix.smem_start + efifb_fix.smem_len) > + (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) { + pr_err("efifb: video memory @ 0x%lx spans multiple EFI memory regions\n", + efifb_fix.smem_start); + err = -EIO; + goto err_release_fb; + } + /* + * If the UEFI memory map covers the efifb region, we may only + * remap it using the attributes the memory map prescribes. + */ + mem_flags |= EFI_MEMORY_WT | EFI_MEMORY_WB; + mem_flags &= md.attribute; + } + if (mem_flags & EFI_MEMORY_WC) + info->screen_base = ioremap_wc(efifb_fix.smem_start, + efifb_fix.smem_len); + else if (mem_flags & EFI_MEMORY_UC) + info->screen_base = ioremap(efifb_fix.smem_start, + efifb_fix.smem_len); + else if (mem_flags & EFI_MEMORY_WT) + info->screen_base = memremap(efifb_fix.smem_start, + efifb_fix.smem_len, MEMREMAP_WT); + else if (mem_flags & EFI_MEMORY_WB) + info->screen_base = memremap(efifb_fix.smem_start, + efifb_fix.smem_len, MEMREMAP_WB); if (!info->screen_base) { - pr_err("efifb: abort, cannot ioremap video memory 0x%x @ 0x%lx\n", + pr_err("efifb: abort, cannot remap video memory 0x%x @ 0x%lx\n", efifb_fix.smem_len, efifb_fix.smem_start); err = -EIO; goto err_release_fb; @@ -371,7 +399,10 @@ err_fb_dealoc: err_groups: sysfs_remove_groups(&dev->dev.kobj, efifb_groups); err_unmap: - iounmap(info->screen_base); + if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC)) + iounmap(info->screen_base); + else + memunmap(info->screen_base); err_release_fb: framebuffer_release(info); err_release_mem: diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 6b237e3f4983..3988c0914322 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -513,7 +513,9 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info, tell_host(vb, vb->inflate_vq); /* balloon's page migration 2nd step -- deflate "page" */ + spin_lock_irqsave(&vb_dev_info->pages_lock, flags); balloon_page_delete(page); + spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags); vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE; set_page_pfns(vb, vb->pfns, page); tell_host(vb, vb->deflate_vq); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a1b18082991b..183cc5418722 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -648,7 +648,7 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall, trace_afs_notify_call(rxcall, call); call->need_attention = true; - u = __atomic_add_unless(&call->usage, 1, 0); + u = atomic_fetch_add_unless(&call->usage, 1, 0); if (u != 0) { trace_afs_call(call, afs_call_trace_wake, u, atomic_read(&call->net->nr_outstanding_calls), @@ -1896,6 +1896,11 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, return ret; } +struct __aio_sigset { + const sigset_t __user *sigmask; + size_t sigsetsize; +}; + SYSCALL_DEFINE6(io_pgetevents, aio_context_t, ctx_id, long, min_nr, diff --git a/fs/block_dev.c b/fs/block_dev.c index 0dd87aaeb39a..aba25414231a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -221,7 +221,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, ret = bio_iov_iter_get_pages(&bio, iter); if (unlikely(ret)) - return ret; + goto out; ret = bio.bi_iter.bi_size; if (iov_iter_rw(iter) == READ) { @@ -250,12 +250,13 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, put_page(bvec->bv_page); } - if (vecs != inline_vecs) - kfree(vecs); - if (unlikely(bio.bi_status)) ret = blk_status_to_errno(bio.bi_status); +out: + if (vecs != inline_vecs) + kfree(vecs); + bio_uninit(&bio); return ret; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e55843f536bc..b3e45714d28f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4238,8 +4238,9 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) struct extent_map *em; u64 start = page_offset(page); u64 end = start + PAGE_SIZE - 1; - struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree; - struct extent_map_tree *map = &BTRFS_I(page->mapping->host)->extent_tree; + struct btrfs_inode *btrfs_inode = BTRFS_I(page->mapping->host); + struct extent_io_tree *tree = &btrfs_inode->io_tree; + struct extent_map_tree *map = &btrfs_inode->extent_tree; if (gfpflags_allow_blocking(mask) && page->mapping->host->i_size > SZ_16M) { @@ -4262,6 +4263,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) extent_map_end(em) - 1, EXTENT_LOCKED | EXTENT_WRITEBACK, 0, NULL)) { + set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &btrfs_inode->runtime_flags); remove_extent_mapping(map, em); /* once for the rb tree */ free_extent_map(em); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 43ecbe620dea..b077544b5232 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3327,11 +3327,13 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp) if (pg) { unlock_page(pg); put_page(pg); + cmp->src_pages[i] = NULL; } pg = cmp->dst_pages[i]; if (pg) { unlock_page(pg); put_page(pg); + cmp->dst_pages[i] = NULL; } } } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 572306036477..6702896cdb8f 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1151,11 +1151,6 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) return ret; } - if (sctx->is_dev_replace && !is_metadata && !have_csum) { - sblocks_for_recheck = NULL; - goto nodatasum_case; - } - /* * read all mirrors one after the other. This includes to * re-read the extent or metadata block that failed (that was @@ -1268,13 +1263,19 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) goto out; } - if (!is_metadata && !have_csum) { + /* + * NOTE: Even for nodatasum case, it's still possible that it's a + * compressed data extent, thus scrub_fixup_nodatasum(), which write + * inode page cache onto disk, could cause serious data corruption. + * + * So here we could only read from disk, and hope our recovery could + * reach disk before the newer write. + */ + if (0 && !is_metadata && !have_csum) { struct scrub_fixup_nodatasum *fixup_nodatasum; WARN_ON(sctx->is_dev_replace); -nodatasum_case: - /* * !is_metadata and !have_csum, this means that the data * might not be COWed, that it might be modified diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e034ad9e23b4..1da162928d1a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1146,6 +1146,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, { int ret; + mutex_lock(&uuid_mutex); mutex_lock(&fs_devices->device_list_mutex); if (fs_devices->opened) { fs_devices->opened++; @@ -1155,6 +1156,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, ret = open_fs_devices(fs_devices, flags, holder); } mutex_unlock(&fs_devices->device_list_mutex); + mutex_unlock(&uuid_mutex); return ret; } diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index d9f001078e08..4a717d400807 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -218,7 +218,8 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) "%s", fsdef->dentry->d_sb->s_id); - fscache_object_init(&fsdef->fscache, NULL, &cache->cache); + fscache_object_init(&fsdef->fscache, &fscache_fsdef_index, + &cache->cache); ret = fscache_add_cache(&cache->cache, &fsdef->fscache, cache->tag); if (ret < 0) diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index ab0bbe93b398..af2b17b21b94 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -186,12 +186,12 @@ try_again: * need to wait for it to be destroyed */ wait_for_old_object: trace_cachefiles_wait_active(object, dentry, xobject); + clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); if (fscache_object_is_live(&xobject->fscache)) { pr_err("\n"); pr_err("Error: Unexpected object collision\n"); cachefiles_printk_object(object, xobject); - BUG(); } atomic_inc(&xobject->usage); write_unlock(&cache->active_lock); @@ -248,7 +248,6 @@ wait_for_old_object: goto try_again; requeue: - clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_timeo); _leave(" = -ETIMEDOUT"); return -ETIMEDOUT; diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 5082c8a49686..40f7595aad10 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -27,6 +27,7 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, struct cachefiles_one_read *monitor = container_of(wait, struct cachefiles_one_read, monitor); struct cachefiles_object *object; + struct fscache_retrieval *op = monitor->op; struct wait_bit_key *key = _key; struct page *page = wait->private; @@ -51,16 +52,22 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, list_del(&wait->entry); /* move onto the action list and queue for FS-Cache thread pool */ - ASSERT(monitor->op); + ASSERT(op); - object = container_of(monitor->op->op.object, - struct cachefiles_object, fscache); + /* We need to temporarily bump the usage count as we don't own a ref + * here otherwise cachefiles_read_copier() may free the op between the + * monitor being enqueued on the op->to_do list and the op getting + * enqueued on the work queue. + */ + fscache_get_retrieval(op); + object = container_of(op->op.object, struct cachefiles_object, fscache); spin_lock(&object->work_lock); - list_add_tail(&monitor->op_link, &monitor->op->to_do); + list_add_tail(&monitor->op_link, &op->to_do); spin_unlock(&object->work_lock); - fscache_enqueue_retrieval(monitor->op); + fscache_enqueue_retrieval(op); + fscache_put_retrieval(op); return 0; } diff --git a/fs/dcache.c b/fs/dcache.c index 0e8e5de3c48a..ceb7b491d1b9 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -358,14 +358,11 @@ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; - bool hashed = !d_unhashed(dentry); - if (hashed) - raw_write_seqcount_begin(&dentry->d_seq); + raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); - if (hashed) - raw_write_seqcount_end(&dentry->d_seq); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -1932,10 +1929,12 @@ struct dentry *d_make_root(struct inode *root_inode) if (root_inode) { res = d_alloc_anon(root_inode->i_sb); - if (res) + if (res) { + res->d_flags |= DCACHE_RCUACCESS; d_instantiate(res, root_inode); - else + } else { iput(root_inode); + } } return res; } diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 71fccccf317e..8c6ab6c95727 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -86,7 +86,9 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, /* length of the variable name itself: remove GUID and separator */ namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1; - uuid_le_to_bin(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + err = guid_parse(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + if (err) + goto out; if (efivar_variable_is_removable(var->var.VendorGuid, dentry->d_name.name, namelen)) diff --git a/fs/exec.c b/fs/exec.c index 2d4e0075bd24..bdd0eacefdf5 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -290,15 +290,15 @@ static int __bprm_mm_init(struct linux_binprm *bprm) struct vm_area_struct *vma = NULL; struct mm_struct *mm = bprm->mm; - bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + bprm->vma = vma = vm_area_alloc(mm); if (!vma) return -ENOMEM; + vma_set_anonymous(vma); if (down_write_killable(&mm->mmap_sem)) { err = -EINTR; goto err_free; } - vma->vm_mm = mm; /* * Place the stack at the largest stack address the architecture @@ -311,7 +311,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm) vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); - INIT_LIST_HEAD(&vma->anon_vma_chain); err = insert_vm_struct(mm, vma); if (err) @@ -326,7 +325,7 @@ err: up_write(&mm->mmap_sem); err_free: bprm->vma = NULL; - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return err; } diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index e68cefe08261..aa52d87985aa 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -368,6 +368,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb, return -EFSCORRUPTED; ext4_lock_group(sb, block_group); + if (buffer_verified(bh)) + goto verified; if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, desc, bh))) { ext4_unlock_group(sb, block_group); @@ -386,6 +388,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb, return -EFSCORRUPTED; } set_buffer_verified(bh); +verified: ext4_unlock_group(sb, block_group); return 0; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index fb83750c1a14..f336cbc6e932 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -90,6 +90,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, return -EFSCORRUPTED; ext4_lock_group(sb, block_group); + if (buffer_verified(bh)) + goto verified; blk = ext4_inode_bitmap(sb, desc); if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh, EXT4_INODES_PER_GROUP(sb) / 8)) { @@ -101,6 +103,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, return -EFSBADCRC; } set_buffer_verified(bh); +verified: ext4_unlock_group(sb, block_group); return 0; } @@ -1385,7 +1388,10 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, ext4_itable_unused_count(sb, gdp)), sbi->s_inodes_per_block); - if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) { + if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) || + ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) - + ext4_itable_unused_count(sb, gdp)) < + EXT4_FIRST_INO(sb)))) { ext4_error(sb, "Something is wrong with group %u: " "used itable blocks: %d; " "itable unused count: %u", diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index e55a8bc870bd..3543fe80a3c4 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -682,6 +682,10 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, goto convert; } + ret = ext4_journal_get_write_access(handle, iloc.bh); + if (ret) + goto out; + flags |= AOP_FLAG_NOFS; page = grab_cache_page_write_begin(mapping, 0, flags); @@ -710,7 +714,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, out_up_read: up_read(&EXT4_I(inode)->xattr_sem); out: - if (handle) + if (handle && (ret != 1)) ext4_journal_stop(handle); brelse(iloc.bh); return ret; @@ -752,6 +756,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, ext4_write_unlock_xattr(inode, &no_expand); brelse(iloc.bh); + mark_inode_dirty(inode); out: return copied; } @@ -898,7 +903,6 @@ retry_journal: goto out; } - page = grab_cache_page_write_begin(mapping, 0, flags); if (!page) { ret = -ENOMEM; @@ -916,6 +920,9 @@ retry_journal: if (ret < 0) goto out_release_page; } + ret = ext4_journal_get_write_access(handle, iloc.bh); + if (ret) + goto out_release_page; up_read(&EXT4_I(inode)->xattr_sem); *pagep = page; @@ -936,7 +943,6 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page) { - int i_size_changed = 0; int ret; ret = ext4_write_inline_data_end(inode, pos, len, copied, page); @@ -954,10 +960,8 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ - if (pos+copied > inode->i_size) { + if (pos+copied > inode->i_size) i_size_write(inode, pos+copied); - i_size_changed = 1; - } unlock_page(page); put_page(page); @@ -967,8 +971,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed) - mark_inode_dirty(inode); + mark_inode_dirty(inode); return copied; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7d6c10017bdf..4efe77286ecd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1389,9 +1389,10 @@ static int ext4_write_end(struct file *file, loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; + int inline_data = ext4_has_inline_data(inode); trace_ext4_write_end(inode, pos, len, copied); - if (ext4_has_inline_data(inode)) { + if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1419,7 +1420,7 @@ static int ext4_write_end(struct file *file, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed) + if (i_size_changed || inline_data) ext4_mark_inode_dirty(handle, inode); if (pos + len > inode->i_size && ext4_can_truncate(inode)) @@ -1493,6 +1494,7 @@ static int ext4_journalled_write_end(struct file *file, int partial = 0; unsigned from, to; int size_changed = 0; + int inline_data = ext4_has_inline_data(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_SIZE - 1); @@ -1500,7 +1502,7 @@ static int ext4_journalled_write_end(struct file *file, BUG_ON(!ext4_handle_valid(handle)); - if (ext4_has_inline_data(inode)) { + if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1531,7 +1533,7 @@ static int ext4_journalled_write_end(struct file *file, if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); - if (size_changed) { + if (size_changed || inline_data) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; @@ -2028,11 +2030,7 @@ static int __ext4_journalled_writepage(struct page *page, } if (inline_data) { - BUFFER_TRACE(inode_bh, "get write access"); - ret = ext4_journal_get_write_access(handle, inode_bh); - - err = ext4_handle_dirty_metadata(handle, inode, inode_bh); - + ret = ext4_mark_inode_dirty(handle, inode); } else { ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, do_journal_get_write_access); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 27b9a76a0dfa..638ad4743477 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -186,11 +186,8 @@ static int kmmpd(void *data) goto exit_thread; } - if (sb_rdonly(sb)) { - ext4_warning(sb, "kmmpd being stopped since filesystem " - "has been remounted as readonly."); - goto exit_thread; - } + if (sb_rdonly(sb)) + break; diff = jiffies - last_update_time; if (diff < mmp_update_interval * HZ) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ba2396a7bd04..b7f7922061be 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2342,7 +2342,7 @@ static int ext4_check_descriptors(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext4_fsblk_t last_block; - ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0) + 1; + ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0); ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; @@ -3141,14 +3141,8 @@ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) if (!gdp) continue; - if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)) - continue; - if (group != 0) + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; - ext4_error(sb, "Inode table for bg 0 marked as " - "needing zeroing"); - if (sb_rdonly(sb)) - return ngroups; } return group; @@ -4085,14 +4079,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } + sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); ret = -EFSCORRUPTED; goto failed_mount2; } - sbi->s_gdb_count = db_count; - timer_setup(&sbi->s_err_report, print_daily_error_info, 0); /* Register extent status tree shrinker */ @@ -5213,6 +5206,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal) ext4_mark_recovery_complete(sb, es); + if (sbi->s_mmp_tsk) + kthread_stop(sbi->s_mmp_tsk); } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 065dc919a0ce..bfd589ea74c0 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -707,13 +707,21 @@ static void fat_set_state(struct super_block *sb, brelse(bh); } +static void fat_reset_iocharset(struct fat_mount_options *opts) +{ + if (opts->iocharset != fat_default_iocharset) { + /* Note: opts->iocharset can be NULL here */ + kfree(opts->iocharset); + opts->iocharset = fat_default_iocharset; + } +} + static void delayed_free(struct rcu_head *p) { struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu); unload_nls(sbi->nls_disk); unload_nls(sbi->nls_io); - if (sbi->options.iocharset != fat_default_iocharset) - kfree(sbi->options.iocharset); + fat_reset_iocharset(&sbi->options); kfree(sbi); } @@ -1132,7 +1140,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, opts->fs_fmask = opts->fs_dmask = current_umask(); opts->allow_utime = -1; opts->codepage = fat_default_codepage; - opts->iocharset = fat_default_iocharset; + fat_reset_iocharset(opts); if (is_vfat) { opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95; opts->rodir = 0; @@ -1289,8 +1297,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, /* vfat specific */ case Opt_charset: - if (opts->iocharset != fat_default_iocharset) - kfree(opts->iocharset); + fat_reset_iocharset(opts); iocharset = match_strdup(&args[0]); if (!iocharset) return -ENOMEM; @@ -1881,8 +1888,7 @@ out_fail: iput(fat_inode); unload_nls(sbi->nls_io); unload_nls(sbi->nls_disk); - if (sbi->options.iocharset != fat_default_iocharset) - kfree(sbi->options.iocharset); + fat_reset_iocharset(&sbi->options); sb->s_fs_info = NULL; kfree(sbi); return error; diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index c184c5a356ff..cdcb376ef8df 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -220,6 +220,7 @@ int fscache_add_cache(struct fscache_cache *cache, { struct fscache_cache_tag *tag; + ASSERTCMP(ifsdef->cookie, ==, &fscache_fsdef_index); BUG_ON(!cache->ops); BUG_ON(!ifsdef); @@ -248,7 +249,6 @@ int fscache_add_cache(struct fscache_cache *cache, if (!cache->kobj) goto error; - ifsdef->cookie = &fscache_fsdef_index; ifsdef->cache = cache; cache->fsdef = ifsdef; diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 97137d7ec5ee..83bfe04456b6 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -516,6 +516,7 @@ static int fscache_alloc_object(struct fscache_cache *cache, goto error; } + ASSERTCMP(object->cookie, ==, cookie); fscache_stat(&fscache_n_object_alloc); object->debug_id = atomic_inc_return(&fscache_object_debug_id); @@ -571,6 +572,8 @@ static int fscache_attach_object(struct fscache_cookie *cookie, _enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id); + ASSERTCMP(object->cookie, ==, cookie); + spin_lock(&cookie->lock); /* there may be multiple initial creations of this object, but we only @@ -610,9 +613,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie, spin_unlock(&cache->object_list_lock); } - /* attach to the cookie */ - object->cookie = cookie; - fscache_cookie_get(cookie, fscache_cookie_get_attach_object); + /* Attach to the cookie. The object already has a ref on it. */ hlist_add_head(&object->cookie_link, &cookie->backing_objects); fscache_objlist_add(object); diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 20e0d0a4dc8c..9edc920f651f 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -327,6 +327,7 @@ void fscache_object_init(struct fscache_object *object, object->store_limit_l = 0; object->cache = cache; object->cookie = cookie; + fscache_cookie_get(cookie, fscache_cookie_get_attach_object); object->parent = NULL; #ifdef CONFIG_FSCACHE_OBJECT_LIST RB_CLEAR_NODE(&object->objlist_link); diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index e30c5975ea58..8d265790374c 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -70,7 +70,8 @@ void fscache_enqueue_operation(struct fscache_operation *op) ASSERT(op->processor != NULL); ASSERT(fscache_object_is_available(op->object)); ASSERTCMP(atomic_read(&op->usage), >, 0); - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS); + ASSERTIFCMP(op->state != FSCACHE_OP_ST_IN_PROGRESS, + op->state, ==, FSCACHE_OP_ST_CANCELLED); fscache_stat(&fscache_n_op_enqueue); switch (op->flags & FSCACHE_OP_TYPE) { @@ -499,7 +500,8 @@ void fscache_put_operation(struct fscache_operation *op) struct fscache_cache *cache; _enter("{OBJ%x OP%x,%d}", - op->object->debug_id, op->debug_id, atomic_read(&op->usage)); + op->object ? op->object->debug_id : 0, + op->debug_id, atomic_read(&op->usage)); ASSERTCMP(atomic_read(&op->usage), >, 0); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d508c7844681..40d4c66c7751 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -411,6 +411,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, bool truncate_op = (lend == LLONG_MAX); memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); + vma_init(&pseudo_vma, current->mm); pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pagevec_init(&pvec); next = start; @@ -595,6 +596,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, * as input to create an allocation policy. */ memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); + vma_init(&pseudo_vma, mm); pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pseudo_vma.vm_file = file; diff --git a/fs/internal.h b/fs/internal.h index 980d005b21b4..5645b4ebf494 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -127,7 +127,6 @@ int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, extern int open_check_o_direct(struct file *f); extern int vfs_open(const struct path *, struct file *, const struct cred *); -extern struct file *filp_clone_open(struct file *); /* * inode.c diff --git a/fs/iomap.c b/fs/iomap.c index 77397b5a96ef..0d0bd8845586 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1443,7 +1443,7 @@ iomap_bmap(struct address_space *mapping, sector_t bno, const struct iomap_ops *ops) { struct inode *inode = mapping->host; - loff_t pos = bno >> inode->i_blkbits; + loff_t pos = bno << inode->i_blkbits; unsigned blocksize = i_blocksize(inode); if (filemap_write_and_wait(mapping)) diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h index 395c4c0d0f06..1682a87c00b2 100644 --- a/fs/jfs/jfs_dinode.h +++ b/fs/jfs/jfs_dinode.h @@ -115,6 +115,13 @@ struct dinode { dxd_t _dxd; /* 16: */ union { __le32 _rdev; /* 4: */ + /* + * The fast symlink area + * is expected to overflow + * into _inlineea when + * needed (which will clear + * INLINEEA). + */ u8 _fastsymlink[128]; } _u; u8 _inlineea[128]; diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 1f26d1910409..9940a1e04cbf 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -87,6 +87,7 @@ struct jfs_inode_info { struct { unchar _unused[16]; /* 16: */ dxd_t _dxd; /* 16: */ + /* _inline may overflow into _inline_ea when needed */ unchar _inline[128]; /* 128: inline symlink */ /* _inline_ea may overlay the last part of * file._xtroot if maxentry = XTROOTINITSLOT diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 1b9264fd54b6..f08571433aba 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -967,8 +967,7 @@ static int __init init_jfs_fs(void) jfs_inode_cachep = kmem_cache_create_usercopy("jfs_ip", sizeof(struct jfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT, - offsetof(struct jfs_inode_info, i_inline), - sizeof_field(struct jfs_inode_info, i_inline), + offsetof(struct jfs_inode_info, i_inline), IDATASIZE, init_once); if (jfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/namespace.c b/fs/namespace.c index 8ddd14806799..bd2f4c68506a 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -659,12 +659,21 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); + smp_mb(); // see mntput_no_expire() if (likely(!read_seqretry(&mount_lock, seq))) return 0; if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { mnt_add_count(mnt, -1); return 1; } + lock_mount_hash(); + if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { + mnt_add_count(mnt, -1); + unlock_mount_hash(); + return 1; + } + unlock_mount_hash(); + /* caller will mntput() */ return -1; } @@ -1195,12 +1204,27 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { rcu_read_lock(); - mnt_add_count(mnt, -1); - if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */ + if (likely(READ_ONCE(mnt->mnt_ns))) { + /* + * Since we don't do lock_mount_hash() here, + * ->mnt_ns can change under us. However, if it's + * non-NULL, then there's a reference that won't + * be dropped until after an RCU delay done after + * turning ->mnt_ns NULL. So if we observe it + * non-NULL under rcu_read_lock(), the reference + * we are dropping is not the final one. + */ + mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); + /* + * make sure that if __legitimize_mnt() has not seen us grab + * mount_lock, we'll see their refcount increment here. + */ + smp_mb(); + mnt_add_count(mnt, -1); if (mnt_get_count(mnt)) { rcu_read_unlock(); unlock_mount_hash(); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6dd146885da9..f6c4ccd693f4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6466,34 +6466,34 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) if (data->arg.new_lock && !data->cancelled) { data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0) - break; + goto out_restart; } - if (data->arg.new_lock_owner != 0) { nfs_confirm_seqid(&lsp->ls_seqid, 0); nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid); set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags); - goto out_done; - } else if (nfs4_update_lock_stateid(lsp, &data->res.stateid)) - goto out_done; - + } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid)) + goto out_restart; break; case -NFS4ERR_BAD_STATEID: case -NFS4ERR_OLD_STATEID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: if (data->arg.new_lock_owner != 0) { - if (nfs4_stateid_match(&data->arg.open_stateid, + if (!nfs4_stateid_match(&data->arg.open_stateid, &lsp->ls_state->open_stateid)) - goto out_done; - } else if (nfs4_stateid_match(&data->arg.lock_stateid, + goto out_restart; + } else if (!nfs4_stateid_match(&data->arg.lock_stateid, &lsp->ls_stateid)) - goto out_done; + goto out_restart; } - if (!data->cancelled) - rpc_restart_call_prepare(task); out_done: dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status); + return; +out_restart: + if (!data->cancelled) + rpc_restart_call_prepare(task); + goto out_done; } static void nfs4_lock_release(void *calldata) @@ -6502,7 +6502,7 @@ static void nfs4_lock_release(void *calldata) dprintk("%s: begin!\n", __func__); nfs_free_seqid(data->arg.open_seqid); - if (data->cancelled) { + if (data->cancelled && data->rpc_status == 0) { struct rpc_task *task; task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp, data->arg.lock_seqid); diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 2751476e6b6e..f098b9f1c396 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -167,6 +167,8 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, } if (compressed) { + if (!msblk->stream) + goto read_failure; length = squashfs_decompress(msblk, bh, b, offset, length, output); if (length < 0) diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index 23813c078cc9..0839efa720b3 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -350,6 +350,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer, TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset); + if (unlikely(length < 0)) + return -EIO; + while (length) { entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0); if (entry->error) { diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 13d80947bf9e..f1c1430ae721 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -194,7 +194,11 @@ static long long read_indexes(struct super_block *sb, int n, } for (i = 0; i < blocks; i++) { - int size = le32_to_cpu(blist[i]); + int size = squashfs_block_size(blist[i]); + if (size < 0) { + err = size; + goto failure; + } block += SQUASHFS_COMPRESSED_SIZE_BLOCK(size); } n -= blocks; @@ -367,7 +371,24 @@ static int read_blocklist(struct inode *inode, int index, u64 *block) sizeof(size)); if (res < 0) return res; - return le32_to_cpu(size); + return squashfs_block_size(size); +} + +void squashfs_fill_page(struct page *page, struct squashfs_cache_entry *buffer, int offset, int avail) +{ + int copied; + void *pageaddr; + + pageaddr = kmap_atomic(page); + copied = squashfs_copy_data(pageaddr, buffer, offset, avail); + memset(pageaddr + copied, 0, PAGE_SIZE - copied); + kunmap_atomic(pageaddr); + + flush_dcache_page(page); + if (copied == avail) + SetPageUptodate(page); + else + SetPageError(page); } /* Copy data into page cache */ @@ -376,7 +397,6 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, { struct inode *inode = page->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - void *pageaddr; int i, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; int start_index = page->index & ~mask, end_index = start_index | mask; @@ -402,12 +422,7 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, if (PageUptodate(push_page)) goto skip_page; - pageaddr = kmap_atomic(push_page); - squashfs_copy_data(pageaddr, buffer, offset, avail); - memset(pageaddr + avail, 0, PAGE_SIZE - avail); - kunmap_atomic(pageaddr); - flush_dcache_page(push_page); - SetPageUptodate(push_page); + squashfs_fill_page(push_page, buffer, offset, avail); skip_page: unlock_page(push_page); if (i != page->index) @@ -416,10 +431,9 @@ skip_page: } /* Read datablock stored packed inside a fragment (tail-end packed block) */ -static int squashfs_readpage_fragment(struct page *page) +static int squashfs_readpage_fragment(struct page *page, int expected) { struct inode *inode = page->mapping->host; - struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb, squashfs_i(inode)->fragment_block, squashfs_i(inode)->fragment_size); @@ -430,23 +444,16 @@ static int squashfs_readpage_fragment(struct page *page) squashfs_i(inode)->fragment_block, squashfs_i(inode)->fragment_size); else - squashfs_copy_cache(page, buffer, i_size_read(inode) & - (msblk->block_size - 1), + squashfs_copy_cache(page, buffer, expected, squashfs_i(inode)->fragment_offset); squashfs_cache_put(buffer); return res; } -static int squashfs_readpage_sparse(struct page *page, int index, int file_end) +static int squashfs_readpage_sparse(struct page *page, int expected) { - struct inode *inode = page->mapping->host; - struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - int bytes = index == file_end ? - (i_size_read(inode) & (msblk->block_size - 1)) : - msblk->block_size; - - squashfs_copy_cache(page, NULL, bytes, 0); + squashfs_copy_cache(page, NULL, expected, 0); return 0; } @@ -456,6 +463,9 @@ static int squashfs_readpage(struct file *file, struct page *page) struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; int index = page->index >> (msblk->block_log - PAGE_SHIFT); int file_end = i_size_read(inode) >> msblk->block_log; + int expected = index == file_end ? + (i_size_read(inode) & (msblk->block_size - 1)) : + msblk->block_size; int res; void *pageaddr; @@ -474,11 +484,11 @@ static int squashfs_readpage(struct file *file, struct page *page) goto error_out; if (bsize == 0) - res = squashfs_readpage_sparse(page, index, file_end); + res = squashfs_readpage_sparse(page, expected); else - res = squashfs_readpage_block(page, block, bsize); + res = squashfs_readpage_block(page, block, bsize, expected); } else - res = squashfs_readpage_fragment(page); + res = squashfs_readpage_fragment(page, expected); if (!res) return 0; diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c index f2310d2a2019..a9ba8d96776a 100644 --- a/fs/squashfs/file_cache.c +++ b/fs/squashfs/file_cache.c @@ -20,7 +20,7 @@ #include "squashfs.h" /* Read separately compressed datablock and memcopy into page cache */ -int squashfs_readpage_block(struct page *page, u64 block, int bsize) +int squashfs_readpage_block(struct page *page, u64 block, int bsize, int expected) { struct inode *i = page->mapping->host; struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, @@ -31,7 +31,7 @@ int squashfs_readpage_block(struct page *page, u64 block, int bsize) ERROR("Unable to read page, block %llx, size %x\n", block, bsize); else - squashfs_copy_cache(page, buffer, buffer->length, 0); + squashfs_copy_cache(page, buffer, expected, 0); squashfs_cache_put(buffer); return res; diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index cb485d8e0e91..80db1b86a27c 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -21,10 +21,11 @@ #include "page_actor.h" static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, - int pages, struct page **page); + int pages, struct page **page, int bytes); /* Read separately compressed datablock directly into page cache */ -int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) +int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, + int expected) { struct inode *inode = target_page->mapping->host; @@ -83,7 +84,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) * using an intermediate buffer. */ res = squashfs_read_cache(target_page, block, bsize, pages, - page); + page, expected); if (res < 0) goto mark_errored; @@ -95,6 +96,11 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) if (res < 0) goto mark_errored; + if (res != expected) { + res = -EIO; + goto mark_errored; + } + /* Last page may have trailing bytes not filled */ bytes = res % PAGE_SIZE; if (bytes) { @@ -138,13 +144,12 @@ out: static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, - int pages, struct page **page) + int pages, struct page **page, int bytes) { struct inode *i = target_page->mapping->host; struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, block, bsize); - int bytes = buffer->length, res = buffer->error, n, offset = 0; - void *pageaddr; + int res = buffer->error, n, offset = 0; if (res) { ERROR("Unable to read page, block %llx, size %x\n", block, @@ -159,12 +164,7 @@ static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, if (page[n] == NULL) continue; - pageaddr = kmap_atomic(page[n]); - squashfs_copy_data(pageaddr, buffer, offset, avail); - memset(pageaddr + avail, 0, PAGE_SIZE - avail); - kunmap_atomic(pageaddr); - flush_dcache_page(page[n]); - SetPageUptodate(page[n]); + squashfs_fill_page(page[n], buffer, offset, avail); unlock_page(page[n]); if (page[n] != target_page) put_page(page[n]); diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c index 0ed6edbc5c71..0681feab4a84 100644 --- a/fs/squashfs/fragment.c +++ b/fs/squashfs/fragment.c @@ -49,11 +49,16 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment, u64 *fragment_block) { struct squashfs_sb_info *msblk = sb->s_fs_info; - int block = SQUASHFS_FRAGMENT_INDEX(fragment); - int offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment); - u64 start_block = le64_to_cpu(msblk->fragment_index[block]); + int block, offset, size; struct squashfs_fragment_entry fragment_entry; - int size; + u64 start_block; + + if (fragment >= msblk->fragments) + return -EIO; + block = SQUASHFS_FRAGMENT_INDEX(fragment); + offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment); + + start_block = le64_to_cpu(msblk->fragment_index[block]); size = squashfs_read_metadata(sb, &fragment_entry, &start_block, &offset, sizeof(fragment_entry)); @@ -61,9 +66,7 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment, return size; *fragment_block = le64_to_cpu(fragment_entry.start_block); - size = le32_to_cpu(fragment_entry.size); - - return size; + return squashfs_block_size(fragment_entry.size); } diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index 887d6d270080..f89f8a74c6ce 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -67,11 +67,12 @@ extern __le64 *squashfs_read_fragment_index_table(struct super_block *, u64, u64, unsigned int); /* file.c */ +void squashfs_fill_page(struct page *, struct squashfs_cache_entry *, int, int); void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int, int); /* file_xxx.c */ -extern int squashfs_readpage_block(struct page *, u64, int); +extern int squashfs_readpage_block(struct page *, u64, int, int); /* id.c */ extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *); diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 24d12fd14177..4e6853f084d0 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -129,6 +129,12 @@ #define SQUASHFS_COMPRESSED_BLOCK(B) (!((B) & SQUASHFS_COMPRESSED_BIT_BLOCK)) +static inline int squashfs_block_size(__le32 raw) +{ + u32 size = le32_to_cpu(raw); + return (size >> 25) ? -EIO : size; +} + /* * Inode number ops. Inodes consist of a compressed block number, and an * uncompressed offset within that block diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 1da565cb50c3..ef69c31947bf 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -75,6 +75,7 @@ struct squashfs_sb_info { unsigned short block_log; long long bytes_used; unsigned int inodes; + unsigned int fragments; int xattr_ids; }; #endif diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 8a73b97217c8..40e657386fa5 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -175,6 +175,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) msblk->inode_table = le64_to_cpu(sblk->inode_table_start); msblk->directory_table = le64_to_cpu(sblk->directory_table_start); msblk->inodes = le32_to_cpu(sblk->inodes); + msblk->fragments = le32_to_cpu(sblk->fragments); flags = le16_to_cpu(sblk->flags); TRACE("Found valid superblock on %pg\n", sb->s_bdev); @@ -185,7 +186,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) TRACE("Filesystem size %lld bytes\n", msblk->bytes_used); TRACE("Block size %d\n", msblk->block_size); TRACE("Number of inodes %d\n", msblk->inodes); - TRACE("Number of fragments %d\n", le32_to_cpu(sblk->fragments)); + TRACE("Number of fragments %d\n", msblk->fragments); TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids)); TRACE("sblk->inode_table_start %llx\n", msblk->inode_table); TRACE("sblk->directory_table_start %llx\n", msblk->directory_table); @@ -272,7 +273,7 @@ allocate_id_index_table: sb->s_export_op = &squashfs_export_ops; handle_fragments: - fragments = le32_to_cpu(sblk->fragments); + fragments = msblk->fragments; if (fragments == 0) goto check_directory_table; diff --git a/fs/timerfd.c b/fs/timerfd.c index cdad49da3ff7..38c695ce385b 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -533,8 +533,8 @@ static int do_timerfd_gettime(int ufd, struct itimerspec64 *t) } SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, - const struct itimerspec __user *, utmr, - struct itimerspec __user *, otmr) + const struct __kernel_itimerspec __user *, utmr, + struct __kernel_itimerspec __user *, otmr) { struct itimerspec64 new, old; int ret; @@ -550,7 +550,7 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, return ret; } -SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr) +SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, otmr) { struct itimerspec64 kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); @@ -559,7 +559,7 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr) return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, const struct compat_itimerspec __user *, utmr, struct compat_itimerspec __user *, otmr) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 594d192b2331..bad9cea37f12 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -633,8 +633,10 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) - if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) + if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + } up_write(&mm->mmap_sem); userfaultfd_ctx_put(release_new_ctx); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index eef466260d43..75dbdc14c45f 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -223,12 +223,13 @@ xfs_alloc_get_rec( error = xfs_btree_get_rec(cur, &rec, stat); if (error || !(*stat)) return error; - if (rec->alloc.ar_blockcount == 0) - goto out_bad_rec; *bno = be32_to_cpu(rec->alloc.ar_startblock); *len = be32_to_cpu(rec->alloc.ar_blockcount); + if (*len == 0) + goto out_bad_rec; + /* check for valid extent range, including overflow */ if (!xfs_verify_agbno(mp, agno, *bno)) goto out_bad_rec; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 33dc34655ac3..30d1d60f1d46 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -731,7 +731,8 @@ xfs_inode_validate_extsize( if ((hint_flag || inherit_flag) && extsize == 0) return __this_address; - if (!(hint_flag || inherit_flag) && extsize != 0) + /* free inodes get flags set to zero but extsize remains */ + if (mode && !(hint_flag || inherit_flag) && extsize != 0) return __this_address; if (extsize_bytes % blocksize_bytes) @@ -777,7 +778,8 @@ xfs_inode_validate_cowextsize( if (hint_flag && cowextsize == 0) return __this_address; - if (!hint_flag && cowextsize != 0) + /* free inodes get flags set to zero but cowextsize remains */ + if (mode && !hint_flag && cowextsize != 0) return __this_address; if (hint_flag && rt_flag) diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index ec07f23678ea..0d4b1d3dbc1e 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -84,42 +84,59 @@ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 ne } #endif -static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) +#ifdef arch_atomic_fetch_add_unless +#define atomic_fetch_add_unless atomic_fetch_add_unless +static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { kasan_check_write(v, sizeof(*v)); - return __arch_atomic_add_unless(v, a, u); + return arch_atomic_fetch_add_unless(v, a, u); } +#endif - -static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +#ifdef arch_atomic64_fetch_add_unless +#define atomic64_fetch_add_unless atomic64_fetch_add_unless +static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_add_unless(v, a, u); + return arch_atomic64_fetch_add_unless(v, a, u); } +#endif +#ifdef arch_atomic_inc +#define atomic_inc atomic_inc static __always_inline void atomic_inc(atomic_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic_inc(v); } +#endif +#ifdef arch_atomic64_inc +#define atomic64_inc atomic64_inc static __always_inline void atomic64_inc(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic64_inc(v); } +#endif +#ifdef arch_atomic_dec +#define atomic_dec atomic_dec static __always_inline void atomic_dec(atomic_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic_dec(v); } +#endif +#ifdef atch_atomic64_dec +#define atomic64_dec static __always_inline void atomic64_dec(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic64_dec(v); } +#endif static __always_inline void atomic_add(int i, atomic_t *v) { @@ -181,65 +198,95 @@ static __always_inline void atomic64_xor(s64 i, atomic64_t *v) arch_atomic64_xor(i, v); } +#ifdef arch_atomic_inc_return +#define atomic_inc_return atomic_inc_return static __always_inline int atomic_inc_return(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_inc_return(v); } +#endif +#ifdef arch_atomic64_in_return +#define atomic64_inc_return atomic64_inc_return static __always_inline s64 atomic64_inc_return(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_inc_return(v); } +#endif +#ifdef arch_atomic_dec_return +#define atomic_dec_return atomic_dec_return static __always_inline int atomic_dec_return(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_dec_return(v); } +#endif +#ifdef arch_atomic64_dec_return +#define atomic64_dec_return atomic64_dec_return static __always_inline s64 atomic64_dec_return(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_dec_return(v); } +#endif -static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v) +#ifdef arch_atomic64_inc_not_zero +#define atomic64_inc_not_zero atomic64_inc_not_zero +static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_inc_not_zero(v); } +#endif +#ifdef arch_atomic64_dec_if_positive +#define atomic64_dec_if_positive atomic64_dec_if_positive static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_dec_if_positive(v); } +#endif +#ifdef arch_atomic_dec_and_test +#define atomic_dec_and_test atomic_dec_and_test static __always_inline bool atomic_dec_and_test(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_dec_and_test(v); } +#endif +#ifdef arch_atomic64_dec_and_test +#define atomic64_dec_and_test atomic64_dec_and_test static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_dec_and_test(v); } +#endif +#ifdef arch_atomic_inc_and_test +#define atomic_inc_and_test atomic_inc_and_test static __always_inline bool atomic_inc_and_test(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_inc_and_test(v); } +#endif +#ifdef arch_atomic64_inc_and_test +#define atomic64_inc_and_test atomic64_inc_and_test static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_inc_and_test(v); } +#endif static __always_inline int atomic_add_return(int i, atomic_t *v) { @@ -325,152 +372,96 @@ static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) return arch_atomic64_fetch_xor(i, v); } +#ifdef arch_atomic_sub_and_test +#define atomic_sub_and_test atomic_sub_and_test static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_sub_and_test(i, v); } +#endif +#ifdef arch_atomic64_sub_and_test +#define atomic64_sub_and_test atomic64_sub_and_test static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_sub_and_test(i, v); } +#endif +#ifdef arch_atomic_add_negative +#define atomic_add_negative atomic_add_negative static __always_inline bool atomic_add_negative(int i, atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_add_negative(i, v); } +#endif +#ifdef arch_atomic64_add_negative +#define atomic64_add_negative atomic64_add_negative static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_add_negative(i, v); } +#endif -static __always_inline unsigned long -cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size) -{ - kasan_check_write(ptr, size); - switch (size) { - case 1: - return arch_cmpxchg((u8 *)ptr, (u8)old, (u8)new); - case 2: - return arch_cmpxchg((u16 *)ptr, (u16)old, (u16)new); - case 4: - return arch_cmpxchg((u32 *)ptr, (u32)old, (u32)new); - case 8: - BUILD_BUG_ON(sizeof(unsigned long) != 8); - return arch_cmpxchg((u64 *)ptr, (u64)old, (u64)new); - } - BUILD_BUG(); - return 0; -} +#define xchg(ptr, new) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg(__ai_ptr, (new)); \ +}) #define cmpxchg(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg_size((ptr), (unsigned long)(old), \ - (unsigned long)(new), sizeof(*(ptr)))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg(__ai_ptr, (old), (new)); \ }) -static __always_inline unsigned long -sync_cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, - int size) -{ - kasan_check_write(ptr, size); - switch (size) { - case 1: - return arch_sync_cmpxchg((u8 *)ptr, (u8)old, (u8)new); - case 2: - return arch_sync_cmpxchg((u16 *)ptr, (u16)old, (u16)new); - case 4: - return arch_sync_cmpxchg((u32 *)ptr, (u32)old, (u32)new); - case 8: - BUILD_BUG_ON(sizeof(unsigned long) != 8); - return arch_sync_cmpxchg((u64 *)ptr, (u64)old, (u64)new); - } - BUILD_BUG(); - return 0; -} - #define sync_cmpxchg(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))sync_cmpxchg_size((ptr), \ - (unsigned long)(old), (unsigned long)(new), \ - sizeof(*(ptr)))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_sync_cmpxchg(__ai_ptr, (old), (new)); \ }) -static __always_inline unsigned long -cmpxchg_local_size(volatile void *ptr, unsigned long old, unsigned long new, - int size) -{ - kasan_check_write(ptr, size); - switch (size) { - case 1: - return arch_cmpxchg_local((u8 *)ptr, (u8)old, (u8)new); - case 2: - return arch_cmpxchg_local((u16 *)ptr, (u16)old, (u16)new); - case 4: - return arch_cmpxchg_local((u32 *)ptr, (u32)old, (u32)new); - case 8: - BUILD_BUG_ON(sizeof(unsigned long) != 8); - return arch_cmpxchg_local((u64 *)ptr, (u64)old, (u64)new); - } - BUILD_BUG(); - return 0; -} - #define cmpxchg_local(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg_local_size((ptr), \ - (unsigned long)(old), (unsigned long)(new), \ - sizeof(*(ptr)))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_local(__ai_ptr, (old), (new)); \ }) -static __always_inline u64 -cmpxchg64_size(volatile u64 *ptr, u64 old, u64 new) -{ - kasan_check_write(ptr, sizeof(*ptr)); - return arch_cmpxchg64(ptr, old, new); -} - #define cmpxchg64(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg64_size((ptr), (u64)(old), \ - (u64)(new))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64(__ai_ptr, (old), (new)); \ }) -static __always_inline u64 -cmpxchg64_local_size(volatile u64 *ptr, u64 old, u64 new) -{ - kasan_check_write(ptr, sizeof(*ptr)); - return arch_cmpxchg64_local(ptr, old, new); -} - #define cmpxchg64_local(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg64_local_size((ptr), (u64)(old), \ - (u64)(new))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_local(__ai_ptr, (old), (new)); \ }) -/* - * Originally we had the following code here: - * __typeof__(p1) ____p1 = (p1); - * kasan_check_write(____p1, 2 * sizeof(*____p1)); - * arch_cmpxchg_double(____p1, (p2), (o1), (o2), (n1), (n2)); - * But it leads to compilation failures (see gcc issue 72873). - * So for now it's left non-instrumented. - * There are few callers of cmpxchg_double(), so it's not critical. - */ #define cmpxchg_double(p1, p2, o1, o2, n1, n2) \ ({ \ - arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2)); \ + typeof(p1) __ai_p1 = (p1); \ + kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1)); \ + arch_cmpxchg_double(__ai_p1, (p2), (o1), (o2), (n1), (n2)); \ }) -#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \ -({ \ - arch_cmpxchg_double_local((p1), (p2), (o1), (o2), (n1), (n2)); \ +#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \ +({ \ + typeof(p1) __ai_p1 = (p1); \ + kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1)); \ + arch_cmpxchg_double_local(__ai_p1, (p2), (o1), (o2), (n1), (n2)); \ }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index abe6dd9ca2a8..13324aa828eb 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -186,11 +186,6 @@ ATOMIC_OP(xor, ^) #include <linux/irqflags.h> -static inline int atomic_add_negative(int i, atomic_t *v) -{ - return atomic_add_return(i, v) < 0; -} - static inline void atomic_add(int i, atomic_t *v) { atomic_add_return(i, v); @@ -201,35 +196,7 @@ static inline void atomic_sub(int i, atomic_t *v) atomic_sub_return(i, v); } -static inline void atomic_inc(atomic_t *v) -{ - atomic_add_return(1, v); -} - -static inline void atomic_dec(atomic_t *v) -{ - atomic_sub_return(1, v); -} - -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - #define atomic_xchg(ptr, v) (xchg(&(ptr)->counter, (v))) #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new))) -#ifndef __atomic_add_unless -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c) - c = old; - return c; -} -#endif - #endif /* __ASM_GENERIC_ATOMIC_H */ diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h index 8d28eb010d0d..97b28b7f1f29 100644 --- a/include/asm-generic/atomic64.h +++ b/include/asm-generic/atomic64.h @@ -11,6 +11,7 @@ */ #ifndef _ASM_GENERIC_ATOMIC64_H #define _ASM_GENERIC_ATOMIC64_H +#include <linux/types.h> typedef struct { long long counter; @@ -50,18 +51,10 @@ ATOMIC64_OPS(xor) #undef ATOMIC64_OP extern long long atomic64_dec_if_positive(atomic64_t *v); +#define atomic64_dec_if_positive atomic64_dec_if_positive extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n); extern long long atomic64_xchg(atomic64_t *v, long long new); -extern int atomic64_add_unless(atomic64_t *v, long long a, long long u); - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) +extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u); +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* _ASM_GENERIC_ATOMIC64_H */ diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h index 04deffaf5f7d..dd90c9792909 100644 --- a/include/asm-generic/bitops/atomic.h +++ b/include/asm-generic/bitops/atomic.h @@ -2,189 +2,67 @@ #ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_ #define _ASM_GENERIC_BITOPS_ATOMIC_H_ -#include <asm/types.h> -#include <linux/irqflags.h> - -#ifdef CONFIG_SMP -#include <asm/spinlock.h> -#include <asm/cache.h> /* we use L1_CACHE_BYTES */ - -/* Use an array of spinlocks for our atomic_ts. - * Hash function to index into a different SPINLOCK. - * Since "a" is usually an address, use one spinlock per cacheline. - */ -# define ATOMIC_HASH_SIZE 4 -# define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ])) - -extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned; - -/* Can't use raw_spin_lock_irq because of #include problems, so - * this is the substitute */ -#define _atomic_spin_lock_irqsave(l,f) do { \ - arch_spinlock_t *s = ATOMIC_HASH(l); \ - local_irq_save(f); \ - arch_spin_lock(s); \ -} while(0) - -#define _atomic_spin_unlock_irqrestore(l,f) do { \ - arch_spinlock_t *s = ATOMIC_HASH(l); \ - arch_spin_unlock(s); \ - local_irq_restore(f); \ -} while(0) - - -#else -# define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0) -# define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0) -#endif +#include <linux/atomic.h> +#include <linux/compiler.h> +#include <asm/barrier.h> /* - * NMI events can occur at any time, including when interrupts have been - * disabled by *_irqsave(). So you can get NMI events occurring while a - * *_bit function is holding a spin lock. If the NMI handler also wants - * to do bit manipulation (and they do) then you can get a deadlock - * between the original caller of *_bit() and the NMI handler. - * - * by Keith Owens + * Implementation of atomic bitops using atomic-fetch ops. + * See Documentation/atomic_bitops.txt for details. */ -/** - * set_bit - Atomically set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * This function is atomic and may not be reordered. See __set_bit() - * if you do not require the atomic guarantees. - * - * Note: there are no guarantees that this function will not be reordered - * on non x86 architectures, so if you are writing portable code, - * make sure not to rely on its reordering guarantees. - * - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ -static inline void set_bit(int nr, volatile unsigned long *addr) +static inline void set_bit(unsigned int nr, volatile unsigned long *p) { - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - *p |= mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p); } -/** - * clear_bit - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * clear_bit() is atomic and may not be reordered. However, it does - * not contain a memory barrier, so if it is used for locking purposes, - * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() - * in order to ensure changes are visible on other processors. - */ -static inline void clear_bit(int nr, volatile unsigned long *addr) +static inline void clear_bit(unsigned int nr, volatile unsigned long *p) { - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - *p &= ~mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p); } -/** - * change_bit - Toggle a bit in memory - * @nr: Bit to change - * @addr: Address to start counting from - * - * change_bit() is atomic and may not be reordered. It may be - * reordered on other architectures than x86. - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ -static inline void change_bit(int nr, volatile unsigned long *addr) +static inline void change_bit(unsigned int nr, volatile unsigned long *p) { - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - *p ^= mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p); } -/** - * test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It may be reordered on other architectures than x86. - * It also implies a memory barrier. - */ -static inline int test_and_set_bit(int nr, volatile unsigned long *addr) +static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p) { + long old; unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old; - unsigned long flags; - _atomic_spin_lock_irqsave(p, flags); - old = *p; - *p = old | mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + if (READ_ONCE(*p) & mask) + return 1; - return (old & mask) != 0; + old = atomic_long_fetch_or(mask, (atomic_long_t *)p); + return !!(old & mask); } -/** - * test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It can be reorderdered on other architectures other than x86. - * It also implies a memory barrier. - */ -static inline int test_and_clear_bit(int nr, volatile unsigned long *addr) +static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p) { + long old; unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old; - unsigned long flags; - _atomic_spin_lock_irqsave(p, flags); - old = *p; - *p = old & ~mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + if (!(READ_ONCE(*p) & mask)) + return 0; - return (old & mask) != 0; + old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p); + return !!(old & mask); } -/** - * test_and_change_bit - Change a bit and return its old value - * @nr: Bit to change - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. - */ -static inline int test_and_change_bit(int nr, volatile unsigned long *addr) +static inline int test_and_change_bit(unsigned int nr, volatile unsigned long *p) { + long old; unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old; - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - old = *p; - *p = old ^ mask; - _atomic_spin_unlock_irqrestore(p, flags); - return (old & mask) != 0; + p += BIT_WORD(nr); + old = atomic_long_fetch_xor(mask, (atomic_long_t *)p); + return !!(old & mask); } #endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */ diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h index 67ab280ad134..3ae021368f48 100644 --- a/include/asm-generic/bitops/lock.h +++ b/include/asm-generic/bitops/lock.h @@ -2,6 +2,10 @@ #ifndef _ASM_GENERIC_BITOPS_LOCK_H_ #define _ASM_GENERIC_BITOPS_LOCK_H_ +#include <linux/atomic.h> +#include <linux/compiler.h> +#include <asm/barrier.h> + /** * test_and_set_bit_lock - Set a bit and return its old value, for lock * @nr: Bit to set @@ -11,7 +15,20 @@ * the returned value is 0. * It can be used to implement bit locks. */ -#define test_and_set_bit_lock(nr, addr) test_and_set_bit(nr, addr) +static inline int test_and_set_bit_lock(unsigned int nr, + volatile unsigned long *p) +{ + long old; + unsigned long mask = BIT_MASK(nr); + + p += BIT_WORD(nr); + if (READ_ONCE(*p) & mask) + return 1; + + old = atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p); + return !!(old & mask); +} + /** * clear_bit_unlock - Clear a bit in memory, for unlock @@ -20,11 +37,11 @@ * * This operation is atomic and provides release barrier semantics. */ -#define clear_bit_unlock(nr, addr) \ -do { \ - smp_mb__before_atomic(); \ - clear_bit(nr, addr); \ -} while (0) +static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p) +{ + p += BIT_WORD(nr); + atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p); +} /** * __clear_bit_unlock - Clear a bit in memory, for unlock @@ -37,11 +54,38 @@ do { \ * * See for example x86's implementation. */ -#define __clear_bit_unlock(nr, addr) \ -do { \ - smp_mb__before_atomic(); \ - clear_bit(nr, addr); \ -} while (0) +static inline void __clear_bit_unlock(unsigned int nr, + volatile unsigned long *p) +{ + unsigned long old; -#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */ + p += BIT_WORD(nr); + old = READ_ONCE(*p); + old &= ~BIT_MASK(nr); + atomic_long_set_release((atomic_long_t *)p, old); +} + +/** + * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom + * byte is negative, for unlock. + * @nr: the bit to clear + * @addr: the address to start counting from + * + * This is a bit of a one-trick-pony for the filemap code, which clears + * PG_locked and tests PG_waiters, + */ +#ifndef clear_bit_unlock_is_negative_byte +static inline bool clear_bit_unlock_is_negative_byte(unsigned int nr, + volatile unsigned long *p) +{ + long old; + unsigned long mask = BIT_MASK(nr); + + p += BIT_WORD(nr); + old = atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p); + return !!(old & BIT(7)); +} +#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte +#endif +#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 01ce3997cb42..1e8e88bdaf09 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -2,6 +2,8 @@ /* Atomic operations usable in machine independent code */ #ifndef _LINUX_ATOMIC_H #define _LINUX_ATOMIC_H +#include <linux/types.h> + #include <asm/atomic.h> #include <asm/barrier.h> @@ -36,40 +38,46 @@ * barriers on top of the relaxed variant. In the case where the relaxed * variant is already fully ordered, no additional barriers are needed. * - * Besides, if an arch has a special barrier for acquire/release, it could - * implement its own __atomic_op_* and use the same framework for building - * variants - * - * If an architecture overrides __atomic_op_acquire() it will probably want - * to define smp_mb__after_spinlock(). + * If an architecture overrides __atomic_acquire_fence() it will probably + * want to define smp_mb__after_spinlock(). */ -#ifndef __atomic_op_acquire +#ifndef __atomic_acquire_fence +#define __atomic_acquire_fence smp_mb__after_atomic +#endif + +#ifndef __atomic_release_fence +#define __atomic_release_fence smp_mb__before_atomic +#endif + +#ifndef __atomic_pre_full_fence +#define __atomic_pre_full_fence smp_mb__before_atomic +#endif + +#ifndef __atomic_post_full_fence +#define __atomic_post_full_fence smp_mb__after_atomic +#endif + #define __atomic_op_acquire(op, args...) \ ({ \ typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - smp_mb__after_atomic(); \ + __atomic_acquire_fence(); \ __ret; \ }) -#endif -#ifndef __atomic_op_release #define __atomic_op_release(op, args...) \ ({ \ - smp_mb__before_atomic(); \ + __atomic_release_fence(); \ op##_relaxed(args); \ }) -#endif -#ifndef __atomic_op_fence #define __atomic_op_fence(op, args...) \ ({ \ typeof(op##_relaxed(args)) __ret; \ - smp_mb__before_atomic(); \ + __atomic_pre_full_fence(); \ __ret = op##_relaxed(args); \ - smp_mb__after_atomic(); \ + __atomic_post_full_fence(); \ __ret; \ }) -#endif /* atomic_add_return_relaxed */ #ifndef atomic_add_return_relaxed @@ -95,11 +103,23 @@ #endif #endif /* atomic_add_return_relaxed */ +#ifndef atomic_inc +#define atomic_inc(v) atomic_add(1, (v)) +#endif + /* atomic_inc_return_relaxed */ #ifndef atomic_inc_return_relaxed + +#ifndef atomic_inc_return +#define atomic_inc_return(v) atomic_add_return(1, (v)) +#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v)) +#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v)) +#define atomic_inc_return_release(v) atomic_add_return_release(1, (v)) +#else /* atomic_inc_return */ #define atomic_inc_return_relaxed atomic_inc_return #define atomic_inc_return_acquire atomic_inc_return #define atomic_inc_return_release atomic_inc_return +#endif /* atomic_inc_return */ #else /* atomic_inc_return_relaxed */ @@ -143,11 +163,23 @@ #endif #endif /* atomic_sub_return_relaxed */ +#ifndef atomic_dec +#define atomic_dec(v) atomic_sub(1, (v)) +#endif + /* atomic_dec_return_relaxed */ #ifndef atomic_dec_return_relaxed + +#ifndef atomic_dec_return +#define atomic_dec_return(v) atomic_sub_return(1, (v)) +#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v)) +#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v)) +#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v)) +#else /* atomic_dec_return */ #define atomic_dec_return_relaxed atomic_dec_return #define atomic_dec_return_acquire atomic_dec_return #define atomic_dec_return_release atomic_dec_return +#endif /* atomic_dec_return */ #else /* atomic_dec_return_relaxed */ @@ -328,12 +360,22 @@ #endif #endif /* atomic_fetch_and_relaxed */ -#ifdef atomic_andnot -/* atomic_fetch_andnot_relaxed */ +#ifndef atomic_andnot +#define atomic_andnot(i, v) atomic_and(~(int)(i), (v)) +#endif + #ifndef atomic_fetch_andnot_relaxed -#define atomic_fetch_andnot_relaxed atomic_fetch_andnot -#define atomic_fetch_andnot_acquire atomic_fetch_andnot -#define atomic_fetch_andnot_release atomic_fetch_andnot + +#ifndef atomic_fetch_andnot +#define atomic_fetch_andnot(i, v) atomic_fetch_and(~(int)(i), (v)) +#define atomic_fetch_andnot_relaxed(i, v) atomic_fetch_and_relaxed(~(int)(i), (v)) +#define atomic_fetch_andnot_acquire(i, v) atomic_fetch_and_acquire(~(int)(i), (v)) +#define atomic_fetch_andnot_release(i, v) atomic_fetch_and_release(~(int)(i), (v)) +#else /* atomic_fetch_andnot */ +#define atomic_fetch_andnot_relaxed atomic_fetch_andnot +#define atomic_fetch_andnot_acquire atomic_fetch_andnot +#define atomic_fetch_andnot_release atomic_fetch_andnot +#endif /* atomic_fetch_andnot */ #else /* atomic_fetch_andnot_relaxed */ @@ -352,7 +394,6 @@ __atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__) #endif #endif /* atomic_fetch_andnot_relaxed */ -#endif /* atomic_andnot */ /* atomic_fetch_xor_relaxed */ #ifndef atomic_fetch_xor_relaxed @@ -520,112 +561,140 @@ #endif /* xchg_relaxed */ /** + * atomic_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns the original value of @v. + */ +#ifndef atomic_fetch_add_unless +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int c = atomic_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!atomic_try_cmpxchg(v, &c, c + a)); + + return c; +} +#endif + +/** * atomic_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns non-zero if @v was not @u, and zero otherwise. + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. */ -static inline int atomic_add_unless(atomic_t *v, int a, int u) +static inline bool atomic_add_unless(atomic_t *v, int a, int u) { - return __atomic_add_unless(v, a, u) != u; + return atomic_fetch_add_unless(v, a, u) != u; } /** * atomic_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic_t * - * Atomically increments @v by 1, so long as @v is non-zero. - * Returns non-zero if @v was non-zero, and zero otherwise. + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. */ #ifndef atomic_inc_not_zero #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) #endif -#ifndef atomic_andnot -static inline void atomic_andnot(int i, atomic_t *v) -{ - atomic_and(~i, v); -} - -static inline int atomic_fetch_andnot(int i, atomic_t *v) -{ - return atomic_fetch_and(~i, v); -} - -static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) +/** + * atomic_inc_and_test - increment and test + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic_inc_and_test +static inline bool atomic_inc_and_test(atomic_t *v) { - return atomic_fetch_and_relaxed(~i, v); + return atomic_inc_return(v) == 0; } +#endif -static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) +/** + * atomic_dec_and_test - decrement and test + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +#ifndef atomic_dec_and_test +static inline bool atomic_dec_and_test(atomic_t *v) { - return atomic_fetch_and_acquire(~i, v); + return atomic_dec_return(v) == 0; } +#endif -static inline int atomic_fetch_andnot_release(int i, atomic_t *v) +/** + * atomic_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic_sub_and_test +static inline bool atomic_sub_and_test(int i, atomic_t *v) { - return atomic_fetch_and_release(~i, v); + return atomic_sub_return(i, v) == 0; } #endif /** - * atomic_inc_not_zero_hint - increment if not null + * atomic_add_negative - add and test if negative + * @i: integer value to add * @v: pointer of type atomic_t - * @hint: probable value of the atomic before the increment - * - * This version of atomic_inc_not_zero() gives a hint of probable - * value of the atomic. This helps processor to not read the memory - * before doing the atomic read/modify/write cycle, lowering - * number of bus transactions on some arches. * - * Returns: 0 if increment was not done, 1 otherwise. + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. */ -#ifndef atomic_inc_not_zero_hint -static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint) +#ifndef atomic_add_negative +static inline bool atomic_add_negative(int i, atomic_t *v) { - int val, c = hint; - - /* sanity test, should be removed by compiler if hint is a constant */ - if (!hint) - return atomic_inc_not_zero(v); - - do { - val = atomic_cmpxchg(v, c, c + 1); - if (val == c) - return 1; - c = val; - } while (c); - - return 0; + return atomic_add_return(i, v) < 0; } #endif #ifndef atomic_inc_unless_negative -static inline int atomic_inc_unless_negative(atomic_t *p) +static inline bool atomic_inc_unless_negative(atomic_t *v) { - int v, v1; - for (v = 0; v >= 0; v = v1) { - v1 = atomic_cmpxchg(p, v, v + 1); - if (likely(v1 == v)) - return 1; - } - return 0; + int c = atomic_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c + 1)); + + return true; } #endif #ifndef atomic_dec_unless_positive -static inline int atomic_dec_unless_positive(atomic_t *p) +static inline bool atomic_dec_unless_positive(atomic_t *v) { - int v, v1; - for (v = 0; v <= 0; v = v1) { - v1 = atomic_cmpxchg(p, v, v - 1); - if (likely(v1 == v)) - return 1; - } - return 0; + int c = atomic_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c - 1)); + + return true; } #endif @@ -639,17 +708,14 @@ static inline int atomic_dec_unless_positive(atomic_t *p) #ifndef atomic_dec_if_positive static inline int atomic_dec_if_positive(atomic_t *v) { - int c, old, dec; - c = atomic_read(v); - for (;;) { + int dec, c = atomic_read(v); + + do { dec = c - 1; if (unlikely(dec < 0)) break; - old = atomic_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } + } while (!atomic_try_cmpxchg(v, &c, dec)); + return dec; } #endif @@ -693,11 +759,23 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_add_return_relaxed */ +#ifndef atomic64_inc +#define atomic64_inc(v) atomic64_add(1, (v)) +#endif + /* atomic64_inc_return_relaxed */ #ifndef atomic64_inc_return_relaxed + +#ifndef atomic64_inc_return +#define atomic64_inc_return(v) atomic64_add_return(1, (v)) +#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v)) +#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v)) +#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v)) +#else /* atomic64_inc_return */ #define atomic64_inc_return_relaxed atomic64_inc_return #define atomic64_inc_return_acquire atomic64_inc_return #define atomic64_inc_return_release atomic64_inc_return +#endif /* atomic64_inc_return */ #else /* atomic64_inc_return_relaxed */ @@ -742,11 +820,23 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_sub_return_relaxed */ +#ifndef atomic64_dec +#define atomic64_dec(v) atomic64_sub(1, (v)) +#endif + /* atomic64_dec_return_relaxed */ #ifndef atomic64_dec_return_relaxed + +#ifndef atomic64_dec_return +#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) +#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v)) +#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v)) +#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v)) +#else /* atomic64_dec_return */ #define atomic64_dec_return_relaxed atomic64_dec_return #define atomic64_dec_return_acquire atomic64_dec_return #define atomic64_dec_return_release atomic64_dec_return +#endif /* atomic64_dec_return */ #else /* atomic64_dec_return_relaxed */ @@ -927,12 +1017,22 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_fetch_and_relaxed */ -#ifdef atomic64_andnot -/* atomic64_fetch_andnot_relaxed */ +#ifndef atomic64_andnot +#define atomic64_andnot(i, v) atomic64_and(~(long long)(i), (v)) +#endif + #ifndef atomic64_fetch_andnot_relaxed -#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot -#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot -#define atomic64_fetch_andnot_release atomic64_fetch_andnot + +#ifndef atomic64_fetch_andnot +#define atomic64_fetch_andnot(i, v) atomic64_fetch_and(~(long long)(i), (v)) +#define atomic64_fetch_andnot_relaxed(i, v) atomic64_fetch_and_relaxed(~(long long)(i), (v)) +#define atomic64_fetch_andnot_acquire(i, v) atomic64_fetch_and_acquire(~(long long)(i), (v)) +#define atomic64_fetch_andnot_release(i, v) atomic64_fetch_and_release(~(long long)(i), (v)) +#else /* atomic64_fetch_andnot */ +#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot +#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot +#define atomic64_fetch_andnot_release atomic64_fetch_andnot +#endif /* atomic64_fetch_andnot */ #else /* atomic64_fetch_andnot_relaxed */ @@ -951,7 +1051,6 @@ static inline int atomic_dec_if_positive(atomic_t *v) __atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__) #endif #endif /* atomic64_fetch_andnot_relaxed */ -#endif /* atomic64_andnot */ /* atomic64_fetch_xor_relaxed */ #ifndef atomic64_fetch_xor_relaxed @@ -1049,30 +1148,164 @@ static inline int atomic_dec_if_positive(atomic_t *v) #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg #endif /* atomic64_try_cmpxchg */ -#ifndef atomic64_andnot -static inline void atomic64_andnot(long long i, atomic64_t *v) +/** + * atomic64_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns the original value of @v. + */ +#ifndef atomic64_fetch_add_unless +static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, + long long u) { - atomic64_and(~i, v); + long long c = atomic64_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!atomic64_try_cmpxchg(v, &c, c + a)); + + return c; } +#endif -static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v) +/** + * atomic64_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u) { - return atomic64_fetch_and(~i, v); + return atomic64_fetch_add_unless(v, a, u) != u; } -static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v) +/** + * atomic64_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +#ifndef atomic64_inc_not_zero +#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +#endif + +/** + * atomic64_inc_and_test - increment and test + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic64_inc_and_test +static inline bool atomic64_inc_and_test(atomic64_t *v) { - return atomic64_fetch_and_relaxed(~i, v); + return atomic64_inc_return(v) == 0; } +#endif -static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v) +/** + * atomic64_dec_and_test - decrement and test + * @v: pointer of type atomic64_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +#ifndef atomic64_dec_and_test +static inline bool atomic64_dec_and_test(atomic64_t *v) { - return atomic64_fetch_and_acquire(~i, v); + return atomic64_dec_return(v) == 0; } +#endif -static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v) +/** + * atomic64_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic64_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic64_sub_and_test +static inline bool atomic64_sub_and_test(long long i, atomic64_t *v) +{ + return atomic64_sub_return(i, v) == 0; +} +#endif + +/** + * atomic64_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +#ifndef atomic64_add_negative +static inline bool atomic64_add_negative(long long i, atomic64_t *v) { - return atomic64_fetch_and_release(~i, v); + return atomic64_add_return(i, v) < 0; +} +#endif + +#ifndef atomic64_inc_unless_negative +static inline bool atomic64_inc_unless_negative(atomic64_t *v) +{ + long long c = atomic64_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#endif + +#ifndef atomic64_dec_unless_positive +static inline bool atomic64_dec_unless_positive(atomic64_t *v) +{ + long long c = atomic64_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#endif + +/* + * atomic64_dec_if_positive - decrement by 1 if old value positive + * @v: pointer of type atomic64_t + * + * The function returns the old value of *v minus 1, even if + * the atomic64 variable, v, was not decremented. + */ +#ifndef atomic64_dec_if_positive +static inline long long atomic64_dec_if_positive(atomic64_t *v) +{ + long long dec, c = atomic64_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!atomic64_try_cmpxchg(v, &c, dec)); + + return dec; } #endif diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 4cac4e1a72ff..af419012d77d 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -2,29 +2,9 @@ #ifndef _LINUX_BITOPS_H #define _LINUX_BITOPS_H #include <asm/types.h> +#include <linux/bits.h> -#ifdef __KERNEL__ -#define BIT(nr) (1UL << (nr)) -#define BIT_ULL(nr) (1ULL << (nr)) -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) -#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) -#define BITS_PER_BYTE 8 #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) -#endif - -/* - * Create a contiguous bitmask starting at bit position @l and ending at - * position @h. For example - * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. - */ -#define GENMASK(h, l) \ - (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) - -#define GENMASK_ULL(h, l) \ - (((~0ULL) - (1ULL << (l)) + 1) & \ - (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/include/linux/bits.h b/include/linux/bits.h new file mode 100644 index 000000000000..2b7b532c1d51 --- /dev/null +++ b/include/linux/bits.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_BITS_H +#define __LINUX_BITS_H +#include <asm/bitsperlong.h> + +#define BIT(nr) (1UL << (nr)) +#define BIT_ULL(nr) (1ULL << (nr)) +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) +#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) +#define BITS_PER_BYTE 8 + +/* + * Create a contiguous bitmask starting at bit position @l and ending at + * position @h. For example + * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. + */ +#define GENMASK(h, l) \ + (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + +#define GENMASK_ULL(h, l) \ + (((~0ULL) - (1ULL << (l)) + 1) & \ + (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* __LINUX_BITS_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e3147eb74222..ca3f2c2edd85 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -287,6 +287,20 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); +/** + * blk_mq_mark_complete() - Set request state to complete + * @rq: request to set to complete state + * + * Returns true if request state was successfully set to complete. If + * successful, the caller is responsibile for seeing this request is ended, as + * blk_mq_complete_request will not work again. + */ +static inline bool blk_mq_mark_complete(struct request *rq) +{ + return cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) == + MQ_RQ_IN_FLIGHT; +} + /* * Driver command data is immediately after the request. So subtract request * size to get back to the original request, add request size to get the PDU. diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 79795c5fa7c3..d50c2f0a655a 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -2,6 +2,7 @@ #ifndef _BPF_CGROUP_H #define _BPF_CGROUP_H +#include <linux/errno.h> #include <linux/jump_label.h> #include <uapi/linux/bpf.h> diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index 687b1760bb9f..f02cee0225d4 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -5,10 +5,10 @@ #include <uapi/linux/bpfilter.h> struct sock; -int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval, +int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen); -int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval, - int *optlen); +int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, + int __user *optlen); extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname, char __user *optval, unsigned int optlen, bool is_set); diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 7dff1963c185..308918928767 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -194,6 +194,9 @@ extern void clocksource_suspend(void); extern void clocksource_resume(void); extern struct clocksource * __init clocksource_default_clock(void); extern void clocksource_mark_unstable(struct clocksource *cs); +extern void +clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles); +extern u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 now); extern u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles); diff --git a/include/linux/compat.h b/include/linux/compat.h index c68acc47da57..df45ee8413d6 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -115,11 +115,6 @@ typedef compat_ulong_t compat_aio_context_t; struct compat_sel_arg_struct; struct rusage; -struct compat_itimerspec { - struct compat_timespec it_interval; - struct compat_timespec it_value; -}; - struct compat_utimbuf { compat_time_t actime; compat_time_t modtime; @@ -300,10 +295,6 @@ extern int compat_get_timespec(struct timespec *, const void __user *); extern int compat_put_timespec(const struct timespec *, void __user *); extern int compat_get_timeval(struct timeval *, const void __user *); extern int compat_put_timeval(const struct timeval *, void __user *); -extern int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits); -extern int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits); struct compat_iovec { compat_uptr_t iov_base; diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h index 31f2774f1994..e70bfd1d2c3f 100644 --- a/include/linux/compat_time.h +++ b/include/linux/compat_time.h @@ -17,7 +17,16 @@ struct compat_timeval { s32 tv_usec; }; +struct compat_itimerspec { + struct compat_timespec it_interval; + struct compat_timespec it_value; +}; + extern int compat_get_timespec64(struct timespec64 *, const void __user *); extern int compat_put_timespec64(const struct timespec64 *, void __user *); +extern int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits); +extern int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits); #endif /* _LINUX_COMPAT_TIME_H */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a97a63eef59f..3233fbe23594 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -30,7 +30,7 @@ struct cpu { }; extern void boot_cpu_init(void); -extern void boot_cpu_state_init(void); +extern void boot_cpu_hotplug_init(void); extern void cpu_init(void); extern void trap_init(void); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 8796ba387152..4cf06a64bc02 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -164,6 +164,7 @@ enum cpuhp_state { CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, + CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index e6c0448ebcc7..31c865d1842e 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -124,7 +124,7 @@ static inline void delayacct_blkio_start(void) static inline void delayacct_blkio_end(struct task_struct *p) { - if (current->delays) + if (p->delays) __delayacct_blkio_end(p); delayacct_clear_flag(DELAYACCT_PF_BLKIO); } diff --git a/include/linux/efi.h b/include/linux/efi.h index 56add823f190..401e4b254e30 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -894,6 +894,16 @@ typedef struct _efi_file_handle { void *flush; } efi_file_handle_t; +typedef struct { + u64 revision; + u32 open_volume; +} efi_file_io_interface_32_t; + +typedef struct { + u64 revision; + u64 open_volume; +} efi_file_io_interface_64_t; + typedef struct _efi_file_io_interface { u64 revision; int (*open_volume)(struct _efi_file_io_interface *, @@ -988,14 +998,12 @@ extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg); extern void efi_gettimeofday (struct timespec64 *ts); extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ #ifdef CONFIG_X86 -extern void efi_late_init(void); extern void efi_free_boot_services(void); extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size, bool nonblocking); extern void efi_find_mirror(void); #else -static inline void efi_late_init(void) {} static inline void efi_free_boot_services(void) {} static inline efi_status_t efi_query_variable_store(u32 attributes, @@ -1651,4 +1659,7 @@ struct linux_efi_tpm_eventlog { extern int efi_tpm_eventlog_init(void); +/* Workqueue to queue EFI Runtime Services */ +extern struct workqueue_struct *efi_rts_wq; + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 7094718b653b..ffcc7724ca21 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -11,6 +11,7 @@ #include <linux/fcntl.h> #include <linux/wait.h> +#include <linux/err.h> /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining diff --git a/include/linux/filter.h b/include/linux/filter.h index 300baad62c88..c73dd7396886 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -765,8 +765,8 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); -static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, - struct net_device *fwd) +static inline int xdp_ok_fwd_dev(const struct net_device *fwd, + unsigned int pktlen) { unsigned int len; @@ -774,7 +774,7 @@ static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; - if (skb->len > len) + if (pktlen > len) return -EMSGSIZE; return 0; diff --git a/include/linux/fs.h b/include/linux/fs.h index d78d146a98da..805bf22898cf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2420,6 +2420,7 @@ extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); +extern struct file *filp_clone_open(struct file *); extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); diff --git a/include/linux/fsl/guts.h b/include/linux/fsl/guts.h index 3efa3b861d44..941b11811f85 100644 --- a/include/linux/fsl/guts.h +++ b/include/linux/fsl/guts.h @@ -16,6 +16,7 @@ #define __FSL_GUTS_H__ #include <linux/types.h> +#include <linux/io.h> /** * Global Utility Registers. diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 7843b98e1c6e..c20c7e197d07 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -105,13 +105,13 @@ static inline bool br_vlan_enabled(const struct net_device *dev) static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { - return -1; + return -EINVAL; } static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { - return -1; + return -EINVAL; } #endif diff --git a/include/linux/igmp.h b/include/linux/igmp.h index f8231854b5d6..119f53941c12 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -109,6 +109,8 @@ struct ip_mc_list { extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); +extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, + unsigned int mode); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 1df940196ab2..ef169d67df92 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -121,6 +121,7 @@ #define ecap_srs(e) ((e >> 31) & 0x1) #define ecap_ers(e) ((e >> 30) & 0x1) #define ecap_prs(e) ((e >> 29) & 0x1) +#define ecap_broken_pasid(e) ((e >> 28) & 0x1) #define ecap_dis(e) ((e >> 27) & 0x1) #define ecap_nest(e) ((e >> 26) & 0x1) #define ecap_mts(e) ((e >> 25) & 0x1) diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index cbb872c1b607..9d2ea3e907d0 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -73,6 +73,7 @@ #define GICD_TYPER_MBIS (1U << 16) #define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1) +#define GICD_TYPER_NUM_LPIS(typer) ((((typer) >> 11) & 0x1f) + 1) #define GICD_TYPER_IRQS(typer) ((((typer) & 0x1f) + 1) * 32) #define GICD_IROUTER_SPI_MODE_ONE (0U << 31) @@ -576,8 +577,8 @@ struct rdists { phys_addr_t phys_base; } __percpu *rdist; struct page *prop_page; - int id_bits; u64 flags; + u32 gicd_typer; bool has_vlpis; bool has_direct_lpi; }; diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9440a2fc8893..e909413e4e38 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -63,7 +63,6 @@ struct pt_regs; struct kretprobe; struct kretprobe_instance; typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *); -typedef int (*kprobe_break_handler_t) (struct kprobe *, struct pt_regs *); typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *, unsigned long flags); typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *, @@ -101,12 +100,6 @@ struct kprobe { */ kprobe_fault_handler_t fault_handler; - /* - * ... called if breakpoint trap occurs in probe handler. - * Return 1 if it handled break, otherwise kernel will see it. - */ - kprobe_break_handler_t break_handler; - /* Saved opcode (which has been replaced with breakpoint) */ kprobe_opcode_t opcode; @@ -155,24 +148,6 @@ static inline int kprobe_ftrace(struct kprobe *p) } /* - * Special probe type that uses setjmp-longjmp type tricks to resume - * execution at a specified entry with a matching prototype corresponding - * to the probed function - a trick to enable arguments to become - * accessible seamlessly by probe handling logic. - * Note: - * Because of the way compilers allocate stack space for local variables - * etc upfront, regardless of sub-scopes within a function, this mirroring - * principle currently works only for probes placed on function entry points. - */ -struct jprobe { - struct kprobe kp; - void *entry; /* probe handling code to jump to */ -}; - -/* For backward compatibility with old code using JPROBE_ENTRY() */ -#define JPROBE_ENTRY(handler) (handler) - -/* * Function-return probe - * Note: * User needs to provide a handler function, and initialize maxactive. @@ -389,9 +364,6 @@ int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); void unregister_kprobes(struct kprobe **kps, int num); -int setjmp_pre_handler(struct kprobe *, struct pt_regs *); -int longjmp_break_handler(struct kprobe *, struct pt_regs *); -void jprobe_return(void); unsigned long arch_deref_entry_point(void *); int register_kretprobe(struct kretprobe *rp); @@ -439,9 +411,6 @@ static inline void unregister_kprobe(struct kprobe *p) static inline void unregister_kprobes(struct kprobe **kps, int num) { } -static inline void jprobe_return(void) -{ -} static inline int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; @@ -468,20 +437,6 @@ static inline int enable_kprobe(struct kprobe *kp) return -ENOSYS; } #endif /* CONFIG_KPROBES */ -static inline int register_jprobe(struct jprobe *p) -{ - return -ENOSYS; -} -static inline int register_jprobes(struct jprobe **jps, int num) -{ - return -ENOSYS; -} -static inline void unregister_jprobe(struct jprobe *p) -{ -} -static inline void unregister_jprobes(struct jprobe **jps, int num) -{ -} static inline int disable_kretprobe(struct kretprobe *rp) { return disable_kprobe(&rp->kp); @@ -490,14 +445,6 @@ static inline int enable_kretprobe(struct kretprobe *rp) { return enable_kprobe(&rp->kp); } -static inline int disable_jprobe(struct jprobe *jp) -{ - return -ENOSYS; -} -static inline int enable_jprobe(struct jprobe *jp) -{ - return -ENOSYS; -} #ifndef CONFIG_KPROBES static inline bool is_kprobe_insn_slot(unsigned long addr) diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 5b9fddbaac41..b2bb44f87f5a 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -93,8 +93,11 @@ static inline ktime_t timeval_to_ktime(struct timeval tv) /* Map the ktime_t to timeval conversion to ns_to_timeval function */ #define ktime_to_timeval(kt) ns_to_timeval((kt)) -/* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */ -#define ktime_to_ns(kt) (kt) +/* Convert ktime_t to nanoseconds */ +static inline s64 ktime_to_ns(const ktime_t kt) +{ + return kt; +} /** * ktime_compare - Compares two ktime_t variables for less, greater or equal diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 4f5f8c21e283..1eb6f244588d 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -27,6 +27,8 @@ */ #define MARVELL_PHY_ID_88E6390 0x01410f90 +#define MARVELL_PHY_FAMILY_ID(id) ((id) >> 4) + /* struct phy_device dev_flags definitions */ #define MARVELL_PHY_M1145_FLAGS_RESISTANCE 0x00000001 #define MARVELL_PHY_M1118_DNS323_LEDS 0x00000002 diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80cbb7fdce4a..83957920653a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -358,6 +358,7 @@ struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; u32 frag_sz_m1; + u32 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -983,14 +984,22 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } -static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, - struct mlx5_frag_buf_ctrl *fbc) +static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, + u32 strides_offset, + struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; fbc->log_sz = log_sz; fbc->sz_m1 = (1 << fbc->log_sz) - 1; fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride; fbc->frag_sz_m1 = (1 << fbc->log_frag_strides) - 1; + fbc->strides_offset = strides_offset; +} + +static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, + struct mlx5_frag_buf_ctrl *fbc) +{ + mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc); } static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, @@ -1004,7 +1013,10 @@ static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, u32 ix) { - unsigned int frag = (ix >> fbc->log_frag_strides); + unsigned int frag; + + ix += fbc->strides_offset; + frag = ix >> fbc->log_frag_strides; return fbc->frag_buf.frags[frag].buf + ((fbc->frag_sz_m1 & ix) << fbc->log_stride); diff --git a/include/linux/mm.h b/include/linux/mm.h index a0fbb9ffe380..68a5121694ef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -155,7 +155,9 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, * mmap() functions). */ -extern struct kmem_cache *vm_area_cachep; +struct vm_area_struct *vm_area_alloc(struct mm_struct *); +struct vm_area_struct *vm_area_dup(struct vm_area_struct *); +void vm_area_free(struct vm_area_struct *); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; @@ -450,6 +452,23 @@ struct vm_operations_struct { unsigned long addr); }; +static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) +{ + static const struct vm_operations_struct dummy_vm_ops = {}; + + vma->vm_mm = mm; + vma->vm_ops = &dummy_vm_ops; + INIT_LIST_HEAD(&vma->anon_vma_chain); +} + +static inline void vma_set_anonymous(struct vm_area_struct *vma) +{ + vma->vm_ops = NULL; +} + +/* flush_tlb_range() takes a vma, not a mm, and can care about flags */ +#define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } + struct mmu_gather; struct inode; @@ -2132,7 +2151,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#ifdef CONFIG_HAVE_MEMBLOCK +#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) void zero_resv_unavail(void); #else static inline void zero_resv_unavail(void) {} diff --git a/include/linux/nmi.h b/include/linux/nmi.h index b8d868d23e79..08f9247e9827 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -45,12 +45,18 @@ extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; -#else + +extern int lockup_detector_online_cpu(unsigned int cpu); +extern int lockup_detector_offline_cpu(unsigned int cpu); +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ static inline void touch_softlockup_watchdog_sched(void) { } static inline void touch_softlockup_watchdog(void) { } static inline void touch_softlockup_watchdog_sync(void) { } static inline void touch_all_softlockup_watchdogs(void) { } -#endif + +#define lockup_detector_online_cpu NULL +#define lockup_detector_offline_cpu NULL +#endif /* CONFIG_SOFTLOCKUP_DETECTOR */ #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..c133ccfa002e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -368,7 +368,6 @@ struct pci_dev { unsigned int transparent:1; /* Subtractive decode bridge */ unsigned int multifunction:1; /* Multi-function device */ - unsigned int is_added:1; unsigned int is_busmaster:1; /* Is busmaster */ unsigned int no_msi:1; /* May not use MSI */ unsigned int no_64bit_msi:1; /* May only use 32-bit MSIs */ @@ -1240,6 +1239,8 @@ int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr, unsigned long pci_address_to_pio(phys_addr_t addr); phys_addr_t pci_pio_to_address(unsigned long pio); int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr); +int devm_pci_remap_iospace(struct device *dev, const struct resource *res, + phys_addr_t phys_addr); void pci_unmap_iospace(struct resource *res); void __iomem *devm_pci_remap_cfgspace(struct device *dev, resource_size_t offset, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1fa12887ec02..53c500f0ca79 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -490,7 +490,7 @@ struct perf_addr_filters_head { }; /** - * enum perf_event_state - the states of a event + * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, @@ -1130,6 +1130,7 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); +extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index c85704fcdbd2..ee7e987ea1b4 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -95,8 +95,8 @@ struct k_itimer { clockid_t it_clock; timer_t it_id; int it_active; - int it_overrun; - int it_overrun_last; + s64 it_overrun; + s64 it_overrun_last; int it_requeue_pending; int it_sigev_notify; ktime_t it_interval; diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 36df6ccbc874..4786c2235b98 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -396,7 +396,16 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after - * the current position. + * the current position which must have been in the list when the RCU read + * lock was taken. + * This would typically require either that you obtained the node from a + * previous walk of the list in the same RCU read-side critical section, or + * that you held some sort of non-RCU reference (such as a reference count) + * to keep the node alive *and* in the list. + * + * This iterator is similar to list_for_each_entry_from_rcu() except + * this starts after the given position and that one starts at the given + * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ @@ -411,6 +420,14 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. + * This would typically require either that you obtained the node from a + * previous walk of the list in the same RCU read-side critical section, or + * that you held some sort of non-RCU reference (such as a reference count) + * to keep the node alive *and* in the list. + * + * This iterator is similar to list_for_each_entry_continue_rcu() except + * this starts from the given position and that one starts from the position + * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 65163aa0bb04..75e5b393cf44 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -64,7 +64,6 @@ void rcu_barrier_tasks(void); void __rcu_read_lock(void); void __rcu_read_unlock(void); -void rcu_read_unlock_special(struct task_struct *t); void synchronize_rcu(void); /* @@ -159,11 +158,11 @@ static inline void rcu_init_nohz(void) { } } while (0) /* - * Note a voluntary context switch for RCU-tasks benefit. This is a - * macro rather than an inline function to avoid #include hell. + * Note a quasi-voluntary context switch for RCU-tasks's benefit. + * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU -#define rcu_note_voluntary_context_switch_lite(t) \ +#define rcu_tasks_qs(t) \ do { \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ @@ -171,14 +170,14 @@ static inline void rcu_init_nohz(void) { } #define rcu_note_voluntary_context_switch(t) \ do { \ rcu_all_qs(); \ - rcu_note_voluntary_context_switch_lite(t); \ + rcu_tasks_qs(t); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ -#define rcu_note_voluntary_context_switch_lite(t) do { } while (0) +#define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() #define call_rcu_tasks call_rcu_sched #define synchronize_rcu_tasks synchronize_sched @@ -195,8 +194,8 @@ static inline void exit_tasks_rcu_finish(void) { } */ #define cond_resched_tasks_rcu_qs() \ do { \ - if (!cond_resched()) \ - rcu_note_voluntary_context_switch_lite(current); \ + rcu_tasks_qs(current); \ + cond_resched(); \ } while (0) /* @@ -567,8 +566,8 @@ static inline void rcu_preempt_sleep_check(void) { } * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to - * kill_dependency(). It could be used as follows: - * `` + * kill_dependency(). It could be used as follows:: + * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); @@ -579,7 +578,6 @@ static inline void rcu_preempt_sleep_check(void) { } * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); - *`` */ #define rcu_pointer_handoff(p) (p) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 7b3c82e8a625..8d9a0ea8f0b5 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -93,7 +93,7 @@ static inline void kfree_call_rcu(struct rcu_head *head, #define rcu_note_context_switch(preempt) \ do { \ rcu_sched_qs(); \ - rcu_note_voluntary_context_switch_lite(current); \ + rcu_tasks_qs(current); \ } while (0) static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) diff --git a/include/linux/refcount.h b/include/linux/refcount.h index a685da2c4522..e28cce21bad6 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -3,9 +3,10 @@ #define _LINUX_REFCOUNT_H #include <linux/atomic.h> -#include <linux/mutex.h> -#include <linux/spinlock.h> -#include <linux/kernel.h> +#include <linux/compiler.h> +#include <linux/spinlock_types.h> + +struct mutex; /** * struct refcount_t - variant of atomic_t specialized for reference counts @@ -42,17 +43,30 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } +extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r); +extern void refcount_add_checked(unsigned int i, refcount_t *r); + +extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r); +extern void refcount_inc_checked(refcount_t *r); + +extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r); + +extern __must_check bool refcount_dec_and_test_checked(refcount_t *r); +extern void refcount_dec_checked(refcount_t *r); + #ifdef CONFIG_REFCOUNT_FULL -extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r); -extern void refcount_add(unsigned int i, refcount_t *r); -extern __must_check bool refcount_inc_not_zero(refcount_t *r); -extern void refcount_inc(refcount_t *r); +#define refcount_add_not_zero refcount_add_not_zero_checked +#define refcount_add refcount_add_checked + +#define refcount_inc_not_zero refcount_inc_not_zero_checked +#define refcount_inc refcount_inc_checked + +#define refcount_sub_and_test refcount_sub_and_test_checked -extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r); +#define refcount_dec_and_test refcount_dec_and_test_checked +#define refcount_dec refcount_dec_checked -extern __must_check bool refcount_dec_and_test(refcount_t *r); -extern void refcount_dec(refcount_t *r); #else # ifdef CONFIG_ARCH_HAS_REFCOUNT # include <asm/refcount.h> diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index b72ebdff0b77..003d09ab308d 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer); void ring_buffer_record_off(struct ring_buffer *buffer); void ring_buffer_record_on(struct ring_buffer *buffer); int ring_buffer_record_is_on(struct ring_buffer *buffer); +int ring_buffer_record_is_set_on(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 1b92a28dd672..6fd615a0eea9 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -106,7 +106,14 @@ static inline int rt_mutex_is_locked(struct rt_mutex *lock) extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); extern void rt_mutex_destroy(struct rt_mutex *lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass); +#define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0) +#else extern void rt_mutex_lock(struct rt_mutex *lock); +#define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock) +#endif + extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); extern int rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout); diff --git a/include/linux/sched.h b/include/linux/sched.h index 43731fe51c97..dac5086e3815 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -167,8 +167,8 @@ struct task_group; * need_sleep = false; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * - * Where wake_up_state() (and all other wakeup primitives) imply enough - * barriers to order the store of the variable against wakeup. + * where wake_up_state() executes a full memory barrier before accessing the + * task state. * * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a @@ -1017,7 +1017,6 @@ struct task_struct { u64 last_sum_exec_runtime; struct callback_head numa_work; - struct list_head numa_entry; struct numa_group *numa_group; /* diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 1c1a1512ec55..913488d828cb 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -40,7 +40,6 @@ extern unsigned int sysctl_numa_balancing_scan_size; #ifdef CONFIG_SCHED_DEBUG extern __read_mostly unsigned int sysctl_sched_migration_cost; extern __read_mostly unsigned int sysctl_sched_nr_migrate; -extern __read_mostly unsigned int sysctl_sched_time_avg; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 5be31eb7b266..108ede99e533 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -75,7 +75,7 @@ extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -extern long kernel_wait4(pid_t, int *, int, struct rusage *); +extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); extern void free_task(struct task_struct *tsk); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 164cdedf6012..610a201126ee 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -630,6 +630,7 @@ typedef unsigned char *sk_buff_data_t; * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @xmit_more: More SKBs are pending for this queue + * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport @@ -735,7 +736,7 @@ struct sk_buff { peeked:1, head_frag:1, xmit_more:1, - __unused:1; /* one bit hole */ + pfmemalloc:1; /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() @@ -754,31 +755,30 @@ struct sk_buff { __u8 __pkt_type_offset[0]; __u8 pkt_type:3; - __u8 pfmemalloc:1; __u8 ignore_df:1; - __u8 nf_trace:1; __u8 ip_summed:2; __u8 ooo_okay:1; + __u8 l4_hash:1; __u8 sw_hash:1; __u8 wifi_acked_valid:1; __u8 wifi_acked:1; - __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; + __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 csum_not_inet:1; - __u8 dst_pending_confirm:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif __u8 ipvs_property:1; + __u8 inner_protocol_type:1; __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index c174844cf663..d0884b525001 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -25,8 +25,6 @@ struct smpboot_thread_data; * parked (cpu offline) * @unpark: Optional unpark function, called when the thread is * unparked (cpu online) - * @cpumask: Internal state. To update which threads are unparked, - * call smpboot_update_cpumask_percpu_thread(). * @selfparking: Thread is not parked by the park function. * @thread_comm: The base name of the thread */ @@ -40,23 +38,12 @@ struct smp_hotplug_thread { void (*cleanup)(unsigned int cpu, bool online); void (*park)(unsigned int cpu); void (*unpark)(unsigned int cpu); - cpumask_var_t cpumask; bool selfparking; const char *thread_comm; }; -int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread, - const struct cpumask *cpumask); - -static inline int -smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) -{ - return smpboot_register_percpu_thread_cpumask(plug_thread, - cpu_possible_mask); -} +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread); void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); -void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *); #endif diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index fd57888d4942..3190997df9ca 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -114,29 +114,48 @@ do { \ #endif /*arch_spin_is_contended*/ /* - * This barrier must provide two things: + * smp_mb__after_spinlock() provides the equivalent of a full memory barrier + * between program-order earlier lock acquisitions and program-order later + * memory accesses. * - * - it must guarantee a STORE before the spin_lock() is ordered against a - * LOAD after it, see the comments at its two usage sites. + * This guarantees that the following two properties hold: * - * - it must ensure the critical section is RCsc. + * 1) Given the snippet: * - * The latter is important for cases where we observe values written by other - * CPUs in spin-loops, without barriers, while being subject to scheduling. + * { X = 0; Y = 0; } * - * CPU0 CPU1 CPU2 + * CPU0 CPU1 * - * for (;;) { - * if (READ_ONCE(X)) - * break; - * } - * X=1 - * <sched-out> - * <sched-in> - * r = X; + * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); + * spin_lock(S); smp_mb(); + * smp_mb__after_spinlock(); r1 = READ_ONCE(X); + * r0 = READ_ONCE(Y); + * spin_unlock(S); * - * without transitivity it could be that CPU1 observes X!=0 breaks the loop, - * we get migrated and CPU2 sees X==0. + * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) + * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments + * preceding the call to smp_mb__after_spinlock() in __schedule() and in + * try_to_wake_up(). + * + * 2) Given the snippet: + * + * { X = 0; Y = 0; } + * + * CPU0 CPU1 CPU2 + * + * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); + * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); + * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); + * WRITE_ONCE(Y, 1); + * spin_unlock(S); + * + * it is forbidden that CPU0's critical section executes before CPU1's + * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) + * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments + * preceding the calls to smp_rmb() in try_to_wake_up() for similar + * snippets but "projected" onto two CPUs. + * + * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 91494d7e8e41..3e72a291c401 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -195,6 +195,16 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) return retval; } +/* Used by tracing, cannot be traced and cannot invoke lockdep. */ +static inline notrace int +srcu_read_lock_notrace(struct srcu_struct *sp) __acquires(sp) +{ + int retval; + + retval = __srcu_read_lock(sp); + return retval; +} + /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @sp: srcu_struct in which to unregister the old reader. @@ -209,6 +219,13 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) __srcu_read_unlock(sp, idx); } +/* Used by tracing, cannot be traced and cannot call lockdep. */ +static inline notrace void +srcu_read_unlock_notrace(struct srcu_struct *sp, int idx) __releases(sp) +{ + __srcu_read_unlock(sp, idx); +} + /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * diff --git a/include/linux/swait.h b/include/linux/swait.h index bf8cb0dee23c..73e06e9986d4 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -16,7 +16,7 @@ * wait-queues, but the semantics are actually completely different, and * every single user we have ever had has been buggy (or pointless). * - * A "swake_up()" only wakes up _one_ waiter, which is not at all what + * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what * "wake_up()" does, and has led to problems. In other cases, it has * been fine, because there's only ever one waiter (kvm), but in that * case gthe whole "simple" wait-queue is just pointless to begin with, @@ -38,8 +38,8 @@ * all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right * sleeper state. * - * - the exclusive mode; because this requires preserving the list order - * and this is hard. + * - the !exclusive mode; because that leads to O(n) wakeups, everything is + * exclusive. * * - custom wake callback functions; because you cannot give any guarantees * about random code. This also allows swait to be used in RT, such that @@ -115,7 +115,7 @@ extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name * CPU0 - waker CPU1 - waiter * * for (;;) { - * @cond = true; prepare_to_swait(&wq_head, &wait, state); + * @cond = true; prepare_to_swait_exclusive(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() * if (swait_active(wq_head)) if (@cond) * wake_up(wq_head); break; @@ -157,20 +157,20 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq) return swait_active(wq); } -extern void swake_up(struct swait_queue_head *q); +extern void swake_up_one(struct swait_queue_head *q); extern void swake_up_all(struct swait_queue_head *q); extern void swake_up_locked(struct swait_queue_head *q); -extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); -extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); +extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state); extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait); extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); -/* as per ___wait_event() but for swait, therefore "exclusive == 0" */ +/* as per ___wait_event() but for swait, therefore "exclusive == 1" */ #define ___swait_event(wq, condition, state, ret, cmd) \ ({ \ + __label__ __out; \ struct swait_queue __wait; \ long __ret = ret; \ \ @@ -183,20 +183,20 @@ extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ - break; \ + goto __out; \ } \ \ cmd; \ } \ finish_swait(&wq, &__wait); \ - __ret; \ +__out: __ret; \ }) #define __swait_event(wq, condition) \ (void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \ schedule()) -#define swait_event(wq, condition) \ +#define swait_event_exclusive(wq, condition) \ do { \ if (condition) \ break; \ @@ -208,7 +208,7 @@ do { \ TASK_UNINTERRUPTIBLE, timeout, \ __ret = schedule_timeout(__ret)) -#define swait_event_timeout(wq, condition, timeout) \ +#define swait_event_timeout_exclusive(wq, condition, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ @@ -220,7 +220,7 @@ do { \ ___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0, \ schedule()) -#define swait_event_interruptible(wq, condition) \ +#define swait_event_interruptible_exclusive(wq, condition) \ ({ \ int __ret = 0; \ if (!(condition)) \ @@ -233,7 +233,7 @@ do { \ TASK_INTERRUPTIBLE, timeout, \ __ret = schedule_timeout(__ret)) -#define swait_event_interruptible_timeout(wq, condition, timeout) \ +#define swait_event_interruptible_timeout_exclusive(wq, condition, timeout)\ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ @@ -246,7 +246,7 @@ do { \ (void)___swait_event(wq, condition, TASK_IDLE, 0, schedule()) /** - * swait_event_idle - wait without system load contribution + * swait_event_idle_exclusive - wait without system load contribution * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @@ -257,7 +257,7 @@ do { \ * condition and doesn't want to contribute to system load. Signals are * ignored. */ -#define swait_event_idle(wq, condition) \ +#define swait_event_idle_exclusive(wq, condition) \ do { \ if (condition) \ break; \ @@ -270,7 +270,7 @@ do { \ __ret = schedule_timeout(__ret)) /** - * swait_event_idle_timeout - wait up to timeout without load contribution + * swait_event_idle_timeout_exclusive - wait up to timeout without load contribution * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout at which we'll give up in jiffies @@ -288,7 +288,7 @@ do { \ * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ -#define swait_event_idle_timeout(wq, condition, timeout) \ +#define swait_event_idle_timeout_exclusive(wq, condition, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a368a68cb667..ebb2f24027e8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -11,6 +11,7 @@ #ifndef _LINUX_SYSCALLS_H #define _LINUX_SYSCALLS_H +struct __aio_sigset; struct epoll_event; struct iattr; struct inode; @@ -505,9 +506,9 @@ asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, /* fs/timerfd.c */ asmlinkage long sys_timerfd_create(int clockid, int flags); asmlinkage long sys_timerfd_settime(int ufd, int flags, - const struct itimerspec __user *utmr, - struct itimerspec __user *otmr); -asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); + const struct __kernel_itimerspec __user *utmr, + struct __kernel_itimerspec __user *otmr); +asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user *otmr); /* fs/utimes.c */ asmlinkage long sys_utimensat(int dfd, const char __user *filename, @@ -572,10 +573,10 @@ asmlinkage long sys_timer_create(clockid_t which_clock, struct sigevent __user *timer_event_spec, timer_t __user * created_timer_id); asmlinkage long sys_timer_gettime(timer_t timer_id, - struct itimerspec __user *setting); + struct __kernel_itimerspec __user *setting); asmlinkage long sys_timer_getoverrun(timer_t timer_id); asmlinkage long sys_timer_settime(timer_t timer_id, int flags, - const struct itimerspec __user *new_setting, + const struct __kernel_itimerspec __user *new_setting, struct itimerspec __user *old_setting); asmlinkage long sys_timer_delete(timer_t timer_id); asmlinkage long sys_clock_settime(clockid_t which_clock, diff --git a/include/linux/time.h b/include/linux/time.h index aed74463592d..27d83fd2ae61 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -14,9 +14,9 @@ int get_timespec64(struct timespec64 *ts, int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts); int get_itimerspec64(struct itimerspec64 *it, - const struct itimerspec __user *uit); + const struct __kernel_itimerspec __user *uit); int put_itimerspec64(const struct itimerspec64 *it, - struct itimerspec __user *uit); + struct __kernel_itimerspec __user *uit); extern time64_t mktime64(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, diff --git a/include/linux/time64.h b/include/linux/time64.h index 0a7b2f79cec7..05634afba0db 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -12,6 +12,7 @@ typedef __u64 timeu64_t; */ #ifndef CONFIG_64BIT_TIME #define __kernel_timespec timespec +#define __kernel_itimerspec itimerspec #endif #include <uapi/linux/time.h> diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 86bc2026efce..edace6b656e9 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,7 +177,7 @@ static inline time64_t ktime_get_clocktai_seconds(void) extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); -extern void timekeeping_inject_sleeptime64(struct timespec64 *delta); +extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /* * struct system_time_snapshot - simultaneous raw/real time capture with diff --git a/include/linux/torture.h b/include/linux/torture.h index 66272862070b..61dfd93b6ee4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -64,6 +64,8 @@ struct torture_random_state { long trs_count; }; #define DEFINE_TORTURE_RANDOM(name) struct torture_random_state name = { 0, 0 } +#define DEFINE_TORTURE_RANDOM_PERCPU(name) \ + DEFINE_PER_CPU(struct torture_random_state, name) unsigned long torture_random(struct torture_random_state *trsp); /* Task shuffler, which causes CPUs to occasionally go idle. */ @@ -79,7 +81,7 @@ void stutter_wait(const char *title); int torture_stutter_init(int s); /* Initialization and cleanup. */ -bool torture_init_begin(char *ttype, bool v); +bool torture_init_begin(char *ttype, int v); void torture_init_end(void); bool torture_cleanup_begin(void); void torture_cleanup_end(void); diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 9324ac2d9ff2..43913ae79f64 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -64,7 +64,8 @@ struct vsock_sock { struct list_head pending_links; struct list_head accept_queue; bool rejected; - struct delayed_work dwork; + struct delayed_work connect_work; + struct delayed_work pending_work; struct delayed_work close_work; bool close_work_scheduled; u32 peer_shutdown; @@ -77,7 +78,6 @@ struct vsock_sock { s64 vsock_stream_has_data(struct vsock_sock *vsk); s64 vsock_stream_has_space(struct vsock_sock *vsk); -void vsock_pending_work(struct work_struct *work); struct sock *__vsock_create(struct net *net, struct socket *sock, struct sock *parent, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5fbfe61f41c6..1beb3ead0385 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5835,10 +5835,11 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, /** * cfg80211_rx_control_port - notification about a received control port frame * @dev: The device the frame matched to - * @buf: control port frame - * @len: length of the frame data - * @addr: The peer from which the frame was received - * @proto: frame protocol, typically PAE or Pre-authentication + * @skb: The skbuf with the control port frame. It is assumed that the skbuf + * is 802.3 formatted (with 802.3 header). The skb can be non-linear. + * This function does not take ownership of the skb, so the caller is + * responsible for any cleanup. The caller must also ensure that + * skb->protocol is set appropriately. * @unencrypted: Whether the frame was received unencrypted * * This function is used to inform userspace about a received control port @@ -5851,8 +5852,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, * Return: %true if the frame was passed to userspace */ bool cfg80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted); + struct sk_buff *skb, bool unencrypted); /** * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 71b9043aa0e7..3d4930528db0 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -281,6 +281,11 @@ static inline void fib6_info_hold(struct fib6_info *f6i) atomic_inc(&f6i->fib6_ref); } +static inline bool fib6_info_hold_safe(struct fib6_info *f6i) +{ + return atomic_inc_not_zero(&f6i->fib6_ref); +} + static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && atomic_dec_and_test(&f6i->fib6_ref)) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 59656fc580df..7b9c82de11cc 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -66,6 +66,12 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } +static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) +{ + return (f6i->fib6_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == + RTF_GATEWAY; +} + void ip6_route_input(struct sk_buff *skb); struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 16475c269749..8f73be494503 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -355,14 +355,7 @@ struct ipv6_txoptions *ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, - struct ipv6_opt_hdr __user *newopt, - int newoptlen); -struct ipv6_txoptions * -ipv6_renew_options_kern(struct sock *sk, - struct ipv6_txoptions *opt, - int newtype, - struct ipv6_opt_hdr *newopt, - int newoptlen); + struct ipv6_opt_hdr *newopt); struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt); @@ -830,7 +823,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, * to minimize possbility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ - rol32(hash, 16); + hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; @@ -1107,6 +1100,8 @@ void ipv6_sysctl_unregister(void); int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); +int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, + const struct in6_addr *addr, unsigned int mode); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); #endif /* _NET_IPV6_H */ diff --git a/include/net/llc.h b/include/net/llc.h index dc35f25eb679..890a87318014 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -116,6 +116,11 @@ static inline void llc_sap_hold(struct llc_sap *sap) refcount_inc(&sap->refcnt); } +static inline bool llc_sap_hold_safe(struct llc_sap *sap) +{ + return refcount_inc_not_zero(&sap->refcnt); +} + void llc_sap_close(struct llc_sap *sap); static inline void llc_sap_put(struct llc_sap *sap) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 08c005ce56e9..dc417ef0a0c5 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -150,6 +150,7 @@ static inline void nft_data_debug(const struct nft_data *data) * @portid: netlink portID of the original message * @seq: netlink sequence number * @family: protocol family + * @level: depth of the chains * @report: notify via unicast netlink message */ struct nft_ctx { @@ -160,6 +161,7 @@ struct nft_ctx { u32 portid; u32 seq; u8 family; + u8 level; bool report; }; @@ -865,7 +867,6 @@ enum nft_chain_flags { * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain - * @level: length of longest path to this chain * @flags: bitmask of enum nft_chain_flags * @name: name of the chain */ @@ -878,7 +879,6 @@ struct nft_chain { struct nft_table *table; u64 handle; u32 use; - u16 level; u8 flags:6, genmask:2; char *name; @@ -1124,7 +1124,6 @@ struct nft_flowtable { u32 genmask:2, use:30; u64 handle; - char *dev_name[NFT_FLOWTABLE_DEVICE_MAX]; /* runtime data below here */ struct nf_hook_ops *ops ____cacheline_aligned; struct nf_flowtable data; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index e0c0c2558ec4..a05134507e7b 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -65,4 +65,10 @@ extern const struct nft_expr_ops nft_payload_fast_ops; extern struct static_key_false nft_counters_enabled; extern struct static_key_false nft_trace_enabled; +extern struct nft_set_type nft_set_rhash_type; +extern struct nft_set_type nft_set_hash_type; +extern struct nft_set_type nft_set_hash_fast_type; +extern struct nft_set_type nft_set_rbtree_type; +extern struct nft_set_type nft_set_bitmap_type; + #endif /* _NET_NF_TABLES_CORE_H */ diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h index 9754a50ecde9..4cc64c8446eb 100644 --- a/include/net/netfilter/nf_tproxy.h +++ b/include/net/netfilter/nf_tproxy.h @@ -64,7 +64,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, * belonging to established connections going through that one. */ struct sock * -nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, +nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, @@ -103,7 +103,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, struct sock *sk); struct sock * -nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, +nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, const u8 protocol, const struct in6_addr *saddr, const struct in6_addr *daddr, const __be16 sport, const __be16 dport, diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h index 9470fd7e4350..32d2454c0479 100644 --- a/include/net/tc_act/tc_csum.h +++ b/include/net/tc_act/tc_csum.h @@ -7,7 +7,6 @@ #include <linux/tc_act/tc_csum.h> struct tcf_csum_params { - int action; u32 update_flags; struct rcu_head rcu; }; diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h index efef0b4b1b2b..46b8c7f1c8d5 100644 --- a/include/net/tc_act/tc_tunnel_key.h +++ b/include/net/tc_act/tc_tunnel_key.h @@ -18,7 +18,6 @@ struct tcf_tunnel_key_params { struct rcu_head rcu; int tcft_action; - int action; struct metadata_dst *tcft_enc_metadata; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index 800582b5dd54..cd3ecda9386a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -342,6 +342,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) { @@ -539,6 +540,7 @@ void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); @@ -828,6 +830,10 @@ struct tcp_skb_cb { #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) +static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) +{ + TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); +} #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, @@ -835,6 +841,11 @@ struct tcp_skb_cb { */ static inline int tcp_v6_iif(const struct sk_buff *skb) { + return TCP_SKB_CB(skb)->header.h6.iif; +} + +static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) +{ bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; @@ -908,8 +919,6 @@ enum tcp_ca_event { CA_EVENT_LOSS, /* loss timeout */ CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */ CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */ - CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */ - CA_EVENT_NON_DELAYED_ACK, }; /* Information about inbound ACK, passed to cong_ops->in_ack_event() */ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 9fe472f2ac95..7161856bcf9c 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -60,6 +60,10 @@ struct xdp_sock { bool zc; /* Protects multiple processes in the control path */ struct mutex mutex; + /* Mutual exclusion of NAPI TX thread and sendmsg error paths + * in the SKB destructor callback. + */ + spinlock_t tx_completion_lock; u64 rx_dropped; }; diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 5936aac357ab..a8d07feff6a0 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -52,6 +52,7 @@ TRACE_EVENT(rcu_utilization, * "cpuqs": CPU passes through a quiescent state. * "cpuonl": CPU comes online. * "cpuofl": CPU goes offline. + * "cpuofl-bgp": CPU goes offline while blocking a grace period. * "reqwait": GP kthread sleeps waiting for grace-period request. * "reqwaitsig": GP kthread awakened by signal from reqwait state. * "fqswait": GP kthread waiting until time to force quiescent states. @@ -63,24 +64,24 @@ TRACE_EVENT(rcu_utilization, */ TRACE_EVENT(rcu_grace_period, - TP_PROTO(const char *rcuname, unsigned long gpnum, const char *gpevent), + TP_PROTO(const char *rcuname, unsigned long gp_seq, const char *gpevent), - TP_ARGS(rcuname, gpnum, gpevent), + TP_ARGS(rcuname, gp_seq, gpevent), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(const char *, gpevent) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->gpevent = gpevent; ), TP_printk("%s %lu %s", - __entry->rcuname, __entry->gpnum, __entry->gpevent) + __entry->rcuname, __entry->gp_seq, __entry->gpevent) ); /* @@ -90,8 +91,8 @@ TRACE_EVENT(rcu_grace_period, * * "Startleaf": Request a grace period based on leaf-node data. * "Prestarted": Someone beat us to the request - * "Startedleaf": Leaf-node start proved sufficient. - * "Startedleafroot": Leaf-node start proved sufficient after checking root. + * "Startedleaf": Leaf node marked for future GP. + * "Startedleafroot": All nodes from leaf to root marked for future GP. * "Startedroot": Requested a nocb grace period based on root-node data. * "NoGPkthread": The RCU grace-period kthread has not yet started. * "StartWait": Start waiting for the requested grace period. @@ -102,17 +103,16 @@ TRACE_EVENT(rcu_grace_period, */ TRACE_EVENT(rcu_future_grace_period, - TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long completed, - unsigned long c, u8 level, int grplo, int grphi, + TP_PROTO(const char *rcuname, unsigned long gp_seq, + unsigned long gp_seq_req, u8 level, int grplo, int grphi, const char *gpevent), - TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent), + TP_ARGS(rcuname, gp_seq, gp_seq_req, level, grplo, grphi, gpevent), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) - __field(unsigned long, completed) - __field(unsigned long, c) + __field(unsigned long, gp_seq) + __field(unsigned long, gp_seq_req) __field(u8, level) __field(int, grplo) __field(int, grphi) @@ -121,19 +121,17 @@ TRACE_EVENT(rcu_future_grace_period, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; - __entry->completed = completed; - __entry->c = c; + __entry->gp_seq = gp_seq; + __entry->gp_seq_req = gp_seq_req; __entry->level = level; __entry->grplo = grplo; __entry->grphi = grphi; __entry->gpevent = gpevent; ), - TP_printk("%s %lu %lu %lu %u %d %d %s", - __entry->rcuname, __entry->gpnum, __entry->completed, - __entry->c, __entry->level, __entry->grplo, __entry->grphi, - __entry->gpevent) + TP_printk("%s %lu %lu %u %d %d %s", + __entry->rcuname, __entry->gp_seq, __entry->gp_seq_req, __entry->level, + __entry->grplo, __entry->grphi, __entry->gpevent) ); /* @@ -145,14 +143,14 @@ TRACE_EVENT(rcu_future_grace_period, */ TRACE_EVENT(rcu_grace_period_init, - TP_PROTO(const char *rcuname, unsigned long gpnum, u8 level, + TP_PROTO(const char *rcuname, unsigned long gp_seq, u8 level, int grplo, int grphi, unsigned long qsmask), - TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask), + TP_ARGS(rcuname, gp_seq, level, grplo, grphi, qsmask), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(u8, level) __field(int, grplo) __field(int, grphi) @@ -161,7 +159,7 @@ TRACE_EVENT(rcu_grace_period_init, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->level = level; __entry->grplo = grplo; __entry->grphi = grphi; @@ -169,7 +167,7 @@ TRACE_EVENT(rcu_grace_period_init, ), TP_printk("%s %lu %u %d %d %lx", - __entry->rcuname, __entry->gpnum, __entry->level, + __entry->rcuname, __entry->gp_seq, __entry->level, __entry->grplo, __entry->grphi, __entry->qsmask) ); @@ -301,24 +299,24 @@ TRACE_EVENT(rcu_nocb_wake, */ TRACE_EVENT(rcu_preempt_task, - TP_PROTO(const char *rcuname, int pid, unsigned long gpnum), + TP_PROTO(const char *rcuname, int pid, unsigned long gp_seq), - TP_ARGS(rcuname, pid, gpnum), + TP_ARGS(rcuname, pid, gp_seq), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(int, pid) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->pid = pid; ), TP_printk("%s %lu %d", - __entry->rcuname, __entry->gpnum, __entry->pid) + __entry->rcuname, __entry->gp_seq, __entry->pid) ); /* @@ -328,23 +326,23 @@ TRACE_EVENT(rcu_preempt_task, */ TRACE_EVENT(rcu_unlock_preempted_task, - TP_PROTO(const char *rcuname, unsigned long gpnum, int pid), + TP_PROTO(const char *rcuname, unsigned long gp_seq, int pid), - TP_ARGS(rcuname, gpnum, pid), + TP_ARGS(rcuname, gp_seq, pid), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(int, pid) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->pid = pid; ), - TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid) + TP_printk("%s %lu %d", __entry->rcuname, __entry->gp_seq, __entry->pid) ); /* @@ -357,15 +355,15 @@ TRACE_EVENT(rcu_unlock_preempted_task, */ TRACE_EVENT(rcu_quiescent_state_report, - TP_PROTO(const char *rcuname, unsigned long gpnum, + TP_PROTO(const char *rcuname, unsigned long gp_seq, unsigned long mask, unsigned long qsmask, u8 level, int grplo, int grphi, int gp_tasks), - TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks), + TP_ARGS(rcuname, gp_seq, mask, qsmask, level, grplo, grphi, gp_tasks), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(unsigned long, mask) __field(unsigned long, qsmask) __field(u8, level) @@ -376,7 +374,7 @@ TRACE_EVENT(rcu_quiescent_state_report, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->mask = mask; __entry->qsmask = qsmask; __entry->level = level; @@ -386,41 +384,41 @@ TRACE_EVENT(rcu_quiescent_state_report, ), TP_printk("%s %lu %lx>%lx %u %d %d %u", - __entry->rcuname, __entry->gpnum, + __entry->rcuname, __entry->gp_seq, __entry->mask, __entry->qsmask, __entry->level, __entry->grplo, __entry->grphi, __entry->gp_tasks) ); /* * Tracepoint for quiescent states detected by force_quiescent_state(). - * These trace events include the type of RCU, the grace-period number that - * was blocked by the CPU, the CPU itself, and the type of quiescent state, - * which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, "kick" - * when kicking a CPU that has been in dyntick-idle mode for too long, or - * "rqc" if the CPU got a quiescent state via its rcu_qs_ctr. + * These trace events include the type of RCU, the grace-period number + * that was blocked by the CPU, the CPU itself, and the type of quiescent + * state, which can be "dti" for dyntick-idle mode, "kick" when kicking + * a CPU that has been in dyntick-idle mode for too long, or "rqc" if the + * CPU got a quiescent state via its rcu_qs_ctr. */ TRACE_EVENT(rcu_fqs, - TP_PROTO(const char *rcuname, unsigned long gpnum, int cpu, const char *qsevent), + TP_PROTO(const char *rcuname, unsigned long gp_seq, int cpu, const char *qsevent), - TP_ARGS(rcuname, gpnum, cpu, qsevent), + TP_ARGS(rcuname, gp_seq, cpu, qsevent), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(int, cpu) __field(const char *, qsevent) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->cpu = cpu; __entry->qsevent = qsevent; ), TP_printk("%s %lu %d %s", - __entry->rcuname, __entry->gpnum, + __entry->rcuname, __entry->gp_seq, __entry->cpu, __entry->qsevent) ); @@ -753,23 +751,23 @@ TRACE_EVENT(rcu_barrier, #else /* #ifdef CONFIG_RCU_TRACE */ -#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0) -#define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \ +#define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0) +#define trace_rcu_future_grace_period(rcuname, gp_seq, gp_seq_req, \ level, grplo, grphi, event) \ do { } while (0) -#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \ +#define trace_rcu_grace_period_init(rcuname, gp_seq, level, grplo, grphi, \ qsmask) do { } while (0) #define trace_rcu_exp_grace_period(rcuname, gqseq, gpevent) \ do { } while (0) #define trace_rcu_exp_funnel_lock(rcuname, level, grplo, grphi, gpevent) \ do { } while (0) #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0) -#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0) -#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0) -#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \ +#define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0) +#define trace_rcu_unlock_preempted_task(rcuname, gp_seq, pid) do { } while (0) +#define trace_rcu_quiescent_state_report(rcuname, gp_seq, mask, qsmask, level, \ grplo, grphi, gp_tasks) do { } \ while (0) -#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0) +#define trace_rcu_fqs(rcuname, gp_seq, cpu, qsevent) do { } while (0) #define trace_rcu_dyntick(polarity, oldnesting, newnesting, dyntick) do { } while (0) #define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0) #define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \ diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h index 3c5038b587ba..d4593a6062ef 100644 --- a/include/uapi/linux/aio_abi.h +++ b/include/uapi/linux/aio_abi.h @@ -29,7 +29,6 @@ #include <linux/types.h> #include <linux/fs.h> -#include <linux/signal.h> #include <asm/byteorder.h> typedef __kernel_ulong_t aio_context_t; @@ -110,10 +109,5 @@ struct iocb { #undef IFBIG #undef IFLITTLE -struct __aio_sigset { - const sigset_t __user *sigmask; - size_t sigsetsize; -}; - #endif /* __LINUX__AIO_ABI_H */ diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 0b5ddbe135a4..972265f32871 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -76,7 +76,7 @@ struct btf_type { */ #define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) #define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) -#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) /* Attributes stored in the BTF_INT_ENCODING */ #define BTF_INT_SIGNED (1 << 0) diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 4ca65b56084f..7363f18e65a5 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -226,7 +226,7 @@ enum tunable_id { ETHTOOL_TX_COPYBREAK, ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ /* - * Add your fresh new tubale attribute above and remember to update + * Add your fresh new tunable attribute above and remember to update * tunable_strings[] in net/core/ethtool.c */ __ETHTOOL_TUNABLE_COUNT, diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b8e288a1f740..eeb787b1c53c 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -143,6 +143,8 @@ enum perf_event_sample_format { PERF_SAMPLE_PHYS_ADDR = 1U << 19, PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ + + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, }; /* diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 29eb659aa77a..e3f6ed8a7064 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -127,6 +127,10 @@ enum { #define TCP_CM_INQ TCP_INQ +#define TCP_REPAIR_ON 1 +#define TCP_REPAIR_OFF 0 +#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ + struct tcp_repair_opt { __u32 opt_code; __u32 opt_val; diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index fcf936656493..6b56a2208be7 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -49,6 +49,13 @@ struct __kernel_timespec { }; #endif +#ifndef __kernel_itimerspec +struct __kernel_itimerspec { + struct __kernel_timespec it_interval; /* timer period */ + struct __kernel_timespec it_value; /* timer expiration */ +}; +#endif + /* * legacy timeval structure, only embedded in structures that * traditionally used 'timeval' to pass time intervals (not absolute diff --git a/init/main.c b/init/main.c index 3b4ada11ed52..5e13c544bbf4 100644 --- a/init/main.c +++ b/init/main.c @@ -561,8 +561,8 @@ asmlinkage __visible void __init start_kernel(void) setup_command_line(command_line); setup_nr_cpu_ids(); setup_per_cpu_areas(); - boot_cpu_state_init(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ + boot_cpu_hotplug_init(); build_all_zonelists(NULL); page_alloc_init(); diff --git a/ipc/sem.c b/ipc/sem.c index 5af1943ad782..76e95e4f3aa2 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2118,7 +2118,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, } do { - queue.status = -EINTR; + WRITE_ONCE(queue.status, -EINTR); queue.sleeper = current; __set_current_state(TASK_INTERRUPTIBLE); diff --git a/ipc/shm.c b/ipc/shm.c index 051a3e1fb8df..fefa00d310fb 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -427,6 +427,17 @@ static int shm_split(struct vm_area_struct *vma, unsigned long addr) return 0; } +static unsigned long shm_pagesize(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + + if (sfd->vm_ops->pagesize) + return sfd->vm_ops->pagesize(vma); + + return PAGE_SIZE; +} + #ifdef CONFIG_NUMA static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new) { @@ -554,6 +565,7 @@ static const struct vm_operations_struct shm_vm_ops = { .close = shm_close, /* callback for when the vm-area is released */ .fault = shm_fault, .split = shm_split, + .pagesize = shm_pagesize, #if defined(CONFIG_NUMA) .set_policy = shm_set_policy, .get_policy = shm_get_policy, diff --git a/kernel/auditsc.c b/kernel/auditsc.c index ceb1c4596c51..80d672a11088 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1279,8 +1279,12 @@ static void show_special(struct audit_context *context, int *call_panic) break; case AUDIT_KERN_MODULE: audit_log_format(ab, "name="); - audit_log_untrustedstring(ab, context->module.name); - kfree(context->module.name); + if (context->module.name) { + audit_log_untrustedstring(ab, context->module.name); + kfree(context->module.name); + } else + audit_log_format(ab, "(null)"); + break; } audit_log_end(ab); @@ -2411,8 +2415,9 @@ void __audit_log_kern_module(char *name) { struct audit_context *context = audit_context(); - context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL); - strcpy(context->module.name, name); + context->module.name = kstrdup(name, GFP_KERNEL); + if (!context->module.name) + audit_log_lost("out of memory in __audit_log_kern_module"); context->type = AUDIT_KERN_MODULE; } diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 544e58f5f642..2aa55d030c77 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -378,7 +378,7 @@ static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf, return -EINVAL; value_type = btf_type_id_size(btf, &btf_value_id, &value_size); - if (!value_type || value_size > map->value_size) + if (!value_type || value_size != map->value_size) return -EINVAL; return 0; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2d49d18b793a..2590700237c1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) */ static bool btf_type_int_is_regular(const struct btf_type *t) { - u16 nr_bits, nr_bytes; + u8 nr_bits, nr_bytes; u32 int_data; int_data = btf_type_int(t); @@ -991,38 +991,38 @@ static void btf_int_bits_seq_show(const struct btf *btf, void *data, u8 bits_offset, struct seq_file *m) { + u16 left_shift_bits, right_shift_bits; u32 int_data = btf_type_int(t); - u16 nr_bits = BTF_INT_BITS(int_data); - u16 total_bits_offset; - u16 nr_copy_bytes; - u16 nr_copy_bits; - u8 nr_upper_bits; - union { - u64 u64_num; - u8 u8_nums[8]; - } print_num; + u8 nr_bits = BTF_INT_BITS(int_data); + u8 total_bits_offset; + u8 nr_copy_bytes; + u8 nr_copy_bits; + u64 print_num; + /* + * bits_offset is at most 7. + * BTF_INT_OFFSET() cannot exceed 64 bits. + */ total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); data += BITS_ROUNDDOWN_BYTES(total_bits_offset); bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); nr_copy_bits = nr_bits + bits_offset; nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits); - print_num.u64_num = 0; - memcpy(&print_num.u64_num, data, nr_copy_bytes); - - /* Ditch the higher order bits */ - nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits); - if (nr_upper_bits) { - /* We need to mask out some bits of the upper byte. */ - u8 mask = (1 << nr_upper_bits) - 1; + print_num = 0; + memcpy(&print_num, data, nr_copy_bytes); - print_num.u8_nums[nr_copy_bytes - 1] &= mask; - } +#ifdef __BIG_ENDIAN_BITFIELD + left_shift_bits = bits_offset; +#else + left_shift_bits = BITS_PER_U64 - nr_copy_bits; +#endif + right_shift_bits = BITS_PER_U64 - nr_bits; - print_num.u64_num >>= bits_offset; + print_num <<= left_shift_bits; + print_num >>= right_shift_bits; - seq_printf(m, "0x%llx", print_num.u64_num); + seq_printf(m, "0x%llx", print_num); } static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, @@ -1032,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, u32 int_data = btf_type_int(t); u8 encoding = BTF_INT_ENCODING(int_data); bool sign = encoding & BTF_INT_SIGNED; - u32 nr_bits = BTF_INT_BITS(int_data); + u8 nr_bits = BTF_INT_BITS(int_data); if (bits_offset || BTF_INT_OFFSET(int_data) || BITS_PER_BYTE_MASKED(nr_bits)) { @@ -1519,9 +1519,9 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, { bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION; const struct btf_member *member; + u32 meta_needed, last_offset; struct btf *btf = env->btf; u32 struct_size = t->size; - u32 meta_needed; u16 i; meta_needed = btf_type_vlen(t) * sizeof(*member); @@ -1534,6 +1534,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, btf_verifier_log_type(env, t, NULL); + last_offset = 0; for_each_member(i, t, member) { if (!btf_name_offset_valid(btf, member->name_off)) { btf_verifier_log_member(env, t, member, @@ -1555,6 +1556,16 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* + * ">" instead of ">=" because the last member could be + * "char a[0];" + */ + if (last_offset > member->offset) { + btf_verifier_log_member(env, t, member, + "Invalid member bits_offset"); + return -EINVAL; + } + if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) { btf_verifier_log_member(env, t, member, "Memmber bits_offset exceeds its struct size"); @@ -1562,6 +1573,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, } btf_verifier_log_member(env, t, member, NULL); + last_offset = member->offset; } return meta_needed; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index e0918d180f08..46f5f29605d4 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -69,7 +69,7 @@ struct bpf_cpu_map { }; static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, - struct xdp_bulk_queue *bq); + struct xdp_bulk_queue *bq, bool in_napi_ctx); static u64 cpu_map_bitmap_size(const union bpf_attr *attr) { @@ -375,7 +375,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu) struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); /* No concurrent bq_enqueue can run at this point */ - bq_flush_to_queue(rcpu, bq); + bq_flush_to_queue(rcpu, bq, false); } free_percpu(rcpu->bulkq); /* Cannot kthread_stop() here, last put free rcpu resources */ @@ -558,7 +558,7 @@ const struct bpf_map_ops cpu_map_ops = { }; static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, - struct xdp_bulk_queue *bq) + struct xdp_bulk_queue *bq, bool in_napi_ctx) { unsigned int processed = 0, drops = 0; const int to_cpu = rcpu->cpu; @@ -578,7 +578,10 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, err = __ptr_ring_produce(q, xdpf); if (err) { drops++; - xdp_return_frame_rx_napi(xdpf); + if (likely(in_napi_ctx)) + xdp_return_frame_rx_napi(xdpf); + else + xdp_return_frame(xdpf); } processed++; } @@ -598,7 +601,7 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) - bq_flush_to_queue(rcpu, bq); + bq_flush_to_queue(rcpu, bq, true); /* Notice, xdp_buff/page MUST be queued here, long enough for * driver to code invoking us to finished, due to driver @@ -661,7 +664,7 @@ void __cpu_map_flush(struct bpf_map *map) /* Flush all frames in bulkq to real queue */ bq = this_cpu_ptr(rcpu->bulkq); - bq_flush_to_queue(rcpu, bq); + bq_flush_to_queue(rcpu, bq, true); /* If already running, costs spin_lock_irqsave + smb_mb */ wake_up_process(rcpu->kthread); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 642c97f6d1b8..750d45edae79 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -217,7 +217,8 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) } static int bq_xmit_all(struct bpf_dtab_netdev *obj, - struct xdp_bulk_queue *bq, u32 flags) + struct xdp_bulk_queue *bq, u32 flags, + bool in_napi_ctx) { struct net_device *dev = obj->dev; int sent = 0, drops = 0, err = 0; @@ -254,7 +255,10 @@ error: struct xdp_frame *xdpf = bq->q[i]; /* RX path under NAPI protection, can return frames faster */ - xdp_return_frame_rx_napi(xdpf); + if (likely(in_napi_ctx)) + xdp_return_frame_rx_napi(xdpf); + else + xdp_return_frame(xdpf); drops++; } goto out; @@ -286,7 +290,7 @@ void __dev_map_flush(struct bpf_map *map) __clear_bit(bit, bitmap); bq = this_cpu_ptr(dev->bulkq); - bq_xmit_all(dev, bq, XDP_XMIT_FLUSH); + bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true); } } @@ -316,7 +320,7 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) - bq_xmit_all(obj, bq, 0); + bq_xmit_all(obj, bq, 0, true); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed @@ -334,10 +338,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, { struct net_device *dev = dst->dev; struct xdp_frame *xdpf; + int err; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(err)) + return err; + xdpf = convert_to_xdp_frame(xdp); if (unlikely(!xdpf)) return -EOVERFLOW; @@ -350,7 +359,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, { int err; - err = __xdp_generic_ok_fwd_dev(skb, dst->dev); + err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; skb->dev = dst->dev; @@ -380,7 +389,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev) __clear_bit(dev->bit, bitmap); bq = per_cpu_ptr(dev->bulkq, cpu); - bq_xmit_all(dev, bq, XDP_XMIT_FLUSH); + bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false); } } } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3ca2198a6d22..513d9dfcf4ee 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -747,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, * old element will be freed immediately. * Otherwise return an error */ - atomic_dec(&htab->count); - return ERR_PTR(-E2BIG); + l_new = ERR_PTR(-E2BIG); + goto dec_count; } l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); - if (!l_new) - return ERR_PTR(-ENOMEM); + if (!l_new) { + l_new = ERR_PTR(-ENOMEM); + goto dec_count; + } } memcpy(l_new->key, key, key_size); @@ -766,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, GFP_ATOMIC | __GFP_NOWARN); if (!pptr) { kfree(l_new); - return ERR_PTR(-ENOMEM); + l_new = ERR_PTR(-ENOMEM); + goto dec_count; } } @@ -780,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new->hash = hash; return l_new; +dec_count: + atomic_dec(&htab->count); + return l_new; } static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index cf7b6a6dbd1f..c4d75c52b4fc 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -312,10 +312,12 @@ static void bpf_tcp_close(struct sock *sk, long timeout) struct smap_psock *psock; struct sock *osk; + lock_sock(sk); rcu_read_lock(); psock = smap_psock_sk(sk); if (unlikely(!psock)) { rcu_read_unlock(); + release_sock(sk); return sk->sk_prot->close(sk, timeout); } @@ -371,6 +373,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout) e = psock_map_pop(sk, psock); } rcu_read_unlock(); + release_sock(sk); close_fun(sk, timeout); } @@ -568,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) while (sg[i].length) { free += sg[i].length; sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); + if (!md->skb) + put_page(sg_page(&sg[i])); sg[i].length = 0; sg[i].page_link = 0; sg[i].offset = 0; @@ -577,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) if (i == MAX_SKB_FRAGS) i = 0; } + if (md->skb) + consume_skb(md->skb); return free; } @@ -1042,12 +1048,12 @@ static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); while (msg_data_left(msg)) { - struct sk_msg_buff *m; + struct sk_msg_buff *m = NULL; bool enospc = false; int copy; if (sk->sk_err) { - err = sk->sk_err; + err = -sk->sk_err; goto out_err; } @@ -1110,8 +1116,11 @@ wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: err = sk_stream_wait_memory(sk, &timeo); - if (err) + if (err) { + if (m && m != psock->cork) + free_start_sg(sk, m); goto out_err; + } } out_err: if (err < 0) @@ -1230,7 +1239,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) */ TCP_SKB_CB(skb)->bpf.sk_redir = NULL; skb->sk = psock->sock; - bpf_compute_data_pointers(skb); + bpf_compute_data_end_sk_skb(skb); preempt_disable(); rc = (*prog->bpf_func)(skb, prog->insnsi); preempt_enable(); @@ -1485,7 +1494,7 @@ static int smap_parse_func_strparser(struct strparser *strp, * any socket yet. */ skb->sk = psock->sock; - bpf_compute_data_pointers(skb); + bpf_compute_data_end_sk_skb(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; rcu_read_unlock(); @@ -1896,7 +1905,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); if (!e) { err = -ENOMEM; - goto out_progs; + goto out_free; } } @@ -2069,7 +2078,13 @@ static int sock_map_update_elem(struct bpf_map *map, return -EOPNOTSUPP; } + lock_sock(skops.sk); + preempt_disable(); + rcu_read_lock(); err = sock_map_ctx_update_elem(&skops, map, key, flags); + rcu_read_unlock(); + preempt_enable(); + release_sock(skops.sk); fput(socket->file); return err; } @@ -2342,7 +2357,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, if (err) goto err; - /* bpf_map_update_elem() can be called in_irq() */ + /* psock is valid here because otherwise above *ctx_update_elem would + * have thrown an error. It is safe to skip error check. + */ + psock = smap_psock_sk(sock); raw_spin_lock_bh(&b->lock); l_old = lookup_elem_raw(head, hash, key, key_size); if (l_old && map_flags == BPF_NOEXIST) { @@ -2360,12 +2378,6 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, goto bucket_err; } - psock = smap_psock_sk(sock); - if (unlikely(!psock)) { - err = -EINVAL; - goto bucket_err; - } - rcu_assign_pointer(e->hash_link, l_new); rcu_assign_pointer(e->htab, container_of(map, struct bpf_htab, map)); @@ -2388,12 +2400,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, raw_spin_unlock_bh(&b->lock); return 0; bucket_err: + smap_release_sock(psock, sock); raw_spin_unlock_bh(&b->lock); err: kfree(e); - psock = smap_psock_sk(sock); - if (psock) - smap_release_sock(psock, sock); return err; } @@ -2415,7 +2425,13 @@ static int sock_hash_update_elem(struct bpf_map *map, return -EINVAL; } + lock_sock(skops.sk); + preempt_disable(); + rcu_read_lock(); err = sock_hash_ctx_update_elem(&skops, map, key, flags); + rcu_read_unlock(); + preempt_enable(); + release_sock(skops.sk); fput(socket->file); return err; } @@ -2472,10 +2488,8 @@ struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - raw_spin_lock_bh(&b->lock); l = lookup_elem_raw(head, hash, key, key_size); sk = l ? l->sk : NULL; - raw_spin_unlock_bh(&b->lock); return sk; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d10ecd78105f..b41c6cf2eb88 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -575,7 +575,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, { int refold; - refold = __atomic_add_unless(&map->refcnt, 1, 0); + refold = atomic_fetch_add_unless(&map->refcnt, 1, 0); if (refold >= BPF_MAX_REFCNT) { __bpf_map_put(map, false); @@ -735,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_update_elem(map, key, value, attr->flags); goto out; - } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_SOCKHASH || + map->map_type == BPF_MAP_TYPE_SOCKMAP) { err = map->ops->map_update_elem(map, key, value, attr->flags); goto out; } @@ -1142,7 +1144,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; - refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0); + refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (refold >= BPF_MAX_REFCNT) { __bpf_prog_put(prog, false); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e2bf834f13a..63aaac52a265 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5430,6 +5430,10 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; + /* Upon error here we cannot fall back to interpreter but + * need a hard reject of the program. Thus -EFAULT is + * propagated in any case. + */ subprog = find_subprog(env, i + insn->imm + 1); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", @@ -5450,7 +5454,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL); if (!func) - return -ENOMEM; + goto out_undo_insn; for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; @@ -5515,7 +5519,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); - err = -EFAULT; + err = -ENOTSUPP; goto out_free; } cond_resched(); @@ -5552,6 +5556,7 @@ out_free: if (func[i]) bpf_jit_free(func[i]); kfree(func); +out_undo_insn: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { @@ -5578,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env) err = jit_subprogs(env); if (err == 0) return 0; + if (err == -EFAULT) + return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON for (i = 0; i < prog->len; i++, insn++) { diff --git a/kernel/compat.c b/kernel/compat.c index 702aa846ddac..8e40efc2928a 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -324,35 +324,6 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, return ret; } -/* Todo: Delete these extern declarations when get/put_compat_itimerspec64() - * are moved to kernel/time/time.c . - */ -extern int __compat_get_timespec64(struct timespec64 *ts64, - const struct compat_timespec __user *cts); -extern int __compat_put_timespec64(const struct timespec64 *ts64, - struct compat_timespec __user *cts); - -int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits) -{ - - if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || - __compat_get_timespec64(&its->it_value, &uits->it_value)) - return -EFAULT; - return 0; -} -EXPORT_SYMBOL_GPL(get_compat_itimerspec64); - -int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits) -{ - if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || - __compat_put_timespec64(&its->it_value, &uits->it_value)) - return -EFAULT; - return 0; -} -EXPORT_SYMBOL_GPL(put_compat_itimerspec64); - /* * We currently only need the following fields from the sigevent * structure: sigev_value, sigev_signo, sig_notify and (sometimes diff --git a/kernel/cpu.c b/kernel/cpu.c index 0db8938fbb23..dd8634dde1ae 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1274,7 +1274,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { - .name = "timers:dead", + .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, @@ -1344,6 +1344,11 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, + [CPUHP_AP_WATCHDOG_ONLINE] = { + .name = "lockup_detector:online", + .startup.single = lockup_detector_online_cpu, + .teardown.single = lockup_detector_offline_cpu, + }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = workqueue_online_cpu, @@ -2010,7 +2015,7 @@ void __init boot_cpu_init(void) /* * Must be called _AFTER_ setting up the per_cpu areas */ -void __init boot_cpu_state_init(void) +void __init boot_cpu_hotplug_init(void) { per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 8f0434a9951a..f6ea33a9f904 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1656,7 +1656,7 @@ perf_event_groups_next(struct perf_event *event) typeof(*event), group_node)) /* - * Add a event from the lists for its context. + * Add an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ static void @@ -1844,7 +1844,7 @@ static void perf_group_attach(struct perf_event *event) } /* - * Remove a event from the lists for its context. + * Remove an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ static void @@ -2148,7 +2148,7 @@ static void __perf_event_disable(struct perf_event *event, } /* - * Disable a event. + * Disable an event. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to @@ -2677,7 +2677,7 @@ static void __perf_event_enable(struct perf_event *event, } /* - * Enable a event. + * Enable an event. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to @@ -2755,7 +2755,7 @@ static int __perf_event_stop(void *info) * events will refuse to restart because of rb::aux_mmap_count==0, * see comments in perf_aux_output_begin(). * - * Since this is happening on a event-local CPU, no trace is lost + * Since this is happening on an event-local CPU, no trace is lost * while restarting. */ if (sd->restart) @@ -4827,7 +4827,7 @@ __perf_read(struct perf_event *event, char __user *buf, size_t count) int ret; /* - * Return end-of-file for a read on a event that is in + * Return end-of-file for a read on an event that is in * error state (i.e. because it was pinned but it couldn't be * scheduled on to the CPU at some point). */ @@ -5273,11 +5273,11 @@ unlock: } EXPORT_SYMBOL_GPL(perf_event_update_userpage); -static int perf_mmap_fault(struct vm_fault *vmf) +static vm_fault_t perf_mmap_fault(struct vm_fault *vmf) { struct perf_event *event = vmf->vma->vm_file->private_data; struct ring_buffer *rb; - int ret = VM_FAULT_SIGBUS; + vm_fault_t ret = VM_FAULT_SIGBUS; if (vmf->flags & FAULT_FLAG_MKWRITE) { if (vmf->pgoff == 0) @@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt) static struct perf_callchain_entry __empty_callchain = { .nr = 0, }; -static struct perf_callchain_entry * +struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs) { bool kernel = !event->attr.exclude_callchain_kernel; @@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header, if (sample_type & PERF_SAMPLE_CALLCHAIN) { int size = 1; - data->callchain = perf_callchain(event, regs); + if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY)) + data->callchain = perf_callchain(event, regs); + size += data->callchain->nr; header->size += size * sizeof(u64); @@ -7335,6 +7337,10 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter, struct file *file, unsigned long offset, unsigned long size) { + /* d_inode(NULL) won't be equal to any mapped user-space file */ + if (!filter->path.dentry) + return false; + if (d_inode(filter->path.dentry) != file_inode(file)) return false; @@ -9898,7 +9904,7 @@ enabled: } /* - * Allocate and initialize a event structure + * Allocate and initialize an event structure */ static struct perf_event * perf_event_alloc(struct perf_event_attr *attr, int cpu, @@ -11229,7 +11235,7 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event) } /* - * Inherit a event from parent task to child task. + * Inherit an event from parent task to child task. * * Returns: * - valid pointer on success diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index 6e28d2866be5..b3814fce5ecb 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -345,13 +345,13 @@ void release_bp_slot(struct perf_event *bp) mutex_unlock(&nr_bp_mutex); } -static int __modify_bp_slot(struct perf_event *bp, u64 old_type) +static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type) { int err; __release_bp_slot(bp, old_type); - err = __reserve_bp_slot(bp, bp->attr.bp_type); + err = __reserve_bp_slot(bp, new_type); if (err) { /* * Reserve the old_type slot back in case @@ -367,12 +367,12 @@ static int __modify_bp_slot(struct perf_event *bp, u64 old_type) return err; } -static int modify_bp_slot(struct perf_event *bp, u64 old_type) +static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type) { int ret; mutex_lock(&nr_bp_mutex); - ret = __modify_bp_slot(bp, old_type); + ret = __modify_bp_slot(bp, old_type, new_type); mutex_unlock(&nr_bp_mutex); return ret; } @@ -400,16 +400,18 @@ int dbg_release_bp_slot(struct perf_event *bp) return 0; } -static int validate_hw_breakpoint(struct perf_event *bp) +static int hw_breakpoint_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - int ret; + int err; - ret = arch_validate_hwbkpt_settings(bp); - if (ret) - return ret; + err = hw_breakpoint_arch_parse(bp, attr, hw); + if (err) + return err; - if (arch_check_bp_in_kernelspace(bp)) { - if (bp->attr.exclude_kernel) + if (arch_check_bp_in_kernelspace(hw)) { + if (attr->exclude_kernel) return -EINVAL; /* * Don't let unprivileged users set a breakpoint in the trap @@ -424,19 +426,22 @@ static int validate_hw_breakpoint(struct perf_event *bp) int register_perf_hw_breakpoint(struct perf_event *bp) { - int ret; - - ret = reserve_bp_slot(bp); - if (ret) - return ret; + struct arch_hw_breakpoint hw; + int err; - ret = validate_hw_breakpoint(bp); + err = reserve_bp_slot(bp); + if (err) + return err; - /* if arch_validate_hwbkpt_settings() fails then release bp slot */ - if (ret) + err = hw_breakpoint_parse(bp, &bp->attr, &hw); + if (err) { release_bp_slot(bp); + return err; + } - return ret; + bp->hw.info = hw; + + return 0; } /** @@ -456,35 +461,44 @@ register_user_hw_breakpoint(struct perf_event_attr *attr, } EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); +static void hw_breakpoint_copy_attr(struct perf_event_attr *to, + struct perf_event_attr *from) +{ + to->bp_addr = from->bp_addr; + to->bp_type = from->bp_type; + to->bp_len = from->bp_len; + to->disabled = from->disabled; +} + int modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr, bool check) { - u64 old_addr = bp->attr.bp_addr; - u64 old_len = bp->attr.bp_len; - int old_type = bp->attr.bp_type; - bool modify = attr->bp_type != old_type; - int err = 0; + struct arch_hw_breakpoint hw; + int err; - bp->attr.bp_addr = attr->bp_addr; - bp->attr.bp_type = attr->bp_type; - bp->attr.bp_len = attr->bp_len; + err = hw_breakpoint_parse(bp, attr, &hw); + if (err) + return err; - if (check && memcmp(&bp->attr, attr, sizeof(*attr))) - return -EINVAL; + if (check) { + struct perf_event_attr old_attr; - err = validate_hw_breakpoint(bp); - if (!err && modify) - err = modify_bp_slot(bp, old_type); + old_attr = bp->attr; + hw_breakpoint_copy_attr(&old_attr, attr); + if (memcmp(&old_attr, attr, sizeof(*attr))) + return -EINVAL; + } - if (err) { - bp->attr.bp_addr = old_addr; - bp->attr.bp_type = old_type; - bp->attr.bp_len = old_len; - return err; + if (bp->attr.bp_type != attr->bp_type) { + err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type); + if (err) + return err; } - bp->attr.disabled = attr->disabled; + hw_breakpoint_copy_attr(&bp->attr, attr); + bp->hw.info = hw; + return 0; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index ccc579a7d32e..aed1ba569954 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -918,7 +918,7 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * EXPORT_SYMBOL_GPL(uprobe_register); /* - * uprobe_apply - unregister a already registered probe. + * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: consumer which wants to add more or remove some breakpoints @@ -947,7 +947,7 @@ int uprobe_apply(struct inode *inode, loff_t offset, } /* - * uprobe_unregister - unregister a already registered probe. + * uprobe_unregister - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: identify which probe if multiple probes are colocated. @@ -1403,7 +1403,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri) /* * Called with no locks held. - * Called in context of a exiting or a exec-ing thread. + * Called in context of an exiting or an exec-ing thread. */ void uprobe_free_utask(struct task_struct *t) { diff --git a/kernel/fail_function.c b/kernel/fail_function.c index 5349c91c2298..bc80a4e268c0 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -184,9 +184,6 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs) if (should_fail(&fei_fault_attr, 1)) { regs_set_return_value(regs, attr->retval); override_function_with_return(regs); - /* Kprobe specific fixup */ - reset_current_kprobe(); - preempt_enable_no_resched(); return 1; } diff --git a/kernel/fork.c b/kernel/fork.c index 5b64c1b8461e..9d8d0e016fc6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -303,11 +303,36 @@ struct kmem_cache *files_cachep; struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ -struct kmem_cache *vm_area_cachep; +static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; +struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) +{ + struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + + if (vma) + vma_init(vma, mm); + return vma; +} + +struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) +{ + struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + + if (new) { + *new = *orig; + INIT_LIST_HEAD(&new->anon_vma_chain); + } + return new; +} + +void vm_area_free(struct vm_area_struct *vma) +{ + kmem_cache_free(vm_area_cachep, vma); +} + static void account_kernel_stack(struct task_struct *tsk, int account) { void *stack = task_stack_page(tsk); @@ -455,11 +480,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto fail_nomem; charge = len; } - tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; - *tmp = *mpnt; - INIT_LIST_HEAD(&tmp->anon_vma_chain); retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; @@ -539,7 +562,7 @@ fail_uprobe_end: fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: - kmem_cache_free(vm_area_cachep, tmp); + vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index c6766f326072..5f3e2baefca9 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -134,7 +134,6 @@ config GENERIC_IRQ_DEBUGFS endmenu config GENERIC_IRQ_MULTI_HANDLER - depends on !MULTI_IRQ_HANDLER bool help Allow to specify the low level IRQ handler at run time. diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index afc7f902d74a..578d0e5f1b5b 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -443,6 +443,7 @@ static void free_desc(unsigned int irq) * We free the descriptor, masks and stat fields via RCU. That * allows demultiplex interrupts to do rcu based management of * the child interrupts. + * This also allows us to use rcu in kstat_irqs_usr(). */ call_rcu(&desc->rcu, delayed_free_desc); } @@ -928,17 +929,17 @@ unsigned int kstat_irqs(unsigned int irq) * kstat_irqs_usr - Get the statistics for an interrupt * @irq: The interrupt number * - * Returns the sum of interrupt counts on all cpus since boot for - * @irq. Contrary to kstat_irqs() this can be called from any - * preemptible context. It's protected against concurrent removal of - * an interrupt descriptor when sparse irqs are enabled. + * Returns the sum of interrupt counts on all cpus since boot for @irq. + * Contrary to kstat_irqs() this can be called from any context. + * It uses rcu since a concurrent removal of an interrupt descriptor is + * observing an rcu grace period before delayed_free_desc()/irq_kobj_release(). */ unsigned int kstat_irqs_usr(unsigned int irq) { unsigned int sum; - irq_lock_sparse(); + rcu_read_lock(); sum = kstat_irqs(irq); - irq_unlock_sparse(); + rcu_read_unlock(); return sum; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index daeabd791d58..fb86146037a7 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -790,9 +790,19 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id) static int irq_wait_for_interrupt(struct irqaction *action) { - set_current_state(TASK_INTERRUPTIBLE); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { + if (kthread_should_stop()) { + /* may need to run one last time */ + if (test_and_clear_bit(IRQTF_RUNTHREAD, + &action->thread_flags)) { + __set_current_state(TASK_RUNNING); + return 0; + } + __set_current_state(TASK_RUNNING); + return -1; + } if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) { @@ -800,10 +810,7 @@ static int irq_wait_for_interrupt(struct irqaction *action) return 0; } schedule(); - set_current_state(TASK_INTERRUPTIBLE); } - __set_current_state(TASK_RUNNING); - return -1; } /* @@ -1024,11 +1031,8 @@ static int irq_thread(void *data) /* * This is the regular exit path. __free_irq() is stopping the * thread via kthread_stop() after calling - * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the - * oneshot mask bit can be set. We cannot verify that as we - * cannot touch the oneshot mask at this point anymore as - * __setup_irq() might have given out currents thread_mask - * again. + * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the + * oneshot mask bit can be set. */ task_work_cancel(current, irq_thread_dtor); return 0; @@ -1068,6 +1072,13 @@ static int irq_setup_forced_threading(struct irqaction *new) if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) return 0; + /* + * No further action required for interrupts which are requested as + * threaded interrupts already + */ + if (new->handler == irq_default_primary_handler) + return 0; + new->flags |= IRQF_ONESHOT; /* @@ -1075,7 +1086,7 @@ static int irq_setup_forced_threading(struct irqaction *new) * thread handler. We force thread them as well by creating a * secondary action. */ - if (new->handler != irq_default_primary_handler && new->thread_fn) { + if (new->handler && new->thread_fn) { /* Allocate the secondary action */ new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!new->secondary) @@ -1244,8 +1255,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) /* * Protects against a concurrent __free_irq() call which might wait - * for synchronize_irq() to complete without holding the optional - * chip bus lock and desc->lock. + * for synchronize_hardirq() to complete without holding the optional + * chip bus lock and desc->lock. Also protects against handing out + * a recycled oneshot thread_mask bit while it's still in use by + * its previous owner. */ mutex_lock(&desc->request_mutex); @@ -1564,9 +1577,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); - if (!desc) - return NULL; - mutex_lock(&desc->request_mutex); chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, flags); @@ -1613,11 +1623,11 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) /* * Drop bus_lock here so the changes which were done in the chip * callbacks above are synced out to the irq chips which hang - * behind a slow bus (I2C, SPI) before calling synchronize_irq(). + * behind a slow bus (I2C, SPI) before calling synchronize_hardirq(). * * Aside of that the bus_lock can also be taken from the threaded * handler in irq_finalize_oneshot() which results in a deadlock - * because synchronize_irq() would wait forever for the thread to + * because kthread_stop() would wait forever for the thread to * complete, which is blocked on the bus lock. * * The still held desc->request_mutex() protects against a @@ -1629,7 +1639,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) unregister_handler_proc(irq, action); /* Make sure it's not being used on another CPU: */ - synchronize_irq(irq); + synchronize_hardirq(irq); #ifdef CONFIG_DEBUG_SHIRQ /* @@ -1638,7 +1648,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) * is so by doing an extra call to the handler .... * * ( We do this after actually deregistering it, to make sure that a - * 'real' IRQ doesn't run in * parallel with our fake. ) + * 'real' IRQ doesn't run in parallel with our fake. ) */ if (action->flags & IRQF_SHARED) { local_irq_save(flags); @@ -1647,6 +1657,12 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) } #endif + /* + * The action has already been removed above, but the thread writes + * its oneshot mask bit when it completes. Though request_mutex is + * held across this which prevents __setup_irq() from handing out + * the same bit to a newly requested action. + */ if (action->thread) { kthread_stop(action->thread); put_task_struct(action->thread); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 37eda10f5c36..da9addb8d655 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -475,22 +475,24 @@ int show_interrupts(struct seq_file *p, void *v) seq_putc(p, '\n'); } - irq_lock_sparse(); + rcu_read_lock(); desc = irq_to_desc(i); if (!desc) goto outsparse; - raw_spin_lock_irqsave(&desc->lock, flags); - for_each_online_cpu(j) - any_count |= kstat_irqs_cpu(i, j); - action = desc->action; - if ((!action || irq_desc_is_chained(desc)) && !any_count) - goto out; + if (desc->kstat_irqs) + for_each_online_cpu(j) + any_count |= *per_cpu_ptr(desc->kstat_irqs, j); + + if ((!desc->action || irq_desc_is_chained(desc)) && !any_count) + goto outsparse; seq_printf(p, "%*d: ", prec, i); for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); + seq_printf(p, "%10u ", desc->kstat_irqs ? + *per_cpu_ptr(desc->kstat_irqs, j) : 0); + raw_spin_lock_irqsave(&desc->lock, flags); if (desc->irq_data.chip) { if (desc->irq_data.chip->irq_print_chip) desc->irq_data.chip->irq_print_chip(&desc->irq_data, p); @@ -511,6 +513,7 @@ int show_interrupts(struct seq_file *p, void *v) if (desc->name) seq_printf(p, "-%-8s", desc->name); + action = desc->action; if (action) { seq_printf(p, " %s", action->name); while ((action = action->next) != NULL) @@ -518,10 +521,9 @@ int show_interrupts(struct seq_file *p, void *v) } seq_putc(p, '\n'); -out: raw_spin_unlock_irqrestore(&desc->lock, flags); outsparse: - irq_unlock_sparse(); + rcu_read_unlock(); return 0; } #endif diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ea619021d901..ab257be4d924 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -627,8 +627,8 @@ static void optimize_kprobe(struct kprobe *p) (kprobe_disabled(p) || kprobes_all_disarmed)) return; - /* Both of break_handler and post_handler are not supported. */ - if (p->break_handler || p->post_handler) + /* kprobes with post_handler can not be optimized */ + if (p->post_handler) return; op = container_of(p, struct optimized_kprobe, kp); @@ -710,9 +710,7 @@ static void reuse_unused_kprobe(struct kprobe *ap) * there is still a relative jump) and disabled. */ op = container_of(ap, struct optimized_kprobe, kp); - if (unlikely(list_empty(&op->list))) - printk(KERN_WARNING "Warning: found a stray unused " - "aggrprobe@%p\n", ap->addr); + WARN_ON_ONCE(list_empty(&op->list)); /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ @@ -985,7 +983,8 @@ static int arm_kprobe_ftrace(struct kprobe *p) ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 0, 0); if (ret) { - pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n", + p->addr, ret); return ret; } @@ -1025,7 +1024,8 @@ static int disarm_kprobe_ftrace(struct kprobe *p) ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); - WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); + WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n", + p->addr, ret); return ret; } #else /* !CONFIG_KPROBES_ON_FTRACE */ @@ -1116,20 +1116,6 @@ static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, } NOKPROBE_SYMBOL(aggr_fault_handler); -static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe *cur = __this_cpu_read(kprobe_instance); - int ret = 0; - - if (cur && cur->break_handler) { - if (cur->break_handler(cur, regs)) - ret = 1; - } - reset_kprobe_instance(); - return ret; -} -NOKPROBE_SYMBOL(aggr_break_handler); - /* Walks the list and increments nmissed count for multiprobe case */ void kprobes_inc_nmissed_count(struct kprobe *p) { @@ -1270,24 +1256,15 @@ static void cleanup_rp_inst(struct kretprobe *rp) } NOKPROBE_SYMBOL(cleanup_rp_inst); -/* -* Add the new probe to ap->list. Fail if this is the -* second jprobe at the address - two jprobes can't coexist -*/ +/* Add the new probe to ap->list */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { BUG_ON(kprobe_gone(ap) || kprobe_gone(p)); - if (p->break_handler || p->post_handler) + if (p->post_handler) unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */ - if (p->break_handler) { - if (ap->break_handler) - return -EEXIST; - list_add_tail_rcu(&p->list, &ap->list); - ap->break_handler = aggr_break_handler; - } else - list_add_rcu(&p->list, &ap->list); + list_add_rcu(&p->list, &ap->list); if (p->post_handler && !ap->post_handler) ap->post_handler = aggr_post_handler; @@ -1310,8 +1287,6 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) /* We don't care the kprobe which has gone. */ if (p->post_handler && !kprobe_gone(p)) ap->post_handler = aggr_post_handler; - if (p->break_handler && !kprobe_gone(p)) - ap->break_handler = aggr_break_handler; INIT_LIST_HEAD(&ap->list); INIT_HLIST_NODE(&ap->hlist); @@ -1706,8 +1681,6 @@ static int __unregister_kprobe_top(struct kprobe *p) goto disarmed; else { /* If disabling probe has special handlers, update aggrprobe */ - if (p->break_handler && !kprobe_gone(p)) - ap->break_handler = NULL; if (p->post_handler && !kprobe_gone(p)) { list_for_each_entry_rcu(list_p, &ap->list, list) { if ((list_p != p) && (list_p->post_handler)) @@ -1812,77 +1785,6 @@ unsigned long __weak arch_deref_entry_point(void *entry) return (unsigned long)entry; } -#if 0 -int register_jprobes(struct jprobe **jps, int num) -{ - int ret = 0, i; - - if (num <= 0) - return -EINVAL; - - for (i = 0; i < num; i++) { - ret = register_jprobe(jps[i]); - - if (ret < 0) { - if (i > 0) - unregister_jprobes(jps, i); - break; - } - } - - return ret; -} -EXPORT_SYMBOL_GPL(register_jprobes); - -int register_jprobe(struct jprobe *jp) -{ - unsigned long addr, offset; - struct kprobe *kp = &jp->kp; - - /* - * Verify probepoint as well as the jprobe handler are - * valid function entry points. - */ - addr = arch_deref_entry_point(jp->entry); - - if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 && - kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) { - kp->pre_handler = setjmp_pre_handler; - kp->break_handler = longjmp_break_handler; - return register_kprobe(kp); - } - - return -EINVAL; -} -EXPORT_SYMBOL_GPL(register_jprobe); - -void unregister_jprobe(struct jprobe *jp) -{ - unregister_jprobes(&jp, 1); -} -EXPORT_SYMBOL_GPL(unregister_jprobe); - -void unregister_jprobes(struct jprobe **jps, int num) -{ - int i; - - if (num <= 0) - return; - mutex_lock(&kprobe_mutex); - for (i = 0; i < num; i++) - if (__unregister_kprobe_top(&jps[i]->kp) < 0) - jps[i]->kp.addr = NULL; - mutex_unlock(&kprobe_mutex); - - synchronize_sched(); - for (i = 0; i < num; i++) { - if (jps[i]->kp.addr) - __unregister_kprobe_bottom(&jps[i]->kp); - } -} -EXPORT_SYMBOL_GPL(unregister_jprobes); -#endif - #ifdef CONFIG_KRETPROBES /* * This kprobe pre_handler is registered with every kretprobe. When probe @@ -1982,7 +1884,6 @@ int register_kretprobe(struct kretprobe *rp) rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; rp->kp.fault_handler = NULL; - rp->kp.break_handler = NULL; /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { @@ -2105,7 +2006,6 @@ static void kill_kprobe(struct kprobe *p) list_for_each_entry_rcu(kp, &p->list, list) kp->flags |= KPROBE_FLAG_GONE; p->post_handler = NULL; - p->break_handler = NULL; kill_optimized_kprobe(p); } /* @@ -2169,11 +2069,12 @@ out: } EXPORT_SYMBOL_GPL(enable_kprobe); +/* Caller must NOT call this in usual path. This is only for critical case */ void dump_kprobe(struct kprobe *kp) { - printk(KERN_WARNING "Dumping kprobe:\n"); - printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n", - kp->symbol_name, kp->addr, kp->offset); + pr_err("Dumping kprobe:\n"); + pr_err("Name: %s\nOffset: %x\nAddress: %pS\n", + kp->symbol_name, kp->offset, kp->addr); } NOKPROBE_SYMBOL(dump_kprobe); @@ -2196,11 +2097,8 @@ static int __init populate_kprobe_blacklist(unsigned long *start, entry = arch_deref_entry_point((void *)*iter); if (!kernel_text_address(entry) || - !kallsyms_lookup_size_offset(entry, &size, &offset)) { - pr_err("Failed to find blacklist at %p\n", - (void *)entry); + !kallsyms_lookup_size_offset(entry, &size, &offset)) continue; - } ent = kmalloc(sizeof(*ent), GFP_KERNEL); if (!ent) @@ -2326,21 +2224,23 @@ static void report_probe(struct seq_file *pi, struct kprobe *p, const char *sym, int offset, char *modname, struct kprobe *pp) { char *kprobe_type; + void *addr = p->addr; if (p->pre_handler == pre_handler_kretprobe) kprobe_type = "r"; - else if (p->pre_handler == setjmp_pre_handler) - kprobe_type = "j"; else kprobe_type = "k"; + if (!kallsyms_show_value()) + addr = NULL; + if (sym) - seq_printf(pi, "%p %s %s+0x%x %s ", - p->addr, kprobe_type, sym, offset, + seq_printf(pi, "%px %s %s+0x%x %s ", + addr, kprobe_type, sym, offset, (modname ? modname : " ")); - else - seq_printf(pi, "%p %s %p ", - p->addr, kprobe_type, p->addr); + else /* try to use %pS */ + seq_printf(pi, "%px %s %pS ", + addr, kprobe_type, p->addr); if (!pp) pp = p; @@ -2428,8 +2328,16 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) struct kprobe_blacklist_entry *ent = list_entry(v, struct kprobe_blacklist_entry, list); - seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr, - (void *)ent->end_addr, (void *)ent->start_addr); + /* + * If /proc/kallsyms is not showing kernel address, we won't + * show them here either. + */ + if (!kallsyms_show_value()) + seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL, + (void *)ent->start_addr); + else + seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr, + (void *)ent->end_addr, (void *)ent->start_addr); return 0; } @@ -2611,7 +2519,7 @@ static int __init debugfs_kprobe_init(void) if (!dir) return -ENOMEM; - file = debugfs_create_file("list", 0444, dir, NULL, + file = debugfs_create_file("list", 0400, dir, NULL, &debugfs_kprobes_operations); if (!file) goto error; @@ -2621,7 +2529,7 @@ static int __init debugfs_kprobe_init(void) if (!file) goto error; - file = debugfs_create_file("blacklist", 0444, dir, NULL, + file = debugfs_create_file("blacklist", 0400, dir, NULL, &debugfs_kprobe_blacklist_ops); if (!file) goto error; @@ -2637,6 +2545,3 @@ late_initcall(debugfs_kprobe_init); #endif /* CONFIG_DEBUG_FS */ module_init(init_kprobes); - -/* defined in arch/.../kernel/kprobes.c */ -EXPORT_SYMBOL_GPL(jprobe_return); diff --git a/kernel/kthread.c b/kernel/kthread.c index 750cb8082694..087d18d771b5 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -190,7 +190,7 @@ static void __kthread_parkme(struct kthread *self) if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) break; - complete_all(&self->parked); + complete(&self->parked); schedule(); } __set_current_state(TASK_RUNNING); @@ -325,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), task = create->result; if (!IS_ERR(task)) { static const struct sched_param param = { .sched_priority = 0 }; + char name[TASK_COMM_LEN]; - vsnprintf(task->comm, sizeof(task->comm), namefmt, args); + /* + * task is already visible to other tasks, so updating + * COMM must be protected. + */ + vsnprintf(name, sizeof(name), namefmt, args); + set_task_comm(task, name); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. @@ -465,7 +471,6 @@ void kthread_unpark(struct task_struct *k) if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) __kthread_bind(k, kthread->cpu, TASK_PARKED); - reinit_completion(&kthread->parked); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); /* * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup. @@ -493,6 +498,9 @@ int kthread_park(struct task_struct *k) if (WARN_ON(k->flags & PF_EXITING)) return -ENOSYS; + if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))) + return -EBUSY; + set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 8402b3349dca..57bef4fbfb31 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -21,6 +21,9 @@ * Davidlohr Bueso <dave@stgolabs.net> * Based on kernel/rcu/torture.c. */ + +#define pr_fmt(fmt) fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/kthread.h> @@ -57,7 +60,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable."); torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s"); torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable"); -torture_param(bool, verbose, true, +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); static char *torture_type = "spin_lock"; diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 4f014be7a4b8..2823d4163a37 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1465,6 +1465,29 @@ rt_mutex_fastunlock(struct rt_mutex *lock, rt_mutex_postunlock(&wake_q); } +static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) +{ + might_sleep(); + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +/** + * rt_mutex_lock_nested - lock a rt_mutex + * + * @lock: the rt_mutex to be locked + * @subclass: the lockdep subclass + */ +void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass) +{ + __rt_mutex_lock(lock, subclass); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); +#endif + +#ifndef CONFIG_DEBUG_LOCK_ALLOC /** * rt_mutex_lock - lock a rt_mutex * @@ -1472,12 +1495,10 @@ rt_mutex_fastunlock(struct rt_mutex *lock, */ void __sched rt_mutex_lock(struct rt_mutex *lock) { - might_sleep(); - - mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); - rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); + __rt_mutex_lock(lock, 0); } EXPORT_SYMBOL_GPL(rt_mutex_lock); +#endif /** * rt_mutex_lock_interruptible - lock a rt_mutex interruptible diff --git a/kernel/memremap.c b/kernel/memremap.c index 5857267a4af5..38283363da06 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -176,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) unsigned long pfn, pgoff, order; pgprot_t pgprot = PAGE_KERNEL; int error, nid, is_ram; + struct dev_pagemap *conflict_pgmap; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) - align_start; + align_end = align_start + align_size - 1; + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return ERR_PTR(-ENOMEM); + } + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return ERR_PTR(-ENOMEM); + } + is_ram = region_intersects(align_start, align_size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); @@ -199,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) mutex_lock(&pgmap_lock); error = 0; - align_end = align_start + align_size - 1; foreach_order_pgoff(res, order, pgoff) { error = __radix_tree_insert(&pgmap_radix, @@ -305,7 +321,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap); #ifdef CONFIG_DEV_PAGEMAP_OPS DEFINE_STATIC_KEY_FALSE(devmap_managed_key); -EXPORT_SYMBOL_GPL(devmap_managed_key); +EXPORT_SYMBOL(devmap_managed_key); static atomic_t devmap_enable; /* @@ -346,5 +362,5 @@ void __put_devmap_managed_page(struct page *page) } else if (!count) __put_page(page); } -EXPORT_SYMBOL_GPL(__put_devmap_managed_page); +EXPORT_SYMBOL(__put_devmap_managed_page); #endif /* CONFIG_DEV_PAGEMAP_OPS */ diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 87331565e505..70178f6ffdc4 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -92,7 +92,7 @@ static void s2idle_enter(void) /* Push all the CPUs into the idle loop. */ wake_up_all_idle_cpus(); /* Make the current CPU wait so it can enter the idle loop too. */ - swait_event(s2idle_wait_head, + swait_event_exclusive(s2idle_wait_head, s2idle_state == S2IDLE_STATE_WAKE); cpuidle_pause(); @@ -160,7 +160,7 @@ void s2idle_wake(void) raw_spin_lock_irqsave(&s2idle_lock, flags); if (s2idle_state > S2IDLE_STATE_NONE) { s2idle_state = S2IDLE_STATE_WAKE; - swake_up(&s2idle_wait_head); + swake_up_one(&s2idle_wait_head); } raw_spin_unlock_irqrestore(&s2idle_lock, flags); } diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 40cea6735c2d..4d04683c31b2 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -91,7 +91,17 @@ static inline void rcu_seq_end(unsigned long *sp) WRITE_ONCE(*sp, rcu_seq_endval(sp)); } -/* Take a snapshot of the update side's sequence number. */ +/* + * rcu_seq_snap - Take a snapshot of the update side's sequence number. + * + * This function returns the earliest value of the grace-period sequence number + * that will indicate that a full grace period has elapsed since the current + * time. Once the grace-period sequence number has reached this value, it will + * be safe to invoke all callbacks that have been registered prior to the + * current time. This value is the current grace-period number plus two to the + * power of the number of low-order bits reserved for state, then rounded up to + * the next value in which the state bits are all zero. + */ static inline unsigned long rcu_seq_snap(unsigned long *sp) { unsigned long s; @@ -108,6 +118,15 @@ static inline unsigned long rcu_seq_current(unsigned long *sp) } /* + * Given a snapshot from rcu_seq_snap(), determine whether or not the + * corresponding update-side operation has started. + */ +static inline bool rcu_seq_started(unsigned long *sp, unsigned long s) +{ + return ULONG_CMP_LT((s - 1) & ~RCU_SEQ_STATE_MASK, READ_ONCE(*sp)); +} + +/* * Given a snapshot from rcu_seq_snap(), determine whether or not a * full update-side operation has occurred. */ @@ -117,6 +136,45 @@ static inline bool rcu_seq_done(unsigned long *sp, unsigned long s) } /* + * Has a grace period completed since the time the old gp_seq was collected? + */ +static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new) +{ + return ULONG_CMP_LT(old, new & ~RCU_SEQ_STATE_MASK); +} + +/* + * Has a grace period started since the time the old gp_seq was collected? + */ +static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new) +{ + return ULONG_CMP_LT((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK, + new); +} + +/* + * Roughly how many full grace periods have elapsed between the collection + * of the two specified grace periods? + */ +static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old) +{ + unsigned long rnd_diff; + + if (old == new) + return 0; + /* + * Compute the number of grace periods (still shifted up), plus + * one if either of new and old is not an exact grace period. + */ + rnd_diff = (new & ~RCU_SEQ_STATE_MASK) - + ((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK) + + ((new & RCU_SEQ_STATE_MASK) || (old & RCU_SEQ_STATE_MASK)); + if (ULONG_CMP_GE(RCU_SEQ_STATE_MASK, rnd_diff)) + return 1; /* Definitely no grace period has elapsed. */ + return ((rnd_diff - RCU_SEQ_STATE_MASK - 1) >> RCU_SEQ_CTR_SHIFT) + 2; +} + +/* * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally * by call_rcu() and rcu callback execution, and are therefore not part of the * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. @@ -276,6 +334,9 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt) /* Is this rcu_node a leaf? */ #define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1) +/* Is this rcu_node the last leaf? */ +#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1]) + /* * Do a full breadth-first scan of the rcu_node structures for the * specified rcu_state structure. @@ -405,8 +466,7 @@ enum rcutorture_type { #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gpnum, unsigned long *completed); -void rcutorture_record_test_transition(void); + unsigned long *gp_seq); void rcutorture_record_progress(unsigned long vernum); void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, @@ -415,15 +475,11 @@ void do_trace_rcu_torture_read(const char *rcutorturename, unsigned long c); #else static inline void rcutorture_get_gp_data(enum rcutorture_type test_type, - int *flags, - unsigned long *gpnum, - unsigned long *completed) + int *flags, unsigned long *gp_seq) { *flags = 0; - *gpnum = 0; - *completed = 0; + *gp_seq = 0; } -static inline void rcutorture_record_test_transition(void) { } static inline void rcutorture_record_progress(unsigned long vernum) { } #ifdef CONFIG_RCU_TRACE void do_trace_rcu_torture_read(const char *rcutorturename, @@ -441,31 +497,26 @@ void do_trace_rcu_torture_read(const char *rcutorturename, static inline void srcutorture_get_gp_data(enum rcutorture_type test_type, struct srcu_struct *sp, int *flags, - unsigned long *gpnum, - unsigned long *completed) + unsigned long *gp_seq) { if (test_type != SRCU_FLAVOR) return; *flags = 0; - *completed = sp->srcu_idx; - *gpnum = *completed; + *gp_seq = sp->srcu_idx; } #elif defined(CONFIG_TREE_SRCU) void srcutorture_get_gp_data(enum rcutorture_type test_type, struct srcu_struct *sp, int *flags, - unsigned long *gpnum, unsigned long *completed); + unsigned long *gp_seq); #endif #ifdef CONFIG_TINY_RCU -static inline unsigned long rcu_batches_started(void) { return 0; } -static inline unsigned long rcu_batches_started_bh(void) { return 0; } -static inline unsigned long rcu_batches_started_sched(void) { return 0; } -static inline unsigned long rcu_batches_completed(void) { return 0; } -static inline unsigned long rcu_batches_completed_bh(void) { return 0; } -static inline unsigned long rcu_batches_completed_sched(void) { return 0; } +static inline unsigned long rcu_get_gp_seq(void) { return 0; } +static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; } +static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; } static inline unsigned long rcu_exp_batches_completed(void) { return 0; } static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; } static inline unsigned long @@ -474,19 +525,16 @@ static inline void rcu_force_quiescent_state(void) { } static inline void rcu_bh_force_quiescent_state(void) { } static inline void rcu_sched_force_quiescent_state(void) { } static inline void show_rcu_gp_kthreads(void) { } +static inline int rcu_get_gp_kthreads_prio(void) { return 0; } #else /* #ifdef CONFIG_TINY_RCU */ -extern unsigned long rcutorture_testseq; -extern unsigned long rcutorture_vernum; -unsigned long rcu_batches_started(void); -unsigned long rcu_batches_started_bh(void); -unsigned long rcu_batches_started_sched(void); -unsigned long rcu_batches_completed(void); -unsigned long rcu_batches_completed_bh(void); -unsigned long rcu_batches_completed_sched(void); +unsigned long rcu_get_gp_seq(void); +unsigned long rcu_bh_get_gp_seq(void); +unsigned long rcu_sched_get_gp_seq(void); unsigned long rcu_exp_batches_completed(void); unsigned long rcu_exp_batches_completed_sched(void); unsigned long srcu_batches_completed(struct srcu_struct *sp); void show_rcu_gp_kthreads(void); +int rcu_get_gp_kthreads_prio(void); void rcu_force_quiescent_state(void); void rcu_bh_force_quiescent_state(void); void rcu_sched_force_quiescent_state(void); diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index e232846516b3..34244523550e 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -19,6 +19,9 @@ * * Authors: Paul E. McKenney <paulmck@us.ibm.com> */ + +#define pr_fmt(fmt) fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -88,7 +91,7 @@ torture_param(int, nreaders, -1, "Number of RCU reader threads"); torture_param(int, nwriters, -1, "Number of RCU updater threads"); torture_param(bool, shutdown, !IS_ENABLED(MODULE), "Shutdown at end of performance tests."); -torture_param(bool, verbose, true, "Enable verbose debugging printk()s"); +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable"); static char *perf_type = "rcu"; @@ -135,8 +138,8 @@ struct rcu_perf_ops { void (*cleanup)(void); int (*readlock)(void); void (*readunlock)(int idx); - unsigned long (*started)(void); - unsigned long (*completed)(void); + unsigned long (*get_gp_seq)(void); + unsigned long (*gp_diff)(unsigned long new, unsigned long old); unsigned long (*exp_completed)(void); void (*async)(struct rcu_head *head, rcu_callback_t func); void (*gp_barrier)(void); @@ -176,8 +179,8 @@ static struct rcu_perf_ops rcu_ops = { .init = rcu_sync_perf_init, .readlock = rcu_perf_read_lock, .readunlock = rcu_perf_read_unlock, - .started = rcu_batches_started, - .completed = rcu_batches_completed, + .get_gp_seq = rcu_get_gp_seq, + .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed, .async = call_rcu, .gp_barrier = rcu_barrier, @@ -206,8 +209,8 @@ static struct rcu_perf_ops rcu_bh_ops = { .init = rcu_sync_perf_init, .readlock = rcu_bh_perf_read_lock, .readunlock = rcu_bh_perf_read_unlock, - .started = rcu_batches_started_bh, - .completed = rcu_batches_completed_bh, + .get_gp_seq = rcu_bh_get_gp_seq, + .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed_sched, .async = call_rcu_bh, .gp_barrier = rcu_barrier_bh, @@ -263,8 +266,8 @@ static struct rcu_perf_ops srcu_ops = { .init = rcu_sync_perf_init, .readlock = srcu_perf_read_lock, .readunlock = srcu_perf_read_unlock, - .started = NULL, - .completed = srcu_perf_completed, + .get_gp_seq = srcu_perf_completed, + .gp_diff = rcu_seq_diff, .exp_completed = srcu_perf_completed, .async = srcu_call_rcu, .gp_barrier = srcu_rcu_barrier, @@ -292,8 +295,8 @@ static struct rcu_perf_ops srcud_ops = { .cleanup = srcu_sync_perf_cleanup, .readlock = srcu_perf_read_lock, .readunlock = srcu_perf_read_unlock, - .started = NULL, - .completed = srcu_perf_completed, + .get_gp_seq = srcu_perf_completed, + .gp_diff = rcu_seq_diff, .exp_completed = srcu_perf_completed, .async = srcu_call_rcu, .gp_barrier = srcu_rcu_barrier, @@ -322,8 +325,8 @@ static struct rcu_perf_ops sched_ops = { .init = rcu_sync_perf_init, .readlock = sched_perf_read_lock, .readunlock = sched_perf_read_unlock, - .started = rcu_batches_started_sched, - .completed = rcu_batches_completed_sched, + .get_gp_seq = rcu_sched_get_gp_seq, + .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed_sched, .async = call_rcu_sched, .gp_barrier = rcu_barrier_sched, @@ -350,8 +353,8 @@ static struct rcu_perf_ops tasks_ops = { .init = rcu_sync_perf_init, .readlock = tasks_perf_read_lock, .readunlock = tasks_perf_read_unlock, - .started = rcu_no_completed, - .completed = rcu_no_completed, + .get_gp_seq = rcu_no_completed, + .gp_diff = rcu_seq_diff, .async = call_rcu_tasks, .gp_barrier = rcu_barrier_tasks, .sync = synchronize_rcu_tasks, @@ -359,9 +362,11 @@ static struct rcu_perf_ops tasks_ops = { .name = "tasks" }; -static bool __maybe_unused torturing_tasks(void) +static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old) { - return cur_ops == &tasks_ops; + if (!cur_ops->gp_diff) + return new - old; + return cur_ops->gp_diff(new, old); } /* @@ -444,8 +449,7 @@ rcu_perf_writer(void *arg) b_rcu_perf_writer_started = cur_ops->exp_completed() / 2; } else { - b_rcu_perf_writer_started = - cur_ops->completed(); + b_rcu_perf_writer_started = cur_ops->get_gp_seq(); } } @@ -502,7 +506,7 @@ retry: cur_ops->exp_completed() / 2; } else { b_rcu_perf_writer_finished = - cur_ops->completed(); + cur_ops->get_gp_seq(); } if (shutdown) { smp_mb(); /* Assign before wake. */ @@ -527,7 +531,7 @@ retry: return 0; } -static inline void +static void rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag) { pr_alert("%s" PERF_FLAG @@ -582,8 +586,8 @@ rcu_perf_cleanup(void) t_rcu_perf_writer_finished - t_rcu_perf_writer_started, ngps, - b_rcu_perf_writer_finished - - b_rcu_perf_writer_started); + rcuperf_seq_diff(b_rcu_perf_writer_finished, + b_rcu_perf_writer_started)); for (i = 0; i < nrealwriters; i++) { if (!writer_durations) break; @@ -671,12 +675,11 @@ rcu_perf_init(void) break; } if (i == ARRAY_SIZE(perf_ops)) { - pr_alert("rcu-perf: invalid perf type: \"%s\"\n", - perf_type); + pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type); pr_alert("rcu-perf types:"); for (i = 0; i < ARRAY_SIZE(perf_ops); i++) - pr_alert(" %s", perf_ops[i]->name); - pr_alert("\n"); + pr_cont(" %s", perf_ops[i]->name); + pr_cont("\n"); firsterr = -EINVAL; goto unwind; } diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 42fcb7f05fac..c596c6f1e457 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -22,6 +22,9 @@ * * See also: Documentation/RCU/torture.txt */ + +#define pr_fmt(fmt) fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -52,6 +55,7 @@ #include <linux/torture.h> #include <linux/vmalloc.h> #include <linux/sched/debug.h> +#include <linux/sched/sysctl.h> #include "rcu.h" @@ -59,6 +63,19 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>"); +/* Bits for ->extendables field, extendables param, and related definitions. */ +#define RCUTORTURE_RDR_SHIFT 8 /* Put SRCU index in upper bits. */ +#define RCUTORTURE_RDR_MASK ((1 << RCUTORTURE_RDR_SHIFT) - 1) +#define RCUTORTURE_RDR_BH 0x1 /* Extend readers by disabling bh. */ +#define RCUTORTURE_RDR_IRQ 0x2 /* ... disabling interrupts. */ +#define RCUTORTURE_RDR_PREEMPT 0x4 /* ... disabling preemption. */ +#define RCUTORTURE_RDR_RCU 0x8 /* ... entering another RCU reader. */ +#define RCUTORTURE_RDR_NBITS 4 /* Number of bits defined above. */ +#define RCUTORTURE_MAX_EXTEND (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \ + RCUTORTURE_RDR_PREEMPT) +#define RCUTORTURE_RDR_MAX_LOOPS 0x7 /* Maximum reader extensions. */ + /* Must be power of two minus one. */ + torture_param(int, cbflood_inter_holdoff, HZ, "Holdoff between floods (jiffies)"); torture_param(int, cbflood_intra_holdoff, 1, @@ -66,6 +83,8 @@ torture_param(int, cbflood_intra_holdoff, 1, torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable"); torture_param(int, cbflood_n_per_burst, 20000, "# callbacks per burst in flood"); +torture_param(int, extendables, RCUTORTURE_MAX_EXTEND, + "Extend readers by disabling bh (1), irqs (2), or preempt (4)"); torture_param(int, fqs_duration, 0, "Duration of fqs bursts (us), 0 to disable"); torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)"); @@ -84,7 +103,7 @@ torture_param(int, object_debug, 0, "Enable debug-object double call_rcu() testing"); torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); torture_param(int, onoff_interval, 0, - "Time between CPU hotplugs (s), 0=disable"); + "Time between CPU hotplugs (jiffies), 0=disable"); torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles"); torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable."); torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable."); @@ -101,7 +120,7 @@ torture_param(int, test_boost_interval, 7, "Interval between boost tests, seconds."); torture_param(bool, test_no_idle_hz, true, "Test support for tickless idle CPUs"); -torture_param(bool, verbose, true, +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); static char *torture_type = "rcu"; @@ -148,9 +167,9 @@ static long n_rcu_torture_boost_ktrerror; static long n_rcu_torture_boost_rterror; static long n_rcu_torture_boost_failure; static long n_rcu_torture_boosts; -static long n_rcu_torture_timers; +static atomic_long_t n_rcu_torture_timers; static long n_barrier_attempts; -static long n_barrier_successes; +static long n_barrier_successes; /* did rcu_barrier test succeed? */ static atomic_long_t n_cbfloods; static struct list_head rcu_torture_removed; @@ -261,8 +280,8 @@ struct rcu_torture_ops { int (*readlock)(void); void (*read_delay)(struct torture_random_state *rrsp); void (*readunlock)(int idx); - unsigned long (*started)(void); - unsigned long (*completed)(void); + unsigned long (*get_gp_seq)(void); + unsigned long (*gp_diff)(unsigned long new, unsigned long old); void (*deferred_free)(struct rcu_torture *p); void (*sync)(void); void (*exp_sync)(void); @@ -274,6 +293,8 @@ struct rcu_torture_ops { void (*stats)(void); int irq_capable; int can_boost; + int extendables; + int ext_irq_conflict; const char *name; }; @@ -302,10 +323,10 @@ static void rcu_read_delay(struct torture_random_state *rrsp) * force_quiescent_state. */ if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) { - started = cur_ops->completed(); + started = cur_ops->get_gp_seq(); ts = rcu_trace_clock_local(); mdelay(longdelay_ms); - completed = cur_ops->completed(); + completed = cur_ops->get_gp_seq(); do_trace_rcu_torture_read(cur_ops->name, NULL, ts, started, completed); } @@ -397,8 +418,8 @@ static struct rcu_torture_ops rcu_ops = { .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, .readunlock = rcu_torture_read_unlock, - .started = rcu_batches_started, - .completed = rcu_batches_completed, + .get_gp_seq = rcu_get_gp_seq, + .gp_diff = rcu_seq_diff, .deferred_free = rcu_torture_deferred_free, .sync = synchronize_rcu, .exp_sync = synchronize_rcu_expedited, @@ -439,8 +460,8 @@ static struct rcu_torture_ops rcu_bh_ops = { .readlock = rcu_bh_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_bh_torture_read_unlock, - .started = rcu_batches_started_bh, - .completed = rcu_batches_completed_bh, + .get_gp_seq = rcu_bh_get_gp_seq, + .gp_diff = rcu_seq_diff, .deferred_free = rcu_bh_torture_deferred_free, .sync = synchronize_rcu_bh, .exp_sync = synchronize_rcu_bh_expedited, @@ -449,6 +470,8 @@ static struct rcu_torture_ops rcu_bh_ops = { .fqs = rcu_bh_force_quiescent_state, .stats = NULL, .irq_capable = 1, + .extendables = (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ), + .ext_irq_conflict = RCUTORTURE_RDR_RCU, .name = "rcu_bh" }; @@ -483,8 +506,7 @@ static struct rcu_torture_ops rcu_busted_ops = { .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_torture_read_unlock, - .started = rcu_no_completed, - .completed = rcu_no_completed, + .get_gp_seq = rcu_no_completed, .deferred_free = rcu_busted_torture_deferred_free, .sync = synchronize_rcu_busted, .exp_sync = synchronize_rcu_busted, @@ -572,8 +594,7 @@ static struct rcu_torture_ops srcu_ops = { .readlock = srcu_torture_read_lock, .read_delay = srcu_read_delay, .readunlock = srcu_torture_read_unlock, - .started = NULL, - .completed = srcu_torture_completed, + .get_gp_seq = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, .exp_sync = srcu_torture_synchronize_expedited, @@ -610,8 +631,7 @@ static struct rcu_torture_ops srcud_ops = { .readlock = srcu_torture_read_lock, .read_delay = srcu_read_delay, .readunlock = srcu_torture_read_unlock, - .started = NULL, - .completed = srcu_torture_completed, + .get_gp_seq = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, .exp_sync = srcu_torture_synchronize_expedited, @@ -622,6 +642,26 @@ static struct rcu_torture_ops srcud_ops = { .name = "srcud" }; +/* As above, but broken due to inappropriate reader extension. */ +static struct rcu_torture_ops busted_srcud_ops = { + .ttype = SRCU_FLAVOR, + .init = srcu_torture_init, + .cleanup = srcu_torture_cleanup, + .readlock = srcu_torture_read_lock, + .read_delay = rcu_read_delay, + .readunlock = srcu_torture_read_unlock, + .get_gp_seq = srcu_torture_completed, + .deferred_free = srcu_torture_deferred_free, + .sync = srcu_torture_synchronize, + .exp_sync = srcu_torture_synchronize_expedited, + .call = srcu_torture_call, + .cb_barrier = srcu_torture_barrier, + .stats = srcu_torture_stats, + .irq_capable = 1, + .extendables = RCUTORTURE_MAX_EXTEND, + .name = "busted_srcud" +}; + /* * Definitions for sched torture testing. */ @@ -648,8 +688,8 @@ static struct rcu_torture_ops sched_ops = { .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, - .started = rcu_batches_started_sched, - .completed = rcu_batches_completed_sched, + .get_gp_seq = rcu_sched_get_gp_seq, + .gp_diff = rcu_seq_diff, .deferred_free = rcu_sched_torture_deferred_free, .sync = synchronize_sched, .exp_sync = synchronize_sched_expedited, @@ -660,6 +700,7 @@ static struct rcu_torture_ops sched_ops = { .fqs = rcu_sched_force_quiescent_state, .stats = NULL, .irq_capable = 1, + .extendables = RCUTORTURE_MAX_EXTEND, .name = "sched" }; @@ -687,8 +728,7 @@ static struct rcu_torture_ops tasks_ops = { .readlock = tasks_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = tasks_torture_read_unlock, - .started = rcu_no_completed, - .completed = rcu_no_completed, + .get_gp_seq = rcu_no_completed, .deferred_free = rcu_tasks_torture_deferred_free, .sync = synchronize_rcu_tasks, .exp_sync = synchronize_rcu_tasks, @@ -700,6 +740,13 @@ static struct rcu_torture_ops tasks_ops = { .name = "tasks" }; +static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old) +{ + if (!cur_ops->gp_diff) + return new - old; + return cur_ops->gp_diff(new, old); +} + static bool __maybe_unused torturing_tasks(void) { return cur_ops == &tasks_ops; @@ -726,6 +773,44 @@ static void rcu_torture_boost_cb(struct rcu_head *head) smp_store_release(&rbip->inflight, 0); } +static int old_rt_runtime = -1; + +static void rcu_torture_disable_rt_throttle(void) +{ + /* + * Disable RT throttling so that rcutorture's boost threads don't get + * throttled. Only possible if rcutorture is built-in otherwise the + * user should manually do this by setting the sched_rt_period_us and + * sched_rt_runtime sysctls. + */ + if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime != -1) + return; + + old_rt_runtime = sysctl_sched_rt_runtime; + sysctl_sched_rt_runtime = -1; +} + +static void rcu_torture_enable_rt_throttle(void) +{ + if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime == -1) + return; + + sysctl_sched_rt_runtime = old_rt_runtime; + old_rt_runtime = -1; +} + +static bool rcu_torture_boost_failed(unsigned long start, unsigned long end) +{ + if (end - start > test_boost_duration * HZ - HZ / 2) { + VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed"); + n_rcu_torture_boost_failure++; + + return true; /* failed */ + } + + return false; /* passed */ +} + static int rcu_torture_boost(void *arg) { unsigned long call_rcu_time; @@ -746,6 +831,21 @@ static int rcu_torture_boost(void *arg) init_rcu_head_on_stack(&rbi.rcu); /* Each pass through the following loop does one boost-test cycle. */ do { + /* Track if the test failed already in this test interval? */ + bool failed = false; + + /* Increment n_rcu_torture_boosts once per boost-test */ + while (!kthread_should_stop()) { + if (mutex_trylock(&boost_mutex)) { + n_rcu_torture_boosts++; + mutex_unlock(&boost_mutex); + break; + } + schedule_timeout_uninterruptible(1); + } + if (kthread_should_stop()) + goto checkwait; + /* Wait for the next test interval. */ oldstarttime = boost_starttime; while (ULONG_CMP_LT(jiffies, oldstarttime)) { @@ -764,11 +864,10 @@ static int rcu_torture_boost(void *arg) /* RCU core before ->inflight = 1. */ smp_store_release(&rbi.inflight, 1); call_rcu(&rbi.rcu, rcu_torture_boost_cb); - if (jiffies - call_rcu_time > - test_boost_duration * HZ - HZ / 2) { - VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed"); - n_rcu_torture_boost_failure++; - } + /* Check if the boost test failed */ + failed = failed || + rcu_torture_boost_failed(call_rcu_time, + jiffies); call_rcu_time = jiffies; } stutter_wait("rcu_torture_boost"); @@ -777,6 +876,14 @@ static int rcu_torture_boost(void *arg) } /* + * If boost never happened, then inflight will always be 1, in + * this case the boost check would never happen in the above + * loop so do another one here. + */ + if (!failed && smp_load_acquire(&rbi.inflight)) + rcu_torture_boost_failed(call_rcu_time, jiffies); + + /* * Set the start time of the next test interval. * Yes, this is vulnerable to long delays, but such * delays simply cause a false negative for the next @@ -788,7 +895,6 @@ static int rcu_torture_boost(void *arg) if (mutex_trylock(&boost_mutex)) { boost_starttime = jiffies + test_boost_interval * HZ; - n_rcu_torture_boosts++; mutex_unlock(&boost_mutex); break; } @@ -1010,7 +1116,7 @@ rcu_torture_writer(void *arg) break; } } - rcutorture_record_progress(++rcu_torture_current_version); + rcu_torture_current_version++; /* Cycle through nesting levels of rcu_expedite_gp() calls. */ if (can_expedite && !(torture_random(&rand) & 0xff & (!!expediting - 1))) { @@ -1084,27 +1190,133 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp) } /* - * RCU torture reader from timer handler. Dereferences rcu_torture_current, - * incrementing the corresponding element of the pipeline array. The - * counter in the element should never be greater than 1, otherwise, the - * RCU implementation is broken. + * Do one extension of an RCU read-side critical section using the + * current reader state in readstate (set to zero for initial entry + * to extended critical section), set the new state as specified by + * newstate (set to zero for final exit from extended critical section), + * and random-number-generator state in trsp. If this is neither the + * beginning or end of the critical section and if there was actually a + * change, do a ->read_delay(). */ -static void rcu_torture_timer(struct timer_list *unused) +static void rcutorture_one_extend(int *readstate, int newstate, + struct torture_random_state *trsp) +{ + int idxnew = -1; + int idxold = *readstate; + int statesnew = ~*readstate & newstate; + int statesold = *readstate & ~newstate; + + WARN_ON_ONCE(idxold < 0); + WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1); + + /* First, put new protection in place to avoid critical-section gap. */ + if (statesnew & RCUTORTURE_RDR_BH) + local_bh_disable(); + if (statesnew & RCUTORTURE_RDR_IRQ) + local_irq_disable(); + if (statesnew & RCUTORTURE_RDR_PREEMPT) + preempt_disable(); + if (statesnew & RCUTORTURE_RDR_RCU) + idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT; + + /* Next, remove old protection, irq first due to bh conflict. */ + if (statesold & RCUTORTURE_RDR_IRQ) + local_irq_enable(); + if (statesold & RCUTORTURE_RDR_BH) + local_bh_enable(); + if (statesold & RCUTORTURE_RDR_PREEMPT) + preempt_enable(); + if (statesold & RCUTORTURE_RDR_RCU) + cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT); + + /* Delay if neither beginning nor end and there was a change. */ + if ((statesnew || statesold) && *readstate && newstate) + cur_ops->read_delay(trsp); + + /* Update the reader state. */ + if (idxnew == -1) + idxnew = idxold & ~RCUTORTURE_RDR_MASK; + WARN_ON_ONCE(idxnew < 0); + WARN_ON_ONCE((idxnew >> RCUTORTURE_RDR_SHIFT) > 1); + *readstate = idxnew | newstate; + WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) < 0); + WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) > 1); +} + +/* Return the biggest extendables mask given current RCU and boot parameters. */ +static int rcutorture_extend_mask_max(void) +{ + int mask; + + WARN_ON_ONCE(extendables & ~RCUTORTURE_MAX_EXTEND); + mask = extendables & RCUTORTURE_MAX_EXTEND & cur_ops->extendables; + mask = mask | RCUTORTURE_RDR_RCU; + return mask; +} + +/* Return a random protection state mask, but with at least one bit set. */ +static int +rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) +{ + int mask = rcutorture_extend_mask_max(); + unsigned long randmask1 = torture_random(trsp) >> 8; + unsigned long randmask2 = randmask1 >> 1; + + WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT); + /* Half the time lots of bits, half the time only one bit. */ + if (randmask1 & 0x1) + mask = mask & randmask2; + else + mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS)); + if ((mask & RCUTORTURE_RDR_IRQ) && + !(mask & RCUTORTURE_RDR_BH) && + (oldmask & RCUTORTURE_RDR_BH)) + mask |= RCUTORTURE_RDR_BH; /* Can't enable bh w/irq disabled. */ + if ((mask & RCUTORTURE_RDR_IRQ) && + !(mask & cur_ops->ext_irq_conflict) && + (oldmask & cur_ops->ext_irq_conflict)) + mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */ + return mask ?: RCUTORTURE_RDR_RCU; +} + +/* + * Do a randomly selected number of extensions of an existing RCU read-side + * critical section. + */ +static void rcutorture_loop_extend(int *readstate, + struct torture_random_state *trsp) +{ + int i; + int mask = rcutorture_extend_mask_max(); + + WARN_ON_ONCE(!*readstate); /* -Existing- RCU read-side critsect! */ + if (!((mask - 1) & mask)) + return; /* Current RCU flavor not extendable. */ + i = (torture_random(trsp) >> 3) & RCUTORTURE_RDR_MAX_LOOPS; + while (i--) { + mask = rcutorture_extend_mask(*readstate, trsp); + rcutorture_one_extend(readstate, mask, trsp); + } +} + +/* + * Do one read-side critical section, returning false if there was + * no data to read. Can be invoked both from process context and + * from a timer handler. + */ +static bool rcu_torture_one_read(struct torture_random_state *trsp) { - int idx; unsigned long started; unsigned long completed; - static DEFINE_TORTURE_RANDOM(rand); - static DEFINE_SPINLOCK(rand_lock); + int newstate; struct rcu_torture *p; int pipe_count; + int readstate = 0; unsigned long long ts; - idx = cur_ops->readlock(); - if (cur_ops->started) - started = cur_ops->started(); - else - started = cur_ops->completed(); + newstate = rcutorture_extend_mask(readstate, trsp); + rcutorture_one_extend(&readstate, newstate, trsp); + started = cur_ops->get_gp_seq(); ts = rcu_trace_clock_local(); p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || @@ -1112,39 +1324,50 @@ static void rcu_torture_timer(struct timer_list *unused) srcu_read_lock_held(srcu_ctlp) || torturing_tasks()); if (p == NULL) { - /* Leave because rcu_torture_writer is not yet underway */ - cur_ops->readunlock(idx); - return; + /* Wait for rcu_torture_writer to get underway */ + rcutorture_one_extend(&readstate, 0, trsp); + return false; } if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); - spin_lock(&rand_lock); - cur_ops->read_delay(&rand); - n_rcu_torture_timers++; - spin_unlock(&rand_lock); + rcutorture_loop_extend(&readstate, trsp); preempt_disable(); pipe_count = p->rtort_pipe_count; if (pipe_count > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - completed = cur_ops->completed(); + completed = cur_ops->get_gp_seq(); if (pipe_count > 1) { - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts, - started, completed); + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, + ts, started, completed); rcu_ftrace_dump(DUMP_ALL); } __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = completed - started; - if (cur_ops->started) - completed++; + completed = rcutorture_seq_diff(completed, started); if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; } __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); - cur_ops->readunlock(idx); + rcutorture_one_extend(&readstate, 0, trsp); + WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK); + return true; +} + +static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand); + +/* + * RCU torture reader from timer handler. Dereferences rcu_torture_current, + * incrementing the corresponding element of the pipeline array. The + * counter in the element should never be greater than 1, otherwise, the + * RCU implementation is broken. + */ +static void rcu_torture_timer(struct timer_list *unused) +{ + atomic_long_inc(&n_rcu_torture_timers); + (void)rcu_torture_one_read(this_cpu_ptr(&rcu_torture_timer_rand)); /* Test call_rcu() invocation from interrupt handler. */ if (cur_ops->call) { @@ -1164,14 +1387,8 @@ static void rcu_torture_timer(struct timer_list *unused) static int rcu_torture_reader(void *arg) { - unsigned long started; - unsigned long completed; - int idx; DEFINE_TORTURE_RANDOM(rand); - struct rcu_torture *p; - int pipe_count; struct timer_list t; - unsigned long long ts; VERBOSE_TOROUT_STRING("rcu_torture_reader task started"); set_user_nice(current, MAX_NICE); @@ -1183,49 +1400,8 @@ rcu_torture_reader(void *arg) if (!timer_pending(&t)) mod_timer(&t, jiffies + 1); } - idx = cur_ops->readlock(); - if (cur_ops->started) - started = cur_ops->started(); - else - started = cur_ops->completed(); - ts = rcu_trace_clock_local(); - p = rcu_dereference_check(rcu_torture_current, - rcu_read_lock_bh_held() || - rcu_read_lock_sched_held() || - srcu_read_lock_held(srcu_ctlp) || - torturing_tasks()); - if (p == NULL) { - /* Wait for rcu_torture_writer to get underway */ - cur_ops->readunlock(idx); + if (!rcu_torture_one_read(&rand)) schedule_timeout_interruptible(HZ); - continue; - } - if (p->rtort_mbtest == 0) - atomic_inc(&n_rcu_torture_mberror); - cur_ops->read_delay(&rand); - preempt_disable(); - pipe_count = p->rtort_pipe_count; - if (pipe_count > RCU_TORTURE_PIPE_LEN) { - /* Should not happen, but... */ - pipe_count = RCU_TORTURE_PIPE_LEN; - } - completed = cur_ops->completed(); - if (pipe_count > 1) { - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, - ts, started, completed); - rcu_ftrace_dump(DUMP_ALL); - } - __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = completed - started; - if (cur_ops->started) - completed++; - if (completed > RCU_TORTURE_PIPE_LEN) { - /* Should not happen, but... */ - completed = RCU_TORTURE_PIPE_LEN; - } - __this_cpu_inc(rcu_torture_batch[completed]); - preempt_enable(); - cur_ops->readunlock(idx); stutter_wait("rcu_torture_reader"); } while (!torture_must_stop()); if (irqreader && cur_ops->irq_capable) { @@ -1282,7 +1458,7 @@ rcu_torture_stats_print(void) pr_cont("rtbf: %ld rtb: %ld nt: %ld ", n_rcu_torture_boost_failure, n_rcu_torture_boosts, - n_rcu_torture_timers); + atomic_long_read(&n_rcu_torture_timers)); torture_onoff_stats(); pr_cont("barrier: %ld/%ld:%ld ", n_barrier_successes, @@ -1324,18 +1500,16 @@ rcu_torture_stats_print(void) if (rtcv_snap == rcu_torture_current_version && rcu_torture_current != NULL) { int __maybe_unused flags = 0; - unsigned long __maybe_unused gpnum = 0; - unsigned long __maybe_unused completed = 0; + unsigned long __maybe_unused gp_seq = 0; rcutorture_get_gp_data(cur_ops->ttype, - &flags, &gpnum, &completed); + &flags, &gp_seq); srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, - &flags, &gpnum, &completed); + &flags, &gp_seq); wtp = READ_ONCE(writer_task); - pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx cpu %d\n", + pr_alert("??? Writer stall state %s(%d) g%lu f%#x ->state %#lx cpu %d\n", rcu_torture_writer_state_getname(), - rcu_torture_writer_state, - gpnum, completed, flags, + rcu_torture_writer_state, gp_seq, flags, wtp == NULL ? ~0UL : wtp->state, wtp == NULL ? -1 : (int)task_cpu(wtp)); if (!splatted && wtp) { @@ -1365,7 +1539,7 @@ rcu_torture_stats(void *arg) return 0; } -static inline void +static void rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) { pr_alert("%s" TORTURE_FLAG @@ -1397,6 +1571,7 @@ static int rcutorture_booster_cleanup(unsigned int cpu) mutex_lock(&boost_mutex); t = boost_tasks[cpu]; boost_tasks[cpu] = NULL; + rcu_torture_enable_rt_throttle(); mutex_unlock(&boost_mutex); /* This must be outside of the mutex, otherwise deadlock! */ @@ -1413,6 +1588,7 @@ static int rcutorture_booster_init(unsigned int cpu) /* Don't allow time recalculation while creating a new task. */ mutex_lock(&boost_mutex); + rcu_torture_disable_rt_throttle(); VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task"); boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL, cpu_to_node(cpu), @@ -1446,7 +1622,7 @@ static int rcu_torture_stall(void *args) VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff"); } if (!kthread_should_stop()) { - stop_at = get_seconds() + stall_cpu; + stop_at = ktime_get_seconds() + stall_cpu; /* RCU CPU stall is expected behavior in following code. */ rcu_read_lock(); if (stall_cpu_irqsoff) @@ -1455,7 +1631,8 @@ static int rcu_torture_stall(void *args) preempt_disable(); pr_alert("rcu_torture_stall start on CPU %d.\n", smp_processor_id()); - while (ULONG_CMP_LT(get_seconds(), stop_at)) + while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(), + stop_at)) continue; /* Induce RCU CPU stall warning. */ if (stall_cpu_irqsoff) local_irq_enable(); @@ -1546,8 +1723,9 @@ static int rcu_torture_barrier(void *arg) atomic_read(&barrier_cbs_invoked), n_barrier_cbs); WARN_ON_ONCE(1); + } else { + n_barrier_successes++; } - n_barrier_successes++; schedule_timeout_interruptible(HZ / 10); } while (!torture_must_stop()); torture_kthread_stopping("rcu_torture_barrier"); @@ -1610,17 +1788,39 @@ static void rcu_torture_barrier_cleanup(void) } } +static bool rcu_torture_can_boost(void) +{ + static int boost_warn_once; + int prio; + + if (!(test_boost == 1 && cur_ops->can_boost) && test_boost != 2) + return false; + + prio = rcu_get_gp_kthreads_prio(); + if (!prio) + return false; + + if (prio < 2) { + if (boost_warn_once == 1) + return false; + + pr_alert("%s: WARN: RCU kthread priority too low to test boosting. Skipping RCU boost test. Try passing rcutree.kthread_prio > 1 on the kernel command line.\n", KBUILD_MODNAME); + boost_warn_once = 1; + return false; + } + + return true; +} + static enum cpuhp_state rcutor_hp; static void rcu_torture_cleanup(void) { int flags = 0; - unsigned long gpnum = 0; - unsigned long completed = 0; + unsigned long gp_seq = 0; int i; - rcutorture_record_test_transition(); if (torture_cleanup_begin()) { if (cur_ops->cb_barrier != NULL) cur_ops->cb_barrier(); @@ -1648,17 +1848,15 @@ rcu_torture_cleanup(void) fakewriter_tasks = NULL; } - rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed); - srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, - &flags, &gpnum, &completed); - pr_alert("%s: End-test grace-period state: g%lu c%lu f%#x\n", - cur_ops->name, gpnum, completed, flags); + rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq); + srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq); + pr_alert("%s: End-test grace-period state: g%lu f%#x\n", + cur_ops->name, gp_seq, flags); torture_stop_kthread(rcu_torture_stats, stats_task); torture_stop_kthread(rcu_torture_fqs, fqs_task); for (i = 0; i < ncbflooders; i++) torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]); - if ((test_boost == 1 && cur_ops->can_boost) || - test_boost == 2) + if (rcu_torture_can_boost()) cpuhp_remove_state(rcutor_hp); /* @@ -1746,7 +1944,7 @@ rcu_torture_init(void) int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, - &sched_ops, &tasks_ops, + &busted_srcud_ops, &sched_ops, &tasks_ops, }; if (!torture_init_begin(torture_type, verbose)) @@ -1763,8 +1961,8 @@ rcu_torture_init(void) torture_type); pr_alert("rcu-torture types:"); for (i = 0; i < ARRAY_SIZE(torture_ops); i++) - pr_alert(" %s", torture_ops[i]->name); - pr_alert("\n"); + pr_cont(" %s", torture_ops[i]->name); + pr_cont("\n"); firsterr = -EINVAL; goto unwind; } @@ -1882,8 +2080,7 @@ rcu_torture_init(void) test_boost_interval = 1; if (test_boost_duration < 2) test_boost_duration = 2; - if ((test_boost == 1 && cur_ops->can_boost) || - test_boost == 2) { + if (rcu_torture_can_boost()) { boost_starttime = jiffies + test_boost_interval * HZ; @@ -1897,7 +2094,7 @@ rcu_torture_init(void) firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup); if (firsterr) goto unwind; - firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ); + firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval); if (firsterr) goto unwind; firsterr = rcu_torture_stall_init(); @@ -1926,7 +2123,6 @@ rcu_torture_init(void) goto unwind; } } - rcutorture_record_test_transition(); torture_init_end(); return 0; diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 622792abe41a..04fc2ed71af8 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -110,7 +110,7 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx) WRITE_ONCE(sp->srcu_lock_nesting[idx], newval); if (!newval && READ_ONCE(sp->srcu_gp_waiting)) - swake_up(&sp->srcu_wq); + swake_up_one(&sp->srcu_wq); } EXPORT_SYMBOL_GPL(__srcu_read_unlock); @@ -140,7 +140,7 @@ void srcu_drive_gp(struct work_struct *wp) idx = sp->srcu_idx; WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx); WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */ - swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx])); + swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx])); WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */ /* Invoke the callbacks we removed above. */ diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index b4123d7a2cec..6c9866a854b1 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -26,6 +26,8 @@ * */ +#define pr_fmt(fmt) "rcu: " fmt + #include <linux/export.h> #include <linux/mutex.h> #include <linux/percpu.h> @@ -390,7 +392,8 @@ void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced) } if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) || WARN_ON(srcu_readers_active(sp))) { - pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq))); + pr_info("%s: Active srcu_struct %p state: %d\n", + __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq))); return; /* Caller forgot to stop doing call_srcu()? */ } free_percpu(sp->sda); @@ -641,6 +644,9 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp, * period s. Losers must either ensure that their desired grace-period * number is recorded on at least their leaf srcu_node structure, or they * must take steps to invoke their own callbacks. + * + * Note that this function also does the work of srcu_funnel_exp_start(), + * in some cases by directly invoking it. */ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp, unsigned long s, bool do_norm) @@ -823,17 +829,17 @@ static void srcu_leak_callback(struct rcu_head *rhp) * more than one CPU, this means that when "func()" is invoked, each CPU * is guaranteed to have executed a full memory barrier since the end of * its last corresponding SRCU read-side critical section whose beginning - * preceded the call to call_rcu(). It also means that each CPU executing + * preceded the call to call_srcu(). It also means that each CPU executing * an SRCU read-side critical section that continues beyond the start of - * "func()" must have executed a memory barrier after the call_rcu() + * "func()" must have executed a memory barrier after the call_srcu() * but before the beginning of that SRCU read-side critical section. * Note that these guarantees include CPUs that are offline, idle, or * executing in user mode, as well as CPUs that are executing in the kernel. * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the + * Furthermore, if CPU A invoked call_srcu() and CPU B invoked the * resulting SRCU callback function "func()", then both CPU A and CPU * B are guaranteed to execute a full memory barrier during the time - * interval between the call to call_rcu() and the invocation of "func()". + * interval between the call to call_srcu() and the invocation of "func()". * This guarantee applies even if CPU A and CPU B are the same CPU (but * again only if the system has more than one CPU). * @@ -1246,13 +1252,12 @@ static void process_srcu(struct work_struct *work) void srcutorture_get_gp_data(enum rcutorture_type test_type, struct srcu_struct *sp, int *flags, - unsigned long *gpnum, unsigned long *completed) + unsigned long *gp_seq) { if (test_type != SRCU_FLAVOR) return; *flags = 0; - *completed = rcu_seq_ctr(sp->srcu_gp_seq); - *gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed); + *gp_seq = rcu_seq_current(&sp->srcu_gp_seq); } EXPORT_SYMBOL_GPL(srcutorture_get_gp_data); @@ -1263,16 +1268,17 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf) unsigned long s0 = 0, s1 = 0; idx = sp->srcu_idx & 0x1; - pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", tt, tf, idx); + pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):", + tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx); for_each_possible_cpu(cpu) { unsigned long l0, l1; unsigned long u0, u1; long c0, c1; - struct srcu_data *counts; + struct srcu_data *sdp; - counts = per_cpu_ptr(sp->sda, cpu); - u0 = counts->srcu_unlock_count[!idx]; - u1 = counts->srcu_unlock_count[idx]; + sdp = per_cpu_ptr(sp->sda, cpu); + u0 = sdp->srcu_unlock_count[!idx]; + u1 = sdp->srcu_unlock_count[idx]; /* * Make sure that a lock is always counted if the corresponding @@ -1280,12 +1286,13 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf) */ smp_rmb(); - l0 = counts->srcu_lock_count[!idx]; - l1 = counts->srcu_lock_count[idx]; + l0 = sdp->srcu_lock_count[!idx]; + l1 = sdp->srcu_lock_count[idx]; c0 = l0 - u0; c1 = l1 - u1; - pr_cont(" %d(%ld,%ld)", cpu, c0, c1); + pr_cont(" %d(%ld,%ld %1p)", + cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist)); s0 += c0; s1 += c1; } diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index a64eee0db39e..befc9321a89c 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -122,10 +122,8 @@ void rcu_check_callbacks(int user) { if (user) rcu_sched_qs(); - else if (!in_softirq()) + if (user || !in_softirq()) rcu_bh_qs(); - if (user) - rcu_note_voluntary_context_switch(current); } /* diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index aa7cade1b9f3..0b760c1369f7 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -27,6 +27,9 @@ * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU */ + +#define pr_fmt(fmt) "rcu: " fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -95,13 +98,13 @@ struct rcu_state sname##_state = { \ .rda = &sname##_data, \ .call = cr, \ .gp_state = RCU_GP_IDLE, \ - .gpnum = 0UL - 300UL, \ - .completed = 0UL - 300UL, \ + .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ .exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \ .exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \ + .ofl_lock = __SPIN_LOCK_UNLOCKED(sname##_state.ofl_lock), \ } RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); @@ -155,6 +158,9 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active); */ static int rcu_scheduler_fully_active __read_mostly; +static void +rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long gps, unsigned long flags); static void rcu_init_new_rnp(struct rcu_node *rnp_leaf); static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); @@ -177,6 +183,13 @@ module_param(gp_init_delay, int, 0444); static int gp_cleanup_delay; module_param(gp_cleanup_delay, int, 0444); +/* Retreive RCU kthreads priority for rcutorture */ +int rcu_get_gp_kthreads_prio(void) +{ + return kthread_prio; +} +EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio); + /* * Number of grace periods between delays, normalized by the duration of * the delay. The longer the delay, the more the grace periods between @@ -189,18 +202,6 @@ module_param(gp_cleanup_delay, int, 0444); #define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */ /* - * Track the rcutorture test sequence number and the update version - * number within a given test. The rcutorture_testseq is incremented - * on every rcutorture module load and unload, so has an odd value - * when a test is running. The rcutorture_vernum is set to zero - * when rcutorture starts and is incremented on each rcutorture update. - * These variables enable correlating rcutorture output with the - * RCU tracing information. - */ -unsigned long rcutorture_testseq; -unsigned long rcutorture_vernum; - -/* * Compute the mask of online CPUs for the specified rcu_node structure. * This will not be stable unless the rcu_node structure's ->lock is * held, but the bit corresponding to the current CPU will be stable @@ -218,7 +219,7 @@ unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) */ static int rcu_gp_in_progress(struct rcu_state *rsp) { - return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum); + return rcu_seq_state(rcu_seq_current(&rsp->gp_seq)); } /* @@ -233,7 +234,7 @@ void rcu_sched_qs(void) if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) return; trace_rcu_grace_period(TPS("rcu_sched"), - __this_cpu_read(rcu_sched_data.gpnum), + __this_cpu_read(rcu_sched_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) @@ -248,7 +249,7 @@ void rcu_bh_qs(void) RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_bh"), - __this_cpu_read(rcu_bh_data.gpnum), + __this_cpu_read(rcu_bh_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); } @@ -380,20 +381,6 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap) } /* - * Do a double-increment of the ->dynticks counter to emulate a - * momentary idle-CPU quiescent state. - */ -static void rcu_dynticks_momentary_idle(void) -{ - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, - &rdtp->dynticks); - - /* It is illegal to call this from idle state. */ - WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); -} - -/* * Set the special (bottom) bit of the specified CPU so that it * will take special action (such as flushing its TLB) on the * next exit from an extended quiescent state. Returns true if @@ -424,12 +411,17 @@ bool rcu_eqs_special_set(int cpu) * * We inform the RCU core by emulating a zero-duration dyntick-idle period. * - * The caller must have disabled interrupts. + * The caller must have disabled interrupts and must not be idle. */ static void rcu_momentary_dyntick_idle(void) { + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + int special; + raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false); - rcu_dynticks_momentary_idle(); + special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks); + /* It is illegal to call this from idle state. */ + WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); } /* @@ -451,7 +443,7 @@ void rcu_note_context_switch(bool preempt) rcu_momentary_dyntick_idle(); this_cpu_inc(rcu_dynticks.rcu_qs_ctr); if (!preempt) - rcu_note_voluntary_context_switch_lite(current); + rcu_tasks_qs(current); out: trace_rcu_utilization(TPS("End context switch")); barrier(); /* Avoid RCU read-side critical sections leaking up. */ @@ -513,8 +505,38 @@ static ulong jiffies_till_first_fqs = ULONG_MAX; static ulong jiffies_till_next_fqs = ULONG_MAX; static bool rcu_kick_kthreads; -module_param(jiffies_till_first_fqs, ulong, 0644); -module_param(jiffies_till_next_fqs, ulong, 0644); +static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp) +{ + ulong j; + int ret = kstrtoul(val, 0, &j); + + if (!ret) + WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j); + return ret; +} + +static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp) +{ + ulong j; + int ret = kstrtoul(val, 0, &j); + + if (!ret) + WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1)); + return ret; +} + +static struct kernel_param_ops first_fqs_jiffies_ops = { + .set = param_set_first_fqs_jiffies, + .get = param_get_ulong, +}; + +static struct kernel_param_ops next_fqs_jiffies_ops = { + .set = param_set_next_fqs_jiffies, + .get = param_get_ulong, +}; + +module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644); +module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644); module_param(rcu_kick_kthreads, bool, 0644); /* @@ -529,58 +551,31 @@ static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(void); /* - * Return the number of RCU batches started thus far for debug & stats. + * Return the number of RCU GPs completed thus far for debug & stats. */ -unsigned long rcu_batches_started(void) +unsigned long rcu_get_gp_seq(void) { - return rcu_state_p->gpnum; + return READ_ONCE(rcu_state_p->gp_seq); } -EXPORT_SYMBOL_GPL(rcu_batches_started); +EXPORT_SYMBOL_GPL(rcu_get_gp_seq); /* - * Return the number of RCU-sched batches started thus far for debug & stats. + * Return the number of RCU-sched GPs completed thus far for debug & stats. */ -unsigned long rcu_batches_started_sched(void) +unsigned long rcu_sched_get_gp_seq(void) { - return rcu_sched_state.gpnum; + return READ_ONCE(rcu_sched_state.gp_seq); } -EXPORT_SYMBOL_GPL(rcu_batches_started_sched); +EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq); /* - * Return the number of RCU BH batches started thus far for debug & stats. + * Return the number of RCU-bh GPs completed thus far for debug & stats. */ -unsigned long rcu_batches_started_bh(void) +unsigned long rcu_bh_get_gp_seq(void) { - return rcu_bh_state.gpnum; + return READ_ONCE(rcu_bh_state.gp_seq); } -EXPORT_SYMBOL_GPL(rcu_batches_started_bh); - -/* - * Return the number of RCU batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed(void) -{ - return rcu_state_p->completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed); - -/* - * Return the number of RCU-sched batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed_sched(void) -{ - return rcu_sched_state.completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); - -/* - * Return the number of RCU BH batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed_bh(void) -{ - return rcu_bh_state.completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); +EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq); /* * Return the number of RCU expedited batches completed thus far for @@ -636,35 +631,42 @@ EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state); */ void show_rcu_gp_kthreads(void) { + int cpu; + struct rcu_data *rdp; + struct rcu_node *rnp; struct rcu_state *rsp; for_each_rcu_flavor(rsp) { pr_info("%s: wait state: %d ->state: %#lx\n", rsp->name, rsp->gp_state, rsp->gp_kthread->state); + rcu_for_each_node_breadth_first(rsp, rnp) { + if (ULONG_CMP_GE(rsp->gp_seq, rnp->gp_seq_needed)) + continue; + pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n", + rnp->grplo, rnp->grphi, rnp->gp_seq, + rnp->gp_seq_needed); + if (!rcu_is_leaf_node(rnp)) + continue; + for_each_leaf_node_possible_cpu(rnp, cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + if (rdp->gpwrap || + ULONG_CMP_GE(rsp->gp_seq, + rdp->gp_seq_needed)) + continue; + pr_info("\tcpu %d ->gp_seq_needed %lu\n", + cpu, rdp->gp_seq_needed); + } + } /* sched_show_task(rsp->gp_kthread); */ } } EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); /* - * Record the number of times rcutorture tests have been initiated and - * terminated. This information allows the debugfs tracing stats to be - * correlated to the rcutorture messages, even when the rcutorture module - * is being repeatedly loaded and unloaded. In other words, we cannot - * store this state in rcutorture itself. - */ -void rcutorture_record_test_transition(void) -{ - rcutorture_testseq++; - rcutorture_vernum = 0; -} -EXPORT_SYMBOL_GPL(rcutorture_record_test_transition); - -/* * Send along grace-period-related data for rcutorture diagnostics. */ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gpnum, unsigned long *completed) + unsigned long *gp_seq) { struct rcu_state *rsp = NULL; @@ -684,23 +686,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, if (rsp == NULL) return; *flags = READ_ONCE(rsp->gp_flags); - *gpnum = READ_ONCE(rsp->gpnum); - *completed = READ_ONCE(rsp->completed); + *gp_seq = rcu_seq_current(&rsp->gp_seq); } EXPORT_SYMBOL_GPL(rcutorture_get_gp_data); /* - * Record the number of writer passes through the current rcutorture test. - * This is also used to correlate debugfs tracing stats with the rcutorture - * messages. - */ -void rcutorture_record_progress(unsigned long vernum) -{ - rcutorture_vernum++; -} -EXPORT_SYMBOL_GPL(rcutorture_record_progress); - -/* * Return the root node of the specified rcu_state structure. */ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) @@ -1059,41 +1049,41 @@ void rcu_request_urgent_qs_task(struct task_struct *t) #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* - * Is the current CPU online? Disable preemption to avoid false positives - * that could otherwise happen due to the current CPU number being sampled, - * this task being preempted, its old CPU being taken offline, resuming - * on some other CPU, then determining that its old CPU is now offline. - * It is OK to use RCU on an offline processor during initial boot, hence - * the check for rcu_scheduler_fully_active. Note also that it is OK - * for a CPU coming online to use RCU for one jiffy prior to marking itself - * online in the cpu_online_mask. Similarly, it is OK for a CPU going - * offline to continue to use RCU for one jiffy after marking itself - * offline in the cpu_online_mask. This leniency is necessary given the - * non-atomic nature of the online and offline processing, for example, - * the fact that a CPU enters the scheduler after completing the teardown - * of the CPU. + * Is the current CPU online as far as RCU is concerned? * - * This is also why RCU internally marks CPUs online during in the - * preparation phase and offline after the CPU has been taken down. + * Disable preemption to avoid false positives that could otherwise + * happen due to the current CPU number being sampled, this task being + * preempted, its old CPU being taken offline, resuming on some other CPU, + * then determining that its old CPU is now offline. Because there are + * multiple flavors of RCU, and because this function can be called in the + * midst of updating the flavors while a given CPU coming online or going + * offline, it is necessary to check all flavors. If any of the flavors + * believe that given CPU is online, it is considered to be online. * - * Disable checking if in an NMI handler because we cannot safely report - * errors from NMI handlers anyway. + * Disable checking if in an NMI handler because we cannot safely + * report errors from NMI handlers anyway. In addition, it is OK to use + * RCU on an offline processor during initial boot, hence the check for + * rcu_scheduler_fully_active. */ bool rcu_lockdep_current_cpu_online(void) { struct rcu_data *rdp; struct rcu_node *rnp; - bool ret; + struct rcu_state *rsp; - if (in_nmi()) + if (in_nmi() || !rcu_scheduler_fully_active) return true; preempt_disable(); - rdp = this_cpu_ptr(&rcu_sched_data); - rnp = rdp->mynode; - ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) || - !rcu_scheduler_fully_active; + for_each_rcu_flavor(rsp) { + rdp = this_cpu_ptr(rsp->rda); + rnp = rdp->mynode; + if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) { + preempt_enable(); + return true; + } + } preempt_enable(); - return ret; + return false; } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); @@ -1115,17 +1105,18 @@ static int rcu_is_cpu_rrupt_from_idle(void) /* * We are reporting a quiescent state on behalf of some other CPU, so * it is our responsibility to check for and handle potential overflow - * of the rcu_node ->gpnum counter with respect to the rcu_data counters. + * of the rcu_node ->gp_seq counter with respect to the rcu_data counters. * After all, the CPU might be in deep idle state, and thus executing no * code whatsoever. */ static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp) { raw_lockdep_assert_held_rcu_node(rnp); - if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum)) + if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4, + rnp->gp_seq)) WRITE_ONCE(rdp->gpwrap, true); - if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum)) - rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4; + if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq)) + rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4; } /* @@ -1137,7 +1128,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) { rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti")); rcu_gpnum_ovf(rdp->mynode, rdp); return 1; } @@ -1159,7 +1150,7 @@ static void rcu_iw_handler(struct irq_work *iwp) rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) { - rdp->rcu_iw_gpnum = rnp->gpnum; + rdp->rcu_iw_gp_seq = rnp->gp_seq; rdp->rcu_iw_pending = false; } raw_spin_unlock_rcu_node(rnp); @@ -1187,7 +1178,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * of the current RCU grace period. */ if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti")); rdp->dynticks_fqs++; rcu_gpnum_ovf(rnp, rdp); return 1; @@ -1203,8 +1194,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu); if (time_after(jiffies, rdp->rsp->gp_start + jtsq) && READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) && - READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc")); + rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) { + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc")); rcu_gpnum_ovf(rnp, rdp); return 1; } else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) { @@ -1212,12 +1203,25 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) smp_store_release(ruqp, true); } - /* Check for the CPU being offline. */ - if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl")); - rdp->offline_fqs++; - rcu_gpnum_ovf(rnp, rdp); - return 1; + /* If waiting too long on an offline CPU, complain. */ + if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) && + time_after(jiffies, rdp->rsp->gp_start + HZ)) { + bool onl; + struct rcu_node *rnp1; + + WARN_ON(1); /* Offline CPUs are supposed to report QS! */ + pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n", + __func__, rnp->grplo, rnp->grphi, rnp->level, + (long)rnp->gp_seq, (long)rnp->completedqs); + for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent) + pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n", + __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask); + onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp)); + pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n", + __func__, rdp->cpu, ".o"[onl], + (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, + (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); + return 1; /* Break things loose after complaining. */ } /* @@ -1256,11 +1260,11 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) { resched_cpu(rdp->cpu); if (IS_ENABLED(CONFIG_IRQ_WORK) && - !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum && + !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq && (rnp->ffmask & rdp->grpmask)) { init_irq_work(&rdp->rcu_iw, rcu_iw_handler); rdp->rcu_iw_pending = true; - rdp->rcu_iw_gpnum = rnp->gpnum; + rdp->rcu_iw_gp_seq = rnp->gp_seq; irq_work_queue_on(&rdp->rcu_iw, rdp->cpu); } } @@ -1274,9 +1278,9 @@ static void record_gp_stall_check_time(struct rcu_state *rsp) unsigned long j1; rsp->gp_start = j; - smp_wmb(); /* Record start time before stall time. */ j1 = rcu_jiffies_till_stall_check(); - WRITE_ONCE(rsp->jiffies_stall, j + j1); + /* Record ->gp_start before ->jiffies_stall. */ + smp_store_release(&rsp->jiffies_stall, j + j1); /* ^^^ */ rsp->jiffies_resched = j + j1 / 2; rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs); } @@ -1302,9 +1306,9 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) j = jiffies; gpa = READ_ONCE(rsp->gp_activity); if (j - gpa > 2 * HZ) { - pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx ->cpu=%d\n", + pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n", rsp->name, j - gpa, - rsp->gpnum, rsp->completed, + (long)rcu_seq_current(&rsp->gp_seq), rsp->gp_flags, gp_state_getname(rsp->gp_state), rsp->gp_state, rsp->gp_kthread ? rsp->gp_kthread->state : ~0, @@ -1359,16 +1363,15 @@ static void rcu_stall_kick_kthreads(struct rcu_state *rsp) } } -static inline void panic_on_rcu_stall(void) +static void panic_on_rcu_stall(void) { if (sysctl_panic_on_rcu_stall) panic("RCU Stall\n"); } -static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) +static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq) { int cpu; - long delta; unsigned long flags; unsigned long gpa; unsigned long j; @@ -1381,25 +1384,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) if (rcu_cpu_stall_suppress) return; - /* Only let one CPU complain about others per time interval. */ - - raw_spin_lock_irqsave_rcu_node(rnp, flags); - delta = jiffies - READ_ONCE(rsp->jiffies_stall); - if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - return; - } - WRITE_ONCE(rsp->jiffies_stall, - jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - /* * OK, time to rat on our buddy... * See Documentation/RCU/stallwarn.txt for info on how to debug * RCU CPU stall warnings. */ - pr_err("INFO: %s detected stalls on CPUs/tasks:", - rsp->name); + pr_err("INFO: %s detected stalls on CPUs/tasks:", rsp->name); print_cpu_stall_info_begin(); rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -1418,17 +1408,16 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) for_each_possible_cpu(cpu) totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, cpu)->cblist); - pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n", + pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n", smp_processor_id(), (long)(jiffies - rsp->gp_start), - (long)rsp->gpnum, (long)rsp->completed, totqlen); + (long)rcu_seq_current(&rsp->gp_seq), totqlen); if (ndetected) { rcu_dump_cpu_stacks(rsp); /* Complain about tasks blocking the grace period. */ rcu_print_detail_task_stall(rsp); } else { - if (READ_ONCE(rsp->gpnum) != gpnum || - READ_ONCE(rsp->completed) == gpnum) { + if (rcu_seq_current(&rsp->gp_seq) != gp_seq) { pr_err("INFO: Stall ended before state dump start\n"); } else { j = jiffies; @@ -1441,6 +1430,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) sched_show_task(current); } } + /* Rewrite if needed in case of slow consoles. */ + if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) + WRITE_ONCE(rsp->jiffies_stall, + jiffies + 3 * rcu_jiffies_till_stall_check() + 3); rcu_check_gp_kthread_starvation(rsp); @@ -1476,15 +1469,16 @@ static void print_cpu_stall(struct rcu_state *rsp) for_each_possible_cpu(cpu) totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, cpu)->cblist); - pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n", + pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n", jiffies - rsp->gp_start, - (long)rsp->gpnum, (long)rsp->completed, totqlen); + (long)rcu_seq_current(&rsp->gp_seq), totqlen); rcu_check_gp_kthread_starvation(rsp); rcu_dump_cpu_stacks(rsp); raw_spin_lock_irqsave_rcu_node(rnp, flags); + /* Rewrite if needed in case of slow consoles. */ if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) WRITE_ONCE(rsp->jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); @@ -1504,10 +1498,11 @@ static void print_cpu_stall(struct rcu_state *rsp) static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) { - unsigned long completed; - unsigned long gpnum; + unsigned long gs1; + unsigned long gs2; unsigned long gps; unsigned long j; + unsigned long jn; unsigned long js; struct rcu_node *rnp; @@ -1520,43 +1515,46 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) /* * Lots of memory barriers to reject false positives. * - * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall, - * then rsp->gp_start, and finally rsp->completed. These values - * are updated in the opposite order with memory barriers (or - * equivalent) during grace-period initialization and cleanup. - * Now, a false positive can occur if we get an new value of - * rsp->gp_start and a old value of rsp->jiffies_stall. But given - * the memory barriers, the only way that this can happen is if one - * grace period ends and another starts between these two fetches. - * Detect this by comparing rsp->completed with the previous fetch - * from rsp->gpnum. + * The idea is to pick up rsp->gp_seq, then rsp->jiffies_stall, + * then rsp->gp_start, and finally another copy of rsp->gp_seq. + * These values are updated in the opposite order with memory + * barriers (or equivalent) during grace-period initialization + * and cleanup. Now, a false positive can occur if we get an new + * value of rsp->gp_start and a old value of rsp->jiffies_stall. + * But given the memory barriers, the only way that this can happen + * is if one grace period ends and another starts between these + * two fetches. This is detected by comparing the second fetch + * of rsp->gp_seq with the previous fetch from rsp->gp_seq. * * Given this check, comparisons of jiffies, rsp->jiffies_stall, * and rsp->gp_start suffice to forestall false positives. */ - gpnum = READ_ONCE(rsp->gpnum); - smp_rmb(); /* Pick up ->gpnum first... */ + gs1 = READ_ONCE(rsp->gp_seq); + smp_rmb(); /* Pick up ->gp_seq first... */ js = READ_ONCE(rsp->jiffies_stall); smp_rmb(); /* ...then ->jiffies_stall before the rest... */ gps = READ_ONCE(rsp->gp_start); - smp_rmb(); /* ...and finally ->gp_start before ->completed. */ - completed = READ_ONCE(rsp->completed); - if (ULONG_CMP_GE(completed, gpnum) || + smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */ + gs2 = READ_ONCE(rsp->gp_seq); + if (gs1 != gs2 || ULONG_CMP_LT(j, js) || ULONG_CMP_GE(gps, js)) return; /* No stall or GP completed since entering function. */ rnp = rdp->mynode; + jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; if (rcu_gp_in_progress(rsp) && - (READ_ONCE(rnp->qsmask) & rdp->grpmask)) { + (READ_ONCE(rnp->qsmask) & rdp->grpmask) && + cmpxchg(&rsp->jiffies_stall, js, jn) == js) { /* We haven't checked in, so go dump stack. */ print_cpu_stall(rsp); } else if (rcu_gp_in_progress(rsp) && - ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) { + ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) && + cmpxchg(&rsp->jiffies_stall, js, jn) == js) { /* They had a few time units to dump stack, so complain. */ - print_other_cpu_stall(rsp, gpnum); + print_other_cpu_stall(rsp, gs2); } } @@ -1577,123 +1575,99 @@ void rcu_cpu_stall_reset(void) WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2); } -/* - * Determine the value that ->completed will have at the end of the - * next subsequent grace period. This is used to tag callbacks so that - * a CPU can invoke callbacks in a timely fashion even if that CPU has - * been dyntick-idle for an extended period with callbacks under the - * influence of RCU_FAST_NO_HZ. - * - * The caller must hold rnp->lock with interrupts disabled. - */ -static unsigned long rcu_cbs_completed(struct rcu_state *rsp, - struct rcu_node *rnp) -{ - raw_lockdep_assert_held_rcu_node(rnp); - - /* - * If RCU is idle, we just wait for the next grace period. - * But we can only be sure that RCU is idle if we are looking - * at the root rcu_node structure -- otherwise, a new grace - * period might have started, but just not yet gotten around - * to initializing the current non-root rcu_node structure. - */ - if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed) - return rnp->completed + 1; - - /* - * If the current rcu_node structure believes that RCU is - * idle, and if the rcu_state structure does not yet reflect - * the start of a new grace period, then the next grace period - * will suffice. The memory barrier is needed to accurately - * sample the rsp->gpnum, and pairs with the second lock - * acquisition in rcu_gp_init(), which is augmented with - * smp_mb__after_unlock_lock() for this purpose. - */ - if (rnp->gpnum == rnp->completed) { - smp_mb(); /* See above block comment. */ - if (READ_ONCE(rsp->gpnum) == rnp->completed) - return rnp->completed + 1; - } - - /* - * Otherwise, wait for a possible partial grace period and - * then the subsequent full grace period. - */ - return rnp->completed + 2; -} - /* Trace-event wrapper function for trace_rcu_future_grace_period. */ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c, const char *s) + unsigned long gp_seq_req, const char *s) { - trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum, - rnp->completed, c, rnp->level, - rnp->grplo, rnp->grphi, s); + trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req, + rnp->level, rnp->grplo, rnp->grphi, s); } /* + * rcu_start_this_gp - Request the start of a particular grace period + * @rnp_start: The leaf node of the CPU from which to start. + * @rdp: The rcu_data corresponding to the CPU from which to start. + * @gp_seq_req: The gp_seq of the grace period to start. + * * Start the specified grace period, as needed to handle newly arrived * callbacks. The required future grace periods are recorded in each - * rcu_node structure's ->need_future_gp[] field. Returns true if there + * rcu_node structure's ->gp_seq_needed field. Returns true if there * is reason to awaken the grace-period kthread. * * The caller must hold the specified rcu_node structure's ->lock, which * is why the caller is responsible for waking the grace-period kthread. + * + * Returns true if the GP thread needs to be awakened else false. */ -static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c) +static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp, + unsigned long gp_seq_req) { bool ret = false; struct rcu_state *rsp = rdp->rsp; - struct rcu_node *rnp_root; + struct rcu_node *rnp; /* * Use funnel locking to either acquire the root rcu_node * structure's lock or bail out if the need for this grace period - * has already been recorded -- or has already started. If there - * is already a grace period in progress in a non-leaf node, no - * recording is needed because the end of the grace period will - * scan the leaf rcu_node structures. Note that rnp->lock must - * not be released. + * has already been recorded -- or if that grace period has in + * fact already started. If there is already a grace period in + * progress in a non-leaf node, no recording is needed because the + * end of the grace period will scan the leaf rcu_node structures. + * Note that rnp_start->lock must not be released. */ - raw_lockdep_assert_held_rcu_node(rnp); - trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf")); - for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) { - if (rnp_root != rnp) - raw_spin_lock_rcu_node(rnp_root); - WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum + - need_future_gp_mask(), c)); - if (need_future_gp_element(rnp_root, c) || - ULONG_CMP_GE(rnp_root->gpnum, c) || - (rnp != rnp_root && - rnp_root->gpnum != rnp_root->completed)) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted")); + raw_lockdep_assert_held_rcu_node(rnp_start); + trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf")); + for (rnp = rnp_start; 1; rnp = rnp->parent) { + if (rnp != rnp_start) + raw_spin_lock_rcu_node(rnp); + if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) || + rcu_seq_started(&rnp->gp_seq, gp_seq_req) || + (rnp != rnp_start && + rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) { + trace_rcu_this_gp(rnp, rdp, gp_seq_req, + TPS("Prestarted")); goto unlock_out; } - need_future_gp_element(rnp_root, c) = true; - if (rnp_root != rnp && rnp_root->parent != NULL) - raw_spin_unlock_rcu_node(rnp_root); - if (!rnp_root->parent) + rnp->gp_seq_needed = gp_seq_req; + if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) { + /* + * We just marked the leaf or internal node, and a + * grace period is in progress, which means that + * rcu_gp_cleanup() will see the marking. Bail to + * reduce contention. + */ + trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, + TPS("Startedleaf")); + goto unlock_out; + } + if (rnp != rnp_start && rnp->parent != NULL) + raw_spin_unlock_rcu_node(rnp); + if (!rnp->parent) break; /* At root, and perhaps also leaf. */ } /* If GP already in progress, just leave, otherwise start one. */ - if (rnp_root->gpnum != rnp_root->completed) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot")); + if (rcu_gp_in_progress(rsp)) { + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot")); goto unlock_out; } - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot")); + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot")); WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT); + rsp->gp_req_activity = jiffies; if (!rsp->gp_kthread) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread")); + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread")); goto unlock_out; } - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq")); + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq")); ret = true; /* Caller must wake GP kthread. */ unlock_out: - if (rnp != rnp_root) - raw_spin_unlock_rcu_node(rnp_root); + /* Push furthest requested GP to leaf node and rcu_data structure. */ + if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) { + rnp_start->gp_seq_needed = rnp->gp_seq_needed; + rdp->gp_seq_needed = rnp->gp_seq_needed; + } + if (rnp != rnp_start) + raw_spin_unlock_rcu_node(rnp); return ret; } @@ -1703,13 +1677,13 @@ unlock_out: */ static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { - unsigned long c = rnp->completed; bool needmore; struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - need_future_gp_element(rnp, c) = false; - needmore = need_any_future_gp(rnp); - trace_rcu_this_gp(rnp, rdp, c, + needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed); + if (!needmore) + rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */ + trace_rcu_this_gp(rnp, rdp, rnp->gp_seq, needmore ? TPS("CleanupMore") : TPS("Cleanup")); return needmore; } @@ -1727,25 +1701,25 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp) !READ_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; - swake_up(&rsp->gp_wq); + swake_up_one(&rsp->gp_wq); } /* - * If there is room, assign a ->completed number to any callbacks on - * this CPU that have not already been assigned. Also accelerate any - * callbacks that were previously assigned a ->completed number that has - * since proven to be too conservative, which can happen if callbacks get - * assigned a ->completed number while RCU is idle, but with reference to - * a non-root rcu_node structure. This function is idempotent, so it does - * not hurt to call it repeatedly. Returns an flag saying that we should - * awaken the RCU grace-period kthread. + * If there is room, assign a ->gp_seq number to any callbacks on this + * CPU that have not already been assigned. Also accelerate any callbacks + * that were previously assigned a ->gp_seq number that has since proven + * to be too conservative, which can happen if callbacks get assigned a + * ->gp_seq number while RCU is idle, but with reference to a non-root + * rcu_node structure. This function is idempotent, so it does not hurt + * to call it repeatedly. Returns an flag saying that we should awaken + * the RCU grace-period kthread. * * The caller must hold rnp->lock with interrupts disabled. */ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { - unsigned long c; + unsigned long gp_seq_req; bool ret = false; raw_lockdep_assert_held_rcu_node(rnp); @@ -1764,22 +1738,50 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * accelerating callback invocation to an earlier grace-period * number. */ - c = rcu_cbs_completed(rsp, rnp); - if (rcu_segcblist_accelerate(&rdp->cblist, c)) - ret = rcu_start_this_gp(rnp, rdp, c); + gp_seq_req = rcu_seq_snap(&rsp->gp_seq); + if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req)) + ret = rcu_start_this_gp(rnp, rdp, gp_seq_req); /* Trace depending on how much we were able to accelerate. */ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL)) - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB")); + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB")); else - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB")); + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB")); return ret; } /* + * Similar to rcu_accelerate_cbs(), but does not require that the leaf + * rcu_node structure's ->lock be held. It consults the cached value + * of ->gp_seq_needed in the rcu_data structure, and if that indicates + * that a new grace-period request be made, invokes rcu_accelerate_cbs() + * while holding the leaf rcu_node structure's ->lock. + */ +static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp, + struct rcu_node *rnp, + struct rcu_data *rdp) +{ + unsigned long c; + bool needwake; + + lockdep_assert_irqs_disabled(); + c = rcu_seq_snap(&rsp->gp_seq); + if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { + /* Old request still live, so mark recent callbacks. */ + (void)rcu_segcblist_accelerate(&rdp->cblist, c); + return; + } + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ + if (needwake) + rcu_gp_kthread_wake(rsp); +} + +/* * Move any callbacks whose grace period has completed to the * RCU_DONE_TAIL sublist, then compact the remaining sublists and - * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL + * assign ->gp_seq numbers to any callbacks in the RCU_NEXT_TAIL * sublist. This function is idempotent, so it does not hurt to * invoke it repeatedly. As long as it is not invoked -too- often... * Returns true if the RCU grace-period kthread needs to be awakened. @@ -1796,10 +1798,10 @@ static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, return false; /* - * Find all callbacks whose ->completed numbers indicate that they + * Find all callbacks whose ->gp_seq numbers indicate that they * are ready to invoke, and put them into the RCU_DONE_TAIL sublist. */ - rcu_segcblist_advance(&rdp->cblist, rnp->completed); + rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq); /* Classify any remaining callbacks. */ return rcu_accelerate_cbs(rsp, rnp, rdp); @@ -1819,39 +1821,38 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, raw_lockdep_assert_held_rcu_node(rnp); - /* Handle the ends of any preceding grace periods first. */ - if (rdp->completed == rnp->completed && - !unlikely(READ_ONCE(rdp->gpwrap))) { - - /* No grace period end, so just accelerate recent callbacks. */ - ret = rcu_accelerate_cbs(rsp, rnp, rdp); + if (rdp->gp_seq == rnp->gp_seq) + return false; /* Nothing to do. */ + /* Handle the ends of any preceding grace periods first. */ + if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) || + unlikely(READ_ONCE(rdp->gpwrap))) { + ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */ + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend")); } else { - - /* Advance callbacks. */ - ret = rcu_advance_cbs(rsp, rnp, rdp); - - /* Remember that we saw this grace-period completion. */ - rdp->completed = rnp->completed; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend")); + ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */ } - if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) { + /* Now handle the beginnings of any new-to-this-CPU grace periods. */ + if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) || + unlikely(READ_ONCE(rdp->gpwrap))) { /* * If the current grace period is waiting for this CPU, * set up to detect a quiescent state, otherwise don't * go looking for one. */ - rdp->gpnum = rnp->gpnum; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); + trace_rcu_grace_period(rsp->name, rnp->gp_seq, TPS("cpustart")); need_gp = !!(rnp->qsmask & rdp->grpmask); rdp->cpu_no_qs.b.norm = need_gp; rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr); rdp->core_needs_qs = need_gp; zero_cpu_stall_ticks(rdp); - WRITE_ONCE(rdp->gpwrap, false); - rcu_gpnum_ovf(rnp, rdp); } + rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */ + if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap) + rdp->gp_seq_needed = rnp->gp_seq_needed; + WRITE_ONCE(rdp->gpwrap, false); + rcu_gpnum_ovf(rnp, rdp); return ret; } @@ -1863,8 +1864,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_save(flags); rnp = rdp->mynode; - if ((rdp->gpnum == READ_ONCE(rnp->gpnum) && - rdp->completed == READ_ONCE(rnp->completed) && + if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) && !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */ !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */ local_irq_restore(flags); @@ -1879,7 +1879,8 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) static void rcu_gp_slow(struct rcu_state *rsp, int delay) { if (delay > 0 && - !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) + !(rcu_seq_ctr(rsp->gp_seq) % + (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) schedule_timeout_uninterruptible(delay); } @@ -1888,7 +1889,9 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay) */ static bool rcu_gp_init(struct rcu_state *rsp) { + unsigned long flags; unsigned long oldmask; + unsigned long mask; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); @@ -1912,9 +1915,9 @@ static bool rcu_gp_init(struct rcu_state *rsp) /* Advance to a new grace period and initialize state. */ record_gp_stall_check_time(rsp); - /* Record GP times before starting GP, hence smp_store_release(). */ - smp_store_release(&rsp->gpnum, rsp->gpnum + 1); - trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); + /* Record GP times before starting GP, hence rcu_seq_start(). */ + rcu_seq_start(&rsp->gp_seq); + trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start")); raw_spin_unlock_irq_rcu_node(rnp); /* @@ -1923,13 +1926,15 @@ static bool rcu_gp_init(struct rcu_state *rsp) * for subsequent online CPUs, and that quiescent-state forcing * will handle subsequent offline CPUs. */ + rsp->gp_state = RCU_GP_ONOFF; rcu_for_each_leaf_node(rsp, rnp) { - rcu_gp_slow(rsp, gp_preinit_delay); + spin_lock(&rsp->ofl_lock); raw_spin_lock_irq_rcu_node(rnp); if (rnp->qsmaskinit == rnp->qsmaskinitnext && !rnp->wait_blkd_tasks) { /* Nothing to do on this leaf rcu_node structure. */ raw_spin_unlock_irq_rcu_node(rnp); + spin_unlock(&rsp->ofl_lock); continue; } @@ -1939,12 +1944,14 @@ static bool rcu_gp_init(struct rcu_state *rsp) /* If zero-ness of ->qsmaskinit changed, propagate up tree. */ if (!oldmask != !rnp->qsmaskinit) { - if (!oldmask) /* First online CPU for this rcu_node. */ - rcu_init_new_rnp(rnp); - else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */ - rnp->wait_blkd_tasks = true; - else /* Last offline CPU and can propagate. */ + if (!oldmask) { /* First online CPU for rcu_node. */ + if (!rnp->wait_blkd_tasks) /* Ever offline? */ + rcu_init_new_rnp(rnp); + } else if (rcu_preempt_has_tasks(rnp)) { + rnp->wait_blkd_tasks = true; /* blocked tasks */ + } else { /* Last offline CPU and can propagate. */ rcu_cleanup_dead_rnp(rnp); + } } /* @@ -1953,18 +1960,19 @@ static bool rcu_gp_init(struct rcu_state *rsp) * still offline, propagate up the rcu_node tree and * clear ->wait_blkd_tasks. Otherwise, if one of this * rcu_node structure's CPUs has since come back online, - * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp() - * checks for this, so just call it unconditionally). + * simply clear ->wait_blkd_tasks. */ if (rnp->wait_blkd_tasks && - (!rcu_preempt_has_tasks(rnp) || - rnp->qsmaskinit)) { + (!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) { rnp->wait_blkd_tasks = false; - rcu_cleanup_dead_rnp(rnp); + if (!rnp->qsmaskinit) + rcu_cleanup_dead_rnp(rnp); } raw_spin_unlock_irq_rcu_node(rnp); + spin_unlock(&rsp->ofl_lock); } + rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */ /* * Set the quiescent-state-needed bits in all the rcu_node @@ -1978,22 +1986,27 @@ static bool rcu_gp_init(struct rcu_state *rsp) * The grace period cannot complete until the initialization * process finishes, because this kthread handles both. */ + rsp->gp_state = RCU_GP_INIT; rcu_for_each_node_breadth_first(rsp, rnp) { rcu_gp_slow(rsp, gp_init_delay); - raw_spin_lock_irq_rcu_node(rnp); + raw_spin_lock_irqsave_rcu_node(rnp, flags); rdp = this_cpu_ptr(rsp->rda); - rcu_preempt_check_blocked_tasks(rnp); + rcu_preempt_check_blocked_tasks(rsp, rnp); rnp->qsmask = rnp->qsmaskinit; - WRITE_ONCE(rnp->gpnum, rsp->gpnum); - if (WARN_ON_ONCE(rnp->completed != rsp->completed)) - WRITE_ONCE(rnp->completed, rsp->completed); + WRITE_ONCE(rnp->gp_seq, rsp->gp_seq); if (rnp == rdp->mynode) (void)__note_gp_changes(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); - trace_rcu_grace_period_init(rsp->name, rnp->gpnum, + trace_rcu_grace_period_init(rsp->name, rnp->gp_seq, rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); - raw_spin_unlock_irq_rcu_node(rnp); + /* Quiescent states for tasks on any now-offline CPUs. */ + mask = rnp->qsmask & ~rnp->qsmaskinitnext; + rnp->rcu_gp_init_mask = mask; + if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp)) + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + else + raw_spin_unlock_irq_rcu_node(rnp); cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); } @@ -2002,7 +2015,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) } /* - * Helper function for swait_event_idle() wakeup at force-quiescent-state + * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state * time. */ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) @@ -2053,6 +2066,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) { unsigned long gp_duration; bool needgp = false; + unsigned long new_gp_seq; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); struct swait_queue_head *sq; @@ -2074,19 +2088,22 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) raw_spin_unlock_irq_rcu_node(rnp); /* - * Propagate new ->completed value to rcu_node structures so - * that other CPUs don't have to wait until the start of the next - * grace period to process their callbacks. This also avoids - * some nasty RCU grace-period initialization races by forcing - * the end of the current grace period to be completely recorded in - * all of the rcu_node structures before the beginning of the next - * grace period is recorded in any of the rcu_node structures. + * Propagate new ->gp_seq value to rcu_node structures so that + * other CPUs don't have to wait until the start of the next grace + * period to process their callbacks. This also avoids some nasty + * RCU grace-period initialization races by forcing the end of + * the current grace period to be completely recorded in all of + * the rcu_node structures before the beginning of the next grace + * period is recorded in any of the rcu_node structures. */ + new_gp_seq = rsp->gp_seq; + rcu_seq_end(&new_gp_seq); rcu_for_each_node_breadth_first(rsp, rnp) { raw_spin_lock_irq_rcu_node(rnp); - WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); + if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) + dump_blkd_tasks(rsp, rnp, 10); WARN_ON_ONCE(rnp->qsmask); - WRITE_ONCE(rnp->completed, rsp->gpnum); + WRITE_ONCE(rnp->gp_seq, new_gp_seq); rdp = this_cpu_ptr(rsp->rda); if (rnp == rdp->mynode) needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; @@ -2100,26 +2117,28 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) rcu_gp_slow(rsp, gp_cleanup_delay); } rnp = rcu_get_root(rsp); - raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */ + raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */ /* Declare grace period done. */ - WRITE_ONCE(rsp->completed, rsp->gpnum); - trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); + rcu_seq_end(&rsp->gp_seq); + trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end")); rsp->gp_state = RCU_GP_IDLE; /* Check for GP requests since above loop. */ rdp = this_cpu_ptr(rsp->rda); - if (need_any_future_gp(rnp)) { - trace_rcu_this_gp(rnp, rdp, rsp->completed - 1, + if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) { + trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed, TPS("CleanupMore")); needgp = true; } /* Advance CBs to reduce false positives below. */ if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) { WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), + rsp->gp_req_activity = jiffies; + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq")); + } else { + WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT); } - WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT); raw_spin_unlock_irq_rcu_node(rnp); } @@ -2141,10 +2160,10 @@ static int __noreturn rcu_gp_kthread(void *arg) /* Handle grace-period start. */ for (;;) { trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("reqwait")); rsp->gp_state = RCU_GP_WAIT_GPS; - swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & + swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); rsp->gp_state = RCU_GP_DONE_GPS; /* Locking provides needed memory barrier. */ @@ -2154,17 +2173,13 @@ static int __noreturn rcu_gp_kthread(void *arg) WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("reqwaitsig")); } /* Handle quiescent-state forcing. */ first_gp_fqs = true; j = jiffies_till_first_fqs; - if (j > HZ) { - j = HZ; - jiffies_till_first_fqs = HZ; - } ret = 0; for (;;) { if (!ret) { @@ -2173,10 +2188,10 @@ static int __noreturn rcu_gp_kthread(void *arg) jiffies + 3 * j); } trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; - ret = swait_event_idle_timeout(rsp->gp_wq, + ret = swait_event_idle_timeout_exclusive(rsp->gp_wq, rcu_gp_fqs_check_wake(rsp, &gf), j); rsp->gp_state = RCU_GP_DOING_FQS; /* Locking provides needed memory barriers. */ @@ -2188,31 +2203,24 @@ static int __noreturn rcu_gp_kthread(void *arg) if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) || (gf & RCU_GP_FLAG_FQS)) { trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqsstart")); rcu_gp_fqs(rsp, first_gp_fqs); first_gp_fqs = false; trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqsend")); cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); ret = 0; /* Force full wait till next FQS. */ j = jiffies_till_next_fqs; - if (j > HZ) { - j = HZ; - jiffies_till_next_fqs = HZ; - } else if (j < 1) { - j = 1; - jiffies_till_next_fqs = 1; - } } else { /* Deal with stray signal. */ cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqswaitsig")); ret = 1; /* Keep old FQS timing. */ j = jiffies; @@ -2256,8 +2264,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) * must be represented by the same rcu_node structure (which need not be a * leaf rcu_node structure, though it often will be). The gps parameter * is the grace-period snapshot, which means that the quiescent states - * are valid only if rnp->gpnum is equal to gps. That structure's lock + * are valid only if rnp->gp_seq is equal to gps. That structure's lock * must be held upon entry, and it is released before return. + * + * As a special case, if mask is zero, the bit-already-cleared check is + * disabled. This allows propagating quiescent state due to resumed tasks + * during grace-period initialization. */ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, @@ -2271,7 +2283,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, /* Walk up the rcu_node hierarchy. */ for (;;) { - if (!(rnp->qsmask & mask) || rnp->gpnum != gps) { + if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) { /* * Our bit has already been cleared, or the @@ -2284,7 +2296,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, WARN_ON_ONCE(!rcu_is_leaf_node(rnp) && rcu_preempt_blocked_readers_cgp(rnp)); rnp->qsmask &= ~mask; - trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum, + trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq, mask, rnp->qsmask, rnp->level, rnp->grplo, rnp->grphi, !!rnp->gp_tasks); @@ -2294,6 +2306,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } + rnp->completedqs = rnp->gp_seq; mask = rnp->grpmask; if (rnp->parent == NULL) { @@ -2323,8 +2336,9 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, * irqs disabled, and this lock is released upon return, but irqs remain * disabled. */ -static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, - struct rcu_node *rnp, unsigned long flags) +static void __maybe_unused +rcu_report_unblock_qs_rnp(struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { unsigned long gps; @@ -2332,12 +2346,15 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, struct rcu_node *rnp_p; raw_lockdep_assert_held_rcu_node(rnp); - if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || - rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { + if (WARN_ON_ONCE(rcu_state_p == &rcu_sched_state) || + WARN_ON_ONCE(rsp != rcu_state_p) || + WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) || + rnp->qsmask != 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; /* Still need more quiescent states! */ } + rnp->completedqs = rnp->gp_seq; rnp_p = rnp->parent; if (rnp_p == NULL) { /* @@ -2348,8 +2365,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, return; } - /* Report up the rest of the hierarchy, tracking current ->gpnum. */ - gps = rnp->gpnum; + /* Report up the rest of the hierarchy, tracking current ->gp_seq. */ + gps = rnp->gp_seq; mask = rnp->grpmask; raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */ @@ -2370,8 +2387,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) rnp = rdp->mynode; raw_spin_lock_irqsave_rcu_node(rnp, flags); - if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum || - rnp->completed == rnp->gpnum || rdp->gpwrap) { + if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq || + rdp->gpwrap) { /* * The grace period in which this quiescent state was @@ -2396,7 +2413,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) */ needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); /* ^^^ Released rnp->lock */ if (needwake) rcu_gp_kthread_wake(rsp); @@ -2441,17 +2458,16 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) */ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { - RCU_TRACE(unsigned long mask;) + RCU_TRACE(bool blkd;) RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);) RCU_TRACE(struct rcu_node *rnp = rdp->mynode;) if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return; - RCU_TRACE(mask = rdp->grpmask;) - trace_rcu_grace_period(rsp->name, - rnp->gpnum + 1 - !!(rnp->qsmask & mask), - TPS("cpuofl")); + RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);) + trace_rcu_grace_period(rsp->name, rnp->gp_seq, + blkd ? TPS("cpuofl") : TPS("cpuofl-bgp")); } /* @@ -2463,7 +2479,7 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) * This function therefore goes up the tree of rcu_node structures, * clearing the corresponding bits in the ->qsmaskinit fields. Note that * the leaf rcu_node structure's ->qsmaskinit field has already been - * updated + * updated. * * This function does check that the specified rcu_node structure has * all CPUs offline and no blocked tasks, so it is OK to invoke it @@ -2476,9 +2492,10 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) long mask; struct rcu_node *rnp = rnp_leaf; - raw_lockdep_assert_held_rcu_node(rnp); + raw_lockdep_assert_held_rcu_node(rnp_leaf); if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || - rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) + WARN_ON_ONCE(rnp_leaf->qsmaskinit) || + WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf))) return; for (;;) { mask = rnp->grpmask; @@ -2487,7 +2504,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) break; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ rnp->qsmaskinit &= ~mask; - rnp->qsmask &= ~mask; + /* Between grace periods, so better already be zero! */ + WARN_ON_ONCE(rnp->qsmask); if (rnp->qsmaskinit) { raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ @@ -2630,6 +2648,7 @@ void rcu_check_callbacks(int user) rcu_sched_qs(); rcu_bh_qs(); + rcu_note_voluntary_context_switch(current); } else if (!in_softirq()) { @@ -2645,8 +2664,7 @@ void rcu_check_callbacks(int user) rcu_preempt_check_callbacks(); if (rcu_pending()) invoke_rcu_core(); - if (user) - rcu_note_voluntary_context_switch(current); + trace_rcu_utilization(TPS("End scheduler-tick")); } @@ -2681,17 +2699,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) /* rcu_initiate_boost() releases rnp->lock */ continue; } - if (rnp->parent && - (rnp->parent->qsmask & rnp->grpmask)) { - /* - * Race between grace-period - * initialization and task exiting RCU - * read-side critical section: Report. - */ - rcu_report_unblock_qs_rnp(rsp, rnp, flags); - /* rcu_report_unblock_qs_rnp() rlses ->lock */ - continue; - } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + continue; } for_each_leaf_node_possible_cpu(rnp, cpu) { unsigned long bit = leaf_node_cpu_bit(rnp, cpu); @@ -2701,8 +2710,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) } } if (mask != 0) { - /* Idle/offline CPUs, report (releases rnp->lock. */ - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + /* Idle/offline CPUs, report (releases rnp->lock). */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); } else { /* Nothing to do here, so just drop the lock. */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2747,6 +2756,65 @@ static void force_quiescent_state(struct rcu_state *rsp) } /* + * This function checks for grace-period requests that fail to motivate + * RCU to come out of its idle mode. + */ +static void +rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) +{ + const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ; + unsigned long flags; + unsigned long j; + struct rcu_node *rnp_root = rcu_get_root(rsp); + static atomic_t warned = ATOMIC_INIT(0); + + if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress(rsp) || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed)) + return; + j = jiffies; /* Expensive access, and in common case don't get here. */ + if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) || + time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) || + atomic_read(&warned)) + return; + + raw_spin_lock_irqsave_rcu_node(rnp, flags); + j = jiffies; + if (rcu_gp_in_progress(rsp) || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || + time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) || + time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) || + atomic_read(&warned)) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return; + } + /* Hold onto the leaf lock to make others see warned==1. */ + + if (rnp_root != rnp) + raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */ + j = jiffies; + if (rcu_gp_in_progress(rsp) || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || + time_before(j, rsp->gp_req_activity + gpssdelay) || + time_before(j, rsp->gp_activity + gpssdelay) || + atomic_xchg(&warned, 1)) { + raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */ + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return; + } + pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n", + __func__, (long)READ_ONCE(rsp->gp_seq), + (long)READ_ONCE(rnp_root->gp_seq_needed), + j - rsp->gp_req_activity, j - rsp->gp_activity, + rsp->gp_flags, rsp->gp_state, rsp->name, + rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL); + WARN_ON(1); + if (rnp_root != rnp) + raw_spin_unlock_rcu_node(rnp_root); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); +} + +/* * This does the RCU core processing work for the specified rcu_state * and rcu_data structures. This may be called only from the CPU to * whom the rdp belongs. @@ -2755,9 +2823,8 @@ static void __rcu_process_callbacks(struct rcu_state *rsp) { unsigned long flags; - bool needwake; struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); - struct rcu_node *rnp; + struct rcu_node *rnp = rdp->mynode; WARN_ON_ONCE(!rdp->beenonline); @@ -2768,18 +2835,13 @@ __rcu_process_callbacks(struct rcu_state *rsp) if (!rcu_gp_in_progress(rsp) && rcu_segcblist_is_enabled(&rdp->cblist)) { local_irq_save(flags); - if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) { - local_irq_restore(flags); - } else { - rnp = rdp->mynode; - raw_spin_lock_rcu_node(rnp); /* irqs disabled. */ - needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - if (needwake) - rcu_gp_kthread_wake(rsp); - } + if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) + rcu_accelerate_cbs_unlocked(rsp, rnp, rdp); + local_irq_restore(flags); } + rcu_check_gp_start_stall(rsp, rnp, rdp); + /* If there are callbacks ready, invoke them. */ if (rcu_segcblist_ready_cbs(&rdp->cblist)) invoke_rcu_callbacks(rsp, rdp); @@ -2833,8 +2895,6 @@ static void invoke_rcu_core(void) static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, struct rcu_head *head, unsigned long flags) { - bool needwake; - /* * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. @@ -2861,13 +2921,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, /* Start a new grace period if one not already started. */ if (!rcu_gp_in_progress(rsp)) { - struct rcu_node *rnp = rdp->mynode; - - raw_spin_lock_rcu_node(rnp); - needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - raw_spin_unlock_rcu_node(rnp); - if (needwake) - rcu_gp_kthread_wake(rsp); + rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp); } else { /* Give the grace period a kick. */ rdp->blimit = LONG_MAX; @@ -3037,7 +3091,7 @@ EXPORT_SYMBOL_GPL(kfree_call_rcu); * when there was in fact only one the whole time, as this just adds * some overhead: RCU still operates correctly. */ -static inline int rcu_blocking_is_gp(void) +static int rcu_blocking_is_gp(void) { int ret; @@ -3136,16 +3190,10 @@ unsigned long get_state_synchronize_rcu(void) { /* * Any prior manipulation of RCU-protected data must happen - * before the load from ->gpnum. + * before the load from ->gp_seq. */ smp_mb(); /* ^^^ */ - - /* - * Make sure this load happens before the purportedly - * time-consuming work between get_state_synchronize_rcu() - * and cond_synchronize_rcu(). - */ - return smp_load_acquire(&rcu_state_p->gpnum); + return rcu_seq_snap(&rcu_state_p->gp_seq); } EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); @@ -3165,15 +3213,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); */ void cond_synchronize_rcu(unsigned long oldstate) { - unsigned long newstate; - - /* - * Ensure that this load happens before any RCU-destructive - * actions the caller might carry out after we return. - */ - newstate = smp_load_acquire(&rcu_state_p->completed); - if (ULONG_CMP_GE(oldstate, newstate)) + if (!rcu_seq_done(&rcu_state_p->gp_seq, oldstate)) synchronize_rcu(); + else + smp_mb(); /* Ensure GP ends before subsequent accesses. */ } EXPORT_SYMBOL_GPL(cond_synchronize_rcu); @@ -3188,16 +3231,10 @@ unsigned long get_state_synchronize_sched(void) { /* * Any prior manipulation of RCU-protected data must happen - * before the load from ->gpnum. + * before the load from ->gp_seq. */ smp_mb(); /* ^^^ */ - - /* - * Make sure this load happens before the purportedly - * time-consuming work between get_state_synchronize_sched() - * and cond_synchronize_sched(). - */ - return smp_load_acquire(&rcu_sched_state.gpnum); + return rcu_seq_snap(&rcu_sched_state.gp_seq); } EXPORT_SYMBOL_GPL(get_state_synchronize_sched); @@ -3217,15 +3254,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_sched); */ void cond_synchronize_sched(unsigned long oldstate) { - unsigned long newstate; - - /* - * Ensure that this load happens before any RCU-destructive - * actions the caller might carry out after we return. - */ - newstate = smp_load_acquire(&rcu_sched_state.completed); - if (ULONG_CMP_GE(oldstate, newstate)) + if (!rcu_seq_done(&rcu_sched_state.gp_seq, oldstate)) synchronize_sched(); + else + smp_mb(); /* Ensure GP ends before subsequent accesses. */ } EXPORT_SYMBOL_GPL(cond_synchronize_sched); @@ -3261,12 +3293,8 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) return 1; - /* Has another RCU grace period completed? */ - if (READ_ONCE(rnp->completed) != rdp->completed) /* outside lock */ - return 1; - - /* Has a new RCU grace period started? */ - if (READ_ONCE(rnp->gpnum) != rdp->gpnum || + /* Have RCU grace period completed or started? */ + if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq || unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */ return 1; @@ -3298,7 +3326,7 @@ static int rcu_pending(void) * non-NULL, store an indication of whether all callbacks are lazy. * (If there are no callbacks, all of them are deemed to be lazy.) */ -static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy) +static bool rcu_cpu_has_callbacks(bool *all_lazy) { bool al = true; bool hc = false; @@ -3484,17 +3512,22 @@ EXPORT_SYMBOL_GPL(rcu_barrier_sched); static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) { long mask; + long oldmask; struct rcu_node *rnp = rnp_leaf; - raw_lockdep_assert_held_rcu_node(rnp); + raw_lockdep_assert_held_rcu_node(rnp_leaf); + WARN_ON_ONCE(rnp->wait_blkd_tasks); for (;;) { mask = rnp->grpmask; rnp = rnp->parent; if (rnp == NULL) return; raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */ + oldmask = rnp->qsmaskinit; rnp->qsmaskinit |= mask; raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */ + if (oldmask) + return; } } @@ -3511,6 +3544,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1); WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks))); + rdp->rcu_ofl_gp_seq = rsp->gp_seq; + rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED; + rdp->rcu_onl_gp_seq = rsp->gp_seq; + rdp->rcu_onl_gp_flags = RCU_GP_CLEANED; rdp->cpu = cpu; rdp->rsp = rsp; rcu_boot_init_nocb_percpu_data(rdp); @@ -3518,9 +3555,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) /* * Initialize a CPU's per-CPU RCU data. Note that only one online or - * offline event can be happening at a given time. Note also that we - * can accept some slop in the rsp->completed access due to the fact - * that this CPU cannot possibly have any RCU callbacks in flight yet. + * offline event can be happening at a given time. Note also that we can + * accept some slop in the rsp->gp_seq access due to the fact that this + * CPU cannot possibly have any RCU callbacks in flight yet. */ static void rcu_init_percpu_data(int cpu, struct rcu_state *rsp) @@ -3549,14 +3586,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ rdp->beenonline = true; /* We have now been online. */ - rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ - rdp->completed = rnp->completed; + rdp->gp_seq = rnp->gp_seq; + rdp->gp_seq_needed = rnp->gp_seq; rdp->cpu_no_qs.b.norm = true; rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu); rdp->core_needs_qs = false; rdp->rcu_iw_pending = false; - rdp->rcu_iw_gpnum = rnp->gpnum - 1; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); + rdp->rcu_iw_gp_seq = rnp->gp_seq - 1; + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } @@ -3705,7 +3742,15 @@ void rcu_cpu_starting(unsigned int cpu) nbits = bitmap_weight(&oldmask, BITS_PER_LONG); /* Allow lockless access for expedited grace periods. */ smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */ - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */ + rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq); + rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags); + if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */ + /* Report QS -after- changing ->qsmaskinitnext! */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + } else { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } } smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } @@ -3713,7 +3758,7 @@ void rcu_cpu_starting(unsigned int cpu) #ifdef CONFIG_HOTPLUG_CPU /* * The CPU is exiting the idle loop into the arch_cpu_idle_dead() - * function. We now remove it from the rcu_node tree's ->qsmaskinit + * function. We now remove it from the rcu_node tree's ->qsmaskinitnext * bit masks. */ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) @@ -3725,9 +3770,18 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; + spin_lock(&rsp->ofl_lock); raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ + rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq); + rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags); + if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */ + /* Report quiescent state -before- changing ->qsmaskinitnext! */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); + } rnp->qsmaskinitnext &= ~mask; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + spin_unlock(&rsp->ofl_lock); } /* @@ -3839,12 +3893,16 @@ static int __init rcu_spawn_gp_kthread(void) struct task_struct *t; /* Force priority into range. */ - if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) + if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2 + && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) + kthread_prio = 2; + else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) kthread_prio = 1; else if (kthread_prio < 0) kthread_prio = 0; else if (kthread_prio > 99) kthread_prio = 99; + if (kthread_prio != kthread_prio_in) pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n", kthread_prio, kthread_prio_in); @@ -3928,8 +3986,9 @@ static void __init rcu_init_one(struct rcu_state *rsp) raw_spin_lock_init(&rnp->fqslock); lockdep_set_class_and_name(&rnp->fqslock, &rcu_fqs_class[i], fqs[i]); - rnp->gpnum = rsp->gpnum; - rnp->completed = rsp->completed; + rnp->gp_seq = rsp->gp_seq; + rnp->gp_seq_needed = rsp->gp_seq; + rnp->completedqs = rsp->gp_seq; rnp->qsmask = 0; rnp->qsmaskinit = 0; rnp->grplo = j * cpustride; @@ -3997,7 +4056,7 @@ static void __init rcu_init_geometry(void) if (rcu_fanout_leaf == RCU_FANOUT_LEAF && nr_cpu_ids == NR_CPUS) return; - pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n", + pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n", rcu_fanout_leaf, nr_cpu_ids); /* diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 78e051dffc5b..4e74df768c57 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -81,18 +81,16 @@ struct rcu_node { raw_spinlock_t __private lock; /* Root rcu_node's lock protects */ /* some rcu_state fields as well as */ /* following. */ - unsigned long gpnum; /* Current grace period for this node. */ - /* This will either be equal to or one */ - /* behind the root rcu_node's gpnum. */ - unsigned long completed; /* Last GP completed for this node. */ - /* This will either be equal to or one */ - /* behind the root rcu_node's gpnum. */ + unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */ + unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */ + unsigned long completedqs; /* All QSes done for this node. */ unsigned long qsmask; /* CPUs or groups that need to switch in */ /* order for current grace period to proceed.*/ /* In leaf rcu_node, each bit corresponds to */ /* an rcu_data structure, otherwise, each */ /* bit corresponds to a child rcu_node */ /* structure. */ + unsigned long rcu_gp_init_mask; /* Mask of offline CPUs at GP init. */ unsigned long qsmaskinit; /* Per-GP initial value for qsmask. */ /* Initialized from ->qsmaskinitnext at the */ @@ -158,7 +156,6 @@ struct rcu_node { struct swait_queue_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ - u8 need_future_gp[4]; /* Counts of upcoming GP requests. */ raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; spinlock_t exp_lock ____cacheline_internodealigned_in_smp; @@ -168,22 +165,6 @@ struct rcu_node { bool exp_need_flush; /* Need to flush workitem? */ } ____cacheline_internodealigned_in_smp; -/* Accessors for ->need_future_gp[] array. */ -#define need_future_gp_mask() \ - (ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1) -#define need_future_gp_element(rnp, c) \ - ((rnp)->need_future_gp[(c) & need_future_gp_mask()]) -#define need_any_future_gp(rnp) \ -({ \ - int __i; \ - bool __nonzero = false; \ - \ - for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++) \ - __nonzero = __nonzero || \ - READ_ONCE((rnp)->need_future_gp[__i]); \ - __nonzero; \ -}) - /* * Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and * are indexed relative to this interval rather than the global CPU ID space. @@ -206,16 +187,14 @@ union rcu_noqs { /* Per-CPU data for read-copy update. */ struct rcu_data { /* 1) quiescent-state and grace-period handling : */ - unsigned long completed; /* Track rsp->completed gp number */ - /* in order to detect GP end. */ - unsigned long gpnum; /* Highest gp number that this CPU */ - /* is aware of having started. */ + unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */ + unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed ctr. */ unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ /* for rcu_all_qs() invocations. */ union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */ bool core_needs_qs; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ - bool gpwrap; /* Possible gpnum/completed wrap. */ + bool gpwrap; /* Possible ->gp_seq wrap. */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ unsigned long ticks_this_gp; /* The number of scheduling-clock */ @@ -239,7 +218,6 @@ struct rcu_data { /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ - unsigned long offline_fqs; /* Kicked due to being offline. */ unsigned long cond_resched_completed; /* Grace period that needs help */ /* from cond_resched(). */ @@ -278,12 +256,16 @@ struct rcu_data { /* Leader CPU takes GP-end wakeups. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ - /* 7) RCU CPU stall data. */ + /* 7) Diagnostic data, including RCU CPU stall warnings. */ unsigned int softirq_snap; /* Snapshot of softirq activity. */ /* ->rcu_iw* fields protected by leaf rcu_node ->lock. */ struct irq_work rcu_iw; /* Check for non-irq activity. */ bool rcu_iw_pending; /* Is ->rcu_iw pending? */ - unsigned long rcu_iw_gpnum; /* ->gpnum associated with ->rcu_iw. */ + unsigned long rcu_iw_gp_seq; /* ->gp_seq associated with ->rcu_iw. */ + unsigned long rcu_ofl_gp_seq; /* ->gp_seq at last offline. */ + short rcu_ofl_gp_flags; /* ->gp_flags at last offline. */ + unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */ + short rcu_onl_gp_flags; /* ->gp_flags at last online. */ int cpu; struct rcu_state *rsp; @@ -340,8 +322,7 @@ struct rcu_state { u8 boost ____cacheline_internodealigned_in_smp; /* Subject to priority boost. */ - unsigned long gpnum; /* Current gp number. */ - unsigned long completed; /* # of last completed gp. */ + unsigned long gp_seq; /* Grace-period sequence #. */ struct task_struct *gp_kthread; /* Task for grace periods. */ struct swait_queue_head gp_wq; /* Where GP task waits. */ short gp_flags; /* Commands for GP task. */ @@ -373,6 +354,8 @@ struct rcu_state { /* but in jiffies. */ unsigned long gp_activity; /* Time of last GP kthread */ /* activity in jiffies. */ + unsigned long gp_req_activity; /* Time of last GP request */ + /* in jiffies. */ unsigned long jiffies_stall; /* Time at which to check */ /* for CPU stalls. */ unsigned long jiffies_resched; /* Time at which to resched */ @@ -384,6 +367,10 @@ struct rcu_state { const char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ struct list_head flavors; /* List of RCU flavors. */ + + spinlock_t ofl_lock ____cacheline_internodealigned_in_smp; + /* Synchronize offline with */ + /* GP pre-initialization. */ }; /* Values for rcu_state structure's gp_flags field. */ @@ -394,16 +381,20 @@ struct rcu_state { #define RCU_GP_IDLE 0 /* Initial state and no GP in progress. */ #define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */ #define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */ -#define RCU_GP_WAIT_FQS 3 /* Wait for force-quiescent-state time. */ -#define RCU_GP_DOING_FQS 4 /* Wait done for force-quiescent-state time. */ -#define RCU_GP_CLEANUP 5 /* Grace-period cleanup started. */ -#define RCU_GP_CLEANED 6 /* Grace-period cleanup complete. */ +#define RCU_GP_ONOFF 3 /* Grace-period initialization hotplug. */ +#define RCU_GP_INIT 4 /* Grace-period initialization. */ +#define RCU_GP_WAIT_FQS 5 /* Wait for force-quiescent-state time. */ +#define RCU_GP_DOING_FQS 6 /* Wait done for force-quiescent-state time. */ +#define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */ +#define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */ #ifndef RCU_TREE_NONCORE static const char * const gp_state_names[] = { "RCU_GP_IDLE", "RCU_GP_WAIT_GPS", "RCU_GP_DONE_GPS", + "RCU_GP_ONOFF", + "RCU_GP_INIT", "RCU_GP_WAIT_FQS", "RCU_GP_DOING_FQS", "RCU_GP_CLEANUP", @@ -449,10 +440,13 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); static int rcu_print_task_exp_stall(struct rcu_node *rnp); -static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); +static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, + struct rcu_node *rnp); static void rcu_preempt_check_callbacks(void); void call_rcu(struct rcu_head *head, rcu_callback_t func); static void __init __rcu_init_preempt(void); +static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, + int ncheck); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static void invoke_rcu_callbacks_kthread(void); @@ -489,7 +483,6 @@ static void __init rcu_spawn_nocb_kthreads(void); #ifdef CONFIG_RCU_NOCB_CPU static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp); #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ -static void __maybe_unused rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); static void rcu_bind_gp_kthread(void); static bool rcu_nohz_full_cpu(struct rcu_state *rsp); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index d40708e8c5d6..0b2c2ad69629 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - swake_up(&rsp->expedited_wq); + swake_up_one(&rsp->expedited_wq); } break; } @@ -472,6 +472,7 @@ retry_ipi: static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, smp_call_func_t func) { + int cpu; struct rcu_node *rnp; trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset")); @@ -486,13 +487,20 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, rnp->rew.rew_func = func; rnp->rew.rew_rsp = rsp; if (!READ_ONCE(rcu_par_gp_wq) || - rcu_scheduler_active != RCU_SCHEDULER_RUNNING) { - /* No workqueues yet. */ + rcu_scheduler_active != RCU_SCHEDULER_RUNNING || + rcu_is_last_leaf_node(rsp, rnp)) { + /* No workqueues yet or last leaf, do direct call. */ sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work); continue; } INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); - queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work); + preempt_disable(); + cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask); + /* If all offline, queue the work on an unbound CPU. */ + if (unlikely(cpu > rnp->grphi)) + cpu = WORK_CPU_UNBOUND; + queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); + preempt_enable(); rnp->exp_need_flush = true; } @@ -518,7 +526,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) jiffies_start = jiffies; for (;;) { - ret = swait_event_timeout( + ret = swait_event_timeout_exclusive( rsp->expedited_wq, sync_rcu_preempt_exp_done_unlocked(rnp_root), jiffies_stall); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7fd12039e512..a97c20ea9bce 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -74,8 +74,8 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tRCU event tracing is enabled.\n"); if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) || (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32)) - pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", - RCU_FANOUT); + pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d.\n", + RCU_FANOUT); if (rcu_fanout_exact) pr_info("\tHierarchical RCU autobalancing is disabled.\n"); if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ)) @@ -88,11 +88,13 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", RCU_FANOUT_LEAF); if (rcu_fanout_leaf != RCU_FANOUT_LEAF) - pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); + pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", + rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%u.\n", NR_CPUS, nr_cpu_ids); #ifdef CONFIG_RCU_BOOST - pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY); + pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", + kthread_prio, CONFIG_RCU_BOOST_DELAY); #endif if (blimit != DEFAULT_RCU_BLIMIT) pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit); @@ -127,6 +129,7 @@ static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data; static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); +static void rcu_read_unlock_special(struct task_struct *t); /* * Tell them what RCU they are running. @@ -183,6 +186,9 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) raw_lockdep_assert_held_rcu_node(rnp); WARN_ON_ONCE(rdp->mynode != rnp); WARN_ON_ONCE(!rcu_is_leaf_node(rnp)); + /* RCU better not be waiting on newly onlined CPUs! */ + WARN_ON_ONCE(rnp->qsmaskinitnext & ~rnp->qsmaskinit & rnp->qsmask & + rdp->grpmask); /* * Decide where to queue the newly blocked task. In theory, @@ -260,8 +266,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * ->exp_tasks pointers, respectively, to reference the newly * blocked tasks. */ - if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) + if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) { rnp->gp_tasks = &t->rcu_node_entry; + WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq); + } if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) rnp->exp_tasks = &t->rcu_node_entry; WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) != @@ -286,20 +294,24 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) } /* - * Record a preemptible-RCU quiescent state for the specified CPU. Note - * that this just means that the task currently running on the CPU is - * not in a quiescent state. There might be any number of tasks blocked - * while in an RCU read-side critical section. + * Record a preemptible-RCU quiescent state for the specified CPU. + * Note that this does not necessarily mean that the task currently running + * on the CPU is in a quiescent state: Instead, it means that the current + * grace period need not wait on any RCU read-side critical section that + * starts later on this CPU. It also means that if the current task is + * in an RCU read-side critical section, it has already added itself to + * some leaf rcu_node structure's ->blkd_tasks list. In addition to the + * current task, there might be any number of other tasks blocked while + * in an RCU read-side critical section. * - * As with the other rcu_*_qs() functions, callers to this function - * must disable preemption. + * Callers to this function must disable preemption. */ static void rcu_preempt_qs(void) { RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n"); if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), - __this_cpu_read(rcu_data_p->gpnum), + __this_cpu_read(rcu_data_p->gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ @@ -348,8 +360,8 @@ static void rcu_preempt_note_context_switch(bool preempt) trace_rcu_preempt_task(rdp->rsp->name, t->pid, (rnp->qsmask & rdp->grpmask) - ? rnp->gpnum - : rnp->gpnum + 1); + ? rnp->gp_seq + : rcu_seq_snap(&rnp->gp_seq)); rcu_preempt_ctxt_queue(rnp, rdp); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special.s) { @@ -456,7 +468,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -void rcu_read_unlock_special(struct task_struct *t) +static void rcu_read_unlock_special(struct task_struct *t) { bool empty_exp; bool empty_norm; @@ -535,13 +547,15 @@ void rcu_read_unlock_special(struct task_struct *t) WARN_ON_ONCE(rnp != t->rcu_blocked_node); WARN_ON_ONCE(!rcu_is_leaf_node(rnp)); empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); + WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq && + (!empty_norm || rnp->qsmask)); empty_exp = sync_rcu_preempt_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); t->rcu_blocked_node = NULL; trace_rcu_unlock_preempted_task(TPS("rcu_preempt"), - rnp->gpnum, t->pid); + rnp->gp_seq, t->pid); if (&t->rcu_node_entry == rnp->gp_tasks) rnp->gp_tasks = np; if (&t->rcu_node_entry == rnp->exp_tasks) @@ -562,7 +576,7 @@ void rcu_read_unlock_special(struct task_struct *t) empty_exp_now = sync_rcu_preempt_exp_done(rnp); if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), - rnp->gpnum, + rnp->gp_seq, 0, rnp->qsmask, rnp->level, rnp->grplo, @@ -686,24 +700,27 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be - * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock + * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock * must be held by the caller. * * Also, if there are blocked tasks on the list, they automatically * block the newly created grace period, so set up ->gp_tasks accordingly. */ -static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) +static void +rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp) { struct task_struct *t; RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n"); - WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); - if (rcu_preempt_has_tasks(rnp)) { + if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) + dump_blkd_tasks(rsp, rnp, 10); + if (rcu_preempt_has_tasks(rnp) && + (rnp->qsmaskinit || rnp->wait_blkd_tasks)) { rnp->gp_tasks = rnp->blkd_tasks.next; t = container_of(rnp->gp_tasks, struct task_struct, rcu_node_entry); trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"), - rnp->gpnum, t->pid); + rnp->gp_seq, t->pid); } WARN_ON_ONCE(rnp->qsmask); } @@ -717,6 +734,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) */ static void rcu_preempt_check_callbacks(void) { + struct rcu_state *rsp = &rcu_preempt_state; struct task_struct *t = current; if (t->rcu_read_lock_nesting == 0) { @@ -725,7 +743,9 @@ static void rcu_preempt_check_callbacks(void) } if (t->rcu_read_lock_nesting > 0 && __this_cpu_read(rcu_data_p->core_needs_qs) && - __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm)) + __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm) && + !t->rcu_read_unlock_special.b.need_qs && + time_after(jiffies, rsp->gp_start + HZ)) t->rcu_read_unlock_special.b.need_qs = true; } @@ -841,6 +861,47 @@ void exit_rcu(void) __rcu_read_unlock(); } +/* + * Dump the blocked-tasks state, but limit the list dump to the + * specified number of elements. + */ +static void +dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) +{ + int cpu; + int i; + struct list_head *lhp; + bool onl; + struct rcu_data *rdp; + struct rcu_node *rnp1; + + raw_lockdep_assert_held_rcu_node(rnp); + pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n", + __func__, rnp->grplo, rnp->grphi, rnp->level, + (long)rnp->gp_seq, (long)rnp->completedqs); + for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent) + pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n", + __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext); + pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n", + __func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks); + pr_info("%s: ->blkd_tasks", __func__); + i = 0; + list_for_each(lhp, &rnp->blkd_tasks) { + pr_cont(" %p", lhp); + if (++i >= 10) + break; + } + pr_cont("\n"); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) { + rdp = per_cpu_ptr(rsp->rda, cpu); + onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp)); + pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n", + cpu, ".o"[onl], + (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, + (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); + } +} + #else /* #ifdef CONFIG_PREEMPT_RCU */ static struct rcu_state *const rcu_state_p = &rcu_sched_state; @@ -911,7 +972,8 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * so there is no need to check for blocked tasks. So check only for * bogus qsmask values. */ -static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) +static void +rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp) { WARN_ON_ONCE(rnp->qsmask); } @@ -949,6 +1011,15 @@ void exit_rcu(void) { } +/* + * Dump the guaranteed-empty blocked-tasks state. Trust but verify. + */ +static void +dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) +{ + WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks)); +} + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_BOOST @@ -1433,7 +1504,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) * completed since we last checked and there are * callbacks not yet ready to invoke. */ - if ((rdp->completed != rnp->completed || + if ((rcu_seq_completed_gp(rdp->gp_seq, + rcu_seq_current(&rnp->gp_seq)) || unlikely(READ_ONCE(rdp->gpwrap))) && rcu_segcblist_pend_cbs(&rdp->cblist)) note_gp_changes(rsp, rdp); @@ -1720,16 +1792,16 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) */ touch_nmi_watchdog(); - if (rsp->gpnum == rdp->gpnum) { + ticks_value = rcu_seq_ctr(rsp->gp_seq - rdp->gp_seq); + if (ticks_value) { + ticks_title = "GPs behind"; + } else { ticks_title = "ticks this GP"; ticks_value = rdp->ticks_this_gp; - } else { - ticks_title = "GPs behind"; - ticks_value = rsp->gpnum - rdp->gpnum; } print_cpu_stall_fast_no_hz(fast_no_hz, cpu); - delta = rdp->mynode->gpnum - rdp->rcu_iw_gpnum; - pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%ld softirq=%u/%u fqs=%ld %s\n", + delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq); + pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n", cpu, "O."[!!cpu_online(cpu)], "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)], @@ -1817,7 +1889,7 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) { - return &rnp->nocb_gp_wq[rnp->completed & 0x1]; + return &rnp->nocb_gp_wq[rcu_seq_ctr(rnp->gp_seq) & 0x1]; } static void rcu_init_one_nocb(struct rcu_node *rnp) @@ -1854,8 +1926,8 @@ static void __wake_nocb_leader(struct rcu_data *rdp, bool force, WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); del_timer(&rdp->nocb_timer); raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); - smp_mb(); /* ->nocb_leader_sleep before swake_up(). */ - swake_up(&rdp_leader->nocb_wq); + smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */ + swake_up_one(&rdp_leader->nocb_wq); } else { raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); } @@ -2069,12 +2141,17 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) bool needwake; struct rcu_node *rnp = rdp->mynode; - raw_spin_lock_irqsave_rcu_node(rnp, flags); - c = rcu_cbs_completed(rdp->rsp, rnp); - needwake = rcu_start_this_gp(rnp, rdp, c); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - if (needwake) - rcu_gp_kthread_wake(rdp->rsp); + local_irq_save(flags); + c = rcu_seq_snap(&rdp->rsp->gp_seq); + if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { + local_irq_restore(flags); + } else { + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + needwake = rcu_start_this_gp(rnp, rdp, c); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + if (needwake) + rcu_gp_kthread_wake(rdp->rsp); + } /* * Wait for the grace period. Do so interruptibly to avoid messing @@ -2082,9 +2159,9 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) */ trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait")); for (;;) { - swait_event_interruptible( - rnp->nocb_gp_wq[c & 0x1], - (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c))); + swait_event_interruptible_exclusive( + rnp->nocb_gp_wq[rcu_seq_ctr(c) & 0x1], + (d = rcu_seq_done(&rnp->gp_seq, c))); if (likely(d)) break; WARN_ON(signal_pending(current)); @@ -2111,7 +2188,7 @@ wait_again: /* Wait for callbacks to appear. */ if (!rcu_nocb_poll) { trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep")); - swait_event_interruptible(my_rdp->nocb_wq, + swait_event_interruptible_exclusive(my_rdp->nocb_wq, !READ_ONCE(my_rdp->nocb_leader_sleep)); raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags); my_rdp->nocb_leader_sleep = true; @@ -2176,7 +2253,7 @@ wait_again: raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { /* List was empty, so wake up the follower. */ - swake_up(&rdp->nocb_wq); + swake_up_one(&rdp->nocb_wq); } } @@ -2193,7 +2270,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) { for (;;) { trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep")); - swait_event_interruptible(rdp->nocb_wq, + swait_event_interruptible_exclusive(rdp->nocb_wq, READ_ONCE(rdp->nocb_follower_head)); if (smp_load_acquire(&rdp->nocb_follower_head)) { /* ^^^ Ensure CB invocation follows _head test. */ @@ -2569,23 +2646,6 @@ static bool init_nocb_callback_list(struct rcu_data *rdp) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* - * An adaptive-ticks CPU can potentially execute in kernel mode for an - * arbitrarily long period of time with the scheduling-clock tick turned - * off. RCU will be paying attention to this CPU because it is in the - * kernel, but the CPU cannot be guaranteed to be executing the RCU state - * machine because the scheduling-clock tick has been disabled. Therefore, - * if an adaptive-ticks CPU is failing to respond to the current grace - * period and has not be idle from an RCU perspective, kick it. - */ -static void __maybe_unused rcu_kick_nohz_cpu(int cpu) -{ -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_cpu(cpu)) - smp_send_reschedule(cpu); -#endif /* #ifdef CONFIG_NO_HZ_FULL */ -} - -/* * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the * grace-period kthread will do force_quiescent_state() processing? * The idea is to avoid waking up RCU core processing on such a @@ -2610,8 +2670,6 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp) */ static void rcu_bind_gp_kthread(void) { - int __maybe_unused cpu; - if (!tick_nohz_full_enabled()) return; housekeeping_affine(current, HK_FLAG_RCU); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 4c230a60ece4..39cb23d22109 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -507,14 +507,15 @@ early_initcall(check_cpu_stall_init); #ifdef CONFIG_TASKS_RCU /* - * Simple variant of RCU whose quiescent states are voluntary context switch, - * user-space execution, and idle. As such, grace periods can take one good - * long time. There are no read-side primitives similar to rcu_read_lock() - * and rcu_read_unlock() because this implementation is intended to get - * the system into a safe state for some of the manipulations involved in - * tracing and the like. Finally, this implementation does not support - * high call_rcu_tasks() rates from multiple CPUs. If this is required, - * per-CPU callback lists will be needed. + * Simple variant of RCU whose quiescent states are voluntary context + * switch, cond_resched_rcu_qs(), user-space execution, and idle. + * As such, grace periods can take one good long time. There are no + * read-side primitives similar to rcu_read_lock() and rcu_read_unlock() + * because this implementation is intended to get the system into a safe + * state for some of the manipulations involved in tracing and the like. + * Finally, this implementation does not support high call_rcu_tasks() + * rates from multiple CPUs. If this is required, per-CPU callback lists + * will be needed. */ /* Global list of callbacks and associated lock. */ @@ -542,11 +543,11 @@ static struct task_struct *rcu_tasks_kthread_ptr; * period elapses, in other words after all currently executing RCU * read-side critical sections have completed. call_rcu_tasks() assumes * that the read-side critical sections end at a voluntary context - * switch (not a preemption!), entry into idle, or transition to usermode - * execution. As such, there are no read-side primitives analogous to - * rcu_read_lock() and rcu_read_unlock() because this primitive is intended - * to determine that all tasks have passed through a safe state, not so - * much for data-strcuture synchronization. + * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle, + * or transition to usermode execution. As such, there are no read-side + * primitives analogous to rcu_read_lock() and rcu_read_unlock() because + * this primitive is intended to determine that all tasks have passed + * through a safe state, not so much for data-strcuture synchronization. * * See the description of call_rcu() for more detailed information on * memory ordering guarantees. @@ -667,6 +668,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) struct rcu_head *list; struct rcu_head *next; LIST_HEAD(rcu_tasks_holdouts); + int fract; /* Run on housekeeping CPUs by default. Sysadm can move if desired. */ housekeeping_affine(current, HK_FLAG_RCU); @@ -748,13 +750,25 @@ static int __noreturn rcu_tasks_kthread(void *arg) * holdouts. When the list is empty, we are done. */ lastreport = jiffies; - while (!list_empty(&rcu_tasks_holdouts)) { + + /* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/ + fract = 10; + + for (;;) { bool firstreport; bool needreport; int rtst; struct task_struct *t1; - schedule_timeout_interruptible(HZ); + if (list_empty(&rcu_tasks_holdouts)) + break; + + /* Slowly back off waiting for holdouts */ + schedule_timeout_interruptible(HZ/fract); + + if (fract > 1) + fract--; + rtst = READ_ONCE(rcu_task_stall_timeout); needreport = rtst > 0 && time_after(jiffies, lastreport + rtst); @@ -800,6 +814,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) list = next; cond_resched(); } + /* Paranoid sleep to keep this from entering a tight loop */ schedule_timeout_uninterruptible(HZ/10); } } diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index d9a02b318108..7fe183404c38 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -20,7 +20,7 @@ obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle.o fair.o rt.o deadline.o obj-y += wait.o wait_bit.o swait.o completion.o -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o +obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index e426b0cb9ac6..a1ad5b7d5521 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -22,8 +22,8 @@ * * See also complete_all(), wait_for_completion() and related routines. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void complete(struct completion *x) { @@ -44,8 +44,8 @@ EXPORT_SYMBOL(complete); * * This will wake up all threads waiting on this particular completion event. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. * * Since complete_all() sets the completion of @x permanently to done * to allow multiple waiters to finish, a call to reinit_completion() diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fe365c9a08e9..d17d99778356 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -17,6 +17,8 @@ #include "../workqueue_internal.h" #include "../smpboot.h" +#include "pelt.h" + #define CREATE_TRACE_POINTS #include <trace/events/sched.h> @@ -45,14 +47,6 @@ const_debug unsigned int sysctl_sched_features = const_debug unsigned int sysctl_sched_nr_migrate = 32; /* - * period over which we average the RT time consumption, measured - * in ms. - * - * default: 1s - */ -const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; - -/* * period over which we measure -rt task CPU usage in us. * default: 1s */ @@ -183,9 +177,9 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->clock_task += delta; -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +#ifdef HAVE_SCHED_AVG_IRQ if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) - sched_rt_avg_update(rq, irq_delta + steal); + update_irq_load_avg(rq, irq_delta + steal); #endif } @@ -412,8 +406,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) * its already queued (either by us or someone else) and will get the * wakeup due to that. * - * This cmpxchg() implies a full barrier, which pairs with the write - * barrier implied by the wakeup in wake_up_q(). + * This cmpxchg() executes a full barrier, which pairs with the full + * barrier executed by the wakeup in wake_up_q(). */ if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) return; @@ -441,8 +435,8 @@ void wake_up_q(struct wake_q_head *head) task->wake_q.next = NULL; /* - * wake_up_process() implies a wmb() to pair with the queueing - * in wake_q_add() so as not to miss wakeups. + * wake_up_process() executes a full barrier, which pairs with + * the queueing in wake_q_add() so as not to miss wakeups. */ wake_up_process(task); put_task_struct(task); @@ -649,23 +643,6 @@ bool sched_can_stop_tick(struct rq *rq) return true; } #endif /* CONFIG_NO_HZ_FULL */ - -void sched_avg_update(struct rq *rq) -{ - s64 period = sched_avg_period(); - - while ((s64)(rq_clock(rq) - rq->age_stamp) > period) { - /* - * Inline assembly required to prevent the compiler - * optimising this loop into a divmod call. - * See __iter_div_u64_rem() for another example of this. - */ - asm("" : "+rm" (rq->age_stamp)); - rq->age_stamp += period; - rq->rt_avg /= 2; - } -} - #endif /* CONFIG_SMP */ #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \ @@ -1199,6 +1176,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) __set_task_cpu(p, new_cpu); } +#ifdef CONFIG_NUMA_BALANCING static void __migrate_swap_task(struct task_struct *p, int cpu) { if (task_on_rq_queued(p)) { @@ -1280,16 +1258,17 @@ unlock: /* * Cross migrate two tasks */ -int migrate_swap(struct task_struct *cur, struct task_struct *p) +int migrate_swap(struct task_struct *cur, struct task_struct *p, + int target_cpu, int curr_cpu) { struct migration_swap_arg arg; int ret = -EINVAL; arg = (struct migration_swap_arg){ .src_task = cur, - .src_cpu = task_cpu(cur), + .src_cpu = curr_cpu, .dst_task = p, - .dst_cpu = task_cpu(p), + .dst_cpu = target_cpu, }; if (arg.src_cpu == arg.dst_cpu) @@ -1314,6 +1293,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p) out: return ret; } +#endif /* CONFIG_NUMA_BALANCING */ /* * wait_task_inactive - wait for a thread to unschedule. @@ -1879,8 +1859,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * rq(c1)->lock (if not at the same time, then in that order). * C) LOCK of the rq(c1)->lock scheduling in task * - * Transitivity guarantees that B happens after A and C after B. - * Note: we only require RCpc transitivity. + * Release/acquire chaining guarantees that B happens after A and C after B. * Note: the CPU doing B need not be c0 or c1 * * Example: @@ -1942,16 +1921,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * UNLOCK rq(0)->lock * * - * However; for wakeups there is a second guarantee we must provide, namely we - * must observe the state that lead to our wakeup. That is, not only must our - * task observe its own prior state, it must also observe the stores prior to - * its wakeup. - * - * This means that any means of doing remote wakeups must order the CPU doing - * the wakeup against the CPU the task is going to end up running on. This, - * however, is already required for the regular Program-Order guarantee above, - * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire). - * + * However, for wakeups there is a second guarantee we must provide, namely we + * must ensure that CONDITION=1 done by the caller can not be reordered with + * accesses to the task state; see try_to_wake_up() and set_current_state(). */ /** @@ -1967,6 +1939,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * Atomic against schedule() which would dequeue a task, also see * set_current_state(). * + * This function executes a full memory barrier before accessing the task + * state; see set_current_state(). + * * Return: %true if @p->state changes (an actual wakeup was done), * %false otherwise. */ @@ -1998,21 +1973,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * be possible to, falsely, observe p->on_rq == 0 and get stuck * in smp_cond_load_acquire() below. * - * sched_ttwu_pending() try_to_wake_up() - * [S] p->on_rq = 1; [L] P->state - * UNLOCK rq->lock -----. - * \ - * +--- RMB - * schedule() / - * LOCK rq->lock -----' - * UNLOCK rq->lock + * sched_ttwu_pending() try_to_wake_up() + * STORE p->on_rq = 1 LOAD p->state + * UNLOCK rq->lock + * + * __schedule() (switch to task 'p') + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * UNLOCK rq->lock * * [task p] - * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq + * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq * - * Pairs with the UNLOCK+LOCK on rq->lock from the - * last wakeup of our task and the schedule that got our task - * current. + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). */ smp_rmb(); if (p->on_rq && ttwu_remote(p, wake_flags)) @@ -2026,15 +2000,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * One must be running (->on_cpu == 1) in order to remove oneself * from the runqueue. * - * [S] ->on_cpu = 1; [L] ->on_rq - * UNLOCK rq->lock - * RMB - * LOCK rq->lock - * [S] ->on_rq = 0; [L] ->on_cpu + * __schedule() (switch to task 'p') try_to_wake_up() + * STORE p->on_cpu = 1 LOAD p->on_rq + * UNLOCK rq->lock + * + * __schedule() (put 'p' to sleep) + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * STORE p->on_rq = 0 LOAD p->on_cpu * - * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock - * from the consecutive calls to schedule(); the first switching to our - * task, the second putting it to sleep. + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). */ smp_rmb(); @@ -2140,8 +2116,7 @@ out: * * Return: 1 if the process was woken up, 0 if it was already running. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * This function executes a full memory barrier before accessing the task state. */ int wake_up_process(struct task_struct *p) { @@ -2317,7 +2292,6 @@ static inline void init_schedstats(void) {} int sched_fork(unsigned long clone_flags, struct task_struct *p) { unsigned long flags; - int cpu = get_cpu(); __sched_fork(clone_flags, p); /* @@ -2353,14 +2327,12 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->sched_reset_on_fork = 0; } - if (dl_prio(p->prio)) { - put_cpu(); + if (dl_prio(p->prio)) return -EAGAIN; - } else if (rt_prio(p->prio)) { + else if (rt_prio(p->prio)) p->sched_class = &rt_sched_class; - } else { + else p->sched_class = &fair_sched_class; - } init_entity_runnable_average(&p->se); @@ -2376,7 +2348,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) * We're setting the CPU for the first time, we don't migrate, * so use __set_task_cpu(). */ - __set_task_cpu(p, cpu); + __set_task_cpu(p, smp_processor_id()); if (p->sched_class->task_fork) p->sched_class->task_fork(p); raw_spin_unlock_irqrestore(&p->pi_lock, flags); @@ -2393,8 +2365,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) plist_node_init(&p->pushable_tasks, MAX_PRIO); RB_CLEAR_NODE(&p->pushable_dl_tasks); #endif - - put_cpu(); return 0; } @@ -5714,13 +5684,6 @@ void set_rq_offline(struct rq *rq) } } -static void set_cpu_rq_start_time(unsigned int cpu) -{ - struct rq *rq = cpu_rq(cpu); - - rq->age_stamp = sched_clock_cpu(cpu); -} - /* * used to mark begin/end of suspend/resume: */ @@ -5838,7 +5801,6 @@ static void sched_rq_cpu_starting(unsigned int cpu) int sched_cpu_starting(unsigned int cpu) { - set_cpu_rq_start_time(cpu); sched_rq_cpu_starting(cpu); sched_tick_start(cpu); return 0; @@ -6106,7 +6068,6 @@ void __init sched_init(void) #ifdef CONFIG_SMP idle_thread_set_boot_cpu(); - set_cpu_rq_start_time(smp_processor_id()); #endif init_sched_fair_class(); @@ -6785,6 +6746,16 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v) seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled); seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time); + if (schedstat_enabled() && tg != &root_task_group) { + u64 ws = 0; + int i; + + for_each_possible_cpu(i) + ws += schedstat_val(tg->se[i]->statistics.wait_sum); + + seq_printf(sf, "wait_sum %llu\n", ws); + } + return 0; } #endif /* CONFIG_CFS_BANDWIDTH */ diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index c907fde01eaa..3fffad3bc8a8 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -53,9 +53,7 @@ struct sugov_cpu { unsigned int iowait_boost_max; u64 last_update; - /* The fields below are only needed when sharing a policy: */ - unsigned long util_cfs; - unsigned long util_dl; + unsigned long bw_dl; unsigned long max; /* The field below is for single-CPU policies only: */ @@ -179,33 +177,90 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, return cpufreq_driver_resolve_freq(policy, freq); } -static void sugov_get_util(struct sugov_cpu *sg_cpu) +/* + * This function computes an effective utilization for the given CPU, to be + * used for frequency selection given the linear relation: f = u * f_max. + * + * The scheduler tracks the following metrics: + * + * cpu_util_{cfs,rt,dl,irq}() + * cpu_bw_dl() + * + * Where the cfs,rt and dl util numbers are tracked with the same metric and + * synchronized windows and are thus directly comparable. + * + * The cfs,rt,dl utilization are the running times measured with rq->clock_task + * which excludes things like IRQ and steal-time. These latter are then accrued + * in the irq utilization. + * + * The DL bandwidth number otoh is not a measured metric but a value computed + * based on the task model parameters and gives the minimal utilization + * required to meet deadlines. + */ +static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); + unsigned long util, irq, max; - sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); - sg_cpu->util_cfs = cpu_util_cfs(rq); - sg_cpu->util_dl = cpu_util_dl(rq); -} - -static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu) -{ - struct rq *rq = cpu_rq(sg_cpu->cpu); + sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); + sg_cpu->bw_dl = cpu_bw_dl(rq); if (rt_rq_is_runnable(&rq->rt)) - return sg_cpu->max; + return max; + + /* + * Early check to see if IRQ/steal time saturates the CPU, can be + * because of inaccuracies in how we track these -- see + * update_irq_load_avg(). + */ + irq = cpu_util_irq(rq); + if (unlikely(irq >= max)) + return max; + + /* + * Because the time spend on RT/DL tasks is visible as 'lost' time to + * CFS tasks and we use the same metric to track the effective + * utilization (PELT windows are synchronized) we can directly add them + * to obtain the CPU's actual utilization. + */ + util = cpu_util_cfs(rq); + util += cpu_util_rt(rq); + + /* + * We do not make cpu_util_dl() a permanent part of this sum because we + * want to use cpu_bw_dl() later on, but we need to check if the + * CFS+RT+DL sum is saturated (ie. no idle time) such that we select + * f_max when there is no idle time. + * + * NOTE: numerical errors or stop class might cause us to not quite hit + * saturation when we should -- something for later. + */ + if ((util + cpu_util_dl(rq)) >= max) + return max; + + /* + * There is still idle time; further improve the number by using the + * irq metric. Because IRQ/steal time is hidden from the task clock we + * need to scale the task numbers: + * + * 1 - irq + * U' = irq + ------- * U + * max + */ + util = scale_irq_capacity(util, irq, max); + util += irq; /* - * Utilization required by DEADLINE must always be granted while, for - * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to - * gracefully reduce the frequency when no tasks show up for longer + * Bandwidth required by DEADLINE must always be granted while, for + * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism + * to gracefully reduce the frequency when no tasks show up for longer * periods of time. * - * Ideally we would like to set util_dl as min/guaranteed freq and - * util_cfs + util_dl as requested freq. However, cpufreq is not yet - * ready for such an interface. So, we only do the latter for now. + * Ideally we would like to set bw_dl as min/guaranteed freq and util + + * bw_dl as requested freq. However, cpufreq is not yet ready for such + * an interface. So, we only do the latter for now. */ - return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs)); + return min(max, util + sg_cpu->bw_dl); } /** @@ -360,7 +415,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } */ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy) { - if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl) + if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl) sg_policy->need_freq_update = true; } @@ -383,9 +438,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, busy = sugov_cpu_is_busy(sg_cpu); - sugov_get_util(sg_cpu); + util = sugov_get_util(sg_cpu); max = sg_cpu->max; - util = sugov_aggregate_util(sg_cpu); sugov_iowait_apply(sg_cpu, time, &util, &max); next_f = get_next_freq(sg_policy, util, max); /* @@ -424,9 +478,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); unsigned long j_util, j_max; - sugov_get_util(j_sg_cpu); + j_util = sugov_get_util(j_sg_cpu); j_max = j_sg_cpu->max; - j_util = sugov_aggregate_util(j_sg_cpu); sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max); if (j_util * max > j_max * util) { diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fbfc3f1d368a..997ea7b839fa 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -16,6 +16,7 @@ * Fabio Checconi <fchecconi@gmail.com> */ #include "sched.h" +#include "pelt.h" struct dl_bandwidth def_dl_bandwidth; @@ -1179,8 +1180,6 @@ static void update_curr_dl(struct rq *rq) curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); - sched_rt_avg_update(rq, delta_exec); - if (dl_entity_is_special(dl_se)) return; @@ -1761,6 +1760,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) deadline_queue_push_tasks(rq); + if (rq->curr->sched_class != &dl_sched_class) + update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + return p; } @@ -1768,6 +1770,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p) { update_curr_dl(rq); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -1784,6 +1787,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) { update_curr_dl(rq); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); /* * Even when we have runtime, update_curr_dl() might have resulted in us * not being the leftmost task anymore. In that case NEED_RESCHED will @@ -2090,8 +2094,14 @@ retry: sub_rq_bw(&next_task->dl, &rq->dl); set_task_cpu(next_task, later_rq->cpu); add_rq_bw(&next_task->dl, &later_rq->dl); + + /* + * Update the later_rq clock here, because the clock is used + * by the cpufreq_update_util() inside __add_running_bw(). + */ + update_rq_clock(later_rq); add_running_bw(&next_task->dl, &later_rq->dl); - activate_task(later_rq, next_task, 0); + activate_task(later_rq, next_task, ENQUEUE_NOCLOCK); ret = 1; resched_curr(later_rq); @@ -2290,8 +2300,17 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (task_on_rq_queued(p) && p->dl.dl_runtime) task_non_contending(p); - if (!task_on_rq_queued(p)) + if (!task_on_rq_queued(p)) { + /* + * Inactive timer is armed. However, p is leaving DEADLINE and + * might migrate away from this rq while continuing to run on + * some other class. We need to remove its contribution from + * this rq running_bw now, or sub_rq_bw (below) will complain. + */ + if (p->dl.dl_non_contending) + sub_running_bw(&p->dl, &rq->dl); sub_rq_bw(&p->dl, &rq->dl); + } /* * We cannot use inactive_task_timer() to invoke sub_running_bw() diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index e593b4118578..870d4f3da285 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -111,20 +111,19 @@ static int sched_feat_set(char *cmp) cmp += 3; } - for (i = 0; i < __SCHED_FEAT_NR; i++) { - if (strcmp(cmp, sched_feat_names[i]) == 0) { - if (neg) { - sysctl_sched_features &= ~(1UL << i); - sched_feat_disable(i); - } else { - sysctl_sched_features |= (1UL << i); - sched_feat_enable(i); - } - break; - } + i = match_string(sched_feat_names, __SCHED_FEAT_NR, cmp); + if (i < 0) + return i; + + if (neg) { + sysctl_sched_features &= ~(1UL << i); + sched_feat_disable(i); + } else { + sysctl_sched_features |= (1UL << i); + sched_feat_enable(i); } - return i; + return 0; } static ssize_t @@ -133,7 +132,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, { char buf[64]; char *cmp; - int i; + int ret; struct inode *inode; if (cnt > 63) @@ -148,10 +147,10 @@ sched_feat_write(struct file *filp, const char __user *ubuf, /* Ensure the static_key remains in a consistent state */ inode = file_inode(filp); inode_lock(inode); - i = sched_feat_set(cmp); + ret = sched_feat_set(cmp); inode_unlock(inode); - if (i == __SCHED_FEAT_NR) - return -EINVAL; + if (ret < 0) + return ret; *ppos += cnt; @@ -843,8 +842,8 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf, unsigned long tpf, unsigned long gsf, unsigned long gpf) { SEQ_printf(m, "numa_faults node=%d ", node); - SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf); - SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf); + SEQ_printf(m, "task_private=%lu task_shared=%lu ", tpf, tsf); + SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gpf, gsf); } #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2f0a0be4d344..309c93fcc604 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -255,9 +255,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq) return cfs_rq->rq; } -/* An entity is a task if it doesn't "own" a runqueue */ -#define entity_is_task(se) (!se->my_q) - static inline struct task_struct *task_of(struct sched_entity *se) { SCHED_WARN_ON(!entity_is_task(se)); @@ -419,7 +416,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq) return container_of(cfs_rq, struct rq, cfs); } -#define entity_is_task(se) 1 #define for_each_sched_entity(se) \ for (; se; se = NULL) @@ -692,7 +688,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) } #ifdef CONFIG_SMP - +#include "pelt.h" #include "sched-pelt.h" static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu); @@ -735,11 +731,12 @@ static void attach_entity_cfs_rq(struct sched_entity *se); * To solve this problem, we also cap the util_avg of successive tasks to * only 1/2 of the left utilization budget: * - * util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n + * util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n * - * where n denotes the nth task. + * where n denotes the nth task and cpu_scale the CPU capacity. * - * For example, a simplest series from the beginning would be like: + * For example, for a CPU with 1024 of capacity, a simplest series from + * the beginning would be like: * * task util_avg: 512, 256, 128, 64, 32, 16, 8, ... * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ... @@ -751,7 +748,8 @@ void post_init_entity_util_avg(struct sched_entity *se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); struct sched_avg *sa = &se->avg; - long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2; + long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq))); + long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2; if (cap > 0) { if (cfs_rq->avg.util_avg != 0) { @@ -1314,7 +1312,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, * of each group. Skip other nodes. */ if (sched_numa_topology_type == NUMA_BACKPLANE && - dist > maxdist) + dist >= maxdist) continue; /* Add up the faults from nearby nodes. */ @@ -1452,15 +1450,12 @@ static unsigned long capacity_of(int cpu); /* Cached statistics for all CPUs within a node */ struct numa_stats { - unsigned long nr_running; unsigned long load; /* Total compute capacity of CPUs on a node */ unsigned long compute_capacity; - /* Approximate capacity in terms of runnable tasks on a node */ - unsigned long task_capacity; - int has_free_capacity; + unsigned int nr_running; }; /* @@ -1487,8 +1482,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid) * the @ns structure is NULL'ed and task_numa_compare() will * not find this node attractive. * - * We'll either bail at !has_free_capacity, or we'll detect a huge - * imbalance and bail there. + * We'll detect a huge imbalance and bail there. */ if (!cpus) return; @@ -1497,9 +1491,8 @@ static void update_numa_stats(struct numa_stats *ns, int nid) smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity); capacity = cpus / smt; /* cores */ - ns->task_capacity = min_t(unsigned, capacity, + capacity = min_t(unsigned, capacity, DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE)); - ns->has_free_capacity = (ns->nr_running < ns->task_capacity); } struct task_numa_env { @@ -1548,28 +1541,12 @@ static bool load_too_imbalanced(long src_load, long dst_load, src_capacity = env->src_stats.compute_capacity; dst_capacity = env->dst_stats.compute_capacity; - /* We care about the slope of the imbalance, not the direction. */ - if (dst_load < src_load) - swap(dst_load, src_load); + imb = abs(dst_load * src_capacity - src_load * dst_capacity); - /* Is the difference below the threshold? */ - imb = dst_load * src_capacity * 100 - - src_load * dst_capacity * env->imbalance_pct; - if (imb <= 0) - return false; - - /* - * The imbalance is above the allowed threshold. - * Compare it with the old imbalance. - */ orig_src_load = env->src_stats.load; orig_dst_load = env->dst_stats.load; - if (orig_dst_load < orig_src_load) - swap(orig_dst_load, orig_src_load); - - old_imb = orig_dst_load * src_capacity * 100 - - orig_src_load * dst_capacity * env->imbalance_pct; + old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity); /* Would this change make things worse? */ return (imb > old_imb); @@ -1582,9 +1559,8 @@ static bool load_too_imbalanced(long src_load, long dst_load, * be exchanged with the source task */ static void task_numa_compare(struct task_numa_env *env, - long taskimp, long groupimp) + long taskimp, long groupimp, bool maymove) { - struct rq *src_rq = cpu_rq(env->src_cpu); struct rq *dst_rq = cpu_rq(env->dst_cpu); struct task_struct *cur; long src_load, dst_load; @@ -1605,97 +1581,73 @@ static void task_numa_compare(struct task_numa_env *env, if (cur == env->p) goto unlock; + if (!cur) { + if (maymove || imp > env->best_imp) + goto assign; + else + goto unlock; + } + /* * "imp" is the fault differential for the source task between the * source and destination node. Calculate the total differential for * the source task and potential destination task. The more negative - * the value is, the more rmeote accesses that would be expected to + * the value is, the more remote accesses that would be expected to * be incurred if the tasks were swapped. */ - if (cur) { - /* Skip this swap candidate if cannot move to the source CPU: */ - if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) - goto unlock; + /* Skip this swap candidate if cannot move to the source cpu */ + if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) + goto unlock; + /* + * If dst and source tasks are in the same NUMA group, or not + * in any group then look only at task weights. + */ + if (cur->numa_group == env->p->numa_group) { + imp = taskimp + task_weight(cur, env->src_nid, dist) - + task_weight(cur, env->dst_nid, dist); /* - * If dst and source tasks are in the same NUMA group, or not - * in any group then look only at task weights. + * Add some hysteresis to prevent swapping the + * tasks within a group over tiny differences. */ - if (cur->numa_group == env->p->numa_group) { - imp = taskimp + task_weight(cur, env->src_nid, dist) - - task_weight(cur, env->dst_nid, dist); - /* - * Add some hysteresis to prevent swapping the - * tasks within a group over tiny differences. - */ - if (cur->numa_group) - imp -= imp/16; - } else { - /* - * Compare the group weights. If a task is all by - * itself (not part of a group), use the task weight - * instead. - */ - if (cur->numa_group) - imp += group_weight(cur, env->src_nid, dist) - - group_weight(cur, env->dst_nid, dist); - else - imp += task_weight(cur, env->src_nid, dist) - - task_weight(cur, env->dst_nid, dist); - } + if (cur->numa_group) + imp -= imp / 16; + } else { + /* + * Compare the group weights. If a task is all by itself + * (not part of a group), use the task weight instead. + */ + if (cur->numa_group && env->p->numa_group) + imp += group_weight(cur, env->src_nid, dist) - + group_weight(cur, env->dst_nid, dist); + else + imp += task_weight(cur, env->src_nid, dist) - + task_weight(cur, env->dst_nid, dist); } - if (imp <= env->best_imp && moveimp <= env->best_imp) + if (imp <= env->best_imp) goto unlock; - if (!cur) { - /* Is there capacity at our destination? */ - if (env->src_stats.nr_running <= env->src_stats.task_capacity && - !env->dst_stats.has_free_capacity) - goto unlock; - - goto balance; - } - - /* Balance doesn't matter much if we're running a task per CPU: */ - if (imp > env->best_imp && src_rq->nr_running == 1 && - dst_rq->nr_running == 1) + if (maymove && moveimp > imp && moveimp > env->best_imp) { + imp = moveimp - 1; + cur = NULL; goto assign; + } /* * In the overloaded case, try and keep the load balanced. */ -balance: - load = task_h_load(env->p); + load = task_h_load(env->p) - task_h_load(cur); + if (!load) + goto assign; + dst_load = env->dst_stats.load + load; src_load = env->src_stats.load - load; - if (moveimp > imp && moveimp > env->best_imp) { - /* - * If the improvement from just moving env->p direction is - * better than swapping tasks around, check if a move is - * possible. Store a slightly smaller score than moveimp, - * so an actually idle CPU will win. - */ - if (!load_too_imbalanced(src_load, dst_load, env)) { - imp = moveimp - 1; - cur = NULL; - goto assign; - } - } - - if (imp <= env->best_imp) - goto unlock; - - if (cur) { - load = task_h_load(cur); - dst_load -= load; - src_load += load; - } - if (load_too_imbalanced(src_load, dst_load, env)) goto unlock; +assign: /* * One idle CPU per node is evaluated for a task numa move. * Call select_idle_sibling to maybe find a better one. @@ -1711,7 +1663,6 @@ balance: local_irq_enable(); } -assign: task_numa_assign(env, cur, imp); unlock: rcu_read_unlock(); @@ -1720,43 +1671,30 @@ unlock: static void task_numa_find_cpu(struct task_numa_env *env, long taskimp, long groupimp) { + long src_load, dst_load, load; + bool maymove = false; int cpu; + load = task_h_load(env->p); + dst_load = env->dst_stats.load + load; + src_load = env->src_stats.load - load; + + /* + * If the improvement from just moving env->p direction is better + * than swapping tasks around, check if a move is possible. + */ + maymove = !load_too_imbalanced(src_load, dst_load, env); + for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { /* Skip this CPU if the source task cannot migrate */ if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed)) continue; env->dst_cpu = cpu; - task_numa_compare(env, taskimp, groupimp); + task_numa_compare(env, taskimp, groupimp, maymove); } } -/* Only move tasks to a NUMA node less busy than the current node. */ -static bool numa_has_capacity(struct task_numa_env *env) -{ - struct numa_stats *src = &env->src_stats; - struct numa_stats *dst = &env->dst_stats; - - if (src->has_free_capacity && !dst->has_free_capacity) - return false; - - /* - * Only consider a task move if the source has a higher load - * than the destination, corrected for CPU capacity on each node. - * - * src->load dst->load - * --------------------- vs --------------------- - * src->compute_capacity dst->compute_capacity - */ - if (src->load * dst->compute_capacity * env->imbalance_pct > - - dst->load * src->compute_capacity * 100) - return true; - - return false; -} - static int task_numa_migrate(struct task_struct *p) { struct task_numa_env env = { @@ -1797,7 +1735,7 @@ static int task_numa_migrate(struct task_struct *p) * elsewhere, so there is no point in (re)trying. */ if (unlikely(!sd)) { - p->numa_preferred_nid = task_node(p); + sched_setnuma(p, task_node(p)); return -EINVAL; } @@ -1811,8 +1749,7 @@ static int task_numa_migrate(struct task_struct *p) update_numa_stats(&env.dst_stats, env.dst_nid); /* Try to find a spot on the preferred nid. */ - if (numa_has_capacity(&env)) - task_numa_find_cpu(&env, taskimp, groupimp); + task_numa_find_cpu(&env, taskimp, groupimp); /* * Look at other nodes in these cases: @@ -1842,8 +1779,7 @@ static int task_numa_migrate(struct task_struct *p) env.dist = dist; env.dst_nid = nid; update_numa_stats(&env.dst_stats, env.dst_nid); - if (numa_has_capacity(&env)) - task_numa_find_cpu(&env, taskimp, groupimp); + task_numa_find_cpu(&env, taskimp, groupimp); } } @@ -1856,15 +1792,13 @@ static int task_numa_migrate(struct task_struct *p) * trying for a better one later. Do not set the preferred node here. */ if (p->numa_group) { - struct numa_group *ng = p->numa_group; - if (env.best_cpu == -1) nid = env.src_nid; else - nid = env.dst_nid; + nid = cpu_to_node(env.best_cpu); - if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng)) - sched_setnuma(p, env.dst_nid); + if (nid != p->numa_preferred_nid) + sched_setnuma(p, nid); } /* No better CPU than the current one was found. */ @@ -1884,7 +1818,8 @@ static int task_numa_migrate(struct task_struct *p) return ret; } - ret = migrate_swap(p, env.best_task); + ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu); + if (ret != 0) trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task)); put_task_struct(env.best_task); @@ -2144,8 +2079,8 @@ static int preferred_group_nid(struct task_struct *p, int nid) static void task_numa_placement(struct task_struct *p) { - int seq, nid, max_nid = -1, max_group_nid = -1; - unsigned long max_faults = 0, max_group_faults = 0; + int seq, nid, max_nid = -1; + unsigned long max_faults = 0; unsigned long fault_types[2] = { 0, 0 }; unsigned long total_faults; u64 runtime, period; @@ -2224,33 +2159,30 @@ static void task_numa_placement(struct task_struct *p) } } - if (faults > max_faults) { - max_faults = faults; + if (!p->numa_group) { + if (faults > max_faults) { + max_faults = faults; + max_nid = nid; + } + } else if (group_faults > max_faults) { + max_faults = group_faults; max_nid = nid; } - - if (group_faults > max_group_faults) { - max_group_faults = group_faults; - max_group_nid = nid; - } } - update_task_scan_period(p, fault_types[0], fault_types[1]); - if (p->numa_group) { numa_group_count_active_nodes(p->numa_group); spin_unlock_irq(group_lock); - max_nid = preferred_group_nid(p, max_group_nid); + max_nid = preferred_group_nid(p, max_nid); } if (max_faults) { /* Set the new preferred node */ if (max_nid != p->numa_preferred_nid) sched_setnuma(p, max_nid); - - if (task_node(p) != p->numa_preferred_nid) - numa_migrate_preferred(p); } + + update_task_scan_period(p, fault_types[0], fault_types[1]); } static inline int get_numa_group(struct numa_group *grp) @@ -2450,14 +2382,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) numa_is_active_node(mem_node, ng)) local = 1; - task_numa_placement(p); - /* * Retry task to preferred node migration periodically, in case it * case it previously failed, or the scheduler moved us. */ - if (time_after(jiffies, p->numa_migrate_retry)) + if (time_after(jiffies, p->numa_migrate_retry)) { + task_numa_placement(p); numa_migrate_preferred(p); + } if (migrated) p->numa_pages_migrated += pages; @@ -2749,19 +2681,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) } while (0) #ifdef CONFIG_SMP -/* - * XXX we want to get rid of these helpers and use the full load resolution. - */ -static inline long se_weight(struct sched_entity *se) -{ - return scale_load_down(se->load.weight); -} - -static inline long se_runnable(struct sched_entity *se) -{ - return scale_load_down(se->runnable_weight); -} - static inline void enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { @@ -3062,314 +2981,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) } #ifdef CONFIG_SMP -/* - * Approximate: - * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) - */ -static u64 decay_load(u64 val, u64 n) -{ - unsigned int local_n; - - if (unlikely(n > LOAD_AVG_PERIOD * 63)) - return 0; - - /* after bounds checking we can collapse to 32-bit */ - local_n = n; - - /* - * As y^PERIOD = 1/2, we can combine - * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD) - * With a look-up table which covers y^n (n<PERIOD) - * - * To achieve constant time decay_load. - */ - if (unlikely(local_n >= LOAD_AVG_PERIOD)) { - val >>= local_n / LOAD_AVG_PERIOD; - local_n %= LOAD_AVG_PERIOD; - } - - val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32); - return val; -} - -static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) -{ - u32 c1, c2, c3 = d3; /* y^0 == 1 */ - - /* - * c1 = d1 y^p - */ - c1 = decay_load((u64)d1, periods); - - /* - * p-1 - * c2 = 1024 \Sum y^n - * n=1 - * - * inf inf - * = 1024 ( \Sum y^n - \Sum y^n - y^0 ) - * n=0 n=p - */ - c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024; - - return c1 + c2 + c3; -} - -/* - * Accumulate the three separate parts of the sum; d1 the remainder - * of the last (incomplete) period, d2 the span of full periods and d3 - * the remainder of the (incomplete) current period. - * - * d1 d2 d3 - * ^ ^ ^ - * | | | - * |<->|<----------------->|<--->| - * ... |---x---|------| ... |------|-----x (now) - * - * p-1 - * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0 - * n=1 - * - * = u y^p + (Step 1) - * - * p-1 - * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2) - * n=1 - */ -static __always_inline u32 -accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, - unsigned long load, unsigned long runnable, int running) -{ - unsigned long scale_freq, scale_cpu; - u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ - u64 periods; - - scale_freq = arch_scale_freq_capacity(cpu); - scale_cpu = arch_scale_cpu_capacity(NULL, cpu); - - delta += sa->period_contrib; - periods = delta / 1024; /* A period is 1024us (~1ms) */ - - /* - * Step 1: decay old *_sum if we crossed period boundaries. - */ - if (periods) { - sa->load_sum = decay_load(sa->load_sum, periods); - sa->runnable_load_sum = - decay_load(sa->runnable_load_sum, periods); - sa->util_sum = decay_load((u64)(sa->util_sum), periods); - - /* - * Step 2 - */ - delta %= 1024; - contrib = __accumulate_pelt_segments(periods, - 1024 - sa->period_contrib, delta); - } - sa->period_contrib = delta; - - contrib = cap_scale(contrib, scale_freq); - if (load) - sa->load_sum += load * contrib; - if (runnable) - sa->runnable_load_sum += runnable * contrib; - if (running) - sa->util_sum += contrib * scale_cpu; - - return periods; -} - -/* - * We can represent the historical contribution to runnable average as the - * coefficients of a geometric series. To do this we sub-divide our runnable - * history into segments of approximately 1ms (1024us); label the segment that - * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g. - * - * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ... - * p0 p1 p2 - * (now) (~1ms ago) (~2ms ago) - * - * Let u_i denote the fraction of p_i that the entity was runnable. - * - * We then designate the fractions u_i as our co-efficients, yielding the - * following representation of historical load: - * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ... - * - * We choose y based on the with of a reasonably scheduling period, fixing: - * y^32 = 0.5 - * - * This means that the contribution to load ~32ms ago (u_32) will be weighted - * approximately half as much as the contribution to load within the last ms - * (u_0). - * - * When a period "rolls over" and we have new u_0`, multiplying the previous - * sum again by y is sufficient to update: - * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) - * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] - */ -static __always_inline int -___update_load_sum(u64 now, int cpu, struct sched_avg *sa, - unsigned long load, unsigned long runnable, int running) -{ - u64 delta; - - delta = now - sa->last_update_time; - /* - * This should only happen when time goes backwards, which it - * unfortunately does during sched clock init when we swap over to TSC. - */ - if ((s64)delta < 0) { - sa->last_update_time = now; - return 0; - } - - /* - * Use 1024ns as the unit of measurement since it's a reasonable - * approximation of 1us and fast to compute. - */ - delta >>= 10; - if (!delta) - return 0; - - sa->last_update_time += delta << 10; - - /* - * running is a subset of runnable (weight) so running can't be set if - * runnable is clear. But there are some corner cases where the current - * se has been already dequeued but cfs_rq->curr still points to it. - * This means that weight will be 0 but not running for a sched_entity - * but also for a cfs_rq if the latter becomes idle. As an example, - * this happens during idle_balance() which calls - * update_blocked_averages() - */ - if (!load) - runnable = running = 0; - - /* - * Now we know we crossed measurement unit boundaries. The *_avg - * accrues by two steps: - * - * Step 1: accumulate *_sum since last_update_time. If we haven't - * crossed period boundaries, finish. - */ - if (!accumulate_sum(delta, cpu, sa, load, runnable, running)) - return 0; - - return 1; -} - -static __always_inline void -___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable) -{ - u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib; - - /* - * Step 2: update *_avg. - */ - sa->load_avg = div_u64(load * sa->load_sum, divider); - sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider); - sa->util_avg = sa->util_sum / divider; -} - -/* - * When a task is dequeued, its estimated utilization should not be update if - * its util_avg has not been updated at least once. - * This flag is used to synchronize util_avg updates with util_est updates. - * We map this information into the LSB bit of the utilization saved at - * dequeue time (i.e. util_est.dequeued). - */ -#define UTIL_AVG_UNCHANGED 0x1 - -static inline void cfs_se_util_change(struct sched_avg *avg) -{ - unsigned int enqueued; - - if (!sched_feat(UTIL_EST)) - return; - - /* Avoid store if the flag has been already set */ - enqueued = avg->util_est.enqueued; - if (!(enqueued & UTIL_AVG_UNCHANGED)) - return; - - /* Reset flag to report util_avg has been updated */ - enqueued &= ~UTIL_AVG_UNCHANGED; - WRITE_ONCE(avg->util_est.enqueued, enqueued); -} - -/* - * sched_entity: - * - * task: - * se_runnable() == se_weight() - * - * group: [ see update_cfs_group() ] - * se_weight() = tg->weight * grq->load_avg / tg->load_avg - * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg - * - * load_sum := runnable_sum - * load_avg = se_weight(se) * runnable_avg - * - * runnable_load_sum := runnable_sum - * runnable_load_avg = se_runnable(se) * runnable_avg - * - * XXX collapse load_sum and runnable_load_sum - * - * cfq_rs: - * - * load_sum = \Sum se_weight(se) * se->avg.load_sum - * load_avg = \Sum se->avg.load_avg - * - * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum - * runnable_load_avg = \Sum se->avg.runable_load_avg - */ - -static int -__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) -{ - if (entity_is_task(se)) - se->runnable_weight = se->load.weight; - - if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) { - ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); - return 1; - } - - return 0; -} - -static int -__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - if (entity_is_task(se)) - se->runnable_weight = se->load.weight; - - if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq, - cfs_rq->curr == se)) { - - ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); - cfs_se_util_change(&se->avg); - return 1; - } - - return 0; -} - -static int -__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) -{ - if (___update_load_sum(now, cpu, &cfs_rq->avg, - scale_load_down(cfs_rq->load.weight), - scale_load_down(cfs_rq->runnable_weight), - cfs_rq->curr != NULL)) { - - ___update_load_avg(&cfs_rq->avg, 1, 1); - return 1; - } - - return 0; -} - #ifdef CONFIG_FAIR_GROUP_SCHED /** * update_tg_load_avg - update the tg's load avg @@ -4037,12 +3648,6 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) #else /* CONFIG_SMP */ -static inline int -update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) -{ - return 0; -} - #define UPDATE_TG 0x0 #define SKIP_AGE_LOAD 0x0 #define DO_ATTACH 0x0 @@ -4726,7 +4331,6 @@ static inline int throttled_lb_pair(struct task_group *tg, throttled_hierarchy(dest_cfs_rq); } -/* updated child weight may affect parent so we have to do this bottom up */ static int tg_unthrottle_up(struct task_group *tg, void *data) { struct rq *rq = data; @@ -5653,8 +5257,6 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load, this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; } - - sched_avg_update(this_rq); } /* Used instead of source_load when we know the type == 0 */ @@ -7294,8 +6896,8 @@ static int task_hot(struct task_struct *p, struct lb_env *env) static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) { struct numa_group *numa_group = rcu_dereference(p->numa_group); - unsigned long src_faults, dst_faults; - int src_nid, dst_nid; + unsigned long src_weight, dst_weight; + int src_nid, dst_nid, dist; if (!static_branch_likely(&sched_numa_balancing)) return -1; @@ -7322,18 +6924,19 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) return 0; /* Leaving a core idle is often worse than degrading locality. */ - if (env->idle != CPU_NOT_IDLE) + if (env->idle == CPU_IDLE) return -1; + dist = node_distance(src_nid, dst_nid); if (numa_group) { - src_faults = group_faults(p, src_nid); - dst_faults = group_faults(p, dst_nid); + src_weight = group_weight(p, src_nid, dist); + dst_weight = group_weight(p, dst_nid, dist); } else { - src_faults = task_faults(p, src_nid); - dst_faults = task_faults(p, dst_nid); + src_weight = task_weight(p, src_nid, dist); + dst_weight = task_weight(p, dst_nid, dist); } - return dst_faults < src_faults; + return dst_weight < src_weight; } #else @@ -7620,6 +7223,22 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) return false; } +static inline bool others_have_blocked(struct rq *rq) +{ + if (READ_ONCE(rq->avg_rt.util_avg)) + return true; + + if (READ_ONCE(rq->avg_dl.util_avg)) + return true; + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + if (READ_ONCE(rq->avg_irq.util_avg)) + return true; +#endif + + return false; +} + #ifdef CONFIG_FAIR_GROUP_SCHED static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) @@ -7679,6 +7298,12 @@ static void update_blocked_averages(int cpu) if (cfs_rq_has_blocked(cfs_rq)) done = false; } + update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + update_irq_load_avg(rq, 0); + /* Don't need periodic decay once load/util_avg are null */ + if (others_have_blocked(rq)) + done = false; #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; @@ -7744,9 +7369,12 @@ static inline void update_blocked_averages(int cpu) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + update_irq_load_avg(rq, 0); #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; - if (!cfs_rq_has_blocked(cfs_rq)) + if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq)) rq->has_blocked_load = 0; #endif rq_unlock_irqrestore(rq, &rf); @@ -7856,39 +7484,32 @@ static inline int get_sd_load_idx(struct sched_domain *sd, static unsigned long scale_rt_capacity(int cpu) { struct rq *rq = cpu_rq(cpu); - u64 total, used, age_stamp, avg; - s64 delta; + unsigned long max = arch_scale_cpu_capacity(NULL, cpu); + unsigned long used, free; + unsigned long irq; - /* - * Since we're reading these variables without serialization make sure - * we read them once before doing sanity checks on them. - */ - age_stamp = READ_ONCE(rq->age_stamp); - avg = READ_ONCE(rq->rt_avg); - delta = __rq_clock_broken(rq) - age_stamp; + irq = cpu_util_irq(rq); - if (unlikely(delta < 0)) - delta = 0; + if (unlikely(irq >= max)) + return 1; - total = sched_avg_period() + delta; + used = READ_ONCE(rq->avg_rt.util_avg); + used += READ_ONCE(rq->avg_dl.util_avg); - used = div_u64(avg, total); + if (unlikely(used >= max)) + return 1; - if (likely(used < SCHED_CAPACITY_SCALE)) - return SCHED_CAPACITY_SCALE - used; + free = max - used; - return 1; + return scale_irq_capacity(free, irq, max); } static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity = arch_scale_cpu_capacity(sd, cpu); + unsigned long capacity = scale_rt_capacity(cpu); struct sched_group *sdg = sd->groups; - cpu_rq(cpu)->cpu_capacity_orig = capacity; - - capacity *= scale_rt_capacity(cpu); - capacity >>= SCHED_CAPACITY_SHIFT; + cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu); if (!capacity) capacity = 1; diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c new file mode 100644 index 000000000000..35475c0c5419 --- /dev/null +++ b/kernel/sched/pelt.c @@ -0,0 +1,399 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Per Entity Load Tracking + * + * Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * Interactivity improvements by Mike Galbraith + * (C) 2007 Mike Galbraith <efault@gmx.de> + * + * Various enhancements by Dmitry Adamushko. + * (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com> + * + * Group scheduling enhancements by Srivatsa Vaddagiri + * Copyright IBM Corporation, 2007 + * Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> + * + * Scaled math optimizations by Thomas Gleixner + * Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de> + * + * Adaptive scheduling granularity, math enhancements by Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * + * Move PELT related code from fair.c into this pelt.c file + * Author: Vincent Guittot <vincent.guittot@linaro.org> + */ + +#include <linux/sched.h> +#include "sched.h" +#include "sched-pelt.h" +#include "pelt.h" + +/* + * Approximate: + * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) + */ +static u64 decay_load(u64 val, u64 n) +{ + unsigned int local_n; + + if (unlikely(n > LOAD_AVG_PERIOD * 63)) + return 0; + + /* after bounds checking we can collapse to 32-bit */ + local_n = n; + + /* + * As y^PERIOD = 1/2, we can combine + * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD) + * With a look-up table which covers y^n (n<PERIOD) + * + * To achieve constant time decay_load. + */ + if (unlikely(local_n >= LOAD_AVG_PERIOD)) { + val >>= local_n / LOAD_AVG_PERIOD; + local_n %= LOAD_AVG_PERIOD; + } + + val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32); + return val; +} + +static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) +{ + u32 c1, c2, c3 = d3; /* y^0 == 1 */ + + /* + * c1 = d1 y^p + */ + c1 = decay_load((u64)d1, periods); + + /* + * p-1 + * c2 = 1024 \Sum y^n + * n=1 + * + * inf inf + * = 1024 ( \Sum y^n - \Sum y^n - y^0 ) + * n=0 n=p + */ + c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024; + + return c1 + c2 + c3; +} + +#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT) + +/* + * Accumulate the three separate parts of the sum; d1 the remainder + * of the last (incomplete) period, d2 the span of full periods and d3 + * the remainder of the (incomplete) current period. + * + * d1 d2 d3 + * ^ ^ ^ + * | | | + * |<->|<----------------->|<--->| + * ... |---x---|------| ... |------|-----x (now) + * + * p-1 + * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0 + * n=1 + * + * = u y^p + (Step 1) + * + * p-1 + * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2) + * n=1 + */ +static __always_inline u32 +accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, + unsigned long load, unsigned long runnable, int running) +{ + unsigned long scale_freq, scale_cpu; + u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ + u64 periods; + + scale_freq = arch_scale_freq_capacity(cpu); + scale_cpu = arch_scale_cpu_capacity(NULL, cpu); + + delta += sa->period_contrib; + periods = delta / 1024; /* A period is 1024us (~1ms) */ + + /* + * Step 1: decay old *_sum if we crossed period boundaries. + */ + if (periods) { + sa->load_sum = decay_load(sa->load_sum, periods); + sa->runnable_load_sum = + decay_load(sa->runnable_load_sum, periods); + sa->util_sum = decay_load((u64)(sa->util_sum), periods); + + /* + * Step 2 + */ + delta %= 1024; + contrib = __accumulate_pelt_segments(periods, + 1024 - sa->period_contrib, delta); + } + sa->period_contrib = delta; + + contrib = cap_scale(contrib, scale_freq); + if (load) + sa->load_sum += load * contrib; + if (runnable) + sa->runnable_load_sum += runnable * contrib; + if (running) + sa->util_sum += contrib * scale_cpu; + + return periods; +} + +/* + * We can represent the historical contribution to runnable average as the + * coefficients of a geometric series. To do this we sub-divide our runnable + * history into segments of approximately 1ms (1024us); label the segment that + * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g. + * + * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ... + * p0 p1 p2 + * (now) (~1ms ago) (~2ms ago) + * + * Let u_i denote the fraction of p_i that the entity was runnable. + * + * We then designate the fractions u_i as our co-efficients, yielding the + * following representation of historical load: + * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ... + * + * We choose y based on the with of a reasonably scheduling period, fixing: + * y^32 = 0.5 + * + * This means that the contribution to load ~32ms ago (u_32) will be weighted + * approximately half as much as the contribution to load within the last ms + * (u_0). + * + * When a period "rolls over" and we have new u_0`, multiplying the previous + * sum again by y is sufficient to update: + * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) + * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] + */ +static __always_inline int +___update_load_sum(u64 now, int cpu, struct sched_avg *sa, + unsigned long load, unsigned long runnable, int running) +{ + u64 delta; + + delta = now - sa->last_update_time; + /* + * This should only happen when time goes backwards, which it + * unfortunately does during sched clock init when we swap over to TSC. + */ + if ((s64)delta < 0) { + sa->last_update_time = now; + return 0; + } + + /* + * Use 1024ns as the unit of measurement since it's a reasonable + * approximation of 1us and fast to compute. + */ + delta >>= 10; + if (!delta) + return 0; + + sa->last_update_time += delta << 10; + + /* + * running is a subset of runnable (weight) so running can't be set if + * runnable is clear. But there are some corner cases where the current + * se has been already dequeued but cfs_rq->curr still points to it. + * This means that weight will be 0 but not running for a sched_entity + * but also for a cfs_rq if the latter becomes idle. As an example, + * this happens during idle_balance() which calls + * update_blocked_averages() + */ + if (!load) + runnable = running = 0; + + /* + * Now we know we crossed measurement unit boundaries. The *_avg + * accrues by two steps: + * + * Step 1: accumulate *_sum since last_update_time. If we haven't + * crossed period boundaries, finish. + */ + if (!accumulate_sum(delta, cpu, sa, load, runnable, running)) + return 0; + + return 1; +} + +static __always_inline void +___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable) +{ + u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib; + + /* + * Step 2: update *_avg. + */ + sa->load_avg = div_u64(load * sa->load_sum, divider); + sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider); + WRITE_ONCE(sa->util_avg, sa->util_sum / divider); +} + +/* + * sched_entity: + * + * task: + * se_runnable() == se_weight() + * + * group: [ see update_cfs_group() ] + * se_weight() = tg->weight * grq->load_avg / tg->load_avg + * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg + * + * load_sum := runnable_sum + * load_avg = se_weight(se) * runnable_avg + * + * runnable_load_sum := runnable_sum + * runnable_load_avg = se_runnable(se) * runnable_avg + * + * XXX collapse load_sum and runnable_load_sum + * + * cfq_rq: + * + * load_sum = \Sum se_weight(se) * se->avg.load_sum + * load_avg = \Sum se->avg.load_avg + * + * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum + * runnable_load_avg = \Sum se->avg.runable_load_avg + */ + +int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) +{ + if (entity_is_task(se)) + se->runnable_weight = se->load.weight; + + if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) { + ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); + return 1; + } + + return 0; +} + +int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + if (entity_is_task(se)) + se->runnable_weight = se->load.weight; + + if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq, + cfs_rq->curr == se)) { + + ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); + cfs_se_util_change(&se->avg); + return 1; + } + + return 0; +} + +int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) +{ + if (___update_load_sum(now, cpu, &cfs_rq->avg, + scale_load_down(cfs_rq->load.weight), + scale_load_down(cfs_rq->runnable_weight), + cfs_rq->curr != NULL)) { + + ___update_load_avg(&cfs_rq->avg, 1, 1); + return 1; + } + + return 0; +} + +/* + * rt_rq: + * + * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked + * util_sum = cpu_scale * load_sum + * runnable_load_sum = load_sum + * + * load_avg and runnable_load_avg are not supported and meaningless. + * + */ + +int update_rt_rq_load_avg(u64 now, struct rq *rq, int running) +{ + if (___update_load_sum(now, rq->cpu, &rq->avg_rt, + running, + running, + running)) { + + ___update_load_avg(&rq->avg_rt, 1, 1); + return 1; + } + + return 0; +} + +/* + * dl_rq: + * + * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked + * util_sum = cpu_scale * load_sum + * runnable_load_sum = load_sum + * + */ + +int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) +{ + if (___update_load_sum(now, rq->cpu, &rq->avg_dl, + running, + running, + running)) { + + ___update_load_avg(&rq->avg_dl, 1, 1); + return 1; + } + + return 0; +} + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +/* + * irq: + * + * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked + * util_sum = cpu_scale * load_sum + * runnable_load_sum = load_sum + * + */ + +int update_irq_load_avg(struct rq *rq, u64 running) +{ + int ret = 0; + /* + * We know the time that has been used by interrupt since last update + * but we don't when. Let be pessimistic and assume that interrupt has + * happened just before the update. This is not so far from reality + * because interrupt will most probably wake up task and trig an update + * of rq clock during which the metric si updated. + * We start to decay with normal context time and then we add the + * interrupt context time. + * We can safely remove running from rq->clock because + * rq->clock += delta with delta >= running + */ + ret = ___update_load_sum(rq->clock - running, rq->cpu, &rq->avg_irq, + 0, + 0, + 0); + ret += ___update_load_sum(rq->clock, rq->cpu, &rq->avg_irq, + 1, + 1, + 1); + + if (ret) + ___update_load_avg(&rq->avg_irq, 1, 1); + + return ret; +} +#endif diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h new file mode 100644 index 000000000000..d2894db28955 --- /dev/null +++ b/kernel/sched/pelt.h @@ -0,0 +1,72 @@ +#ifdef CONFIG_SMP + +int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se); +int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se); +int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq); +int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); +int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +int update_irq_load_avg(struct rq *rq, u64 running); +#else +static inline int +update_irq_load_avg(struct rq *rq, u64 running) +{ + return 0; +} +#endif + +/* + * When a task is dequeued, its estimated utilization should not be update if + * its util_avg has not been updated at least once. + * This flag is used to synchronize util_avg updates with util_est updates. + * We map this information into the LSB bit of the utilization saved at + * dequeue time (i.e. util_est.dequeued). + */ +#define UTIL_AVG_UNCHANGED 0x1 + +static inline void cfs_se_util_change(struct sched_avg *avg) +{ + unsigned int enqueued; + + if (!sched_feat(UTIL_EST)) + return; + + /* Avoid store if the flag has been already set */ + enqueued = avg->util_est.enqueued; + if (!(enqueued & UTIL_AVG_UNCHANGED)) + return; + + /* Reset flag to report util_avg has been updated */ + enqueued &= ~UTIL_AVG_UNCHANGED; + WRITE_ONCE(avg->util_est.enqueued, enqueued); +} + +#else + +static inline int +update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int +update_rt_rq_load_avg(u64 now, struct rq *rq, int running) +{ + return 0; +} + +static inline int +update_dl_rq_load_avg(u64 now, struct rq *rq, int running) +{ + return 0; +} + +static inline int +update_irq_load_avg(struct rq *rq, u64 running) +{ + return 0; +} +#endif + + diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 572567078b60..2e2955a8cf8f 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -5,6 +5,8 @@ */ #include "sched.h" +#include "pelt.h" + int sched_rr_timeslice = RR_TIMESLICE; int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; @@ -836,6 +838,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) * can be time-consuming. Try to avoid it when possible. */ raw_spin_lock(&rt_rq->rt_runtime_lock); + if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF) + rt_rq->rt_runtime = rt_b->rt_runtime; skip = !rt_rq->rt_time && !rt_rq->rt_nr_running; raw_spin_unlock(&rt_rq->rt_runtime_lock); if (skip) @@ -971,8 +975,6 @@ static void update_curr_rt(struct rq *rq) curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); - sched_rt_avg_update(rq, delta_exec); - if (!rt_bandwidth_enabled()) return; @@ -1576,6 +1578,14 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) rt_queue_push_tasks(rq); + /* + * If prev task was rt, put_prev_task() has already updated the + * utilization. We only care of the case where we start to schedule a + * rt task + */ + if (rq->curr->sched_class != &rt_sched_class) + update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + return p; } @@ -1583,6 +1593,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); + /* * The previous task needs to be made eligible for pushing * if it is still active @@ -2312,6 +2324,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); watchdog(rq, p); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c7742dcc136c..4a2e8cae63c4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -594,6 +594,7 @@ struct rt_rq { unsigned long rt_nr_total; int overloaded; struct plist_head pushable_tasks; + #endif /* CONFIG_SMP */ int rt_queued; @@ -673,7 +674,26 @@ struct dl_rq { u64 bw_ratio; }; +#ifdef CONFIG_FAIR_GROUP_SCHED +/* An entity is a task if it doesn't "own" a runqueue */ +#define entity_is_task(se) (!se->my_q) +#else +#define entity_is_task(se) 1 +#endif + #ifdef CONFIG_SMP +/* + * XXX we want to get rid of these helpers and use the full load resolution. + */ +static inline long se_weight(struct sched_entity *se) +{ + return scale_load_down(se->load.weight); +} + +static inline long se_runnable(struct sched_entity *se) +{ + return scale_load_down(se->runnable_weight); +} static inline bool sched_asym_prefer(int a, int b) { @@ -833,8 +853,12 @@ struct rq { struct list_head cfs_tasks; - u64 rt_avg; - u64 age_stamp; + struct sched_avg avg_rt; + struct sched_avg avg_dl; +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +#define HAVE_SCHED_AVG_IRQ + struct sched_avg avg_irq; +#endif u64 idle_stamp; u64 avg_idle; @@ -1075,7 +1099,8 @@ enum numa_faults_stats { }; extern void sched_setnuma(struct task_struct *p, int node); extern int migrate_task_to(struct task_struct *p, int cpu); -extern int migrate_swap(struct task_struct *, struct task_struct *); +extern int migrate_swap(struct task_struct *p, struct task_struct *t, + int cpu, int scpu); extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p); #else static inline void @@ -1690,15 +1715,9 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); -extern const_debug unsigned int sysctl_sched_time_avg; extern const_debug unsigned int sysctl_sched_nr_migrate; extern const_debug unsigned int sysctl_sched_migration_cost; -static inline u64 sched_avg_period(void) -{ - return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2; -} - #ifdef CONFIG_SCHED_HRTICK /* @@ -1735,8 +1754,6 @@ unsigned long arch_scale_freq_capacity(int cpu) #endif #ifdef CONFIG_SMP -extern void sched_avg_update(struct rq *rq); - #ifndef arch_scale_cpu_capacity static __always_inline unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) @@ -1747,12 +1764,6 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) return SCHED_CAPACITY_SCALE; } #endif - -static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) -{ - rq->rt_avg += rt_delta * arch_scale_freq_capacity(cpu_of(rq)); - sched_avg_update(rq); -} #else #ifndef arch_scale_cpu_capacity static __always_inline @@ -1761,8 +1772,6 @@ unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) return SCHED_CAPACITY_SCALE; } #endif -static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } -static inline void sched_avg_update(struct rq *rq) { } #endif struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) @@ -2177,11 +2186,16 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL -static inline unsigned long cpu_util_dl(struct rq *rq) +static inline unsigned long cpu_bw_dl(struct rq *rq) { return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT; } +static inline unsigned long cpu_util_dl(struct rq *rq) +{ + return READ_ONCE(rq->avg_dl.util_avg); +} + static inline unsigned long cpu_util_cfs(struct rq *rq) { unsigned long util = READ_ONCE(rq->cfs.avg.util_avg); @@ -2193,4 +2207,37 @@ static inline unsigned long cpu_util_cfs(struct rq *rq) return util; } + +static inline unsigned long cpu_util_rt(struct rq *rq) +{ + return READ_ONCE(rq->avg_rt.util_avg); +} +#endif + +#ifdef HAVE_SCHED_AVG_IRQ +static inline unsigned long cpu_util_irq(struct rq *rq) +{ + return rq->avg_irq.util_avg; +} + +static inline +unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max) +{ + util *= (max - irq); + util /= max; + + return util; + +} +#else +static inline unsigned long cpu_util_irq(struct rq *rq) +{ + return 0; +} + +static inline +unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max) +{ + return util; +} #endif diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index b6fb2c3b3ff7..66b59ac77c22 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -32,7 +32,7 @@ void swake_up_locked(struct swait_queue_head *q) } EXPORT_SYMBOL(swake_up_locked); -void swake_up(struct swait_queue_head *q) +void swake_up_one(struct swait_queue_head *q) { unsigned long flags; @@ -40,7 +40,7 @@ void swake_up(struct swait_queue_head *q) swake_up_locked(q); raw_spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL(swake_up); +EXPORT_SYMBOL(swake_up_one); /* * Does not allow usage from IRQ disabled, since we must be able to @@ -69,14 +69,14 @@ void swake_up_all(struct swait_queue_head *q) } EXPORT_SYMBOL(swake_up_all); -void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) +static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) { wait->task = current; if (list_empty(&wait->task_list)) - list_add(&wait->task_list, &q->task_list); + list_add_tail(&wait->task_list, &q->task_list); } -void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state) +void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state) { unsigned long flags; @@ -85,16 +85,28 @@ void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int set_current_state(state); raw_spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL(prepare_to_swait); +EXPORT_SYMBOL(prepare_to_swait_exclusive); long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state) { - if (signal_pending_state(state, current)) - return -ERESTARTSYS; + unsigned long flags; + long ret = 0; - prepare_to_swait(q, wait, state); + raw_spin_lock_irqsave(&q->lock, flags); + if (unlikely(signal_pending_state(state, current))) { + /* + * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one() + * must not see us. + */ + list_del_init(&wait->task_list); + ret = -ERESTARTSYS; + } else { + __prepare_to_swait(q, wait); + set_current_state(state); + } + raw_spin_unlock_irqrestore(&q->lock, flags); - return 0; + return ret; } EXPORT_SYMBOL(prepare_to_swait_event); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 05a831427bc7..56a0fed30c0a 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -47,7 +47,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu); } - if (!cpumask_test_cpu(cpu, sched_group_span(group))) { + if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) { printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu); } diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 928be527477e..870f97b313e3 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -134,8 +134,8 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: is directly passed to the wakeup function * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) @@ -180,8 +180,8 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark); * * On UP it can prevent extra preemption. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) @@ -392,35 +392,36 @@ static inline bool is_kthread_should_stop(void) * if (condition) * break; * - * p->state = mode; condition = true; - * smp_mb(); // A smp_wmb(); // C - * if (!wq_entry->flags & WQ_FLAG_WOKEN) wq_entry->flags |= WQ_FLAG_WOKEN; - * schedule() try_to_wake_up(); - * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~ - * wq_entry->flags &= ~WQ_FLAG_WOKEN; condition = true; - * smp_mb() // B smp_wmb(); // C - * wq_entry->flags |= WQ_FLAG_WOKEN; - * } - * remove_wait_queue(&wq_head, &wait); + * // in wait_woken() // in woken_wake_function() * + * p->state = mode; wq_entry->flags |= WQ_FLAG_WOKEN; + * smp_mb(); // A try_to_wake_up(): + * if (!(wq_entry->flags & WQ_FLAG_WOKEN)) <full barrier> + * schedule() if (p->state & mode) + * p->state = TASK_RUNNING; p->state = TASK_RUNNING; + * wq_entry->flags &= ~WQ_FLAG_WOKEN; ~~~~~~~~~~~~~~~~~~ + * smp_mb(); // B condition = true; + * } smp_mb(); // C + * remove_wait_queue(&wq_head, &wait); wq_entry->flags |= WQ_FLAG_WOKEN; */ long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout) { - set_current_state(mode); /* A */ /* - * The above implies an smp_mb(), which matches with the smp_wmb() from - * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must - * also observe all state before the wakeup. + * The below executes an smp_mb(), which matches with the full barrier + * executed by the try_to_wake_up() in woken_wake_function() such that + * either we see the store to wq_entry->flags in woken_wake_function() + * or woken_wake_function() sees our store to current->state. */ + set_current_state(mode); /* A */ if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop()) timeout = schedule_timeout(timeout); __set_current_state(TASK_RUNNING); /* - * The below implies an smp_mb(), it too pairs with the smp_wmb() from - * woken_wake_function() such that we must either observe the wait - * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss - * an event. + * The below executes an smp_mb(), which matches with the smp_mb() (C) + * in woken_wake_function() such that either we see the wait condition + * being true or the store to wq_entry->flags in woken_wake_function() + * follows ours in the coherence order. */ smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */ @@ -430,14 +431,8 @@ EXPORT_SYMBOL(wait_woken); int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key) { - /* - * Although this function is called under waitqueue lock, LOCK - * doesn't imply write barrier and the users expects write - * barrier semantics on wakeup functions. The following - * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() - * and is paired with smp_store_mb() in wait_woken(). - */ - smp_wmb(); /* C */ + /* Pairs with the smp_store_mb() in wait_woken(). */ + smp_mb(); /* C */ wq_entry->flags |= WQ_FLAG_WOKEN; return default_wake_function(wq_entry, mode, sync, key); diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 5043e7433f4b..c230c2dd48e1 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -238,8 +238,7 @@ int smpboot_unpark_threads(unsigned int cpu) mutex_lock(&smpboot_threads_lock); list_for_each_entry(cur, &hotplug_threads, list) - if (cpumask_test_cpu(cpu, cur->cpumask)) - smpboot_unpark_thread(cur, cpu); + smpboot_unpark_thread(cur, cpu); mutex_unlock(&smpboot_threads_lock); return 0; } @@ -280,34 +279,26 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht) } /** - * smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related + * smpboot_register_percpu_thread - Register a per_cpu thread related * to hotplug * @plug_thread: Hotplug thread descriptor - * @cpumask: The cpumask where threads run * * Creates and starts the threads on all online cpus. */ -int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread, - const struct cpumask *cpumask) +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) { unsigned int cpu; int ret = 0; - if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL)) - return -ENOMEM; - cpumask_copy(plug_thread->cpumask, cpumask); - get_online_cpus(); mutex_lock(&smpboot_threads_lock); for_each_online_cpu(cpu) { ret = __smpboot_create_thread(plug_thread, cpu); if (ret) { smpboot_destroy_threads(plug_thread); - free_cpumask_var(plug_thread->cpumask); goto out; } - if (cpumask_test_cpu(cpu, cpumask)) - smpboot_unpark_thread(plug_thread, cpu); + smpboot_unpark_thread(plug_thread, cpu); } list_add(&plug_thread->list, &hotplug_threads); out: @@ -315,7 +306,7 @@ out: put_online_cpus(); return ret; } -EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask); +EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread); /** * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug @@ -331,44 +322,9 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) smpboot_destroy_threads(plug_thread); mutex_unlock(&smpboot_threads_lock); put_online_cpus(); - free_cpumask_var(plug_thread->cpumask); } EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); -/** - * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked - * @plug_thread: Hotplug thread descriptor - * @new: Revised mask to use - * - * The cpumask field in the smp_hotplug_thread must not be updated directly - * by the client, but only by calling this function. - * This function can only be called on a registered smp_hotplug_thread. - */ -void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) -{ - struct cpumask *old = plug_thread->cpumask; - static struct cpumask tmp; - unsigned int cpu; - - lockdep_assert_cpus_held(); - mutex_lock(&smpboot_threads_lock); - - /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(&tmp, old, new); - for_each_cpu_and(cpu, &tmp, cpu_online_mask) - smpboot_park_thread(plug_thread, cpu); - - /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(&tmp, new, old); - for_each_cpu_and(cpu, &tmp, cpu_online_mask) - smpboot_unpark_thread(plug_thread, cpu); - - cpumask_copy(old, new); - - mutex_unlock(&smpboot_threads_lock); -} - static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); /* diff --git a/kernel/softirq.c b/kernel/softirq.c index 900dcfee542c..6f584861d329 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -79,12 +79,16 @@ static void wakeup_softirqd(void) /* * If ksoftirqd is scheduled, we do not want to process pending softirqs - * right now. Let ksoftirqd handle this at its own rate, to get fairness. + * right now. Let ksoftirqd handle this at its own rate, to get fairness, + * unless we're doing some of the synchronous softirqs. */ -static bool ksoftirqd_running(void) +#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ)) +static bool ksoftirqd_running(unsigned long pending) { struct task_struct *tsk = __this_cpu_read(ksoftirqd); + if (pending & SOFTIRQ_NOW_MASK) + return false; return tsk && (tsk->state == TASK_RUNNING); } @@ -328,7 +332,7 @@ asmlinkage __visible void do_softirq(void) pending = local_softirq_pending(); - if (pending && !ksoftirqd_running()) + if (pending && !ksoftirqd_running(pending)) do_softirq_own_stack(); local_irq_restore(flags); @@ -355,7 +359,7 @@ void irq_enter(void) static inline void invoke_softirq(void) { - if (ksoftirqd_running()) + if (ksoftirqd_running(local_softirq_pending())) return; if (!force_irqthreads) { @@ -386,7 +390,7 @@ static inline void tick_irq_exit(void) /* Make sure that timer wheel updates are propagated */ if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) { - if (!in_interrupt()) + if (!in_irq()) tick_nohz_irq_exit(); } #endif diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index f89014a2c238..067cb83f37ea 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -81,6 +81,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) unsigned long flags; bool enabled; + preempt_disable(); raw_spin_lock_irqsave(&stopper->lock, flags); enabled = stopper->enabled; if (enabled) @@ -90,6 +91,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) raw_spin_unlock_irqrestore(&stopper->lock, flags); wake_up_q(&wakeq); + preempt_enable(); return enabled; } @@ -236,13 +238,24 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1, struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2); DEFINE_WAKE_Q(wakeq); int err; + retry: + /* + * The waking up of stopper threads has to happen in the same + * scheduling context as the queueing. Otherwise, there is a + * possibility of one of the above stoppers being woken up by another + * CPU, and preempting us. This will cause us to not wake up the other + * stopper forever. + */ + preempt_disable(); raw_spin_lock_irq(&stopper1->lock); raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); - err = -ENOENT; - if (!stopper1->enabled || !stopper2->enabled) + if (!stopper1->enabled || !stopper2->enabled) { + err = -ENOENT; goto unlock; + } + /* * Ensure that if we race with __stop_cpus() the stoppers won't get * queued up in reverse order leading to system deadlock. @@ -253,24 +266,30 @@ retry: * It can be falsely true but it is safe to spin until it is cleared, * queue_stop_cpus_work() does everything under preempt_disable(). */ - err = -EDEADLK; - if (unlikely(stop_cpus_in_progress)) - goto unlock; + if (unlikely(stop_cpus_in_progress)) { + err = -EDEADLK; + goto unlock; + } err = 0; __cpu_stop_queue_work(stopper1, work1, &wakeq); __cpu_stop_queue_work(stopper2, work2, &wakeq); + unlock: raw_spin_unlock(&stopper2->lock); raw_spin_unlock_irq(&stopper1->lock); if (unlikely(err == -EDEADLK)) { + preempt_enable(); + while (stop_cpus_in_progress) cpu_relax(); + goto retry; } wake_up_q(&wakeq); + preempt_enable(); return err; } diff --git a/kernel/sys.c b/kernel/sys.c index 38509dc1f77b..e27b51d3facd 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2512,11 +2512,11 @@ static int do_sysinfo(struct sysinfo *info) { unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; - struct timespec tp; + struct timespec64 tp; memset(info, 0, sizeof(struct sysinfo)); - get_monotonic_boottime(&tp); + ktime_get_boottime_ts64(&tp); info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2d9837c0aff4..f22f76b7a138 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -368,14 +368,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "sched_time_avg_ms", - .data = &sysctl_sched_time_avg, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - }, #ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c index dd53e354f630..7bca480151b0 100644 --- a/kernel/test_kprobes.c +++ b/kernel/test_kprobes.c @@ -162,90 +162,6 @@ static int test_kprobes(void) } -#if 0 -static u32 jph_val; - -static u32 j_kprobe_target(u32 value) -{ - if (preemptible()) { - handler_errors++; - pr_err("jprobe-handler is preemptible\n"); - } - if (value != rand1) { - handler_errors++; - pr_err("incorrect value in jprobe handler\n"); - } - - jph_val = rand1; - jprobe_return(); - return 0; -} - -static struct jprobe jp = { - .entry = j_kprobe_target, - .kp.symbol_name = "kprobe_target" -}; - -static int test_jprobe(void) -{ - int ret; - - ret = register_jprobe(&jp); - if (ret < 0) { - pr_err("register_jprobe returned %d\n", ret); - return ret; - } - - ret = target(rand1); - unregister_jprobe(&jp); - if (jph_val == 0) { - pr_err("jprobe handler not called\n"); - handler_errors++; - } - - return 0; -} - -static struct jprobe jp2 = { - .entry = j_kprobe_target, - .kp.symbol_name = "kprobe_target2" -}; - -static int test_jprobes(void) -{ - int ret; - struct jprobe *jps[2] = {&jp, &jp2}; - - /* addr and flags should be cleard for reusing kprobe. */ - jp.kp.addr = NULL; - jp.kp.flags = 0; - ret = register_jprobes(jps, 2); - if (ret < 0) { - pr_err("register_jprobes returned %d\n", ret); - return ret; - } - - jph_val = 0; - ret = target(rand1); - if (jph_val == 0) { - pr_err("jprobe handler not called\n"); - handler_errors++; - } - - jph_val = 0; - ret = target2(rand1); - if (jph_val == 0) { - pr_err("jprobe handler2 not called\n"); - handler_errors++; - } - unregister_jprobes(jps, 2); - - return 0; -} -#else -#define test_jprobe() (0) -#define test_jprobes() (0) -#endif #ifdef CONFIG_KRETPROBES static u32 krph_val; @@ -383,16 +299,6 @@ int init_test_probes(void) if (ret < 0) errors++; - num_tests++; - ret = test_jprobe(); - if (ret < 0) - errors++; - - num_tests++; - ret = test_jprobes(); - if (ret < 0) - errors++; - #ifdef CONFIG_KRETPROBES num_tests++; ret = test_kretprobe(); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 639321bf2e39..fa5de5e8de61 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -581,11 +581,11 @@ static void alarm_timer_rearm(struct k_itimer *timr) * @timr: Pointer to the posixtimer data struct * @now: Current time to forward the timer against */ -static int alarm_timer_forward(struct k_itimer *timr, ktime_t now) +static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; - return (int) alarm_forward(alarm, timr->it_interval, now); + return alarm_forward(alarm, timr->it_interval, now); } /** @@ -808,7 +808,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, /* Convert (if necessary) to absolute time */ if (flags != TIMER_ABSTIME) { ktime_t now = alarm_bases[type].gettime(); - exp = ktime_add(now, exp); + + exp = ktime_add_safe(now, exp); } ret = alarmtimer_do_nsleep(&alarm, exp, type); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 16c027e9cc73..8c0e4092f661 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -463,6 +463,12 @@ void clockevents_register_device(struct clock_event_device *dev) dev->cpumask = cpumask_of(smp_processor_id()); } + if (dev->cpumask == cpu_all_mask) { + WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n", + dev->name); + dev->cpumask = cpu_possible_mask; + } + raw_spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index f89a78e2792b..f74fb00d8064 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -94,6 +94,8 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift); /*[Clocksource internal variables]--------- * curr_clocksource: * currently selected clocksource. + * suspend_clocksource: + * used to calculate the suspend time. * clocksource_list: * linked list with the registered clocksources * clocksource_mutex: @@ -102,10 +104,12 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift); * Name of the user-specified clocksource. */ static struct clocksource *curr_clocksource; +static struct clocksource *suspend_clocksource; static LIST_HEAD(clocksource_list); static DEFINE_MUTEX(clocksource_mutex); static char override_name[CS_NAME_LEN]; static int finished_booting; +static u64 suspend_start; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); @@ -447,6 +451,140 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) { } #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ +static bool clocksource_is_suspend(struct clocksource *cs) +{ + return cs == suspend_clocksource; +} + +static void __clocksource_suspend_select(struct clocksource *cs) +{ + /* + * Skip the clocksource which will be stopped in suspend state. + */ + if (!(cs->flags & CLOCK_SOURCE_SUSPEND_NONSTOP)) + return; + + /* + * The nonstop clocksource can be selected as the suspend clocksource to + * calculate the suspend time, so it should not supply suspend/resume + * interfaces to suspend the nonstop clocksource when system suspends. + */ + if (cs->suspend || cs->resume) { + pr_warn("Nonstop clocksource %s should not supply suspend/resume interfaces\n", + cs->name); + } + + /* Pick the best rating. */ + if (!suspend_clocksource || cs->rating > suspend_clocksource->rating) + suspend_clocksource = cs; +} + +/** + * clocksource_suspend_select - Select the best clocksource for suspend timing + * @fallback: if select a fallback clocksource + */ +static void clocksource_suspend_select(bool fallback) +{ + struct clocksource *cs, *old_suspend; + + old_suspend = suspend_clocksource; + if (fallback) + suspend_clocksource = NULL; + + list_for_each_entry(cs, &clocksource_list, list) { + /* Skip current if we were requested for a fallback. */ + if (fallback && cs == old_suspend) + continue; + + __clocksource_suspend_select(cs); + } +} + +/** + * clocksource_start_suspend_timing - Start measuring the suspend timing + * @cs: current clocksource from timekeeping + * @start_cycles: current cycles from timekeeping + * + * This function will save the start cycle values of suspend timer to calculate + * the suspend time when resuming system. + * + * This function is called late in the suspend process from timekeeping_suspend(), + * that means processes are freezed, non-boot cpus and interrupts are disabled + * now. It is therefore possible to start the suspend timer without taking the + * clocksource mutex. + */ +void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles) +{ + if (!suspend_clocksource) + return; + + /* + * If current clocksource is the suspend timer, we should use the + * tkr_mono.cycle_last value as suspend_start to avoid same reading + * from suspend timer. + */ + if (clocksource_is_suspend(cs)) { + suspend_start = start_cycles; + return; + } + + if (suspend_clocksource->enable && + suspend_clocksource->enable(suspend_clocksource)) { + pr_warn_once("Failed to enable the non-suspend-able clocksource.\n"); + return; + } + + suspend_start = suspend_clocksource->read(suspend_clocksource); +} + +/** + * clocksource_stop_suspend_timing - Stop measuring the suspend timing + * @cs: current clocksource from timekeeping + * @cycle_now: current cycles from timekeeping + * + * This function will calculate the suspend time from suspend timer. + * + * Returns nanoseconds since suspend started, 0 if no usable suspend clocksource. + * + * This function is called early in the resume process from timekeeping_resume(), + * that means there is only one cpu, no processes are running and the interrupts + * are disabled. It is therefore possible to stop the suspend timer without + * taking the clocksource mutex. + */ +u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now) +{ + u64 now, delta, nsec = 0; + + if (!suspend_clocksource) + return 0; + + /* + * If current clocksource is the suspend timer, we should use the + * tkr_mono.cycle_last value from timekeeping as current cycle to + * avoid same reading from suspend timer. + */ + if (clocksource_is_suspend(cs)) + now = cycle_now; + else + now = suspend_clocksource->read(suspend_clocksource); + + if (now > suspend_start) { + delta = clocksource_delta(now, suspend_start, + suspend_clocksource->mask); + nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult, + suspend_clocksource->shift); + } + + /* + * Disable the suspend timer to save power if current clocksource is + * not the suspend timer. + */ + if (!clocksource_is_suspend(cs) && suspend_clocksource->disable) + suspend_clocksource->disable(suspend_clocksource); + + return nsec; +} + /** * clocksource_suspend - suspend the clocksource(s) */ @@ -792,6 +930,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) clocksource_select(); clocksource_select_watchdog(false); + __clocksource_suspend_select(cs); mutex_unlock(&clocksource_mutex); return 0; } @@ -820,6 +959,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating) clocksource_select(); clocksource_select_watchdog(false); + clocksource_suspend_select(false); mutex_unlock(&clocksource_mutex); } EXPORT_SYMBOL(clocksource_change_rating); @@ -845,6 +985,15 @@ static int clocksource_unbind(struct clocksource *cs) return -EBUSY; } + if (clocksource_is_suspend(cs)) { + /* + * Select and try to install a replacement suspend clocksource. + * If no replacement suspend clocksource, we will just let the + * clocksource go and have no suspend clocksource. + */ + clocksource_suspend_select(true); + } + clocksource_watchdog_lock(&flags); clocksource_dequeue_watchdog(cs); list_del_init(&cs->list); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 3e93c54bd3a1..e1a549c9e399 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -718,8 +718,8 @@ static void hrtimer_switch_to_hres(void) struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { - printk(KERN_WARNING "Could not switch to high resolution " - "mode on CPU %d\n", base->cpu); + pr_warn("Could not switch to high resolution mode on CPU %u\n", + base->cpu); return; } base->hres_active = 1; @@ -1573,8 +1573,7 @@ retry: else expires_next = ktime_add(now, delta); tick_program_event(expires_next, 1); - printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n", - ktime_to_ns(delta)); + pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } /* called with interrupts disabled */ diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index a09ded765f6c..c5e0cba3b39c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -502,7 +502,7 @@ static void sched_sync_hw_clock(struct timespec64 now, { struct timespec64 next; - getnstimeofday64(&next); + ktime_get_real_ts64(&next); if (!fail) next.tv_sec = 659; else { @@ -537,7 +537,7 @@ static void sync_rtc_clock(void) if (!IS_ENABLED(CONFIG_RTC_SYSTOHC)) return; - getnstimeofday64(&now); + ktime_get_real_ts64(&now); adjust = now; if (persistent_clock_is_local) @@ -591,7 +591,7 @@ static bool sync_cmos_clock(void) * Architectures are strongly encouraged to use rtclib and not * implement this legacy API. */ - getnstimeofday64(&now); + ktime_get_real_ts64(&now); if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) { if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); @@ -642,7 +642,7 @@ void ntp_notify_cmos_timer(void) /* * Propagate a new txc->status value into the NTP state: */ -static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) +static inline void process_adj_status(const struct timex *txc) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; @@ -665,12 +665,10 @@ static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) } -static inline void process_adjtimex_modes(struct timex *txc, - struct timespec64 *ts, - s32 *time_tai) +static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai) { if (txc->modes & ADJ_STATUS) - process_adj_status(txc, ts); + process_adj_status(txc); if (txc->modes & ADJ_NANO) time_status |= STA_NANO; @@ -718,7 +716,7 @@ static inline void process_adjtimex_modes(struct timex *txc, * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ -int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) +int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai) { int result; @@ -735,7 +733,7 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) /* If there are input parameters, then process them: */ if (txc->modes) - process_adjtimex_modes(txc, ts, time_tai); + process_adjtimex_modes(txc, time_tai); txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, NTP_SCALE_SHIFT); @@ -1022,12 +1020,11 @@ void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_t static int __init ntp_tick_adj_setup(char *str) { - int rc = kstrtol(str, 0, (long *)&ntp_tick_adj); - + int rc = kstrtos64(str, 0, &ntp_tick_adj); if (rc) return rc; - ntp_tick_adj <<= NTP_SCALE_SHIFT; + ntp_tick_adj <<= NTP_SCALE_SHIFT; return 1; } diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 909bd1f1bfb1..c24b0e13f011 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -8,6 +8,6 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern ktime_t ntp_get_next_leap(void); extern int second_overflow(time64_t secs); -extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); -extern void __hardpps(const struct timespec64 *, const struct timespec64 *); +extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai); +extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 9cdf54b04ca8..294d7b65af33 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -85,7 +85,7 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now) continue; timer->it.cpu.expires += incr; - timer->it_overrun += 1 << i; + timer->it_overrun += 1LL << i; delta -= incr; } } diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 26aa9569e24a..2c6847d5d69b 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -81,7 +81,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp) ktime_get_ts64(tp); break; case CLOCK_BOOTTIME: - get_monotonic_boottime64(tp); + ktime_get_boottime_ts64(tp); break; default: return -EINVAL; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index e08ce3f27447..3ac7295306dc 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -228,21 +228,21 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp) */ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp) { - getrawmonotonic64(tp); + ktime_get_raw_ts64(tp); return 0; } static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp) { - *tp = current_kernel_time64(); + ktime_get_coarse_real_ts64(tp); return 0; } static int posix_get_monotonic_coarse(clockid_t which_clock, struct timespec64 *tp) { - *tp = get_monotonic_coarse64(); + ktime_get_coarse_ts64(tp); return 0; } @@ -254,13 +254,13 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 * static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp) { - get_monotonic_boottime64(tp); + ktime_get_boottime_ts64(tp); return 0; } static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) { - timekeeping_clocktai64(tp); + ktime_get_clocktai_ts64(tp); return 0; } @@ -283,6 +283,17 @@ static __init int init_posix_timers(void) } __initcall(init_posix_timers); +/* + * The siginfo si_overrun field and the return value of timer_getoverrun(2) + * are of type int. Clamp the overrun value to INT_MAX + */ +static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval) +{ + s64 sum = timr->it_overrun_last + (s64)baseval; + + return sum > (s64)INT_MAX ? INT_MAX : (int)sum; +} + static void common_hrtimer_rearm(struct k_itimer *timr) { struct hrtimer *timer = &timr->it.real.timer; @@ -290,9 +301,8 @@ static void common_hrtimer_rearm(struct k_itimer *timr) if (!timr->it_interval) return; - timr->it_overrun += (unsigned int) hrtimer_forward(timer, - timer->base->get_time(), - timr->it_interval); + timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(), + timr->it_interval); hrtimer_restart(timer); } @@ -321,10 +331,10 @@ void posixtimer_rearm(struct siginfo *info) timr->it_active = 1; timr->it_overrun_last = timr->it_overrun; - timr->it_overrun = -1; + timr->it_overrun = -1LL; ++timr->it_requeue_pending; - info->si_overrun += timr->it_overrun_last; + info->si_overrun = timer_overrun_to_int(timr, info->si_overrun); } unlock_timer(timr, flags); @@ -418,9 +428,8 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) now = ktime_add(now, kj); } #endif - timr->it_overrun += (unsigned int) - hrtimer_forward(timer, now, - timr->it_interval); + timr->it_overrun += hrtimer_forward(timer, now, + timr->it_interval); ret = HRTIMER_RESTART; ++timr->it_requeue_pending; timr->it_active = 1; @@ -524,7 +533,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, new_timer->it_id = (timer_t) new_timer_id; new_timer->it_clock = which_clock; new_timer->kclock = kc; - new_timer->it_overrun = -1; + new_timer->it_overrun = -1LL; if (event) { rcu_read_lock(); @@ -645,11 +654,11 @@ static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now) return __hrtimer_expires_remaining_adjusted(timer, now); } -static int common_hrtimer_forward(struct k_itimer *timr, ktime_t now) +static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now) { struct hrtimer *timer = &timr->it.real.timer; - return (int)hrtimer_forward(timer, now, timr->it_interval); + return hrtimer_forward(timer, now, timr->it_interval); } /* @@ -743,7 +752,7 @@ static int do_timer_gettime(timer_t timer_id, struct itimerspec64 *setting) /* Get the time remaining on a POSIX.1b interval timer. */ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, - struct itimerspec __user *, setting) + struct __kernel_itimerspec __user *, setting) { struct itimerspec64 cur_setting; @@ -755,7 +764,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, return ret; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME + COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, struct compat_itimerspec __user *, setting) { @@ -768,6 +778,7 @@ COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, } return ret; } + #endif /* @@ -789,7 +800,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) if (!timr) return -EINVAL; - overrun = timr->it_overrun_last; + overrun = timer_overrun_to_int(timr, 0); unlock_timer(timr, flags); return overrun; @@ -906,8 +917,8 @@ retry: /* Set a POSIX.1b interval timer */ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, - const struct itimerspec __user *, new_setting, - struct itimerspec __user *, old_setting) + const struct __kernel_itimerspec __user *, new_setting, + struct __kernel_itimerspec __user *, old_setting) { struct itimerspec64 new_spec, old_spec; struct itimerspec64 *rtn = old_setting ? &old_spec : NULL; @@ -927,7 +938,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, return error; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, struct compat_itimerspec __user *, new, struct compat_itimerspec __user *, old) diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index 151e28f5bf30..ddb21145211a 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -19,7 +19,7 @@ struct k_clock { void (*timer_get)(struct k_itimer *timr, struct itimerspec64 *cur_setting); void (*timer_rearm)(struct k_itimer *timr); - int (*timer_forward)(struct k_itimer *timr, ktime_t now); + s64 (*timer_forward)(struct k_itimer *timr, ktime_t now); ktime_t (*timer_remaining)(struct k_itimer *timr, ktime_t now); int (*timer_try_to_cancel)(struct k_itimer *timr); void (*timer_arm)(struct k_itimer *timr, ktime_t expires, diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index 58045eb976c3..a59641fb88b6 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -90,7 +90,7 @@ static struct clock_event_device ce_broadcast_hrtimer = { .max_delta_ticks = ULONG_MAX, .mult = 1, .shift = 0, - .cpumask = cpu_all_mask, + .cpumask = cpu_possible_mask, }; static enum hrtimer_restart bc_handler(struct hrtimer *t) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index da9455a6b42b..5b33e2f5c0ed 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -642,7 +642,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) static inline bool local_timer_softirq_pending(void) { - return local_softirq_pending() & TIMER_SOFTIRQ; + return local_softirq_pending() & BIT(TIMER_SOFTIRQ); } static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) diff --git a/kernel/time/time.c b/kernel/time/time.c index 2b41e8e2d31d..ccdb351277ee 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -64,7 +64,7 @@ EXPORT_SYMBOL(sys_tz); */ SYSCALL_DEFINE1(time, time_t __user *, tloc) { - time_t i = get_seconds(); + time_t i = (time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) @@ -107,11 +107,9 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr) /* compat_time_t is a 32 bit "long" and needs to get converted. */ COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) { - struct timeval tv; compat_time_t i; - do_gettimeofday(&tv); - i = tv.tv_sec; + i = (compat_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) @@ -931,7 +929,7 @@ int compat_put_timespec64(const struct timespec64 *ts, void __user *uts) EXPORT_SYMBOL_GPL(compat_put_timespec64); int get_itimerspec64(struct itimerspec64 *it, - const struct itimerspec __user *uit) + const struct __kernel_itimerspec __user *uit) { int ret; @@ -946,7 +944,7 @@ int get_itimerspec64(struct itimerspec64 *it, EXPORT_SYMBOL_GPL(get_itimerspec64); int put_itimerspec64(const struct itimerspec64 *it, - struct itimerspec __user *uit) + struct __kernel_itimerspec __user *uit) { int ret; @@ -959,3 +957,24 @@ int put_itimerspec64(const struct itimerspec64 *it, return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); + +int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits) +{ + + if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || + __compat_get_timespec64(&its->it_value, &uits->it_value)) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(get_compat_itimerspec64); + +int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits) +{ + if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || + __compat_put_timespec64(&its->it_value, &uits->it_value)) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(put_compat_itimerspec64); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 4786df904c22..d9e659a12c76 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -34,6 +34,14 @@ #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) +enum timekeeping_adv_mode { + /* Update timekeeper when a tick has passed */ + TK_ADV_TICK, + + /* Update timekeeper on a direct frequency change */ + TK_ADV_FREQ +}; + /* * The most important data for readout fits into a single 64 byte * cache line. @@ -97,7 +105,7 @@ static inline void tk_normalize_xtime(struct timekeeper *tk) } } -static inline struct timespec64 tk_xtime(struct timekeeper *tk) +static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; @@ -154,7 +162,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ -static inline u64 tk_clock_read(struct tk_read_base *tkr) +static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); @@ -203,7 +211,7 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) } } -static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) +static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; @@ -247,7 +255,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } -static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) +static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { u64 cycle_now, delta; @@ -344,7 +352,7 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; static inline u32 arch_gettimeoffset(void) { return 0; } #endif -static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta) +static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta) { u64 nsec; @@ -355,7 +363,7 @@ static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta) return nsec + arch_gettimeoffset(); } -static inline u64 timekeeping_get_ns(struct tk_read_base *tkr) +static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { u64 delta; @@ -363,7 +371,7 @@ static inline u64 timekeeping_get_ns(struct tk_read_base *tkr) return timekeeping_delta_to_ns(tkr, delta); } -static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles) +static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { u64 delta; @@ -386,7 +394,8 @@ static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles) * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ -static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf) +static void update_fast_timekeeper(const struct tk_read_base *tkr, + struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; @@ -541,10 +550,10 @@ EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ -static void halt_fast_timekeeper(struct timekeeper *tk) +static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; - struct tk_read_base *tkr = &tk->tkr_mono; + const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); @@ -1269,7 +1278,7 @@ EXPORT_SYMBOL(do_settimeofday64); * * Adds or subtracts an offset value from the current time. */ -static int timekeeping_inject_offset(struct timespec64 *ts) +static int timekeeping_inject_offset(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; @@ -1510,8 +1519,20 @@ void __weak read_boot_clock64(struct timespec64 *ts) ts->tv_nsec = 0; } -/* Flag for if timekeeping_resume() has injected sleeptime */ -static bool sleeptime_injected; +/* + * Flag reflecting whether timekeeping_resume() has injected sleeptime. + * + * The flag starts of false and is only set when a suspend reaches + * timekeeping_suspend(), timekeeping_resume() sets it to false when the + * timekeeper clocksource is not stopping across suspend and has been + * used to update sleep time. If the timekeeper clocksource has stopped + * then the flag stays true and is used by the RTC resume code to decide + * whether sleeptime must be injected and if so the flag gets false then. + * + * If a suspend fails before reaching timekeeping_resume() then the flag + * stays false and prevents erroneous sleeptime injection. + */ +static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; @@ -1577,7 +1598,7 @@ static struct timespec64 timekeeping_suspend_time; * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, - struct timespec64 *delta) + const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING @@ -1610,7 +1631,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, */ bool timekeeping_rtc_skipresume(void) { - return sleeptime_injected; + return !suspend_timing_needed; } /** @@ -1638,7 +1659,7 @@ bool timekeeping_rtc_skipsuspend(void) * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ -void timekeeping_inject_sleeptime64(struct timespec64 *delta) +void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; @@ -1646,6 +1667,8 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta) raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); + suspend_timing_needed = false; + timekeeping_forward_now(tk); __timekeeping_inject_sleeptime(tk, delta); @@ -1669,9 +1692,9 @@ void timekeeping_resume(void) struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; - u64 cycle_now; + u64 cycle_now, nsec; + bool inject_sleeptime = false; - sleeptime_injected = false; read_persistent_clock64(&ts_new); clockevents_resume(); @@ -1693,22 +1716,19 @@ void timekeeping_resume(void) * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tk->tkr_mono); - if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > tk->tkr_mono.cycle_last) { - u64 nsec, cyc_delta; - - cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, - tk->tkr_mono.mask); - nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift); + nsec = clocksource_stop_suspend_timing(clock, cycle_now); + if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); - sleeptime_injected = true; + inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); - sleeptime_injected = true; + inject_sleeptime = true; } - if (sleeptime_injected) + if (inject_sleeptime) { + suspend_timing_needed = false; __timekeeping_inject_sleeptime(tk, &ts_delta); + } /* Re-base the last cycle value */ tk->tkr_mono.cycle_last = cycle_now; @@ -1732,6 +1752,8 @@ int timekeeping_suspend(void) unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; + struct clocksource *curr_clock; + u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); @@ -1743,11 +1765,22 @@ int timekeeping_suspend(void) if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; + suspend_timing_needed = true; + raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; + /* + * Since we've called forward_now, cycle_last stores the value + * just read from the current clocksource. Save this to potentially + * use in suspend timing. + */ + curr_clock = tk->tkr_mono.clock; + cycle_now = tk->tkr_mono.cycle_last; + clocksource_start_suspend_timing(curr_clock, cycle_now); + if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, @@ -2021,11 +2054,11 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, return offset; } -/** - * update_wall_time - Uses the current clocksource to increment the wall time - * +/* + * timekeeping_advance - Updates the timekeeper to the current time and + * current NTP tick length */ -void update_wall_time(void) +static void timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; @@ -2042,14 +2075,17 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; + + if (mode != TK_ADV_TICK) + goto out; #else offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); -#endif /* Check if there's really nothing to do */ - if (offset < real_tk->cycle_interval) + if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) goto out; +#endif /* Do some additional sanity checking */ timekeeping_check_update(tk, offset); @@ -2106,6 +2142,15 @@ out: } /** + * update_wall_time - Uses the current clocksource to increment the wall time + * + */ +void update_wall_time(void) +{ + timekeeping_advance(TK_ADV_TICK); +} + +/** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * @@ -2220,7 +2265,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, /** * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ -static int timekeeping_validate_timex(struct timex *txc) +static int timekeeping_validate_timex(const struct timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ @@ -2310,7 +2355,7 @@ int do_adjtimex(struct timex *txc) return ret; } - getnstimeofday64(&ts); + ktime_get_real_ts64(&ts); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); @@ -2327,6 +2372,10 @@ int do_adjtimex(struct timex *txc) write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + /* Update the multiplier immediately if frequency was set directly */ + if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) + timekeeping_advance(TK_ADV_FREQ); + if (tai != orig_tai) clock_was_set(); diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index 0754cadfa9e6..238e4be60229 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -70,7 +70,7 @@ static int __init tk_debug_sleep_time_init(void) } late_initcall(tk_debug_sleep_time_init); -void tk_debug_account_sleep_time(struct timespec64 *t) +void tk_debug_account_sleep_time(const struct timespec64 *t) { /* Cap bin index so we don't overflow the array */ int bin = min(fls(t->tv_sec), NUM_BINS-1); diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index cf5c0828ee31..bcbb52db2256 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -8,7 +8,7 @@ #include <linux/time.h> #ifdef CONFIG_DEBUG_FS -extern void tk_debug_account_sleep_time(struct timespec64 *t); +extern void tk_debug_account_sleep_time(const struct timespec64 *t); #else #define tk_debug_account_sleep_time(x) #endif diff --git a/kernel/time/timer.c b/kernel/time/timer.c index cc2d23e6ff61..fa49cd753dea 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -581,7 +581,7 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) * wheel: */ base->next_expiry = timer->expires; - wake_up_nohz_cpu(base->cpu); + wake_up_nohz_cpu(base->cpu); } static void @@ -1657,6 +1657,22 @@ static inline void __run_timers(struct timer_base *base) raw_spin_lock_irq(&base->lock); + /* + * timer_base::must_forward_clk must be cleared before running + * timers so that any timer functions that call mod_timer() will + * not try to forward the base. Idle tracking / clock forwarding + * logic is only used with BASE_STD timers. + * + * The must_forward_clk flag is cleared unconditionally also for + * the deferrable base. The deferrable base is not affected by idle + * tracking and never forwarded, so clearing the flag is a NOOP. + * + * The fact that the deferrable base is never forwarded can cause + * large variations in granularity for deferrable timers, but they + * can be deferred for long periods due to idle anyway. + */ + base->must_forward_clk = false; + while (time_after_eq(jiffies, base->clk)) { levels = collect_expired_timers(base, heads); @@ -1676,19 +1692,6 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - /* - * must_forward_clk must be cleared before running timers so that any - * timer functions that call mod_timer will not try to forward the - * base. idle trcking / clock forwarding logic is only used with - * BASE_STD timers. - * - * The deferrable base does not do idle tracking at all, so we do - * not forward it. This can result in very large variations in - * granularity for deferrable timers, but they can be deferred for - * long periods due to idle. - */ - base->must_forward_clk = false; - __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); diff --git a/kernel/torture.c b/kernel/torture.c index 3de1efbecd6a..1ac24a826589 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -20,6 +20,9 @@ * Author: Paul E. McKenney <paulmck@us.ibm.com> * Based on kernel/rcu/torture.c. */ + +#define pr_fmt(fmt) fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -53,7 +56,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>"); static char *torture_type; -static bool verbose; +static int verbose; /* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */ #define FULLSTOP_DONTSTOP 0 /* Normal operation. */ @@ -98,7 +101,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) return false; - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: offlining %d\n", torture_type, cpu); @@ -111,7 +114,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, "torture_onoff task: offline %d failed: errno %d\n", torture_type, cpu, ret); } else { - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: offlined %d\n", torture_type, cpu); @@ -147,7 +150,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) return false; - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: onlining %d\n", torture_type, cpu); @@ -160,7 +163,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, "torture_onoff task: online %d failed: errno %d\n", torture_type, cpu, ret); } else { - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: onlined %d\n", torture_type, cpu); @@ -647,7 +650,7 @@ static void torture_stutter_cleanup(void) * The runnable parameter points to a flag that controls whether or not * the test is currently runnable. If there is no such flag, pass in NULL. */ -bool torture_init_begin(char *ttype, bool v) +bool torture_init_begin(char *ttype, int v) { mutex_lock(&fullstop_mutex); if (torture_type != NULL) { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6a46af21765c..0b0b688ea166 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3227,6 +3227,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer) } /** + * ring_buffer_record_is_set_on - return true if the ring buffer is set writable + * @buffer: The ring buffer to see if write is set enabled + * + * Returns true if the ring buffer is set writable by ring_buffer_record_on(). + * Note that this does NOT mean it is in a writable state. + * + * It may return true when the ring buffer has been disabled by + * ring_buffer_record_disable(), as that is a temporary disabling of + * the ring buffer. + */ +int ring_buffer_record_is_set_on(struct ring_buffer *buffer) +{ + return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF); +} + +/** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer * @buffer: The ring buffer to stop writes to. * @cpu: The CPU buffer to stop diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 87cf25171fb8..823687997b01 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&tr->max_lock); + /* Inherit the recordable setting from trace_buffer */ + if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer)) + ring_buffer_record_on(tr->max_buffer.buffer); + else + ring_buffer_record_off(tr->max_buffer.buffer); + swap(tr->trace_buffer.buffer, tr->max_buffer.buffer); __update_max_tr(tr, tsk, cpu); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index d18249683682..5dea177cef53 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -679,6 +679,8 @@ event_trigger_callback(struct event_command *cmd_ops, goto out_free; out_reg: + /* Up the trigger_data count to make sure reg doesn't free it on failure */ + event_trigger_init(trigger_ops, trigger_data); ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file); /* * The above returns on success the # of functions enabled, @@ -686,11 +688,13 @@ event_trigger_callback(struct event_command *cmd_ops, * Consider no functions a failure too. */ if (!ret) { + cmd_ops->unreg(glob, trigger_ops, trigger_data, file); ret = -ENOENT; - goto out_free; - } else if (ret < 0) - goto out_free; - ret = 0; + } else if (ret > 0) + ret = 0; + + /* Down the counter of trigger_data or free it if not used anymore */ + event_trigger_free(trigger_ops, trigger_data); out: return ret; @@ -1416,6 +1420,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops, goto out; } + /* Up the trigger_data count to make sure nothing frees it on failure */ + event_trigger_init(trigger_ops, trigger_data); + if (trigger) { number = strsep(&trigger, ":"); @@ -1466,6 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, goto out_disable; /* Just return zero, not the number of enabled functions */ ret = 0; + event_trigger_free(trigger_ops, trigger_data); out: return ret; @@ -1476,7 +1484,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, out_free: if (cmd_ops->set_filter) cmd_ops->set_filter(NULL, trigger_data, NULL); - kfree(trigger_data); + event_trigger_free(trigger_ops, trigger_data); kfree(enable_data); goto out; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 21f718472942..e9d99463e5df 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -400,11 +400,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event, static int enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) { + struct event_file_link *link = NULL; int ret = 0; if (file) { - struct event_file_link *link; - link = kmalloc(sizeof(*link), GFP_KERNEL); if (!link) { ret = -ENOMEM; @@ -424,6 +423,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) else ret = enable_kprobe(&tk->rp.kp); } + + if (ret) { + if (file) { + /* Notice the if is true on not WARN() */ + if (!WARN_ON_ONCE(!link)) + list_del_rcu(&link->list); + kfree(link); + tk->tp.flags &= ~TP_FLAG_TRACE; + } else { + tk->tp.flags &= ~TP_FLAG_PROFILE; + } + } out: return ret; } @@ -1217,16 +1228,11 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) /* * We need to check and see if we modified the pc of the - * pt_regs, and if so clear the kprobe and return 1 so that we - * don't do the single stepping. - * The ftrace kprobe handler leaves it up to us to re-enable - * preemption here before returning if we've modified the ip. + * pt_regs, and if so return 1 so that we don't do the + * single stepping. */ - if (orig_ip != instruction_pointer(regs)) { - reset_current_kprobe(); - preempt_enable_no_resched(); + if (orig_ip != instruction_pointer(regs)) return 1; - } if (!ret) return 0; } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 576d18045811..5470dce212c0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -18,18 +18,14 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/sysctl.h> -#include <linux/smpboot.h> -#include <linux/sched/rt.h> -#include <uapi/linux/sched/types.h> #include <linux/tick.h> -#include <linux/workqueue.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> +#include <linux/stop_machine.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h> -#include <linux/kthread.h> static DEFINE_MUTEX(watchdog_mutex); @@ -169,11 +165,10 @@ static void lockup_detector_update_enable(void) unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; -static bool softlockup_threads_initialized __read_mostly; +static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); -static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); @@ -335,6 +330,27 @@ static void watchdog_interrupt_count(void) __this_cpu_inc(hrtimer_interrupts); } +static DEFINE_PER_CPU(struct completion, softlockup_completion); +static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); + +/* + * The watchdog thread function - touches the timestamp. + * + * It only runs once every sample_period seconds (4 seconds by + * default) to reset the softlockup timestamp. If this gets delayed + * for more than 2*watchdog_thresh seconds then the debug-printout + * triggers in watchdog_timer_fn(). + */ +static int softlockup_fn(void *data) +{ + __this_cpu_write(soft_lockup_hrtimer_cnt, + __this_cpu_read(hrtimer_interrupts)); + __touch_watchdog(); + complete(this_cpu_ptr(&softlockup_completion)); + + return 0; +} + /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { @@ -350,7 +366,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) watchdog_interrupt_count(); /* kick the softlockup detector */ - wake_up_process(__this_cpu_read(softlockup_watchdog)); + if (completion_done(this_cpu_ptr(&softlockup_completion))) { + reinit_completion(this_cpu_ptr(&softlockup_completion)); + stop_one_cpu_nowait(smp_processor_id(), + softlockup_fn, NULL, + this_cpu_ptr(&softlockup_stop_work)); + } /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); @@ -448,16 +469,15 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; } -static void watchdog_set_prio(unsigned int policy, unsigned int prio) -{ - struct sched_param param = { .sched_priority = prio }; - - sched_setscheduler(current, policy, ¶m); -} - static void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); + struct completion *done = this_cpu_ptr(&softlockup_completion); + + WARN_ON_ONCE(cpu != smp_processor_id()); + + init_completion(done); + complete(done); /* * Start the timer first to prevent the NMI watchdog triggering @@ -473,15 +493,14 @@ static void watchdog_enable(unsigned int cpu) /* Enable the perf event */ if (watchdog_enabled & NMI_WATCHDOG_ENABLED) watchdog_nmi_enable(cpu); - - watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } static void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - watchdog_set_prio(SCHED_NORMAL, 0); + WARN_ON_ONCE(cpu != smp_processor_id()); + /* * Disable the perf event first. That prevents that a large delay * between disabling the timer and disabling the perf event causes @@ -489,79 +508,66 @@ static void watchdog_disable(unsigned int cpu) */ watchdog_nmi_disable(cpu); hrtimer_cancel(hrtimer); + wait_for_completion(this_cpu_ptr(&softlockup_completion)); } -static void watchdog_cleanup(unsigned int cpu, bool online) +static int softlockup_stop_fn(void *data) { - watchdog_disable(cpu); + watchdog_disable(smp_processor_id()); + return 0; } -static int watchdog_should_run(unsigned int cpu) +static void softlockup_stop_all(void) { - return __this_cpu_read(hrtimer_interrupts) != - __this_cpu_read(soft_lockup_hrtimer_cnt); + int cpu; + + if (!softlockup_initialized) + return; + + for_each_cpu(cpu, &watchdog_allowed_mask) + smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false); + + cpumask_clear(&watchdog_allowed_mask); } -/* - * The watchdog thread function - touches the timestamp. - * - * It only runs once every sample_period seconds (4 seconds by - * default) to reset the softlockup timestamp. If this gets delayed - * for more than 2*watchdog_thresh seconds then the debug-printout - * triggers in watchdog_timer_fn(). - */ -static void watchdog(unsigned int cpu) +static int softlockup_start_fn(void *data) { - __this_cpu_write(soft_lockup_hrtimer_cnt, - __this_cpu_read(hrtimer_interrupts)); - __touch_watchdog(); + watchdog_enable(smp_processor_id()); + return 0; } -static struct smp_hotplug_thread watchdog_threads = { - .store = &softlockup_watchdog, - .thread_should_run = watchdog_should_run, - .thread_fn = watchdog, - .thread_comm = "watchdog/%u", - .setup = watchdog_enable, - .cleanup = watchdog_cleanup, - .park = watchdog_disable, - .unpark = watchdog_enable, -}; - -static void softlockup_update_smpboot_threads(void) +static void softlockup_start_all(void) { - lockdep_assert_held(&watchdog_mutex); - - if (!softlockup_threads_initialized) - return; + int cpu; - smpboot_update_cpumask_percpu_thread(&watchdog_threads, - &watchdog_allowed_mask); + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + for_each_cpu(cpu, &watchdog_allowed_mask) + smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false); } -/* Temporarily park all watchdog threads */ -static void softlockup_park_all_threads(void) +int lockup_detector_online_cpu(unsigned int cpu) { - cpumask_clear(&watchdog_allowed_mask); - softlockup_update_smpboot_threads(); + watchdog_enable(cpu); + return 0; } -/* Unpark enabled threads */ -static void softlockup_unpark_threads(void) +int lockup_detector_offline_cpu(unsigned int cpu) { - cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); - softlockup_update_smpboot_threads(); + watchdog_disable(cpu); + return 0; } static void lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); - softlockup_park_all_threads(); + + softlockup_stop_all(); set_sample_period(); lockup_detector_update_enable(); if (watchdog_enabled && watchdog_thresh) - softlockup_unpark_threads(); + softlockup_start_all(); + watchdog_nmi_start(); cpus_read_unlock(); /* @@ -580,8 +586,6 @@ static void lockup_detector_reconfigure(void) */ static __init void lockup_detector_setup(void) { - int ret; - /* * If sysctl is off and watchdog got disabled on the command line, * nothing to do here. @@ -592,24 +596,13 @@ static __init void lockup_detector_setup(void) !(watchdog_enabled && watchdog_thresh)) return; - ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_allowed_mask); - if (ret) { - pr_err("Failed to initialize soft lockup detector threads\n"); - return; - } - mutex_lock(&watchdog_mutex); - softlockup_threads_initialized = true; lockup_detector_reconfigure(); + softlockup_initialized = true; mutex_unlock(&watchdog_mutex); } #else /* CONFIG_SOFTLOCKUP_DETECTOR */ -static inline int watchdog_park_threads(void) { return 0; } -static inline void watchdog_unpark_threads(void) { } -static inline int watchdog_enable_all_cpus(void) { return 0; } -static inline void watchdog_disable_all_cpus(void) { } static void lockup_detector_reconfigure(void) { cpus_read_lock(); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index e449a23e9d59..1f7020d65d0a 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -175,8 +175,8 @@ static int hardlockup_detector_event_create(void) evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); if (IS_ERR(evt)) { - pr_info("Perf event create on CPU %d failed with %ld\n", cpu, - PTR_ERR(evt)); + pr_debug("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); return PTR_ERR(evt); } this_cpu_write(watchdog_ev, evt); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8838d1158d19..0b066b3c9284 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1718,7 +1718,7 @@ config KPROBES_SANITY_TEST default n help This option provides for testing basic kprobes functionality on - boot. A sample kprobe, jprobe and kretprobe are inserted and + boot. Samples of kprobe and kretprobe are inserted and verified for functionality. Say N if you are unsure. diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index c253c1b46c6b..befb127507c0 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -5,7 +5,7 @@ if HAVE_ARCH_KASAN config KASAN bool "KASan: runtime memory debugger" - depends on SLUB || (SLAB && !DEBUG_SLAB) + depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB) select SLUB_DEBUG if SLUB select CONSTRUCTORS select STACKDEPOT diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 19d42ea75ec2..98fa559ebd80 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -1,9 +1,6 @@ config ARCH_HAS_UBSAN_SANITIZE_ALL bool -config ARCH_WANTS_UBSAN_NO_NULL - def_bool n - config UBSAN bool "Undefined behaviour sanity checker" help @@ -39,14 +36,6 @@ config UBSAN_ALIGNMENT Enabling this option on architectures that support unaligned accesses may produce a lot of false positives. -config UBSAN_NULL - bool "Enable checking of null pointers" - depends on UBSAN - default y if !ARCH_WANTS_UBSAN_NO_NULL - help - This option enables detection of memory accesses via a - null pointer. - config TEST_UBSAN tristate "Module for testing for undefined behavior detection" depends on m && UBSAN diff --git a/lib/atomic64.c b/lib/atomic64.c index 53c2d5edc826..1d91e31eceec 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -178,18 +178,18 @@ long long atomic64_xchg(atomic64_t *v, long long new) } EXPORT_SYMBOL(atomic64_xchg); -int atomic64_add_unless(atomic64_t *v, long long a, long long u) +long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u) { unsigned long flags; raw_spinlock_t *lock = lock_addr(v); - int ret = 0; + long long val; raw_spin_lock_irqsave(lock, flags); - if (v->counter != u) { + val = v->counter; + if (val != u) v->counter += a; - ret = 1; - } raw_spin_unlock_irqrestore(lock, flags); - return ret; + + return val; } -EXPORT_SYMBOL(atomic64_add_unless); +EXPORT_SYMBOL(atomic64_fetch_add_unless); diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 994be4805cec..70935ed91125 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -360,9 +360,12 @@ static void debug_object_is_on_stack(void *addr, int onstack) limit++; if (is_on_stack) - pr_warn("object is on stack, but not annotated\n"); + pr_warn("object %p is on stack %p, but NOT annotated.\n", addr, + task_stack_page(current)); else - pr_warn("object is not on stack, but annotated\n"); + pr_warn("object %p is NOT on stack %p, but annotated.\n", addr, + task_stack_page(current)); + WARN_ON(1); } @@ -1185,8 +1188,7 @@ void __init debug_objects_mem_init(void) if (!obj_cache || debug_objects_replace_static_objects()) { debug_objects_enabled = 0; - if (obj_cache) - kmem_cache_destroy(obj_cache); + kmem_cache_destroy(obj_cache); pr_warn("out of memory.\n"); } else debug_objects_selftest(); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 7e43cd54c84c..8be175df3075 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -596,15 +596,70 @@ static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset, return ret; } +static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes, + struct iov_iter *i) +{ + struct pipe_inode_info *pipe = i->pipe; + size_t n, off, xfer = 0; + int idx; + + if (!sanity(i)) + return 0; + + bytes = n = push_pipe(i, bytes, &idx, &off); + if (unlikely(!n)) + return 0; + for ( ; n; idx = next_idx(idx, pipe), off = 0) { + size_t chunk = min_t(size_t, n, PAGE_SIZE - off); + unsigned long rem; + + rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr, + chunk); + i->idx = idx; + i->iov_offset = off + chunk - rem; + xfer += chunk - rem; + if (rem) + break; + n -= chunk; + addr += chunk; + } + i->count -= xfer; + return xfer; +} + +/** + * _copy_to_iter_mcsafe - copy to user with source-read error exception handling + * @addr: source kernel address + * @bytes: total transfer length + * @iter: destination iterator + * + * The pmem driver arranges for filesystem-dax to use this facility via + * dax_copy_to_iter() for protecting read/write to persistent memory. + * Unless / until an architecture can guarantee identical performance + * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a + * performance regression to switch more users to the mcsafe version. + * + * Otherwise, the main differences between this and typical _copy_to_iter(). + * + * * Typical tail/residue handling after a fault retries the copy + * byte-by-byte until the fault happens again. Re-triggering machine + * checks is potentially fatal so the implementation uses source + * alignment and poison alignment assumptions to avoid re-triggering + * hardware exceptions. + * + * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies. + * Compare to copy_to_iter() where only ITER_IOVEC attempts might return + * a short copy. + * + * See MCSAFE_TEST for self-test. + */ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; unsigned long rem, curr_addr, s_addr = (unsigned long) addr; - if (unlikely(i->type & ITER_PIPE)) { - WARN_ON(1); - return 0; - } + if (unlikely(i->type & ITER_PIPE)) + return copy_pipe_to_iter_mcsafe(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, @@ -701,6 +756,20 @@ size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +/** + * _copy_from_iter_flushcache - write destination through cpu cache + * @addr: destination kernel address + * @bytes: total transfer length + * @iter: source iterator + * + * The pmem driver arranges for filesystem-dax to use this facility via + * dax_copy_from_iter() for ensuring that writes to persistent memory + * are flushed through the CPU cache. It is differentiated from + * _copy_from_iter_nocache() in that guarantees all data is flushed for + * all iterator types. The _copy_from_iter_nocache() only attempts to + * bypass the cache for the ITER_IOVEC case, and on some archs may use + * instructions that strand dirty-data in the cache. + */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; diff --git a/lib/refcount.c b/lib/refcount.c index d3b81cefce91..ebcf8cd49e05 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -35,13 +35,13 @@ * */ +#include <linux/mutex.h> #include <linux/refcount.h> +#include <linux/spinlock.h> #include <linux/bug.h> -#ifdef CONFIG_REFCOUNT_FULL - /** - * refcount_add_not_zero - add a value to a refcount unless it is 0 + * refcount_add_not_zero_checked - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * @@ -58,7 +58,7 @@ * * Return: false if the passed refcount is 0, true otherwise */ -bool refcount_add_not_zero(unsigned int i, refcount_t *r) +bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -79,10 +79,10 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r) return true; } -EXPORT_SYMBOL(refcount_add_not_zero); +EXPORT_SYMBOL(refcount_add_not_zero_checked); /** - * refcount_add - add a value to a refcount + * refcount_add_checked - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * @@ -97,14 +97,14 @@ EXPORT_SYMBOL(refcount_add_not_zero); * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ -void refcount_add(unsigned int i, refcount_t *r) +void refcount_add_checked(unsigned int i, refcount_t *r) { - WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); + WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n"); } -EXPORT_SYMBOL(refcount_add); +EXPORT_SYMBOL(refcount_add_checked); /** - * refcount_inc_not_zero - increment a refcount unless it is 0 + * refcount_inc_not_zero_checked - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN. @@ -115,7 +115,7 @@ EXPORT_SYMBOL(refcount_add); * * Return: true if the increment was successful, false otherwise */ -bool refcount_inc_not_zero(refcount_t *r) +bool refcount_inc_not_zero_checked(refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -134,10 +134,10 @@ bool refcount_inc_not_zero(refcount_t *r) return true; } -EXPORT_SYMBOL(refcount_inc_not_zero); +EXPORT_SYMBOL(refcount_inc_not_zero_checked); /** - * refcount_inc - increment a refcount + * refcount_inc_checked - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN. @@ -148,14 +148,14 @@ EXPORT_SYMBOL(refcount_inc_not_zero); * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ -void refcount_inc(refcount_t *r) +void refcount_inc_checked(refcount_t *r) { - WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); + WARN_ONCE(!refcount_inc_not_zero_checked(r), "refcount_t: increment on 0; use-after-free.\n"); } -EXPORT_SYMBOL(refcount_inc); +EXPORT_SYMBOL(refcount_inc_checked); /** - * refcount_sub_and_test - subtract from a refcount and test if it is 0 + * refcount_sub_and_test_checked - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * @@ -174,7 +174,7 @@ EXPORT_SYMBOL(refcount_inc); * * Return: true if the resulting refcount is 0, false otherwise */ -bool refcount_sub_and_test(unsigned int i, refcount_t *r) +bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -192,10 +192,10 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r) return !new; } -EXPORT_SYMBOL(refcount_sub_and_test); +EXPORT_SYMBOL(refcount_sub_and_test_checked); /** - * refcount_dec_and_test - decrement a refcount and test if it is 0 + * refcount_dec_and_test_checked - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to @@ -207,14 +207,14 @@ EXPORT_SYMBOL(refcount_sub_and_test); * * Return: true if the resulting refcount is 0, false otherwise */ -bool refcount_dec_and_test(refcount_t *r) +bool refcount_dec_and_test_checked(refcount_t *r) { - return refcount_sub_and_test(1, r); + return refcount_sub_and_test_checked(1, r); } -EXPORT_SYMBOL(refcount_dec_and_test); +EXPORT_SYMBOL(refcount_dec_and_test_checked); /** - * refcount_dec - decrement a refcount + * refcount_dec_checked - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement @@ -223,12 +223,11 @@ EXPORT_SYMBOL(refcount_dec_and_test); * Provides release memory ordering, such that prior loads and stores are done * before. */ -void refcount_dec(refcount_t *r) +void refcount_dec_checked(refcount_t *r) { - WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); + WARN_ONCE(refcount_dec_and_test_checked(r), "refcount_t: decrement hit 0; leaking memory.\n"); } -EXPORT_SYMBOL(refcount_dec); -#endif /* CONFIG_REFCOUNT_FULL */ +EXPORT_SYMBOL(refcount_dec_checked); /** * refcount_dec_if_one - decrement a refcount if it is 1 diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 9427b5766134..e5c8586cf717 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -774,7 +774,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter) skip++; if (list == iter->list) { iter->p = p; - skip = skip; + iter->skip = skip; goto found; } } @@ -964,8 +964,16 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_stop); static size_t rounded_hashtable_size(const struct rhashtable_params *params) { - return max(roundup_pow_of_two(params->nelem_hint * 4 / 3), - (unsigned long)params->min_size); + size_t retsize; + + if (params->nelem_hint) + retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3), + (unsigned long)params->min_size); + else + retsize = max(HASH_DEFAULT_SIZE, + (unsigned long)params->min_size); + + return retsize; } static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) @@ -1022,8 +1030,6 @@ int rhashtable_init(struct rhashtable *ht, struct bucket_table *tbl; size_t size; - size = HASH_DEFAULT_SIZE; - if ((!params->key_len && !params->obj_hashfn) || (params->obj_hashfn && !params->obj_cmpfn)) return -EINVAL; @@ -1050,8 +1056,7 @@ int rhashtable_init(struct rhashtable *ht, ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE); - if (params->nelem_hint) - size = rounded_hashtable_size(&ht->p); + size = rounded_hashtable_size(&ht->p); if (params->locks_mul) ht->p.locks_mul = roundup_pow_of_two(params->locks_mul); @@ -1143,13 +1148,14 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, void (*free_fn)(void *ptr, void *arg), void *arg) { - struct bucket_table *tbl; + struct bucket_table *tbl, *next_tbl; unsigned int i; cancel_work_sync(&ht->run_work); mutex_lock(&ht->mutex); tbl = rht_dereference(ht->tbl, ht); +restart: if (free_fn) { for (i = 0; i < tbl->size; i++) { struct rhash_head *pos, *next; @@ -1166,7 +1172,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, } } + next_tbl = rht_dereference(tbl->future_tbl, ht); bucket_table_free(tbl); + if (next_tbl) { + tbl = next_tbl; + goto restart; + } mutex_unlock(&ht->mutex); } EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1cd7c1a57a14..25346bd99364 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2084,6 +2084,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (vma_is_dax(vma)) return; page = pmd_page(_pmd); + if (!PageDirty(page) && pmd_dirty(_pmd)) + set_page_dirty(page); if (!PageReferenced(page) && pmd_young(_pmd)) SetPageReferenced(page); page_remove_rmap(page, true); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 039ddbc574e9..3103099f64fd 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3167,6 +3167,13 @@ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) return 0; } +/* + * When a new function is introduced to vm_operations_struct and added + * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. + * This is because under System V memory model, mappings created via + * shmget/shmat with "huge page" specified are backed by hugetlbfs files, + * their original vm_ops are overwritten with shm_vm_ops. + */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, diff --git a/mm/memblock.c b/mm/memblock.c index 11e46f83e1ad..4b5d245fafc1 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,6 +20,7 @@ #include <linux/kmemleak.h> #include <linux/seq_file.h> #include <linux/memblock.h> +#include <linux/bootmem.h> #include <asm/sections.h> #include <linux/io.h> @@ -1225,6 +1226,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } +#if defined(CONFIG_NO_BOOTMEM) /** * memblock_virt_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes @@ -1432,6 +1434,7 @@ void * __init memblock_virt_alloc_try_nid( (u64)max_addr); return NULL; } +#endif /** * __memblock_free_early - free boot memory block diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e6f0d5ef320a..b2173f7e5164 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -850,7 +850,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) int nid; int i; - while ((memcg = parent_mem_cgroup(memcg))) { + for (; memcg; memcg = parent_mem_cgroup(memcg)) { for_each_node(nid) { mz = mem_cgroup_nodeinfo(memcg, nid); for (i = 0; i <= DEF_PRIORITY; i++) { @@ -4037,6 +4037,14 @@ static struct cftype mem_cgroup_legacy_files[] = { static DEFINE_IDR(mem_cgroup_idr); +static void mem_cgroup_id_remove(struct mem_cgroup *memcg) +{ + if (memcg->id.id > 0) { + idr_remove(&mem_cgroup_idr, memcg->id.id); + memcg->id.id = 0; + } +} + static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) { VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0); @@ -4047,8 +4055,7 @@ static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { VM_BUG_ON(atomic_read(&memcg->id.ref) < n); if (atomic_sub_and_test(n, &memcg->id.ref)) { - idr_remove(&mem_cgroup_idr, memcg->id.id); - memcg->id.id = 0; + mem_cgroup_id_remove(memcg); /* Memcg ID pins CSS */ css_put(&memcg->css); @@ -4185,8 +4192,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); return memcg; fail: - if (memcg->id.id > 0) - idr_remove(&mem_cgroup_idr, memcg->id.id); + mem_cgroup_id_remove(memcg); __mem_cgroup_free(memcg); return NULL; } @@ -4245,6 +4251,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) return &memcg->css; fail: + mem_cgroup_id_remove(memcg); mem_cgroup_free(memcg); return ERR_PTR(-ENOMEM); } diff --git a/mm/memory.c b/mm/memory.c index 18355e0b971a..3d0a74ab70f2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1423,11 +1423,9 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { - if (next - addr != HPAGE_PMD_SIZE) { - VM_BUG_ON_VMA(vma_is_anonymous(vma) && - !rwsem_is_locked(&tlb->mm->mmap_sem), vma); + if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); - } else if (zap_huge_pmd(tlb, vma, pmd, addr)) + else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ } @@ -4403,6 +4401,9 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); + if (!maddr) + return -ENOMEM; + if (write) memcpy_toio(maddr + offset, buf, len); else diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 9ac49ef17b4e..01f1a14facc4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2505,6 +2505,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) /* Create pseudo-vma that contains just the policy */ memset(&pvma, 0, sizeof(struct vm_area_struct)); + vma_init(&pvma, NULL); pvma.vm_end = TASK_SIZE; /* policy covers entire file */ mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ diff --git a/mm/mmap.c b/mm/mmap.c index 5801b5f0a634..17bbf4d3e24f 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -182,7 +182,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return next; } @@ -911,7 +911,7 @@ again: anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); - kmem_cache_free(vm_area_cachep, next); + vm_area_free(next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove another next too. It would clutter @@ -1729,19 +1729,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (!vma) { error = -ENOMEM; goto unacct_error; } - vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; - INIT_LIST_HEAD(&vma->anon_vma_chain); if (file) { if (vm_flags & VM_DENYWRITE) { @@ -1780,6 +1778,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, error = shmem_zero_setup(vma); if (error) goto free_vma; + } else { + vma_set_anonymous(vma); } vma_link(mm, vma, prev, rb_link, rb_parent); @@ -1832,7 +1832,7 @@ allow_write_and_free_vma: if (vm_flags & VM_DENYWRITE) allow_write_access(file); free_vma: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); unacct_error: if (charged) vm_unacct_memory(charged); @@ -2620,15 +2620,10 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, return err; } - new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new = vm_area_dup(vma); if (!new) return -ENOMEM; - /* most fields are the same, copy all, and then fixup */ - *new = *vma; - - INIT_LIST_HEAD(&new->anon_vma_chain); - if (new_below) new->vm_end = addr; else { @@ -2669,7 +2664,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, out_free_mpol: mpol_put(vma_policy(new)); out_free_vma: - kmem_cache_free(vm_area_cachep, new); + vm_area_free(new); return err; } @@ -2984,14 +2979,13 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla /* * create a vma struct for an anonymous mapping */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (!vma) { vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = mm; + vma_set_anonymous(vma); vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; @@ -3202,16 +3196,14 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { - new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new_vma = vm_area_dup(vma); if (!new_vma) goto out; - *new_vma = *vma; new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; if (vma_dup_policy(vma, new_vma)) goto out_free_vma; - INIT_LIST_HEAD(&new_vma->anon_vma_chain); if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) @@ -3226,7 +3218,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: - kmem_cache_free(vm_area_cachep, new_vma); + vm_area_free(new_vma); out: return NULL; } @@ -3350,12 +3342,10 @@ static struct vm_area_struct *__install_special_mapping( int ret; struct vm_area_struct *vma; - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; @@ -3376,7 +3366,7 @@ static struct vm_area_struct *__install_special_mapping( return vma; out: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return ERR_PTR(ret); } diff --git a/mm/nommu.c b/mm/nommu.c index 4452d8bd9ae4..9fc9e43335b6 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -769,7 +769,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); put_nommu_region(vma->vm_region); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); } /* @@ -1145,6 +1145,8 @@ static int do_mmap_private(struct vm_area_struct *vma, if (ret < len) memset(base + ret, 0, len - ret); + } else { + vma_set_anonymous(vma); } return 0; @@ -1204,7 +1206,7 @@ unsigned long do_mmap(struct file *file, if (!region) goto error_getting_region; - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(current->mm); if (!vma) goto error_getting_vma; @@ -1212,7 +1214,6 @@ unsigned long do_mmap(struct file *file, region->vm_flags = vm_flags; region->vm_pgoff = pgoff; - INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_flags = vm_flags; vma->vm_pgoff = pgoff; @@ -1368,7 +1369,7 @@ error: kmem_cache_free(vm_region_jar, region); if (vma->vm_file) fput(vma->vm_file); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return ret; sharing_violation: @@ -1469,14 +1470,13 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, if (!region) return -ENOMEM; - new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new = vm_area_dup(vma); if (!new) { kmem_cache_free(vm_region_jar, region); return -ENOMEM; } /* most fields are the same, copy all, and then fixup */ - *new = *vma; *region = *vma->vm_region; new->vm_region = region; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5d800d61ddb7..a790ef4be74e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6383,7 +6383,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, free_area_init_core(pgdat); } -#ifdef CONFIG_HAVE_MEMBLOCK +#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) /* * Only struct pages that are backed by physical memory are zeroed and * initialized by going through __init_single_page(). But, there are some @@ -6421,7 +6421,7 @@ void __paginginit zero_resv_unavail(void) if (pgcnt) pr_info("Reserved but unavailable: %lld pages", pgcnt); } -#endif /* CONFIG_HAVE_MEMBLOCK */ +#endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP diff --git a/mm/shmem.c b/mm/shmem.c index 2cab84403055..41b9bbf24e16 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1421,6 +1421,7 @@ static void shmem_pseudo_vma_init(struct vm_area_struct *vma, { /* Create a pseudo vma that just contains the policy */ memset(vma, 0, sizeof(*vma)); + vma_init(vma, NULL); /* Bias interleave by inode number to distribute better across nodes */ vma->vm_pgoff = index + info->vfs_inode.i_ino; vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); diff --git a/mm/zswap.c b/mm/zswap.c index 7d34e69507e3..cd91fd9d96b8 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1026,6 +1026,15 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, ret = -ENOMEM; goto reject; } + + /* A second zswap_is_full() check after + * zswap_shrink() to make sure it's now + * under the max_pool_percent + */ + if (zswap_is_full()) { + ret = -ENOMEM; + goto reject; + } } /* allocate entry */ diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index af8c4b38b746..d84227d75717 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -244,7 +244,7 @@ static int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size) * the packet count limit, so... */ if (atm_may_send(pvcc->atmvcc, size) && - atomic_inc_not_zero_hint(&pvcc->inflight, NONE_INFLIGHT)) + atomic_inc_not_zero(&pvcc->inflight)) return 1; /* diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index be09a9883825..73bf6a93a3cf 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -2732,7 +2732,7 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; - struct batadv_gw_node *curr_gw; + struct batadv_gw_node *curr_gw = NULL; int ret = 0; void *hdr; @@ -2780,6 +2780,8 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, ret = 0; out: + if (curr_gw) + batadv_gw_node_put(curr_gw); if (router_ifinfo) batadv_neigh_ifinfo_put(router_ifinfo); if (router) diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index ec93337ee259..6baec4e68898 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -927,7 +927,7 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; - struct batadv_gw_node *curr_gw; + struct batadv_gw_node *curr_gw = NULL; int ret = 0; void *hdr; @@ -995,6 +995,8 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, ret = 0; out: + if (curr_gw) + batadv_gw_node_put(curr_gw); if (router_ifinfo) batadv_neigh_ifinfo_put(router_ifinfo); if (router) diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 4229b01ac7b5..87479c60670e 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -19,6 +19,7 @@ #include "debugfs.h" #include "main.h" +#include <linux/dcache.h> #include <linux/debugfs.h> #include <linux/err.h> #include <linux/errno.h> @@ -344,6 +345,25 @@ out: } /** + * batadv_debugfs_rename_hardif() - Fix debugfs path for renamed hardif + * @hard_iface: hard interface which was renamed + */ +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface) +{ + const char *name = hard_iface->net_dev->name; + struct dentry *dir; + struct dentry *d; + + dir = hard_iface->debug_dir; + if (!dir) + return; + + d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name); + if (!d) + pr_err("Can't rename debugfs dir to %s\n", name); +} + +/** * batadv_debugfs_del_hardif() - delete the base directory for a hard interface * in debugfs. * @hard_iface: hard interface which is deleted. @@ -414,6 +434,26 @@ out: } /** + * batadv_debugfs_rename_meshif() - Fix debugfs path for renamed softif + * @dev: net_device which was renamed + */ +void batadv_debugfs_rename_meshif(struct net_device *dev) +{ + struct batadv_priv *bat_priv = netdev_priv(dev); + const char *name = dev->name; + struct dentry *dir; + struct dentry *d; + + dir = bat_priv->debug_dir; + if (!dir) + return; + + d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name); + if (!d) + pr_err("Can't rename debugfs dir to %s\n", name); +} + +/** * batadv_debugfs_del_meshif() - Remove interface dependent debugfs entries * @dev: netdev struct of the soft interface */ diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 37b069698b04..08a592ffbee5 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -30,8 +30,10 @@ struct net_device; void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); int batadv_debugfs_add_meshif(struct net_device *dev); +void batadv_debugfs_rename_meshif(struct net_device *dev); void batadv_debugfs_del_meshif(struct net_device *dev); int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface); +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface); void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface); #else @@ -49,6 +51,10 @@ static inline int batadv_debugfs_add_meshif(struct net_device *dev) return 0; } +static inline void batadv_debugfs_rename_meshif(struct net_device *dev) +{ +} + static inline void batadv_debugfs_del_meshif(struct net_device *dev) { } @@ -60,6 +66,11 @@ int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface) } static inline +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface) +{ +} + +static inline void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface) { } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index c405d15befd6..2f0d42f2f913 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -989,6 +989,32 @@ void batadv_hardif_remove_interfaces(void) rtnl_unlock(); } +/** + * batadv_hard_if_event_softif() - Handle events for soft interfaces + * @event: NETDEV_* event to handle + * @net_dev: net_device which generated an event + * + * Return: NOTIFY_* result + */ +static int batadv_hard_if_event_softif(unsigned long event, + struct net_device *net_dev) +{ + struct batadv_priv *bat_priv; + + switch (event) { + case NETDEV_REGISTER: + batadv_sysfs_add_meshif(net_dev); + bat_priv = netdev_priv(net_dev); + batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); + break; + case NETDEV_CHANGENAME: + batadv_debugfs_rename_meshif(net_dev); + break; + } + + return NOTIFY_DONE; +} + static int batadv_hard_if_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -997,12 +1023,8 @@ static int batadv_hard_if_event(struct notifier_block *this, struct batadv_hard_iface *primary_if = NULL; struct batadv_priv *bat_priv; - if (batadv_softif_is_valid(net_dev) && event == NETDEV_REGISTER) { - batadv_sysfs_add_meshif(net_dev); - bat_priv = netdev_priv(net_dev); - batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); - return NOTIFY_DONE; - } + if (batadv_softif_is_valid(net_dev)) + return batadv_hard_if_event_softif(event, net_dev); hard_iface = batadv_hardif_get_by_netdev(net_dev); if (!hard_iface && (event == NETDEV_REGISTER || @@ -1051,6 +1073,9 @@ static int batadv_hard_if_event(struct notifier_block *this, if (batadv_is_wifi_hardif(hard_iface)) hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; break; + case NETDEV_CHANGENAME: + batadv_debugfs_rename_hardif(hard_iface); + break; default: break; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 3986551397ca..12a2b7d21376 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1705,7 +1705,9 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, ether_addr_copy(common->addr, tt_addr); common->vid = vid; - common->flags = flags; + if (!is_multicast_ether_addr(common->addr)) + common->flags = flags & (~BATADV_TT_SYNC_MASK); + tt_global_entry->roam_at = 0; /* node must store current time in case of roaming. This is * needed to purge this entry out on timeout (if nobody claims @@ -1768,7 +1770,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, * TT_CLIENT_TEMP, therefore they have to be copied in the * client entry */ - common->flags |= flags & (~BATADV_TT_SYNC_MASK); + if (!is_multicast_ether_addr(common->addr)) + common->flags |= flags & (~BATADV_TT_SYNC_MASK); /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 68c3578343b4..22a78eedf4b1 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -96,6 +96,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; u32 retval, duration; + int hh_len = ETH_HLEN; struct sk_buff *skb; void *data; int ret; @@ -131,12 +132,22 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, skb_reset_network_header(skb); if (is_l2) - __skb_push(skb, ETH_HLEN); + __skb_push(skb, hh_len); if (is_direct_pkt_access) bpf_compute_data_pointers(skb); retval = bpf_test_run(prog, skb, repeat, &duration); - if (!is_l2) - __skb_push(skb, ETH_HLEN); + if (!is_l2) { + if (skb_headroom(skb) < hh_len) { + int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); + + if (pskb_expand_head(skb, nhead, 0, GFP_USER)) { + kfree_skb(skb); + return -ENOMEM; + } + } + memset(__skb_push(skb, hh_len), 0, hh_len); + } + size = skb->len; /* bpf program can never convert linear skb to non-linear */ if (WARN_ON_ONCE(skb_is_nonlinear(skb))) diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index e0adcd123f48..711d7156efd8 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -131,8 +131,10 @@ static void caif_flow_cb(struct sk_buff *skb) caifd = caif_get(skb->dev); WARN_ON(caifd == NULL); - if (caifd == NULL) + if (!caifd) { + rcu_read_unlock(); return; + } caifd_hold(caifd); rcu_read_unlock(); diff --git a/net/core/dev.c b/net/core/dev.c index a5aa1c7444e6..559a91271f82 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7149,16 +7149,19 @@ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) dev->tx_queue_len = new_len; res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev); res = notifier_to_errno(res); - if (res) { - netdev_err(dev, - "refused to change device tx_queue_len\n"); - dev->tx_queue_len = orig_len; - return res; - } - return dev_qdisc_change_tx_queue_len(dev); + if (res) + goto err_rollback; + res = dev_qdisc_change_tx_queue_len(dev); + if (res) + goto err_rollback; } return 0; + +err_rollback: + netdev_err(dev, "refused to change device tx_queue_len\n"); + dev->tx_queue_len = orig_len; + return res; } /** diff --git a/net/core/filter.c b/net/core/filter.c index 0ca6907d7efe..9dfd145eedcc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -459,11 +459,21 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) (!unaligned_ok && offset >= 0 && offset + ip_align >= 0 && offset + ip_align % size == 0))) { + bool ldx_off_ok = offset <= S16_MAX; + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset); - *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian); - *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D, - offset); + *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, + size, 2 + endian + (!ldx_off_ok * 2)); + if (ldx_off_ok) { + *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, + BPF_REG_D, offset); + } else { + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D); + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset); + *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, + BPF_REG_TMP, 0); + } if (endian) *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8); *insn++ = BPF_JMP_A(8); @@ -1702,24 +1712,26 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { + u8 *end = skb_tail_pointer(skb); + u8 *net = skb_network_header(skb); + u8 *mac = skb_mac_header(skb); u8 *ptr; - if (unlikely(offset > 0xffff || len > skb_headlen(skb))) + if (unlikely(offset > 0xffff || len > (end - mac))) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: - ptr = skb_mac_header(skb) + offset; + ptr = mac + offset; break; case BPF_HDR_START_NET: - ptr = skb_network_header(skb) + offset; + ptr = net + offset; break; default: goto err_clear; } - if (likely(ptr >= skb_mac_header(skb) && - ptr + len <= skb_tail_pointer(skb))) { + if (likely(ptr >= mac && ptr + len <= end)) { memcpy(to, ptr, len); return 0; } @@ -1762,6 +1774,37 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = { .arg2_type = ARG_ANYTHING, }; +static inline int sk_skb_try_make_writable(struct sk_buff *skb, + unsigned int write_len) +{ + int err = __bpf_try_make_writable(skb, write_len); + + bpf_compute_data_end_sk_skb(skb); + return err; +} + +BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) +{ + /* Idea is the following: should the needed direct read/write + * test fail during runtime, we can pull in more data and redo + * again, since implicitly, we invalidate previous checks here. + * + * Or, since we know how much we need to make read/writeable, + * this can be done once at the program beginning for direct + * access case. By this we overcome limitations of only current + * headroom being accessible. + */ + return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb)); +} + +static const struct bpf_func_proto sk_skb_pull_data_proto = { + .func = sk_skb_pull_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { @@ -2779,7 +2822,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) static u32 __bpf_skb_max_len(const struct sk_buff *skb) { - return skb->dev->mtu + skb->dev->hard_header_len; + return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len : + SKB_MAX_ALLOC; } static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff) @@ -2863,8 +2907,8 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) return __skb_trim_rcsum(skb, new_len); } -BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, - u64, flags) +static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, + u64 flags) { u32 max_len = __bpf_skb_max_len(skb); u32 min_len = __bpf_skb_min_len(skb); @@ -2900,6 +2944,13 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, if (!ret && skb_is_gso(skb)) skb_gso_reset(skb); } + return ret; +} + +BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, + u64, flags) +{ + int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_pointers(skb); return ret; @@ -2914,9 +2965,27 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, +BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { + int ret = __bpf_skb_change_tail(skb, new_len, flags); + + bpf_compute_data_end_sk_skb(skb); + return ret; +} + +static const struct bpf_func_proto sk_skb_change_tail_proto = { + .func = sk_skb_change_tail, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + +static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, + u64 flags) +{ u32 max_len = __bpf_skb_max_len(skb); u32 new_len = skb->len + head_room; int ret; @@ -2941,8 +3010,16 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, skb_reset_mac_header(skb); } + return ret; +} + +BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + int ret = __bpf_skb_change_head(skb, head_room, flags); + bpf_compute_data_pointers(skb); - return 0; + return ret; } static const struct bpf_func_proto bpf_skb_change_head_proto = { @@ -2954,6 +3031,23 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + int ret = __bpf_skb_change_head(skb, head_room, flags); + + bpf_compute_data_end_sk_skb(skb); + return ret; +} + +static const struct bpf_func_proto sk_skb_change_head_proto = { + .func = sk_skb_change_head, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : @@ -3046,12 +3140,16 @@ static int __bpf_tx_xdp(struct net_device *dev, u32 index) { struct xdp_frame *xdpf; - int sent; + int err, sent; if (!dev->netdev_ops->ndo_xdp_xmit) { return -EOPNOTSUPP; } + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(err)) + return err; + xdpf = convert_to_xdp_frame(xdp); if (unlikely(!xdpf)) return -EOVERFLOW; @@ -3285,7 +3383,8 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, goto err; } - if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + err = xdp_ok_fwd_dev(fwd, skb->len); + if (unlikely(err)) goto err; skb->dev = fwd; @@ -4439,10 +4538,10 @@ static const struct bpf_func_proto bpf_lwt_push_encap_proto = { .arg4_type = ARG_CONST_SIZE }; +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len) { -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); void *srh_tlvs, *srh_end, *ptr; @@ -4468,9 +4567,6 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, memcpy(skb->data + offset, from, len); return 0; -#else /* CONFIG_IPV6_SEG6_BPF */ - return -EOPNOTSUPP; -#endif } static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { @@ -4486,7 +4582,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, u32, action, void *, param, u32, param_len) { -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh; @@ -4534,9 +4629,6 @@ BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, default: return -EINVAL; } -#else /* CONFIG_IPV6_SEG6_BPF */ - return -EOPNOTSUPP; -#endif } static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { @@ -4552,7 +4644,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, s32, len) { -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); void *srh_end, *srh_tlvs, *ptr; @@ -4596,9 +4687,6 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, srh_state->hdrlen += len; srh_state->valid = 0; return 0; -#else /* CONFIG_IPV6_SEG6_BPF */ - return -EOPNOTSUPP; -#endif } static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { @@ -4609,6 +4697,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; +#endif /* CONFIG_IPV6_SEG6_BPF */ bool bpf_helper_changes_pkt_data(void *func) { @@ -4617,9 +4706,12 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_skb_store_bytes || func == bpf_skb_change_proto || func == bpf_skb_change_head || + func == sk_skb_change_head || func == bpf_skb_change_tail || + func == sk_skb_change_tail || func == bpf_skb_adjust_room || func == bpf_skb_pull_data || + func == sk_skb_pull_data || func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || @@ -4627,11 +4719,12 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_xdp_adjust_meta || func == bpf_msg_pull_data || func == bpf_xdp_adjust_tail || - func == bpf_lwt_push_encap || +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) func == bpf_lwt_seg6_store_bytes || func == bpf_lwt_seg6_adjust_srh || - func == bpf_lwt_seg6_action - ) + func == bpf_lwt_seg6_action || +#endif + func == bpf_lwt_push_encap) return true; return false; @@ -4871,11 +4964,11 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: - return &bpf_skb_pull_data_proto; + return &sk_skb_pull_data_proto; case BPF_FUNC_skb_change_tail: - return &bpf_skb_change_tail_proto; + return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: - return &bpf_skb_change_head_proto; + return &sk_skb_change_head_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: @@ -4966,12 +5059,14 @@ static const struct bpf_func_proto * lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_FUNC_lwt_seg6_store_bytes: return &bpf_lwt_seg6_store_bytes_proto; case BPF_FUNC_lwt_seg6_action: return &bpf_lwt_seg6_action_proto; case BPF_FUNC_lwt_seg6_adjust_srh: return &bpf_lwt_seg6_adjust_srh_proto; +#endif default: return lwt_out_func_proto(func_id, prog); } diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index b2b2323bdc84..188d693cb251 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -77,8 +77,20 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, d->lock = lock; spin_lock_bh(lock); } - if (d->tail) - return gnet_stats_copy(d, type, NULL, 0, padattr); + if (d->tail) { + int ret = gnet_stats_copy(d, type, NULL, 0, padattr); + + /* The initial attribute added in gnet_stats_copy() may be + * preceded by a padding attribute, in which case d->tail will + * end up pointing at the padding instead of the real attribute. + * Fix this so gnet_stats_finish_copy() adjusts the length of + * the right attribute. + */ + if (ret == 0 && d->tail->nla_type == padattr) + d->tail = (struct nlattr *)((char *)d->tail + + NLA_ALIGN(d->tail->nla_len)); + return ret; + } return 0; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index e7e626fb87bb..e45098593dc0 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -217,7 +217,7 @@ static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog, if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME]) return -EINVAL; - prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL); + prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_ATOMIC); if (!prog->name) return -ENOMEM; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 68bf07206744..43a932cb609b 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -269,7 +269,7 @@ static void __page_pool_empty_ring(struct page_pool *pool) struct page *page; /* Empty recycle ring */ - while ((page = ptr_ring_consume(&pool->ring))) { + while ((page = ptr_ring_consume_bh(&pool->ring))) { /* Verify the refcnt invariant of cached pages */ if (!(page_ref_count(page) == 1)) pr_crit("%s() page_pool refcnt %d violation\n", diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5ef61222fdef..e3f743c141b3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2759,9 +2759,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) return err; } - dev->rtnl_link_state = RTNL_LINK_INITIALIZED; - - __dev_notify_flags(dev, old_flags, ~0U); + if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { + __dev_notify_flags(dev, old_flags, 0U); + } else { + dev->rtnl_link_state = RTNL_LINK_INITIALIZED; + __dev_notify_flags(dev, old_flags, ~0U); + } return 0; } EXPORT_SYMBOL(rtnl_configure_link); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index eba8dae22c25..fb35b62af272 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -858,6 +858,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) n->cloned = 1; n->nohdr = 0; n->peeked = 0; + C(pfmemalloc); n->destructor = NULL; C(tail); C(end); @@ -3719,6 +3720,7 @@ normal: net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); + err = -EINVAL; goto err; } @@ -3752,11 +3754,10 @@ skip_fraglist: perform_csum_check: if (!csum) { - if (skb_has_shared_frag(nskb)) { - err = __skb_linearize(nskb); - if (err) - goto err; - } + if (skb_has_shared_frag(nskb) && + __skb_linearize(nskb)) + goto err; + if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = diff --git a/net/core/sock.c b/net/core/sock.c index 9e8f65585b81..bc2d7a37297f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2277,9 +2277,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg, pfrag->offset += use; sge = sg + sg_curr - 1; - if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page && - sg->offset + sg->length == orig_offset) { - sg->length += use; + if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page && + sge->offset + sge->length == orig_offset) { + sge->length += use; } else { sge = sg + sg_curr; sg_unmark_end(sge); diff --git a/net/core/xdp.c b/net/core/xdp.c index 9d1f22072d5d..6771f1855b96 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -345,7 +345,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, rcu_read_lock(); /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); - xa->zc_alloc->free(xa->zc_alloc, handle); + if (!WARN_ON_ONCE(!xa)) + xa->zc_alloc->free(xa->zc_alloc, handle); rcu_read_unlock(); default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 2b75df469220..842a9c7c73a3 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -229,14 +229,16 @@ static void ccid2_cwnd_restart(struct sock *sk, const u32 now) struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); u32 cwnd = hc->tx_cwnd, restart_cwnd, iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache); + s32 delta = now - hc->tx_lsndtime; hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2)); /* don't reduce cwnd below the initial window (IW) */ restart_cwnd = min(cwnd, iwnd); - cwnd >>= (now - hc->tx_lsndtime) / hc->tx_rto; - hc->tx_cwnd = max(cwnd, restart_cwnd); + while ((delta -= hc->tx_rto) >= 0 && cwnd > restart_cwnd) + cwnd >>= 1; + hc->tx_cwnd = max(cwnd, restart_cwnd); hc->tx_cwnd_stamp = now; hc->tx_cwnd_used = 0; diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 40c851693f77..0c9478b91fa5 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -86,35 +86,39 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) opt++; kdebug("options: '%s'", opt); do { + int opt_len, opt_nlen; const char *eq; - int opt_len, opt_nlen, opt_vlen, tmp; + char optval[128]; next_opt = memchr(opt, '#', end - opt) ?: end; opt_len = next_opt - opt; - if (opt_len <= 0 || opt_len > 128) { + if (opt_len <= 0 || opt_len > sizeof(optval)) { pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n", opt_len); return -EINVAL; } - eq = memchr(opt, '=', opt_len) ?: end; - opt_nlen = eq - opt; - eq++; - opt_vlen = next_opt - eq; /* will be -1 if no value */ + eq = memchr(opt, '=', opt_len); + if (eq) { + opt_nlen = eq - opt; + eq++; + memcpy(optval, eq, next_opt - eq); + optval[next_opt - eq] = '\0'; + } else { + opt_nlen = opt_len; + optval[0] = '\0'; + } - tmp = opt_vlen >= 0 ? opt_vlen : 0; - kdebug("option '%*.*s' val '%*.*s'", - opt_nlen, opt_nlen, opt, tmp, tmp, eq); + kdebug("option '%*.*s' val '%s'", + opt_nlen, opt_nlen, opt, optval); /* see if it's an error number representing a DNS error * that's to be recorded as the result in this key */ if (opt_nlen == sizeof(DNS_ERRORNO_OPTION) - 1 && memcmp(opt, DNS_ERRORNO_OPTION, opt_nlen) == 0) { kdebug("dns error number option"); - if (opt_vlen <= 0) - goto bad_option_value; - ret = kstrtoul(eq, 10, &derrno); + ret = kstrtoul(optval, 10, &derrno); if (ret < 0) goto bad_option_value; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1e3b6a6d8a40..9864bcd3d317 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -639,7 +639,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev) + if (!dev->phydev && !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) @@ -659,7 +659,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev) + if (!dev->phydev && !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) @@ -1248,6 +1248,9 @@ int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); + if (!netif_running(slave_dev)) + return 0; + netif_device_detach(slave_dev); rtnl_lock(); @@ -1261,6 +1264,9 @@ int dsa_slave_resume(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); + if (!netif_running(slave_dev)) + return 0; + netif_device_attach(slave_dev); rtnl_lock(); diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 275449b0d633..3297e7fa9945 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -90,12 +90,18 @@ static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n) return 0; } +static int lowpan_get_iflink(const struct net_device *dev) +{ + return lowpan_802154_dev(dev)->wdev->ifindex; +} + static const struct net_device_ops lowpan_netdev_ops = { .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, .ndo_neigh_construct = lowpan_neigh_construct, + .ndo_get_iflink = lowpan_get_iflink, }; static void lowpan_setup(struct net_device *ldev) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b21833651394..2998b0e47d4b 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -292,18 +292,19 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); - BUG_ON(!in_dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { + bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, + .flowi4_oif = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), .flowi4_scope = scope, - .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0, + .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 85b617b655bc..75151be21413 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1200,13 +1200,13 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - im->sfmode = pmc->sfmode; - if (pmc->sfmode == MCAST_INCLUDE) { + if (im->sfmode == MCAST_INCLUDE) { im->tomb = pmc->tomb; im->sources = pmc->sources; for (psf = im->sources; psf; psf = psf->sf_next) - psf->sf_crcount = im->crcount; + psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + } else { + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; } in_dev_put(pmc->interface); kfree(pmc); @@ -1288,7 +1288,7 @@ static void igmp_group_dropped(struct ip_mc_list *im) #endif } -static void igmp_group_added(struct ip_mc_list *im) +static void igmp_group_added(struct ip_mc_list *im, unsigned int mode) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST @@ -1316,7 +1316,13 @@ static void igmp_group_added(struct ip_mc_list *im) } /* else, v3 */ - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should + * not send filter-mode change record as the mode should be from + * IN() to IN(A). + */ + if (mode == MCAST_EXCLUDE) + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + igmp_ifc_event(in_dev); #endif } @@ -1381,8 +1387,8 @@ static void ip_mc_hash_remove(struct in_device *in_dev, /* * A socket has joined a multicast group on device dev. */ - -void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) +static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, + unsigned int mode) { struct ip_mc_list *im; #ifdef CONFIG_IP_MULTICAST @@ -1394,7 +1400,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) { im->users++; - ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0); + ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0); goto out; } } @@ -1408,8 +1414,8 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) in_dev_hold(in_dev); im->multiaddr = addr; /* initial mode is (EX, empty) */ - im->sfmode = MCAST_EXCLUDE; - im->sfcount[MCAST_EXCLUDE] = 1; + im->sfmode = mode; + im->sfcount[mode] = 1; refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST @@ -1426,12 +1432,17 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im); #endif - igmp_group_added(im); + igmp_group_added(im, mode); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: return; } + +void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) +{ + __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE); +} EXPORT_SYMBOL(ip_mc_inc_group); static int ip_mc_check_iphdr(struct sk_buff *skb) @@ -1688,7 +1699,7 @@ void ip_mc_remap(struct in_device *in_dev) #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif - igmp_group_added(pmc); + igmp_group_added(pmc, pmc->sfmode); } } @@ -1751,7 +1762,7 @@ void ip_mc_up(struct in_device *in_dev) #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif - igmp_group_added(pmc); + igmp_group_added(pmc, pmc->sfmode); } } @@ -2130,8 +2141,8 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) /* Join a multicast group */ - -int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) +static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, + unsigned int mode) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; @@ -2172,15 +2183,30 @@ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) memcpy(&iml->multi, imr, sizeof(*imr)); iml->next_rcu = inet->mc_list; iml->sflist = NULL; - iml->sfmode = MCAST_EXCLUDE; + iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); - ip_mc_inc_group(in_dev, addr); + __ip_mc_inc_group(in_dev, addr, mode); err = 0; done: return err; } + +/* Join ASM (Any-Source Multicast) group + */ +int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) +{ + return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE); +} EXPORT_SYMBOL(ip_mc_join_group); +/* Join SSM (Source-Specific Multicast) group + */ +int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, + unsigned int mode) +{ + return __ip_mc_join_group(sk, imr, mode); +} + static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c9e35b81d093..0d70608cc2e1 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -90,7 +90,7 @@ static void inet_frags_free_cb(void *ptr, void *arg) void inet_frags_exit_net(struct netns_frags *nf) { - nf->low_thresh = 0; /* prevent creation of new frags */ + nf->high_thresh = 0; /* prevent creation of new frags */ rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL); } @@ -157,9 +157,6 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, { struct inet_frag_queue *q; - if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) - return NULL; - q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (!q) return NULL; @@ -204,6 +201,9 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { struct inet_frag_queue *fq; + if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) + return NULL; + rcu_read_lock(); fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 8e9528ebaa8e..d14d741fb05e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -383,11 +383,16 @@ found: int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */ if (i < next->len) { + int delta = -next->truesize; + /* Eat head of the next overlapped fragment * and leave the loop. The next ones cannot overlap. */ if (!pskb_pull(next, i)) goto err; + delta += next->truesize; + if (delta) + add_frag_mem_limit(qp->q.net, delta); next->ip_defrag_offset += i; qp->q.meat -= i; if (next->ip_summed != CHECKSUM_UNNECESSARY) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b3308e9d9762..0e3edd25f881 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index fc32fdbeefa6..c0fe5ad996f2 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { struct sockaddr_in sin; const struct iphdr *iph = ip_hdr(skb); - __be16 *ports = (__be16 *)skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 > (int)skb->len) + end = skb_transport_offset(skb) + 4; + if (end > 0 && !pskb_may_pull(skb, end)) return; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin.sin_family = AF_INET; sin.sin_addr.s_addr = iph->daddr; @@ -984,7 +987,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr; mreq.imr_address.s_addr = mreqs.imr_interface; mreq.imr_ifindex = 0; - err = ip_mc_join_group(sk, &mreq); + err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); if (err && err != -EADDRINUSE) break; omode = MCAST_INCLUDE; @@ -1061,7 +1064,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, mreq.imr_multiaddr = psin->sin_addr; mreq.imr_address.s_addr = 0; mreq.imr_ifindex = greqs.gsr_interface; - err = ip_mc_join_group(sk, &mreq); + err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); if (err && err != -EADDRINUSE) break; greqs.gsr_interface = mreq.imr_ifindex; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index ca0dad90803a..e77872c93c20 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1898,6 +1898,7 @@ static struct xt_match ipt_builtin_mt[] __read_mostly = { .checkentry = icmp_checkentry, .proto = IPPROTO_ICMP, .family = NFPROTO_IPV4, + .me = THIS_MODULE, }, }; diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 805e83ec3ad9..164714104965 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -37,7 +37,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, * to a listener socket if there's one */ struct sock *sk2; - sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, + sk2 = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, laddr ? laddr : iph->daddr, hp->source, lport ? lport : hp->dest, skb->dev, NF_TPROXY_LOOKUP_LISTENER); @@ -71,7 +71,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) EXPORT_SYMBOL_GPL(nf_tproxy_laddr4); struct sock * -nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, +nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, @@ -79,16 +79,21 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, const enum nf_tproxy_lookup_t lookup_type) { struct sock *sk; - struct tcphdr *tcph; switch (protocol) { - case IPPROTO_TCP: + case IPPROTO_TCP: { + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, ip_hdrlen(skb), + sizeof(struct tcphdr), &_hdr); + if (hp == NULL) + return NULL; + switch (lookup_type) { case NF_TPROXY_LOOKUP_LISTENER: - tcph = hp; sk = inet_lookup_listener(net, &tcp_hashinfo, skb, ip_hdrlen(skb) + - __tcp_hdrlen(tcph), + __tcp_hdrlen(hp), saddr, sport, daddr, dport, in->ifindex, 0); @@ -110,6 +115,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, BUG(); } break; + } case IPPROTO_UDP: sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, in->ifindex); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index af0a857d8352..5fa335fd3852 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -189,8 +189,9 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, if (write && ret == 0) { low = make_kgid(user_ns, urange[0]); high = make_kgid(user_ns, urange[1]); - if (!gid_valid(low) || !gid_valid(high) || - (urange[1] < urange[0]) || gid_lt(high, low)) { + if (!gid_valid(low) || !gid_valid(high)) + return -EINVAL; + if (urange[1] < urange[0] || gid_lt(high, low)) { low = make_kgid(&init_user_ns, 1); high = make_kgid(&init_user_ns, 0); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e7b53d2a971f..4491faf83f4f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1998,7 +1998,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, * shouldn't happen. */ if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), - "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n", + "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags)) break; @@ -2013,7 +2013,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; WARN(!(flags & MSG_PEEK), - "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n", + "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } @@ -2562,6 +2562,8 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); + tp->copied_seq = tp->rcv_nxt; + tp->urg_data = 0; tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); @@ -2821,14 +2823,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_REPAIR: if (!tcp_can_repair_sock(sk)) err = -EPERM; - else if (val == 1) { + else if (val == TCP_REPAIR_ON) { tp->repair = 1; sk->sk_reuse = SK_FORCE_REUSE; tp->repair_queue = TCP_NO_QUEUE; - } else if (val == 0) { + } else if (val == TCP_REPAIR_OFF) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; tcp_send_window_probe(sk); + } else if (val == TCP_REPAIR_OFF_NO_WP) { + tp->repair = 0; + sk->sk_reuse = SK_NO_REUSE; } else err = -EINVAL; @@ -3720,8 +3725,7 @@ int tcp_abort(struct sock *sk, int err) struct request_sock *req = inet_reqsk(sk); local_bh_disable(); - inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, - req); + inet_csk_reqsk_queue_drop(req->rsk_listener, req); local_bh_enable(); return 0; } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 58e2f479ffb4..4bfff3c87e8e 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -354,6 +354,10 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ cwnd = (cwnd + 1) & ~1U; + /* Ensure gain cycling gets inflight above BDP even for small BDPs. */ + if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT) + cwnd += 2; + return cwnd; } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 5f5e5936760e..8b637f9f23a2 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -55,7 +55,6 @@ struct dctcp { u32 dctcp_alpha; u32 next_seq; u32 ce_state; - u32 delayed_ack_reserved; u32 loss_cwnd; }; @@ -96,7 +95,6 @@ static void dctcp_init(struct sock *sk) ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); - ca->delayed_ack_reserved = 0; ca->loss_cwnd = 0; ca->ce_state = 0; @@ -131,23 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=0 to CE=1 and delayed - * ACK has not sent yet. - */ - if (!ca->ce_state && ca->delayed_ack_reserved) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=0. */ - tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; + if (!ca->ce_state) { + /* State has changed from CE=0 to CE=1, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk, 1); } ca->prior_rcv_nxt = tp->rcv_nxt; @@ -161,23 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=1 to CE=0 and delayed - * ACK has not sent yet. - */ - if (ca->ce_state && ca->delayed_ack_reserved) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=1. */ - tp->ecn_flags |= TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; + if (ca->ce_state) { + /* State has changed from CE=1 to CE=0, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk, 1); } ca->prior_rcv_nxt = tp->rcv_nxt; @@ -248,25 +228,6 @@ static void dctcp_state(struct sock *sk, u8 new_state) } } -static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev) -{ - struct dctcp *ca = inet_csk_ca(sk); - - switch (ev) { - case CA_EVENT_DELAYED_ACK: - if (!ca->delayed_ack_reserved) - ca->delayed_ack_reserved = 1; - break; - case CA_EVENT_NON_DELAYED_ACK: - if (ca->delayed_ack_reserved) - ca->delayed_ack_reserved = 0; - break; - default: - /* Don't care for the rest. */ - break; - } -} - static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) { switch (ev) { @@ -276,10 +237,6 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) case CA_EVENT_ECN_NO_CE: dctcp_ce_state_1_to_0(sk); break; - case CA_EVENT_DELAYED_ACK: - case CA_EVENT_NON_DELAYED_ACK: - dctcp_update_ack_reserved(sk, ev); - break; default: /* Don't care for the rest. */ break; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8e5522c6833a..f9dcb29be12d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -215,7 +215,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.quick = quickacks; } -static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) +void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -223,6 +223,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } +EXPORT_SYMBOL(tcp_enter_quickack_mode); /* Send ACKs quickly, if "quick" count is not exhausted * and the session is not interactive. @@ -245,8 +246,15 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp) static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb) { - if (tcp_hdr(skb)->cwr) + if (tcp_hdr(skb)->cwr) { tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; + + /* If the sender is telling us it has entered CWR, then its + * cwnd may be very low (even just 1 packet), so we should ACK + * immediately. + */ + tcp_enter_quickack_mode((struct sock *)tp, 2); + } } static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) @@ -4357,6 +4365,23 @@ static bool tcp_try_coalesce(struct sock *sk, return true; } +static bool tcp_ooo_try_coalesce(struct sock *sk, + struct sk_buff *to, + struct sk_buff *from, + bool *fragstolen) +{ + bool res = tcp_try_coalesce(sk, to, from, fragstolen); + + /* In case tcp_drop() is called later, update to->gso_segs */ + if (res) { + u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) + + max_t(u16, 1, skb_shinfo(from)->gso_segs); + + skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF); + } + return res; +} + static void tcp_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); @@ -4480,8 +4505,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) /* In the typical case, we are adding an skb to the end of the list. * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ - if (tcp_try_coalesce(sk, tp->ooo_last_skb, - skb, &fragstolen)) { + if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, + skb, &fragstolen)) { coalesce_done: tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); @@ -4509,7 +4534,7 @@ coalesce_done: /* All the bits are present. Drop. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb); + tcp_drop(sk, skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); goto add_sack; @@ -4528,11 +4553,11 @@ coalesce_done: TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb1); + tcp_drop(sk, skb1); goto merge_right; } - } else if (tcp_try_coalesce(sk, skb1, - skb, &fragstolen)) { + } else if (tcp_ooo_try_coalesce(sk, skb1, + skb, &fragstolen)) { goto coalesce_done; } p = &parent->rb_right; @@ -4901,6 +4926,7 @@ end: static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 range_truesize, sum_tiny = 0; struct sk_buff *skb, *head; u32 start, end; @@ -4912,6 +4938,7 @@ new_range: } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; + range_truesize = skb->truesize; for (head = skb;;) { skb = skb_rb_next(skb); @@ -4922,11 +4949,20 @@ new_range: if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { - tcp_collapse(sk, NULL, &tp->out_of_order_queue, - head, skb, start, end); + /* Do not attempt collapsing tiny skbs */ + if (range_truesize != head->truesize || + end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) { + tcp_collapse(sk, NULL, &tp->out_of_order_queue, + head, skb, start, end); + } else { + sum_tiny += range_truesize; + if (sum_tiny > sk->sk_rcvbuf >> 3) + return; + } goto new_range; } + range_truesize += skb->truesize; if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; if (after(TCP_SKB_CB(skb)->end_seq, end)) @@ -4941,6 +4977,7 @@ new_range: * 2) not add too big latencies if thousands of packets sit there. * (But if application shrinks SO_RCVBUF, we could still end up * freeing whole queue here) + * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks. * * Return true if queue has shrunk. */ @@ -4948,20 +4985,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct rb_node *node, *prev; + int goal; if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); + goal = sk->sk_rcvbuf >> 3; node = &tp->ooo_last_skb->rbnode; do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); + goal -= rb_to_skb(node)->truesize; tcp_drop(sk, rb_to_skb(node)); - sk_mem_reclaim(sk); - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && - !tcp_under_memory_pressure(sk)) - break; + if (!prev || goal <= 0) { + sk_mem_reclaim(sk); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + !tcp_under_memory_pressure(sk)) + break; + goal = sk->sk_rcvbuf >> 3; + } node = prev; } while (node); tp->ooo_last_skb = rb_to_skb(prev); @@ -4996,6 +5039,9 @@ static int tcp_prune_queue(struct sock *sk) else if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) + return 0; + tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) tcp_collapse(sk, &sk->sk_receive_queue, NULL, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bea17f1e8302..3b2711e33e4c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -156,11 +156,24 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) */ if (tcptw->tw_ts_recent_stamp && (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) { - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; - tp->rx_opt.ts_recent = tcptw->tw_ts_recent; - tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; + /* In case of repair and re-using TIME-WAIT sockets we still + * want to be sure that it is safe as above but honor the + * sequence numbers and time stamps set as part of the repair + * process. + * + * Without this check re-using a TIME-WAIT socket with TCP + * repair would accumulate a -1 on the repair assigned + * sequence number. The first time it is reused the sequence + * is -1, the second time -2, etc. This fixes that issue + * without appearing to create any others. + */ + if (likely(!tp->repair)) { + tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; + if (tp->write_seq == 0) + tp->write_seq = 1; + tp->rx_opt.ts_recent = tcptw->tw_ts_recent; + tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; + } sock_hold(sktw); return 1; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8e08b409c71e..c4172c1fb198 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) +static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, + u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } + + if (unlikely(rcv_nxt != tp->rcv_nxt)) + return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1023,8 +1027,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ -static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, - gfp_t gfp_mask) +static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, + int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; @@ -1100,7 +1104,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); - th->ack_seq = htonl(tp->rcv_nxt); + th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->tcp_flags); @@ -1141,7 +1145,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); + tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); @@ -1178,6 +1182,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, return err; } +static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, + gfp_t gfp_mask) +{ + return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, + tcp_sk(sk)->rcv_nxt); +} + /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, @@ -3523,8 +3534,6 @@ void tcp_send_delayed_ack(struct sock *sk) int ato = icsk->icsk_ack.ato; unsigned long timeout; - tcp_ca_event(sk, CA_EVENT_DELAYED_ACK); - if (ato > TCP_DELACK_MIN) { const struct tcp_sock *tp = tcp_sk(sk); int max_ato = HZ / 2; @@ -3573,7 +3582,7 @@ void tcp_send_delayed_ack(struct sock *sk) } /* This routine sends an ack and also updates the window. */ -void tcp_send_ack(struct sock *sk) +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { struct sk_buff *buff; @@ -3581,8 +3590,6 @@ void tcp_send_ack(struct sock *sk) if (sk->sk_state == TCP_CLOSE) return; - tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK); - /* We are not putting this on the write queue, so * tcp_transmit_skb() will set the ownership to this * sock. @@ -3608,9 +3615,14 @@ void tcp_send_ack(struct sock *sk) skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ - tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0); + __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); +} +EXPORT_SYMBOL_GPL(__tcp_send_ack); + +void tcp_send_ack(struct sock *sk) +{ + __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } -EXPORT_SYMBOL_GPL(tcp_send_ack); /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 0eff75525da1..b3885ca22d6f 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -108,6 +108,7 @@ config IPV6_MIP6 config IPV6_ILA tristate "IPv6: Identifier Locator Addressing (ILA)" depends on NETFILTER + select DST_CACHE select LWTUNNEL ---help--- Support for IPv6 Identifier Locator Addressing (ILA). diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 91580c62bb86..f66a1cae3366 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2374,7 +2374,8 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, continue; if ((rt->fib6_flags & noflags) != 0) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; break; } out: diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 1323b9679cf7..1c0bb9fb76e6 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -799,8 +799,7 @@ static int calipso_opt_update(struct sock *sk, struct ipv6_opt_hdr *hop) { struct ipv6_txoptions *old = txopt_get(inet6_sk(sk)), *txopts; - txopts = ipv6_renew_options_kern(sk, old, IPV6_HOPOPTS, - hop, hop ? ipv6_optlen(hop) : 0); + txopts = ipv6_renew_options(sk, old, IPV6_HOPOPTS, hop); txopt_put(old); if (IS_ERR(txopts)) return PTR_ERR(txopts); @@ -1222,8 +1221,7 @@ static int calipso_req_setattr(struct request_sock *req, if (IS_ERR(new)) return PTR_ERR(new); - txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, - new, new ? ipv6_optlen(new) : 0); + txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new); kfree(new); @@ -1260,8 +1258,7 @@ static void calipso_req_delattr(struct request_sock *req) if (calipso_opt_del(req_inet->ipv6_opt->hopopt, &new)) return; /* Nothing to do */ - txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, - new, new ? ipv6_optlen(new) : 0); + txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new); if (!IS_ERR(txopts)) { txopts = xchg(&req_inet->ipv6_opt, txopts); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 2ee08b6a86a4..1a1f876f8e28 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -700,13 +700,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; - __be16 *ports = (__be16 *) skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 <= (int)skb->len) { + end = skb_transport_offset(skb) + 4; + if (end <= 0 || pskb_may_pull(skb, end)) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 97513f35bcc5..88a7579c23bd 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -669,8 +669,10 @@ skip_cow: sg_init_table(sg, nfrags); ret = skb_to_sgvec(skb, sg, 0, skb->len); - if (unlikely(ret < 0)) + if (unlikely(ret < 0)) { + kfree(tmp); goto out; + } skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 5bc2bf3733ab..20291c2036fc 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -1015,29 +1015,21 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) } EXPORT_SYMBOL_GPL(ipv6_dup_options); -static int ipv6_renew_option(void *ohdr, - struct ipv6_opt_hdr __user *newopt, int newoptlen, - int inherit, - struct ipv6_opt_hdr **hdr, - char **p) +static void ipv6_renew_option(int renewtype, + struct ipv6_opt_hdr **dest, + struct ipv6_opt_hdr *old, + struct ipv6_opt_hdr *new, + int newtype, char **p) { - if (inherit) { - if (ohdr) { - memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr)); - *hdr = (struct ipv6_opt_hdr *)*p; - *p += CMSG_ALIGN(ipv6_optlen(*hdr)); - } - } else { - if (newopt) { - if (copy_from_user(*p, newopt, newoptlen)) - return -EFAULT; - *hdr = (struct ipv6_opt_hdr *)*p; - if (ipv6_optlen(*hdr) > newoptlen) - return -EINVAL; - *p += CMSG_ALIGN(newoptlen); - } - } - return 0; + struct ipv6_opt_hdr *src; + + src = (renewtype == newtype ? new : old); + if (!src) + return; + + memcpy(*p, src, ipv6_optlen(src)); + *dest = (struct ipv6_opt_hdr *)*p; + *p += CMSG_ALIGN(ipv6_optlen(*dest)); } /** @@ -1063,13 +1055,11 @@ static int ipv6_renew_option(void *ohdr, */ struct ipv6_txoptions * ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, - int newtype, - struct ipv6_opt_hdr __user *newopt, int newoptlen) + int newtype, struct ipv6_opt_hdr *newopt) { int tot_len = 0; char *p; struct ipv6_txoptions *opt2; - int err; if (opt) { if (newtype != IPV6_HOPOPTS && opt->hopopt) @@ -1082,8 +1072,8 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt)); } - if (newopt && newoptlen) - tot_len += CMSG_ALIGN(newoptlen); + if (newopt) + tot_len += CMSG_ALIGN(ipv6_optlen(newopt)); if (!tot_len) return NULL; @@ -1098,29 +1088,19 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, opt2->tot_len = tot_len; p = (char *)(opt2 + 1); - err = ipv6_renew_option(opt ? opt->hopopt : NULL, newopt, newoptlen, - newtype != IPV6_HOPOPTS, - &opt2->hopopt, &p); - if (err) - goto out; - - err = ipv6_renew_option(opt ? opt->dst0opt : NULL, newopt, newoptlen, - newtype != IPV6_RTHDRDSTOPTS, - &opt2->dst0opt, &p); - if (err) - goto out; - - err = ipv6_renew_option(opt ? opt->srcrt : NULL, newopt, newoptlen, - newtype != IPV6_RTHDR, - (struct ipv6_opt_hdr **)&opt2->srcrt, &p); - if (err) - goto out; - - err = ipv6_renew_option(opt ? opt->dst1opt : NULL, newopt, newoptlen, - newtype != IPV6_DSTOPTS, - &opt2->dst1opt, &p); - if (err) - goto out; + ipv6_renew_option(IPV6_HOPOPTS, &opt2->hopopt, + (opt ? opt->hopopt : NULL), + newopt, newtype, &p); + ipv6_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt, + (opt ? opt->dst0opt : NULL), + newopt, newtype, &p); + ipv6_renew_option(IPV6_RTHDR, + (struct ipv6_opt_hdr **)&opt2->srcrt, + (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL), + newopt, newtype, &p); + ipv6_renew_option(IPV6_DSTOPTS, &opt2->dst1opt, + (opt ? opt->dst1opt : NULL), + newopt, newtype, &p); opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) + (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) + @@ -1128,37 +1108,6 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0); return opt2; -out: - sock_kfree_s(sk, opt2, opt2->tot_len); - return ERR_PTR(err); -} - -/** - * ipv6_renew_options_kern - replace a specific ext hdr with a new one. - * - * @sk: sock from which to allocate memory - * @opt: original options - * @newtype: option type to replace in @opt - * @newopt: new option of type @newtype to replace (kernel-mem) - * @newoptlen: length of @newopt - * - * See ipv6_renew_options(). The difference is that @newopt is - * kernel memory, rather than user memory. - */ -struct ipv6_txoptions * -ipv6_renew_options_kern(struct sock *sk, struct ipv6_txoptions *opt, - int newtype, struct ipv6_opt_hdr *newopt, - int newoptlen) -{ - struct ipv6_txoptions *ret_val; - const mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - ret_val = ipv6_renew_options(sk, opt, newtype, - (struct ipv6_opt_hdr __user *)newopt, - newoptlen); - set_fs(old_fs); - return ret_val; } struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index be491bf6ab6e..ef2505aefc15 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -402,9 +402,10 @@ static int icmp6_iif(const struct sk_buff *skb) /* for local traffic to local address, skb dev is the loopback * device. Check if there is a dst attached to the skb and if so - * get the real device index. + * get the real device index. Same is needed for replies to a link + * local address on a device enslaved to an L3 master device */ - if (unlikely(iif == LOOPBACK_IFINDEX)) { + if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); if (rt6) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1fb2f3118d60..d212738e9d10 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -935,20 +935,19 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); - enum fib_event_type event = FIB_EVENT_ENTRY_ADD; - struct fib6_info *iter = NULL, *match = NULL; + struct fib6_info *iter = NULL; struct fib6_info __rcu **ins; + struct fib6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); - int append = (info->nlh && - (info->nlh->nlmsg_flags & NLM_F_APPEND)); int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; + bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); u16 nlflags = NLM_F_EXCL; int err; - if (append) + if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND)) nlflags |= NLM_F_APPEND; ins = &fn->leaf; @@ -970,8 +969,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, nlflags &= ~NLM_F_EXCL; if (replace) { - found++; - break; + if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { + found++; + break; + } + if (rt_can_ecmp) + fallback_ins = fallback_ins ?: ins; + goto next_iter; } if (rt6_duplicate_nexthop(iter, rt)) { @@ -986,51 +990,71 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); return -EEXIST; } - - /* first route that matches */ - if (!match) - match = iter; + /* If we have the same destination and the same metric, + * but not the same gateway, then the route we try to + * add is sibling to this route, increment our counter + * of siblings, and later we will add our route to the + * list. + * Only static routes (which don't have flag + * RTF_EXPIRES) are used for ECMPv6. + * + * To avoid long list, we only had siblings if the + * route have a gateway. + */ + if (rt_can_ecmp && + rt6_qualify_for_ecmp(iter)) + rt->fib6_nsiblings++; } if (iter->fib6_metric > rt->fib6_metric) break; +next_iter: ins = &iter->fib6_next; } + if (fallback_ins && !found) { + /* No ECMP-able route found, replace first non-ECMP one */ + ins = fallback_ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + found++; + } + /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; /* Link this route to others same route. */ - if (append && match) { + if (rt->fib6_nsiblings) { + unsigned int fib6_nsiblings; struct fib6_info *sibling, *temp_sibling; - if (rt->fib6_flags & RTF_REJECT) { - NL_SET_ERR_MSG(extack, - "Can not append a REJECT route"); - return -EINVAL; - } else if (match->fib6_flags & RTF_REJECT) { - NL_SET_ERR_MSG(extack, - "Can not append to a REJECT route"); - return -EINVAL; + /* Find the first route that have the same metric */ + sibling = leaf; + while (sibling) { + if (sibling->fib6_metric == rt->fib6_metric && + rt6_qualify_for_ecmp(sibling)) { + list_add_tail(&rt->fib6_siblings, + &sibling->fib6_siblings); + break; + } + sibling = rcu_dereference_protected(sibling->fib6_next, + lockdep_is_held(&rt->fib6_table->tb6_lock)); } - event = FIB_EVENT_ENTRY_APPEND; - rt->fib6_nsiblings = match->fib6_nsiblings; - list_add_tail(&rt->fib6_siblings, &match->fib6_siblings); - match->fib6_nsiblings++; - /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings * is broken! */ + fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, - &match->fib6_siblings, fib6_siblings) { + &rt->fib6_siblings, fib6_siblings) { sibling->fib6_nsiblings++; - BUG_ON(sibling->fib6_nsiblings != match->fib6_nsiblings); + BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); + fib6_nsiblings++; } - - rt6_multipath_rebalance(match); + BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); + rt6_multipath_rebalance(temp_sibling); } /* @@ -1043,8 +1067,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, add: nlflags |= NLM_F_CREATE; - err = call_fib6_entry_notifiers(info->nl_net, event, rt, - extack); + err = call_fib6_entry_notifiers(info->nl_net, + FIB_EVENT_ENTRY_ADD, + rt, extack); if (err) return err; @@ -1062,7 +1087,7 @@ add: } } else { - struct fib6_info *tmp; + int nsiblings; if (!found) { if (add) @@ -1077,57 +1102,48 @@ add: if (err) return err; - /* if route being replaced has siblings, set tmp to - * last one, otherwise tmp is current route. this is - * used to set fib6_next for new route - */ - if (iter->fib6_nsiblings) - tmp = list_last_entry(&iter->fib6_siblings, - struct fib6_info, - fib6_siblings); - else - tmp = iter; - - /* insert new route */ atomic_inc(&rt->fib6_ref); rcu_assign_pointer(rt->fib6_node, fn); - rt->fib6_next = tmp->fib6_next; + rt->fib6_next = iter->fib6_next; rcu_assign_pointer(*ins, rt); - if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + nsiblings = iter->fib6_nsiblings; + iter->fib6_node = NULL; + fib6_purge_rt(iter, fn, info->nl_net); + if (rcu_access_pointer(fn->rr_ptr) == iter) + fn->rr_ptr = NULL; + fib6_info_release(iter); - /* delete old route */ - rt = iter; - - if (rt->fib6_nsiblings) { - struct fib6_info *tmp; - + if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ - list_for_each_entry_safe(iter, tmp, &rt->fib6_siblings, - fib6_siblings) { - iter->fib6_node = NULL; - fib6_purge_rt(iter, fn, info->nl_net); - if (rcu_access_pointer(fn->rr_ptr) == iter) - fn->rr_ptr = NULL; - fib6_info_release(iter); - - rt->fib6_nsiblings--; - info->nl_net->ipv6.rt6_stats->fib_rt_entries--; + ins = &rt->fib6_next; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + while (iter) { + if (iter->fib6_metric > rt->fib6_metric) + break; + if (rt6_qualify_for_ecmp(iter)) { + *ins = iter->fib6_next; + iter->fib6_node = NULL; + fib6_purge_rt(iter, fn, info->nl_net); + if (rcu_access_pointer(fn->rr_ptr) == iter) + fn->rr_ptr = NULL; + fib6_info_release(iter); + nsiblings--; + info->nl_net->ipv6.rt6_stats->fib_rt_entries--; + } else { + ins = &iter->fib6_next; + } + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->fib6_table->tb6_lock)); } + WARN_ON(nsiblings != 0); } - - WARN_ON(rt->fib6_nsiblings != 0); - - rt->fib6_node = NULL; - fib6_purge_rt(rt, fn, info->nl_net); - if (rcu_access_pointer(fn->rr_ptr) == rt) - fn->rr_ptr = NULL; - fib6_info_release(rt); } return 0; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c8cf2fdbb13b..cd2cfb04e5d8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -927,7 +927,6 @@ tx_err: static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct ip6_tnl *t = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); struct net_device_stats *stats; @@ -1010,6 +1009,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; } } else { + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + switch (skb->protocol) { case htons(ETH_P_IP): memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a14fb4fcdf18..3168847c30d1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -570,6 +570,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 00e138a44cbb..1cc9650af9fb 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1133,12 +1133,8 @@ route_lookup: max_headroom += 8; mtu -= 8; } - if (skb->protocol == htons(ETH_P_IPV6)) { - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; - } else if (mtu < 576) { - mtu = 576; - } + mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ? + IPV6_MIN_MTU : IPV4_MIN_MTU); skb_dst_update_pmtu(skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index b7f28deddaea..c72ae3a4fe09 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -480,10 +480,6 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) goto tx_err_dst_release; } - skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); - skb_dst_set(skb, dst); - skb->dev = skb_dst(skb)->dev; - mtu = dst_mtu(dst); if (!skb->ignore_df && skb->len > mtu) { skb_dst_update_pmtu(skb, mtu); @@ -498,9 +494,14 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) htonl(mtu)); } - return -EMSGSIZE; + err = -EMSGSIZE; + goto tx_err_dst_release; } + skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); + skb_dst_set(skb, dst); + skb->dev = skb_dst(skb)->dev; + err = dst_output(t->net, skb->sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4d780c7f0130..568ca4187cd1 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -398,6 +398,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_DSTOPTS: { struct ipv6_txoptions *opt; + struct ipv6_opt_hdr *new = NULL; + + /* hop-by-hop / destination options are privileged option */ + retv = -EPERM; + if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) + break; /* remove any sticky options header with a zero option * length, per RFC3542. @@ -409,17 +415,22 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, else if (optlen < sizeof(struct ipv6_opt_hdr) || optlen & 0x7 || optlen > 8 * 255) goto e_inval; - - /* hop-by-hop / destination options are privileged option */ - retv = -EPERM; - if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) - break; + else { + new = memdup_user(optval, optlen); + if (IS_ERR(new)) { + retv = PTR_ERR(new); + break; + } + if (unlikely(ipv6_optlen(new) > optlen)) { + kfree(new); + goto e_inval; + } + } opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); - opt = ipv6_renew_options(sk, opt, optname, - (struct ipv6_opt_hdr __user *)optval, - optlen); + opt = ipv6_renew_options(sk, opt, optname, new); + kfree(new); if (IS_ERR(opt)) { retv = PTR_ERR(opt); break; @@ -718,8 +729,9 @@ done: struct sockaddr_in6 *psin6; psin6 = (struct sockaddr_in6 *)&greqs.gsr_group; - retv = ipv6_sock_mc_join(sk, greqs.gsr_interface, - &psin6->sin6_addr); + retv = ipv6_sock_mc_join_ssm(sk, greqs.gsr_interface, + &psin6->sin6_addr, + MCAST_INCLUDE); /* prior join w/ different source is ok */ if (retv && retv != -EADDRINUSE) break; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index c0c74088f2af..f60f310785fd 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -95,6 +95,8 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int delta); static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); +static int __ipv6_dev_mc_inc(struct net_device *dev, + const struct in6_addr *addr, unsigned int mode); #define MLD_QRV_DEFAULT 2 /* RFC3810, 9.2. Query Interval */ @@ -132,7 +134,8 @@ static int unsolicited_report_interval(struct inet6_dev *idev) return iv > 0 ? iv : 1; } -int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) +static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, + const struct in6_addr *addr, unsigned int mode) { struct net_device *dev = NULL; struct ipv6_mc_socklist *mc_lst; @@ -179,7 +182,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) } mc_lst->ifindex = dev->ifindex; - mc_lst->sfmode = MCAST_EXCLUDE; + mc_lst->sfmode = mode; rwlock_init(&mc_lst->sflock); mc_lst->sflist = NULL; @@ -187,7 +190,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) * now add/increase the group membership on the device */ - err = ipv6_dev_mc_inc(dev, addr); + err = __ipv6_dev_mc_inc(dev, addr, mode); if (err) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); @@ -199,8 +202,19 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } + +int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) +{ + return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE); +} EXPORT_SYMBOL(ipv6_sock_mc_join); +int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, + const struct in6_addr *addr, unsigned int mode) +{ + return __ipv6_sock_mc_join(sk, ifindex, addr, mode); +} + /* * socket leave on multicast group */ @@ -646,7 +660,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, return rv; } -static void igmp6_group_added(struct ifmcaddr6 *mc) +static void igmp6_group_added(struct ifmcaddr6 *mc, unsigned int mode) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; @@ -672,7 +686,13 @@ static void igmp6_group_added(struct ifmcaddr6 *mc) } /* else v2 */ - mc->mca_crcount = mc->idev->mc_qrv; + /* Based on RFC3810 6.1, for newly added INCLUDE SSM, we + * should not send filter-mode change record as the mode + * should be from IN() to IN(A). + */ + if (mode == MCAST_EXCLUDE) + mc->mca_crcount = mc->idev->mc_qrv; + mld_ifc_event(mc->idev); } @@ -770,13 +790,13 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) spin_lock_bh(&im->mca_lock); if (pmc) { im->idev = pmc->idev; - im->mca_crcount = idev->mc_qrv; - im->mca_sfmode = pmc->mca_sfmode; - if (pmc->mca_sfmode == MCAST_INCLUDE) { + if (im->mca_sfmode == MCAST_INCLUDE) { im->mca_tomb = pmc->mca_tomb; im->mca_sources = pmc->mca_sources; for (psf = im->mca_sources; psf; psf = psf->sf_next) - psf->sf_crcount = im->mca_crcount; + psf->sf_crcount = idev->mc_qrv; + } else { + im->mca_crcount = idev->mc_qrv; } in6_dev_put(pmc->idev); kfree(pmc); @@ -831,7 +851,8 @@ static void ma_put(struct ifmcaddr6 *mc) } static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, - const struct in6_addr *addr) + const struct in6_addr *addr, + unsigned int mode) { struct ifmcaddr6 *mc; @@ -849,9 +870,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, refcount_set(&mc->mca_refcnt, 1); spin_lock_init(&mc->mca_lock); - /* initial mode is (EX, empty) */ - mc->mca_sfmode = MCAST_EXCLUDE; - mc->mca_sfcount[MCAST_EXCLUDE] = 1; + mc->mca_sfmode = mode; + mc->mca_sfcount[mode] = 1; if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) || IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) @@ -863,7 +883,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, /* * device multicast group inc (add if not found) */ -int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) +static int __ipv6_dev_mc_inc(struct net_device *dev, + const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; struct inet6_dev *idev; @@ -887,14 +908,13 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) if (ipv6_addr_equal(&mc->mca_addr, addr)) { mc->mca_users++; write_unlock_bh(&idev->lock); - ip6_mc_add_src(idev, &mc->mca_addr, MCAST_EXCLUDE, 0, - NULL, 0); + ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0); in6_dev_put(idev); return 0; } } - mc = mca_alloc(idev, addr); + mc = mca_alloc(idev, addr, mode); if (!mc) { write_unlock_bh(&idev->lock); in6_dev_put(idev); @@ -911,11 +931,16 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) write_unlock_bh(&idev->lock); mld_del_delrec(idev, mc); - igmp6_group_added(mc); + igmp6_group_added(mc, mode); ma_put(mc); return 0; } +int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) +{ + return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE); +} + /* * device multicast group del */ @@ -1751,7 +1776,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, psf_next = psf->sf_next; - if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { + if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) { psf_prev = psf; continue; } @@ -2066,7 +2091,7 @@ static void mld_send_initial_cr(struct inet6_dev *idev) if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_CHANGE_TO_EXCLUDE; else - type = MLD2_CHANGE_TO_INCLUDE; + type = MLD2_ALLOW_NEW_SOURCES; skb = add_grec(skb, pmc, type, 0, 0, 1); spin_unlock_bh(&pmc->mca_lock); } @@ -2546,7 +2571,7 @@ void ipv6_mc_up(struct inet6_dev *idev) ipv6_mc_reset(idev); for (i = idev->mc_list; i; i = i->next) { mld_del_delrec(idev, i); - igmp6_group_added(i); + igmp6_group_added(i, i->mca_sfmode); } read_unlock_bh(&idev->lock); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index e640d2f3c55c..0ec273997d1d 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -811,7 +811,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) return; } } - if (ndopts.nd_opts_nonce) + if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1) memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6); inc = ipv6_addr_is_multicast(daddr); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 7eab959734bc..daf2e9e9193d 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1909,6 +1909,7 @@ static struct xt_match ip6t_builtin_mt[] __read_mostly = { .checkentry = icmp6_checkentry, .proto = IPPROTO_ICMPV6, .family = NFPROTO_IPV6, + .me = THIS_MODULE, }, }; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index a452d99c9f52..e4d9e6976d3c 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -585,6 +585,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) fq->q.meat == fq->q.len && nf_ct_frag6_reasm(fq, skb, dev)) ret = 0; + else + skb_dst_drop(skb); out_unlock: spin_unlock_bh(&fq->q.lock); diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c index bf1d6c421e3b..5dfd33af6451 100644 --- a/net/ipv6/netfilter/nf_tproxy_ipv6.c +++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c @@ -55,7 +55,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, * to a listener socket if there's one */ struct sock *sk2; - sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, hp, tproto, + sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, tproto, &iph->saddr, nf_tproxy_laddr6(skb, laddr, &iph->daddr), hp->source, @@ -72,7 +72,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait6); struct sock * -nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, +nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, const u8 protocol, const struct in6_addr *saddr, const struct in6_addr *daddr, const __be16 sport, const __be16 dport, @@ -80,15 +80,20 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, const enum nf_tproxy_lookup_t lookup_type) { struct sock *sk; - struct tcphdr *tcph; switch (protocol) { - case IPPROTO_TCP: + case IPPROTO_TCP: { + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, thoff, + sizeof(struct tcphdr), &_hdr); + if (hp == NULL) + return NULL; + switch (lookup_type) { case NF_TPROXY_LOOKUP_LISTENER: - tcph = hp; sk = inet6_lookup_listener(net, &tcp_hashinfo, skb, - thoff + __tcp_hdrlen(tcph), + thoff + __tcp_hdrlen(hp), saddr, sport, daddr, ntohs(dport), in->ifindex, 0); @@ -110,6 +115,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, BUG(); } break; + } case IPPROTO_UDP: sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, in->ifindex); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 86a0e4333d42..7208c16302f6 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -972,18 +972,15 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) rt->dst.lastuse = jiffies; } +/* Caller must already hold reference to @from */ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; - fib6_info_hold(from); rcu_assign_pointer(rt->from, from); dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); - if (from->fib6_metrics != &dst_default_metrics) { - rt->dst._metrics |= DST_METRICS_REFCOUNTED; - refcount_inc(&from->fib6_metrics->refcnt); - } } +/* Caller must already hold reference to @ort */ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) { struct net_device *dev = fib6_info_nh_dev(ort); @@ -1044,9 +1041,14 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt) struct net_device *dev = rt->fib6_nh.nh_dev; struct rt6_info *nrt; + if (!fib6_info_hold_safe(rt)) + return NULL; + nrt = ip6_dst_alloc(dev_net(dev), dev, flags); if (nrt) ip6_rt_copy_init(nrt, rt); + else + fib6_info_release(rt); return nrt; } @@ -1178,10 +1180,15 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort, * Clone the route. */ + if (!fib6_info_hold_safe(ort)) + return NULL; + dev = ip6_rt_get_dev_rcu(ort); rt = ip6_dst_alloc(dev_net(dev), dev, 0); - if (!rt) + if (!rt) { + fib6_info_release(ort); return NULL; + } ip6_rt_copy_init(rt, ort); rt->rt6i_flags |= RTF_CACHE; @@ -1210,12 +1217,17 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt) struct net_device *dev; struct rt6_info *pcpu_rt; + if (!fib6_info_hold_safe(rt)) + return NULL; + rcu_read_lock(); dev = ip6_rt_get_dev_rcu(rt); pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags); rcu_read_unlock(); - if (!pcpu_rt) + if (!pcpu_rt) { + fib6_info_release(rt); return NULL; + } ip6_rt_copy_init(pcpu_rt, rt); pcpu_rt->rt6i_flags |= RTF_PCPU; return pcpu_rt; @@ -2486,7 +2498,7 @@ restart: out: if (ret) - dst_hold(&ret->dst); + ip6_hold_safe(net, &ret, true); else ret = ip6_create_rt_rcu(rt); @@ -3303,7 +3315,8 @@ static int ip6_route_del(struct fib6_config *cfg, continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; rcu_read_unlock(); /* if gateway was specified only delete the one hop */ @@ -3409,6 +3422,9 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu rcu_read_lock(); from = rcu_dereference(rt->from); + /* This fib6_info_hold() is safe here because we hold reference to rt + * and rt already holds reference to fib6_info. + */ fib6_info_hold(from); rcu_read_unlock(); @@ -3470,7 +3486,8 @@ static struct fib6_info *rt6_get_route_info(struct net *net, continue; if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr)) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; break; } out: @@ -3530,8 +3547,8 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr)) break; } - if (rt) - fib6_info_hold(rt); + if (rt && !fib6_info_hold_safe(rt)) + rt = NULL; rcu_read_unlock(); return rt; } @@ -3579,8 +3596,8 @@ restart: struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && - (!idev || idev->cnf.accept_ra != 2)) { - fib6_info_hold(rt); + (!idev || idev->cnf.accept_ra != 2) && + fib6_info_hold_safe(rt)) { rcu_read_unlock(); ip6_del_rt(net, rt); goto restart; @@ -3842,7 +3859,7 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric == rt->fib6_metric && - iter->fib6_nsiblings) + rt6_qualify_for_ecmp(iter)) return iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); @@ -4388,6 +4405,13 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, rt = NULL; goto cleanup; } + if (!rt6_qualify_for_ecmp(rt)) { + err = -EINVAL; + NL_SET_ERR_MSG(extack, + "Device only routes can not be added for IPv6 using the multipath API."); + fib6_info_release(rt); + goto cleanup; + } rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1; @@ -4439,7 +4463,6 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); - cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_APPEND; nhn++; } diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 19ccf0dc996c..a8854dd3e9c5 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -101,7 +101,7 @@ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb, if (do_flowlabel > 0) { hash = skb_get_hash(skb); - rol32(hash, 16); + hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; } else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) { flowlabel = ip6_flowlabel(inner_hdr); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7efa9fd7e109..03e6b7a2bc53 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -938,7 +938,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) &tcp_hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, - ntohs(th->source), tcp_v6_iif(skb), + ntohs(th->source), + tcp_v6_iif_l3_slave(skb), tcp_v6_sdif(skb)); if (!sk1) goto out; @@ -1609,7 +1610,8 @@ do_time_wait: skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, - ntohs(th->dest), tcp_v6_iif(skb), + ntohs(th->dest), + tcp_v6_iif_l3_slave(skb), sdif); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index e398797878a9..cf6cca260e7b 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1201,13 +1201,18 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel, l2tp_session_get(sock_net(sk), tunnel, stats.session_id); - if (session && session->pwtype == L2TP_PWTYPE_PPP) { - err = pppol2tp_session_ioctl(session, cmd, - arg); + if (!session) { + err = -EBADR; + break; + } + if (session->pwtype != L2TP_PWTYPE_PPP) { l2tp_session_dec_refcount(session); - } else { err = -EBADR; + break; } + + err = pppol2tp_session_ioctl(session, cmd, arg); + l2tp_session_dec_refcount(session); break; } #ifdef CONFIG_XFRM diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 89041260784c..260b3dc1b4a2 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -73,8 +73,8 @@ struct llc_sap *llc_sap_find(unsigned char sap_value) rcu_read_lock_bh(); sap = __llc_sap_find(sap_value); - if (sap) - llc_sap_hold(sap); + if (!sap || !llc_sap_hold_safe(sap)) + sap = NULL; rcu_read_unlock_bh(); return sap; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0a38cc1cbebc..932985ca4e66 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2254,11 +2254,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, sdata->control_port_over_nl80211)) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); bool noencrypt = status->flag & RX_FLAG_DECRYPTED; - struct ethhdr *ehdr = eth_hdr(skb); - cfg80211_rx_control_port(dev, skb->data, skb->len, - ehdr->h_source, - be16_to_cpu(skb->protocol), noencrypt); + cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { /* deliver to local stack */ diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 5e2e511c4a6f..d02fbfec3783 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2111,7 +2111,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (!sta->uploaded) continue; - if (sta->sdata->vif.type != NL80211_IFTYPE_AP) + if (sta->sdata->vif.type != NL80211_IFTYPE_AP && + sta->sdata->vif.type != NL80211_IFTYPE_AP_VLAN) continue; for (state = IEEE80211_STA_NOTEXIST; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index dbd7d1fad277..f0a1c536ef15 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -460,6 +460,13 @@ config NF_TABLES if NF_TABLES +config NF_TABLES_SET + tristate "Netfilter nf_tables set infrastructure" + help + This option enables the nf_tables set infrastructure that allows to + look up for elements in a set and to build one-way mappings between + matchings and actions. + config NF_TABLES_INET depends on IPV6 select NF_TABLES_IPV4 @@ -493,24 +500,6 @@ config NFT_FLOW_OFFLOAD This option adds the "flow_offload" expression that you can use to choose what flows are placed into the hardware. -config NFT_SET_RBTREE - tristate "Netfilter nf_tables rbtree set module" - help - This option adds the "rbtree" set type (Red Black tree) that is used - to build interval-based sets. - -config NFT_SET_HASH - tristate "Netfilter nf_tables hash set module" - help - This option adds the "hash" set type that is used to build one-way - mappings between matchings and actions. - -config NFT_SET_BITMAP - tristate "Netfilter nf_tables bitmap set module" - help - This option adds the "bitmap" set type that is used to build sets - whose keys are smaller or equal to 16 bits. - config NFT_COUNTER tristate "Netfilter nf_tables counter module" help diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 44449389e527..8a76dced974d 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -78,7 +78,11 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o +nf_tables_set-objs := nf_tables_set_core.o \ + nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o + obj-$(CONFIG_NF_TABLES) += nf_tables.o +obj-$(CONFIG_NF_TABLES_SET) += nf_tables_set.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_CONNLIMIT) += nft_connlimit.o obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o @@ -91,9 +95,6 @@ obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o -obj-$(CONFIG_NFT_SET_RBTREE) += nft_set_rbtree.o -obj-$(CONFIG_NFT_SET_HASH) += nft_set_hash.o -obj-$(CONFIG_NFT_SET_BITMAP) += nft_set_bitmap.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o obj-$(CONFIG_NFT_LOG) += nft_log.o obj-$(CONFIG_NFT_MASQ) += nft_masq.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3465da2a98bd..3d5280425027 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2043,7 +2043,7 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp) return -EOPNOTSUPP; /* On boot, we can set this without any fancy locking. */ - if (!nf_conntrack_htable_size) + if (!nf_conntrack_hash) return param_set_uint(val, kp); rc = kstrtouint(val, 0, &hashsize); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index abe647d5b8c6..9ce6336d1e55 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -243,14 +243,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, [CT_DCCP_ROLE_SERVER] = { @@ -371,14 +371,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 896d4a36081d..f5745e4c6513 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -75,6 +75,7 @@ static void nft_ctx_init(struct nft_ctx *ctx, { ctx->net = net; ctx->family = family; + ctx->level = 0; ctx->table = table; ctx->chain = chain; ctx->nla = nla; @@ -1597,7 +1598,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, struct nft_base_chain *basechain; struct nft_stats *stats = NULL; struct nft_chain_hook hook; - const struct nlattr *name; struct nf_hook_ops *ops; struct nft_trans *trans; int err; @@ -1645,12 +1645,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, return PTR_ERR(stats); } + err = -ENOMEM; trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); - if (trans == NULL) { - free_percpu(stats); - return -ENOMEM; - } + if (trans == NULL) + goto err; nft_trans_chain_stats(trans) = stats; nft_trans_chain_update(trans) = true; @@ -1660,19 +1659,37 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, else nft_trans_chain_policy(trans) = -1; - name = nla[NFTA_CHAIN_NAME]; - if (nla[NFTA_CHAIN_HANDLE] && name) { - nft_trans_chain_name(trans) = - nla_strdup(name, GFP_KERNEL); - if (!nft_trans_chain_name(trans)) { - kfree(trans); - free_percpu(stats); - return -ENOMEM; + if (nla[NFTA_CHAIN_HANDLE] && + nla[NFTA_CHAIN_NAME]) { + struct nft_trans *tmp; + char *name; + + err = -ENOMEM; + name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); + if (!name) + goto err; + + err = -EEXIST; + list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) { + if (tmp->msg_type == NFT_MSG_NEWCHAIN && + tmp->ctx.table == table && + nft_trans_chain_update(tmp) && + nft_trans_chain_name(tmp) && + strcmp(name, nft_trans_chain_name(tmp)) == 0) { + kfree(name); + goto err; + } } + + nft_trans_chain_name(trans) = name; } list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; +err: + free_percpu(stats); + kfree(trans); + return err; } static int nf_tables_newchain(struct net *net, struct sock *nlsk, @@ -2254,6 +2271,39 @@ done: return skb->len; } +static int nf_tables_dump_rules_start(struct netlink_callback *cb) +{ + const struct nlattr * const *nla = cb->data; + struct nft_rule_dump_ctx *ctx = NULL; + + if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); + if (!ctx) + return -ENOMEM; + + if (nla[NFTA_RULE_TABLE]) { + ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], + GFP_ATOMIC); + if (!ctx->table) { + kfree(ctx); + return -ENOMEM; + } + } + if (nla[NFTA_RULE_CHAIN]) { + ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], + GFP_ATOMIC); + if (!ctx->chain) { + kfree(ctx->table); + kfree(ctx); + return -ENOMEM; + } + } + } + + cb->data = ctx; + return 0; +} + static int nf_tables_dump_rules_done(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = cb->data; @@ -2283,38 +2333,13 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start= nf_tables_dump_rules_start, .dump = nf_tables_dump_rules, .done = nf_tables_dump_rules_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { - struct nft_rule_dump_ctx *ctx; - - ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); - if (!ctx) - return -ENOMEM; - - if (nla[NFTA_RULE_TABLE]) { - ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], - GFP_ATOMIC); - if (!ctx->table) { - kfree(ctx); - return -ENOMEM; - } - } - if (nla[NFTA_RULE_CHAIN]) { - ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], - GFP_ATOMIC); - if (!ctx->chain) { - kfree(ctx->table); - kfree(ctx); - return -ENOMEM; - } - } - c.data = ctx; - } - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -2384,6 +2409,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) struct nft_rule *rule; int err; + if (ctx->level == NFT_JUMP_STACK_SIZE) + return -EMLINK; + list_for_each_entry(rule, &chain->rules, list) { if (!nft_is_active_next(ctx->net, rule)) continue; @@ -3161,6 +3189,18 @@ done: return skb->len; } +static int nf_tables_dump_sets_start(struct netlink_callback *cb) +{ + struct nft_ctx *ctx_dump = NULL; + + ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC); + if (ctx_dump == NULL) + return -ENOMEM; + + cb->data = ctx_dump; + return 0; +} + static int nf_tables_dump_sets_done(struct netlink_callback *cb) { kfree(cb->data); @@ -3188,18 +3228,12 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_sets_start, .dump = nf_tables_dump_sets, .done = nf_tables_dump_sets_done, + .data = &ctx, .module = THIS_MODULE, }; - struct nft_ctx *ctx_dump; - - ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_ATOMIC); - if (ctx_dump == NULL) - return -ENOMEM; - - *ctx_dump = ctx; - c.data = ctx_dump; return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -3849,6 +3883,15 @@ nla_put_failure: return -ENOSPC; } +static int nf_tables_dump_set_start(struct netlink_callback *cb) +{ + struct nft_set_dump_ctx *dump_ctx = cb->data; + + cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC); + + return cb->data ? 0 : -ENOMEM; +} + static int nf_tables_dump_set_done(struct netlink_callback *cb) { kfree(cb->data); @@ -4002,20 +4045,17 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_set_start, .dump = nf_tables_dump_set, .done = nf_tables_dump_set_done, .module = THIS_MODULE, }; - struct nft_set_dump_ctx *dump_ctx; - - dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_ATOMIC); - if (!dump_ctx) - return -ENOMEM; - - dump_ctx->set = set; - dump_ctx->ctx = ctx; + struct nft_set_dump_ctx dump_ctx = { + .set = set, + .ctx = ctx, + }; - c.data = dump_ctx; + c.data = &dump_ctx; return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -4975,38 +5015,42 @@ done: return skb->len; } -static int nf_tables_dump_obj_done(struct netlink_callback *cb) +static int nf_tables_dump_obj_start(struct netlink_callback *cb) { - struct nft_obj_filter *filter = cb->data; + const struct nlattr * const *nla = cb->data; + struct nft_obj_filter *filter = NULL; - if (filter) { - kfree(filter->table); - kfree(filter); + if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) { + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); + if (!filter) + return -ENOMEM; + + if (nla[NFTA_OBJ_TABLE]) { + filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); + if (!filter->table) { + kfree(filter); + return -ENOMEM; + } + } + + if (nla[NFTA_OBJ_TYPE]) + filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); } + cb->data = filter; return 0; } -static struct nft_obj_filter * -nft_obj_filter_alloc(const struct nlattr * const nla[]) +static int nf_tables_dump_obj_done(struct netlink_callback *cb) { - struct nft_obj_filter *filter; - - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); - if (!filter) - return ERR_PTR(-ENOMEM); + struct nft_obj_filter *filter = cb->data; - if (nla[NFTA_OBJ_TABLE]) { - filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return ERR_PTR(-ENOMEM); - } + if (filter) { + kfree(filter->table); + kfree(filter); } - if (nla[NFTA_OBJ_TYPE]) - filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - return filter; + return 0; } /* called with rcu_read_lock held */ @@ -5027,21 +5071,13 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, .dump = nf_tables_dump_obj, .done = nf_tables_dump_obj_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_OBJ_TABLE] || - nla[NFTA_OBJ_TYPE]) { - struct nft_obj_filter *filter; - - filter = nft_obj_filter_alloc(nla); - if (IS_ERR(filter)) - return -ENOMEM; - - c.data = filter; - } return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5320,8 +5356,6 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx, flowtable->ops[i].priv = &flowtable->data; flowtable->ops[i].hook = flowtable->data.type->hook; flowtable->ops[i].dev = dev_array[i]; - flowtable->dev_name[i] = kstrdup(dev_array[i]->name, - GFP_KERNEL); } return err; @@ -5479,10 +5513,8 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, err6: i = flowtable->ops_len; err5: - for (k = i - 1; k >= 0; k--) { - kfree(flowtable->dev_name[k]); + for (k = i - 1; k >= 0; k--) nf_unregister_net_hook(net, &flowtable->ops[k]); - } kfree(flowtable->ops); err4: @@ -5581,9 +5613,10 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; for (i = 0; i < flowtable->ops_len; i++) { - if (flowtable->dev_name[i][0] && - nla_put_string(skb, NFTA_DEVICE_NAME, - flowtable->dev_name[i])) + const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev); + + if (dev && + nla_put_string(skb, NFTA_DEVICE_NAME, dev->name)) goto nla_put_failure; } nla_nest_end(skb, nest_devs); @@ -5650,37 +5683,39 @@ done: return skb->len; } -static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) +static int nf_tables_dump_flowtable_start(struct netlink_callback *cb) { - struct nft_flowtable_filter *filter = cb->data; + const struct nlattr * const *nla = cb->data; + struct nft_flowtable_filter *filter = NULL; - if (!filter) - return 0; + if (nla[NFTA_FLOWTABLE_TABLE]) { + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); + if (!filter) + return -ENOMEM; - kfree(filter->table); - kfree(filter); + filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], + GFP_ATOMIC); + if (!filter->table) { + kfree(filter); + return -ENOMEM; + } + } + cb->data = filter; return 0; } -static struct nft_flowtable_filter * -nft_flowtable_filter_alloc(const struct nlattr * const nla[]) +static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) { - struct nft_flowtable_filter *filter; + struct nft_flowtable_filter *filter = cb->data; - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); if (!filter) - return ERR_PTR(-ENOMEM); + return 0; - if (nla[NFTA_FLOWTABLE_TABLE]) { - filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], - GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return ERR_PTR(-ENOMEM); - } - } - return filter; + kfree(filter->table); + kfree(filter); + + return 0; } /* called with rcu_read_lock held */ @@ -5700,20 +5735,13 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_flowtable_start, .dump = nf_tables_dump_flowtable, .done = nf_tables_dump_flowtable_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_FLOWTABLE_TABLE]) { - struct nft_flowtable_filter *filter; - - filter = nft_flowtable_filter_alloc(nla); - if (IS_ERR(filter)) - return -ENOMEM; - - c.data = filter; - } return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5783,6 +5811,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); module_put(flowtable->data.type->owner); + kfree(flowtable); } static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, @@ -5825,7 +5854,6 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev, continue; nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]); - flowtable->dev_name[i][0] = '\0'; flowtable->ops[i].dev = NULL; break; } @@ -6086,6 +6114,9 @@ static void nft_commit_release(struct nft_trans *trans) case NFT_MSG_DELTABLE: nf_tables_table_destroy(&trans->ctx); break; + case NFT_MSG_NEWCHAIN: + kfree(nft_trans_chain_name(trans)); + break; case NFT_MSG_DELCHAIN: nf_tables_chain_destroy(&trans->ctx); break; @@ -6315,13 +6346,15 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE); break; case NFT_MSG_NEWCHAIN: - if (nft_trans_chain_update(trans)) + if (nft_trans_chain_update(trans)) { nft_chain_commit_update(trans); - else + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + /* trans destroyed after rcu grace period */ + } else { nft_clear(net, trans->ctx.chain); - - nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); - nft_trans_destroy(trans); + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + nft_trans_destroy(trans); + } break; case NFT_MSG_DELCHAIN: nft_chain_del(trans->ctx.chain); @@ -6471,7 +6504,7 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { free_percpu(nft_trans_chain_stats(trans)); - + kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { trans->ctx.table->use--; @@ -6837,13 +6870,6 @@ int nft_validate_register_store(const struct nft_ctx *ctx, err = nf_tables_check_loops(ctx, data->verdict.chain); if (err < 0) return err; - - if (ctx->chain->level + 1 > - data->verdict.chain->level) { - if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE) - return -EMLINK; - data->verdict.chain->level = ctx->chain->level + 1; - } } return 0; diff --git a/net/netfilter/nf_tables_set_core.c b/net/netfilter/nf_tables_set_core.c new file mode 100644 index 000000000000..814789644bd3 --- /dev/null +++ b/net/netfilter/nf_tables_set_core.c @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <net/netfilter/nf_tables_core.h> + +static int __init nf_tables_set_module_init(void) +{ + nft_register_set(&nft_set_hash_fast_type); + nft_register_set(&nft_set_hash_type); + nft_register_set(&nft_set_rhash_type); + nft_register_set(&nft_set_bitmap_type); + nft_register_set(&nft_set_rbtree_type); + + return 0; +} + +static void __exit nf_tables_set_module_exit(void) +{ + nft_unregister_set(&nft_set_rbtree_type); + nft_unregister_set(&nft_set_bitmap_type); + nft_unregister_set(&nft_set_rhash_type); + nft_unregister_set(&nft_set_hash_type); + nft_unregister_set(&nft_set_hash_fast_type); +} + +module_init(nf_tables_set_module_init); +module_exit(nf_tables_set_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 8d1ff654e5af..32535eea51b2 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -832,10 +832,18 @@ nft_target_select_ops(const struct nft_ctx *ctx, rev = ntohl(nla_get_be32(tb[NFTA_TARGET_REV])); family = ctx->family; + if (strcmp(tg_name, XT_ERROR_TARGET) == 0 || + strcmp(tg_name, XT_STANDARD_TARGET) == 0 || + strcmp(tg_name, "standard") == 0) + return ERR_PTR(-EINVAL); + /* Re-use the existing target if it's already loaded. */ list_for_each_entry(nft_target, &nft_target_list, head) { struct xt_target *target = nft_target->ops.data; + if (!target->target) + continue; + if (nft_target_cmp(target, tg_name, rev, family)) return &nft_target->ops; } @@ -844,6 +852,11 @@ nft_target_select_ops(const struct nft_ctx *ctx, if (IS_ERR(target)) return ERR_PTR(-ENOENT); + if (!target->target) { + err = -EINVAL; + goto err; + } + if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) { err = -EINVAL; goto err; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 15adf8ca82c3..0777a93211e2 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -98,6 +98,7 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, const struct nft_data **d) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; int err; @@ -109,9 +110,11 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: + pctx->level++; err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; + pctx->level--; break; default: break; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 42e6fadf1417..c2a1d84cdfc4 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -155,7 +155,9 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; + int err; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) @@ -165,10 +167,17 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - return nft_chain_validate(ctx, data->verdict.chain); + pctx->level++; + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + pctx->level--; + break; default: - return 0; + break; } + + return 0; } static int nft_lookup_validate(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index d6626e01c7ee..128bc16f52dd 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -296,7 +296,7 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_bitmap_type __read_mostly = { +struct nft_set_type nft_set_bitmap_type __read_mostly = { .owner = THIS_MODULE, .ops = { .privsize = nft_bitmap_privsize, @@ -314,20 +314,3 @@ static struct nft_set_type nft_bitmap_type __read_mostly = { .get = nft_bitmap_get, }, }; - -static int __init nft_bitmap_module_init(void) -{ - return nft_register_set(&nft_bitmap_type); -} - -static void __exit nft_bitmap_module_exit(void) -{ - nft_unregister_set(&nft_bitmap_type); -} - -module_init(nft_bitmap_module_init); -module_exit(nft_bitmap_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 6f9a1365a09f..90c3e7e6cacb 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -387,6 +387,7 @@ static void nft_rhash_destroy(const struct nft_set *set) struct nft_rhash *priv = nft_set_priv(set); cancel_delayed_work_sync(&priv->gc_work); + rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)set); } @@ -654,7 +655,7 @@ static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features return true; } -static struct nft_set_type nft_rhash_type __read_mostly = { +struct nft_set_type nft_set_rhash_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT | NFT_SET_EVAL, @@ -677,7 +678,7 @@ static struct nft_set_type nft_rhash_type __read_mostly = { }, }; -static struct nft_set_type nft_hash_type __read_mostly = { +struct nft_set_type nft_set_hash_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_MAP | NFT_SET_OBJECT, .ops = { @@ -697,7 +698,7 @@ static struct nft_set_type nft_hash_type __read_mostly = { }, }; -static struct nft_set_type nft_hash_fast_type __read_mostly = { +struct nft_set_type nft_set_hash_fast_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_MAP | NFT_SET_OBJECT, .ops = { @@ -716,26 +717,3 @@ static struct nft_set_type nft_hash_fast_type __read_mostly = { .get = nft_hash_get, }, }; - -static int __init nft_hash_module_init(void) -{ - if (nft_register_set(&nft_hash_fast_type) || - nft_register_set(&nft_hash_type) || - nft_register_set(&nft_rhash_type)) - return 1; - return 0; -} - -static void __exit nft_hash_module_exit(void) -{ - nft_unregister_set(&nft_rhash_type); - nft_unregister_set(&nft_hash_type); - nft_unregister_set(&nft_hash_fast_type); -} - -module_init(nft_hash_module_init); -module_exit(nft_hash_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 7f3a9a211034..9873d734b494 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -381,7 +381,7 @@ static void nft_rbtree_gc(struct work_struct *work) gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); if (!gcb) - goto out; + break; atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); @@ -390,10 +390,12 @@ static void nft_rbtree_gc(struct work_struct *work) rbe = rb_entry(prev, struct nft_rbtree_elem, node); atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); + prev = NULL; } node = rb_next(node); + if (!node) + break; } -out: if (gcb) { for (i = 0; i < gcb->head.cnt; i++) { rbe = gcb->elems[i]; @@ -440,6 +442,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) struct rb_node *node; cancel_delayed_work_sync(&priv->gc_work); + rcu_barrier(); while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); @@ -462,7 +465,7 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_rbtree_type __read_mostly = { +struct nft_set_type nft_set_rbtree_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { @@ -481,20 +484,3 @@ static struct nft_set_type nft_rbtree_type __read_mostly = { .get = nft_rbtree_get, }, }; - -static int __init nft_rbtree_module_init(void) -{ - return nft_register_set(&nft_rbtree_type); -} - -static void __exit nft_rbtree_module_exit(void) -{ - nft_unregister_set(&nft_rbtree_type); -} - -module_init(nft_rbtree_module_init); -module_exit(nft_rbtree_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 58fce4e749a9..d76550a8b642 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -61,7 +61,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ - sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, + sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, iph->daddr, hp->source, hp->dest, skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED); @@ -77,7 +77,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, else if (!sk) /* no, there's no established connection, check if * there's a listener on the redirected addr/port */ - sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, + sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, laddr, hp->source, lport, skb->dev, NF_TPROXY_LOOKUP_LISTENER); @@ -150,7 +150,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ - sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto, + sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto, &iph->saddr, &iph->daddr, hp->source, hp->dest, xt_in(par), NF_TPROXY_LOOKUP_ESTABLISHED); @@ -171,7 +171,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) else if (!sk) /* no there's no established connection, check if * there's a listener on the redirected addr/port */ - sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, + sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto, &iph->saddr, laddr, hp->source, lport, xt_in(par), NF_TPROXY_LOOKUP_LISTENER); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 393573a99a5a..56704d95f82d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -63,6 +63,7 @@ #include <linux/hash.h> #include <linux/genetlink.h> #include <linux/net_namespace.h> +#include <linux/nospec.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -679,6 +680,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, if (protocol < 0 || protocol >= MAX_LINKS) return -EPROTONOSUPPORT; + protocol = array_index_nospec(protocol, MAX_LINKS); netlink_lock_table(); #ifdef CONFIG_MODULES @@ -1009,6 +1011,11 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } + if (nlk->ngroups == 0) + groups = 0; + else if (nlk->ngroups < 8*sizeof(groups)) + groups &= (1UL << nlk->ngroups) - 1; + bound = nlk->bound; if (bound) { /* Ensure nlk->portid is up-to-date. */ diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 2ceefa183cee..6a196e438b6c 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -752,11 +752,14 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); - pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT, + pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, 0, frag_len + LLCP_HEADER_SIZE, &err); if (pdu == NULL) { - pr_err("Could not allocate PDU\n"); - continue; + pr_err("Could not allocate PDU (error=%d)\n", err); + len -= remaining_len; + if (len == 0) + len = err; + break; } pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI); diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 9696ef96b719..1a30e165eeb4 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -104,7 +104,7 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, __skb_pull(skb, nsh_len); skb_reset_mac_header(skb); - skb_reset_mac_len(skb); + skb->mac_len = proto == htons(ETH_P_TEB) ? ETH_HLEN : 0; skb->protocol = proto; features &= NETIF_F_SG; diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index b891a91577f8..c038e021a591 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -211,6 +211,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) if (!meter) return ERR_PTR(-ENOMEM); + meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]); meter->used = div_u64(ktime_get_ns(), 1000 * 1000); meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0; meter->keep_stats = !a[OVS_METER_ATTR_CLEAR]; @@ -280,6 +281,10 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) u32 meter_id; bool failed; + if (!a[OVS_METER_ATTR_ID]) { + return -ENODEV; + } + meter = dp_meter_create(a); if (IS_ERR_OR_NULL(meter)) return PTR_ERR(meter); @@ -298,11 +303,6 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_unlock; } - if (!a[OVS_METER_ATTR_ID]) { - err = -ENODEV; - goto exit_unlock; - } - meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); /* Cannot fail after this. */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 57634bc3da74..e6445d8f3f57 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2878,6 +2878,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); + if (len < reserve) + skb_reset_network_header(skb); } /* Returns -EFAULT on error */ @@ -4224,6 +4226,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } if (req->tp_block_nr) { + unsigned int min_frame_size; + /* Sanity tests and some calculations */ err = -EBUSY; if (unlikely(rb->pg_vec)) @@ -4246,12 +4250,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; + min_frame_size = po->tp_hdrlen + po->tp_reserve; if (po->tp_version >= TPACKET_V3 && - req->tp_block_size <= - BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + sizeof(struct tpacket3_hdr)) + req->tp_block_size < + BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size) goto out; - if (unlikely(req->tp_frame_size < po->tp_hdrlen + - po->tp_reserve)) + if (unlikely(req->tp_frame_size < min_frame_size)) goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 2aa07b547b16..86e1e37eb4e8 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -191,8 +191,13 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->type = cpu_to_le32(type); hdr->src_node_id = cpu_to_le32(from->sq_node); hdr->src_port_id = cpu_to_le32(from->sq_port); - hdr->dst_node_id = cpu_to_le32(to->sq_node); - hdr->dst_port_id = cpu_to_le32(to->sq_port); + if (to->sq_port == QRTR_PORT_CTRL) { + hdr->dst_node_id = cpu_to_le32(node->nid); + hdr->dst_port_id = cpu_to_le32(QRTR_NODE_BCAST); + } else { + hdr->dst_node_id = cpu_to_le32(to->sq_node); + hdr->dst_port_id = cpu_to_le32(to->sq_port); + } hdr->size = cpu_to_le32(len); hdr->confirm_rx = 0; @@ -764,6 +769,10 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) node = NULL; if (addr->sq_node == QRTR_NODE_BCAST) { enqueue_fn = qrtr_bcast_enqueue; + if (addr->sq_port != QRTR_PORT_CTRL) { + release_sock(sk); + return -ENOTCONN; + } } else if (addr->sq_node == ipc->us.sq_node) { enqueue_fn = qrtr_local_enqueue; } else { diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 48332a6ed738..d152e48ea371 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -344,6 +344,11 @@ struct rds_ib_mr *rds_ib_reg_frmr(struct rds_ib_device *rds_ibdev, struct rds_ib_frmr *frmr; int ret; + if (!ic) { + /* TODO: Add FRWR support for RDS_GET_MR using proxy qp*/ + return ERR_PTR(-EOPNOTSUPP); + } + do { if (ibmr) rds_ib_free_frmr(ibmr, true); diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 0ea4ab017a8c..655f01d427fe 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -115,7 +115,8 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_connection *iinfo); void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *); void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, - struct rds_sock *rs, u32 *key_ret); + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn); void rds_ib_sync_mr(void *trans_private, int dir); void rds_ib_free_mr(void *trans_private, int invalidate); void rds_ib_flush_mrs(void); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index e678699268a2..2e49a40a5e11 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -537,11 +537,12 @@ void rds_ib_flush_mrs(void) } void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, - struct rds_sock *rs, u32 *key_ret) + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn) { struct rds_ib_device *rds_ibdev; struct rds_ib_mr *ibmr = NULL; - struct rds_ib_connection *ic = rs->rs_conn->c_transport_data; + struct rds_ib_connection *ic = NULL; int ret; rds_ibdev = rds_ib_get_device(rs->rs_bound_addr); @@ -550,6 +551,9 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, goto out; } + if (conn) + ic = conn->c_transport_data; + if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) { ret = -ENODEV; goto out; @@ -559,17 +563,18 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, ibmr = rds_ib_reg_frmr(rds_ibdev, ic, sg, nents, key_ret); else ibmr = rds_ib_reg_fmr(rds_ibdev, sg, nents, key_ret); - if (ibmr) - rds_ibdev = NULL; - - out: - if (!ibmr) + if (IS_ERR(ibmr)) { + ret = PTR_ERR(ibmr); pr_warn("RDS/IB: rds_ib_get_mr failed (errno=%d)\n", ret); + } else { + return ibmr; + } + out: if (rds_ibdev) rds_ib_dev_put(rds_ibdev); - return ibmr; + return ERR_PTR(ret); } void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool) diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 634cfcb7bba6..80920e47f2c7 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -170,7 +170,8 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, } static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, - u64 *cookie_ret, struct rds_mr **mr_ret) + u64 *cookie_ret, struct rds_mr **mr_ret, + struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; unsigned int nr_pages; @@ -269,7 +270,8 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ trans_private = rs->rs_transport->get_mr(sg, nents, rs, - &mr->r_key); + &mr->r_key, + cp ? cp->cp_conn : NULL); if (IS_ERR(trans_private)) { for (i = 0 ; i < nents; i++) @@ -330,7 +332,7 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen) sizeof(struct rds_get_mr_args))) return -EFAULT; - return __rds_rdma_map(rs, &args, NULL, NULL); + return __rds_rdma_map(rs, &args, NULL, NULL, NULL); } int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen) @@ -354,7 +356,7 @@ int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen) new_args.cookie_addr = args.cookie_addr; new_args.flags = args.flags; - return __rds_rdma_map(rs, &new_args, NULL, NULL); + return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL); } /* @@ -782,7 +784,8 @@ int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, rm->m_rdma_cookie != 0) return -EINVAL; - return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr); + return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, + &rm->rdma.op_rdma_mr, rm->m_conn_path); } /* diff --git a/net/rds/rds.h b/net/rds/rds.h index f2272fb8cd45..60b3b787fbdb 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -464,6 +464,8 @@ struct rds_message { struct scatterlist *op_sg; } data; }; + + struct rds_conn_path *m_conn_path; }; /* @@ -544,7 +546,8 @@ struct rds_transport { unsigned int avail); void (*exit)(void); void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg, - struct rds_sock *rs, u32 *key_ret); + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn); void (*sync_mr)(void *trans_private, int direction); void (*free_mr)(void *trans_private, int invalidate); void (*flush_mrs)(void); diff --git a/net/rds/send.c b/net/rds/send.c index 94c7f74909be..59f17a2335f4 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1169,6 +1169,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) rs->rs_conn = conn; } + if (conn->c_trans->t_mp_capable) + cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)]; + else + cpath = &conn->c_path[0]; + + rm->m_conn_path = cpath; + /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr); if (ret) { @@ -1192,11 +1199,6 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } - if (conn->c_trans->t_mp_capable) - cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)]; - else - cpath = &conn->c_path[0]; - if (rds_destroy_pending(conn)) { ret = -EAGAIN; goto out; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5fb7d3254d9e..707630ab4713 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -104,9 +104,9 @@ struct rxrpc_net { #define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */ u8 peer_keepalive_cursor; - ktime_t peer_keepalive_base; - struct hlist_head peer_keepalive[RXRPC_KEEPALIVE_TIME + 1]; - struct hlist_head peer_keepalive_new; + time64_t peer_keepalive_base; + struct list_head peer_keepalive[32]; + struct list_head peer_keepalive_new; struct timer_list peer_keepalive_timer; struct work_struct peer_keepalive_work; }; @@ -295,7 +295,7 @@ struct rxrpc_peer { struct hlist_head error_targets; /* targets for net error distribution */ struct work_struct error_distributor; struct rb_root service_conns; /* Service connections */ - struct hlist_node keepalive_link; /* Link in net->peer_keepalive[] */ + struct list_head keepalive_link; /* Link in net->peer_keepalive[] */ time64_t last_tx_at; /* Last time packet sent here */ seqlock_t service_conn_lock; spinlock_t lock; /* access lock */ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index a9a9be5519b9..9d1e298b784c 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -116,9 +116,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, while (*pp) { parent = *pp; xcall = rb_entry(parent, struct rxrpc_call, sock_node); - if (user_call_ID < call->user_call_ID) + if (user_call_ID < xcall->user_call_ID) pp = &(*pp)->rb_left; - else if (user_call_ID > call->user_call_ID) + else if (user_call_ID > xcall->user_call_ID) pp = &(*pp)->rb_right; else goto id_in_use; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f6734d8cb01a..9486293fef5c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -415,7 +415,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, bool rxrpc_queue_call(struct rxrpc_call *call) { const void *here = __builtin_return_address(0); - int n = __atomic_add_unless(&call->usage, 1, 0); + int n = atomic_fetch_add_unless(&call->usage, 1, 0); if (n == 0) return false; if (rxrpc_queue_work(&call->processor)) diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 8229a52c2acd..3fde001fcc39 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -136,7 +136,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, } ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(conn->debug_id, serial, ret, rxrpc_tx_fail_call_final_resend); @@ -245,7 +245,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, return -EAGAIN; } - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); _leave(" = 0"); return 0; diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 4c77a78a252a..77440a356b14 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -266,7 +266,7 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn) bool rxrpc_queue_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); - int n = __atomic_add_unless(&conn->usage, 1, 0); + int n = atomic_fetch_add_unless(&conn->usage, 1, 0); if (n == 0) return false; if (rxrpc_queue_work(&conn->processor)) @@ -309,7 +309,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn) const void *here = __builtin_return_address(0); if (conn) { - int n = __atomic_add_unless(&conn->usage, 1, 0); + int n = atomic_fetch_add_unless(&conn->usage, 1, 0); if (n > 0) trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here); else diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index b493e6b62740..777c3ed4cfc0 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -305,7 +305,7 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) const void *here = __builtin_return_address(0); if (local) { - int n = __atomic_add_unless(&local->usage, 1, 0); + int n = atomic_fetch_add_unless(&local->usage, 1, 0); if (n > 0) trace_rxrpc_local(local, rxrpc_local_got, n + 1, here); else diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 5d6a773db973..417d80867c4f 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -85,12 +85,12 @@ static __net_init int rxrpc_init_net(struct net *net) hash_init(rxnet->peer_hash); spin_lock_init(&rxnet->peer_hash_lock); for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++) - INIT_HLIST_HEAD(&rxnet->peer_keepalive[i]); - INIT_HLIST_HEAD(&rxnet->peer_keepalive_new); + INIT_LIST_HEAD(&rxnet->peer_keepalive[i]); + INIT_LIST_HEAD(&rxnet->peer_keepalive_new); timer_setup(&rxnet->peer_keepalive_timer, rxrpc_peer_keepalive_timeout, 0); INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker); - rxnet->peer_keepalive_base = ktime_add(ktime_get_real(), NSEC_PER_SEC); + rxnet->peer_keepalive_base = ktime_get_seconds(); ret = -ENOMEM; rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index f03de1c59ba3..4774c8f5634d 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -209,7 +209,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, now = ktime_get_real(); if (ping) call->ping_time = now; - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_fail_call_ack); @@ -296,7 +296,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1, sizeof(pkt)); - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_fail_call_abort); @@ -391,7 +391,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, * message and update the peer record */ ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); up_read(&conn->params.local->defrag_sem); if (ret < 0) @@ -457,7 +457,7 @@ send_fragmentable: if (ret == 0) { ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); opt = IP_PMTUDISC_DO; kernel_setsockopt(conn->params.local->socket, SOL_IP, @@ -475,7 +475,7 @@ send_fragmentable: if (ret == 0) { ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); opt = IPV6_PMTUDISC_DO; kernel_setsockopt(conn->params.local->socket, @@ -599,6 +599,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) trace_rxrpc_tx_fail(peer->debug_id, 0, ret, rxrpc_tx_fail_version_keepalive); - peer->last_tx_at = ktime_get_real(); + peer->last_tx_at = ktime_get_seconds(); _leave(""); } diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 0ed8b651cec2..4f9da2f51c69 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -350,97 +350,117 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, } /* - * Perform keep-alive pings with VERSION packets to keep any NAT alive. + * Perform keep-alive pings. */ -void rxrpc_peer_keepalive_worker(struct work_struct *work) +static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, + struct list_head *collector, + time64_t base, + u8 cursor) { - struct rxrpc_net *rxnet = - container_of(work, struct rxrpc_net, peer_keepalive_work); struct rxrpc_peer *peer; - unsigned long delay; - ktime_t base, now = ktime_get_real(); - s64 diff; - u8 cursor, slot; + const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1; + time64_t keepalive_at; + int slot; - base = rxnet->peer_keepalive_base; - cursor = rxnet->peer_keepalive_cursor; + spin_lock_bh(&rxnet->peer_hash_lock); - _enter("%u,%lld", cursor, ktime_sub(now, base)); + while (!list_empty(collector)) { + peer = list_entry(collector->next, + struct rxrpc_peer, keepalive_link); -next_bucket: - diff = ktime_to_ns(ktime_sub(now, base)); - if (diff < 0) - goto resched; + list_del_init(&peer->keepalive_link); + if (!rxrpc_get_peer_maybe(peer)) + continue; - _debug("at %u", cursor); - spin_lock_bh(&rxnet->peer_hash_lock); -next_peer: - if (!rxnet->live) { spin_unlock_bh(&rxnet->peer_hash_lock); - goto out; - } - /* Everything in the bucket at the cursor is processed this second; the - * bucket at cursor + 1 goes now + 1s and so on... - */ - if (hlist_empty(&rxnet->peer_keepalive[cursor])) { - if (hlist_empty(&rxnet->peer_keepalive_new)) { - spin_unlock_bh(&rxnet->peer_hash_lock); - goto emptied_bucket; + keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; + slot = keepalive_at - base; + _debug("%02x peer %u t=%d {%pISp}", + cursor, peer->debug_id, slot, &peer->srx.transport); + + if (keepalive_at <= base || + keepalive_at > base + RXRPC_KEEPALIVE_TIME) { + rxrpc_send_keepalive(peer); + slot = RXRPC_KEEPALIVE_TIME; } - hlist_move_list(&rxnet->peer_keepalive_new, - &rxnet->peer_keepalive[cursor]); + /* A transmission to this peer occurred since last we examined + * it so put it into the appropriate future bucket. + */ + slot += cursor; + slot &= mask; + spin_lock_bh(&rxnet->peer_hash_lock); + list_add_tail(&peer->keepalive_link, + &rxnet->peer_keepalive[slot & mask]); + rxrpc_put_peer(peer); } - peer = hlist_entry(rxnet->peer_keepalive[cursor].first, - struct rxrpc_peer, keepalive_link); - hlist_del_init(&peer->keepalive_link); - if (!rxrpc_get_peer_maybe(peer)) - goto next_peer; - spin_unlock_bh(&rxnet->peer_hash_lock); +} - _debug("peer %u {%pISp}", peer->debug_id, &peer->srx.transport); +/* + * Perform keep-alive pings with VERSION packets to keep any NAT alive. + */ +void rxrpc_peer_keepalive_worker(struct work_struct *work) +{ + struct rxrpc_net *rxnet = + container_of(work, struct rxrpc_net, peer_keepalive_work); + const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1; + time64_t base, now, delay; + u8 cursor, stop; + LIST_HEAD(collector); -recalc: - diff = ktime_divns(ktime_sub(peer->last_tx_at, base), NSEC_PER_SEC); - if (diff < -30 || diff > 30) - goto send; /* LSW of 64-bit time probably wrapped on 32-bit */ - diff += RXRPC_KEEPALIVE_TIME - 1; - if (diff < 0) - goto send; + now = ktime_get_seconds(); + base = rxnet->peer_keepalive_base; + cursor = rxnet->peer_keepalive_cursor; + _enter("%lld,%u", base - now, cursor); - slot = (diff > RXRPC_KEEPALIVE_TIME - 1) ? RXRPC_KEEPALIVE_TIME - 1 : diff; - if (slot == 0) - goto send; + if (!rxnet->live) + return; - /* A transmission to this peer occurred since last we examined it so - * put it into the appropriate future bucket. + /* Remove to a temporary list all the peers that are currently lodged + * in expired buckets plus all new peers. + * + * Everything in the bucket at the cursor is processed this + * second; the bucket at cursor + 1 goes at now + 1s and so + * on... */ - slot = (slot + cursor) % ARRAY_SIZE(rxnet->peer_keepalive); spin_lock_bh(&rxnet->peer_hash_lock); - hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive[slot]); - rxrpc_put_peer(peer); - goto next_peer; - -send: - rxrpc_send_keepalive(peer); - now = ktime_get_real(); - goto recalc; + list_splice_init(&rxnet->peer_keepalive_new, &collector); + + stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive); + while (base <= now && (s8)(cursor - stop) < 0) { + list_splice_tail_init(&rxnet->peer_keepalive[cursor & mask], + &collector); + base++; + cursor++; + } -emptied_bucket: - cursor++; - if (cursor >= ARRAY_SIZE(rxnet->peer_keepalive)) - cursor = 0; - base = ktime_add_ns(base, NSEC_PER_SEC); - goto next_bucket; + base = now; + spin_unlock_bh(&rxnet->peer_hash_lock); -resched: rxnet->peer_keepalive_base = base; rxnet->peer_keepalive_cursor = cursor; - delay = nsecs_to_jiffies(-diff) + 1; - timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay); -out: + rxrpc_peer_keepalive_dispatch(rxnet, &collector, base, cursor); + ASSERT(list_empty(&collector)); + + /* Schedule the timer for the next occupied timeslot. */ + cursor = rxnet->peer_keepalive_cursor; + stop = cursor + RXRPC_KEEPALIVE_TIME - 1; + for (; (s8)(cursor - stop) < 0; cursor++) { + if (!list_empty(&rxnet->peer_keepalive[cursor & mask])) + break; + base++; + } + + now = ktime_get_seconds(); + delay = base - now; + if (delay < 1) + delay = 1; + delay *= HZ; + if (rxnet->live) + timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay); + _leave(""); } diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 1b7e8107b3ae..1dc7648e3eff 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -322,7 +322,7 @@ struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local, if (!peer) { peer = prealloc; hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); - hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive_new); + list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); } spin_unlock(&rxnet->peer_hash_lock); @@ -367,8 +367,8 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, if (!peer) { hash_add_rcu(rxnet->peer_hash, &candidate->hash_link, hash_key); - hlist_add_head(&candidate->keepalive_link, - &rxnet->peer_keepalive_new); + list_add_tail(&candidate->keepalive_link, + &rxnet->peer_keepalive_new); } spin_unlock_bh(&rxnet->peer_hash_lock); @@ -406,7 +406,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) const void *here = __builtin_return_address(0); if (peer) { - int n = __atomic_add_unless(&peer->usage, 1, 0); + int n = atomic_fetch_add_unless(&peer->usage, 1, 0); if (n > 0) trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here); else @@ -441,7 +441,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) spin_lock_bh(&rxnet->peer_hash_lock); hash_del_rcu(&peer->hash_link); - hlist_del_init(&peer->keepalive_link); + list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); kfree_rcu(peer, rcu); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 278ac0807a60..47cb019c521a 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -669,7 +669,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) return -EAGAIN; } - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); _leave(" = 0"); return 0; } @@ -725,7 +725,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn, return -EAGAIN; } - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); _leave(" = 0"); return 0; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 526a8e491626..6e7124e57918 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -91,7 +91,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, } params_old = rtnl_dereference(p->params); - params_new->action = parm->action; + p->tcf_action = parm->action; params_new->update_flags = parm->update_flags; rcu_assign_pointer(p->params, params_new); if (params_old) @@ -561,7 +561,7 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&p->tcf_tm); bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb); - action = params->action; + action = READ_ONCE(p->tcf_action); if (unlikely(action == TC_ACT_SHOT)) goto drop_stats; @@ -599,11 +599,11 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, .index = p->tcf_index, .refcnt = p->tcf_refcnt - ref, .bindcnt = p->tcf_bindcnt - bind, + .action = p->tcf_action, }; struct tcf_t t; params = rtnl_dereference(p->params); - opt.action = params->action; opt.update_flags = params->update_flags; if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt)) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 626dac81a48a..9bc6c2ae98a5 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -36,7 +36,7 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&t->tcf_tm); bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb); - action = params->action; + action = READ_ONCE(t->tcf_action); switch (params->tcft_action) { case TCA_TUNNEL_KEY_ACT_RELEASE: @@ -182,7 +182,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, params_old = rtnl_dereference(t->params); - params_new->action = parm->action; + t->tcf_action = parm->action; params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; @@ -254,13 +254,13 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, .index = t->tcf_index, .refcnt = t->tcf_refcnt - ref, .bindcnt = t->tcf_bindcnt - bind, + .action = t->tcf_action, }; struct tcf_t tm; params = rtnl_dereference(t->params); opt.t_action = params->tcft_action; - opt.action = params->action; if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index cdc3c87c53e6..f74513a7c7a8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1053,7 +1053,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, for (tp = rtnl_dereference(chain->filter_chain); tp; tp = rtnl_dereference(tp->next)) tfilter_notify(net, oskb, n, tp, block, - q, parent, 0, event, false); + q, parent, NULL, event, false); } static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1444,7 +1444,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, block, q, parent, 0, + if (tcf_fill_node(net, skb, tp, block, q, parent, NULL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index cd2e0e342fb6..6c0a9d5dbf94 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -479,24 +479,28 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, q->cparams.mtu = psched_mtu(qdisc_dev(sch)); if (opt) { - int err = fq_codel_change(sch, opt, extack); + err = fq_codel_change(sch, opt, extack); if (err) - return err; + goto init_failure; } err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) - return err; + goto init_failure; if (!q->flows) { q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_codel_flow), GFP_KERNEL); - if (!q->flows) - return -ENOMEM; + if (!q->flows) { + err = -ENOMEM; + goto init_failure; + } q->backlogs = kvcalloc(q->flows_cnt, sizeof(u32), GFP_KERNEL); - if (!q->backlogs) - return -ENOMEM; + if (!q->backlogs) { + err = -ENOMEM; + goto alloc_failure; + } for (i = 0; i < q->flows_cnt; i++) { struct fq_codel_flow *flow = q->flows + i; @@ -509,6 +513,13 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; + +alloc_failure: + kvfree(q->flows); + q->flows = NULL; +init_failure: + q->flows_cnt = 0; + return err; } static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 445b7ef61677..12cac85da994 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -282,7 +282,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) if (dst) { /* Re-fetch, as under layers may have a higher minimum size */ - pmtu = SCTP_TRUNC4(dst_mtu(dst)); + pmtu = sctp_dst_mtu(dst); change = t->pathmtu != pmtu; } t->pathmtu = pmtu; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 3c1405df936c..e7de5f282722 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -147,7 +147,8 @@ static int smc_release(struct socket *sock) smc->clcsock = NULL; } if (smc->use_fallback) { - sock_put(sk); /* passive closing */ + if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) + sock_put(sk); /* passive closing */ sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); } @@ -417,12 +418,18 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) { int rc; - if (reason_code < 0) /* error, fallback is not possible */ + if (reason_code < 0) { /* error, fallback is not possible */ + if (smc->sk.sk_state == SMC_INIT) + sock_put(&smc->sk); /* passive closing */ return reason_code; + } if (reason_code != SMC_CLC_DECL_REPLY) { rc = smc_clc_send_decline(smc, reason_code); - if (rc < 0) + if (rc < 0) { + if (smc->sk.sk_state == SMC_INIT) + sock_put(&smc->sk); /* passive closing */ return rc; + } } return smc_connect_fallback(smc); } @@ -435,8 +442,6 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code, smc_lgr_forget(smc->conn.lgr); mutex_unlock(&smc_create_lgr_pending); smc_conn_free(&smc->conn); - if (reason_code < 0 && smc->sk.sk_state == SMC_INIT) - sock_put(&smc->sk); /* passive closing */ return reason_code; } @@ -1117,6 +1122,8 @@ static void smc_tcp_listen_work(struct work_struct *work) sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); + new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf; + new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf; sock_hold(&new_smc->sk); /* sock_put in passive closing */ if (!schedule_work(&new_smc->smc_listen_work)) sock_put(&new_smc->sk); @@ -1392,8 +1399,7 @@ static int smc_shutdown(struct socket *sock, int how) lock_sock(sk); rc = -ENOTCONN; - if ((sk->sk_state != SMC_LISTEN) && - (sk->sk_state != SMC_ACTIVE) && + if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_PEERCLOSEWAIT1) && (sk->sk_state != SMC_PEERCLOSEWAIT2) && (sk->sk_state != SMC_APPCLOSEWAIT1) && @@ -1452,7 +1458,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (optlen < sizeof(int)) return -EINVAL; - get_user(val, (int __user *)optval); + if (get_user(val, (int __user *)optval)) + return -EFAULT; lock_sock(sk); switch (optname) { @@ -1515,15 +1522,22 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, smc = smc_sk(sock->sk); conn = &smc->conn; + lock_sock(&smc->sk); if (smc->use_fallback) { - if (!smc->clcsock) + if (!smc->clcsock) { + release_sock(&smc->sk); return -EBADF; - return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg); + } + answ = smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg); + release_sock(&smc->sk); + return answ; } switch (cmd) { case SIOCINQ: /* same as FIONREAD */ - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; @@ -1532,8 +1546,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, break; case SIOCOUTQ: /* output queue size (not send + not acked) */ - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; @@ -1543,8 +1559,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, break; case SIOCOUTQNSD: /* output queue size (not send only) */ - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; @@ -1552,8 +1570,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, answ = smc_tx_prepared_sends(&smc->conn); break; case SIOCATMARK: - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) { answ = 0; @@ -1569,8 +1589,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, } break; default: + release_sock(&smc->sk); return -ENOIOCTLCMD; } + release_sock(&smc->sk); return put_user(answ, (int __user *)arg); } diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index a7e8d63fc8ae..9bde1e4ca288 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -233,7 +233,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, /* force immediate tx of current consumer cursor, but * under send_lock to guarantee arrival in seqno-order */ - smc_tx_sndbuf_nonempty(conn); + if (smc->sk.sk_state != SMC_INIT) + smc_tx_sndbuf_nonempty(conn); } } diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 717449b1da0b..ae5d168653ce 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -250,6 +250,7 @@ out: int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, u8 expected_type) { + long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo; struct sock *clc_sk = smc->clcsock->sk; struct smc_clc_msg_hdr *clcm = buf; struct msghdr msg = {NULL, 0}; @@ -306,7 +307,6 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, memset(&msg, 0, sizeof(struct msghdr)); iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen); krflags = MSG_WAITALL; - smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME; len = sock_recvmsg(smc->clcsock, &msg, krflags); if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) { smc->sk.sk_err = EPROTO; @@ -322,6 +322,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, } out: + smc->clcsock->sk->sk_rcvtimeo = rcvtimeo; return reason_code; } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index fa41d9881741..ac961dfb1ea1 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -107,6 +107,8 @@ static void smc_close_active_abort(struct smc_sock *smc) } switch (sk->sk_state) { case SMC_INIT: + sk->sk_state = SMC_PEERABORTWAIT; + break; case SMC_ACTIVE: sk->sk_state = SMC_PEERABORTWAIT; release_sock(sk); diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index cee666400752..f82886b7d1d8 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -495,7 +495,8 @@ out: void smc_tx_consumer_update(struct smc_connection *conn, bool force) { - union smc_host_cursor cfed, cons; + union smc_host_cursor cfed, cons, prod; + int sender_free = conn->rmb_desc->len; int to_confirm; smc_curs_write(&cons, @@ -505,11 +506,18 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) smc_curs_read(&conn->rx_curs_confirmed, conn), conn); to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons); + if (to_confirm > conn->rmbe_update_limit) { + smc_curs_write(&prod, + smc_curs_read(&conn->local_rx_ctrl.prod, conn), + conn); + sender_free = conn->rmb_desc->len - + smc_curs_diff(conn->rmb_desc->len, &prod, &cfed); + } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || force || ((to_confirm > conn->rmbe_update_limit) && - ((to_confirm > (conn->rmb_desc->len / 2)) || + ((sender_free <= (conn->rmb_desc->len / 2)) || conn->local_rx_ctrl.prod_flags.write_blocked))) { if ((smc_cdc_get_slot_and_msg_send(conn) < 0) && conn->alert_token_local) { /* connection healthy */ diff --git a/net/socket.c b/net/socket.c index 85633622c94d..8c24d5dc4bc8 100644 --- a/net/socket.c +++ b/net/socket.c @@ -89,6 +89,7 @@ #include <linux/magic.h> #include <linux/slab.h> #include <linux/xattr.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -2522,6 +2523,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) if (call < 1 || call > SYS_SENDMMSG) return -EINVAL; + call = array_index_nospec(call, SYS_SENDMMSG + 1); len = nargs[call]; if (len > sizeof(a)) @@ -2688,7 +2690,8 @@ EXPORT_SYMBOL(sock_unregister); bool sock_is_registered(int family) { - return family < NPROTO && rcu_access_pointer(net_families[family]); + return family < NPROTO && + rcu_access_pointer(net_families[array_index_nospec(family, NPROTO)]); } static int __init sock_init(void) diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 9f666e0650e2..2830709957bd 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -133,6 +133,8 @@ static void disc_dupl_alert(struct tipc_bearer *b, u32 node_addr, } /* tipc_disc_addr_trial(): - handle an address uniqueness trial from peer + * Returns true if message should be dropped by caller, i.e., if it is a + * trial message or we are inside trial period. Otherwise false. */ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, struct tipc_media_addr *maddr, @@ -168,8 +170,9 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); } + /* Accept regular link requests/responses only after trial period */ if (mtyp != DSC_TRIAL_MSG) - return false; + return trial; sugg_addr = tipc_node_try_addr(net, peer_id, src); if (sugg_addr) @@ -284,7 +287,6 @@ static void tipc_disc_timeout(struct timer_list *t) { struct tipc_discoverer *d = from_timer(d, t, timer); struct tipc_net *tn = tipc_net(d->net); - u32 self = tipc_own_addr(d->net); struct tipc_media_addr maddr; struct sk_buff *skb = NULL; struct net *net = d->net; @@ -298,12 +300,14 @@ static void tipc_disc_timeout(struct timer_list *t) goto exit; } - /* Did we just leave the address trial period ? */ - if (!self && !time_before(jiffies, tn->addr_trial_end)) { - self = tn->trial_addr; - tipc_net_finalize(net, self); - msg_set_prevnode(buf_msg(d->skb), self); + /* Trial period over ? */ + if (!time_before(jiffies, tn->addr_trial_end)) { + /* Did we just leave it ? */ + if (!tipc_own_addr(net)) + tipc_net_finalize(net, tn->trial_addr); + msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); + msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net)); } /* Adjust timeout interval according to discovery phase */ diff --git a/net/tipc/net.c b/net/tipc/net.c index 4fbaa0464405..62199cf5a56c 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -121,12 +121,15 @@ int tipc_net_init(struct net *net, u8 *node_id, u32 addr) void tipc_net_finalize(struct net *net, u32 addr) { - tipc_set_node_addr(net, addr); - smp_mb(); - tipc_named_reinit(net); - tipc_sk_reinit(net); - tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, - TIPC_CLUSTER_SCOPE, 0, addr); + struct tipc_net *tn = tipc_net(net); + + if (!cmpxchg(&tn->node_addr, 0, addr)) { + tipc_set_node_addr(net, addr); + tipc_named_reinit(net); + tipc_sk_reinit(net); + tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, + TIPC_CLUSTER_SCOPE, 0, addr); + } } void tipc_net_stop(struct net *net) diff --git a/net/tipc/node.c b/net/tipc/node.c index 6a44eb812baf..0453bd451ce8 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -797,6 +797,7 @@ static u32 tipc_node_suggest_addr(struct net *net, u32 addr) } /* tipc_node_try_addr(): Check if addr can be used by peer, suggest other if not + * Returns suggested address if any, otherwise 0 */ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr) { @@ -819,12 +820,14 @@ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr) if (n) { addr = n->addr; tipc_node_put(n); + return addr; } - /* Even this node may be in trial phase */ + + /* Even this node may be in conflict */ if (tn->trial_addr == addr) return tipc_node_suggest_addr(net, addr); - return addr; + return 0; } void tipc_node_check_dest(struct net *net, u32 addr, diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d2380548f8f6..1f3d9789af30 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -440,7 +440,7 @@ alloc_encrypted: ret = tls_push_record(sk, msg->msg_flags, record_type); if (!ret) continue; - if (ret == -EAGAIN) + if (ret < 0) goto send_end; copied -= try_to_copy; @@ -646,6 +646,9 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, return NULL; } + if (sk->sk_shutdown & RCV_SHUTDOWN) + return NULL; + if (sock_flag(sk, SOCK_DONE)) return NULL; @@ -701,6 +704,10 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, nsg = skb_to_sgvec(skb, &sgin[1], rxm->offset + tls_ctx->rx.prepend_size, rxm->full_len - tls_ctx->rx.prepend_size); + if (nsg < 0) { + ret = nsg; + goto out; + } tls_make_aad(ctx->rx_aad_ciphertext, rxm->full_len - tls_ctx->rx.overhead_size, @@ -712,6 +719,7 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, rxm->full_len - tls_ctx->rx.overhead_size, skb, sk->sk_allocation); +out: if (sgin != &sgin_arr[0]) kfree(sgin); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index c1076c19b858..ab27a2872935 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -451,14 +451,14 @@ static int vsock_send_shutdown(struct sock *sk, int mode) return transport->shutdown(vsock_sk(sk), mode); } -void vsock_pending_work(struct work_struct *work) +static void vsock_pending_work(struct work_struct *work) { struct sock *sk; struct sock *listener; struct vsock_sock *vsk; bool cleanup; - vsk = container_of(work, struct vsock_sock, dwork.work); + vsk = container_of(work, struct vsock_sock, pending_work.work); sk = sk_vsock(vsk); listener = vsk->listener; cleanup = true; @@ -498,7 +498,6 @@ out: sock_put(sk); sock_put(listener); } -EXPORT_SYMBOL_GPL(vsock_pending_work); /**** SOCKET OPERATIONS ****/ @@ -597,6 +596,8 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) return retval; } +static void vsock_connect_timeout(struct work_struct *work); + struct sock *__vsock_create(struct net *net, struct socket *sock, struct sock *parent, @@ -638,6 +639,8 @@ struct sock *__vsock_create(struct net *net, vsk->sent_request = false; vsk->ignore_connecting_rst = false; vsk->peer_shutdown = 0; + INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout); + INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work); psk = parent ? vsock_sk(parent) : NULL; if (parent) { @@ -1117,7 +1120,7 @@ static void vsock_connect_timeout(struct work_struct *work) struct vsock_sock *vsk; int cancel = 0; - vsk = container_of(work, struct vsock_sock, dwork.work); + vsk = container_of(work, struct vsock_sock, connect_work.work); sk = sk_vsock(vsk); lock_sock(sk); @@ -1221,9 +1224,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, * timeout fires. */ sock_hold(sk); - INIT_DELAYED_WORK(&vsk->dwork, - vsock_connect_timeout); - schedule_delayed_work(&vsk->dwork, timeout); + schedule_delayed_work(&vsk->connect_work, timeout); /* Skip ahead to preserve error code set above. */ goto out_wait; diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index a7a73ffe675b..cb332adb84cd 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1094,8 +1094,7 @@ static int vmci_transport_recv_listen(struct sock *sk, vpending->listener = sk; sock_hold(sk); sock_hold(pending); - INIT_DELAYED_WORK(&vpending->dwork, vsock_pending_work); - schedule_delayed_work(&vpending->dwork, HZ); + schedule_delayed_work(&vpending->pending_work, HZ); out: return err; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4eece06be1e7..80bc986c79e5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4409,6 +4409,7 @@ static int parse_station_flags(struct genl_info *info, params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_MFP) | BIT(NL80211_STA_FLAG_AUTHORIZED); + break; default: return -EINVAL; } @@ -14923,20 +14924,24 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, EXPORT_SYMBOL(cfg80211_mgmt_tx_status); static int __nl80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, + struct sk_buff *skb, bool unencrypted, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct ethhdr *ehdr = eth_hdr(skb); + const u8 *addr = ehdr->h_source; + u16 proto = be16_to_cpu(skb->protocol); struct sk_buff *msg; void *hdr; + struct nlattr *frame; + u32 nlportid = READ_ONCE(wdev->conn_owner_nlportid); if (!nlportid) return -ENOENT; - msg = nlmsg_new(100 + len, gfp); + msg = nlmsg_new(100 + skb->len, gfp); if (!msg) return -ENOMEM; @@ -14950,13 +14955,17 @@ static int __nl80211_rx_control_port(struct net_device *dev, nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), NL80211_ATTR_PAD) || - nla_put(msg, NL80211_ATTR_FRAME, len, buf) || nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) || nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) || (unencrypted && nla_put_flag(msg, NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT))) goto nla_put_failure; + frame = nla_reserve(msg, NL80211_ATTR_FRAME, skb->len); + if (!frame) + goto nla_put_failure; + + skb_copy_bits(skb, 0, nla_data(frame), skb->len); genlmsg_end(msg, hdr); return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); @@ -14967,14 +14976,12 @@ static int __nl80211_rx_control_port(struct net_device *dev, } bool cfg80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted) + struct sk_buff *skb, bool unencrypted) { int ret; - trace_cfg80211_rx_control_port(dev, buf, len, addr, proto, unencrypted); - ret = __nl80211_rx_control_port(dev, buf, len, addr, proto, - unencrypted, GFP_ATOMIC); + trace_cfg80211_rx_control_port(dev, skb, unencrypted); + ret = __nl80211_rx_control_port(dev, skb, unencrypted, GFP_ATOMIC); trace_cfg80211_return_bool(ret == 0); return ret == 0; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index bbe6298e4bb9..4fc66a117b7d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2240,7 +2240,9 @@ static void wiphy_update_regulatory(struct wiphy *wiphy, * as some drivers used this to restore its orig_* reg domain. */ if (initiator == NL80211_REGDOM_SET_BY_CORE && - wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) + wiphy->regulatory_flags & REGULATORY_CUSTOM_REG && + !(wiphy->regulatory_flags & + REGULATORY_WIPHY_SELF_MANAGED)) reg_call_notifier(wiphy, lr); return; } @@ -2787,26 +2789,6 @@ static void notify_self_managed_wiphys(struct regulatory_request *request) } } -static bool reg_only_self_managed_wiphys(void) -{ - struct cfg80211_registered_device *rdev; - struct wiphy *wiphy; - bool self_managed_found = false; - - ASSERT_RTNL(); - - list_for_each_entry(rdev, &cfg80211_rdev_list, list) { - wiphy = &rdev->wiphy; - if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) - self_managed_found = true; - else - return false; - } - - /* make sure at least one self-managed wiphy exists */ - return self_managed_found; -} - /* * Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_* * Regulatory hints come on a first come first serve basis and we @@ -2839,10 +2821,6 @@ static void reg_process_pending_hints(void) spin_unlock(®_requests_lock); notify_self_managed_wiphys(reg_request); - if (reg_only_self_managed_wiphys()) { - reg_free_request(reg_request); - return; - } reg_process_hint(reg_request); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 2b417a2fe63f..7c73510b161f 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2627,23 +2627,25 @@ TRACE_EVENT(cfg80211_mgmt_tx_status, ); TRACE_EVENT(cfg80211_rx_control_port, - TP_PROTO(struct net_device *netdev, const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted), - TP_ARGS(netdev, buf, len, addr, proto, unencrypted), + TP_PROTO(struct net_device *netdev, struct sk_buff *skb, + bool unencrypted), + TP_ARGS(netdev, skb, unencrypted), TP_STRUCT__entry( NETDEV_ENTRY - MAC_ENTRY(addr) + __field(int, len) + MAC_ENTRY(from) __field(u16, proto) __field(bool, unencrypted) ), TP_fast_assign( NETDEV_ASSIGN; - MAC_ASSIGN(addr, addr); - __entry->proto = proto; + __entry->len = skb->len; + MAC_ASSIGN(from, eth_hdr(skb)->h_source); + __entry->proto = be16_to_cpu(skb->protocol); __entry->unencrypted = unencrypted; ), - TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT " proto: 0x%x, unencrypted: %s", - NETDEV_PR_ARG, MAC_PR_ARG(addr), + TP_printk(NETDEV_PR_FMT ", len=%d, " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s", + NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(from), __entry->proto, BOOL_TO_STR(__entry->unencrypted)) ); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 59fb7d3c36a3..4e937cd7c17d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -84,10 +84,8 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { int err = xskq_produce_batch_desc(xs->rx, (u64)xdp->handle, len); - if (err) { - xdp_return_buff(xdp); + if (err) xs->rx_dropped++; - } return err; } @@ -199,8 +197,11 @@ static void xsk_destruct_skb(struct sk_buff *skb) { u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg; struct xdp_sock *xs = xdp_sk(skb->sk); + unsigned long flags; + spin_lock_irqsave(&xs->tx_completion_lock, flags); WARN_ON_ONCE(xskq_produce_addr(xs->umem->cq, addr)); + spin_unlock_irqrestore(&xs->tx_completion_lock, flags); sock_wfree(skb); } @@ -215,9 +216,6 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, struct sk_buff *skb; int err = 0; - if (unlikely(!xs->tx)) - return -ENOBUFS; - mutex_lock(&xs->mutex); while (xskq_peek_desc(xs->tx, &desc)) { @@ -230,22 +228,13 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, goto out; } - if (xskq_reserve_addr(xs->umem->cq)) { - err = -EAGAIN; + if (xskq_reserve_addr(xs->umem->cq)) goto out; - } - len = desc.len; - if (unlikely(len > xs->dev->mtu)) { - err = -EMSGSIZE; + if (xs->queue_id >= xs->dev->real_num_tx_queues) goto out; - } - - if (xs->queue_id >= xs->dev->real_num_tx_queues) { - err = -ENXIO; - goto out; - } + len = desc.len; skb = sock_alloc_send_skb(sk, len, 1, &err); if (unlikely(!skb)) { err = -EAGAIN; @@ -268,15 +257,15 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, skb->destructor = xsk_destruct_skb; err = dev_direct_xmit(skb, xs->queue_id); + xskq_discard_desc(xs->tx); /* Ignore NET_XMIT_CN as packet might have been sent */ if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) { - err = -EAGAIN; - /* SKB consumed by dev_direct_xmit() */ + /* SKB completed but not sent */ + err = -EBUSY; goto out; } sent_frame = true; - xskq_discard_desc(xs->tx); } out: @@ -297,6 +286,8 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) return -ENXIO; if (unlikely(!(xs->dev->flags & IFF_UP))) return -ENETDOWN; + if (unlikely(!xs->tx)) + return -ENOBUFS; if (need_wait) return -EOPNOTSUPP; @@ -755,6 +746,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, xs = xdp_sk(sk); mutex_init(&xs->mutex); + spin_lock_init(&xs->tx_completion_lock); local_bh_disable(); sock_prot_inuse_add(net, &xsk_proto, 1); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index ef6a6f0ec949..8a64b150be54 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -62,14 +62,9 @@ static inline u32 xskq_nb_avail(struct xsk_queue *q, u32 dcnt) return (entries > dcnt) ? dcnt : entries; } -static inline u32 xskq_nb_free_lazy(struct xsk_queue *q, u32 producer) -{ - return q->nentries - (producer - q->cons_tail); -} - static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt) { - u32 free_entries = xskq_nb_free_lazy(q, producer); + u32 free_entries = q->nentries - (producer - q->cons_tail); if (free_entries >= dcnt) return free_entries; @@ -129,7 +124,7 @@ static inline int xskq_produce_addr(struct xsk_queue *q, u64 addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; - if (xskq_nb_free(q, q->prod_tail, LAZY_UPDATE_THRESHOLD) == 0) + if (xskq_nb_free(q, q->prod_tail, 1) == 0) return -ENOSPC; ring->desc[q->prod_tail++ & q->ring_mask] = addr; @@ -255,7 +250,7 @@ static inline bool xskq_full_desc(struct xsk_queue *q) static inline bool xskq_empty_desc(struct xsk_queue *q) { - return xskq_nb_free(q, q->prod_tail, 1) == q->nentries; + return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries; } void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5f48251c1319..7c5e8978aeaa 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2286,6 +2286,9 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); + if (IS_ERR(dst)) + dst_release(dst_orig); + return dst; } EXPORT_SYMBOL(xfrm_lookup_route); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 080035f056d9..33878e6e0d0a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1025,10 +1025,12 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb, { struct sock *nlsk = rcu_dereference(net->xfrm.nlsk); - if (nlsk) - return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); - else - return -1; + if (!nlsk) { + kfree_skb(skb); + return -EPIPE; + } + + return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); } static inline unsigned int xfrm_spdinfo_msgsize(void) @@ -1671,9 +1673,11 @@ static inline unsigned int userpolicy_type_attrsize(void) #ifdef CONFIG_XFRM_SUB_POLICY static int copy_to_user_policy_type(u8 type, struct sk_buff *skb) { - struct xfrm_userpolicy_type upt = { - .type = type, - }; + struct xfrm_userpolicy_type upt; + + /* Sadly there are two holes in struct xfrm_userpolicy_type */ + memset(&upt, 0, sizeof(upt)); + upt.type = type; return nla_put(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt); } diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore new file mode 100644 index 000000000000..8ae4940025f8 --- /dev/null +++ b/samples/bpf/.gitignore @@ -0,0 +1,49 @@ +cpustat +fds_example +lathist +load_sock_ops +lwt_len_hist +map_perf_test +offwaketime +per_socket_stats_example +sampleip +sock_example +sockex1 +sockex2 +sockex3 +spintest +syscall_nrs.h +syscall_tp +task_fd_query +tc_l2_redirect +test_cgrp2_array_pin +test_cgrp2_attach +test_cgrp2_attach2 +test_cgrp2_sock +test_cgrp2_sock2 +test_current_task_under_cgroup +test_lru_dist +test_map_in_map +test_overhead +test_probe_write_user +trace_event +trace_output +tracex1 +tracex2 +tracex3 +tracex4 +tracex5 +tracex6 +tracex7 +xdp1 +xdp2 +xdp_adjust_tail +xdp_fwd +xdp_monitor +xdp_redirect +xdp_redirect_cpu +xdp_redirect_map +xdp_router_ipv4 +xdp_rxq_info +xdp_tx_iptunnel +xdpsock diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c index 95c16324760c..0b6f22feb2c9 100644 --- a/samples/bpf/parse_varlen.c +++ b/samples/bpf/parse_varlen.c @@ -6,6 +6,7 @@ */ #define KBUILD_MODNAME "foo" #include <linux/if_ether.h> +#include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/in.h> @@ -108,11 +109,6 @@ static int parse_ipv6(void *data, uint64_t nh_off, void *data_end) return 0; } -struct vlan_hdr { - uint16_t h_vlan_TCI; - uint16_t h_vlan_encapsulated_proto; -}; - SEC("varlen") int handle_ingress(struct __sk_buff *skb) { diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c index 6caf47afa635..9d6dcaa9db92 100644 --- a/samples/bpf/test_overhead_user.c +++ b/samples/bpf/test_overhead_user.c @@ -6,6 +6,7 @@ */ #define _GNU_SOURCE #include <sched.h> +#include <errno.h> #include <stdio.h> #include <sys/types.h> #include <asm/unistd.h> @@ -44,8 +45,13 @@ static void test_task_rename(int cpu) exit(1); } start_time = time_get_ns(); - for (i = 0; i < MAX_CNT; i++) - write(fd, buf, sizeof(buf)); + for (i = 0; i < MAX_CNT; i++) { + if (write(fd, buf, sizeof(buf)) < 0) { + printf("task rename failed: %s\n", strerror(errno)); + close(fd); + return; + } + } printf("task_rename:%d: %lld events per sec\n", cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); close(fd); @@ -63,8 +69,13 @@ static void test_urandom_read(int cpu) exit(1); } start_time = time_get_ns(); - for (i = 0; i < MAX_CNT; i++) - read(fd, buf, sizeof(buf)); + for (i = 0; i < MAX_CNT; i++) { + if (read(fd, buf, sizeof(buf)) < 0) { + printf("failed to read from /dev/urandom: %s\n", strerror(errno)); + close(fd); + return; + } + } printf("urandom_read:%d: %lld events per sec\n", cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); close(fd); diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 1fa1becfa641..d08046ab81f0 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -122,6 +122,16 @@ static void print_stacks(void) } } +static inline int generate_load(void) +{ + if (system("dd if=/dev/zero of=/dev/null count=5000k status=none") < 0) { + printf("failed to generate some load with dd: %s\n", strerror(errno)); + return -1; + } + + return 0; +} + static void test_perf_event_all_cpu(struct perf_event_attr *attr) { int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); @@ -142,7 +152,11 @@ static void test_perf_event_all_cpu(struct perf_event_attr *attr) assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0); assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE) == 0); } - system("dd if=/dev/zero of=/dev/null count=5000k status=none"); + + if (generate_load() < 0) { + error = 1; + goto all_cpu_err; + } print_stacks(); all_cpu_err: for (i--; i >= 0; i--) { @@ -156,7 +170,7 @@ all_cpu_err: static void test_perf_event_task(struct perf_event_attr *attr) { - int pmu_fd; + int pmu_fd, error = 0; /* per task perf event, enable inherit so the "dd ..." command can be traced properly. * Enabling inherit will cause bpf_perf_prog_read_time helper failure. @@ -171,10 +185,17 @@ static void test_perf_event_task(struct perf_event_attr *attr) } assert(ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0); assert(ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE) == 0); - system("dd if=/dev/zero of=/dev/null count=5000k status=none"); + + if (generate_load() < 0) { + error = 1; + goto err; + } print_stacks(); +err: ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE); close(pmu_fd); + if (error) + int_exit(0); } static void test_bpf_perf_event(void) diff --git a/samples/bpf/xdp2skb_meta.sh b/samples/bpf/xdp2skb_meta.sh index b9c9549c4c27..4bde9d066c46 100755 --- a/samples/bpf/xdp2skb_meta.sh +++ b/samples/bpf/xdp2skb_meta.sh @@ -16,8 +16,8 @@ BPF_FILE=xdp2skb_meta_kern.o DIR=$(dirname $0) -export TC=/usr/sbin/tc -export IP=/usr/sbin/ip +[ -z "$TC" ] && TC=tc +[ -z "$IP" ] && IP=ip function usage() { echo "" @@ -53,7 +53,7 @@ function _call_cmd() { local allow_fail="$2" shift 2 if [[ -n "$VERBOSE" ]]; then - echo "$(basename $cmd) $@" + echo "$cmd $@" fi if [[ -n "$DRYRUN" ]]; then return diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c index 303e9e7161f3..4938dcbaecbf 100644 --- a/samples/bpf/xdp_redirect_cpu_kern.c +++ b/samples/bpf/xdp_redirect_cpu_kern.c @@ -14,7 +14,7 @@ #include <uapi/linux/bpf.h> #include "bpf_helpers.h" -#define MAX_CPUS 12 /* WARNING - sync with _user.c */ +#define MAX_CPUS 64 /* WARNING - sync with _user.c */ /* Special map type that can XDP_REDIRECT frames to another CPU */ struct bpf_map_def SEC("maps") cpu_map = { diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index f6efaefd485b..4b4d78fffe30 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -19,7 +19,7 @@ static const char *__doc__ = #include <arpa/inet.h> #include <linux/if_link.h> -#define MAX_CPUS 12 /* WARNING - sync with _kern.c */ +#define MAX_CPUS 64 /* WARNING - sync with _kern.c */ /* How many xdp_progs are defined in _kern.c */ #define MAX_PROG 5 @@ -527,7 +527,7 @@ static void stress_cpumap(void) * procedure. */ create_cpu_entry(1, 1024, 0, false); - create_cpu_entry(1, 128, 0, false); + create_cpu_entry(1, 8, 0, false); create_cpu_entry(1, 16000, 0, false); } diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index d69c8d78d3fd..5904b1543831 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -729,7 +729,7 @@ static void kick_tx(int fd) int ret; ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0); - if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN) + if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY) return; lassert(0); } diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan index b593b36ccff8..38b2b4818e8e 100644 --- a/scripts/Makefile.ubsan +++ b/scripts/Makefile.ubsan @@ -14,10 +14,6 @@ ifdef CONFIG_UBSAN_ALIGNMENT CFLAGS_UBSAN += $(call cc-option, -fsanitize=alignment) endif -ifdef CONFIG_UBSAN_NULL - CFLAGS_UBSAN += $(call cc-option, -fsanitize=null) -endif - # -fsanitize=* options makes GCC less smart than usual and # increase number of 'maybe-uninitialized false-positives CFLAGS_UBSAN += $(call cc-option, -Wno-maybe-uninitialized) diff --git a/scripts/tags.sh b/scripts/tags.sh index 412a70cce558..26de7d5aa5c8 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -152,6 +152,7 @@ regex_asm=( ) regex_c=( '/^SYSCALL_DEFINE[0-9](\([[:alnum:]_]*\).*/sys_\1/' + '/^BPF_CALL_[0-9](\([[:alnum:]_]*\).*/\1/' '/^COMPAT_SYSCALL_DEFINE[0-9](\([[:alnum:]_]*\).*/compat_sys_\1/' '/^TRACE_EVENT(\([[:alnum:]_]*\).*/trace_\1/' '/^TRACE_EVENT(\([[:alnum:]_]*\).*/trace_\1_rcuidle/' diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 69616d00481c..b53026a72e73 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -635,7 +635,7 @@ static int snd_rawmidi_info_select_user(struct snd_card *card, int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream, struct snd_rawmidi_params * params) { - char *newbuf; + char *newbuf, *oldbuf; struct snd_rawmidi_runtime *runtime = substream->runtime; if (substream->append && substream->use_count > 1) @@ -648,13 +648,17 @@ int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream, return -EINVAL; } if (params->buffer_size != runtime->buffer_size) { - newbuf = krealloc(runtime->buffer, params->buffer_size, - GFP_KERNEL); + newbuf = kmalloc(params->buffer_size, GFP_KERNEL); if (!newbuf) return -ENOMEM; + spin_lock_irq(&runtime->lock); + oldbuf = runtime->buffer; runtime->buffer = newbuf; runtime->buffer_size = params->buffer_size; runtime->avail = runtime->buffer_size; + runtime->appl_ptr = runtime->hw_ptr = 0; + spin_unlock_irq(&runtime->lock); + kfree(oldbuf); } runtime->avail_min = params->avail_min; substream->active_sensing = !params->no_active_sensing; @@ -665,7 +669,7 @@ EXPORT_SYMBOL(snd_rawmidi_output_params); int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream, struct snd_rawmidi_params * params) { - char *newbuf; + char *newbuf, *oldbuf; struct snd_rawmidi_runtime *runtime = substream->runtime; snd_rawmidi_drain_input(substream); @@ -676,12 +680,16 @@ int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream, return -EINVAL; } if (params->buffer_size != runtime->buffer_size) { - newbuf = krealloc(runtime->buffer, params->buffer_size, - GFP_KERNEL); + newbuf = kmalloc(params->buffer_size, GFP_KERNEL); if (!newbuf) return -ENOMEM; + spin_lock_irq(&runtime->lock); + oldbuf = runtime->buffer; runtime->buffer = newbuf; runtime->buffer_size = params->buffer_size; + runtime->appl_ptr = runtime->hw_ptr = 0; + spin_unlock_irq(&runtime->lock); + kfree(oldbuf); } runtime->avail_min = params->avail_min; return 0; diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index e7fcfc3b8885..f641c20095f7 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -964,6 +964,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC), SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO), + SND_PCI_QUIRK(0x103c, 0x836e, "HP ProBook 455 G5", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 7496be4491b1..f6af3e1c2b93 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2366,6 +2366,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), @@ -6569,6 +6570,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), + SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h new file mode 100644 index 000000000000..5072cbd15c82 --- /dev/null +++ b/tools/arch/arm64/include/uapi/asm/unistd.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2012 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#define __ARCH_WANT_RENAMEAT + +#include <asm-generic/unistd.h> diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h index ac5ba55066dd..985534d0b448 100644 --- a/tools/arch/powerpc/include/uapi/asm/unistd.h +++ b/tools/arch/powerpc/include/uapi/asm/unistd.h @@ -399,5 +399,6 @@ #define __NR_pkey_free 385 #define __NR_pkey_mprotect 386 #define __NR_rseq 387 +#define __NR_io_pgetevents 388 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/tools/arch/x86/include/asm/mcsafe_test.h b/tools/arch/x86/include/asm/mcsafe_test.h new file mode 100644 index 000000000000..2ccd588fbad4 --- /dev/null +++ b/tools/arch/x86/include/asm/mcsafe_test.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MCSAFE_TEST_H_ +#define _MCSAFE_TEST_H_ + +.macro MCSAFE_TEST_CTL +.endm + +.macro MCSAFE_TEST_SRC reg count target +.endm + +.macro MCSAFE_TEST_DST reg count target +.endm +#endif /* _MCSAFE_TEST_H_ */ diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 9a53a06e5a3e..298ef1479240 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -3,6 +3,7 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> +#include <asm/mcsafe_test.h> #include <asm/alternative-asm.h> #include <asm/export.h> @@ -183,12 +184,15 @@ ENTRY(memcpy_orig) ENDPROC(memcpy_orig) #ifndef CONFIG_UML + +MCSAFE_TEST_CTL + /* - * memcpy_mcsafe_unrolled - memory copy with machine check exception handling + * __memcpy_mcsafe - memory copy with machine check exception handling * Note that we only catch machine checks when reading the source addresses. * Writes to target are posted and don't generate machine checks. */ -ENTRY(memcpy_mcsafe_unrolled) +ENTRY(__memcpy_mcsafe) cmpl $8, %edx /* Less than 8 bytes? Go to byte copy loop */ jb .L_no_whole_words @@ -204,58 +208,33 @@ ENTRY(memcpy_mcsafe_unrolled) subl $8, %ecx negl %ecx subl %ecx, %edx -.L_copy_leading_bytes: +.L_read_leading_bytes: movb (%rsi), %al + MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes + MCSAFE_TEST_DST %rdi 1 .E_leading_bytes +.L_write_leading_bytes: movb %al, (%rdi) incq %rsi incq %rdi decl %ecx - jnz .L_copy_leading_bytes + jnz .L_read_leading_bytes .L_8byte_aligned: - /* Figure out how many whole cache lines (64-bytes) to copy */ - movl %edx, %ecx - andl $63, %edx - shrl $6, %ecx - jz .L_no_whole_cache_lines - - /* Loop copying whole cache lines */ -.L_cache_w0: movq (%rsi), %r8 -.L_cache_w1: movq 1*8(%rsi), %r9 -.L_cache_w2: movq 2*8(%rsi), %r10 -.L_cache_w3: movq 3*8(%rsi), %r11 - movq %r8, (%rdi) - movq %r9, 1*8(%rdi) - movq %r10, 2*8(%rdi) - movq %r11, 3*8(%rdi) -.L_cache_w4: movq 4*8(%rsi), %r8 -.L_cache_w5: movq 5*8(%rsi), %r9 -.L_cache_w6: movq 6*8(%rsi), %r10 -.L_cache_w7: movq 7*8(%rsi), %r11 - movq %r8, 4*8(%rdi) - movq %r9, 5*8(%rdi) - movq %r10, 6*8(%rdi) - movq %r11, 7*8(%rdi) - leaq 64(%rsi), %rsi - leaq 64(%rdi), %rdi - decl %ecx - jnz .L_cache_w0 - - /* Are there any trailing 8-byte words? */ -.L_no_whole_cache_lines: movl %edx, %ecx andl $7, %edx shrl $3, %ecx jz .L_no_whole_words - /* Copy trailing words */ -.L_copy_trailing_words: +.L_read_words: movq (%rsi), %r8 - mov %r8, (%rdi) - leaq 8(%rsi), %rsi - leaq 8(%rdi), %rdi + MCSAFE_TEST_SRC %rsi 8 .E_read_words + MCSAFE_TEST_DST %rdi 8 .E_write_words +.L_write_words: + movq %r8, (%rdi) + addq $8, %rsi + addq $8, %rdi decl %ecx - jnz .L_copy_trailing_words + jnz .L_read_words /* Any trailing bytes? */ .L_no_whole_words: @@ -264,38 +243,55 @@ ENTRY(memcpy_mcsafe_unrolled) /* Copy trailing bytes */ movl %edx, %ecx -.L_copy_trailing_bytes: +.L_read_trailing_bytes: movb (%rsi), %al + MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes + MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes +.L_write_trailing_bytes: movb %al, (%rdi) incq %rsi incq %rdi decl %ecx - jnz .L_copy_trailing_bytes + jnz .L_read_trailing_bytes /* Copy successful. Return zero */ .L_done_memcpy_trap: xorq %rax, %rax ret -ENDPROC(memcpy_mcsafe_unrolled) -EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled) +ENDPROC(__memcpy_mcsafe) +EXPORT_SYMBOL_GPL(__memcpy_mcsafe) .section .fixup, "ax" - /* Return -EFAULT for any failure */ -.L_memcpy_mcsafe_fail: - mov $-EFAULT, %rax + /* + * Return number of bytes not copied for any failure. Note that + * there is no "tail" handling since the source buffer is 8-byte + * aligned and poison is cacheline aligned. + */ +.E_read_words: + shll $3, %ecx +.E_leading_bytes: + addl %edx, %ecx +.E_trailing_bytes: + mov %ecx, %eax ret + /* + * For write fault handling, given the destination is unaligned, + * we handle faults on multi-byte writes with a byte-by-byte + * copy up to the write-protected page. + */ +.E_write_words: + shll $3, %ecx + addl %edx, %ecx + movl %ecx, %edx + jmp mcsafe_handle_tail + .previous - _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes) + _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words) + _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes) + _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes) + _ASM_EXTABLE(.L_write_words, .E_write_words) + _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes) #endif diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 32f9e397a6c0..3f140eff039f 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -217,6 +217,14 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) int err; int fd; + if (argc < 3) { + p_err("too few arguments, id ID and FILE path is required"); + return -1; + } else if (argc > 3) { + p_err("too many arguments"); + return -1; + } + if (!is_prefix(*argv, "id")) { p_err("expected 'id' got %s", *argv); return -1; @@ -230,9 +238,6 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) } NEXT_ARG(); - if (argc != 1) - usage(); - fd = get_fd_by_id(id); if (fd < 0) { p_err("can't get prog by id (%u): %s", id, strerror(errno)); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 097b1a5e046b..f74a8bcbda87 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -36,6 +36,7 @@ #include <assert.h> #include <errno.h> #include <fcntl.h> +#include <linux/kernel.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -90,7 +91,8 @@ static bool map_is_map_of_progs(__u32 type) static void *alloc_value(struct bpf_map_info *info) { if (map_is_per_cpu(info->type)) - return malloc(info->value_size * get_possible_cpus()); + return malloc(round_up(info->value_size, 8) * + get_possible_cpus()); else return malloc(info->value_size); } @@ -161,9 +163,10 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, jsonw_name(json_wtr, "value"); print_hex_data_json(value, info->value_size); } else { - unsigned int i, n; + unsigned int i, n, step; n = get_possible_cpus(); + step = round_up(info->value_size, 8); jsonw_name(json_wtr, "key"); print_hex_data_json(key, info->key_size); @@ -176,7 +179,7 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, jsonw_int_field(json_wtr, "cpu", i); jsonw_name(json_wtr, "value"); - print_hex_data_json(value + i * info->value_size, + print_hex_data_json(value + i * step, info->value_size); jsonw_end_object(json_wtr); @@ -207,9 +210,10 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, printf("\n"); } else { - unsigned int i, n; + unsigned int i, n, step; n = get_possible_cpus(); + step = round_up(info->value_size, 8); printf("key:\n"); fprint_hex(stdout, key, info->key_size, " "); @@ -217,7 +221,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, for (i = 0; i < n; i++) { printf("value (CPU %02d):%c", i, info->value_size > 16 ? '\n' : ' '); - fprint_hex(stdout, value + i * info->value_size, + fprint_hex(stdout, value + i * step, info->value_size, " "); printf("\n"); } diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h new file mode 100644 index 000000000000..42990676a55e --- /dev/null +++ b/tools/include/uapi/asm-generic/unistd.h @@ -0,0 +1,783 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#include <asm/bitsperlong.h> + +/* + * This file contains the system call numbers, based on the + * layout of the x86-64 architecture, which embeds the + * pointer to the syscall in the table. + * + * As a basic principle, no duplication of functionality + * should be added, e.g. we don't use lseek when llseek + * is present. New architectures should use this file + * and implement the less feature-full calls in user space. + */ + +#ifndef __SYSCALL +#define __SYSCALL(x, y) +#endif + +#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT) +#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32) +#else +#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64) +#endif + +#ifdef __SYSCALL_COMPAT +#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp) +#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp) +#else +#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys) +#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64) +#endif + +#define __NR_io_setup 0 +__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup) +#define __NR_io_destroy 1 +__SYSCALL(__NR_io_destroy, sys_io_destroy) +#define __NR_io_submit 2 +__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit) +#define __NR_io_cancel 3 +__SYSCALL(__NR_io_cancel, sys_io_cancel) +#define __NR_io_getevents 4 +__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents) + +/* fs/xattr.c */ +#define __NR_setxattr 5 +__SYSCALL(__NR_setxattr, sys_setxattr) +#define __NR_lsetxattr 6 +__SYSCALL(__NR_lsetxattr, sys_lsetxattr) +#define __NR_fsetxattr 7 +__SYSCALL(__NR_fsetxattr, sys_fsetxattr) +#define __NR_getxattr 8 +__SYSCALL(__NR_getxattr, sys_getxattr) +#define __NR_lgetxattr 9 +__SYSCALL(__NR_lgetxattr, sys_lgetxattr) +#define __NR_fgetxattr 10 +__SYSCALL(__NR_fgetxattr, sys_fgetxattr) +#define __NR_listxattr 11 +__SYSCALL(__NR_listxattr, sys_listxattr) +#define __NR_llistxattr 12 +__SYSCALL(__NR_llistxattr, sys_llistxattr) +#define __NR_flistxattr 13 +__SYSCALL(__NR_flistxattr, sys_flistxattr) +#define __NR_removexattr 14 +__SYSCALL(__NR_removexattr, sys_removexattr) +#define __NR_lremovexattr 15 +__SYSCALL(__NR_lremovexattr, sys_lremovexattr) +#define __NR_fremovexattr 16 +__SYSCALL(__NR_fremovexattr, sys_fremovexattr) + +/* fs/dcache.c */ +#define __NR_getcwd 17 +__SYSCALL(__NR_getcwd, sys_getcwd) + +/* fs/cookies.c */ +#define __NR_lookup_dcookie 18 +__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie) + +/* fs/eventfd.c */ +#define __NR_eventfd2 19 +__SYSCALL(__NR_eventfd2, sys_eventfd2) + +/* fs/eventpoll.c */ +#define __NR_epoll_create1 20 +__SYSCALL(__NR_epoll_create1, sys_epoll_create1) +#define __NR_epoll_ctl 21 +__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl) +#define __NR_epoll_pwait 22 +__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait) + +/* fs/fcntl.c */ +#define __NR_dup 23 +__SYSCALL(__NR_dup, sys_dup) +#define __NR_dup3 24 +__SYSCALL(__NR_dup3, sys_dup3) +#define __NR3264_fcntl 25 +__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64) + +/* fs/inotify_user.c */ +#define __NR_inotify_init1 26 +__SYSCALL(__NR_inotify_init1, sys_inotify_init1) +#define __NR_inotify_add_watch 27 +__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch) +#define __NR_inotify_rm_watch 28 +__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch) + +/* fs/ioctl.c */ +#define __NR_ioctl 29 +__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl) + +/* fs/ioprio.c */ +#define __NR_ioprio_set 30 +__SYSCALL(__NR_ioprio_set, sys_ioprio_set) +#define __NR_ioprio_get 31 +__SYSCALL(__NR_ioprio_get, sys_ioprio_get) + +/* fs/locks.c */ +#define __NR_flock 32 +__SYSCALL(__NR_flock, sys_flock) + +/* fs/namei.c */ +#define __NR_mknodat 33 +__SYSCALL(__NR_mknodat, sys_mknodat) +#define __NR_mkdirat 34 +__SYSCALL(__NR_mkdirat, sys_mkdirat) +#define __NR_unlinkat 35 +__SYSCALL(__NR_unlinkat, sys_unlinkat) +#define __NR_symlinkat 36 +__SYSCALL(__NR_symlinkat, sys_symlinkat) +#define __NR_linkat 37 +__SYSCALL(__NR_linkat, sys_linkat) +#ifdef __ARCH_WANT_RENAMEAT +/* renameat is superseded with flags by renameat2 */ +#define __NR_renameat 38 +__SYSCALL(__NR_renameat, sys_renameat) +#endif /* __ARCH_WANT_RENAMEAT */ + +/* fs/namespace.c */ +#define __NR_umount2 39 +__SYSCALL(__NR_umount2, sys_umount) +#define __NR_mount 40 +__SC_COMP(__NR_mount, sys_mount, compat_sys_mount) +#define __NR_pivot_root 41 +__SYSCALL(__NR_pivot_root, sys_pivot_root) + +/* fs/nfsctl.c */ +#define __NR_nfsservctl 42 +__SYSCALL(__NR_nfsservctl, sys_ni_syscall) + +/* fs/open.c */ +#define __NR3264_statfs 43 +__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \ + compat_sys_statfs64) +#define __NR3264_fstatfs 44 +__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \ + compat_sys_fstatfs64) +#define __NR3264_truncate 45 +__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \ + compat_sys_truncate64) +#define __NR3264_ftruncate 46 +__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \ + compat_sys_ftruncate64) + +#define __NR_fallocate 47 +__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate) +#define __NR_faccessat 48 +__SYSCALL(__NR_faccessat, sys_faccessat) +#define __NR_chdir 49 +__SYSCALL(__NR_chdir, sys_chdir) +#define __NR_fchdir 50 +__SYSCALL(__NR_fchdir, sys_fchdir) +#define __NR_chroot 51 +__SYSCALL(__NR_chroot, sys_chroot) +#define __NR_fchmod 52 +__SYSCALL(__NR_fchmod, sys_fchmod) +#define __NR_fchmodat 53 +__SYSCALL(__NR_fchmodat, sys_fchmodat) +#define __NR_fchownat 54 +__SYSCALL(__NR_fchownat, sys_fchownat) +#define __NR_fchown 55 +__SYSCALL(__NR_fchown, sys_fchown) +#define __NR_openat 56 +__SC_COMP(__NR_openat, sys_openat, compat_sys_openat) +#define __NR_close 57 +__SYSCALL(__NR_close, sys_close) +#define __NR_vhangup 58 +__SYSCALL(__NR_vhangup, sys_vhangup) + +/* fs/pipe.c */ +#define __NR_pipe2 59 +__SYSCALL(__NR_pipe2, sys_pipe2) + +/* fs/quota.c */ +#define __NR_quotactl 60 +__SYSCALL(__NR_quotactl, sys_quotactl) + +/* fs/readdir.c */ +#define __NR_getdents64 61 +__SYSCALL(__NR_getdents64, sys_getdents64) + +/* fs/read_write.c */ +#define __NR3264_lseek 62 +__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek) +#define __NR_read 63 +__SYSCALL(__NR_read, sys_read) +#define __NR_write 64 +__SYSCALL(__NR_write, sys_write) +#define __NR_readv 65 +__SC_COMP(__NR_readv, sys_readv, compat_sys_readv) +#define __NR_writev 66 +__SC_COMP(__NR_writev, sys_writev, compat_sys_writev) +#define __NR_pread64 67 +__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64) +#define __NR_pwrite64 68 +__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64) +#define __NR_preadv 69 +__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv) +#define __NR_pwritev 70 +__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev) + +/* fs/sendfile.c */ +#define __NR3264_sendfile 71 +__SYSCALL(__NR3264_sendfile, sys_sendfile64) + +/* fs/select.c */ +#define __NR_pselect6 72 +__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6) +#define __NR_ppoll 73 +__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll) + +/* fs/signalfd.c */ +#define __NR_signalfd4 74 +__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4) + +/* fs/splice.c */ +#define __NR_vmsplice 75 +__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice) +#define __NR_splice 76 +__SYSCALL(__NR_splice, sys_splice) +#define __NR_tee 77 +__SYSCALL(__NR_tee, sys_tee) + +/* fs/stat.c */ +#define __NR_readlinkat 78 +__SYSCALL(__NR_readlinkat, sys_readlinkat) +#define __NR3264_fstatat 79 +__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat) +#define __NR3264_fstat 80 +__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat) + +/* fs/sync.c */ +#define __NR_sync 81 +__SYSCALL(__NR_sync, sys_sync) +#define __NR_fsync 82 +__SYSCALL(__NR_fsync, sys_fsync) +#define __NR_fdatasync 83 +__SYSCALL(__NR_fdatasync, sys_fdatasync) +#ifdef __ARCH_WANT_SYNC_FILE_RANGE2 +#define __NR_sync_file_range2 84 +__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \ + compat_sys_sync_file_range2) +#else +#define __NR_sync_file_range 84 +__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \ + compat_sys_sync_file_range) +#endif + +/* fs/timerfd.c */ +#define __NR_timerfd_create 85 +__SYSCALL(__NR_timerfd_create, sys_timerfd_create) +#define __NR_timerfd_settime 86 +__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \ + compat_sys_timerfd_settime) +#define __NR_timerfd_gettime 87 +__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \ + compat_sys_timerfd_gettime) + +/* fs/utimes.c */ +#define __NR_utimensat 88 +__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat) + +/* kernel/acct.c */ +#define __NR_acct 89 +__SYSCALL(__NR_acct, sys_acct) + +/* kernel/capability.c */ +#define __NR_capget 90 +__SYSCALL(__NR_capget, sys_capget) +#define __NR_capset 91 +__SYSCALL(__NR_capset, sys_capset) + +/* kernel/exec_domain.c */ +#define __NR_personality 92 +__SYSCALL(__NR_personality, sys_personality) + +/* kernel/exit.c */ +#define __NR_exit 93 +__SYSCALL(__NR_exit, sys_exit) +#define __NR_exit_group 94 +__SYSCALL(__NR_exit_group, sys_exit_group) +#define __NR_waitid 95 +__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid) + +/* kernel/fork.c */ +#define __NR_set_tid_address 96 +__SYSCALL(__NR_set_tid_address, sys_set_tid_address) +#define __NR_unshare 97 +__SYSCALL(__NR_unshare, sys_unshare) + +/* kernel/futex.c */ +#define __NR_futex 98 +__SC_COMP(__NR_futex, sys_futex, compat_sys_futex) +#define __NR_set_robust_list 99 +__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \ + compat_sys_set_robust_list) +#define __NR_get_robust_list 100 +__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \ + compat_sys_get_robust_list) + +/* kernel/hrtimer.c */ +#define __NR_nanosleep 101 +__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep) + +/* kernel/itimer.c */ +#define __NR_getitimer 102 +__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer) +#define __NR_setitimer 103 +__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer) + +/* kernel/kexec.c */ +#define __NR_kexec_load 104 +__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load) + +/* kernel/module.c */ +#define __NR_init_module 105 +__SYSCALL(__NR_init_module, sys_init_module) +#define __NR_delete_module 106 +__SYSCALL(__NR_delete_module, sys_delete_module) + +/* kernel/posix-timers.c */ +#define __NR_timer_create 107 +__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create) +#define __NR_timer_gettime 108 +__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime) +#define __NR_timer_getoverrun 109 +__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) +#define __NR_timer_settime 110 +__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime) +#define __NR_timer_delete 111 +__SYSCALL(__NR_timer_delete, sys_timer_delete) +#define __NR_clock_settime 112 +__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime) +#define __NR_clock_gettime 113 +__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime) +#define __NR_clock_getres 114 +__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres) +#define __NR_clock_nanosleep 115 +__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \ + compat_sys_clock_nanosleep) + +/* kernel/printk.c */ +#define __NR_syslog 116 +__SYSCALL(__NR_syslog, sys_syslog) + +/* kernel/ptrace.c */ +#define __NR_ptrace 117 +__SYSCALL(__NR_ptrace, sys_ptrace) + +/* kernel/sched/core.c */ +#define __NR_sched_setparam 118 +__SYSCALL(__NR_sched_setparam, sys_sched_setparam) +#define __NR_sched_setscheduler 119 +__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler) +#define __NR_sched_getscheduler 120 +__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler) +#define __NR_sched_getparam 121 +__SYSCALL(__NR_sched_getparam, sys_sched_getparam) +#define __NR_sched_setaffinity 122 +__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \ + compat_sys_sched_setaffinity) +#define __NR_sched_getaffinity 123 +__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \ + compat_sys_sched_getaffinity) +#define __NR_sched_yield 124 +__SYSCALL(__NR_sched_yield, sys_sched_yield) +#define __NR_sched_get_priority_max 125 +__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max) +#define __NR_sched_get_priority_min 126 +__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) +#define __NR_sched_rr_get_interval 127 +__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \ + compat_sys_sched_rr_get_interval) + +/* kernel/signal.c */ +#define __NR_restart_syscall 128 +__SYSCALL(__NR_restart_syscall, sys_restart_syscall) +#define __NR_kill 129 +__SYSCALL(__NR_kill, sys_kill) +#define __NR_tkill 130 +__SYSCALL(__NR_tkill, sys_tkill) +#define __NR_tgkill 131 +__SYSCALL(__NR_tgkill, sys_tgkill) +#define __NR_sigaltstack 132 +__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack) +#define __NR_rt_sigsuspend 133 +__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend) +#define __NR_rt_sigaction 134 +__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction) +#define __NR_rt_sigprocmask 135 +__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask) +#define __NR_rt_sigpending 136 +__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending) +#define __NR_rt_sigtimedwait 137 +__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \ + compat_sys_rt_sigtimedwait) +#define __NR_rt_sigqueueinfo 138 +__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \ + compat_sys_rt_sigqueueinfo) +#define __NR_rt_sigreturn 139 +__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn) + +/* kernel/sys.c */ +#define __NR_setpriority 140 +__SYSCALL(__NR_setpriority, sys_setpriority) +#define __NR_getpriority 141 +__SYSCALL(__NR_getpriority, sys_getpriority) +#define __NR_reboot 142 +__SYSCALL(__NR_reboot, sys_reboot) +#define __NR_setregid 143 +__SYSCALL(__NR_setregid, sys_setregid) +#define __NR_setgid 144 +__SYSCALL(__NR_setgid, sys_setgid) +#define __NR_setreuid 145 +__SYSCALL(__NR_setreuid, sys_setreuid) +#define __NR_setuid 146 +__SYSCALL(__NR_setuid, sys_setuid) +#define __NR_setresuid 147 +__SYSCALL(__NR_setresuid, sys_setresuid) +#define __NR_getresuid 148 +__SYSCALL(__NR_getresuid, sys_getresuid) +#define __NR_setresgid 149 +__SYSCALL(__NR_setresgid, sys_setresgid) +#define __NR_getresgid 150 +__SYSCALL(__NR_getresgid, sys_getresgid) +#define __NR_setfsuid 151 +__SYSCALL(__NR_setfsuid, sys_setfsuid) +#define __NR_setfsgid 152 +__SYSCALL(__NR_setfsgid, sys_setfsgid) +#define __NR_times 153 +__SC_COMP(__NR_times, sys_times, compat_sys_times) +#define __NR_setpgid 154 +__SYSCALL(__NR_setpgid, sys_setpgid) +#define __NR_getpgid 155 +__SYSCALL(__NR_getpgid, sys_getpgid) +#define __NR_getsid 156 +__SYSCALL(__NR_getsid, sys_getsid) +#define __NR_setsid 157 +__SYSCALL(__NR_setsid, sys_setsid) +#define __NR_getgroups 158 +__SYSCALL(__NR_getgroups, sys_getgroups) +#define __NR_setgroups 159 +__SYSCALL(__NR_setgroups, sys_setgroups) +#define __NR_uname 160 +__SYSCALL(__NR_uname, sys_newuname) +#define __NR_sethostname 161 +__SYSCALL(__NR_sethostname, sys_sethostname) +#define __NR_setdomainname 162 +__SYSCALL(__NR_setdomainname, sys_setdomainname) +#define __NR_getrlimit 163 +__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit) +#define __NR_setrlimit 164 +__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit) +#define __NR_getrusage 165 +__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage) +#define __NR_umask 166 +__SYSCALL(__NR_umask, sys_umask) +#define __NR_prctl 167 +__SYSCALL(__NR_prctl, sys_prctl) +#define __NR_getcpu 168 +__SYSCALL(__NR_getcpu, sys_getcpu) + +/* kernel/time.c */ +#define __NR_gettimeofday 169 +__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday) +#define __NR_settimeofday 170 +__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday) +#define __NR_adjtimex 171 +__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex) + +/* kernel/timer.c */ +#define __NR_getpid 172 +__SYSCALL(__NR_getpid, sys_getpid) +#define __NR_getppid 173 +__SYSCALL(__NR_getppid, sys_getppid) +#define __NR_getuid 174 +__SYSCALL(__NR_getuid, sys_getuid) +#define __NR_geteuid 175 +__SYSCALL(__NR_geteuid, sys_geteuid) +#define __NR_getgid 176 +__SYSCALL(__NR_getgid, sys_getgid) +#define __NR_getegid 177 +__SYSCALL(__NR_getegid, sys_getegid) +#define __NR_gettid 178 +__SYSCALL(__NR_gettid, sys_gettid) +#define __NR_sysinfo 179 +__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo) + +/* ipc/mqueue.c */ +#define __NR_mq_open 180 +__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open) +#define __NR_mq_unlink 181 +__SYSCALL(__NR_mq_unlink, sys_mq_unlink) +#define __NR_mq_timedsend 182 +__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend) +#define __NR_mq_timedreceive 183 +__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \ + compat_sys_mq_timedreceive) +#define __NR_mq_notify 184 +__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify) +#define __NR_mq_getsetattr 185 +__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr) + +/* ipc/msg.c */ +#define __NR_msgget 186 +__SYSCALL(__NR_msgget, sys_msgget) +#define __NR_msgctl 187 +__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl) +#define __NR_msgrcv 188 +__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv) +#define __NR_msgsnd 189 +__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd) + +/* ipc/sem.c */ +#define __NR_semget 190 +__SYSCALL(__NR_semget, sys_semget) +#define __NR_semctl 191 +__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl) +#define __NR_semtimedop 192 +__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop) +#define __NR_semop 193 +__SYSCALL(__NR_semop, sys_semop) + +/* ipc/shm.c */ +#define __NR_shmget 194 +__SYSCALL(__NR_shmget, sys_shmget) +#define __NR_shmctl 195 +__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl) +#define __NR_shmat 196 +__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat) +#define __NR_shmdt 197 +__SYSCALL(__NR_shmdt, sys_shmdt) + +/* net/socket.c */ +#define __NR_socket 198 +__SYSCALL(__NR_socket, sys_socket) +#define __NR_socketpair 199 +__SYSCALL(__NR_socketpair, sys_socketpair) +#define __NR_bind 200 +__SYSCALL(__NR_bind, sys_bind) +#define __NR_listen 201 +__SYSCALL(__NR_listen, sys_listen) +#define __NR_accept 202 +__SYSCALL(__NR_accept, sys_accept) +#define __NR_connect 203 +__SYSCALL(__NR_connect, sys_connect) +#define __NR_getsockname 204 +__SYSCALL(__NR_getsockname, sys_getsockname) +#define __NR_getpeername 205 +__SYSCALL(__NR_getpeername, sys_getpeername) +#define __NR_sendto 206 +__SYSCALL(__NR_sendto, sys_sendto) +#define __NR_recvfrom 207 +__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom) +#define __NR_setsockopt 208 +__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt) +#define __NR_getsockopt 209 +__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt) +#define __NR_shutdown 210 +__SYSCALL(__NR_shutdown, sys_shutdown) +#define __NR_sendmsg 211 +__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg) +#define __NR_recvmsg 212 +__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg) + +/* mm/filemap.c */ +#define __NR_readahead 213 +__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead) + +/* mm/nommu.c, also with MMU */ +#define __NR_brk 214 +__SYSCALL(__NR_brk, sys_brk) +#define __NR_munmap 215 +__SYSCALL(__NR_munmap, sys_munmap) +#define __NR_mremap 216 +__SYSCALL(__NR_mremap, sys_mremap) + +/* security/keys/keyctl.c */ +#define __NR_add_key 217 +__SYSCALL(__NR_add_key, sys_add_key) +#define __NR_request_key 218 +__SYSCALL(__NR_request_key, sys_request_key) +#define __NR_keyctl 219 +__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl) + +/* arch/example/kernel/sys_example.c */ +#define __NR_clone 220 +__SYSCALL(__NR_clone, sys_clone) +#define __NR_execve 221 +__SC_COMP(__NR_execve, sys_execve, compat_sys_execve) + +#define __NR3264_mmap 222 +__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap) +/* mm/fadvise.c */ +#define __NR3264_fadvise64 223 +__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64) + +/* mm/, CONFIG_MMU only */ +#ifndef __ARCH_NOMMU +#define __NR_swapon 224 +__SYSCALL(__NR_swapon, sys_swapon) +#define __NR_swapoff 225 +__SYSCALL(__NR_swapoff, sys_swapoff) +#define __NR_mprotect 226 +__SYSCALL(__NR_mprotect, sys_mprotect) +#define __NR_msync 227 +__SYSCALL(__NR_msync, sys_msync) +#define __NR_mlock 228 +__SYSCALL(__NR_mlock, sys_mlock) +#define __NR_munlock 229 +__SYSCALL(__NR_munlock, sys_munlock) +#define __NR_mlockall 230 +__SYSCALL(__NR_mlockall, sys_mlockall) +#define __NR_munlockall 231 +__SYSCALL(__NR_munlockall, sys_munlockall) +#define __NR_mincore 232 +__SYSCALL(__NR_mincore, sys_mincore) +#define __NR_madvise 233 +__SYSCALL(__NR_madvise, sys_madvise) +#define __NR_remap_file_pages 234 +__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages) +#define __NR_mbind 235 +__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind) +#define __NR_get_mempolicy 236 +__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy) +#define __NR_set_mempolicy 237 +__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy) +#define __NR_migrate_pages 238 +__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages) +#define __NR_move_pages 239 +__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages) +#endif + +#define __NR_rt_tgsigqueueinfo 240 +__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \ + compat_sys_rt_tgsigqueueinfo) +#define __NR_perf_event_open 241 +__SYSCALL(__NR_perf_event_open, sys_perf_event_open) +#define __NR_accept4 242 +__SYSCALL(__NR_accept4, sys_accept4) +#define __NR_recvmmsg 243 +__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg) + +/* + * Architectures may provide up to 16 syscalls of their own + * starting with this value. + */ +#define __NR_arch_specific_syscall 244 + +#define __NR_wait4 260 +__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4) +#define __NR_prlimit64 261 +__SYSCALL(__NR_prlimit64, sys_prlimit64) +#define __NR_fanotify_init 262 +__SYSCALL(__NR_fanotify_init, sys_fanotify_init) +#define __NR_fanotify_mark 263 +__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) +#define __NR_name_to_handle_at 264 +__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) +#define __NR_open_by_handle_at 265 +__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \ + compat_sys_open_by_handle_at) +#define __NR_clock_adjtime 266 +__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime) +#define __NR_syncfs 267 +__SYSCALL(__NR_syncfs, sys_syncfs) +#define __NR_setns 268 +__SYSCALL(__NR_setns, sys_setns) +#define __NR_sendmmsg 269 +__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg) +#define __NR_process_vm_readv 270 +__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \ + compat_sys_process_vm_readv) +#define __NR_process_vm_writev 271 +__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \ + compat_sys_process_vm_writev) +#define __NR_kcmp 272 +__SYSCALL(__NR_kcmp, sys_kcmp) +#define __NR_finit_module 273 +__SYSCALL(__NR_finit_module, sys_finit_module) +#define __NR_sched_setattr 274 +__SYSCALL(__NR_sched_setattr, sys_sched_setattr) +#define __NR_sched_getattr 275 +__SYSCALL(__NR_sched_getattr, sys_sched_getattr) +#define __NR_renameat2 276 +__SYSCALL(__NR_renameat2, sys_renameat2) +#define __NR_seccomp 277 +__SYSCALL(__NR_seccomp, sys_seccomp) +#define __NR_getrandom 278 +__SYSCALL(__NR_getrandom, sys_getrandom) +#define __NR_memfd_create 279 +__SYSCALL(__NR_memfd_create, sys_memfd_create) +#define __NR_bpf 280 +__SYSCALL(__NR_bpf, sys_bpf) +#define __NR_execveat 281 +__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat) +#define __NR_userfaultfd 282 +__SYSCALL(__NR_userfaultfd, sys_userfaultfd) +#define __NR_membarrier 283 +__SYSCALL(__NR_membarrier, sys_membarrier) +#define __NR_mlock2 284 +__SYSCALL(__NR_mlock2, sys_mlock2) +#define __NR_copy_file_range 285 +__SYSCALL(__NR_copy_file_range, sys_copy_file_range) +#define __NR_preadv2 286 +__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2) +#define __NR_pwritev2 287 +__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2) +#define __NR_pkey_mprotect 288 +__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect) +#define __NR_pkey_alloc 289 +__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc) +#define __NR_pkey_free 290 +__SYSCALL(__NR_pkey_free, sys_pkey_free) +#define __NR_statx 291 +__SYSCALL(__NR_statx, sys_statx) +#define __NR_io_pgetevents 292 +__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) + +#undef __NR_syscalls +#define __NR_syscalls 293 + +/* + * 32 bit systems traditionally used different + * syscalls for off_t and loff_t arguments, while + * 64 bit systems only need the off_t version. + * For new 32 bit platforms, there is no need to + * implement the old 32 bit off_t syscalls, so + * they take different names. + * Here we map the numbers so that both versions + * use the same syscall table layout. + */ +#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT) +#define __NR_fcntl __NR3264_fcntl +#define __NR_statfs __NR3264_statfs +#define __NR_fstatfs __NR3264_fstatfs +#define __NR_truncate __NR3264_truncate +#define __NR_ftruncate __NR3264_ftruncate +#define __NR_lseek __NR3264_lseek +#define __NR_sendfile __NR3264_sendfile +#define __NR_newfstatat __NR3264_fstatat +#define __NR_fstat __NR3264_fstat +#define __NR_mmap __NR3264_mmap +#define __NR_fadvise64 __NR3264_fadvise64 +#ifdef __NR3264_stat +#define __NR_stat __NR3264_stat +#define __NR_lstat __NR3264_lstat +#endif +#else +#define __NR_fcntl64 __NR3264_fcntl +#define __NR_statfs64 __NR3264_statfs +#define __NR_fstatfs64 __NR3264_fstatfs +#define __NR_truncate64 __NR3264_truncate +#define __NR_ftruncate64 __NR3264_ftruncate +#define __NR_llseek __NR3264_lseek +#define __NR_sendfile64 __NR3264_sendfile +#define __NR_fstatat64 __NR3264_fstatat +#define __NR_fstat64 __NR3264_fstat +#define __NR_mmap2 __NR3264_mmap +#define __NR_fadvise64_64 __NR3264_fadvise64 +#ifdef __NR3264_stat +#define __NR_stat64 __NR3264_stat +#define __NR_lstat64 __NR3264_lstat +#endif +#endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 59b19b6a40d7..b7db3261c62d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1857,7 +1857,8 @@ union bpf_attr { * is resolved), the nexthop address is returned in ipv4_dst * or ipv6_dst based on family, smac is set to mac address of * egress device, dmac is set to nexthop mac address, rt_metric - * is set to metric from route (IPv4/IPv6 only). + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. * * *plen* argument is the size of the passed in struct. * *flags* argument can be a combination of one or more of the @@ -1873,9 +1874,10 @@ union bpf_attr { * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. * Return - * Egress device index on success, 0 if packet needs to continue - * up the stack for further processing or a negative error in case - * of failure. + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * * packet is not forwarded or needs assist from full stack * * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) * Description @@ -2612,6 +2614,18 @@ struct bpf_raw_tracepoint_args { #define BPF_FIB_LOOKUP_DIRECT BIT(0) #define BPF_FIB_LOOKUP_OUTPUT BIT(1) +enum { + BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ + BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */ + BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */ + BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */ + BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */ + BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */ + BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ + BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ + BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ +}; + struct bpf_fib_lookup { /* input: network family for lookup (AF_INET, AF_INET6) * output: network family of egress nexthop @@ -2625,7 +2639,11 @@ struct bpf_fib_lookup { /* total length of packet from network header - used for MTU check */ __u16 tot_len; - __u32 ifindex; /* L3 device index for lookup */ + + /* input: L3 device index for lookup + * output: device index from FIB lookup + */ + __u32 ifindex; union { /* inputs to lookup */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 0b5ddbe135a4..972265f32871 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -76,7 +76,7 @@ struct btf_type { */ #define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) #define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) -#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) /* Attributes stored in the BTF_INT_ENCODING */ #define BTF_INT_SIGNED (1 << 0) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h new file mode 100644 index 000000000000..48e8a225b985 --- /dev/null +++ b/tools/include/uapi/linux/in.h @@ -0,0 +1,301 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions of the Internet Protocol. + * + * Version: @(#)in.h 1.0.1 04/21/93 + * + * Authors: Original taken from the GNU Project <netinet/in.h> file. + * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _UAPI_LINUX_IN_H +#define _UAPI_LINUX_IN_H + +#include <linux/types.h> +#include <linux/libc-compat.h> +#include <linux/socket.h> + +#if __UAPI_DEF_IN_IPPROTO +/* Standard well-defined IP protocols. */ +enum { + IPPROTO_IP = 0, /* Dummy protocol for TCP */ +#define IPPROTO_IP IPPROTO_IP + IPPROTO_ICMP = 1, /* Internet Control Message Protocol */ +#define IPPROTO_ICMP IPPROTO_ICMP + IPPROTO_IGMP = 2, /* Internet Group Management Protocol */ +#define IPPROTO_IGMP IPPROTO_IGMP + IPPROTO_IPIP = 4, /* IPIP tunnels (older KA9Q tunnels use 94) */ +#define IPPROTO_IPIP IPPROTO_IPIP + IPPROTO_TCP = 6, /* Transmission Control Protocol */ +#define IPPROTO_TCP IPPROTO_TCP + IPPROTO_EGP = 8, /* Exterior Gateway Protocol */ +#define IPPROTO_EGP IPPROTO_EGP + IPPROTO_PUP = 12, /* PUP protocol */ +#define IPPROTO_PUP IPPROTO_PUP + IPPROTO_UDP = 17, /* User Datagram Protocol */ +#define IPPROTO_UDP IPPROTO_UDP + IPPROTO_IDP = 22, /* XNS IDP protocol */ +#define IPPROTO_IDP IPPROTO_IDP + IPPROTO_TP = 29, /* SO Transport Protocol Class 4 */ +#define IPPROTO_TP IPPROTO_TP + IPPROTO_DCCP = 33, /* Datagram Congestion Control Protocol */ +#define IPPROTO_DCCP IPPROTO_DCCP + IPPROTO_IPV6 = 41, /* IPv6-in-IPv4 tunnelling */ +#define IPPROTO_IPV6 IPPROTO_IPV6 + IPPROTO_RSVP = 46, /* RSVP Protocol */ +#define IPPROTO_RSVP IPPROTO_RSVP + IPPROTO_GRE = 47, /* Cisco GRE tunnels (rfc 1701,1702) */ +#define IPPROTO_GRE IPPROTO_GRE + IPPROTO_ESP = 50, /* Encapsulation Security Payload protocol */ +#define IPPROTO_ESP IPPROTO_ESP + IPPROTO_AH = 51, /* Authentication Header protocol */ +#define IPPROTO_AH IPPROTO_AH + IPPROTO_MTP = 92, /* Multicast Transport Protocol */ +#define IPPROTO_MTP IPPROTO_MTP + IPPROTO_BEETPH = 94, /* IP option pseudo header for BEET */ +#define IPPROTO_BEETPH IPPROTO_BEETPH + IPPROTO_ENCAP = 98, /* Encapsulation Header */ +#define IPPROTO_ENCAP IPPROTO_ENCAP + IPPROTO_PIM = 103, /* Protocol Independent Multicast */ +#define IPPROTO_PIM IPPROTO_PIM + IPPROTO_COMP = 108, /* Compression Header Protocol */ +#define IPPROTO_COMP IPPROTO_COMP + IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */ +#define IPPROTO_SCTP IPPROTO_SCTP + IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */ +#define IPPROTO_UDPLITE IPPROTO_UDPLITE + IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */ +#define IPPROTO_MPLS IPPROTO_MPLS + IPPROTO_RAW = 255, /* Raw IP packets */ +#define IPPROTO_RAW IPPROTO_RAW + IPPROTO_MAX +}; +#endif + +#if __UAPI_DEF_IN_ADDR +/* Internet address. */ +struct in_addr { + __be32 s_addr; +}; +#endif + +#define IP_TOS 1 +#define IP_TTL 2 +#define IP_HDRINCL 3 +#define IP_OPTIONS 4 +#define IP_ROUTER_ALERT 5 +#define IP_RECVOPTS 6 +#define IP_RETOPTS 7 +#define IP_PKTINFO 8 +#define IP_PKTOPTIONS 9 +#define IP_MTU_DISCOVER 10 +#define IP_RECVERR 11 +#define IP_RECVTTL 12 +#define IP_RECVTOS 13 +#define IP_MTU 14 +#define IP_FREEBIND 15 +#define IP_IPSEC_POLICY 16 +#define IP_XFRM_POLICY 17 +#define IP_PASSSEC 18 +#define IP_TRANSPARENT 19 + +/* BSD compatibility */ +#define IP_RECVRETOPTS IP_RETOPTS + +/* TProxy original addresses */ +#define IP_ORIGDSTADDR 20 +#define IP_RECVORIGDSTADDR IP_ORIGDSTADDR + +#define IP_MINTTL 21 +#define IP_NODEFRAG 22 +#define IP_CHECKSUM 23 +#define IP_BIND_ADDRESS_NO_PORT 24 +#define IP_RECVFRAGSIZE 25 + +/* IP_MTU_DISCOVER values */ +#define IP_PMTUDISC_DONT 0 /* Never send DF frames */ +#define IP_PMTUDISC_WANT 1 /* Use per route hints */ +#define IP_PMTUDISC_DO 2 /* Always DF */ +#define IP_PMTUDISC_PROBE 3 /* Ignore dst pmtu */ +/* Always use interface mtu (ignores dst pmtu) but don't set DF flag. + * Also incoming ICMP frag_needed notifications will be ignored on + * this socket to prevent accepting spoofed ones. + */ +#define IP_PMTUDISC_INTERFACE 4 +/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get + * fragmented if they exeed the interface mtu + */ +#define IP_PMTUDISC_OMIT 5 + +#define IP_MULTICAST_IF 32 +#define IP_MULTICAST_TTL 33 +#define IP_MULTICAST_LOOP 34 +#define IP_ADD_MEMBERSHIP 35 +#define IP_DROP_MEMBERSHIP 36 +#define IP_UNBLOCK_SOURCE 37 +#define IP_BLOCK_SOURCE 38 +#define IP_ADD_SOURCE_MEMBERSHIP 39 +#define IP_DROP_SOURCE_MEMBERSHIP 40 +#define IP_MSFILTER 41 +#define MCAST_JOIN_GROUP 42 +#define MCAST_BLOCK_SOURCE 43 +#define MCAST_UNBLOCK_SOURCE 44 +#define MCAST_LEAVE_GROUP 45 +#define MCAST_JOIN_SOURCE_GROUP 46 +#define MCAST_LEAVE_SOURCE_GROUP 47 +#define MCAST_MSFILTER 48 +#define IP_MULTICAST_ALL 49 +#define IP_UNICAST_IF 50 + +#define MCAST_EXCLUDE 0 +#define MCAST_INCLUDE 1 + +/* These need to appear somewhere around here */ +#define IP_DEFAULT_MULTICAST_TTL 1 +#define IP_DEFAULT_MULTICAST_LOOP 1 + +/* Request struct for multicast socket ops */ + +#if __UAPI_DEF_IP_MREQ +struct ip_mreq { + struct in_addr imr_multiaddr; /* IP multicast address of group */ + struct in_addr imr_interface; /* local IP address of interface */ +}; + +struct ip_mreqn { + struct in_addr imr_multiaddr; /* IP multicast address of group */ + struct in_addr imr_address; /* local IP address of interface */ + int imr_ifindex; /* Interface index */ +}; + +struct ip_mreq_source { + __be32 imr_multiaddr; + __be32 imr_interface; + __be32 imr_sourceaddr; +}; + +struct ip_msfilter { + __be32 imsf_multiaddr; + __be32 imsf_interface; + __u32 imsf_fmode; + __u32 imsf_numsrc; + __be32 imsf_slist[1]; +}; + +#define IP_MSFILTER_SIZE(numsrc) \ + (sizeof(struct ip_msfilter) - sizeof(__u32) \ + + (numsrc) * sizeof(__u32)) + +struct group_req { + __u32 gr_interface; /* interface index */ + struct __kernel_sockaddr_storage gr_group; /* group address */ +}; + +struct group_source_req { + __u32 gsr_interface; /* interface index */ + struct __kernel_sockaddr_storage gsr_group; /* group address */ + struct __kernel_sockaddr_storage gsr_source; /* source address */ +}; + +struct group_filter { + __u32 gf_interface; /* interface index */ + struct __kernel_sockaddr_storage gf_group; /* multicast address */ + __u32 gf_fmode; /* filter mode */ + __u32 gf_numsrc; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */ +}; + +#define GROUP_FILTER_SIZE(numsrc) \ + (sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \ + + (numsrc) * sizeof(struct __kernel_sockaddr_storage)) +#endif + +#if __UAPI_DEF_IN_PKTINFO +struct in_pktinfo { + int ipi_ifindex; + struct in_addr ipi_spec_dst; + struct in_addr ipi_addr; +}; +#endif + +/* Structure describing an Internet (IP) socket address. */ +#if __UAPI_DEF_SOCKADDR_IN +#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */ +struct sockaddr_in { + __kernel_sa_family_t sin_family; /* Address family */ + __be16 sin_port; /* Port number */ + struct in_addr sin_addr; /* Internet address */ + + /* Pad to size of `struct sockaddr'. */ + unsigned char __pad[__SOCK_SIZE__ - sizeof(short int) - + sizeof(unsigned short int) - sizeof(struct in_addr)]; +}; +#define sin_zero __pad /* for BSD UNIX comp. -FvK */ +#endif + +#if __UAPI_DEF_IN_CLASS +/* + * Definitions of the bits in an Internet address integer. + * On subnets, host and network parts are found according + * to the subnet mask, not these masks. + */ +#define IN_CLASSA(a) ((((long int) (a)) & 0x80000000) == 0) +#define IN_CLASSA_NET 0xff000000 +#define IN_CLASSA_NSHIFT 24 +#define IN_CLASSA_HOST (0xffffffff & ~IN_CLASSA_NET) +#define IN_CLASSA_MAX 128 + +#define IN_CLASSB(a) ((((long int) (a)) & 0xc0000000) == 0x80000000) +#define IN_CLASSB_NET 0xffff0000 +#define IN_CLASSB_NSHIFT 16 +#define IN_CLASSB_HOST (0xffffffff & ~IN_CLASSB_NET) +#define IN_CLASSB_MAX 65536 + +#define IN_CLASSC(a) ((((long int) (a)) & 0xe0000000) == 0xc0000000) +#define IN_CLASSC_NET 0xffffff00 +#define IN_CLASSC_NSHIFT 8 +#define IN_CLASSC_HOST (0xffffffff & ~IN_CLASSC_NET) + +#define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000) +#define IN_MULTICAST(a) IN_CLASSD(a) +#define IN_MULTICAST_NET 0xF0000000 + +#define IN_EXPERIMENTAL(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) +#define IN_BADCLASS(a) IN_EXPERIMENTAL((a)) + +/* Address to accept any incoming messages. */ +#define INADDR_ANY ((unsigned long int) 0x00000000) + +/* Address to send to all hosts. */ +#define INADDR_BROADCAST ((unsigned long int) 0xffffffff) + +/* Address indicating an error return. */ +#define INADDR_NONE ((unsigned long int) 0xffffffff) + +/* Network number for local host loopback. */ +#define IN_LOOPBACKNET 127 + +/* Address to loopback in software to local host. */ +#define INADDR_LOOPBACK 0x7f000001 /* 127.0.0.1 */ +#define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000) + +/* Defines for Multicast INADDR */ +#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ +#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ +#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ +#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ +#endif + +/* <asm/byteorder.h> contains the htonl type stuff.. */ +#include <asm/byteorder.h> + + +#endif /* _UAPI_LINUX_IN_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index b8e288a1f740..eeb787b1c53c 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -143,6 +143,8 @@ enum perf_event_sample_format { PERF_SAMPLE_PHYS_ADDR = 1U << 19, PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ + + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, }; /* diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 8c54a4b6f187..c36a3a76986a 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1,8 +1,7 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: LGPL-2.1 /* Copyright (c) 2018 Facebook */ #include <stdlib.h> -#include <stdint.h> #include <string.h> #include <unistd.h> #include <errno.h> @@ -27,13 +26,13 @@ struct btf { struct btf_type **types; const char *strings; void *nohdr_data; - uint32_t nr_types; - uint32_t types_size; - uint32_t data_size; + __u32 nr_types; + __u32 types_size; + __u32 data_size; int fd; }; -static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset) +static const char *btf_name_by_offset(const struct btf *btf, __u32 offset) { if (offset < btf->hdr->str_len) return &btf->strings[offset]; @@ -45,7 +44,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) { if (btf->types_size - btf->nr_types < 2) { struct btf_type **new_types; - u32 expand_by, new_size; + __u32 expand_by, new_size; if (btf->types_size == BTF_MAX_NR_TYPES) return -E2BIG; @@ -72,7 +71,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log) { const struct btf_header *hdr = btf->hdr; - u32 meta_left; + __u32 meta_left; if (btf->data_size < sizeof(struct btf_header)) { elog("BTF header not found\n"); @@ -151,7 +150,7 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) while (next_type < end_type) { struct btf_type *t = next_type; - uint16_t vlen = BTF_INFO_VLEN(t->info); + __u16 vlen = BTF_INFO_VLEN(t->info); int err; next_type += sizeof(*t); @@ -190,8 +189,7 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) return 0; } -static const struct btf_type *btf_type_by_id(const struct btf *btf, - uint32_t type_id) +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) { if (type_id > btf->nr_types) return NULL; @@ -209,7 +207,7 @@ static bool btf_type_is_void_or_null(const struct btf_type *t) return !t || btf_type_is_void(t); } -static int64_t btf_type_size(const struct btf_type *t) +static __s64 btf_type_size(const struct btf_type *t) { switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_INT: @@ -226,15 +224,15 @@ static int64_t btf_type_size(const struct btf_type *t) #define MAX_RESOLVE_DEPTH 32 -int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) +__s64 btf__resolve_size(const struct btf *btf, __u32 type_id) { const struct btf_array *array; const struct btf_type *t; - uint32_t nelems = 1; - int64_t size = -1; + __u32 nelems = 1; + __s64 size = -1; int i; - t = btf_type_by_id(btf, type_id); + t = btf__type_by_id(btf, type_id); for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) { size = btf_type_size(t); @@ -259,7 +257,7 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) return -EINVAL; } - t = btf_type_by_id(btf, type_id); + t = btf__type_by_id(btf, type_id); } if (size < 0) @@ -271,9 +269,9 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) return nelems * size; } -int32_t btf__find_by_name(const struct btf *btf, const char *type_name) +__s32 btf__find_by_name(const struct btf *btf, const char *type_name) { - uint32_t i; + __u32 i; if (!strcmp(type_name, "void")) return 0; @@ -302,10 +300,9 @@ void btf__free(struct btf *btf) free(btf); } -struct btf *btf__new(uint8_t *data, uint32_t size, - btf_print_fn_t err_log) +struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log) { - uint32_t log_buf_size = 0; + __u32 log_buf_size = 0; char *log_buf = NULL; struct btf *btf; int err; diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 74bb344035bb..caac3a404dc5 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -1,22 +1,24 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: LGPL-2.1 */ /* Copyright (c) 2018 Facebook */ #ifndef __BPF_BTF_H #define __BPF_BTF_H -#include <stdint.h> +#include <linux/types.h> #define BTF_ELF_SEC ".BTF" struct btf; +struct btf_type; typedef int (*btf_print_fn_t)(const char *, ...) __attribute__((format(printf, 1, 2))); void btf__free(struct btf *btf); -struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log); -int32_t btf__find_by_name(const struct btf *btf, const char *type_name); -int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id); +struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log); +__s32 btf__find_by_name(const struct btf *btf, const char *type_name); +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); +__s64 btf__resolve_size(const struct btf *btf, __u32 type_id); int btf__fd(const struct btf *btf); #endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a1e96b5de5ff..1aafdbe827fe 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -36,6 +36,7 @@ #include <linux/err.h> #include <linux/kernel.h> #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/list.h> #include <linux/limits.h> #include <sys/stat.h> @@ -216,8 +217,8 @@ struct bpf_map { size_t offset; int map_ifindex; struct bpf_map_def def; - uint32_t btf_key_type_id; - uint32_t btf_value_type_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; }; @@ -1014,68 +1015,72 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) { + const struct btf_type *container_type; + const struct btf_member *key, *value; struct bpf_map_def *def = &map->def; const size_t max_name = 256; - int64_t key_size, value_size; - int32_t key_id, value_id; - char name[max_name]; + char container_name[max_name]; + __s64 key_size, value_size; + __s32 container_id; - /* Find key type by name from BTF */ - if (snprintf(name, max_name, "%s_key", map->name) == max_name) { - pr_warning("map:%s length of BTF key_type:%s_key is too long\n", + if (snprintf(container_name, max_name, "____btf_map_%s", map->name) == + max_name) { + pr_warning("map:%s length of '____btf_map_%s' is too long\n", map->name, map->name); return -EINVAL; } - key_id = btf__find_by_name(btf, name); - if (key_id < 0) { - pr_debug("map:%s key_type:%s cannot be found in BTF\n", - map->name, name); - return key_id; + container_id = btf__find_by_name(btf, container_name); + if (container_id < 0) { + pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n", + map->name, container_name); + return container_id; } - key_size = btf__resolve_size(btf, key_id); - if (key_size < 0) { - pr_warning("map:%s key_type:%s cannot get the BTF type_size\n", - map->name, name); - return key_size; + container_type = btf__type_by_id(btf, container_id); + if (!container_type) { + pr_warning("map:%s cannot find BTF type for container_id:%u\n", + map->name, container_id); + return -EINVAL; } - if (def->key_size != key_size) { - pr_warning("map:%s key_type:%s has BTF type_size:%u != key_size:%u\n", - map->name, name, (unsigned int)key_size, def->key_size); + if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT || + BTF_INFO_VLEN(container_type->info) < 2) { + pr_warning("map:%s container_name:%s is an invalid container struct\n", + map->name, container_name); return -EINVAL; } - /* Find value type from BTF */ - if (snprintf(name, max_name, "%s_value", map->name) == max_name) { - pr_warning("map:%s length of BTF value_type:%s_value is too long\n", - map->name, map->name); - return -EINVAL; + key = (struct btf_member *)(container_type + 1); + value = key + 1; + + key_size = btf__resolve_size(btf, key->type); + if (key_size < 0) { + pr_warning("map:%s invalid BTF key_type_size\n", + map->name); + return key_size; } - value_id = btf__find_by_name(btf, name); - if (value_id < 0) { - pr_debug("map:%s value_type:%s cannot be found in BTF\n", - map->name, name); - return value_id; + if (def->key_size != key_size) { + pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", + map->name, (__u32)key_size, def->key_size); + return -EINVAL; } - value_size = btf__resolve_size(btf, value_id); + value_size = btf__resolve_size(btf, value->type); if (value_size < 0) { - pr_warning("map:%s value_type:%s cannot get the BTF type_size\n", - map->name, name); + pr_warning("map:%s invalid BTF value_type_size\n", map->name); return value_size; } if (def->value_size != value_size) { - pr_warning("map:%s value_type:%s has BTF type_size:%u != value_size:%u\n", - map->name, name, (unsigned int)value_size, def->value_size); + pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", + map->name, (__u32)value_size, def->value_size); return -EINVAL; } - map->btf_key_type_id = key_id; - map->btf_value_type_id = value_id; + map->btf_key_type_id = key->type; + map->btf_value_type_id = value->type; return 0; } @@ -2089,12 +2094,12 @@ const char *bpf_map__name(struct bpf_map *map) return map ? map->name : NULL; } -uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map) +__u32 bpf_map__btf_key_type_id(const struct bpf_map *map) { return map ? map->btf_key_type_id : 0; } -uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map) +__u32 bpf_map__btf_value_type_id(const struct bpf_map *map) { return map ? map->btf_value_type_id : 0; } @@ -2268,8 +2273,8 @@ bpf_perf_event_read_simple(void *mem, unsigned long size, volatile struct perf_event_mmap_page *header = mem; __u64 data_tail = header->data_tail; __u64 data_head = header->data_head; + int ret = LIBBPF_PERF_EVENT_ERROR; void *base, *begin, *end; - int ret; asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ if (data_head == data_tail) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 09976531aa74..b33ae02f7d0e 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -244,8 +244,8 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); int bpf_map__fd(struct bpf_map *map); const struct bpf_map_def *bpf_map__def(struct bpf_map *map); const char *bpf_map__name(struct bpf_map *map); -uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map); -uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map); +__u32 bpf_map__btf_key_type_id(const struct bpf_map *map); +__u32 bpf_map__btf_value_type_id(const struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); int bpf_map__set_priv(struct bpf_map *map, void *priv, diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index 1b09f3175a1f..0cbd1ef8f86d 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -804,7 +804,7 @@ type of fence: Second, some types of fence affect the way the memory subsystem propagates stores. When a fence instruction is executed on CPU C: - For each other CPU C', smb_wmb() forces all po-earlier stores + For each other CPU C', smp_wmb() forces all po-earlier stores on C to propagate to C' before any po-later stores do. For each other CPU C', any store which propagates to C before diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt index ee4309a87fc4..af72700cc20a 100644 --- a/tools/memory-model/Documentation/recipes.txt +++ b/tools/memory-model/Documentation/recipes.txt @@ -126,7 +126,7 @@ However, it is not necessarily the case that accesses ordered by locking will be seen as ordered by CPUs not holding that lock. Consider this example: - /* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */ + /* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */ void CPU0(void) { spin_lock(&mylock); @@ -292,7 +292,7 @@ and to use smp_load_acquire() instead of smp_rmb(). However, the older smp_wmb() and smp_rmb() APIs are still heavily used, so it is important to understand their use cases. The general approach is shown below: - /* See MP+wmbonceonce+rmbonceonce.litmus. */ + /* See MP+fencewmbonceonce+fencermbonceonce.litmus. */ void CPU0(void) { WRITE_ONCE(x, 1); @@ -322,9 +322,9 @@ the following write-side code fragment: And the xlog_valid_lsn() function in fs/xfs/xfs_log_priv.h contains the corresponding read-side code fragment: - cur_cycle = ACCESS_ONCE(log->l_curr_cycle); + cur_cycle = READ_ONCE(log->l_curr_cycle); smp_rmb(); - cur_block = ACCESS_ONCE(log->l_curr_block); + cur_block = READ_ONCE(log->l_curr_block); Alternatively, consider the following comment in function perf_output_put_handle() in kernel/events/ring_buffer.c: @@ -360,7 +360,7 @@ can be seen in the LB+poonceonces.litmus litmus test. One way of avoiding the counter-intuitive outcome is through the use of a control dependency paired with a full memory barrier: - /* See LB+ctrlonceonce+mbonceonce.litmus. */ + /* See LB+fencembonceonce+ctrlonceonce.litmus. */ void CPU0(void) { r0 = READ_ONCE(x); @@ -476,7 +476,7 @@ that one CPU first stores to one variable and then loads from a second, while another CPU stores to the second variable and then loads from the first. Preserving order requires nothing less than full barriers: - /* See SB+mbonceonces.litmus. */ + /* See SB+fencembonceonces.litmus. */ void CPU0(void) { WRITE_ONCE(x, 1); diff --git a/tools/memory-model/README b/tools/memory-model/README index 734f7feaa5dc..ee987ce20aae 100644 --- a/tools/memory-model/README +++ b/tools/memory-model/README @@ -35,13 +35,13 @@ BASIC USAGE: HERD7 The memory model is used, in conjunction with "herd7", to exhaustively explore the state space of small litmus tests. -For example, to run SB+mbonceonces.litmus against the memory model: +For example, to run SB+fencembonceonces.litmus against the memory model: - $ herd7 -conf linux-kernel.cfg litmus-tests/SB+mbonceonces.litmus + $ herd7 -conf linux-kernel.cfg litmus-tests/SB+fencembonceonces.litmus Here is the corresponding output: - Test SB+mbonceonces Allowed + Test SB+fencembonceonces Allowed States 3 0:r0=0; 1:r0=1; 0:r0=1; 1:r0=0; @@ -50,8 +50,8 @@ Here is the corresponding output: Witnesses Positive: 0 Negative: 3 Condition exists (0:r0=0 /\ 1:r0=0) - Observation SB+mbonceonces Never 0 3 - Time SB+mbonceonces 0.01 + Observation SB+fencembonceonces Never 0 3 + Time SB+fencembonceonces 0.01 Hash=d66d99523e2cac6b06e66f4c995ebb48 The "Positive: 0 Negative: 3" and the "Never 0 3" each indicate that @@ -67,16 +67,16 @@ BASIC USAGE: KLITMUS7 The "klitmus7" tool converts a litmus test into a Linux kernel module, which may then be loaded and run. -For example, to run SB+mbonceonces.litmus against hardware: +For example, to run SB+fencembonceonces.litmus against hardware: $ mkdir mymodules - $ klitmus7 -o mymodules litmus-tests/SB+mbonceonces.litmus + $ klitmus7 -o mymodules litmus-tests/SB+fencembonceonces.litmus $ cd mymodules ; make $ sudo sh run.sh The corresponding output includes: - Test SB+mbonceonces Allowed + Test SB+fencembonceonces Allowed Histogram (3 states) 644580 :>0:r0=1; 1:r0=0; 644328 :>0:r0=0; 1:r0=1; @@ -86,8 +86,8 @@ The corresponding output includes: Positive: 0, Negative: 2000000 Condition exists (0:r0=0 /\ 1:r0=0) is NOT validated Hash=d66d99523e2cac6b06e66f4c995ebb48 - Observation SB+mbonceonces Never 0 2000000 - Time SB+mbonceonces 0.16 + Observation SB+fencembonceonces Never 0 2000000 + Time SB+fencembonceonces 0.16 The "Positive: 0 Negative: 2000000" and the "Never 0 2000000" indicate that during two million trials, the state specified in this litmus diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell index 64f5740e0e75..b84fb2f67109 100644 --- a/tools/memory-model/linux-kernel.bell +++ b/tools/memory-model/linux-kernel.bell @@ -13,7 +13,7 @@ "Linux-kernel memory consistency model" -enum Accesses = 'once (*READ_ONCE,WRITE_ONCE,ACCESS_ONCE*) || +enum Accesses = 'once (*READ_ONCE,WRITE_ONCE*) || 'release (*smp_store_release*) || 'acquire (*smp_load_acquire*) || 'noreturn (* R of non-return RMW *) diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus index 98a3716efa37..e729d2776e89 100644 --- a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus +++ b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus @@ -1,4 +1,4 @@ -C IRIW+mbonceonces+OnceOnce +C IRIW+fencembonceonces+OnceOnce (* * Result: Never diff --git a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus index 7a39a0aaa976..0f749e419b34 100644 --- a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus +++ b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus @@ -1,4 +1,4 @@ -C ISA2+pooncelock+pooncelock+pombonce.litmus +C ISA2+pooncelock+pooncelock+pombonce (* * Result: Sometimes diff --git a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus index de6708229dd1..4727f5aaf03b 100644 --- a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus +++ b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus @@ -1,4 +1,4 @@ -C LB+ctrlonceonce+mbonceonce +C LB+fencembonceonce+ctrlonceonce (* * Result: Never diff --git a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus index c078f38ff27a..a273da9faa6d 100644 --- a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus +++ b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus @@ -1,4 +1,4 @@ -C MP+wmbonceonce+rmbonceonce +C MP+fencewmbonceonce+fencermbonceonce (* * Result: Never diff --git a/tools/memory-model/litmus-tests/R+mbonceonces.litmus b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus index a0e884ad2132..222a0b850b4a 100644 --- a/tools/memory-model/litmus-tests/R+mbonceonces.litmus +++ b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus @@ -1,4 +1,4 @@ -C R+mbonceonces +C R+fencembonceonces (* * Result: Never diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README index 17eb9a8c222d..4581ec2d3c57 100644 --- a/tools/memory-model/litmus-tests/README +++ b/tools/memory-model/litmus-tests/README @@ -18,7 +18,7 @@ CoWW+poonceonce.litmus Test of write-write coherence, that is, whether or not two successive writes to the same variable are ordered. -IRIW+mbonceonces+OnceOnce.litmus +IRIW+fencembonceonces+OnceOnce.litmus Test of independent reads from independent writes with smp_mb() between each pairs of reads. In other words, is smp_mb() sufficient to cause two different reading processes to agree on @@ -47,7 +47,7 @@ ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus Can a release-acquire chain order a prior store against a later load? -LB+ctrlonceonce+mbonceonce.litmus +LB+fencembonceonce+ctrlonceonce.litmus Does a control dependency and an smp_mb() suffice for the load-buffering litmus test, where each process reads from one of two variables then writes to the other? @@ -88,14 +88,14 @@ MP+porevlocks.litmus As below, but with the first access of the writer process and the second access of reader process protected by a lock. -MP+wmbonceonce+rmbonceonce.litmus +MP+fencewmbonceonce+fencermbonceonce.litmus Does a smp_wmb() (between the stores) and an smp_rmb() (between the loads) suffice for the message-passing litmus test, where one process writes data and then a flag, and the other process reads the flag and then the data. (This is similar to the ISA2 tests, but with two processes instead of three.) -R+mbonceonces.litmus +R+fencembonceonces.litmus This is the fully ordered (via smp_mb()) version of one of the classic counterintuitive litmus tests that illustrates the effects of store propagation delays. @@ -103,7 +103,7 @@ R+mbonceonces.litmus R+poonceonces.litmus As above, but without the smp_mb() invocations. -SB+mbonceonces.litmus +SB+fencembonceonces.litmus This is the fully ordered (again, via smp_mb() version of store buffering, which forms the core of Dekker's mutual-exclusion algorithm. @@ -111,15 +111,24 @@ SB+mbonceonces.litmus SB+poonceonces.litmus As above, but without the smp_mb() invocations. +SB+rfionceonce-poonceonces.litmus + This litmus test demonstrates that LKMM is not fully multicopy + atomic. (Neither is it other multicopy atomic.) This litmus test + also demonstrates the "locations" debugging aid, which designates + additional registers and locations to be printed out in the dump + of final states in the herd7 output. Without the "locations" + statement, only those registers and locations mentioned in the + "exists" clause will be printed. + S+poonceonces.litmus As below, but without the smp_wmb() and acquire load. -S+wmbonceonce+poacquireonce.litmus +S+fencewmbonceonce+poacquireonce.litmus Can a smp_wmb(), instead of a release, and an acquire order a prior store against a subsequent store? WRC+poonceonces+Once.litmus -WRC+pooncerelease+rmbonceonce+Once.litmus +WRC+pooncerelease+fencermbonceonce+Once.litmus These two are members of an extension of the MP litmus-test class in which the first write is moved to a separate process. The second is forbidden because smp_store_release() is @@ -134,7 +143,7 @@ Z6.0+pooncelock+poonceLock+pombonce.litmus As above, but with smp_mb__after_spinlock() immediately following the spin_lock(). -Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus +Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus Is the ordering provided by a release-acquire chain sufficient to make ordering apparent to accesses by a process that does not participate in that release-acquire chain? diff --git a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus index c53350205d28..18479823cd6c 100644 --- a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus +++ b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus @@ -1,4 +1,4 @@ -C S+wmbonceonce+poacquireonce +C S+fencewmbonceonce+poacquireonce (* * Result: Never diff --git a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus index 74b874ffa8da..ed5fff18d223 100644 --- a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus +++ b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus @@ -1,4 +1,4 @@ -C SB+mbonceonces +C SB+fencembonceonces (* * Result: Never diff --git a/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus new file mode 100644 index 000000000000..04a16603660b --- /dev/null +++ b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus @@ -0,0 +1,32 @@ +C SB+rfionceonce-poonceonces + +(* + * Result: Sometimes + * + * This litmus test demonstrates that LKMM is not fully multicopy atomic. + *) + +{} + +P0(int *x, int *y) +{ + int r1; + int r2; + + WRITE_ONCE(*x, 1); + r1 = READ_ONCE(*x); + r2 = READ_ONCE(*y); +} + +P1(int *x, int *y) +{ + int r3; + int r4; + + WRITE_ONCE(*y, 1); + r3 = READ_ONCE(*y); + r4 = READ_ONCE(*x); +} + +locations [0:r1; 1:r3; x; y] (* Debug aid: Print things not in "exists". *) +exists (0:r2=0 /\ 1:r4=0) diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus index ad3448b941e6..e9947250d7de 100644 --- a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus +++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus @@ -1,4 +1,4 @@ -C WRC+pooncerelease+rmbonceonce+Once +C WRC+pooncerelease+fencermbonceonce+Once (* * Result: Never diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus index a20fc3fafb53..88e70b87a683 100644 --- a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus +++ b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus @@ -1,4 +1,4 @@ -C Z6.0+pooncerelease+poacquirerelease+mbonceonce +C Z6.0+pooncerelease+poacquirerelease+fencembonceonce (* * Result: Sometimes diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh index af0aa15ab84e..ca528f9a24d4 100644..100755 --- a/tools/memory-model/scripts/checkalllitmus.sh +++ b/tools/memory-model/scripts/checkalllitmus.sh @@ -9,7 +9,7 @@ # appended. # # Usage: -# sh checkalllitmus.sh [ directory ] +# checkalllitmus.sh [ directory ] # # The LINUX_HERD_OPTIONS environment variable may be used to specify # arguments to herd, whose default is defined by the checklitmus.sh script. diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh index e2e477472844..bf12a75c0719 100644..100755 --- a/tools/memory-model/scripts/checklitmus.sh +++ b/tools/memory-model/scripts/checklitmus.sh @@ -8,7 +8,7 @@ # with ".out" appended. # # Usage: -# sh checklitmus.sh file.litmus +# checklitmus.sh file.litmus # # The LINUX_HERD_OPTIONS environment variable may be used to specify # arguments to herd, which default to "-conf linux-kernel.cfg". Thus, diff --git a/tools/objtool/arch/x86/include/asm/orc_types.h b/tools/objtool/arch/x86/include/asm/orc_types.h index 9c9dc579bd7d..46f516dd80ce 100644 --- a/tools/objtool/arch/x86/include/asm/orc_types.h +++ b/tools/objtool/arch/x86/include/asm/orc_types.h @@ -88,6 +88,7 @@ struct orc_entry { unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; + unsigned end:1; } __packed; /* @@ -101,6 +102,7 @@ struct unwind_hint { s16 sp_offset; u8 sp_reg; u8 type; + u8 end; }; #endif /* __ASSEMBLY__ */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f4a25bd1871f..2928939b98ec 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1157,6 +1157,7 @@ static int read_unwind_hints(struct objtool_file *file) cfa->offset = hint->sp_offset; insn->state.type = hint->type; + insn->state.end = hint->end; } return 0; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index c6b68fcb926f..95700a2bcb7c 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -31,7 +31,7 @@ struct insn_state { int stack_size; unsigned char type; bool bp_scratch; - bool drap; + bool drap, end; int drap_reg, drap_offset; struct cfi_reg vals[CFI_NUM_REGS]; }; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 0d1acb704f64..7ec85d567598 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -519,10 +519,12 @@ struct section *elf_create_section(struct elf *elf, const char *name, sec->sh.sh_flags = SHF_ALLOC; - /* Add section name to .shstrtab */ + /* Add section name to .shstrtab (or .strtab for Clang) */ shstrtab = find_section_by_name(elf, ".shstrtab"); + if (!shstrtab) + shstrtab = find_section_by_name(elf, ".strtab"); if (!shstrtab) { - WARN("can't find .shstrtab section"); + WARN("can't find .shstrtab or .strtab section"); return NULL; } diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index c3343820916a..faa444270ee3 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -203,7 +203,8 @@ int orc_dump(const char *_objname) print_reg(orc[i].bp_reg, orc[i].bp_offset); - printf(" type:%s\n", orc_type_name(orc[i].type)); + printf(" type:%s end:%d\n", + orc_type_name(orc[i].type), orc[i].end); } elf_end(elf); diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 18384d9be4e1..3f98dcfbc177 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -31,6 +31,8 @@ int create_orc(struct objtool_file *file) struct cfi_reg *cfa = &insn->state.cfa; struct cfi_reg *bp = &insn->state.regs[CFI_BP]; + orc->end = insn->state.end; + if (cfa->base == CFI_UNDEFINED) { orc->sp_reg = ORC_REG_UNDEFINED; continue; diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 11300dbe35c5..236b9b97dfdb 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -18,6 +18,10 @@ various perf commands with the -e option. OPTIONS ------- +-d:: +--desc:: +Print extra event descriptions. (default) + --no-desc:: Don't print descriptions. @@ -25,11 +29,13 @@ Don't print descriptions. --long-desc:: Print longer event descriptions. +--debug:: +Enable debugging output. + --details:: Print how named events are resolved internally into perf events, and also any extra expressions computed by perf stat. - [[EVENT_MODIFIERS]] EVENT MODIFIERS --------------- @@ -234,7 +240,7 @@ perf also supports group leader sampling using the :S specifier. perf record -e '{cycles,instructions}:S' ... perf report --group -Normally all events in a event group sample, but with :S only +Normally all events in an event group sample, but with :S only the first event (the leader) samples, and it only reads the values of the other events in the group. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 04168da4268e..246dee081efd 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -94,7 +94,7 @@ OPTIONS "perf report" to view group events together. --filter=<filter>:: - Event filter. This option should follow a event selector (-e) which + Event filter. This option should follow an event selector (-e) which selects either tracepoint event(s) or a hardware trace PMU (e.g. Intel PT or CoreSight). @@ -153,7 +153,7 @@ OPTIONS --exclude-perf:: Don't record events issued by perf itself. This option should follow - a event selector (-e) which selects tracepoint event(s). It adds a + an event selector (-e) which selects tracepoint event(s). It adds a filter expression 'common_pid != $PERFPID' to filters. If other '--filter' exists, the new filter expression will be combined with them by '&&'. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index f5a3b402589e..f6d1a03c7523 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -54,6 +54,8 @@ endif ifeq ($(SRCARCH),arm64) NO_PERF_REGS := 0 + NO_SYSCALL_TABLE := 0 + CFLAGS += -I$(OUTPUT)arch/arm64/include/generated LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif @@ -905,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative)) mandir = share/man infodir = share/info perfexecdir = libexec/perf-core -perf_include_dir = lib/include/perf -perf_examples_dir = lib/examples/perf +perf_include_dir = lib/perf/include +perf_examples_dir = lib/perf/examples sharedir = $(prefix)/share template_dir = share/perf-core/templates STRACE_GROUPS_DIR = share/perf-core/strace/groups diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index ecc9fc952655..b3d1b12a5081 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -384,6 +384,8 @@ export INSTALL SHELL_PATH SHELL = $(SHELL_PATH) +linux_uapi_dir := $(srctree)/tools/include/uapi/linux + beauty_outdir := $(OUTPUT)trace/beauty/generated beauty_ioctl_outdir := $(beauty_outdir)/ioctl drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c @@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl) $(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@ +socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c +socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh + +$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl) + $(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@ + vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(sndrv_ctl_ioctl_array) \ $(kcmp_type_array) \ $(kvm_ioctl_array) \ + $(socket_ipproto_array) \ $(vhost_virtio_ioctl_array) \ $(madvise_behavior_array) \ $(perf_ioctl_array) \ @@ -860,6 +869,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)$(sndrv_pcm_ioctl_array) \ $(OUTPUT)$(kvm_ioctl_array) \ $(OUTPUT)$(kcmp_type_array) \ + $(OUTPUT)$(socket_ipproto_array) \ $(OUTPUT)$(vhost_virtio_ioctl_array) \ $(OUTPUT)$(perf_ioctl_array) \ $(OUTPUT)$(prctl_option_array) \ diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 91de4860faad..f013b115dc86 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -4,3 +4,24 @@ PERF_HAVE_DWARF_REGS := 1 endif PERF_HAVE_JITDUMP := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 + +# +# Syscall table generation for perf +# + +out := $(OUTPUT)arch/arm64/include/generated/asm +header := $(out)/syscalls.c +sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h +sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ +systbl := $(sysprf)/mksyscalltbl + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@ + +clean:: + $(call QUIET_CLEAN, arm64) $(RM) $(header) + +archheaders: $(header) diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl new file mode 100755 index 000000000000..52e197317d3e --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -0,0 +1,62 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate system call table for perf. Derived from +# powerpc script. +# +# Copyright IBM Corp. 2017 +# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> +# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> +# Changed by: Kim Phillips <kim.phillips@arm.com> + +gcc=$1 +hostcc=$2 +input=$3 + +if ! test -r $input; then + echo "Could not read input file" >&2 + exit 1 +fi + +create_table_from_c() +{ + local sc nr last_sc + + create_table_exe=`mktemp /tmp/create-table-XXXXXX` + + { + + cat <<-_EoHEADER + #include <stdio.h> + #define __ARCH_WANT_RENAMEAT + #include "$input" + int main(int argc, char *argv[]) + { + _EoHEADER + + while read sc nr; do + printf "%s\n" " printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);" + last_sc=$sc + done + + printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);" + printf "}\n" + + } | $hostcc -o $create_table_exe -x c - + + $create_table_exe + + rm -f $create_table_exe +} + +create_table() +{ + echo "static const char *syscalltbl_arm64[] = {" + create_table_from_c + echo "};" +} + +$gcc -E -dM -x c $input \ + |sed -ne 's/^#define __NR_//p' \ + |sort -t' ' -k2 -nu \ + |create_table diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index ef5d59a5742e..7c6eeb4633fe 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -58,9 +58,13 @@ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) } /* - * Check if return address is on the stack. + * Check if return address is on the stack. If return address + * is in a register (typically R0), it is yet to be saved on + * the stack. */ - if (nops != 0 || ops != NULL) + if ((nops != 0 || ops != NULL) && + !(nops == 1 && ops[0].atom == DW_OP_regx && + ops[0].number2 == 0 && ops[0].offset == 0)) return 0; /* @@ -246,7 +250,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) if (!chain || chain->nr < 3) return skip_slot; - ip = chain->ips[2]; + ip = chain->ips[1]; thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c index d233e2eb9592..aaabab5e2830 100644 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -102,7 +102,7 @@ const char * const kvm_skip_events[] = { int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid) { - if (strstr(cpuid, "IBM/S390")) { + if (strstr(cpuid, "IBM")) { kvm->exit_reasons = sie_exit_reasons; kvm->exit_reasons_isa = "SIE"; } else diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index 63a74c32ddc5..e33ef5bc31c5 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include "../../util/intel-pt.h" diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 06bae7023a51..950539f9a4f7 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -2,6 +2,7 @@ #include <stdbool.h> #include <errno.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include "../../perf.h" diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index 60bf11943047..eafce1a130a1 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o perf-y += futex-requeue.o perf-y += futex-lock-pi.o +perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index b43f8d2a34ec..9ad015a1e202 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -6,6 +6,7 @@ #define altinstr_replacement text #define globl p2align 4; .globl #define _ASM_EXTABLE_FAULT(x, y) +#define _ASM_EXTABLE(x, y) #include "../../arch/x86/lib/memcpy_64.S" /* diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c new file mode 100644 index 000000000000..4130734dde84 --- /dev/null +++ b/tools/perf/bench/mem-memcpy-x86-64-lib.c @@ -0,0 +1,24 @@ +/* + * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy + * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy' + * happy. + */ +#include <linux/types.h> + +unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt); +unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len); + +unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len) +{ + for (; len; --len, to++, from++) { + /* + * Call the assembly routine back directly since + * memcpy_mcsafe() may silently fallback to memcpy. + */ + unsigned long rem = __memcpy_mcsafe(to, from, 1); + + if (rem) + break; + } + return len; +} diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 6a8738f7ead3..f3aa9d02a5ab 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2193,7 +2193,7 @@ static void print_cacheline(struct c2c_hists *c2c_hists, fprintf(out, "%s\n", bf); fprintf(out, " -------------------------------------------------------------\n"); - hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true); + hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false); } static void print_pareto(FILE *out) @@ -2268,7 +2268,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session) fprintf(out, "=================================================\n"); fprintf(out, "#\n"); - hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false); + hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true); fprintf(out, "\n"); fprintf(out, "=================================================\n"); @@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) " s Toggle full length of symbol and source line columns \n" " q Return back to cacheline list \n"; + if (!he) + return 0; + /* Display compact version first. */ c2c.symbol_full = false; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index d660cb7b222b..39db2ee32d48 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -696,7 +696,7 @@ static void hists__process(struct hists *hists) hists__output_resort(hists, NULL); hists__fprintf(hists, !quiet, 0, 0, 0, stdout, - symbol_conf.use_callchain); + !symbol_conf.use_callchain); } static void data__fprintf(void) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index c04dc7b53797..02f7a3c27761 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -478,8 +478,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, hists__fprintf_nr_sample_events(hists, rep, evname, stdout); hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout, - symbol_conf.use_callchain || - symbol_conf.show_branchflag_count); + !(symbol_conf.use_callchain || + symbol_conf.show_branchflag_count)); fprintf(stdout, "\n\n"); } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 05be023c3f0e..d097b5b47eb8 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -296,18 +296,6 @@ static int create_perf_stat_counter(struct perf_evsel *evsel) return perf_evsel__open_per_thread(evsel, evsel_list->threads); } -/* - * Does the counter have nsecs as a unit? - */ -static inline int nsec_counter(struct perf_evsel *evsel) -{ - if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || - perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) - return 1; - - return 0; -} - static int process_synthesized_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -1058,34 +1046,6 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused, fprintf(os->fh, "%*s ", metric_only_len, unit); } -static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) -{ - FILE *output = stat_config.output; - double msecs = avg / NSEC_PER_MSEC; - const char *fmt_v, *fmt_n; - char name[25]; - - fmt_v = csv_output ? "%.6f%s" : "%18.6f%s"; - fmt_n = csv_output ? "%s" : "%-25s"; - - aggr_printout(evsel, id, nr); - - scnprintf(name, sizeof(name), "%s%s", - perf_evsel__name(evsel), csv_output ? "" : " (msec)"); - - fprintf(output, fmt_v, msecs, csv_sep); - - if (csv_output) - fprintf(output, "%s%s", evsel->unit, csv_sep); - else - fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep); - - fprintf(output, fmt_n, name); - - if (evsel->cgrp) - fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); -} - static int first_shadow_cpu(struct perf_evsel *evsel, int id) { int i; @@ -1241,11 +1201,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, return; } - if (metric_only) - /* nothing */; - else if (nsec_counter(counter)) - nsec_printout(id, nr, counter, uval); - else + if (!metric_only) abs_printout(id, nr, counter, uval); out.print_metric = pm; @@ -1331,7 +1287,7 @@ static void collect_all_aliases(struct perf_evsel *counter, alias->scale != counter->scale || alias->cgrp != counter->cgrp || strcmp(alias->unit, counter->unit) || - nsec_counter(alias) != nsec_counter(counter)) + perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter)) break; alias->merged_stat = true; cb(alias, data, false); @@ -2449,6 +2405,18 @@ static int add_default_attributes(void) return 0; if (transaction_run) { + /* Handle -T as -M transaction. Once platform specific metrics + * support has been added to the json files, all archictures + * will use this approach. To determine transaction support + * on an architecture test for such a metric name. + */ + if (metricgroup__has_metric("transaction")) { + struct option opt = { .value = &evsel_list }; + + return metricgroup__parse_groups(&opt, "transaction", + &metric_events); + } + if (pmu_have_event("cpu", "cycles-ct") && pmu_have_event("cpu", "el-start")) err = parse_events(evsel_list, transaction_attrs, diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index ffdc2769ff9f..d21d8751e749 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -307,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top) hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); hists__fprintf(hists, false, top->print_entries - printed, win_width, - top->min_percent, stdout, symbol_conf.use_callchain); + top->min_percent, stdout, !symbol_conf.use_callchain); } static void prompt_integer(int *target, const char *msg) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6a748eca2edb..88561eed7950 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -291,7 +291,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha { int idx = val - sa->offset; - if (idx < 0 || idx >= sa->nr_entries) + if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL) return scnprintf(bf, size, intfmt, val); return scnprintf(bf, size, "%s", sa->entries[idx]); @@ -761,10 +761,12 @@ static struct syscall_fmt { .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, { .name = "socket", .arg = { [0] = STRARRAY(family, socket_families), - [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, + [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, }, { .name = "socketpair", .arg = { [0] = STRARRAY(family, socket_families), - [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, + [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, }, { .name = "stat", .alias = "newstat", }, { .name = "statx", .arg = { [0] = { .scnprintf = SCA_FDAT, /* fdat */ }, @@ -2990,6 +2992,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str, if (trace__validate_ev_qualifier(trace)) goto out; + trace->trace_syscalls = true; } err = 0; @@ -3045,7 +3048,7 @@ int cmd_trace(int argc, const char **argv) }, .output = stderr, .show_comm = true, - .trace_syscalls = true, + .trace_syscalls = false, .kernel_syscallchains = false, .max_stack = UINT_MAX, }; @@ -3191,13 +3194,7 @@ int cmd_trace(int argc, const char **argv) if (!trace.trace_syscalls && !trace.trace_pgfaults && trace.evlist->nr_entries == 0 /* Was --events used? */) { - pr_err("Please specify something to trace.\n"); - return -1; - } - - if (!trace.trace_syscalls && trace.ev_qualifier) { - pr_err("The -e option can't be used with --no-syscalls.\n"); - goto out; + trace.trace_syscalls = true; } if (output_name != NULL) { diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 10f333e2e825..de28466c0186 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h include/uapi/linux/fcntl.h include/uapi/linux/kcmp.h include/uapi/linux/kvm.h +include/uapi/linux/in.h include/uapi/linux/perf_event.h include/uapi/linux/prctl.h include/uapi/linux/sched.h @@ -35,6 +36,7 @@ arch/s390/include/uapi/asm/ptrace.h arch/s390/include/uapi/asm/sie.h arch/arm/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h +arch/arm64/include/uapi/asm/unistd.h arch/alpha/include/uapi/asm/errno.h arch/mips/include/asm/errno.h arch/mips/include/uapi/asm/errno.h @@ -53,6 +55,7 @@ include/uapi/asm-generic/errno.h include/uapi/asm-generic/errno-base.h include/uapi/asm-generic/ioctls.h include/uapi/asm-generic/mman-common.h +include/uapi/asm-generic/unistd.h ' check_2 () { diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h index dd764ad5efdf..a63aa6241b7f 100644 --- a/tools/perf/include/bpf/bpf.h +++ b/tools/perf/include/bpf/bpf.h @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #ifndef _PERF_BPF_H #define _PERF_BPF_H + +#include <uapi/linux/bpf.h> + #define SEC(NAME) __attribute__((section(NAME), used)) #define probe(function, vars) \ diff --git a/tools/perf/perf.h b/tools/perf/perf.h index a1a97956136f..21bf7f5a3cf5 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -5,6 +5,7 @@ #include <time.h> #include <stdbool.h> #include <linux/types.h> +#include <linux/stddef.h> #include <linux/perf_event.h> extern bool test_attr__enabled; @@ -24,7 +25,9 @@ static inline unsigned long long rdclock(void) return ts.tv_sec * 1000000000ULL + ts.tv_nsec; } +#ifndef MAX_NR_CPUS #define MAX_NR_CPUS 1024 +#endif extern const char *input_name; extern bool perf_host, perf_guest; diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json index bc03c06c3918..752e47eb6977 100644 --- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json +++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json @@ -12,6 +12,21 @@ "ArchStdEvent": "L1D_CACHE_REFILL_WR", }, { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER", + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM", + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN", + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + }, + { "ArchStdEvent": "L1D_TLB_REFILL_RD", }, { @@ -24,9 +39,75 @@ "ArchStdEvent": "L1D_TLB_WR", }, { + "ArchStdEvent": "L2D_TLB_REFILL_RD", + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR", + }, + { + "ArchStdEvent": "L2D_TLB_RD", + }, + { + "ArchStdEvent": "L2D_TLB_WR", + }, + { "ArchStdEvent": "BUS_ACCESS_RD", - }, - { + }, + { "ArchStdEvent": "BUS_ACCESS_WR", - } + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + }, + { + "ArchStdEvent": "MEM_ACCESS_WR", + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + }, + { + "ArchStdEvent": "EXC_UNDEF", + }, + { + "ArchStdEvent": "EXC_SVC", + }, + { + "ArchStdEvent": "EXC_PABORT", + }, + { + "ArchStdEvent": "EXC_DABORT", + }, + { + "ArchStdEvent": "EXC_IRQ", + }, + { + "ArchStdEvent": "EXC_FIQ", + }, + { + "ArchStdEvent": "EXC_SMC", + }, + { + "ArchStdEvent": "EXC_HVC", + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER", + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ", + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ", + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json index 0feedb40f30f..b6b7f29ca831 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json @@ -1,107 +1,125 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1I_L2_SOURCED_WRITES", "BriefDescription": "L1I L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache" }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "L1D_L2_SOURCED_WRITES", "BriefDescription": "L1D L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "L1I_L3_LOCAL_WRITES", "BriefDescription": "L1I L3 Local Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "L1D_L3_LOCAL_WRITES", "BriefDescription": "L1D L3 Local Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "L1I_L3_REMOTE_WRITES", "BriefDescription": "L1I L3 Remote Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L1D_L3_REMOTE_WRITES", "BriefDescription": "L1D L3 Remote Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "L1D_LMEM_SOURCED_WRITES", "BriefDescription": "L1D Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "L1I_LMEM_SOURCED_WRITES", "BriefDescription": "L1I Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "L1I_CACHELINE_INVALIDATES", "BriefDescription": "L1I Cacheline Invalidates", "PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "142", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L2C_STORES_SENT", "BriefDescription": "L2C Stores Sent", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json index 9a002b6967f1..436ce33f1182 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json @@ -1,335 +1,391 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line." }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "DTLB1_HPAGE_WRITES", "BriefDescription": "DTLB1 One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "DTLB1_GPAGE_WRITES", "BriefDescription": "DTLB1 Two-Gigabyte Page Writes", "PublicDescription": "Counter:132 Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page." }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L1D_L2D_SOURCED_WRITES", "BriefDescription": "L1D L2D Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1I_L2I_SOURCED_WRITES", "BriefDescription": "L1I L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "TX_C_TEND", "BriefDescription": "Completed TEND instructions in constrained TX mode", "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TX_NC_TEND", "BriefDescription": "Completed TEND instructions in non-constrained TX mode", "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "L1C_TLB1_MISSES", "BriefDescription": "L1C TLB1 Misses", "PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "L1D_ONNODE_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Node L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "L1D_ONNODE_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Node L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "149", "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "151", "EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "154", "EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "156", "EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "157", "EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "158", "EventName": "L1D_ONNODE_MEM_SOURCED_WRITES", "BriefDescription": "L1D On-Node Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory" }, { + "Unit": "CPU-M-CF", "EventCode": "159", "EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "160", "EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "161", "EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES", "BriefDescription": "L1D On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "162", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "163", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "164", "EventName": "L1I_ONNODE_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "165", "EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "166", "EventName": "L1I_ONNODE_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Node L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "167", "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "168", "EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "169", "EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "170", "EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "171", "EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "172", "EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "173", "EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "174", "EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "175", "EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "176", "EventName": "L1I_ONNODE_MEM_SOURCED_WRITES", "BriefDescription": "L1I On-Node Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory" }, { + "Unit": "CPU-M-CF", "EventCode": "177", "EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "178", "EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "179", "EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES", "BriefDescription": "L1I On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "218", "EventName": "TX_NC_TABORT", "BriefDescription": "Aborted transactions in non-constrained TX mode", "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "219", "EventName": "TX_C_TABORT_NO_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "220", "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "448", "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE", "BriefDescription": "Cycle count with one thread active", "PublicDescription": "Cycle count with one thread active" }, { + "Unit": "CPU-M-CF", "EventCode": "449", "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json index 8f653c9d899d..17fb5241928b 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json @@ -1,47 +1,55 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index aa4dfb46b65b..e7a3524b748f 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -1,317 +1,370 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "Counter:128 Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "DTLB2_WRITES", "BriefDescription": "DTLB2 Writes", "PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "DTLB2_MISSES", "BriefDescription": "DTLB2 Misses", "PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle" }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "DTLB2_HPAGE_WRITES", "BriefDescription": "DTLB2 One-Megabyte Page Writes", "PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "DTLB2_GPAGE_WRITES", "BriefDescription": "DTLB2 Two-Gigabyte Page Writes", "PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB" }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L1D_L2D_SOURCED_WRITES", "BriefDescription": "L1D L2D Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "ITLB2_WRITES", "BriefDescription": "ITLB2 Writes", "PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "ITLB2_MISSES", "BriefDescription": "ITLB2 Misses", "PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1I_L2I_SOURCED_WRITES", "BriefDescription": "L1I L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "TLB2_ENGINES_BUSY", "BriefDescription": "TLB2 Engines Busy", "PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "TX_C_TEND", "BriefDescription": "Completed TEND instructions in constrained TX mode", "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TX_NC_TEND", "BriefDescription": "Completed TEND instructions in non-constrained TX mode", "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "L1C_TLB2_MISSES", "BriefDescription": "L1C TLB2 Misses", "PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D On-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "149", "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "151", "EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D Off-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "154", "EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "156", "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "157", "EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "158", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO", "BriefDescription": "L1D On-Chip L3 Sourced Writes read-only", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "162", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "163", "EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "164", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "165", "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "166", "EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I On-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "167", "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "168", "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "169", "EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I Off-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "170", "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "171", "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "172", "EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "173", "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "174", "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "175", "EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "224", "EventName": "BCD_DFP_EXECUTION_SLOTS", "BriefDescription": "BCD DFP Execution Slots", "PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT" }, { + "Unit": "CPU-M-CF", "EventCode": "225", "EventName": "VX_BCD_EXECUTION_SLOTS", "BriefDescription": "VX BCD Execution Slots", "PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG" }, { + "Unit": "CPU-M-CF", "EventCode": "226", "EventName": "DECIMAL_INSTRUCTIONS", "BriefDescription": "Decimal Instructions", "PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP" }, { + "Unit": "CPU-M-CF", "EventCode": "232", "EventName": "LAST_HOST_TRANSLATIONS", "BriefDescription": "Last host translation done", "PublicDescription": "Last Host Translation done" }, { + "Unit": "CPU-M-CF", "EventCode": "243", "EventName": "TX_NC_TABORT", "BriefDescription": "Aborted transactions in non-constrained TX mode", "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "244", "EventName": "TX_C_TABORT_NO_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "245", "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "448", "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE", "BriefDescription": "Cycle count with one thread active", "PublicDescription": "Cycle count with one thread active" }, { + "Unit": "CPU-M-CF", "EventCode": "449", "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json index b6d7fec7c2e7..b7b42a870bb0 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json @@ -1,143 +1,167 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1D_L2_SOURCED_WRITES", "BriefDescription": "L1D L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "L1I_L2_SOURCED_WRITES", "BriefDescription": "L1I L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L2C_STORES_SENT", "BriefDescription": "L2C Stores Sent", "PublicDescription": "Incremented by one for every store sent to Level-2 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "L1D_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1I_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "DTLB1_HPAGE_WRITES", "BriefDescription": "DTLB1 One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "L1D_LMEM_SOURCED_WRITES", "BriefDescription": "L1D Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "142", "EventName": "L1I_LMEM_SOURCED_WRITES", "BriefDescription": "L1I Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Chip L3 Sourced Writes", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json index 8682126aabb2..162251037219 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json @@ -1,209 +1,244 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "L1D_L2I_SOURCED_WRITES", "BriefDescription": "L1D L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "L1I_L2I_SOURCED_WRITES", "BriefDescription": "L1I L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "L1D_L2D_SOURCED_WRITES", "BriefDescription": "L1D L2D Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "L1D_LMEM_SOURCED_WRITES", "BriefDescription": "L1D Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "L1I_LMEM_SOURCED_WRITES", "BriefDescription": "L1I Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "DTLB1_HPAGE_WRITES", "BriefDescription": "DTLB1 One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "142", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L1D_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "149", "EventName": "TX_NC_TEND", "BriefDescription": "Completed TEND instructions in non-constrained TX mode", "PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "151", "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "154", "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "156", "EventName": "L1I_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "157", "EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "158", "EventName": "TX_C_TEND", "BriefDescription": "Completed TEND instructions in constrained TX mode", "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "159", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "160", "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "161", "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "177", "EventName": "TX_NC_TABORT", "BriefDescription": "Aborted transactions in non-constrained TX mode", "PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "178", "EventName": "TX_C_TABORT_NO_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "179", "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index db3a594ee1e4..68c92bb599ee 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -233,6 +233,8 @@ static struct map { { "QPI LL", "uncore_qpi" }, { "SBO", "uncore_sbox" }, { "iMPH-U", "uncore_arb" }, + { "CPU-M-CF", "cpum_cf" }, + { "CPU-M-SF", "cpum_sf" }, {} }; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index dd850a26d579..d7a5e1b9aa6f 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -385,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest) if (!t->subtest.get_nr) pr_debug("%s:", t->desc); else - pr_debug("%s subtest %d:", t->desc, subtest); + pr_debug("%s subtest %d:", t->desc, subtest + 1); switch (err) { case TEST_OK: diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 61211918bfba..3b97ac018d5a 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1322,6 +1322,14 @@ static int test__intel_pt(struct perf_evlist *evlist) return 0; } +static int test__checkevent_complex_name(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0); + return 0; +} + static int count_tracepoints(void) { struct dirent *events_ent; @@ -1658,6 +1666,11 @@ static struct evlist_test test__events[] = { .check = test__intel_pt, .id = 52, }, + { + .name = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk", + .check = test__checkevent_complex_name, + .id = 53 + } }; static struct evlist_test test__events_pmu[] = { @@ -1676,6 +1689,11 @@ static struct evlist_test test__events_pmu[] = { .check = test__checkevent_pmu_partial_time_callgraph, .id = 2, }, + { + .name = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp", + .check = test__checkevent_complex_name, + .id = 3, + } }; struct terms_test { diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 94e513e62b34..3013ac8f83d0 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -13,11 +13,24 @@ libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g') nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254 +event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?' + +add_libc_inet_pton_event() { + + event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \ + grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))") + + if [ $? -ne 0 -o -z "$event_name" ] ; then + printf "FAIL: could not add event\n" + return 1 + fi +} + trace_libc_inet_pton_backtrace() { expected=`mktemp -u /tmp/expected.XXX` - echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected + echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected case "$(uname -m)" in s390x) @@ -26,6 +39,12 @@ trace_libc_inet_pton_backtrace() { echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; + ppc64|ppc64le) + eventattr='max-stack=4' + echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected + ;; *) eventattr='max-stack=3' echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected @@ -35,7 +54,7 @@ trace_libc_inet_pton_backtrace() { perf_data=`mktemp -u /tmp/perf.data.XXX` perf_script=`mktemp -u /tmp/perf.script.XXX` - perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1 + perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1 perf script -i $perf_data > $perf_script exec 3<$perf_script @@ -46,7 +65,7 @@ trace_libc_inet_pton_backtrace() { echo "$line" | egrep -q "$pattern" if [ $? -ne 0 ] ; then printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line" - exit 1 + return 1 fi done @@ -56,13 +75,20 @@ trace_libc_inet_pton_backtrace() { # even if the perf script output does not match. } +delete_libc_inet_pton_event() { + + if [ -n "$event_name" ] ; then + perf probe -q -d $event_name + fi +} + # Check for IPv6 interface existence ip a sh lo | fgrep -q inet6 || exit 2 skip_if_no_perf_probe && \ -perf probe -q $libc inet_pton && \ +add_libc_inet_pton_event && \ trace_libc_inet_pton_backtrace err=$? rm -f ${perf_data} ${perf_script} ${expected} -perf probe -q -d probe_libc:inet_pton +delete_libc_inet_pton_event exit $err diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build index 66330d4b739b..f528ba35e140 100644 --- a/tools/perf/trace/beauty/Build +++ b/tools/perf/trace/beauty/Build @@ -7,4 +7,5 @@ endif libperf-y += kcmp.o libperf-y += pkey_alloc.o libperf-y += prctl.o +libperf-y += socket.o libperf-y += statx.o diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 984a504d335c..9615af5d412b 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg); #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3 +size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol + size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg); #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh index 2149d3a98e42..9d3816815e60 100755 --- a/tools/perf/trace/beauty/drm_ioctl.sh +++ b/tools/perf/trace/beauty/drm_ioctl.sh @@ -1,13 +1,14 @@ #!/bin/sh -drm_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/ + printf "#ifndef DRM_COMMAND_BASE\n" -grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h +grep "#define DRM_COMMAND_BASE" $header_dir/drm.h printf "#endif\n" printf "static const char *drm_ioctl_cmds[] = {\n" -grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \ +grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \ sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[ ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/ [\2] = "\1",/g' -grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $drm_header_dir/i915_drm.h | \ +grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $header_dir/i915_drm.h | \ sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[ ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh index 40d063b8c082..a3c304caa336 100755 --- a/tools/perf/trace/beauty/kcmp_type.sh +++ b/tools/perf/trace/beauty/kcmp_type.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *kcmp_types[] = {\n" regex='^[[:space:]]+(KCMP_(\w+)),' diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh index bd28817afced..c4699fd46bb6 100755 --- a/tools/perf/trace/beauty/kvm_ioctl.sh +++ b/tools/perf/trace/beauty/kvm_ioctl.sh @@ -1,10 +1,10 @@ #!/bin/sh -kvm_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *kvm_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${kvm_header_dir}/kvm.h | \ +egrep $regex ${header_dir}/kvm.h | \ sed -r "s/$regex/\2 \1/g" | \ egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \ sort | xargs printf "\t[%s] = \"%s\",\n" diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh index 60ef8640ee70..431639eb4d29 100755 --- a/tools/perf/trace/beauty/madvise_behavior.sh +++ b/tools/perf/trace/beauty/madvise_behavior.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/ printf "static const char *madvise_advices[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*' diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh index faea4237c793..6492c74df928 100755 --- a/tools/perf/trace/beauty/perf_ioctl.sh +++ b/tools/perf/trace/beauty/perf_ioctl.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *perf_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*' diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh index 62e51a02b839..e0a51aeb20b2 100755 --- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh +++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/ printf "static const char *pkey_alloc_access_rights[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*' diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh index aad5ab130539..eb511bb5fbd3 100755 --- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh +++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh @@ -1,8 +1,8 @@ #!/bin/sh -sound_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/ printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n" -grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \ +grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \ sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh index b7e9ef6b2f55..6818392968b2 100755 --- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh +++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh @@ -1,8 +1,8 @@ #!/bin/sh -sound_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/ printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n" -grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \ +grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \ sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c new file mode 100644 index 000000000000..65227269384b --- /dev/null +++ b/tools/perf/trace/beauty/socket.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * trace/beauty/socket.c + * + * Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + */ + +#include "trace/beauty/beauty.h" +#include <sys/types.h> +#include <sys/socket.h> + +static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size) +{ +#include "trace/beauty/generated/socket_ipproto_array.c" + static DEFINE_STRARRAY(socket_ipproto); + + return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol); +} + +size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg) +{ + int domain = syscall_arg__val(arg, 0); + + if (domain == AF_INET || domain == AF_INET6) + return socket__scnprintf_ipproto(arg->val, bf, size); + + return syscall_arg__scnprintf_int(bf, size, arg); +} diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh new file mode 100755 index 000000000000..a3cc24633bec --- /dev/null +++ b/tools/perf/trace/beauty/socket_ipproto.sh @@ -0,0 +1,11 @@ +#!/bin/sh + +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ + +printf "static const char *socket_ipproto[] = {\n" +regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*' + +egrep $regex ${header_dir}/in.h | \ + sed -r "s/$regex/\2 \1/g" | \ + sort | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n" diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh index 76f1de697787..0f6a5197d0be 100755 --- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh +++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -1,17 +1,17 @@ #!/bin/sh -vhost_virtio_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *vhost_virtio_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ +egrep $regex ${header_dir}/vhost.h | \ sed -r "s/$regex/\2 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ +egrep $regex ${header_dir}/vhost.h | \ sed -r "s/$regex/\2 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 69b7a28f7a1c..74c4ae1f0a05 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -529,7 +529,7 @@ out: static int hist_entry__fprintf(struct hist_entry *he, size_t size, char *bf, size_t bfsz, FILE *fp, - bool use_callchain) + bool ignore_callchains) { int ret; int callchain_ret = 0; @@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, ret = fprintf(fp, "%s\n", bf); - if (hist_entry__has_callchains(he) && use_callchain) + if (hist_entry__has_callchains(he) && !ignore_callchains) callchain_ret = hist_entry_callchain__fprintf(he, total_period, 0, fp); @@ -755,7 +755,7 @@ int hists__fprintf_headers(struct hists *hists, FILE *fp) size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, - bool use_callchain) + bool ignore_callchains) { struct rb_node *nd; size_t ret = 0; @@ -799,7 +799,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, if (percent < min_pcnt) continue; - ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain); + ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains); if (max_rows && ++nr_rows >= max_rows) break; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index cee658733e2c..3d02ae38ec56 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj) err = bpf_object__load(obj); if (err) { - pr_debug("bpf: load objects failed\n"); + char bf[128]; + libbpf_strerror(err, bf, sizeof(bf)); + pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf); return err; } return 0; diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 7798a2cc8a86..31279a7bd919 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -20,9 +20,10 @@ static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,} static struct comm_str *comm_str__get(struct comm_str *cs) { - if (cs) - refcount_inc(&cs->refcnt); - return cs; + if (cs && refcount_inc_not_zero(&cs->refcnt)) + return cs; + + return NULL; } static void comm_str__put(struct comm_str *cs) @@ -67,9 +68,14 @@ struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root) parent = *p; iter = rb_entry(parent, struct comm_str, rb_node); + /* + * If we race with comm_str__put, iter->refcnt is 0 + * and it will be removed within comm_str__put call + * shortly, ignore it in this search. + */ cmp = strcmp(str, iter->str); - if (!cmp) - return comm_str__get(iter); + if (!cmp && comm_str__get(iter)) + return iter; if (cmp < 0) p = &(*p)->rb_left; diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 4d5fc374e730..938def6d0bb9 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -31,6 +31,8 @@ #endif #endif +#define CS_ETM_INVAL_ADDR 0xdeadbeefdeadbeefUL + struct cs_etm_decoder { void *data; void (*packet_printer)(const char *msg); @@ -261,8 +263,8 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder) decoder->tail = 0; decoder->packet_count = 0; for (i = 0; i < MAX_BUFFER; i++) { - decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL; - decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL; + decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR; decoder->packet_buffer[i].last_instr_taken_branch = false; decoder->packet_buffer[i].exc = false; decoder->packet_buffer[i].exc_ret = false; @@ -295,8 +297,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder, decoder->packet_buffer[et].exc = false; decoder->packet_buffer[et].exc_ret = false; decoder->packet_buffer[et].cpu = *((int *)inode->priv); - decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL; - decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL; + decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR; if (decoder->packet_count == MAX_BUFFER - 1) return OCSD_RESP_WAIT; diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h index 743f5f444304..612b5755f742 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h @@ -23,6 +23,7 @@ struct cs_etm_buffer { }; enum cs_etm_sample_type { + CS_ETM_EMPTY = 0, CS_ETM_RANGE = 1 << 0, CS_ETM_TRACE_ON = 1 << 1, }; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 822ba915d144..2ae640257fdb 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq) static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) { + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + /* * The packet records the execution range with an exclusive end address * @@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) return packet->end_addr - A64_INSTR_SIZE; } +static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet) +{ + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + + return packet->start_addr; +} + static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet) { /* @@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq) be = &bs->entries[etmq->last_branch_pos]; be->from = cs_etm__last_executed_instr(etmq->prev_packet); - be->to = etmq->packet->start_addr; + be->to = cs_etm__first_executed_instr(etmq->packet); /* No support for mispredict */ be->flags.mispred = 0; be->flags.predicted = 1; @@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq) sample.ip = cs_etm__last_executed_instr(etmq->prev_packet); sample.pid = etmq->pid; sample.tid = etmq->tid; - sample.addr = etmq->packet->start_addr; + sample.addr = cs_etm__first_executed_instr(etmq->packet); sample.id = etmq->etm->branches_id; sample.stream_id = etmq->etm->branches_id; sample.period = 1; @@ -897,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) etmq->period_instructions = instrs_over; } - if (etm->sample_branches && - etmq->prev_packet && - etmq->prev_packet->sample_type == CS_ETM_RANGE && - etmq->prev_packet->last_instr_taken_branch) { - ret = cs_etm__synth_branch_sample(etmq); - if (ret) - return ret; + if (etm->sample_branches && etmq->prev_packet) { + bool generate_sample = false; + + /* Generate sample for tracing on packet */ + if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON) + generate_sample = true; + + /* Generate sample for branch taken packet */ + if (etmq->prev_packet->sample_type == CS_ETM_RANGE && + etmq->prev_packet->last_instr_taken_branch) + generate_sample = true; + + if (generate_sample) { + ret = cs_etm__synth_branch_sample(etmq); + if (ret) + return ret; + } } if (etm->sample_branches || etm->synth_opts.last_branch) { @@ -922,10 +945,17 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) static int cs_etm__flush(struct cs_etm_queue *etmq) { int err = 0; + struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet *tmp; + if (!etmq->prev_packet) + return 0; + + /* Handle start tracing packet */ + if (etmq->prev_packet->sample_type == CS_ETM_EMPTY) + goto swap_packet; + if (etmq->etm->synth_opts.last_branch && - etmq->prev_packet && etmq->prev_packet->sample_type == CS_ETM_RANGE) { /* * Generate a last branch event for the branches left in the @@ -939,8 +969,22 @@ static int cs_etm__flush(struct cs_etm_queue *etmq) err = cs_etm__synth_instruction_sample( etmq, addr, etmq->period_instructions); + if (err) + return err; + etmq->period_instructions = 0; + } + + if (etm->sample_branches && + etmq->prev_packet->sample_type == CS_ETM_RANGE) { + err = cs_etm__synth_branch_sample(etmq); + if (err) + return err; + } + +swap_packet: + if (etmq->etm->synth_opts.last_branch) { /* * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for * the next incoming packet. @@ -1020,6 +1064,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq) */ cs_etm__flush(etmq); break; + case CS_ETM_EMPTY: + /* + * Should not receive empty packet, + * report error. + */ + pr_err("CS ETM Trace: empty packet\n"); + return -EINVAL; default: break; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 94fce4f537e9..ddf84b941abf 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -260,6 +260,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) evsel->attr.sample_period = 1; } + if (perf_evsel__is_clock(evsel)) { + /* + * The evsel->unit points to static alias->unit + * so it's ok to use static string in here. + */ + static const char *unit = "msec"; + + evsel->unit = unit; + evsel->scale = 1e-6; + } + return evsel; } @@ -848,6 +859,12 @@ static void apply_config_terms(struct perf_evsel *evsel, } } +static bool is_dummy_event(struct perf_evsel *evsel) +{ + return (evsel->attr.type == PERF_TYPE_SOFTWARE) && + (evsel->attr.config == PERF_COUNT_SW_DUMMY); +} + /* * The enable_on_exec/disabled value strategy: * @@ -1086,6 +1103,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, else perf_evsel__reset_sample_bit(evsel, PERIOD); } + + /* + * For initial_delay, a dummy event is added implicitly. + * The software event will trigger -EOPNOTSUPP error out, + * if BRANCH_STACK bit is set. + */ + if (opts->initial_delay && is_dummy_event(evsel)) + perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); } static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d277930b19a1..973c03167947 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -402,10 +402,13 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel); static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel) { - struct perf_event_attr *attr = &evsel->attr; + return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT); +} - return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) && - (attr->type == PERF_TYPE_SOFTWARE); +static inline bool perf_evsel__is_clock(struct perf_evsel *evsel) +{ + return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || + perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK); } struct perf_attr_details { diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 653ff65aa2c3..5af58aac91ad 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2587,7 +2587,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPR(NUMA_TOPOLOGY, numa_topology, true), FEAT_OPN(BRANCH_STACK, branch_stack, false), FEAT_OPR(PMU_MAPPINGS, pmu_mappings, false), - FEAT_OPN(GROUP_DESC, group_desc, false), + FEAT_OPR(GROUP_DESC, group_desc, false), FEAT_OPN(AUXTRACE, auxtrace, false), FEAT_OPN(STAT, stat, false), FEAT_OPN(CACHE, cache, true), diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 90d4577a92dc..6d7fe44aadc0 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -2,6 +2,7 @@ #ifndef __PERF_HEADER_H #define __PERF_HEADER_H +#include <linux/stddef.h> #include <linux/perf_event.h> #include <sys/types.h> #include <stdbool.h> diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 73049f7f0f60..3badd7f1e1b8 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -181,7 +181,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, - bool use_callchain); + bool ignore_callchains); size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index e7b4a8b513f2..b300a3973448 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -408,23 +408,16 @@ out_err: } /* - * Caller must eventually drop thread->refcnt returned with a successful - * lookup/new thread inserted. + * Front-end cache - TID lookups come in blocks, + * so most of the time we dont have to look up + * the full rbtree: */ -static struct thread *____machine__findnew_thread(struct machine *machine, - struct threads *threads, - pid_t pid, pid_t tid, - bool create) +static struct thread* +__threads__get_last_match(struct threads *threads, struct machine *machine, + int pid, int tid) { - struct rb_node **p = &threads->entries.rb_node; - struct rb_node *parent = NULL; struct thread *th; - /* - * Front-end cache - TID lookups come in blocks, - * so most of the time we dont have to look up - * the full rbtree: - */ th = threads->last_match; if (th != NULL) { if (th->tid == tid) { @@ -435,12 +428,57 @@ static struct thread *____machine__findnew_thread(struct machine *machine, threads->last_match = NULL; } + return NULL; +} + +static struct thread* +threads__get_last_match(struct threads *threads, struct machine *machine, + int pid, int tid) +{ + struct thread *th = NULL; + + if (perf_singlethreaded) + th = __threads__get_last_match(threads, machine, pid, tid); + + return th; +} + +static void +__threads__set_last_match(struct threads *threads, struct thread *th) +{ + threads->last_match = th; +} + +static void +threads__set_last_match(struct threads *threads, struct thread *th) +{ + if (perf_singlethreaded) + __threads__set_last_match(threads, th); +} + +/* + * Caller must eventually drop thread->refcnt returned with a successful + * lookup/new thread inserted. + */ +static struct thread *____machine__findnew_thread(struct machine *machine, + struct threads *threads, + pid_t pid, pid_t tid, + bool create) +{ + struct rb_node **p = &threads->entries.rb_node; + struct rb_node *parent = NULL; + struct thread *th; + + th = threads__get_last_match(threads, machine, pid, tid); + if (th) + return th; + while (*p != NULL) { parent = *p; th = rb_entry(parent, struct thread, rb_node); if (th->tid == tid) { - threads->last_match = th; + threads__set_last_match(threads, th); machine__update_thread_pid(machine, th, pid); return thread__get(th); } @@ -477,7 +515,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, * It is now in the rbtree, get a ref */ thread__get(th); - threads->last_match = th; + threads__set_last_match(threads, th); ++threads->nr; } @@ -1635,7 +1673,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th, struct threads *threads = machine__threads(machine, th->tid); if (threads->last_match == th) - threads->last_match = NULL; + threads__set_last_match(threads, NULL); BUG_ON(refcount_read(&th->refcnt) == 0); if (lock) @@ -2272,6 +2310,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) { struct callchain_cursor *cursor = arg; const char *srcline = NULL; + u64 addr; if (symbol_conf.hide_unresolved && entry->sym == NULL) return 0; @@ -2279,7 +2318,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0) return 0; - srcline = callchain_srcline(entry->map, entry->sym, entry->ip); + /* + * Convert entry->ip from a virtual address to an offset in + * its corresponding binary. + */ + addr = map__map_ip(entry->map, entry->ip); + + srcline = callchain_srcline(entry->map, entry->sym, addr); return callchain_cursor_append(cursor, entry->ip, entry->map, entry->sym, false, NULL, 0, 0, 0, srcline); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 1ddc3d1d0147..a28f9b5cc4ff 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, if (raw) s = (char *)pe->metric_name; else { - if (asprintf(&s, "%s\n\t[%s]", - pe->metric_name, pe->desc) < 0) + if (asprintf(&s, "%s\n%*s%s]", + pe->metric_name, 8, "[", pe->desc) < 0) return; } @@ -490,3 +490,25 @@ out: metricgroup__free_egroups(&group_list); return ret; } + +bool metricgroup__has_metric(const char *metric) +{ + struct pmu_events_map *map = perf_pmu__find_map(NULL); + struct pmu_event *pe; + int i; + + if (!map) + return false; + + for (i = 0; ; i++) { + pe = &map->table[i]; + + if (!pe->name && !pe->metric_group && !pe->metric_name) + break; + if (!pe->metric_expr) + continue; + if (match_metric(pe->metric_name, metric)) + return true; + } + return false; +} diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 06854e125ee7..8a155dba0581 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -28,4 +28,5 @@ int metricgroup__parse_groups(const struct option *opt, struct rblist *metric_events); void metricgroup__print(bool metrics, bool groups, char *filter, bool raw); +bool metricgroup__has_metric(const char *metric); #endif diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 760558dcfd18..cae1a9a39722 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -10,6 +10,7 @@ #define __PERF_NAMESPACES_H #include <sys/types.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include <linux/refcount.h> #include <linux/types.h> diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 3ba6a1742f91..afd68524ffa9 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -652,12 +652,6 @@ static int is_arm_pmu_core(const char *name) if (stat(path, &st) == 0) return 1; - /* Look for cpu sysfs (specific to s390) */ - scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s", - sysfs, name); - if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5)) - return 1; - return 0; } diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 594d14a02b67..99990f5f2512 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -913,11 +913,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ratio = total / avg; print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio); - } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) || - perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) { + } else if (perf_evsel__is_clock(evsel)) { if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) print_metric(ctxp, NULL, "%8.3f", "CPUs utilized", - avg / ratio); + avg / (ratio * evsel->scale)); else print_metric(ctxp, NULL, NULL, "CPUs utilized", 0); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) { diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 0ee7f568d60c..3393d7ee9401 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_powerpc_64; #include <asm/syscalls_32.c> const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID; static const char **syscalltbl_native = syscalltbl_powerpc_32; +#elif defined(__aarch64__) +#include <asm/syscalls.c> +const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID; +static const char **syscalltbl_native = syscalltbl_arm64; #endif struct syscall { diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 538db4e5d1e6..6f318b15950e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -77,7 +77,7 @@ static int entry(u64 ip, struct unwind_info *ui) if (__report_module(&al, ip, ui)) return -1; - e->ip = al.addr; + e->ip = ip; e->map = al.map; e->sym = al.sym; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 6a11bc7e6b27..79f521a552cf 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -575,7 +575,7 @@ static int entry(u64 ip, struct thread *thread, struct addr_location al; e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); - e.ip = al.addr; + e.ip = ip; e.map = al.map; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index d39e4ff7d0bf..a6db83a88e85 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -106,7 +106,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics \fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3.... The system summary is the average of all CPUs in the system. Note that these are software, reflecting what was requested. The hardware counters reflect what was actually achieved. \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. These numbers are from hardware residency counters. \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor. -\fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. +\fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. \fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms. \fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz. \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters. @@ -114,7 +114,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics \fBCorWatt\fP Watts consumed by the core part of the package. \fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors. \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors. -\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. +\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system. Note that the meaning of this field is model specific. For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits. Comparing PkgWatt and PkgTmp to system limits is necessary. \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM. .fi .SH TOO MUCH INFORMATION EXAMPLE diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 4d14bbbf9b63..980bd9d20646 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1163,9 +1163,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_ if (!printed || !summary_only) print_header("\t"); - if (topo.num_cpus > 1) - format_counters(&average.threads, &average.cores, - &average.packages); + format_counters(&average.threads, &average.cores, &average.packages); printed = 1; @@ -1692,7 +1690,7 @@ void get_apic_id(struct thread_data *t) t->x2apic_id = edx; if (debug && (t->apic_id != t->x2apic_id)) - fprintf(stderr, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); + fprintf(outf, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); } /* @@ -2473,55 +2471,43 @@ int get_core_id(int cpu) void set_node_data(void) { - char path[80]; - FILE *filep; - int pkg, node, cpu; - - struct pkg_node_info { - int count; - int min; - } *pni; - - pni = calloc(topo.num_packages, sizeof(struct pkg_node_info)); - if (!pni) - err(1, "calloc pkg_node_count"); - - for (pkg = 0; pkg < topo.num_packages; pkg++) - pni[pkg].min = topo.num_cpus; - - for (node = 0; node <= topo.max_node_num; node++) { - /* find the "first" cpu in the node */ - sprintf(path, "/sys/bus/node/devices/node%d/cpulist", node); - filep = fopen(path, "r"); - if (!filep) - continue; - fscanf(filep, "%d", &cpu); - fclose(filep); - - pkg = cpus[cpu].physical_package_id; - pni[pkg].count++; - - if (node < pni[pkg].min) - pni[pkg].min = node; - } - - for (pkg = 0; pkg < topo.num_packages; pkg++) - if (pni[pkg].count > topo.nodes_per_pkg) - topo.nodes_per_pkg = pni[0].count; - - /* Fake 1 node per pkg for machines that don't - * expose nodes and thus avoid -nan results - */ - if (topo.nodes_per_pkg == 0) - topo.nodes_per_pkg = 1; - - for (cpu = 0; cpu < topo.num_cpus; cpu++) { - pkg = cpus[cpu].physical_package_id; - node = cpus[cpu].physical_node_id; - cpus[cpu].logical_node_id = node - pni[pkg].min; + int pkg, node, lnode, cpu, cpux; + int cpu_count; + + /* initialize logical_node_id */ + for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu) + cpus[cpu].logical_node_id = -1; + + cpu_count = 0; + for (pkg = 0; pkg < topo.num_packages; pkg++) { + lnode = 0; + for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu) { + if (cpus[cpu].physical_package_id != pkg) + continue; + /* find a cpu with an unset logical_node_id */ + if (cpus[cpu].logical_node_id != -1) + continue; + cpus[cpu].logical_node_id = lnode; + node = cpus[cpu].physical_node_id; + cpu_count++; + /* + * find all matching cpus on this pkg and set + * the logical_node_id + */ + for (cpux = cpu; cpux <= topo.max_cpu_num; cpux++) { + if ((cpus[cpux].physical_package_id == pkg) && + (cpus[cpux].physical_node_id == node)) { + cpus[cpux].logical_node_id = lnode; + cpu_count++; + } + } + lnode++; + if (lnode > topo.nodes_per_pkg) + topo.nodes_per_pkg = lnode; + } + if (cpu_count >= topo.max_cpu_num) + break; } - free(pni); - } int get_physical_node_id(struct cpu_topology *thiscpu) @@ -4471,7 +4457,9 @@ void process_cpuid() family = (fms >> 8) & 0xf; model = (fms >> 4) & 0xf; stepping = fms & 0xf; - if (family == 6 || family == 0xf) + if (family == 0xf) + family += (fms >> 20) & 0xff; + if (family >= 6) model += ((fms >> 16) & 0xf) << 4; if (!quiet) { @@ -4840,16 +4828,8 @@ void topology_probe() siblings = get_thread_siblings(&cpus[i]); if (siblings > max_siblings) max_siblings = siblings; - if (cpus[i].thread_id != -1) + if (cpus[i].thread_id == 0) topo.num_cores++; - - if (debug > 1) - fprintf(outf, - "cpu %d pkg %d node %d core %d thread %d\n", - i, cpus[i].physical_package_id, - cpus[i].physical_node_id, - cpus[i].physical_core_id, - cpus[i].thread_id); } topo.cores_per_node = max_core_id + 1; @@ -4875,6 +4855,20 @@ void topology_probe() topo.threads_per_core = max_siblings; if (debug > 1) fprintf(outf, "max_siblings %d\n", max_siblings); + + if (debug < 1) + return; + + for (i = 0; i <= topo.max_cpu_num; ++i) { + fprintf(outf, + "cpu %d pkg %d node %d lnode %d core %d thread %d\n", + i, cpus[i].physical_package_id, + cpus[i].physical_node_id, + cpus[i].logical_node_id, + cpus[i].physical_core_id, + cpus[i].thread_id); + } + } void @@ -5102,7 +5096,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 18.06.20" + fprintf(outf, "turbostat version 18.07.27" " - Len Brown <lenb@kernel.org>\n"); } diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 7a6214e9ae58..a362e3d7abc6 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -105,7 +105,7 @@ $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) -BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM) +BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') ifneq ($(BTF_LLC_PROBE),) ifneq ($(BTF_PAHOLE_PROBE),) diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index f2f28b6c8915..810de20e8e26 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -158,6 +158,15 @@ struct bpf_map_def { unsigned int numa_node; }; +#define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val) \ + struct ____btf_map_##name { \ + type_key key; \ + type_val value; \ + }; \ + struct ____btf_map_##name \ + __attribute__ ((section(".maps." #name), used)) \ + ____btf_map_##name = { } + static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) = (void *) BPF_FUNC_skb_load_bytes; static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) = diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 3619f3023088..ffdd27737c9e 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -247,6 +247,34 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 4, }, +{ + .descr = "struct test #3 Invalid member offset", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int64 */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8), + + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 16), + BTF_MEMBER_ENC(NAME_TBD, 1, 64), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* int64 n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0", + .str_sec_size = sizeof("\0A\0m\0n\0"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "struct_test3_map", + .key_size = sizeof(int), + .value_size = 16, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid member bits_offset", +}, + /* Test member exceeds the size of struct. * * struct A { @@ -479,7 +507,7 @@ static struct btf_raw_test raw_tests[] = { .key_size = sizeof(int), .value_size = sizeof(void *) * 4, .key_type_id = 1, - .value_type_id = 4, + .value_type_id = 5, .max_entries = 4, }, @@ -1264,6 +1292,88 @@ static struct btf_raw_test raw_tests[] = { .err_str = "type != 0", }, +{ + .descr = "arraymap invalid btf key (a bit field)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* 32 bit int with 32 bit offset */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 32, 32, 8), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 2, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + +{ + .descr = "arraymap invalid btf key (!= 32 bits)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* 16 bit int with 0 bit offset */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 16, 2), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 2, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + +{ + .descr = "arraymap invalid btf value (too small)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + /* btf_value_size < map->value_size */ + .value_size = sizeof(__u64), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + +{ + .descr = "arraymap invalid btf value (too big)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + /* btf_value_size > map->value_size */ + .value_size = sizeof(__u16), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + }; /* struct btf_raw_test raw_tests[] */ static const char *get_next_str(const char *start, const char *end) @@ -2023,7 +2133,7 @@ static struct btf_raw_test pprint_test = { BTF_ENUM_ENC(NAME_TBD, 2), BTF_ENUM_ENC(NAME_TBD, 3), /* struct pprint_mapv */ /* [16] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 28), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 32), BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */ BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */ BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */ diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c index 8c7ca096ecf2..b21b876f475d 100644 --- a/tools/testing/selftests/bpf/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/test_btf_haskv.c @@ -10,11 +10,6 @@ struct ipv_counts { unsigned int v6; }; -typedef int btf_map_key; -typedef struct ipv_counts btf_map_value; -btf_map_key dumm_key; -btf_map_value dummy_value; - struct bpf_map_def SEC("maps") btf_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(int), @@ -22,6 +17,8 @@ struct bpf_map_def SEC("maps") btf_map = { .max_entries = 4, }; +BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts); + struct dummy_tracepoint_args { unsigned long long pad; struct sock *sock; diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh index 270fa8f49573..785eabf2a593 100755 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -115,14 +115,14 @@ ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65 -ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF obj test_lwt_seg6local.o sec add_egr_x dev veth4 +ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4 -ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF obj test_lwt_seg6local.o sec pop_egr dev veth6 +ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6 ip netns exec ns4 ip -6 addr add fc42::1 dev lo ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87 ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 -ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF obj test_lwt_seg6local.o sec inspect_t dev veth8 +ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8 ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 9e78df207919..0c7d9e556b47 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -354,7 +354,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, while (s->bytes_recvd < total_bytes) { if (txmsg_cork) { timeout.tv_sec = 0; - timeout.tv_usec = 1000; + timeout.tv_usec = 300000; } else { timeout.tv_sec = 1; timeout.tv_usec = 0; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 2ecd27b670d7..41106d9d5cc7 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -4975,6 +4975,24 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_LWT_XMIT, }, { + "make headroom for LWT_XMIT", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_2, 34), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_skb_change_head), + /* split for s390 to succeed */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, 42), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_skb_change_head), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_LWT_XMIT, + }, + { "invalid access of tc_classid for LWT_IN", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, @@ -11987,6 +12005,46 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_XDP, }, { + "xadd/w check whether src/dst got mangled, 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3), + BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .retval = 3, + }, + { + "xadd/w check whether src/dst got mangled, 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3), + BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .retval = 3, + }, + { "bpf_get_stack return R0 within range", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), @@ -12554,8 +12612,11 @@ static void do_test_single(struct bpf_test *test, bool unpriv, } if (fd_prog >= 0) { + __u8 tmp[TEST_DATA_LEN << 2]; + __u32 size_tmp = sizeof(tmp); + err = bpf_prog_test_run(fd_prog, 1, test->data, - sizeof(test->data), NULL, NULL, + sizeof(test->data), tmp, &size_tmp, &retval, NULL); if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) { printf("Unexpected bpf_prog_test_run error\n"); diff --git a/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc new file mode 100644 index 000000000000..3b1f45e13a2e --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc @@ -0,0 +1,28 @@ +#!/bin/sh +# description: Snapshot and tracing setting +# flags: instance + +[ ! -f snapshot ] && exit_unsupported + +echo "Set tracing off" +echo 0 > tracing_on + +echo "Allocate and take a snapshot" +echo 1 > snapshot + +# Since trace buffer is empty, snapshot is also empty, but allocated +grep -q "Snapshot is allocated" snapshot + +echo "Ensure keep tracing off" +test `cat tracing_on` -eq 0 + +echo "Set tracing on" +echo 1 > tracing_on + +echo "Take a snapshot again" +echo 1 > snapshot + +echo "Ensure keep tracing on" +test `cat tracing_on` -eq 1 + +exit 0 diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 78245d60d8bc..0f45633bd634 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -740,13 +740,6 @@ ipv6_rt_add() run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" log_test $? 2 "Attempt to add duplicate route - reject route" - # iproute2 prepend only sets NLM_F_CREATE - # - adds a new route; does NOT convert existing route to ECMP - add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" - run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2" - check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024" - log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)" - # route append with same prefix adds a new route # - iproute2 sets NLM_F_CREATE | NLM_F_APPEND add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" @@ -754,27 +747,6 @@ ipv6_rt_add() check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" log_test $? 0 "Append nexthop to existing route - gw" - add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" - run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3" - check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1" - log_test $? 0 "Append nexthop to existing route - dev only" - - # multipath route can not have a nexthop that is a reject route - add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" - run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64" - log_test $? 2 "Append nexthop to existing route - reject route" - - # reject route can not be converted to multipath route - run_cmd "$IP -6 ro flush 2001:db8:104::/64" - run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" - run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2" - log_test $? 2 "Append nexthop to existing reject route - gw" - - run_cmd "$IP -6 ro flush 2001:db8:104::/64" - run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" - run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3" - log_test $? 2 "Append nexthop to existing reject route - dev only" - # insert mpath directly add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" @@ -819,13 +791,6 @@ ipv6_rt_replace_single() check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" log_test $? 0 "Single path with multipath" - # single path with reject - # - add_initial_route6 "nexthop via 2001:db8:101::2" - run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64" - check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024" - log_test $? 0 "Single path with reject route" - # single path with single path using MULTIPATH attribute # add_initial_route6 "via 2001:db8:101::2" @@ -873,12 +838,6 @@ ipv6_rt_replace_mpath() check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" log_test $? 0 "Multipath with single path via multipath attribute" - # multipath with reject - add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" - run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64" - check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024" - log_test $? 0 "Multipath with reject route" - # route replace fails - invalid nexthop 1 add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3" diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 77f762780199..e8c5dff448eb 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -402,7 +402,7 @@ int main(int argc, char *argv[]) exit(1); } - fd = socket(AF_INET6, SOCK_STREAM, 0); + fd = socket(cfg_family, SOCK_STREAM, 0); if (fd == -1) { perror("socket"); exit(1); diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index 792fa4d0285e..850767befa47 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -35,9 +35,6 @@ run_udp() { echo "udp gso" run_in_netns ${args} -S - - echo "udp gso zerocopy" - run_in_netns ${args} -S -z } run_tcp() { diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index c15f270e121d..65541c21a544 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -1,6 +1,6 @@ #!/bin/bash # -# Usage: configinit.sh config-spec-file [ build output dir ] +# Usage: configinit.sh config-spec-file build-output-dir results-dir # # Create a .config file from the spec file. Run from the kernel source tree. # Exits with 0 if all went well, with 1 if all went well but the config @@ -40,20 +40,18 @@ mkdir $T c=$1 buildloc=$2 +resdir=$3 builddir= -if test -n $buildloc +if echo $buildloc | grep -q '^O=' then - if echo $buildloc | grep -q '^O=' + builddir=`echo $buildloc | sed -e 's/^O=//'` + if test ! -d $builddir then - builddir=`echo $buildloc | sed -e 's/^O=//'` - if test ! -d $builddir - then - mkdir $builddir - fi - else - echo Bad build directory: \"$buildloc\" - exit 2 + mkdir $builddir fi +else + echo Bad build directory: \"$buildloc\" + exit 2 fi sed -e 's/^\(CONFIG[0-9A-Z_]*\)=.*$/grep -v "^# \1" |/' < $c > $T/u.sh @@ -61,12 +59,12 @@ sed -e 's/^\(CONFIG[0-9A-Z_]*=\).*$/grep -v \1 |/' < $c >> $T/u.sh grep '^grep' < $T/u.sh > $T/upd.sh echo "cat - $c" >> $T/upd.sh make mrproper -make $buildloc distclean > $builddir/Make.distclean 2>&1 -make $buildloc $TORTURE_DEFCONFIG > $builddir/Make.defconfig.out 2>&1 +make $buildloc distclean > $resdir/Make.distclean 2>&1 +make $buildloc $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 mv $builddir/.config $builddir/.config.sav sh $T/upd.sh < $builddir/.config.sav > $builddir/.config cp $builddir/.config $builddir/.config.new -yes '' | make $buildloc oldconfig > $builddir/Make.oldconfig.out 2> $builddir/Make.oldconfig.err +yes '' | make $buildloc oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err # verify new config matches specification. configcheck.sh $builddir/.config $c diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 34d126734cde..9115fcdb5617 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -2,7 +2,7 @@ # # Build a kvm-ready Linux kernel from the tree in the current directory. # -# Usage: kvm-build.sh config-template build-dir +# Usage: kvm-build.sh config-template build-dir resdir # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by @@ -29,6 +29,7 @@ then exit 1 fi builddir=${2} +resdir=${3} T=${TMPDIR-/tmp}/test-linux.sh.$$ trap 'rm -rf $T' 0 @@ -41,19 +42,19 @@ CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_CONSOLE=y ___EOF___ -configinit.sh $T/config O=$builddir +configinit.sh $T/config O=$builddir $resdir retval=$? if test $retval -gt 1 then exit 2 fi ncpus=`cpus2use.sh` -make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $builddir/Make.out 2>&1 +make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $resdir/Make.out 2>&1 retval=$? -if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out +if test $retval -ne 0 || grep "rcu[^/]*": < $resdir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $resdir/Make.out then echo Kernel build error - egrep "Stop|Error|error:|warning:" < $builddir/Make.out + egrep "Stop|Error|error:|warning:" < $resdir/Make.out echo Run aborted. exit 3 fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index 477ecb1293ab..0fa8a61ccb7b 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -70,4 +70,5 @@ else else print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i fi + echo $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i > $i/console.log.rcu.diags fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index c27e97824163..c9bab57a77eb 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -39,6 +39,7 @@ do head -1 $resdir/log fi TORTURE_SUITE="`cat $i/../TORTURE_SUITE`" + rm -f $i/console.log.*.diags kvm-recheck-${TORTURE_SUITE}.sh $i if test -f "$i/console.log" then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index c5b0f94341d9..f7247ee00514 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -98,14 +98,15 @@ then ln -s $base_resdir/.config $resdir # for kvm-recheck.sh # Arch-independent indicator touch $resdir/builtkernel -elif kvm-build.sh $T/Kc2 $builddir +elif kvm-build.sh $T/Kc2 $builddir $resdir then # Had to build a kernel for this test. QEMU="`identify_qemu $builddir/vmlinux`" BOOT_IMAGE="`identify_boot_image $QEMU`" - cp $builddir/Make*.out $resdir cp $builddir/vmlinux $resdir cp $builddir/.config $resdir + cp $builddir/Module.symvers $resdir > /dev/null || : + cp $builddir/System.map $resdir > /dev/null || : if test -n "$BOOT_IMAGE" then cp $builddir/$BOOT_IMAGE $resdir diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 56610dbbdf73..5a7a62d76a50 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -347,7 +347,7 @@ function dump(first, pastlast, batchnum) print "needqemurun=" jn=1 for (j = first; j < pastlast; j++) { - builddir=KVM "/b" jn + builddir=KVM "/b1" cpusr[jn] = cpus[j]; if (cfrep[cf[j]] == "") { cfr[jn] = cf[j]; diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 17293436f551..84933f6aed77 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -163,6 +163,13 @@ then print_warning Summary: $summary cat $T.diags >> $file.diags fi +for i in $file.*.diags +do + if test -f "$i" + then + cat $i >> $file.diags + fi +done if ! test -s $file.diags then rm -f $file.diags diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot index 5d2cc0bd50a0..5c3213cc3ad7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot @@ -1,5 +1,5 @@ -rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30 -rcutree.gp_preinit_delay=3 +rcutorture.onoff_interval=200 rcutorture.onoff_holdoff=30 +rcutree.gp_preinit_delay=12 rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot deleted file mode 100644 index 883149b5f2d1..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot +++ /dev/null @@ -1 +0,0 @@ -rcutree.rcu_fanout_exact=1 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh index 24ec91041957..7bab8246392b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh @@ -39,7 +39,7 @@ rcutorture_param_onoff () { if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2" then echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2 - echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30 + echo rcutorture.onoff_interval=1000 rcutorture.onoff_holdoff=30 fi } diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c index ca6cd146aafe..dcf73c5dab6e 100644 --- a/tools/testing/selftests/timers/raw_skew.c +++ b/tools/testing/selftests/timers/raw_skew.c @@ -134,6 +134,11 @@ int main(int argv, char **argc) printf(" %lld.%i(act)", ppm/1000, abs((int)(ppm%1000))); if (llabs(eppm - ppm) > 1000) { + if (tx1.offset || tx2.offset || + tx1.freq != tx2.freq || tx1.tick != tx2.tick) { + printf(" [SKIP]\n"); + return ksft_exit_skip("The clock was adjusted externally. Shutdown NTPd or other time sync daemons\n"); + } printf(" [FAILED]\n"); return ksft_exit_fail(); } diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c index 95dd14648ba5..0f395dfb7774 100644 --- a/tools/usb/ffs-test.c +++ b/tools/usb/ffs-test.c @@ -44,12 +44,25 @@ /******************** Little Endian Handling ********************************/ -#define cpu_to_le16(x) htole16(x) -#define cpu_to_le32(x) htole32(x) +/* + * cpu_to_le16/32 are used when initializing structures, a context where a + * function call is not allowed. To solve this, we code cpu_to_le16/32 in a way + * that allows them to be used when initializing structures. + */ + +#if __BYTE_ORDER == __LITTLE_ENDIAN +#define cpu_to_le16(x) (x) +#define cpu_to_le32(x) (x) +#else +#define cpu_to_le16(x) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8)) +#define cpu_to_le32(x) \ + ((((x) & 0xff000000u) >> 24) | (((x) & 0x00ff0000u) >> 8) | \ + (((x) & 0x0000ff00u) << 8) | (((x) & 0x000000ffu) << 24)) +#endif + #define le32_to_cpu(x) le32toh(x) #define le16_to_cpu(x) le16toh(x) - /******************** Messages and Errors ***********************************/ static const char argv0[] = "ffs-test"; diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h index 0ac3caf90877..d0351f83aebe 100644 --- a/tools/virtio/asm/barrier.h +++ b/tools/virtio/asm/barrier.h @@ -13,8 +13,8 @@ } while (0); /* Weak barriers should be used. If not - it's a bug */ # define mb() abort() -# define rmb() abort() -# define wmb() abort() +# define dma_rmb() abort() +# define dma_wmb() abort() #else #error Please fill in barrier macros #endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index fca8381bbe04..fb22bccfbc8a 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -52,6 +52,11 @@ static inline void *kmalloc(size_t s, gfp_t gfp) return __kmalloc_fake; return malloc(s); } +static inline void *kmalloc_array(unsigned n, size_t s, gfp_t gfp) +{ + return kmalloc(n * s, gfp); +} + static inline void *kzalloc(size_t s, gfp_t gfp) { void *p = kmalloc(s, gfp); diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 04e554cae3a2..108250e4d376 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -604,7 +604,7 @@ void kvm_arm_resume_guest(struct kvm *kvm) kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.pause = false; - swake_up(kvm_arch_vcpu_wq(vcpu)); + swake_up_one(kvm_arch_vcpu_wq(vcpu)); } } @@ -612,7 +612,7 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu) { struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); - swait_event_interruptible(*wq, ((!vcpu->arch.power_off) && + swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) && (!vcpu->arch.pause))); if (vcpu->arch.power_off || vcpu->arch.pause) { diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index c95ab4c5a475..9b73d3ad918a 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -155,7 +155,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) smp_mb(); /* Make sure the above is visible */ wq = kvm_arch_vcpu_wq(vcpu); - swake_up(wq); + swake_up_one(wq); return PSCI_RET_SUCCESS; } diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 57bcb27dcf30..23c2519c5b32 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -107,7 +107,7 @@ static void async_pf_execute(struct work_struct *work) trace_kvm_async_pf_completed(addr, gva); if (swq_has_sleeper(&vcpu->wq)) - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); mmput(mm); kvm_put_kvm(vcpu->kvm); diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 90d30fbe95ae..b20b751286fc 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -119,8 +119,12 @@ irqfd_shutdown(struct work_struct *work) { struct kvm_kernel_irqfd *irqfd = container_of(work, struct kvm_kernel_irqfd, shutdown); + struct kvm *kvm = irqfd->kvm; u64 cnt; + /* Make sure irqfd has been initalized in assign path. */ + synchronize_srcu(&kvm->irq_srcu); + /* * Synchronize with the wait-queue and unhook ourselves to prevent * further events. @@ -387,7 +391,6 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) idx = srcu_read_lock(&kvm->irq_srcu); irqfd_update(kvm, irqfd); - srcu_read_unlock(&kvm->irq_srcu, idx); list_add_tail(&irqfd->list, &kvm->irqfds.items); @@ -402,11 +405,6 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) if (events & EPOLLIN) schedule_work(&irqfd->inject); - /* - * do not drop the file until the irqfd is fully initialized, otherwise - * we might race against the EPOLLHUP - */ - fdput(f); #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS if (kvm_arch_has_irq_bypass()) { irqfd->consumer.token = (void *)irqfd->eventfd; @@ -421,6 +419,13 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) } #endif + srcu_read_unlock(&kvm->irq_srcu, idx); + + /* + * do not drop the file until the irqfd is fully initialized, otherwise + * we might race against the EPOLLHUP + */ + fdput(f); return 0; fail: diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8b47507faab5..3d233ebfbee9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2172,7 +2172,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) kvm_arch_vcpu_blocking(vcpu); for (;;) { - prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); if (kvm_vcpu_check_block(vcpu) < 0) break; @@ -2214,7 +2214,7 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) wqp = kvm_arch_vcpu_wq(vcpu); if (swq_has_sleeper(wqp)) { - swake_up(wqp); + swake_up_one(wqp); ++vcpu->stat.halt_wakeup; return true; } |
