diff options
856 files changed, 29245 insertions, 10758 deletions
@@ -2478,12 +2478,11 @@ S: D-90453 Nuernberg S: Germany N: Arnaldo Carvalho de Melo -E: acme@ghostprotocols.net +E: acme@kernel.org E: arnaldo.melo@gmail.com E: acme@redhat.com -W: http://oops.ghostprotocols.net:81/blog/ P: 1024D/9224DF01 D5DF E3BB E3C8 BCBB F8AD 841A B6AB 4681 9224 DF01 -D: IPX, LLC, DCCP, cyc2x, wl3501_cs, net/ hacks +D: tools/, IPX, LLC, DCCP, cyc2x, wl3501_cs, net/ hacks S: Brazil N: Karsten Merker diff --git a/Documentation/ABI/testing/sysfs-devices-edac b/Documentation/ABI/testing/sysfs-devices-edac index 6568e0010e1a..46ff929fd52a 100644 --- a/Documentation/ABI/testing/sysfs-devices-edac +++ b/Documentation/ABI/testing/sysfs-devices-edac @@ -138,3 +138,20 @@ Contact: Mauro Carvalho Chehab <m.chehab@samsung.com> Description: This attribute file will display what type of memory is currently on this csrow. Normally, either buffered or unbuffered memory (for example, Unbuffered-DDR3). + +What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_ce_count +Date: October 2016 +Contact: linux-edac@vger.kernel.org +Description: This attribute file displays the total count of correctable + errors that have occurred on this DIMM. This count is very important + to examine. CEs provide early indications that a DIMM is beginning + to fail. This count field should be monitored for non-zero values + and report such information to the system administrator. + +What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_ue_count +Date: October 2016 +Contact: linux-edac@vger.kernel.org +Description: This attribute file displays the total count of uncorrectable + errors that have occurred on this DIMM. If panic_on_ue is set, this + counter will not have a chance to increment, since EDAC will panic the + system diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html index 7eb47ac25ad7..d583c653a703 100644 --- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html +++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html @@ -4,7 +4,7 @@ <head><title>A Tour Through TREE_RCU's Data Structures [LWN.net]</title> <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1"> - <p>January 27, 2016</p> + <p>December 18, 2016</p> <p>This article was contributed by Paul E. McKenney</p> <h3>Introduction</h3> @@ -31,9 +31,6 @@ to each other. Accessor Functions</a> </ol> -At the end we have the -<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>. - <h3><a name="Data-Structure Relationships">Data-Structure Relationships</a></h3> <p>RCU is for all intents and purposes a large state machine, and its diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/ExpRCUFlow.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpRCUFlow.svg new file mode 100644 index 000000000000..7c6c90bd02c9 --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpRCUFlow.svg @@ -0,0 +1,830 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:39:46 2015 --> + +<!-- Magnification: 3.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="952.6817" + height="1219.6219" + viewBox="-66 -66 12729.905 16296.808" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="ExpRCUFlow.svg"> + <metadata + id="metadata94"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs92"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path4146" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0" + refX="0" + id="Arrow1Mend" + style="overflow:visible"> + <path + id="path3852" + d="M 0,0 5,-5 -12.5,0 5,5 0,0 z" + style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt" + transform="matrix(-0.4,0,0,-0.4,-4,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0" + refX="0" + id="Arrow1Mend-9" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path3852-7" + d="M 0,0 5,-5 -12.5,0 5,5 0,0 z" + style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt" + transform="matrix(-0.4,0,0,-0.4,-4,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-7" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-6" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-1" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-16" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-8" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-160" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-5" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-78" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-66" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-8" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-56" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-19" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-89" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-85" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-3" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-73" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-55" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-5" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-88" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-198" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-2" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-22" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="marker5072" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path5074" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-87" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-63" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-6" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-26" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-0" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-51" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="1090" + inkscape:window-height="1148" + id="namedview90" + showgrid="true" + inkscape:zoom="0.80021373" + inkscape:cx="462.49289" + inkscape:cy="623.19585" + inkscape:window-x="557" + inkscape:window-y="24" + inkscape:window-maximized="0" + inkscape:current-layer="g4" + inkscape:snap-grids="false" + fit-margin-top="5" + fit-margin-right="5" + fit-margin-bottom="5" + fit-margin-left="5" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4" + transform="translate(23.312813,523.41305)"> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line --> + <!-- Arrowhead on XXXpoint 11475 2250 - 11475 3465--> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line --> + <!-- Arrowhead on XXXpoint 11475 5625 - 11475 6840--> + <!-- Line --> + <!-- Arrowhead on XXXpoint 7875 225 - 10665 225--> + <!-- Line --> + <!-- Arrowhead on XXXpoint 9675 675 - 7785 675--> + <!-- Line --> + <!-- Arrowhead on XXXpoint 9675 4725 - 10665 4725--> + <!-- Line --> + <!-- Arrowhead on XXXpoint 9225 5175 - 10665 5175--> + <!-- Line --> + <!-- Arrowhead on XXXpoint 8775 11475 - 10665 11475--> + <!-- Line: box --> + <!-- Line --> + <!-- Arrowhead on XXXpoint 11475 9000 - 11475 10215--> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <g + id="g4104" + transform="translate(-1068.9745,0)"> + <rect + transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)" + y="-7383.8755" + x="-6124.8989" + height="1966.2251" + width="1953.6969" + id="rect3032-1-0" + style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <text + sodipodi:linespacing="125%" + id="text4098" + y="818.40338" + x="8168.2671" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="818.40338" + x="8168.2671" + id="tspan4100" + sodipodi:role="line">Idle or</tspan><tspan + id="tspan4102" + y="1152.4579" + x="8168.2671" + sodipodi:role="line">offline?</tspan></text> + </g> + <g + id="g4114" + transform="translate(0,147.96969)"> + <rect + id="rect6" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1475.6636" + width="4401.7612" + y="0" + x="0" /> + <text + sodipodi:linespacing="125%" + id="text4110" + y="835.11212" + x="2206.4917" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="835.11212" + x="2206.4917" + id="tspan4112" + sodipodi:role="line">CPU N Start</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="M 4432.5052,897.4924 5684.8749,880.79414" + id="path4119" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="M 8503.0006,874.12161 9755.3703,857.42334" + id="path4119-8" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <text + xml:space="preserve" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="8617.0977" + y="705.50983" + id="text4593" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4595" + x="8617.0977" + y="705.50983">Y</tspan></text> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9" + transform="translate(9722.4732,131.27105)"> + <rect + id="rect6-0" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="0" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5" + y="835.11212" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="835.11212" + x="1460.1007" + id="tspan4112-9" + sodipodi:role="line">Done</tspan></text> + </g> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-5" + transform="translate(0,3705.3456)"> + <rect + id="rect6-1" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1475.6636" + width="4401.7612" + y="0" + x="0" /> + <text + sodipodi:linespacing="125%" + id="text4110-9" + y="835.11212" + x="2206.4917" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="835.11212" + x="2206.4917" + sodipodi:role="line" + id="tspan4776">Send IPI to CPU N</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="M 7102.5627,2263.5171 4430.8404,3682.8694" + id="path4119-3" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4104-1" + transform="translate(-1065.3349,6403.5782)"> + <rect + transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)" + y="-7383.8755" + x="-6124.8989" + height="1966.2251" + width="1953.6969" + id="rect3032-1-0-6" + style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <text + sodipodi:linespacing="125%" + id="text4098-3" + y="482.00006" + x="8168.2671" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + id="tspan4102-8" + y="482.00006" + x="8168.2671" + sodipodi:role="line">In RCU</tspan><tspan + y="816.05457" + x="8168.2671" + sodipodi:role="line" + id="tspan4833">read-side</tspan><tspan + y="1150.109" + x="8168.2671" + sodipodi:role="line" + id="tspan4835">critical</tspan><tspan + y="1484.1636" + x="8168.2671" + sodipodi:role="line" + id="tspan4837">section?</tspan></text> + </g> + <text + xml:space="preserve" + style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="6463.0864" + y="2285.6765" + id="text4593-0" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4595-6" + x="6463.0864" + y="2285.6765">N</tspan></text> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654108, 80.17308215;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 2189.1897,5219.361 16.6983,1252.3697" + id="path4119-0" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-5-2" + transform="translate(0,6551.5479)"> + <rect + id="rect6-1-7" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1475.6636" + width="4401.7612" + y="0" + x="0" /> + <text + sodipodi:linespacing="125%" + id="text4110-9-5" + y="835.11212" + x="2206.4917" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="835.11212" + x="2206.4917" + sodipodi:role="line" + id="tspan4776-5">IPI Handler</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="m 4432.5052,7297.9678 1252.3697,-16.6982" + id="path4119-2" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="m 8503.0013,7278.6595 1252.369,-16.6982" + id="path4119-8-7" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <text + xml:space="preserve" + style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="8617.0977" + y="7110.0186" + id="text4593-4" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4595-0" + x="8617.0977" + y="7110.0186">N</tspan></text> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3" + transform="translate(9722.4732,6535.809)"> + <rect + id="rect6-0-7" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7" + y="503.71591" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="503.71591" + x="1460.1007" + id="tspan4112-9-0" + sodipodi:role="line">Report CPU</tspan><tspan + y="837.77039" + x="1460.1007" + sodipodi:role="line" + id="tspan4923">Quiescent</tspan><tspan + y="1171.825" + x="1460.1007" + sodipodi:role="line" + id="tspan4925">State</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654335, 80.17308669;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 7102.5627,8725.7454 16.6983,1252.3697" + id="path4119-0-0" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <text + xml:space="preserve" + style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="6797.0522" + y="9018.6807" + id="text4593-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4595-2" + x="6797.0522" + y="9018.6807">Y</tspan></text> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3-8" + transform="translate(-80.17308,11381.108)"> + <rect + id="rect6-0-7-5" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7-6" + y="841.88086" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="841.88086" + x="1460.1007" + sodipodi:role="line" + id="tspan4925-1">rcu_read_unlock()</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654562, 80.17309124;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 1362.6256,10071.26 16.6983,1252.369" + id="path4119-0-0-7" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 1362.6256,12883.919 16.6983,1252.369" + id="path4119-0-0-7-7" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3-8-1" + transform="translate(9722.4732,11389.458)"> + <rect + id="rect6-0-7-5-1" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7-6-2" + y="841.88086" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="841.88086" + x="1460.1007" + sodipodi:role="line" + id="tspan4925-1-2">Context Switch</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654789, 80.17309578;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 11165.272,10071.26 16.698,1252.369" + id="path4119-0-0-7-8" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3-9" + transform="translate(-80.17308,14163.046)"> + <rect + id="rect6-0-7-1" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7-3" + y="503.71591" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="503.71591" + x="1460.1007" + id="tspan4112-9-0-4" + sodipodi:role="line">Report CPU</tspan><tspan + y="837.77039" + x="1460.1007" + sodipodi:role="line" + id="tspan4923-3">and Task</tspan><tspan + y="1171.825" + x="1460.1007" + sodipodi:role="line" + id="tspan4925-9">Quiescent States</tspan></text> + </g> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3-8-1-8" + transform="translate(5663.2978,11389.458)"> + <rect + id="rect6-0-7-5-1-1" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7-6-2-4" + y="841.88086" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="841.88086" + x="1460.1007" + sodipodi:role="line" + id="tspan4925-1-2-4">Enqueue Task</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="M 9827.612,12141.988 8575.243,12125.29" + id="path4119-8-7-5" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 7106.0965,12818.962 16.6983,1252.369" + id="path4119-0-0-7-7-5" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3-9-2" + transform="translate(5663.2978,14098.088)"> + <rect + id="rect6-0-7-1-8" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7-3-4" + y="503.71591" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="503.71591" + x="1460.1007" + sodipodi:role="line" + id="tspan4923-3-2">Report CPU</tspan><tspan + y="837.77039" + x="1460.1007" + sodipodi:role="line" + id="tspan4925-9-9">Quiescent</tspan><tspan + y="1171.825" + x="1460.1007" + sodipodi:role="line" + id="tspan5239">State</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654562, 80.17309124;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="M 5733.305,14095.542 2761.014,12809.774" + id="path4119-0-0-2" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654107, 80.17308214;stroke-dashoffset:0" + d="m 1353.3524,10079.499 9701.6916,0 100.189,-16.698" + id="path5265" + inkscape:connector-curvature="0" + sodipodi:nodetypes="ccc" /> + </g> +</svg> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg new file mode 100644 index 000000000000..e4233ac93c2b --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg @@ -0,0 +1,826 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:39:46 2015 --> + +<!-- Magnification: 3.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="952.6817" + height="1425.6191" + viewBox="-66 -66 12729.905 19049.38" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="ExpSchedFlow.svg"> + <metadata + id="metadata94"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs92"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path4146" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0" + refX="0" + id="Arrow1Mend" + style="overflow:visible"> + <path + id="path3852" + d="M 0,0 5,-5 -12.5,0 5,5 0,0 z" + style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt" + transform="matrix(-0.4,0,0,-0.4,-4,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0" + refX="0" + id="Arrow1Mend-9" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path3852-7" + d="M 0,0 5,-5 -12.5,0 5,5 0,0 z" + style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt" + transform="matrix(-0.4,0,0,-0.4,-4,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-7" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-6" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-1" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-16" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-8" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-160" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-5" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-78" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-66" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-8" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-56" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-19" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-89" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-85" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-3" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-73" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-55" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-5" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-88" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-198" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-2" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-22" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="marker5072" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path5074" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-87" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-63" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-6" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-26" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-0" + style="overflow:visible"> + <path + inkscape:connector-curvature="0" + id="path4146-51" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-58" + style="overflow:visible"> + <path + id="path4146-61" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="1090" + inkscape:window-height="1148" + id="namedview90" + showgrid="true" + inkscape:zoom="0.80021373" + inkscape:cx="462.49289" + inkscape:cy="473.6718" + inkscape:window-x="770" + inkscape:window-y="24" + inkscape:window-maximized="0" + inkscape:current-layer="g4114-9-3-9" + inkscape:snap-grids="false" + fit-margin-top="5" + fit-margin-right="5" + fit-margin-bottom="5" + fit-margin-left="5" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4" + transform="translate(23.312814,523.41265)"> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line --> + <!-- Arrowhead on XXXpoint 11475 2250 - 11475 3465--> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line: box --> + <!-- Line --> + <!-- Arrowhead on XXXpoint 11475 5625 - 11475 6840--> + <!-- Line --> + <!-- Arrowhead on XXXpoint 7875 225 - 10665 225--> + <!-- Line --> + <!-- Arrowhead on XXXpoint 9675 675 - 7785 675--> + <!-- Line --> + <!-- Arrowhead on XXXpoint 9675 4725 - 10665 4725--> + <!-- Line --> + <!-- Arrowhead on XXXpoint 9225 5175 - 10665 5175--> + <!-- Line --> + <!-- Arrowhead on XXXpoint 8775 11475 - 10665 11475--> + <!-- Line: box --> + <!-- Line --> + <!-- Arrowhead on XXXpoint 11475 9000 - 11475 10215--> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <!-- Text --> + <g + id="g4104" + transform="translate(-1068.9745,0)"> + <rect + transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)" + y="-7383.8755" + x="-6124.8989" + height="1966.2251" + width="1953.6969" + id="rect3032-1-0" + style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <text + sodipodi:linespacing="125%" + id="text4098" + y="818.40338" + x="8168.2671" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="818.40338" + x="8168.2671" + id="tspan4100" + sodipodi:role="line">Idle or</tspan><tspan + id="tspan4102" + y="1152.4579" + x="8168.2671" + sodipodi:role="line">offline?</tspan></text> + </g> + <g + id="g4114" + transform="translate(0,147.96969)"> + <rect + id="rect6" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1475.6636" + width="4401.7612" + y="0" + x="0" /> + <text + sodipodi:linespacing="125%" + id="text4110" + y="835.11212" + x="2206.4917" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="835.11212" + x="2206.4917" + id="tspan4112" + sodipodi:role="line">CPU N Start</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="M 4432.5052,897.4924 5684.8749,880.79414" + id="path4119" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="M 8503.0006,874.12161 9755.3703,857.42334" + id="path4119-8" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <text + xml:space="preserve" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="8617.0977" + y="705.50983" + id="text4593" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4595" + x="8617.0977" + y="705.50983">Y</tspan></text> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9" + transform="translate(9722.4732,131.27105)"> + <rect + id="rect6-0" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="0" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5" + y="835.11212" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="835.11212" + x="1460.1007" + id="tspan4112-9" + sodipodi:role="line">Done</tspan></text> + </g> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-5" + transform="translate(0,3705.3456)"> + <rect + id="rect6-1" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1475.6636" + width="4401.7612" + y="0" + x="0" /> + <text + sodipodi:linespacing="125%" + id="text4110-9" + y="835.11212" + x="2206.4917" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="835.11212" + x="2206.4917" + sodipodi:role="line" + id="tspan4776">Send IPI to CPU N</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="M 7102.5627,2263.5171 4430.8404,3682.8694" + id="path4119-3" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4104-1" + transform="translate(-1065.3349,6403.5782)"> + <rect + transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)" + y="-7383.8755" + x="-6124.8989" + height="1966.2251" + width="1953.6969" + id="rect3032-1-0-6" + style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <text + sodipodi:linespacing="125%" + id="text4098-3" + y="985.4306" + x="8168.2671" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="985.4306" + x="8168.2671" + sodipodi:role="line" + id="tspan3109">CPU idle?</tspan></text> + </g> + <text + xml:space="preserve" + style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="6463.0864" + y="2285.6765" + id="text4593-0" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4595-6" + x="6463.0864" + y="2285.6765">N</tspan></text> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654108, 80.17308215;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 2189.1897,5219.361 16.6983,1252.3697" + id="path4119-0" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-5-2" + transform="translate(0,6551.5479)"> + <rect + id="rect6-1-7" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1475.6636" + width="4401.7612" + y="0" + x="0" /> + <text + sodipodi:linespacing="125%" + id="text4110-9-5" + y="835.11212" + x="2206.4917" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="835.11212" + x="2206.4917" + sodipodi:role="line" + id="tspan4776-5">IPI Handler</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="m 4432.5052,7297.9678 1252.3697,-16.6982" + id="path4119-2" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + d="m 8503.0013,7278.6595 1252.369,-16.6982" + id="path4119-8-7" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <text + xml:space="preserve" + style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="8617.0977" + y="7110.0186" + id="text4593-4" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4595-0" + x="8617.0977" + y="7110.0186">Y</tspan></text> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3" + transform="translate(9722.4732,6535.809)"> + <rect + id="rect6-0-7" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7" + y="503.71591" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="503.71591" + x="1460.1007" + id="tspan4112-9-0" + sodipodi:role="line">Report CPU</tspan><tspan + y="837.77039" + x="1460.1007" + sodipodi:role="line" + id="tspan4923">Quiescent</tspan><tspan + y="1171.825" + x="1460.1007" + sodipodi:role="line" + id="tspan4925">State</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654335, 80.17308669;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 7102.5627,11478.337 16.6983,1252.35" + id="path4119-0-0" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <text + xml:space="preserve" + style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="6797.0522" + y="9018.6807" + id="text4593-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4595-2" + x="6797.0522" + y="9018.6807">N</tspan></text> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3-8" + transform="translate(-80.17308,14133.68)"> + <rect + id="rect6-0-7-5" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7-6" + y="841.88086" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="841.88086" + x="1460.1007" + sodipodi:role="line" + id="tspan4925-1">Context Switch</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654562, 80.17309124;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 1362.6256,12823.832 16.6983,1252.369" + id="path4119-0-0-7" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 1362.6256,15636.491 16.6983,1252.369" + id="path4119-0-0-7-7" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3-8-1" + transform="translate(9722.4732,14142.03)"> + <rect + id="rect6-0-7-5-1" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7-6-2" + y="841.88086" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="841.88086" + x="1460.1007" + sodipodi:role="line" + id="tspan4925-1-2">CPU Offline</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654789, 80.17309578;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 11165.272,12823.832 16.698,1252.369" + id="path4119-0-0-7-8" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3-9" + transform="translate(-80.17308,16915.618)"> + <rect + id="rect6-0-7-1" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7-3" + y="505.47754" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="505.47754" + x="1460.1007" + id="tspan4112-9-0-4" + sodipodi:role="line">Report CPU</tspan><tspan + y="839.53204" + x="1460.1007" + sodipodi:role="line" + id="tspan4925-9">Quiescent</tspan><tspan + y="1173.5865" + x="1460.1007" + sodipodi:role="line" + id="tspan3168">State</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 11165.272,15571.534 16.698,1252.369" + id="path4119-0-0-7-7-5" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3-9-2" + transform="translate(9722.4732,16850.66)"> + <rect + id="rect6-0-7-1-8" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7-3-4" + y="503.71591" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="503.71591" + x="1460.1007" + sodipodi:role="line" + id="tspan4923-3-2">Report CPU</tspan><tspan + y="837.77039" + x="1460.1007" + sodipodi:role="line" + id="tspan4925-9-9">Quiescent</tspan><tspan + y="1171.825" + x="1460.1007" + sodipodi:role="line" + id="tspan5239">State</tspan></text> + </g> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654107, 80.17308214;stroke-dashoffset:0" + d="m 1353.3524,12832.071 9701.6916,0 100.189,-16.698" + id="path5265" + inkscape:connector-curvature="0" + sodipodi:nodetypes="ccc" /> + <path + style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)" + d="m 7112.6465,8669.1867 16.6983,1252.369" + id="path4119-0-0-7-7-5-7" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4114-9-3-8-1-8-3" + transform="translate(5663.1399,9972.3627)"> + <rect + id="rect6-0-7-5-1-1-9" + style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none" + rx="0" + height="1425.5687" + width="2748.6331" + y="29.467337" + x="80.17308" /> + <text + sodipodi:linespacing="125%" + id="text4110-5-7-6-2-4-0" + y="841.88086" + x="1460.1007" + style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + xml:space="preserve"><tspan + y="841.88086" + x="1460.1007" + sodipodi:role="line" + id="tspan4925-1-2-4-5">reched_cpu()</tspan></text> + </g> + </g> +</svg> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html new file mode 100644 index 000000000000..7a3194c5559a --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html @@ -0,0 +1,626 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" + "http://www.w3.org/TR/html4/loose.dtd"> + <html> + <head><title>A Tour Through TREE_RCU's Expedited Grace Periods</title> + <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1"> + +<h2>Introduction</h2> + +This document describes RCU's expedited grace periods. +Unlike RCU's normal grace periods, which accept long latencies to attain +high efficiency and minimal disturbance, expedited grace periods accept +lower efficiency and significant disturbance to attain shorter latencies. + +<p> +There are three flavors of RCU (RCU-bh, RCU-preempt, and RCU-sched), +but only two flavors of expedited grace periods because the RCU-bh +expedited grace period maps onto the RCU-sched expedited grace period. +Each of the remaining two implementations is covered in its own section. + +<ol> +<li> <a href="#Expedited Grace Period Design"> + Expedited Grace Period Design</a> +<li> <a href="#RCU-preempt Expedited Grace Periods"> + RCU-preempt Expedited Grace Periods</a> +<li> <a href="#RCU-sched Expedited Grace Periods"> + RCU-sched Expedited Grace Periods</a> +<li> <a href="#Expedited Grace Period and CPU Hotplug"> + Expedited Grace Period and CPU Hotplug</a> +<li> <a href="#Expedited Grace Period Refinements"> + Expedited Grace Period Refinements</a> +</ol> + +<h2><a name="Expedited Grace Period Design"> +Expedited Grace Period Design</a></h2> + +<p> +The expedited RCU grace periods cannot be accused of being subtle, +given that they for all intents and purposes hammer every CPU that +has not yet provided a quiescent state for the current expedited +grace period. +The one saving grace is that the hammer has grown a bit smaller +over time: The old call to <tt>try_stop_cpus()</tt> has been +replaced with a set of calls to <tt>smp_call_function_single()</tt>, +each of which results in an IPI to the target CPU. +The corresponding handler function checks the CPU's state, motivating +a faster quiescent state where possible, and triggering a report +of that quiescent state. +As always for RCU, once everything has spent some time in a quiescent +state, the expedited grace period has completed. + +<p> +The details of the <tt>smp_call_function_single()</tt> handler's +operation depend on the RCU flavor, as described in the following +sections. + +<h2><a name="RCU-preempt Expedited Grace Periods"> +RCU-preempt Expedited Grace Periods</a></h2> + +<p> +The overall flow of the handling of a given CPU by an RCU-preempt +expedited grace period is shown in the following diagram: + +<p><img src="ExpRCUFlow.svg" alt="ExpRCUFlow.svg" width="55%"> + +<p> +The solid arrows denote direct action, for example, a function call. +The dotted arrows denote indirect action, for example, an IPI +or a state that is reached after some time. + +<p> +If a given CPU is offline or idle, <tt>synchronize_rcu_expedited()</tt> +will ignore it because idle and offline CPUs are already residing +in quiescent states. +Otherwise, the expedited grace period will use +<tt>smp_call_function_single()</tt> to send the CPU an IPI, which +is handled by <tt>sync_rcu_exp_handler()</tt>. + +<p> +However, because this is preemptible RCU, <tt>sync_rcu_exp_handler()</tt> +can check to see if the CPU is currently running in an RCU read-side +critical section. +If not, the handler can immediately report a quiescent state. +Otherwise, it sets flags so that the outermost <tt>rcu_read_unlock()</tt> +invocation will provide the needed quiescent-state report. +This flag-setting avoids the previous forced preemption of all +CPUs that might have RCU read-side critical sections. +In addition, this flag-setting is done so as to avoid increasing +the overhead of the common-case fastpath through the scheduler. + +<p> +Again because this is preemptible RCU, an RCU read-side critical section +can be preempted. +When that happens, RCU will enqueue the task, which will the continue to +block the current expedited grace period until it resumes and finds its +outermost <tt>rcu_read_unlock()</tt>. +The CPU will report a quiescent state just after enqueuing the task because +the CPU is no longer blocking the grace period. +It is instead the preempted task doing the blocking. +The list of blocked tasks is managed by <tt>rcu_preempt_ctxt_queue()</tt>, +which is called from <tt>rcu_preempt_note_context_switch()</tt>, which +in turn is called from <tt>rcu_note_context_switch()</tt>, which in +turn is called from the scheduler. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Why not just have the expedited grace period check the + state of all the CPUs? + After all, that would avoid all those real-time-unfriendly IPIs. +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Because we want the RCU read-side critical sections to run fast, + which means no memory barriers. + Therefore, it is not possible to safely check the state from some + other CPU. + And even if it was possible to safely check the state, it would + still be necessary to IPI the CPU to safely interact with the + upcoming <tt>rcu_read_unlock()</tt> invocation, which means that + the remote state testing would not help the worst-case + latency that real-time applications care about. + + <p><font color="ffffff">One way to prevent your real-time + application from getting hit with these IPIs is to + build your kernel with <tt>CONFIG_NO_HZ_FULL=y</tt>. + RCU would then perceive the CPU running your application + as being idle, and it would be able to safely detect that + state without needing to IPI the CPU. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<p> +Please note that this is just the overall flow: +Additional complications can arise due to races with CPUs going idle +or offline, among other things. + +<h2><a name="RCU-sched Expedited Grace Periods"> +RCU-sched Expedited Grace Periods</a></h2> + +<p> +The overall flow of the handling of a given CPU by an RCU-sched +expedited grace period is shown in the following diagram: + +<p><img src="ExpSchedFlow.svg" alt="ExpSchedFlow.svg" width="55%"> + +<p> +As with RCU-preempt's <tt>synchronize_rcu_expedited()</tt>, +<tt>synchronize_sched_expedited()</tt> ignores offline and +idle CPUs, again because they are in remotely detectable +quiescent states. +However, the <tt>synchronize_rcu_expedited()</tt> handler +is <tt>sync_sched_exp_handler()</tt>, and because the +<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt> +leave no trace of their invocation, in general it is not possible to tell +whether or not the current CPU is in an RCU read-side critical section. +The best that <tt>sync_sched_exp_handler()</tt> can do is to check +for idle, on the off-chance that the CPU went idle while the IPI +was in flight. +If the CPU is idle, then tt>sync_sched_exp_handler()</tt> reports +the quiescent state. + +<p> +Otherwise, the handler invokes <tt>resched_cpu()</tt>, which forces +a future context switch. +At the time of the context switch, the CPU reports the quiescent state. +Should the CPU go offline first, it will report the quiescent state +at that time. + +<h2><a name="Expedited Grace Period and CPU Hotplug"> +Expedited Grace Period and CPU Hotplug</a></h2> + +<p> +The expedited nature of expedited grace periods require a much tighter +interaction with CPU hotplug operations than is required for normal +grace periods. +In addition, attempting to IPI offline CPUs will result in splats, but +failing to IPI online CPUs can result in too-short grace periods. +Neither option is acceptable in production kernels. + +<p> +The interaction between expedited grace periods and CPU hotplug operations +is carried out at several levels: + +<ol> +<li> The number of CPUs that have ever been online is tracked + by the <tt>rcu_state</tt> structure's <tt>->ncpus</tt> + field. + The <tt>rcu_state</tt> structure's <tt>->ncpus_snap</tt> + field tracks the number of CPUs that have ever been online + at the beginning of an RCU expedited grace period. + Note that this number never decreases, at least in the absence + of a time machine. +<li> The identities of the CPUs that have ever been online is + tracked by the <tt>rcu_node</tt> structure's + <tt>->expmaskinitnext</tt> field. + The <tt>rcu_node</tt> structure's <tt>->expmaskinit</tt> + field tracks the identities of the CPUs that were online + at least once at the beginning of the most recent RCU + expedited grace period. + The <tt>rcu_state</tt> structure's <tt>->ncpus</tt> and + <tt>->ncpus_snap</tt> fields are used to detect when + new CPUs have come online for the first time, that is, + when the <tt>rcu_node</tt> structure's <tt>->expmaskinitnext</tt> + field has changed since the beginning of the last RCU + expedited grace period, which triggers an update of each + <tt>rcu_node</tt> structure's <tt>->expmaskinit</tt> + field from its <tt>->expmaskinitnext</tt> field. +<li> Each <tt>rcu_node</tt> structure's <tt>->expmaskinit</tt> + field is used to initialize that structure's + <tt>->expmask</tt> at the beginning of each RCU + expedited grace period. + This means that only those CPUs that have been online at least + once will be considered for a given grace period. +<li> Any CPU that goes offline will clear its bit in its leaf + <tt>rcu_node</tt> structure's <tt>->qsmaskinitnext</tt> + field, so any CPU with that bit clear can safely be ignored. + However, it is possible for a CPU coming online or going offline + to have this bit set for some time while <tt>cpu_online</tt> + returns <tt>false</tt>. +<li> For each non-idle CPU that RCU believes is currently online, the grace + period invokes <tt>smp_call_function_single()</tt>. + If this succeeds, the CPU was fully online. + Failure indicates that the CPU is in the process of coming online + or going offline, in which case it is necessary to wait for a + short time period and try again. + The purpose of this wait (or series of waits, as the case may be) + is to permit a concurrent CPU-hotplug operation to complete. +<li> In the case of RCU-sched, one of the last acts of an outgoing CPU + is to invoke <tt>rcu_report_dead()</tt>, which + reports a quiescent state for that CPU. + However, this is likely paranoia-induced redundancy. <!-- @@@ --> +</ol> + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Why all the dancing around with multiple counters and masks + tracking CPUs that were once online? + Why not just have a single set of masks tracking the currently + online CPUs and be done with it? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Maintaining single set of masks tracking the online CPUs <i>sounds</i> + easier, at least until you try working out all the race conditions + between grace-period initialization and CPU-hotplug operations. + For example, suppose initialization is progressing down the + tree while a CPU-offline operation is progressing up the tree. + This situation can result in bits set at the top of the tree + that have no counterparts at the bottom of the tree. + Those bits will never be cleared, which will result in + grace-period hangs. + In short, that way lies madness, to say nothing of a great many + bugs, hangs, and deadlocks. + + <p><font color="ffffff"> + In contrast, the current multi-mask multi-counter scheme ensures + that grace-period initialization will always see consistent masks + up and down the tree, which brings significant simplifications + over the single-mask method. + + <p><font color="ffffff"> + This is an instance of + <a href="http://www.cs.columbia.edu/~library/TR-repository/reports/reports-1992/cucs-039-92.ps.gz"><font color="ffffff"> + deferring work in order to avoid synchronization</a>. + Lazily recording CPU-hotplug events at the beginning of the next + grace period greatly simplifies maintenance of the CPU-tracking + bitmasks in the <tt>rcu_node</tt> tree. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<h2><a name="Expedited Grace Period Refinements"> +Expedited Grace Period Refinements</a></h2> + +<ol> +<li> <a href="#Idle-CPU Checks">Idle-CPU checks</a>. +<li> <a href="#Batching via Sequence Counter"> + Batching via sequence counter</a>. +<li> <a href="#Funnel Locking and Wait/Wakeup"> + Funnel locking and wait/wakeup</a>. +<li> <a href="#Use of Workqueues">Use of Workqueues</a>. +<li> <a href="#Stall Warnings">Stall warnings</a>. +</ol> + +<h3><a name="Idle-CPU Checks">Idle-CPU Checks</a></h3> + +<p> +Each expedited grace period checks for idle CPUs when initially forming +the mask of CPUs to be IPIed and again just before IPIing a CPU +(both checks are carried out by <tt>sync_rcu_exp_select_cpus()</tt>). +If the CPU is idle at any time between those two times, the CPU will +not be IPIed. +Instead, the task pushing the grace period forward will include the +idle CPUs in the mask passed to <tt>rcu_report_exp_cpu_mult()</tt>. + +<p> +For RCU-sched, there is an additional check for idle in the IPI +handler, <tt>sync_sched_exp_handler()</tt>. +If the IPI has interrupted the idle loop, then +<tt>sync_sched_exp_handler()</tt> invokes <tt>rcu_report_exp_rdp()</tt> +to report the corresponding quiescent state. + +<p> +For RCU-preempt, there is no specific check for idle in the +IPI handler (<tt>sync_rcu_exp_handler()</tt>), but because +RCU read-side critical sections are not permitted within the +idle loop, if <tt>sync_rcu_exp_handler()</tt> sees that the CPU is within +RCU read-side critical section, the CPU cannot possibly be idle. +Otherwise, <tt>sync_rcu_exp_handler()</tt> invokes +<tt>rcu_report_exp_rdp()</tt> to report the corresponding quiescent +state, regardless of whether or not that quiescent state was due to +the CPU being idle. + +<p> +In summary, RCU expedited grace periods check for idle when building +the bitmask of CPUs that must be IPIed, just before sending each IPI, +and (either explicitly or implicitly) within the IPI handler. + +<h3><a name="Batching via Sequence Counter"> +Batching via Sequence Counter</a></h3> + +<p> +If each grace-period request was carried out separately, expedited +grace periods would have abysmal scalability and +problematic high-load characteristics. +Because each grace-period operation can serve an unlimited number of +updates, it is important to <i>batch</i> requests, so that a single +expedited grace-period operation will cover all requests in the +corresponding batch. + +<p> +This batching is controlled by a sequence counter named +<tt>->expedited_sequence</tt> in the <tt>rcu_state</tt> structure. +This counter has an odd value when there is an expedited grace period +in progress and an even value otherwise, so that dividing the counter +value by two gives the number of completed grace periods. +During any given update request, the counter must transition from +even to odd and then back to even, thus indicating that a grace +period has elapsed. +Therefore, if the initial value of the counter is <tt>s</tt>, +the updater must wait until the counter reaches at least the +value <tt>(s+3)&~0x1</tt>. +This counter is managed by the following access functions: + +<ol> +<li> <tt>rcu_exp_gp_seq_start()</tt>, which marks the start of + an expedited grace period. +<li> <tt>rcu_exp_gp_seq_end()</tt>, which marks the end of an + expedited grace period. +<li> <tt>rcu_exp_gp_seq_snap()</tt>, which obtains a snapshot of + the counter. +<li> <tt>rcu_exp_gp_seq_done()</tt>, which returns <tt>true</tt> + if a full expedited grace period has elapsed since the + corresponding call to <tt>rcu_exp_gp_seq_snap()</tt>. +</ol> + +<p> +Again, only one request in a given batch need actually carry out +a grace-period operation, which means there must be an efficient +way to identify which of many concurrent reqeusts will initiate +the grace period, and that there be an efficient way for the +remaining requests to wait for that grace period to complete. +However, that is the topic of the next section. + +<h3><a name="Funnel Locking and Wait/Wakeup"> +Funnel Locking and Wait/Wakeup</a></h3> + +<p> +The natural way to sort out which of a batch of updaters will initiate +the expedited grace period is to use the <tt>rcu_node</tt> combining +tree, as implemented by the <tt>exp_funnel_lock()</tt> function. +The first updater corresponding to a given grace period arriving +at a given <tt>rcu_node</tt> structure records its desired grace-period +sequence number in the <tt>->exp_seq_rq</tt> field and moves up +to the next level in the tree. +Otherwise, if the <tt>->exp_seq_rq</tt> field already contains +the sequence number for the desired grace period or some later one, +the updater blocks on one of four wait queues in the +<tt>->exp_wq[]</tt> array, using the second-from-bottom +and third-from bottom bits as an index. +An <tt>->exp_lock</tt> field in the <tt>rcu_node</tt> structure +synchronizes access to these fields. + +<p> +An empty <tt>rcu_node</tt> tree is shown in the following diagram, +with the white cells representing the <tt>->exp_seq_rq</tt> field +and the red cells representing the elements of the +<tt>->exp_wq[]</tt> array. + +<p><img src="Funnel0.svg" alt="Funnel0.svg" width="75%"> + +<p> +The next diagram shows the situation after the arrival of Task A +and Task B at the leftmost and rightmost leaf <tt>rcu_node</tt> +structures, respectively. +The current value of the <tt>rcu_state</tt> structure's +<tt>->expedited_sequence</tt> field is zero, so adding three and +clearing the bottom bit results in the value two, which both tasks +record in the <tt>->exp_seq_rq</tt> field of their respective +<tt>rcu_node</tt> structures: + +<p><img src="Funnel1.svg" alt="Funnel1.svg" width="75%"> + +<p> +Each of Tasks A and B will move up to the root +<tt>rcu_node</tt> structure. +Suppose that Task A wins, recording its desired grace-period sequence +number and resulting in the state shown below: + +<p><img src="Funnel2.svg" alt="Funnel2.svg" width="75%"> + +<p> +Task A now advances to initiate a new grace period, while Task B +moves up to the root <tt>rcu_node</tt> structure, and, seeing that +its desired sequence number is already recorded, blocks on +<tt>->exp_wq[1]</tt>. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Why <tt>->exp_wq[1]</tt>? + Given that the value of these tasks' desired sequence number is + two, so shouldn't they instead block on <tt>->exp_wq[2]</tt>? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + No. + + <p><font color="ffffff"> + Recall that the bottom bit of the desired sequence number indicates + whether or not a grace period is currently in progress. + It is therefore necessary to shift the sequence number right one + bit position to obtain the number of the grace period. + This results in <tt>->exp_wq[1]</tt>. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<p> +If Tasks C and D also arrive at this point, they will compute the +same desired grace-period sequence number, and see that both leaf +<tt>rcu_node</tt> structures already have that value recorded. +They will therefore block on their respective <tt>rcu_node</tt> +structures' <tt>->exp_wq[1]</tt> fields, as shown below: + +<p><img src="Funnel3.svg" alt="Funnel3.svg" width="75%"> + +<p> +Task A now acquires the <tt>rcu_state</tt> structure's +<tt>->exp_mutex</tt> and initiates the grace period, which +increments <tt>->expedited_sequence</tt>. +Therefore, if Tasks E and F arrive, they will compute +a desired sequence number of 4 and will record this value as +shown below: + +<p><img src="Funnel4.svg" alt="Funnel4.svg" width="75%"> + +<p> +Tasks E and F will propagate up the <tt>rcu_node</tt> +combining tree, with Task F blocking on the root <tt>rcu_node</tt> +structure and Task E wait for Task A to finish so that +it can start the next grace period. +The resulting state is as shown below: + +<p><img src="Funnel5.svg" alt="Funnel5.svg" width="75%"> + +<p> +Once the grace period completes, Task A +starts waking up the tasks waiting for this grace period to complete, +increments the <tt>->expedited_sequence</tt>, +acquires the <tt>->exp_wake_mutex</tt> and then releases the +<tt>->exp_mutex</tt>. +This results in the following state: + +<p><img src="Funnel6.svg" alt="Funnel6.svg" width="75%"> + +<p> +Task E can then acquire <tt>->exp_mutex</tt> and increment +<tt>->expedited_sequence</tt> to the value three. +If new tasks G and H arrive and moves up the combining tree at the +same time, the state will be as follows: + +<p><img src="Funnel7.svg" alt="Funnel7.svg" width="75%"> + +<p> +Note that three of the root <tt>rcu_node</tt> structure's +waitqueues are now occupied. +However, at some point, Task A will wake up the +tasks blocked on the <tt>->exp_wq</tt> waitqueues, resulting +in the following state: + +<p><img src="Funnel8.svg" alt="Funnel8.svg" width="75%"> + +<p> +Execution will continue with Tasks E and H completing +their grace periods and carrying out their wakeups. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + What happens if Task A takes so long to do its wakeups + that Task E's grace period completes? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Then Task E will block on the <tt>->exp_wake_mutex</tt>, + which will also prevent it from releasing <tt>->exp_mutex</tt>, + which in turn will prevent the next grace period from starting. + This last is important in preventing overflow of the + <tt>->exp_wq[]</tt> array. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<h3><a name="Use of Workqueues">Use of Workqueues</a></h3> + +<p> +In earlier implementations, the task requesting the expedited +grace period also drove it to completion. +This straightforward approach had the disadvantage of needing to +account for signals sent to user tasks, +so more recent implemementations use the Linux kernel's +<a href="https://www.kernel.org/doc/Documentation/workqueue.txt">workqueues</a>. + +<p> +The requesting task still does counter snapshotting and funnel-lock +processing, but the task reaching the top of the funnel lock +does a <tt>schedule_work()</tt> (from <tt>_synchronize_rcu_expedited()</tt> +so that a workqueue kthread does the actual grace-period processing. +Because workqueue kthreads do not accept signals, grace-period-wait +processing need not allow for signals. + +In addition, this approach allows wakeups for the previous expedited +grace period to be overlapped with processing for the next expedited +grace period. +Because there are only four sets of waitqueues, it is necessary to +ensure that the previous grace period's wakeups complete before the +next grace period's wakeups start. +This is handled by having the <tt>->exp_mutex</tt> +guard expedited grace-period processing and the +<tt>->exp_wake_mutex</tt> guard wakeups. +The key point is that the <tt>->exp_mutex</tt> is not released +until the first wakeup is complete, which means that the +<tt>->exp_wake_mutex</tt> has already been acquired at that point. +This approach ensures that the previous grace period's wakeups can +be carried out while the current grace period is in process, but +that these wakeups will complete before the next grace period starts. +This means that only three waitqueues are required, guaranteeing that +the four that are provided are sufficient. + +<h3><a name="Stall Warnings">Stall Warnings</a></h3> + +<p> +Expediting grace periods does nothing to speed things up when RCU +readers take too long, and therefore expedited grace periods check +for stalls just as normal grace periods do. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + But why not just let the normal grace-period machinery + detect the stalls, given that a given reader must block + both normal and expedited grace periods? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Because it is quite possible that at a given time there + is no normal grace period in progress, in which case the + normal grace period cannot emit a stall warning. +</font></td></tr> +<tr><td> </td></tr> +</table> + +The <tt>synchronize_sched_expedited_wait()</tt> function loops waiting +for the expedited grace period to end, but with a timeout set to the +current RCU CPU stall-warning time. +If this time is exceeded, any CPUs or <tt>rcu_node</tt> structures +blocking the current grace period are printed. +Each stall warning results in another pass through the loop, but the +second and subsequent passes use longer stall times. + +<h3><a name="Summary"> +Summary</a></h3> + +<p> +Expedited grace periods use a sequence-number approach to promote +batching, so that a single grace-period operation can serve numerous +requests. +A funnel lock is used to efficiently identify the one task out of +a concurrent group that will request the grace period. +All members of the group will block on waitqueues provided in +the <tt>rcu_node</tt> structure. +The actual grace-period processing is carried out by a workqueue. + +<p> +CPU-hotplug operations are noted lazily in order to prevent the need +for tight synchronization between expedited grace periods and +CPU-hotplug operations. +The dyntick-idle counters are used to avoid sending IPIs to idle CPUs, +at least in the common case. +RCU-preempt and RCU-sched use different IPI handlers and different +code to respond to the state changes carried out by those handlers, +but otherwise use common code. + +<p> +Quiescent states are tracked using the <tt>rcu_node</tt> tree, +and once all necessary quiescent states have been reported, +all tasks waiting on this expedited grace period are awakened. +A pair of mutexes are used to allow one grace period's wakeups +to proceed concurrently with the next grace period's processing. + +<p> +This combination of mechanisms allows expedited grace periods to +run reasonably efficiently. +However, for non-time-critical tasks, normal grace periods should be +used instead because their longer duration permits much higher +degrees of batching, and thus much lower per-request overheads. + +</body></html> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel0.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel0.svg new file mode 100644 index 000000000000..98af66557908 --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel0.svg @@ -0,0 +1,275 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="490.05093" + height="125.78741" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="Funnel0.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart-4" + style="overflow:visible"> + <path + id="path3789-9" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + id="path3792-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.3670394" + inkscape:cx="201.06495" + inkscape:cy="-86.548414" + inkscape:document-units="px" + inkscape:current-layer="layer1" + showgrid="false" + inkscape:window-width="1351" + inkscape:window-height="836" + inkscape:window-x="171" + inkscape:window-y="279" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-117.08462,-249.92053)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991" /></flowRoot> <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="362.371" + y="262.51819" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="362.371" + y="262.51819">->expedited_sequence: 0</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101" + width="43.158947" + height="26.33428" + x="253.55223" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3" + width="43.158947" + height="26.33428" + x="297.04141" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6" + width="43.158947" + height="26.33428" + x="427.509" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7" + width="43.158947" + height="26.33428" + x="384.01981" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7-5" + width="43.158947" + height="26.33428" + x="340.53061" + y="275.07489" /> + <g + id="g3997" + transform="translate(-0.87295532,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="145.45404" + y="360.25174" + id="text3013" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015" + x="145.45404" + y="360.25174" + style="font-size:10px">:0</tspan></text> + </g> + <g + id="g3997-7" + transform="translate(260.06223,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35-0" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9-3" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1-6" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2-0" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="145.45404" + y="360.25174" + id="text3013-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6" + x="145.45404" + y="360.25174" + style="font-size:10px">:0</tspan></text> + </g> + </g> +</svg> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel1.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel1.svg new file mode 100644 index 000000000000..e0184a37aec7 --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel1.svg @@ -0,0 +1,275 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="490.05093" + height="125.78741" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="Funnel1.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart-4" + style="overflow:visible"> + <path + id="path3789-9" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + id="path3792-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.3670394" + inkscape:cx="201.06495" + inkscape:cy="-86.548414" + inkscape:document-units="px" + inkscape:current-layer="g3997-7" + showgrid="false" + inkscape:window-width="1351" + inkscape:window-height="836" + inkscape:window-x="363" + inkscape:window-y="336" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-117.08462,-249.92053)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991" /></flowRoot> <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="362.371" + y="262.51819" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="362.371" + y="262.51819">->expedited_sequence: 0</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101" + width="43.158947" + height="26.33428" + x="253.55223" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3" + width="43.158947" + height="26.33428" + x="297.04141" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6" + width="43.158947" + height="26.33428" + x="427.509" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7" + width="43.158947" + height="26.33428" + x="384.01981" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7-5" + width="43.158947" + height="26.33428" + x="340.53061" + y="275.07489" /> + <g + id="g3997" + transform="translate(-0.87295532,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="146.00092" + y="360.25174" + id="text3013" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015" + x="146.00092" + y="360.25174" + style="font-size:10px">A:2</tspan></text> + </g> + <g + id="g3997-7" + transform="translate(260.06223,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35-0" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9-3" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1-6" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2-0" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="145.54926" + y="360.25174" + id="text3013-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6" + x="145.54926" + y="360.25174" + style="font-size:10px">B:2</tspan></text> + </g> + </g> +</svg> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel2.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel2.svg new file mode 100644 index 000000000000..1bc3fed54d58 --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel2.svg @@ -0,0 +1,287 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="490.05093" + height="125.78741" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="Funnel2.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart-4" + style="overflow:visible"> + <path + id="path3789-9" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + id="path3792-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.3670394" + inkscape:cx="114.01552" + inkscape:cy="-86.548414" + inkscape:document-units="px" + inkscape:current-layer="g3997-7" + showgrid="false" + inkscape:window-width="1351" + inkscape:window-height="836" + inkscape:window-x="363" + inkscape:window-y="336" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-117.08462,-249.92053)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991" /></flowRoot> <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="362.371" + y="262.51819" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="362.371" + y="262.51819">->expedited_sequence: 0</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101" + width="43.158947" + height="26.33428" + x="253.55223" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3" + width="43.158947" + height="26.33428" + x="297.04141" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6" + width="43.158947" + height="26.33428" + x="427.509" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7" + width="43.158947" + height="26.33428" + x="384.01981" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7-5" + width="43.158947" + height="26.33428" + x="340.53061" + y="275.07489" /> + <g + id="g3997" + transform="translate(-0.87295532,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="146.00092" + y="360.25174" + id="text3013" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015" + x="146.00092" + y="360.25174" + style="font-size:10px">:2</tspan></text> + </g> + <g + id="g3997-7" + transform="translate(260.06223,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35-0" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9-3" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1-6" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2-0" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="145.54926" + y="360.25174" + id="text3013-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6" + x="145.54926" + y="360.25174" + style="font-size:10px">B:2</tspan></text> + </g> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="275.59558" + y="291.95297" + id="text3013-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-7" + x="275.59558" + y="291.95297" + style="font-size:10px">A:2</tspan></text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel3.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel3.svg new file mode 100644 index 000000000000..6d8a1bffb3e4 --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel3.svg @@ -0,0 +1,323 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="490.05093" + height="125.78741" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="Funnel3.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart-4" + style="overflow:visible"> + <path + id="path3789-9" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + id="path3792-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.3670394" + inkscape:cx="114.01552" + inkscape:cy="-86.548414" + inkscape:document-units="px" + inkscape:current-layer="layer1" + showgrid="false" + inkscape:window-width="1351" + inkscape:window-height="836" + inkscape:window-x="68" + inkscape:window-y="180" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-117.08462,-249.92053)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991" /></flowRoot> <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="362.371" + y="262.51819" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="362.371" + y="262.51819">->expedited_sequence: 0 GP: A</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101" + width="43.158947" + height="26.33428" + x="253.55223" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3" + width="43.158947" + height="26.33428" + x="297.04141" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6" + width="43.158947" + height="26.33428" + x="427.509" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7" + width="43.158947" + height="26.33428" + x="384.01981" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7-5" + width="43.158947" + height="26.33428" + x="340.53061" + y="275.07489" /> + <g + id="g3997" + transform="translate(-0.87295532,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="146.00092" + y="360.25174" + id="text3013" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015" + x="146.00092" + y="360.25174" + style="font-size:10px">:2</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="232.51051" + y="360.18094" + id="text3013-3-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-6" + x="232.51051" + y="360.18094" + style="font-size:10px">C</tspan></text> + </g> + <g + id="g3019" + transform="translate(260.06223,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35-0" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62-9" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9-3" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1-6" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2-0" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="145.54926" + y="360.25174" + id="text3013-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6" + x="145.54926" + y="360.25174" + style="font-size:10px">:2</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="232.31764" + y="360.18582" + id="text3013-3-3-7" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-6-5" + x="232.31764" + y="360.18582" + style="font-size:10px">D</tspan></text> + </g> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="275.59558" + y="291.95297" + id="text3013-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-7" + x="275.59558" + y="291.95297" + style="font-size:10px">:2</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="361.97092" + y="291.88705" + id="text3013-3-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7" + x="361.97092" + y="291.88705" + style="font-size:10px">B</tspan></text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel4.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel4.svg new file mode 100644 index 000000000000..44018fd6342b --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel4.svg @@ -0,0 +1,323 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="490.05093" + height="125.78741" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="Funnel4.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart-4" + style="overflow:visible"> + <path + id="path3789-9" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + id="path3792-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.3670394" + inkscape:cx="114.01552" + inkscape:cy="-86.548414" + inkscape:document-units="px" + inkscape:current-layer="layer1" + showgrid="false" + inkscape:window-width="1351" + inkscape:window-height="836" + inkscape:window-x="68" + inkscape:window-y="180" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-117.08462,-249.92053)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991" /></flowRoot> <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="362.371" + y="262.51819" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="362.371" + y="262.51819">->expedited_sequence: 1 GP: A</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101" + width="43.158947" + height="26.33428" + x="253.55223" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3" + width="43.158947" + height="26.33428" + x="297.04141" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6" + width="43.158947" + height="26.33428" + x="427.509" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7" + width="43.158947" + height="26.33428" + x="384.01981" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7-5" + width="43.158947" + height="26.33428" + x="340.53061" + y="275.07489" /> + <g + id="g3997" + transform="translate(-0.87295532,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="146.00092" + y="360.25174" + id="text3013" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015" + x="146.00092" + y="360.25174" + style="font-size:10px">E:4</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="232.51051" + y="360.18094" + id="text3013-3-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-6" + x="232.51051" + y="360.18094" + style="font-size:10px">C</tspan></text> + </g> + <g + id="g3019" + transform="translate(260.06223,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35-0" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62-9" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9-3" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1-6" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2-0" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="145.54926" + y="360.25174" + id="text3013-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6" + x="145.54926" + y="360.25174" + style="font-size:10px">F:4</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="232.31764" + y="360.18582" + id="text3013-3-3-7" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-6-5" + x="232.31764" + y="360.18582" + style="font-size:10px">D</tspan></text> + </g> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="275.59558" + y="291.95297" + id="text3013-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-7" + x="275.59558" + y="291.95297" + style="font-size:10px">:2</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="361.97092" + y="291.88705" + id="text3013-3-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7" + x="361.97092" + y="291.88705" + style="font-size:10px">B</tspan></text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel5.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel5.svg new file mode 100644 index 000000000000..e5eef50454fb --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel5.svg @@ -0,0 +1,335 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="490.05093" + height="125.78741" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="Funnel5.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart-4" + style="overflow:visible"> + <path + id="path3789-9" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + id="path3792-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.3670394" + inkscape:cx="114.01552" + inkscape:cy="-86.548414" + inkscape:document-units="px" + inkscape:current-layer="layer1" + showgrid="false" + inkscape:window-width="1351" + inkscape:window-height="836" + inkscape:window-x="68" + inkscape:window-y="180" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-117.08462,-249.92053)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991" /></flowRoot> <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="362.371" + y="262.51819" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="362.371" + y="262.51819">->expedited_sequence: 1 GP: A,E</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101" + width="43.158947" + height="26.33428" + x="253.55223" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3" + width="43.158947" + height="26.33428" + x="297.04141" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6" + width="43.158947" + height="26.33428" + x="427.509" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7" + width="43.158947" + height="26.33428" + x="384.01981" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7-5" + width="43.158947" + height="26.33428" + x="340.53061" + y="275.07489" /> + <g + id="g3997" + transform="translate(-0.87295532,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="146.00092" + y="360.25174" + id="text3013" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015" + x="146.00092" + y="360.25174" + style="font-size:10px">:4</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="232.51051" + y="360.18094" + id="text3013-3-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-6" + x="232.51051" + y="360.18094" + style="font-size:10px">C</tspan></text> + </g> + <g + id="g3019" + transform="translate(260.06223,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35-0" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62-9" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9-3" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1-6" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2-0" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="145.54926" + y="360.25174" + id="text3013-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6" + x="145.54926" + y="360.25174" + style="font-size:10px">:4</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="232.31764" + y="360.18582" + id="text3013-3-3-7" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-6-5" + x="232.31764" + y="360.18582" + style="font-size:10px">D</tspan></text> + </g> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="275.59558" + y="291.95297" + id="text3013-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-7" + x="275.59558" + y="291.95297" + style="font-size:10px">:4</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="361.97092" + y="291.88705" + id="text3013-3-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7" + x="361.97092" + y="291.88705" + style="font-size:10px">B</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="405.40396" + y="291.88705" + id="text3013-3-36-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7-6" + x="405.40396" + y="291.88705" + style="font-size:10px">F</tspan></text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel6.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel6.svg new file mode 100644 index 000000000000..fbd2c1892886 --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel6.svg @@ -0,0 +1,335 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="490.05093" + height="125.78741" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="Funnel6.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart-4" + style="overflow:visible"> + <path + id="path3789-9" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + id="path3792-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.3670394" + inkscape:cx="114.01552" + inkscape:cy="-86.548414" + inkscape:document-units="px" + inkscape:current-layer="layer1" + showgrid="false" + inkscape:window-width="1351" + inkscape:window-height="836" + inkscape:window-x="68" + inkscape:window-y="180" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-117.08462,-249.92053)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991" /></flowRoot> <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="362.371" + y="262.51819" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="362.371" + y="262.51819">->expedited_sequence: 2 GP: E Wakeup: A</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101" + width="43.158947" + height="26.33428" + x="253.55223" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3" + width="43.158947" + height="26.33428" + x="297.04141" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6" + width="43.158947" + height="26.33428" + x="427.509" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7" + width="43.158947" + height="26.33428" + x="384.01981" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7-5" + width="43.158947" + height="26.33428" + x="340.53061" + y="275.07489" /> + <g + id="g3997" + transform="translate(-0.87295532,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="146.00092" + y="360.25174" + id="text3013" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015" + x="146.00092" + y="360.25174" + style="font-size:10px">:4</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="232.51051" + y="360.18094" + id="text3013-3-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-6" + x="232.51051" + y="360.18094" + style="font-size:10px">C</tspan></text> + </g> + <g + id="g3019" + transform="translate(260.06223,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35-0" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62-9" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9-3" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1-6" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2-0" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="145.54926" + y="360.25174" + id="text3013-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6" + x="145.54926" + y="360.25174" + style="font-size:10px">:4</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="232.31764" + y="360.18582" + id="text3013-3-3-7" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-6-5" + x="232.31764" + y="360.18582" + style="font-size:10px">D</tspan></text> + </g> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="275.59558" + y="291.95297" + id="text3013-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-7" + x="275.59558" + y="291.95297" + style="font-size:10px">:4</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="361.97092" + y="291.88705" + id="text3013-3-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7" + x="361.97092" + y="291.88705" + style="font-size:10px">B</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="405.40396" + y="291.88705" + id="text3013-3-36-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7-6" + x="405.40396" + y="291.88705" + style="font-size:10px">F</tspan></text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel7.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel7.svg new file mode 100644 index 000000000000..502e159ed278 --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel7.svg @@ -0,0 +1,347 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="490.05093" + height="125.78741" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="Funnel7.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart-4" + style="overflow:visible"> + <path + id="path3789-9" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + id="path3792-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.3670394" + inkscape:cx="114.01552" + inkscape:cy="-86.548414" + inkscape:document-units="px" + inkscape:current-layer="layer1" + showgrid="false" + inkscape:window-width="1351" + inkscape:window-height="836" + inkscape:window-x="68" + inkscape:window-y="180" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-117.08462,-249.92053)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991" /></flowRoot> <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="362.371" + y="262.51819" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="362.371" + y="262.51819">->expedited_sequence: 3 GP: E,H Wakeup: A</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101" + width="43.158947" + height="26.33428" + x="253.55223" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3" + width="43.158947" + height="26.33428" + x="297.04141" + y="275.07489" /> + <rect + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101-3-6" + width="43.158947" + height="26.33428" + x="427.509" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7" + width="43.158947" + height="26.33428" + x="384.01981" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7-5" + width="43.158947" + height="26.33428" + x="340.53061" + y="275.07489" /> + <g + id="g3997" + transform="translate(-0.87295532,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="146.00092" + y="360.25174" + id="text3013" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015" + x="146.00092" + y="360.25174" + style="font-size:10px">:4</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="232.51051" + y="360.18094" + id="text3013-3-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-6" + x="232.51051" + y="360.18094" + style="font-size:10px">C</tspan></text> + </g> + <g + id="g3019" + transform="translate(260.06223,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35-0" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62-9" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9-3" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1-6" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2-0" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="145.54926" + y="360.25174" + id="text3013-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6" + x="145.54926" + y="360.25174" + style="font-size:10px">:6</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="232.31764" + y="360.18582" + id="text3013-3-3-7" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-6-5" + x="232.31764" + y="360.18582" + style="font-size:10px">D</tspan></text> + </g> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="275.59558" + y="291.95297" + id="text3013-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-7" + x="275.59558" + y="291.95297" + style="font-size:10px">:6</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="361.97092" + y="291.88705" + id="text3013-3-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7" + x="361.97092" + y="291.88705" + style="font-size:10px">B</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="405.40396" + y="291.88705" + id="text3013-3-36-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7-6" + x="405.40396" + y="291.88705" + style="font-size:10px">F</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="449.22031" + y="291.88217" + id="text3013-3-36-3-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7-6-6" + x="449.22031" + y="291.88217" + style="font-size:10px">G</tspan></text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel8.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel8.svg new file mode 100644 index 000000000000..677401551c7d --- /dev/null +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel8.svg @@ -0,0 +1,311 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="490.05093" + height="125.78741" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="Funnel8.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart-4" + style="overflow:visible"> + <path + id="path3789-9" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + id="path3792-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.3670394" + inkscape:cx="114.01552" + inkscape:cy="-86.548414" + inkscape:document-units="px" + inkscape:current-layer="layer1" + showgrid="false" + inkscape:window-width="1351" + inkscape:window-height="836" + inkscape:window-x="68" + inkscape:window-y="180" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-117.08462,-249.92053)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991" /></flowRoot> <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="362.371" + y="262.51819" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="362.371" + y="262.51819">->expedited_sequence: 3 GP: E,H</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101" + width="43.158947" + height="26.33428" + x="253.55223" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3" + width="43.158947" + height="26.33428" + x="297.04141" + y="275.07489" /> + <rect + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect3101-3-6" + width="43.158947" + height="26.33428" + x="427.509" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7" + width="43.158947" + height="26.33428" + x="384.01981" + y="275.07489" /> + <rect + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" + id="rect3101-3-6-7-5" + width="43.158947" + height="26.33428" + x="340.53061" + y="275.07489" /> + <g + id="g3997" + transform="translate(-0.87295532,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2" + style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="146.00092" + y="360.25174" + id="text3013" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015" + x="146.00092" + y="360.25174" + style="font-size:10px">:4</tspan></text> + </g> + <g + id="g3019" + transform="translate(260.06223,0)"> + <rect + y="343.37366" + x="123.95757" + height="26.33428" + width="43.158947" + id="rect3101-35-0" + style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="167.44673" + height="26.33428" + width="43.158947" + id="rect3101-3-62-9" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="297.91437" + height="26.33428" + width="43.158947" + id="rect3101-3-6-9-3" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="254.42516" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-1-6" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <rect + y="343.37366" + x="210.93593" + height="26.33428" + width="43.158947" + id="rect3101-3-6-7-5-2-0" + style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" /> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="145.54926" + y="360.25174" + id="text3013-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6" + x="145.54926" + y="360.25174" + style="font-size:10px">:6</tspan></text> + </g> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="275.59558" + y="291.95297" + id="text3013-36" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-7" + x="275.59558" + y="291.95297" + style="font-size:10px">:6</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="405.40396" + y="291.88705" + id="text3013-3-36-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7-6" + x="405.40396" + y="291.88705" + style="font-size:10px">F</tspan></text> + <text + xml:space="preserve" + style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans" + x="449.22031" + y="291.88217" + id="text3013-3-36-3-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan3015-6-7-6-6" + x="449.22031" + y="291.88217" + style="font-size:10px">G</tspan></text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html index 39bcb74ea733..21593496aca6 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.html +++ b/Documentation/RCU/Design/Requirements/Requirements.html @@ -1480,7 +1480,7 @@ speed-of-light delays if nothing else. <p> Furthermore, uncertainty about external state is inherent in many cases. -For example, a pair of veternarians might use heartbeat to determine +For example, a pair of veterinarians might use heartbeat to determine whether or not a given cat was alive. But how long should they wait after the last heartbeat to decide that the cat is in fact dead? @@ -1489,9 +1489,9 @@ mean that a relaxed cat would be considered to cycle between death and life more than 100 times per minute. Moreover, just as with human beings, a cat's heart might stop for some period of time, so the exact wait period is a judgment call. -One of our pair of veternarians might wait 30 seconds before pronouncing +One of our pair of veterinarians might wait 30 seconds before pronouncing the cat dead, while the other might insist on waiting a full minute. -The two veternarians would then disagree on the state of the cat during +The two veterinarians would then disagree on the state of the cat during the final 30 seconds of the minute following the last heartbeat. <p> @@ -1945,7 +1945,7 @@ guard against mishaps and misuse: <ol> <li> It is all too easy to forget to use <tt>rcu_read_lock()</tt> everywhere that it is needed, so kernels built with - <tt>CONFIG_PROVE_RCU=y</tt> will spat if + <tt>CONFIG_PROVE_RCU=y</tt> will splat if <tt>rcu_dereference()</tt> is used outside of an RCU read-side critical section. Update-side code can use <tt>rcu_dereference_protected()</tt>, @@ -2421,7 +2421,7 @@ However, there are some restrictions on the code placed within <li> Blocking is prohibited. In practice, this is not a serious restriction given that idle tasks are prohibited from blocking to begin with. -<li> Although nesting <tt>RCU_NONIDLE()</tt> is permited, they cannot +<li> Although nesting <tt>RCU_NONIDLE()</tt> is permitted, they cannot nest indefinitely deeply. However, given that they can be nested on the order of a million deep, even on 32-bit systems, this should not be a serious @@ -2885,7 +2885,7 @@ APIs for defining and initializing <tt>srcu_struct</tt> structures. <h3><a name="Tasks RCU">Tasks RCU</a></h3> <p> -Some forms of tracing use “tramopolines” to handle the +Some forms of tracing use “trampolines” to handle the binary rewriting required to install different types of probes. It would be good to be able to free old trampolines, which sounds like a job for some form of RCU. diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index 00a3a38b375a..6549012033f9 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -237,7 +237,7 @@ o "ktl" is the low-order 16 bits (in hexadecimal) of the count of The output of "cat rcu/rcu_preempt/rcuexp" looks as follows: -s=21872 wd1=0 wd2=0 wd3=5 n=0 enq=0 sc=21872 +s=21872 wd1=0 wd2=0 wd3=5 enq=0 sc=21872 These fields are as follows: @@ -249,9 +249,6 @@ o "wd1", "wd2", and "wd3" are the number of times that an attempt completed an expedited grace period that satisfies the attempted request. "Our work is done." -o "n" is number of times that a concurrent CPU-hotplug operation - forced a fallback to a normal grace period. - o "enq" is the number of quiescent states still outstanding. o "sc" is the number of times that the attempt to start a diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index be7c0d9506b1..635d11135090 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -549,15 +549,6 @@ loops can be debugged more effectively on production systems. - clocksource.arm_arch_timer.fsl-a008585= - [ARM64] - Format: <bool> - Enable/disable the workaround of Freescale/NXP - erratum A-008585. This can be useful for KVM - guests, if the guest device tree doesn't show the - erratum. If unspecified, the workaround is - enabled based on the device tree. - clearcpuid=BITNUM [X86] Disable CPUID feature X for the kernel. See arch/x86/include/asm/cpufeatures.h for the valid bit @@ -3278,6 +3269,13 @@ Lazy RCU callbacks are those which RCU can prove do nothing more than free memory. + rcutree.rcu_kick_kthreads= [KNL] + Cause the grace-period kthread to get an extra + wake_up() if it sleeps three times longer than + it should at force-quiescent-state time. + This wake_up() will be accompanied by a + WARN_ONCE() splat and an ftrace_dump(). + rcuperf.gp_exp= [KNL] Measure performance of expedited synchronous grace-period primitives. @@ -3563,6 +3561,10 @@ rhash_entries= [KNL,NET] Set number of hash buckets for route cache + ring3mwait=disable + [KNL] Disable ring 3 MONITOR/MWAIT feature on supported + CPUs. + ro [KNL] Mount root device read-only on boot rodata= [KNL] diff --git a/Documentation/admin-guide/ras.rst b/Documentation/admin-guide/ras.rst index d71340e86c27..9939348bd4a3 100644 --- a/Documentation/admin-guide/ras.rst +++ b/Documentation/admin-guide/ras.rst @@ -438,11 +438,13 @@ A typical EDAC system has the following structure under │  │  ├── ce_count │  │  ├── ce_noinfo_count │  │  ├── dimm0 + │  │  │  ├── dimm_ce_count │  │  │  ├── dimm_dev_type │  │  │  ├── dimm_edac_mode │  │  │  ├── dimm_label │  │  │  ├── dimm_location │  │  │  ├── dimm_mem_type + │  │  │  ├── dimm_ue_count │  │  │  ├── size │  │  │  └── uevent │  │  ├── max_location @@ -457,11 +459,13 @@ A typical EDAC system has the following structure under │  │  ├── ce_count │  │  ├── ce_noinfo_count │  │  ├── dimm0 + │  │  │  ├── dimm_ce_count │  │  │  ├── dimm_dev_type │  │  │  ├── dimm_edac_mode │  │  │  ├── dimm_label │  │  │  ├── dimm_location │  │  │  ├── dimm_mem_type + │  │  │  ├── dimm_ue_count │  │  │  ├── size │  │  │  └── uevent │  │  ├── max_location @@ -483,6 +487,22 @@ this ``X`` memory module: This attribute file displays, in count of megabytes, the memory that this csrow contains. +- ``dimm_ue_count`` - Uncorrectable Errors count attribute file + + This attribute file displays the total count of uncorrectable + errors that have occurred on this DIMM. If panic_on_ue is set + this counter will not have a chance to increment, since EDAC + will panic the system. + +- ``dimm_ce_count`` - Correctable Errors count attribute file + + This attribute file displays the total count of correctable + errors that have occurred on this DIMM. This count is very + important to examine. CEs provide early indications that a + DIMM is beginning to fail. This count field should be + monitored for non-zero values and report such information + to the system administrator. + - ``dimm_dev_type`` - Device type attribute file This attribute file will display what type of DRAM device is diff --git a/Documentation/devicetree/bindings/arm/arch_timer.txt b/Documentation/devicetree/bindings/arm/arch_timer.txt index ad440a2b8051..e926aea1147d 100644 --- a/Documentation/devicetree/bindings/arm/arch_timer.txt +++ b/Documentation/devicetree/bindings/arm/arch_timer.txt @@ -31,6 +31,12 @@ to deliver its interrupts via SPIs. This also affects writes to the tval register, due to the implicit counter read. +- hisilicon,erratum-161010101 : A boolean property. Indicates the + presence of Hisilicon erratum 161010101, which says that reading the + counters is unreliable in some cases, and reads may return a value 32 + beyond the correct value. This also affects writes to the tval + registers, due to the implicit counter read. + ** Optional properties: - arm,cpu-registers-not-fw-configured : Firmware does not initialize diff --git a/Documentation/devicetree/bindings/hwmon/adc128d818.txt b/Documentation/devicetree/bindings/hwmon/adc128d818.txt new file mode 100644 index 000000000000..08bab0e94d25 --- /dev/null +++ b/Documentation/devicetree/bindings/hwmon/adc128d818.txt @@ -0,0 +1,38 @@ +TI ADC128D818 ADC System Monitor With Temperature Sensor +-------------------------------------------------------- + +Operation modes: + + - Mode 0: 7 single-ended voltage readings (IN0-IN6), + 1 temperature reading (internal) + - Mode 1: 8 single-ended voltage readings (IN0-IN7), + no temperature + - Mode 2: 4 pseudo-differential voltage readings + (IN0-IN1, IN3-IN2, IN4-IN5, IN7-IN6), + 1 temperature reading (internal) + - Mode 3: 4 single-ended voltage readings (IN0-IN3), + 2 pseudo-differential voltage readings + (IN4-IN5, IN7-IN6), + 1 temperature reading (internal) + +If no operation mode is configured via device tree, the driver keeps the +currently active chip operation mode (default is mode 0). + + +Required node properties: + + - compatible: must be set to "ti,adc128d818" + - reg: I2C address of the device + +Optional node properties: + + - ti,mode: Operation mode (see above). + + +Example (operation mode 2): + + adc128d818@1d { + compatible = "ti,adc128d818"; + reg = <0x1d>; + ti,mode = <2>; + }; diff --git a/Documentation/devicetree/bindings/hwmon/lm70.txt b/Documentation/devicetree/bindings/hwmon/lm70.txt index e7fd921aa4f1..ea417a0d32af 100644 --- a/Documentation/devicetree/bindings/hwmon/lm70.txt +++ b/Documentation/devicetree/bindings/hwmon/lm70.txt @@ -4,6 +4,7 @@ Required properties: - compatible: one of "ti,lm70" "ti,tmp121" + "ti,tmp122" "ti,lm71" "ti,lm74" diff --git a/Documentation/devicetree/bindings/hwmon/lm90.txt b/Documentation/devicetree/bindings/hwmon/lm90.txt index e8632486b9ef..97581266e329 100644 --- a/Documentation/devicetree/bindings/hwmon/lm90.txt +++ b/Documentation/devicetree/bindings/hwmon/lm90.txt @@ -33,6 +33,11 @@ Optional properties: LM90 "-ALERT" pin output. See interrupt-controller/interrupts.txt for the format. +- #thermal-sensor-cells: should be set to 1. See thermal/thermal.txt for + details. See <include/dt-bindings/thermal/lm90.h> for the + definition of the local, remote and 2nd remote sensor index + constants. + Example LM90 node: temp-sensor { @@ -41,4 +46,5 @@ temp-sensor { vcc-supply = <&palmas_ldo6_reg>; interrupt-parent = <&gpio>; interrupts = <TEGRA_GPIO(O, 4) IRQ_TYPE_LEVEL_LOW>; + #thermal-sensor-cells = <1>; } diff --git a/Documentation/devicetree/bindings/hwmon/sht15.txt b/Documentation/devicetree/bindings/hwmon/sht15.txt new file mode 100644 index 000000000000..6a80277cc426 --- /dev/null +++ b/Documentation/devicetree/bindings/hwmon/sht15.txt @@ -0,0 +1,19 @@ +Sensirion SHT15 Humidity and Temperature Sensor + +Required properties: + + - "compatible": must be "sensirion,sht15". + - "data-gpios": GPIO connected to the data line. + - "clk-gpios": GPIO connected to the clock line. + - "vcc-supply": regulator that drives the VCC pin. + +Example: + + sensor { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_sensor>; + compatible = "sensirion,sht15"; + clk-gpios = <&gpio4 12 0>; + data-gpios = <&gpio4 13 0>; + vcc-supply = <®_sht15>; + }; diff --git a/Documentation/devicetree/bindings/hwmon/stts751.txt b/Documentation/devicetree/bindings/hwmon/stts751.txt new file mode 100644 index 000000000000..3ee1dc30e72f --- /dev/null +++ b/Documentation/devicetree/bindings/hwmon/stts751.txt @@ -0,0 +1,15 @@ +* STTS751 thermometer. + +Required node properties: +- compatible: "stts751" +- reg: I2C bus address of the device + +Optional properties: +- smbus-timeout-disable: when set, the smbus timeout function will be disabled + +Example stts751 node: + +temp-sensor { + compatible = "stts751"; + reg = <0x48>; +} diff --git a/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt b/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt new file mode 100644 index 000000000000..97c1167fa533 --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt @@ -0,0 +1,22 @@ +* Cortina Systems Gemini interrupt controller + +This interrupt controller is found on the Gemini SoCs. + +Required properties: +- compatible: must be "cortina,gemini-interrupt-controller" +- reg: The register bank for the interrupt controller. +- interrupt-controller: Identifies the node as an interrupt controller +- #interrupt-cells: The number of cells to define the interrupts. + Must be 2 as the controller can specify level or rising edge + IRQs. The bindings follows the standard binding for controllers + with two cells specified in + interrupt-controller/interrupts.txt + +Example: + +interrupt-controller@48000000 { + compatible = "cortina,gemini-interrupt-controller"; + reg = <0x48000000 0x1000>; + interrupt-controller; + #interrupt-cells = <2>; +}; diff --git a/Documentation/devicetree/bindings/mtd/aspeed-smc.txt b/Documentation/devicetree/bindings/mtd/aspeed-smc.txt new file mode 100644 index 000000000000..49f6528ef547 --- /dev/null +++ b/Documentation/devicetree/bindings/mtd/aspeed-smc.txt @@ -0,0 +1,51 @@ +* Aspeed Firmware Memory controller +* Aspeed SPI Flash Memory Controller + +The Firmware Memory Controller in the Aspeed AST2500 SoC supports +three chip selects, two of which are always of SPI type and the third +can be SPI or NOR type flash. These bindings only describe SPI. + +The two SPI flash memory controllers in the AST2500 each support two +chip selects. + +Required properties: + - compatible : Should be one of + "aspeed,ast2400-fmc" for the AST2400 Firmware Memory Controller + "aspeed,ast2400-spi" for the AST2400 SPI Flash memory Controller + "aspeed,ast2500-fmc" for the AST2500 Firmware Memory Controller + "aspeed,ast2500-spi" for the AST2500 SPI flash memory controllers + + - reg : the first contains the control register location and length, + the second contains the memory window mapping address and length + - #address-cells : must be 1 corresponding to chip select child binding + - #size-cells : must be 0 corresponding to chip select child binding + +Optional properties: + - interrupts : Should contain the interrupt for the dma device if an + FMC + +The child nodes are the SPI flash modules which must have a compatible +property as specified in bindings/mtd/jedec,spi-nor.txt + +Optionally, the child node can contain properties for SPI mode (may be +ignored): + - spi-max-frequency - max frequency of spi bus + + +Example: +fmc: fmc@1e620000 { + compatible = "aspeed,ast2500-fmc"; + reg = < 0x1e620000 0x94 + 0x20000000 0x02000000 >; + #address-cells = <1>; + #size-cells = <0>; + interrupts = <19>; + flash@0 { + reg = < 0 >; + compatible = "jedec,spi-nor"; + /* spi-max-frequency = <>; */ + /* m25p,fast-read; */ + #address-cells = <1>; + #size-cells = <1>; + }; +}; diff --git a/Documentation/devicetree/bindings/mtd/common.txt b/Documentation/devicetree/bindings/mtd/common.txt new file mode 100644 index 000000000000..fc068b923d7a --- /dev/null +++ b/Documentation/devicetree/bindings/mtd/common.txt @@ -0,0 +1,15 @@ +* Common properties of all MTD devices + +Optional properties: +- label: user-defined MTD device name. Can be used to assign user + friendly names to MTD devices (instead of the flash model or flash + controller based name) in order to ease flash device identification + and/or describe what they are used for. + +Example: + + flash@0 { + label = "System-firmware"; + + /* flash type specific properties */ + }; diff --git a/Documentation/devicetree/bindings/mtd/cortina,gemini-flash.txt b/Documentation/devicetree/bindings/mtd/cortina,gemini-flash.txt new file mode 100644 index 000000000000..3fa1b34d69ad --- /dev/null +++ b/Documentation/devicetree/bindings/mtd/cortina,gemini-flash.txt @@ -0,0 +1,24 @@ +Flash device on Cortina Systems Gemini SoC + +This flash is regular CFI compatible (Intel or AMD extended) flash chips with +some special bits that can be controlled by the machine's system controller. + +Required properties: +- compatible : must be "cortina,gemini-flash", "cfi-flash"; +- reg : memory address for the flash chip +- syscon : must be a phandle to the system controller +- bank-width : width in bytes of flash interface, should be <2> + +For the rest of the properties, see mtd-physmap.txt. + +The device tree may optionally contain sub-nodes describing partitions of the +address space. See partition.txt for more detail. + +Example: + +flash@30000000 { + compatible = "cortina,gemini-flash", "cfi-flash"; + reg = <0x30000000 0x01000000>; + syscon = <&syscon>; + bank-width = <2>; +}; diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt index 2c91c03e7eb0..3e920ec5c4d3 100644 --- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt +++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt @@ -14,6 +14,8 @@ Required properties: at25df641 at26df081a mr25h256 + mr25h10 + mr25h40 mx25l4005a mx25l1606e mx25l6405d diff --git a/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt b/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt index fb314f09861b..5ded66ad7aef 100644 --- a/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt +++ b/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt @@ -1,7 +1,13 @@ * Serial NOR flash controller for MTK MT81xx (and similar) Required properties: -- compatible: should be "mediatek,mt8173-nor"; +- compatible: The possible values are: + "mediatek,mt2701-nor" + "mediatek,mt7623-nor" + "mediatek,mt8173-nor" + For mt8173, compatible should be "mediatek,mt8173-nor". + For every other SoC, should contain both the SoC-specific compatible string + and "mediatek,mt8173-nor". - reg: physical base address and length of the controller's register - clocks: the phandle of the clocks needed by the nor controller - clock-names: the names of the clocks diff --git a/Documentation/devicetree/bindings/power/supply/axp20x_ac_power.txt b/Documentation/devicetree/bindings/power/supply/axp20x_ac_power.txt new file mode 100644 index 000000000000..826e8a879121 --- /dev/null +++ b/Documentation/devicetree/bindings/power/supply/axp20x_ac_power.txt @@ -0,0 +1,22 @@ +AXP20X and AXP22X PMICs' AC power supply + +Required Properties: + - compatible: One of: + "x-powers,axp202-ac-power-supply" + "x-powers,axp221-ac-power-supply" + +This node is a subnode of the axp20x PMIC. + +The AXP20X can read the current current and voltage supplied by AC by +reading ADC channels from the AXP20X ADC. + +The AXP22X is only able to tell if an AC power supply is present and +usable. + +Example: + +&axp209 { + ac_power_supply: ac-power-supply { + compatible = "x-powers,axp202-ac-power-supply"; + }; +}; diff --git a/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt b/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt index f1d7beec45bf..ba8d35f66cbe 100644 --- a/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt +++ b/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt @@ -3,6 +3,11 @@ AXP20x USB power supply Required Properties: -compatible: One of: "x-powers,axp202-usb-power-supply" "x-powers,axp221-usb-power-supply" + "x-powers,axp223-usb-power-supply" + +The AXP223 PMIC shares most of its behaviour with the AXP221 but has slight +variations such as the former being able to set the VBUS power supply max +current to 100mA, unlike the latter. This node is a subnode of the axp20x PMIC. diff --git a/Documentation/devicetree/bindings/power/supply/bq27xxx.txt b/Documentation/devicetree/bindings/power/supply/bq27xxx.txt new file mode 100644 index 000000000000..b0c95ef63e68 --- /dev/null +++ b/Documentation/devicetree/bindings/power/supply/bq27xxx.txt @@ -0,0 +1,36 @@ +Binding for TI BQ27XXX fuel gauge family + +Required properties: +- compatible: Should contain one of the following: + * "ti,bq27200" - BQ27200 + * "ti,bq27210" - BQ27210 + * "ti,bq27500" - deprecated, use revision specific property below + * "ti,bq27510" - deprecated, use revision specific property below + * "ti,bq27520" - deprecated, use revision specific property below + * "ti,bq27500-1" - BQ27500/1 + * "ti,bq27510g1" - BQ27510-g1 + * "ti,bq27510g2" - BQ27510-g2 + * "ti,bq27510g3" - BQ27510-g3 + * "ti,bq27520g1" - BQ27520-g1 + * "ti,bq27520g2" - BQ27520-g2 + * "ti,bq27520g3" - BQ27520-g3 + * "ti,bq27520g4" - BQ27520-g4 + * "ti,bq27530" - BQ27530 + * "ti,bq27531" - BQ27531 + * "ti,bq27541" - BQ27541 + * "ti,bq27542" - BQ27542 + * "ti,bq27546" - BQ27546 + * "ti,bq27742" - BQ27742 + * "ti,bq27545" - BQ27545 + * "ti,bq27421" - BQ27421 + * "ti,bq27425" - BQ27425 + * "ti,bq27441" - BQ27441 + * "ti,bq27621" - BQ27621 +- reg: integer, i2c address of the device. + +Example: + +bq27510g3 { + compatible = "ti,bq27510g3"; + reg = <0x55>; +}; diff --git a/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt b/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt index 65b88fac854b..06f8a5ddb68e 100644 --- a/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt +++ b/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt @@ -105,6 +105,22 @@ PROPERTIES regulation must be done externally to fully comply with the JEITA safety guidelines if this flag is set. +- usb_otg_in-supply: + Usage: optional + Value type: <phandle> + Description: Reference to the regulator supplying power to the USB_OTG_IN + pin. + +child nodes: +- otg-vbus: + Usage: optional + Description: This node defines a regulator used to control the direction + of VBUS voltage - specifically: whether to supply voltage + to VBUS for host mode operation of the OTG port, or allow + input voltage from external VBUS for charging. In the + hardware, the supply for this regulator comes from + usb_otg_in-supply. + EXAMPLE charger@1000 { compatible = "qcom,pm8941-charger"; @@ -128,4 +144,7 @@ charger@1000 { qcom,fast-charge-current-limit = <1000000>; qcom,dc-charge-current-limit = <1000000>; + usb_otg_in-supply = <&pm8941_5vs1>; + + otg-vbus {}; }; diff --git a/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt b/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt new file mode 100644 index 000000000000..a3719623a94f --- /dev/null +++ b/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt @@ -0,0 +1,23 @@ +SBS sbs-charger +~~~~~~~~~~ + +Required properties: + - compatible: "<vendor>,<part-number>", "sbs,sbs-charger" as fallback. The part + number compatible string might be used in order to take care of vendor + specific registers. + +Optional properties: +- interrupt-parent: Should be the phandle for the interrupt controller. Use in + conjunction with "interrupts". +- interrupts: Interrupt mapping for GPIO IRQ. Use in conjunction with + "interrupt-parent". If an interrupt is not provided the driver will switch + automatically to polling. + +Example: + + ltc4100@9 { + compatible = "lltc,ltc4100", "sbs,sbs-charger"; + reg = <0x9>; + interrupt-parent = <&gpio6>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; + }; diff --git a/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt b/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt index 3bf55757ceec..de45e1a2a4d9 100644 --- a/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt +++ b/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt @@ -8,8 +8,10 @@ Optional properties : - interrupts : Specify the interrupt to be used to trigger when the AC adapter is either plugged in or removed. - ti,ac-detect-gpios : This GPIO is optionally used to read the AC adapter - presence. This is a Host GPIO that is configured as an input and - connected to the bq24735. + status. This is a Host GPIO that is configured as an input and connected + to the ACOK pin on the bq24735. Note: for backwards compatibility reasons, + the GPIO must be active on AC adapter absence despite ACOK being active + (high) on AC adapter presence. - ti,charge-current : Used to control and set the charging current. This value must be between 128mA and 8.128A with a 64mA step resolution. The POR value is 0x0000h. This number is in mA (e.g. 8192), see spec for more information @@ -25,6 +27,8 @@ Optional properties : - ti,external-control : Indicates that the charger is configured externally and that the host should not attempt to enable/disable charging or set the charge voltage/current. + - poll-interval : In case 'interrupts' is not specified, poll AC adapter + presence with this interval (milliseconds). Example: diff --git a/Documentation/devicetree/bindings/power_supply/maxim,max14656.txt b/Documentation/devicetree/bindings/power_supply/maxim,max14656.txt new file mode 100644 index 000000000000..e03e85ae6572 --- /dev/null +++ b/Documentation/devicetree/bindings/power_supply/maxim,max14656.txt @@ -0,0 +1,25 @@ +Maxim MAX14656 / AL32 USB Charger Detector + +Required properties : +- compatible : "maxim,max14656"; +- reg: i2c slave address +- interrupt-parent: the phandle for the interrupt controller +- interrupts: interrupt line + +Example: + +&i2c2 { + clock-frequency = <50000>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i2c2>; + status = "okay"; + + max14656@35 { + compatible = "maxim,max14656"; + reg = <0x35>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_charger_detect>; + interrupt-parent = <&gpio6>; + interrupts = <26 IRQ_TYPE_LEVEL_HIGH>; + }; +}; diff --git a/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt b/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt new file mode 100644 index 000000000000..16ea1d3b2e9e --- /dev/null +++ b/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt @@ -0,0 +1,22 @@ +Cortina Systems Gemini timer + +This timer is embedded in the Cortina Systems Gemini SoCs. + +Required properties: + +- compatible : Must be "cortina,gemini-timer" +- reg : Should contain registers location and length +- interrupts : Should contain the three timer interrupts with + flags for rising edge +- syscon : a phandle to the global Gemini system controller + +Example: + +timer@43000000 { + compatible = "cortina,gemini-timer"; + reg = <0x43000000 0x1000>; + interrupts = <14 IRQ_TYPE_EDGE_RISING>, /* Timer 1 */ + <15 IRQ_TYPE_EDGE_RISING>, /* Timer 2 */ + <16 IRQ_TYPE_EDGE_RISING>; /* Timer 3 */ + syscon = <&syscon>; +}; diff --git a/Documentation/devicetree/bindings/timer/renesas,ostm.txt b/Documentation/devicetree/bindings/timer/renesas,ostm.txt new file mode 100644 index 000000000000..be3ae0fdf775 --- /dev/null +++ b/Documentation/devicetree/bindings/timer/renesas,ostm.txt @@ -0,0 +1,30 @@ +* Renesas OS Timer (OSTM) + +The OSTM is a multi-channel 32-bit timer/counter with fixed clock +source that can operate in either interval count down timer or free-running +compare match mode. + +Channels are independent from each other. + +Required Properties: + + - compatible: must be one or more of the following: + - "renesas,r7s72100-ostm" for the r7s72100 OSTM + - "renesas,ostm" for any OSTM + This is a fallback for the above renesas,*-ostm entries + + - reg: base address and length of the register block for a timer channel. + + - interrupts: interrupt specifier for the timer channel. + + - clocks: clock specifier for the timer channel. + +Example: R7S72100 (RZ/A1H) OSTM node + + ostm0: timer@fcfec000 { + compatible = "renesas,r7s72100-ostm", "renesas,ostm"; + reg = <0xfcfec000 0x30>; + interrupts = <GIC_SPI 102 IRQ_TYPE_EDGE_RISING>; + clocks = <&mstp5_clks R7S72100_CLK_OSTM0>; + power-domains = <&cpg_clocks>; + }; diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt index ca9d1eb46bc0..bf34d5b3a733 100644 --- a/Documentation/driver-model/devres.txt +++ b/Documentation/driver-model/devres.txt @@ -306,6 +306,11 @@ IRQ devm_request_any_context_irq() devm_request_irq() devm_request_threaded_irq() + devm_irq_alloc_descs() + devm_irq_alloc_desc() + devm_irq_alloc_desc_at() + devm_irq_alloc_desc_from() + devm_irq_alloc_descs_from() LED devm_led_classdev_register() diff --git a/Documentation/hwmon/hwmon-kernel-api.txt b/Documentation/hwmon/hwmon-kernel-api.txt index 2505ae67e2b6..53a806696c64 100644 --- a/Documentation/hwmon/hwmon-kernel-api.txt +++ b/Documentation/hwmon/hwmon-kernel-api.txt @@ -89,6 +89,10 @@ the call to devm_hwmon_device_register_with_groups or hwmon_device_register_with_info and if the automatic (device managed) removal would be too late. +All supported hwmon device registration functions only accept valid device +names. Device names including invalid characters (whitespace, '*', or '-') +will be rejected. The 'name' parameter is mandatory. + Using devm_hwmon_device_register_with_info() -------------------------------------------- diff --git a/Documentation/hwmon/lm70 b/Documentation/hwmon/lm70 index 1bb2db440671..c3a1f2ea017d 100644 --- a/Documentation/hwmon/lm70 +++ b/Documentation/hwmon/lm70 @@ -6,6 +6,8 @@ Supported chips: Datasheet: http://www.national.com/pf/LM/LM70.html * Texas Instruments TMP121/TMP123 Information: http://focus.ti.com/docs/prod/folders/print/tmp121.html + * Texas Instruments TMP122/TMP124 + Information: http://www.ti.com/product/tmp122 * National Semiconductor LM71 Datasheet: http://www.ti.com/product/LM71 * National Semiconductor LM74 @@ -35,8 +37,10 @@ As a real (in-tree) example of this "SPI protocol driver" interfacing with a "SPI master controller driver", see drivers/spi/spi_lm70llp.c and its associated documentation. -The LM74 and TMP121/TMP123 are very similar; main difference is 13-bit -temperature data (0.0625 degrees celsius resolution). +The LM74 and TMP121/TMP122/TMP123/TMP124 are very similar; main difference is +13-bit temperature data (0.0625 degrees celsius resolution). + +The TMP122/TMP124 also feature configurable temperature thresholds. The LM71 is also very similar; main difference is 14-bit temperature data (0.03125 degrees celsius resolution). diff --git a/Documentation/hwmon/sht21 b/Documentation/hwmon/sht21 index db17fda45c3e..47f4765db256 100644 --- a/Documentation/hwmon/sht21 +++ b/Documentation/hwmon/sht21 @@ -35,6 +35,7 @@ sysfs-Interface temp1_input - temperature input humidity1_input - humidity input +eic - Electronic Identification Code Notes ----- @@ -45,5 +46,5 @@ humidity and 66 ms for temperature. To keep self heating below 0.1 degree Celsius, the device should not be active for more than 10% of the time, e.g. maximum two measurements per second at the given resolution. -Different resolutions, the on-chip heater, using the CRC checksum and reading -the serial number are not supported yet. +Different resolutions, the on-chip heater, and using the CRC checksum +are not supported yet. diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface index 2cc95ad46604..fc337c317c67 100644 --- a/Documentation/hwmon/sysfs-interface +++ b/Documentation/hwmon/sysfs-interface @@ -86,8 +86,9 @@ given driver if the chip has the feature. name The chip name. This should be a short, lowercase string, not containing - spaces nor dashes, representing the chip name. This is - the only mandatory attribute. + whitespace, dashes, or the wildcard character '*'. + This attribute represents the chip name. It is the only + mandatory attribute. I2C devices get this attribute created automatically. RO diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt index 8a112dc304c3..34c3a1b50b9a 100644 --- a/Documentation/locking/ww-mutex-design.txt +++ b/Documentation/locking/ww-mutex-design.txt @@ -309,11 +309,15 @@ Design: normal mutex locks, which are far more common. As such there is only a small increase in code size if wait/wound mutexes are not used. + We maintain the following invariants for the wait list: + (1) Waiters with an acquire context are sorted by stamp order; waiters + without an acquire context are interspersed in FIFO order. + (2) Among waiters with contexts, only the first one can have other locks + acquired already (ctx->acquired > 0). Note that this waiter may come + after other waiters without contexts in the list. + In general, not much contention is expected. The locks are typically used to - serialize access to resources for devices. The only way to make wakeups - smarter would be at the cost of adding a field to struct mutex_waiter. This - would add overhead to all cases where normal mutexes are used, and - ww_mutexes are generally less performance sensitive. + serialize access to resources for devices. Lockdep: Special care has been taken to warn for as many cases of api abuse diff --git a/Documentation/media/uapi/v4l/pixfmt-007.rst b/Documentation/media/uapi/v4l/pixfmt-007.rst index 44bb5a7059b3..95a23a28c595 100644 --- a/Documentation/media/uapi/v4l/pixfmt-007.rst +++ b/Documentation/media/uapi/v4l/pixfmt-007.rst @@ -211,7 +211,13 @@ Colorspace sRGB (V4L2_COLORSPACE_SRGB) The :ref:`srgb` standard defines the colorspace used by most webcams and computer graphics. The default transfer function is ``V4L2_XFER_FUNC_SRGB``. The default Y'CbCr encoding is -``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is full range. +``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is limited range. + +Note that the :ref:`sycc` standard specifies full range quantization, +however all current capture hardware supported by the kernel convert +R'G'B' to limited range Y'CbCr. So choosing full range as the default +would break how applications interpret the quantization range. + The chromaticities of the primary colors and the white reference are: @@ -276,7 +282,7 @@ the following ``V4L2_YCBCR_ENC_601`` encoding as defined by :ref:`sycc`: Y' is clamped to the range [0…1] and Cb and Cr are clamped to the range [-0.5…0.5]. This transform is identical to one defined in SMPTE -170M/BT.601. The Y'CbCr quantization is full range. +170M/BT.601. The Y'CbCr quantization is limited range. .. _col-adobergb: @@ -288,10 +294,15 @@ The :ref:`adobergb` standard defines the colorspace used by computer graphics that use the AdobeRGB colorspace. This is also known as the :ref:`oprgb` standard. The default transfer function is ``V4L2_XFER_FUNC_ADOBERGB``. The default Y'CbCr encoding is -``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is full -range. The chromaticities of the primary colors and the white reference -are: +``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is limited +range. + +Note that the :ref:`oprgb` standard specifies full range quantization, +however all current capture hardware supported by the kernel convert +R'G'B' to limited range Y'CbCr. So choosing full range as the default +would break how applications interpret the quantization range. +The chromaticities of the primary colors and the white reference are: .. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.7cm}| @@ -344,7 +355,7 @@ the following ``V4L2_YCBCR_ENC_601`` encoding: Y' is clamped to the range [0…1] and Cb and Cr are clamped to the range [-0.5…0.5]. This transform is identical to one defined in SMPTE -170M/BT.601. The Y'CbCr quantization is full range. +170M/BT.601. The Y'CbCr quantization is limited range. .. _col-bt2020: diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index ba818ecce6f9..d2b0a8d81258 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -640,6 +640,10 @@ See also the subsection on "Cache Coherency" for a more thorough example. CONTROL DEPENDENCIES -------------------- +Control dependencies can be a bit tricky because current compilers do +not understand them. The purpose of this section is to help you prevent +the compiler's ignorance from breaking your code. + A load-load control dependency requires a full read memory barrier, not simply a data dependency barrier to make it work correctly. Consider the following bit of code: @@ -667,14 +671,15 @@ for load-store control dependencies, as in the following example: q = READ_ONCE(a); if (q) { - WRITE_ONCE(b, p); + WRITE_ONCE(b, 1); } -Control dependencies pair normally with other types of barriers. That -said, please note that READ_ONCE() is not optional! Without the -READ_ONCE(), the compiler might combine the load from 'a' with other -loads from 'a', and the store to 'b' with other stores to 'b', with -possible highly counterintuitive effects on ordering. +Control dependencies pair normally with other types of barriers. +That said, please note that neither READ_ONCE() nor WRITE_ONCE() +are optional! Without the READ_ONCE(), the compiler might combine the +load from 'a' with other loads from 'a'. Without the WRITE_ONCE(), +the compiler might combine the store to 'b' with other stores to 'b'. +Either can result in highly counterintuitive effects on ordering. Worse yet, if the compiler is able to prove (say) that the value of variable 'a' is always non-zero, it would be well within its rights @@ -682,7 +687,7 @@ to optimize the original example by eliminating the "if" statement as follows: q = a; - b = p; /* BUG: Compiler and CPU can both reorder!!! */ + b = 1; /* BUG: Compiler and CPU can both reorder!!! */ So don't leave out the READ_ONCE(). @@ -692,11 +697,11 @@ branches of the "if" statement as follows: q = READ_ONCE(a); if (q) { barrier(); - WRITE_ONCE(b, p); + WRITE_ONCE(b, 1); do_something(); } else { barrier(); - WRITE_ONCE(b, p); + WRITE_ONCE(b, 1); do_something_else(); } @@ -705,12 +710,12 @@ optimization levels: q = READ_ONCE(a); barrier(); - WRITE_ONCE(b, p); /* BUG: No ordering vs. load from a!!! */ + WRITE_ONCE(b, 1); /* BUG: No ordering vs. load from a!!! */ if (q) { - /* WRITE_ONCE(b, p); -- moved up, BUG!!! */ + /* WRITE_ONCE(b, 1); -- moved up, BUG!!! */ do_something(); } else { - /* WRITE_ONCE(b, p); -- moved up, BUG!!! */ + /* WRITE_ONCE(b, 1); -- moved up, BUG!!! */ do_something_else(); } @@ -723,10 +728,10 @@ memory barriers, for example, smp_store_release(): q = READ_ONCE(a); if (q) { - smp_store_release(&b, p); + smp_store_release(&b, 1); do_something(); } else { - smp_store_release(&b, p); + smp_store_release(&b, 1); do_something_else(); } @@ -735,10 +740,10 @@ ordering is guaranteed only when the stores differ, for example: q = READ_ONCE(a); if (q) { - WRITE_ONCE(b, p); + WRITE_ONCE(b, 1); do_something(); } else { - WRITE_ONCE(b, r); + WRITE_ONCE(b, 2); do_something_else(); } @@ -751,10 +756,10 @@ the needed conditional. For example: q = READ_ONCE(a); if (q % MAX) { - WRITE_ONCE(b, p); + WRITE_ONCE(b, 1); do_something(); } else { - WRITE_ONCE(b, r); + WRITE_ONCE(b, 2); do_something_else(); } @@ -763,7 +768,7 @@ equal to zero, in which case the compiler is within its rights to transform the above code into the following: q = READ_ONCE(a); - WRITE_ONCE(b, p); + WRITE_ONCE(b, 1); do_something_else(); Given this transformation, the CPU is not required to respect the ordering @@ -776,10 +781,10 @@ one, perhaps as follows: q = READ_ONCE(a); BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */ if (q % MAX) { - WRITE_ONCE(b, p); + WRITE_ONCE(b, 1); do_something(); } else { - WRITE_ONCE(b, r); + WRITE_ONCE(b, 2); do_something_else(); } @@ -812,30 +817,28 @@ not necessarily apply to code following the if-statement: q = READ_ONCE(a); if (q) { - WRITE_ONCE(b, p); + WRITE_ONCE(b, 1); } else { - WRITE_ONCE(b, r); + WRITE_ONCE(b, 2); } - WRITE_ONCE(c, 1); /* BUG: No ordering against the read from "a". */ + WRITE_ONCE(c, 1); /* BUG: No ordering against the read from 'a'. */ It is tempting to argue that there in fact is ordering because the compiler cannot reorder volatile accesses and also cannot reorder -the writes to "b" with the condition. Unfortunately for this line -of reasoning, the compiler might compile the two writes to "b" as +the writes to 'b' with the condition. Unfortunately for this line +of reasoning, the compiler might compile the two writes to 'b' as conditional-move instructions, as in this fanciful pseudo-assembly language: ld r1,a - ld r2,p - ld r3,r cmp r1,$0 - cmov,ne r4,r2 - cmov,eq r4,r3 + cmov,ne r4,$1 + cmov,eq r4,$2 st r4,b st $1,c A weakly ordered CPU would have no dependency of any sort between the load -from "a" and the store to "c". The control dependencies would extend +from 'a' and the store to 'c'. The control dependencies would extend only to the pair of cmov instructions and the store depending on them. In short, control dependencies apply only to the stores in the then-clause and else-clause of the if-statement in question (including functions @@ -843,7 +846,7 @@ invoked by those two clauses), not to code following that if-statement. Finally, control dependencies do -not- provide transitivity. This is demonstrated by two related examples, with the initial values of -x and y both being zero: +'x' and 'y' both being zero: CPU 0 CPU 1 ======================= ======================= @@ -915,6 +918,9 @@ In summary: (*) Control dependencies do -not- provide transitivity. If you need transitivity, use smp_mb(). + (*) Compilers do not understand control dependencies. It is therefore + your job to ensure that they do not break your code. + SMP BARRIER PAIRING ------------------- diff --git a/Documentation/mtd/intel-spi.txt b/Documentation/mtd/intel-spi.txt new file mode 100644 index 000000000000..bc357729c2cb --- /dev/null +++ b/Documentation/mtd/intel-spi.txt @@ -0,0 +1,88 @@ +Upgrading BIOS using intel-spi +------------------------------ + +Many Intel CPUs like Baytrail and Braswell include SPI serial flash host +controller which is used to hold BIOS and other platform specific data. +Since contents of the SPI serial flash is crucial for machine to function, +it is typically protected by different hardware protection mechanisms to +avoid accidental (or on purpose) overwrite of the content. + +Not all manufacturers protect the SPI serial flash, mainly because it +allows upgrading the BIOS image directly from an OS. + +The intel-spi driver makes it possible to read and write the SPI serial +flash, if certain protection bits are not set and locked. If it finds +any of them set, the whole MTD device is made read-only to prevent +partial overwrites. By default the driver exposes SPI serial flash +contents as read-only but it can be changed from kernel command line, +passing "intel-spi.writeable=1". + +Please keep in mind that overwriting the BIOS image on SPI serial flash +might render the machine unbootable and requires special equipment like +Dediprog to revive. You have been warned! + +Below are the steps how to upgrade MinnowBoard MAX BIOS directly from +Linux. + + 1) Download and extract the latest Minnowboard MAX BIOS SPI image + [1]. At the time writing this the latest image is v92. + + 2) Install mtd-utils package [2]. We need this in order to erase the SPI + serial flash. Distros like Debian and Fedora have this prepackaged with + name "mtd-utils". + + 3) Add "intel-spi.writeable=1" to the kernel command line and reboot + the board (you can also reload the driver passing "writeable=1" as + module parameter to modprobe). + + 4) Once the board is up and running again, find the right MTD partition + (it is named as "BIOS"): + + # cat /proc/mtd + dev: size erasesize name + mtd0: 00800000 00001000 "BIOS" + + So here it will be /dev/mtd0 but it may vary. + + 5) Make backup of the existing image first: + + # dd if=/dev/mtd0ro of=bios.bak + 16384+0 records in + 16384+0 records out + 8388608 bytes (8.4 MB) copied, 10.0269 s, 837 kB/s + + 6) Verify the backup + + # sha1sum /dev/mtd0ro bios.bak + fdbb011920572ca6c991377c4b418a0502668b73 /dev/mtd0ro + fdbb011920572ca6c991377c4b418a0502668b73 bios.bak + + The SHA1 sums must match. Otherwise do not continue any further! + + 7) Erase the SPI serial flash. After this step, do not reboot the + board! Otherwise it will not start anymore. + + # flash_erase /dev/mtd0 0 0 + Erasing 4 Kibyte @ 7ff000 -- 100 % complete + + 8) Once completed without errors you can write the new BIOS image: + + # dd if=MNW2MAX1.X64.0092.R01.1605221712.bin of=/dev/mtd0 + + 9) Verify that the new content of the SPI serial flash matches the new + BIOS image: + + # sha1sum /dev/mtd0ro MNW2MAX1.X64.0092.R01.1605221712.bin + 9b4df9e4be2057fceec3a5529ec3d950836c87a2 /dev/mtd0ro + 9b4df9e4be2057fceec3a5529ec3d950836c87a2 MNW2MAX1.X64.0092.R01.1605221712.bin + + The SHA1 sums should match. + + 10) Now you can reboot your board and observe the new BIOS starting up + properly. + +References +---------- + +[1] https://firmware.intel.com/sites/default/files/MinnowBoard.MAX_.X64.92.R01.zip +[2] http://www.linux-mtd.infradead.org/ diff --git a/Documentation/scheduler/sched-deadline.txt b/Documentation/scheduler/sched-deadline.txt index 8e37b0ba2c9d..cbc1b46cbf70 100644 --- a/Documentation/scheduler/sched-deadline.txt +++ b/Documentation/scheduler/sched-deadline.txt @@ -408,6 +408,11 @@ CONTENTS * the new scheduling related syscalls that manipulate it, i.e., sched_setattr() and sched_getattr() are implemented. + For debugging purposes, the leftover runtime and absolute deadline of a + SCHED_DEADLINE task can be retrieved through /proc/<pid>/sched (entries + dl.runtime and dl.deadline, both values in ns). A programmatic way to + retrieve these values from production code is under discussion. + 4.3 Default behavior --------------------- @@ -476,6 +481,7 @@ CONTENTS Still missing: + - programmatic way to retrieve current runtime and absolute deadline - refinements to deadline inheritance, especially regarding the possibility of retaining bandwidth isolation among non-interacting tasks. This is being studied from both theoretical and practical points of view, and diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt index a03f0d944fe6..d8fce3e78457 100644 --- a/Documentation/scheduler/sched-rt-group.txt +++ b/Documentation/scheduler/sched-rt-group.txt @@ -158,11 +158,11 @@ as its prone to starvation without deadline scheduling. Consider two sibling groups A and B; both have 50% bandwidth, but A's period is twice the length of B's. -* group A: period=100000us, runtime=10000us - - this runs for 0.01s once every 0.1s +* group A: period=100000us, runtime=50000us + - this runs for 0.05s once every 0.1s -* group B: period= 50000us, runtime=10000us - - this runs for 0.01s twice every 0.1s (or once every 0.05 sec). +* group B: period= 50000us, runtime=25000us + - this runs for 0.025s twice every 0.1s (or once every 0.05 sec). This means that currently a while (1) loop in A will run for the full period of B and can starve B's tasks (assuming they are of lower priority) for a whole diff --git a/Documentation/timers/timer_stats.txt b/Documentation/timers/timer_stats.txt deleted file mode 100644 index de835ee97455..000000000000 --- a/Documentation/timers/timer_stats.txt +++ /dev/null @@ -1,73 +0,0 @@ -timer_stats - timer usage statistics ------------------------------------- - -timer_stats is a debugging facility to make the timer (ab)usage in a Linux -system visible to kernel and userspace developers. If enabled in the config -but not used it has almost zero runtime overhead, and a relatively small -data structure overhead. Even if collection is enabled runtime all the -locking is per-CPU and lookup is hashed. - -timer_stats should be used by kernel and userspace developers to verify that -their code does not make unduly use of timers. This helps to avoid unnecessary -wakeups, which should be avoided to optimize power consumption. - -It can be enabled by CONFIG_TIMER_STATS in the "Kernel hacking" configuration -section. - -timer_stats collects information about the timer events which are fired in a -Linux system over a sample period: - -- the pid of the task(process) which initialized the timer -- the name of the process which initialized the timer -- the function where the timer was initialized -- the callback function which is associated to the timer -- the number of events (callbacks) - -timer_stats adds an entry to /proc: /proc/timer_stats - -This entry is used to control the statistics functionality and to read out the -sampled information. - -The timer_stats functionality is inactive on bootup. - -To activate a sample period issue: -# echo 1 >/proc/timer_stats - -To stop a sample period issue: -# echo 0 >/proc/timer_stats - -The statistics can be retrieved by: -# cat /proc/timer_stats - -While sampling is enabled, each readout from /proc/timer_stats will see -newly updated statistics. Once sampling is disabled, the sampled information -is kept until a new sample period is started. This allows multiple readouts. - -Sample output of /proc/timer_stats: - -Timerstats sample period: 3.888770 s - 12, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) - 15, 1 swapper hcd_submit_urb (rh_timer_func) - 4, 959 kedac schedule_timeout (process_timeout) - 1, 0 swapper page_writeback_init (wb_timer_fn) - 28, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) - 22, 2948 IRQ 4 tty_flip_buffer_push (delayed_work_timer_fn) - 3, 3100 bash schedule_timeout (process_timeout) - 1, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) - 1, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) - 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) - 1, 2292 ip __netdev_watchdog_up (dev_watchdog) - 1, 23 events/1 do_cache_clean (delayed_work_timer_fn) -90 total events, 30.0 events/sec - -The first column is the number of events, the second column the pid, the third -column is the name of the process. The forth column shows the function which -initialized the timer and in parenthesis the callback function which was -executed on expiry. - - Thomas, Ingo - -Added flag to indicate 'deferrable timer' in /proc/timer_stats. A deferrable -timer will appear as follows - 10D, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) - diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt index 95a4d34af3fd..b8527c6b7646 100644 --- a/Documentation/x86/zero-page.txt +++ b/Documentation/x86/zero-page.txt @@ -31,6 +31,8 @@ Offset Proto Name Meaning 1E9/001 ALL eddbuf_entries Number of entries in eddbuf (below) 1EA/001 ALL edd_mbr_sig_buf_entries Number of entries in edd_mbr_sig_buffer (below) +1EB/001 ALL kbd_status Numlock is enabled +1EC/001 ALL secure_boot Secure boot is enabled in the firmware 1EF/001 ALL sentinel Used to detect broken bootloaders 290/040 ALL edd_mbr_sig_buffer EDD MBR signatures 2D0/A00 ALL e820_map E820 memory map table diff --git a/MAINTAINERS b/MAINTAINERS index 107c10e8f2d2..6f39cf610ecf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -643,7 +643,7 @@ S: Maintained F: drivers/gpio/gpio-altera.c ALTERA SYSTEM RESOURCE DRIVER FOR ARRIA10 DEVKIT -M: Thor Thayer <tthayer@opensource.altera.com> +M: Thor Thayer <thor.thayer@linux.intel.com> S: Maintained F: drivers/gpio/gpio-altera-a10sr.c F: drivers/mfd/altera-a10sr.c @@ -877,8 +877,8 @@ S: Odd fixes F: drivers/hwmon/applesmc.c APPLETALK NETWORK LAYER -M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> -S: Maintained +L: netdev@vger.kernel.org +S: Odd fixes F: drivers/net/appletalk/ F: net/appletalk/ @@ -1788,7 +1788,7 @@ S: Maintained F: drivers/clk/socfpga/ ARM/SOCFPGA EDAC SUPPORT -M: Thor Thayer <tthayer@opensource.altera.com> +M: Thor Thayer <thor.thayer@linux.intel.com> S: Maintained F: drivers/edac/altera_edac. @@ -6727,9 +6727,8 @@ S: Odd Fixes F: drivers/tty/ipwireless/ IPX NETWORK LAYER -M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> L: netdev@vger.kernel.org -S: Maintained +S: Odd fixes F: include/net/ipx.h F: include/uapi/linux/ipx.h F: net/ipx/ @@ -7501,8 +7500,8 @@ S: Maintained F: drivers/misc/lkdtm* LLC (802.2) -M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> -S: Maintained +L: netdev@vger.kernel.org +S: Odd fixes F: include/linux/llc.h F: include/uapi/linux/llc.h F: include/net/llc* @@ -7535,6 +7534,7 @@ S: Maintained F: Documentation/hwmon/lm90 F: Documentation/devicetree/bindings/hwmon/lm90.txt F: drivers/hwmon/lm90.c +F: include/dt-bindings/thermal/lm90.h LM95234 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> @@ -13373,10 +13373,8 @@ S: Maintained F: drivers/input/misc/wistron_btns.c WL3501 WIRELESS PCMCIA CARD DRIVER -M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> L: linux-wireless@vger.kernel.org -W: http://oops.ghostprotocols.net:81/blog -S: Maintained +S: Odd fixes F: drivers/net/wireless/wl3501* WOLFSON MICROELECTRONICS DRIVERS @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc8 +EXTRAVERSION = NAME = Fearless Coyote # *DOCUMENTATION* @@ -87,10 +87,12 @@ endif ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4 ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),) quiet=silent_ + tools_silent=s endif else # make-3.8x ifneq ($(filter s% -s%,$(MAKEFLAGS)),) quiet=silent_ + tools_silent=-s endif endif @@ -1607,11 +1609,11 @@ image_name: # Clear a bunch of variables before executing the submake tools/: FORCE $(Q)mkdir -p $(objtree)/tools - $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ + $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ tools/%: FORCE $(Q)mkdir -p $(objtree)/tools - $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $* + $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $* # Single targets # --------------------------------------------------------------------------- diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild index bf8475ce85ee..baa152b9348e 100644 --- a/arch/alpha/include/asm/Kbuild +++ b/arch/alpha/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += exec.h generic-y += export.h generic-y += irq_work.h diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 54d8616644e2..9d27a7d333dc 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1145,7 +1145,7 @@ struct rusage32 { SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) { struct rusage32 r; - cputime_t utime, stime; + u64 utime, stime; unsigned long utime_jiffies, stime_jiffies; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN) @@ -1155,16 +1155,16 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) switch (who) { case RUSAGE_SELF: task_cputime(current, &utime, &stime); - utime_jiffies = cputime_to_jiffies(utime); - stime_jiffies = cputime_to_jiffies(stime); + utime_jiffies = nsecs_to_jiffies(utime); + stime_jiffies = nsecs_to_jiffies(stime); jiffies_to_timeval32(utime_jiffies, &r.ru_utime); jiffies_to_timeval32(stime_jiffies, &r.ru_stime); r.ru_minflt = current->min_flt; r.ru_majflt = current->maj_flt; break; case RUSAGE_CHILDREN: - utime_jiffies = cputime_to_jiffies(current->signal->cutime); - stime_jiffies = cputime_to_jiffies(current->signal->cstime); + utime_jiffies = nsecs_to_jiffies(current->signal->cutime); + stime_jiffies = nsecs_to_jiffies(current->signal->cstime); jiffies_to_timeval32(utime_jiffies, &r.ru_utime); jiffies_to_timeval32(stime_jiffies, &r.ru_stime); r.ru_minflt = current->signal->cmin_flt; diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index c332604606dd..63a04013d05a 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += auxvec.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 028d2b70e3b5..f57ec511e7ae 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -824,6 +824,7 @@ CONFIG_QCOM_SMSM=y CONFIG_QCOM_WCNSS_CTRL=m CONFIG_ROCKCHIP_PM_DOMAINS=y CONFIG_COMMON_CLK_QCOM=y +CONFIG_QCOM_CLK_RPM=y CONFIG_CHROME_PLATFORMS=y CONFIG_STAGING_BOARD=y CONFIG_CROS_EC_CHARDEV=m diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index efb21757d41f..b14e8c7d71bd 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += bitsperlong.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += early_ioremap.h generic-y += emergency-restart.h diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 0b06f5341b45..e4e6a9d6a825 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -55,6 +55,7 @@ void efi_virtmap_unload(void); #define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) #define __efi_call_early(f, ...) f(__VA_ARGS__) +#define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (false) #define efi_call_proto(protocol, f, instance, ...) \ diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 1f59ea051bab..b7e0125c0bbf 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -478,11 +478,10 @@ extern unsigned long __must_check arm_copy_from_user(void *to, const void __user *from, unsigned long n); static inline unsigned long __must_check -__copy_from_user(void *to, const void __user *from, unsigned long n) +__arch_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned int __ua_flags; - check_object_size(to, n, false); __ua_flags = uaccess_save_and_enable(); n = arm_copy_from_user(to, from, n); uaccess_restore(__ua_flags); @@ -495,18 +494,15 @@ extern unsigned long __must_check __copy_to_user_std(void __user *to, const void *from, unsigned long n); static inline unsigned long __must_check -__copy_to_user(void __user *to, const void *from, unsigned long n) +__arch_copy_to_user(void __user *to, const void *from, unsigned long n) { #ifndef CONFIG_UACCESS_WITH_MEMCPY unsigned int __ua_flags; - - check_object_size(from, n, true); __ua_flags = uaccess_save_and_enable(); n = arm_copy_to_user(to, from, n); uaccess_restore(__ua_flags); return n; #else - check_object_size(from, n, true); return arm_copy_to_user(to, from, n); #endif } @@ -526,25 +522,49 @@ __clear_user(void __user *addr, unsigned long n) } #else -#define __copy_from_user(to, from, n) (memcpy(to, (void __force *)from, n), 0) -#define __copy_to_user(to, from, n) (memcpy((void __force *)to, from, n), 0) +#define __arch_copy_from_user(to, from, n) \ + (memcpy(to, (void __force *)from, n), 0) +#define __arch_copy_to_user(to, from, n) \ + (memcpy((void __force *)to, from, n), 0) #define __clear_user(addr, n) (memset((void __force *)addr, 0, n), 0) #endif -static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) +static inline unsigned long __must_check +__copy_from_user(void *to, const void __user *from, unsigned long n) +{ + check_object_size(to, n, false); + return __arch_copy_from_user(to, from, n); +} + +static inline unsigned long __must_check +copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; + + check_object_size(to, n, false); + if (likely(access_ok(VERIFY_READ, from, n))) - res = __copy_from_user(to, from, n); + res = __arch_copy_from_user(to, from, n); if (unlikely(res)) memset(to + (n - res), 0, res); return res; } -static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) +static inline unsigned long __must_check +__copy_to_user(void __user *to, const void *from, unsigned long n) { + check_object_size(from, n, true); + + return __arch_copy_to_user(to, from, n); +} + +static inline unsigned long __must_check +copy_to_user(void __user *to, const void *from, unsigned long n) +{ + check_object_size(from, n, true); + if (access_ok(VERIFY_WRITE, to, n)) - n = __copy_to_user(to, from, n); + n = __arch_copy_to_user(to, from, n); return n; } diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S index 8ecfd15c3a02..df73914e81c8 100644 --- a/arch/arm/lib/getuser.S +++ b/arch/arm/lib/getuser.S @@ -67,7 +67,7 @@ ENTRY(__get_user_4) ENDPROC(__get_user_4) ENTRY(__get_user_8) - check_uaccess r0, 8, r1, r2, __get_user_bad + check_uaccess r0, 8, r1, r2, __get_user_bad8 #ifdef CONFIG_THUMB2_KERNEL 5: TUSER(ldr) r2, [r0] 6: TUSER(ldr) r3, [r0, #4] diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig index 2bb4b09f079e..ad7d604ff001 100644 --- a/arch/arm/mach-shmobile/Kconfig +++ b/arch/arm/mach-shmobile/Kconfig @@ -57,6 +57,7 @@ config ARCH_R7S72100 select PM select PM_GENERIC_DOMAINS select SYS_SUPPORTS_SH_MTU2 + select RENESAS_OSTM config ARCH_R8A73A4 bool "R-Mobile APE6 (R8A73A40)" diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 111742126897..f7dfd6d58659 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -96,7 +96,7 @@ config ARM64 select HAVE_RCU_TABLE_FREE select HAVE_SYSCALL_TRACEPOINTS select HAVE_KPROBES - select HAVE_KRETPROBES if HAVE_KPROBES + select HAVE_KRETPROBES select IOMMU_DMA if IOMMU_SUPPORT select IRQ_DOMAIN select IRQ_FORCED_THREADING diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 8365a84c2640..a12f1afc95a3 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -1,6 +1,5 @@ generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += delay.h generic-y += div64.h generic-y += dma.h diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index eaa5bbe3fa87..b4b34004a21e 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -29,41 +29,29 @@ #include <clocksource/arm_arch_timer.h> -#if IS_ENABLED(CONFIG_FSL_ERRATUM_A008585) +#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND) extern struct static_key_false arch_timer_read_ool_enabled; -#define needs_fsl_a008585_workaround() \ +#define needs_unstable_timer_counter_workaround() \ static_branch_unlikely(&arch_timer_read_ool_enabled) #else -#define needs_fsl_a008585_workaround() false +#define needs_unstable_timer_counter_workaround() false #endif -u32 __fsl_a008585_read_cntp_tval_el0(void); -u32 __fsl_a008585_read_cntv_tval_el0(void); -u64 __fsl_a008585_read_cntvct_el0(void); -/* - * The number of retries is an arbitrary value well beyond the highest number - * of iterations the loop has been observed to take. - */ -#define __fsl_a008585_read_reg(reg) ({ \ - u64 _old, _new; \ - int _retries = 200; \ - \ - do { \ - _old = read_sysreg(reg); \ - _new = read_sysreg(reg); \ - _retries--; \ - } while (unlikely(_old != _new) && _retries); \ - \ - WARN_ON_ONCE(!_retries); \ - _new; \ -}) +struct arch_timer_erratum_workaround { + const char *id; /* Indicate the Erratum ID */ + u32 (*read_cntp_tval_el0)(void); + u32 (*read_cntv_tval_el0)(void); + u64 (*read_cntvct_el0)(void); +}; + +extern const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround; #define arch_timer_reg_read_stable(reg) \ ({ \ u64 _val; \ - if (needs_fsl_a008585_workaround()) \ - _val = __fsl_a008585_read_##reg(); \ + if (needs_unstable_timer_counter_workaround()) \ + _val = timer_unstable_counter_workaround->read_##reg();\ else \ _val = read_sysreg(reg); \ _val; \ diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 0b6b1633017f..e7445281e534 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -50,6 +50,7 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); #define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) #define __efi_call_early(f, ...) f(__VA_ARGS__) +#define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (true) #define efi_call_proto(protocol, f, instance, ...) \ diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild index 241b9b9729d8..3d7ef2c17a7c 100644 --- a/arch/avr32/include/asm/Kbuild +++ b/arch/avr32/include/asm/Kbuild @@ -1,6 +1,5 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += delay.h generic-y += device.h generic-y += div64.h diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild index 2fb67b59d188..d6fa60b158be 100644 --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += auxvec.h generic-y += bitsperlong.h generic-y += bugs.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 64465e7e2245..4e9f57433f3a 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -5,7 +5,6 @@ generic-y += barrier.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild index 1778805f6380..9f19e19bff9d 100644 --- a/arch/cris/include/asm/Kbuild +++ b/arch/cris/include/asm/Kbuild @@ -4,7 +4,6 @@ generic-y += barrier.h generic-y += bitsperlong.h generic-y += clkdev.h generic-y += cmpxchg.h -generic-y += cputime.h generic-y += device.h generic-y += div64.h generic-y += errno.h diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild index 1fa084cf1a43..0f5b0d5d313c 100644 --- a/arch/frv/include/asm/Kbuild +++ b/arch/frv/include/asm/Kbuild @@ -1,6 +1,5 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += exec.h generic-y += irq_work.h generic-y += mcs_spinlock.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index 373cb23301e3..5efd0c87f3c0 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -5,7 +5,6 @@ generic-y += bugs.h generic-y += cacheflush.h generic-y += checksum.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += delay.h generic-y += device.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index db8ddabc6bd2..a43a7c90e4af 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -6,7 +6,6 @@ generic-y += barrier.h generic-y += bug.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/ia64/include/asm/cputime.h b/arch/ia64/include/asm/cputime.h index e2d3f5baf265..3d665c0627a8 100644 --- a/arch/ia64/include/asm/cputime.h +++ b/arch/ia64/include/asm/cputime.h @@ -18,11 +18,7 @@ #ifndef __IA64_CPUTIME_H #define __IA64_CPUTIME_H -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -# include <asm-generic/cputime.h> -#else -# include <asm/processor.h> -# include <asm-generic/cputime_nsecs.h> +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE extern void arch_vtime_task_switch(struct task_struct *tsk); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index c7026429816b..8742d741d19a 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -27,6 +27,12 @@ struct thread_info { mm_segment_t addr_limit; /* user-level address space limit */ int preempt_count; /* 0=premptable, <0=BUG; will also serve as bh-counter */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + __u64 utime; + __u64 stime; + __u64 gtime; + __u64 hardirq_time; + __u64 softirq_time; + __u64 idle_time; __u64 ac_stamp; __u64 ac_leave; __u64 ac_stime; diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S index c9b5e942f671..3204fddc439c 100644 --- a/arch/ia64/kernel/head.S +++ b/arch/ia64/kernel/head.S @@ -1031,7 +1031,7 @@ GLOBAL_ENTRY(ia64_native_sched_clock) END(ia64_native_sched_clock) #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -GLOBAL_ENTRY(cycle_to_cputime) +GLOBAL_ENTRY(cycle_to_nsec) alloc r16=ar.pfs,1,0,0,0 addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0 ;; @@ -1047,7 +1047,7 @@ GLOBAL_ENTRY(cycle_to_cputime) ;; shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT br.ret.sptk.many rp -END(cycle_to_cputime) +END(cycle_to_nsec) #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_IA64_BRL_EMU diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 7ec7acc844c2..c483ece3eb84 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -619,6 +619,8 @@ setup_arch (char **cmdline_p) check_sal_cache_flush(); #endif paging_init(); + + clear_sched_clock_stable(); } /* diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 71775b95d6cc..faa116822c4c 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -21,6 +21,7 @@ #include <linux/timex.h> #include <linux/timekeeper_internal.h> #include <linux/platform_device.h> +#include <linux/cputime.h> #include <asm/machvec.h> #include <asm/delay.h> @@ -59,18 +60,43 @@ static struct clocksource *itc_clocksource; #include <linux/kernel_stat.h> -extern cputime_t cycle_to_cputime(u64 cyc); +extern u64 cycle_to_nsec(u64 cyc); -void vtime_account_user(struct task_struct *tsk) +void vtime_flush(struct task_struct *tsk) { - cputime_t delta_utime; struct thread_info *ti = task_thread_info(tsk); + u64 delta; - if (ti->ac_utime) { - delta_utime = cycle_to_cputime(ti->ac_utime); - account_user_time(tsk, delta_utime); - ti->ac_utime = 0; + if (ti->utime) + account_user_time(tsk, cycle_to_nsec(ti->utime)); + + if (ti->gtime) + account_guest_time(tsk, cycle_to_nsec(ti->gtime)); + + if (ti->idle_time) + account_idle_time(cycle_to_nsec(ti->idle_time)); + + if (ti->stime) { + delta = cycle_to_nsec(ti->stime); + account_system_index_time(tsk, delta, CPUTIME_SYSTEM); + } + + if (ti->hardirq_time) { + delta = cycle_to_nsec(ti->hardirq_time); + account_system_index_time(tsk, delta, CPUTIME_IRQ); + } + + if (ti->softirq_time) { + delta = cycle_to_nsec(ti->softirq_time)); + account_system_index_time(tsk, delta, CPUTIME_SOFTIRQ); } + + ti->utime = 0; + ti->gtime = 0; + ti->idle_time = 0; + ti->stime = 0; + ti->hardirq_time = 0; + ti->softirq_time = 0; } /* @@ -83,7 +109,7 @@ void arch_vtime_task_switch(struct task_struct *prev) struct thread_info *pi = task_thread_info(prev); struct thread_info *ni = task_thread_info(current); - pi->ac_stamp = ni->ac_stamp; + ni->ac_stamp = pi->ac_stamp; ni->ac_stime = ni->ac_utime = 0; } @@ -91,18 +117,15 @@ void arch_vtime_task_switch(struct task_struct *prev) * Account time for a transition between system, hard irq or soft irq state. * Note that this function is called with interrupts enabled. */ -static cputime_t vtime_delta(struct task_struct *tsk) +static __u64 vtime_delta(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); - cputime_t delta_stime; - __u64 now; + __u64 now, delta_stime; WARN_ON_ONCE(!irqs_disabled()); now = ia64_get_itc(); - - delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp)); - ti->ac_stime = 0; + delta_stime = now - ti->ac_stamp; ti->ac_stamp = now; return delta_stime; @@ -110,15 +133,25 @@ static cputime_t vtime_delta(struct task_struct *tsk) void vtime_account_system(struct task_struct *tsk) { - cputime_t delta = vtime_delta(tsk); - - account_system_time(tsk, 0, delta); + struct thread_info *ti = task_thread_info(tsk); + __u64 stime = vtime_delta(tsk); + + if ((tsk->flags & PF_VCPU) && !irq_count()) + ti->gtime += stime; + else if (hardirq_count()) + ti->hardirq_time += stime; + else if (in_serving_softirq()) + ti->softirq_time += stime; + else + ti->stime += stime; } EXPORT_SYMBOL_GPL(vtime_account_system); void vtime_account_idle(struct task_struct *tsk) { - account_idle_time(vtime_delta(tsk)); + struct thread_info *ti = task_thread_info(tsk); + + ti->idle_time += vtime_delta(tsk); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild index 860e440611c9..652100b64a71 100644 --- a/arch/m32r/include/asm/Kbuild +++ b/arch/m32r/include/asm/Kbuild @@ -1,6 +1,5 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += exec.h generic-y += irq_work.h generic-y += kvm_para.h diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 1f2e5d31cb24..6c76d6c24b3d 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += barrier.h generic-y += bitsperlong.h generic-y += clkdev.h -generic-y += cputime.h generic-y += device.h generic-y += emergency-restart.h generic-y += errno.h diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild index 167150c701d1..d3731f0db73b 100644 --- a/arch/metag/include/asm/Kbuild +++ b/arch/metag/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += auxvec.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += dma.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index b0ae88c9fed9..6275eb051801 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += barrier.h generic-y += clkdev.h -generic-y += cputime.h generic-y += device.h generic-y += exec.h generic-y += irq_work.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 3269b742a75e..994b1c4392be 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -1,7 +1,6 @@ # MIPS headers generic-(CONFIG_GENERIC_CSUM) += checksum.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += dma-contiguous.h generic-y += emergency-restart.h diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 9c7f3e136d50..4a2ff3953b99 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -99,15 +99,7 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) #undef TASK_SIZE #define TASK_SIZE TASK_SIZE32 -#undef cputime_to_timeval -#define cputime_to_timeval cputime_to_compat_timeval -static __inline__ void -cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value) -{ - unsigned long jiffies = cputime_to_jiffies(cputime); - - value->tv_usec = (jiffies % HZ) * (1000000L / HZ); - value->tv_sec = jiffies / HZ; -} +#undef ns_to_timeval +#define ns_to_timeval ns_to_compat_timeval #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 1ab34322dd97..3916404e7fd1 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -102,15 +102,7 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) #undef TASK_SIZE #define TASK_SIZE TASK_SIZE32 -#undef cputime_to_timeval -#define cputime_to_timeval cputime_to_compat_timeval -static __inline__ void -cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value) -{ - unsigned long jiffies = cputime_to_jiffies(cputime); - - value->tv_usec = (jiffies % HZ) * (1000000L / HZ); - value->tv_sec = jiffies / HZ; -} +#undef ns_to_timeval +#define ns_to_timeval ns_to_compat_timeval #include "../../../fs/binfmt_elf.c" diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild index 1c8dd0f5cd5d..97f64c723a0c 100644 --- a/arch/mn10300/include/asm/Kbuild +++ b/arch/mn10300/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += barrier.h generic-y += clkdev.h -generic-y += cputime.h generic-y += exec.h generic-y += irq_work.h generic-y += mcs_spinlock.h diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index d63330e88379..35b0e883761a 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -6,7 +6,6 @@ generic-y += bitsperlong.h generic-y += bug.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index 2832f031fb11..ef8d1ccc3e45 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -12,7 +12,6 @@ generic-y += checksum.h generic-y += clkdev.h generic-y += cmpxchg-local.h generic-y += cmpxchg.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index 91f53c07f410..4e179d770d69 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += auxvec.h generic-y += barrier.h generic-y += clkdev.h -generic-y += cputime.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h diff --git a/arch/parisc/kernel/binfmt_elf32.c b/arch/parisc/kernel/binfmt_elf32.c index 00dc66f9c2ba..f2adcf33f8f2 100644 --- a/arch/parisc/kernel/binfmt_elf32.c +++ b/arch/parisc/kernel/binfmt_elf32.c @@ -91,14 +91,7 @@ struct elf_prpsinfo32 current->thread.map_base = DEFAULT_MAP_BASE32; \ current->thread.task_size = DEFAULT_TASK_SIZE32 \ -#undef cputime_to_timeval -#define cputime_to_timeval cputime_to_compat_timeval -static __inline__ void -cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value) -{ - unsigned long jiffies = cputime_to_jiffies(cputime); - value->tv_usec = (jiffies % HZ) * (1000000L / HZ); - value->tv_sec = jiffies / HZ; -} +#undef ns_to_timeval +#define ns_to_timeval ns_to_compat_timeval #include "../../../fs/binfmt_elf.c" diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 2e66a887788e..068ed3607bac 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -36,6 +36,7 @@ #undef PCI_DEBUG #include <linux/proc_fs.h> #include <linux/export.h> +#include <linux/sched.h> #include <asm/processor.h> #include <asm/sections.h> @@ -176,6 +177,7 @@ void __init setup_arch(char **cmdline_p) conswitchp = &dummy_con; /* we use do_take_over_console() later ! */ #endif + clear_sched_clock_stable(); } /* diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi index c744569a20e1..a97296c64eb2 100644 --- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi @@ -678,5 +678,6 @@ compatible = "fsl,t2080-l2-cache-controller"; reg = <0xc20000 0x40000>; next-level-cache = <&cpc>; + interrupts = <16 2 1 9>; }; }; diff --git a/arch/powerpc/include/asm/accounting.h b/arch/powerpc/include/asm/accounting.h index c133246df467..3abcf98ed2e0 100644 --- a/arch/powerpc/include/asm/accounting.h +++ b/arch/powerpc/include/asm/accounting.h @@ -12,9 +12,17 @@ /* Stuff for accurate time accounting */ struct cpu_accounting_data { - unsigned long user_time; /* accumulated usermode TB ticks */ - unsigned long system_time; /* accumulated system TB ticks */ - unsigned long user_time_scaled; /* accumulated usermode SPURR ticks */ + /* Accumulated cputime values to flush on ticks*/ + unsigned long utime; + unsigned long stime; + unsigned long utime_scaled; + unsigned long stime_scaled; + unsigned long gtime; + unsigned long hardirq_time; + unsigned long softirq_time; + unsigned long steal_time; + unsigned long idle_time; + /* Internal counters */ unsigned long starttime; /* TB value snapshot */ unsigned long starttime_user; /* TB value on exit to usermode */ unsigned long startspurr; /* SPURR value snapshot */ diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index aa2e6a34b872..99b541865d8d 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -16,12 +16,7 @@ #ifndef __POWERPC_CPUTIME_H #define __POWERPC_CPUTIME_H -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -#include <asm-generic/cputime.h> -#ifdef __KERNEL__ -static inline void setup_cputime_one_jiffy(void) { } -#endif -#else +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include <linux/types.h> #include <linux/time.h> @@ -36,65 +31,6 @@ typedef u64 __nocast cputime64_t; #define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new) #ifdef __KERNEL__ - -/* - * One jiffy in timebase units computed during initialization - */ -extern cputime_t cputime_one_jiffy; - -/* - * Convert cputime <-> jiffies - */ -extern u64 __cputime_jiffies_factor; - -static inline unsigned long cputime_to_jiffies(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_jiffies_factor); -} - -static inline cputime_t jiffies_to_cputime(const unsigned long jif) -{ - u64 ct; - unsigned long sec; - - /* have to be a little careful about overflow */ - ct = jif % HZ; - sec = jif / HZ; - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, HZ); - } - if (sec) - ct += (cputime_t) sec * tb_ticks_per_sec; - return (__force cputime_t) ct; -} - -static inline void setup_cputime_one_jiffy(void) -{ - cputime_one_jiffy = jiffies_to_cputime(1); -} - -static inline cputime64_t jiffies64_to_cputime64(const u64 jif) -{ - u64 ct; - u64 sec = jif; - - /* have to be a little careful about overflow */ - ct = do_div(sec, HZ); - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, HZ); - } - if (sec) - ct += (u64) sec * tb_ticks_per_sec; - return (__force cputime64_t) ct; -} - -static inline u64 cputime64_to_jiffies64(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_jiffies_factor); -} - /* * Convert cputime <-> microseconds */ @@ -105,117 +41,6 @@ static inline unsigned long cputime_to_usecs(const cputime_t ct) return mulhdu((__force u64) ct, __cputime_usec_factor); } -static inline cputime_t usecs_to_cputime(const unsigned long us) -{ - u64 ct; - unsigned long sec; - - /* have to be a little careful about overflow */ - ct = us % 1000000; - sec = us / 1000000; - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, 1000000); - } - if (sec) - ct += (cputime_t) sec * tb_ticks_per_sec; - return (__force cputime_t) ct; -} - -#define usecs_to_cputime64(us) usecs_to_cputime(us) - -/* - * Convert cputime <-> seconds - */ -extern u64 __cputime_sec_factor; - -static inline unsigned long cputime_to_secs(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_sec_factor); -} - -static inline cputime_t secs_to_cputime(const unsigned long sec) -{ - return (__force cputime_t)((u64) sec * tb_ticks_per_sec); -} - -/* - * Convert cputime <-> timespec - */ -static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p) -{ - u64 x = (__force u64) ct; - unsigned int frac; - - frac = do_div(x, tb_ticks_per_sec); - p->tv_sec = x; - x = (u64) frac * 1000000000; - do_div(x, tb_ticks_per_sec); - p->tv_nsec = x; -} - -static inline cputime_t timespec_to_cputime(const struct timespec *p) -{ - u64 ct; - - ct = (u64) p->tv_nsec * tb_ticks_per_sec; - do_div(ct, 1000000000); - return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec); -} - -/* - * Convert cputime <-> timeval - */ -static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p) -{ - u64 x = (__force u64) ct; - unsigned int frac; - - frac = do_div(x, tb_ticks_per_sec); - p->tv_sec = x; - x = (u64) frac * 1000000; - do_div(x, tb_ticks_per_sec); - p->tv_usec = x; -} - -static inline cputime_t timeval_to_cputime(const struct timeval *p) -{ - u64 ct; - - ct = (u64) p->tv_usec * tb_ticks_per_sec; - do_div(ct, 1000000); - return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec); -} - -/* - * Convert cputime <-> clock_t (units of 1/USER_HZ seconds) - */ -extern u64 __cputime_clockt_factor; - -static inline unsigned long cputime_to_clock_t(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_clockt_factor); -} - -static inline cputime_t clock_t_to_cputime(const unsigned long clk) -{ - u64 ct; - unsigned long sec; - - /* have to be a little careful about overflow */ - ct = clk % USER_HZ; - sec = clk / USER_HZ; - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, USER_HZ); - } - if (sec) - ct += (u64) sec * tb_ticks_per_sec; - return (__force cputime_t) ct; -} - -#define cputime64_to_clock_t(ct) cputime_to_clock_t((cputime_t)(ct)) - /* * PPC64 uses PACA which is task independent for storing accounting data while * PPC32 uses struct thread_info, therefore at task switch the accounting data diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 6a6792bb39fb..708c3e592eeb 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -187,7 +187,6 @@ struct paca_struct { /* Stuff for accurate time accounting */ struct cpu_accounting_data accounting; - u64 stolen_time; /* TB ticks taken by hypervisor */ u64 dtl_ridx; /* read index in dispatch log */ struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 195a9fc8f81c..9e8e771f8acb 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -249,9 +249,9 @@ int main(void) DEFINE(ACCOUNT_STARTTIME_USER, offsetof(struct paca_struct, accounting.starttime_user)); DEFINE(ACCOUNT_USER_TIME, - offsetof(struct paca_struct, accounting.user_time)); + offsetof(struct paca_struct, accounting.utime)); DEFINE(ACCOUNT_SYSTEM_TIME, - offsetof(struct paca_struct, accounting.system_time)); + offsetof(struct paca_struct, accounting.stime)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost)); DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso)); @@ -262,9 +262,9 @@ int main(void) DEFINE(ACCOUNT_STARTTIME_USER, offsetof(struct thread_info, accounting.starttime_user)); DEFINE(ACCOUNT_USER_TIME, - offsetof(struct thread_info, accounting.user_time)); + offsetof(struct thread_info, accounting.utime)); DEFINE(ACCOUNT_SYSTEM_TIME, - offsetof(struct thread_info, accounting.system_time)); + offsetof(struct thread_info, accounting.stime)); #endif #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index bc2e08d415fa..14e485525e31 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -57,6 +57,7 @@ #include <linux/clk-provider.h> #include <linux/suspend.h> #include <linux/rtc.h> +#include <linux/cputime.h> #include <asm/trace.h> #include <asm/io.h> @@ -72,7 +73,6 @@ #include <asm/smp.h> #include <asm/vdso_datapage.h> #include <asm/firmware.h> -#include <asm/cputime.h> #include <asm/asm-prototypes.h> /* powerpc clocksource/clockevent code */ @@ -152,20 +152,11 @@ EXPORT_SYMBOL_GPL(ppc_tb_freq); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* - * Factors for converting from cputime_t (timebase ticks) to - * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds). - * These are all stored as 0.64 fixed-point binary fractions. + * Factor for converting from cputime_t (timebase ticks) to + * microseconds. This is stored as 0.64 fixed-point binary fraction. */ -u64 __cputime_jiffies_factor; -EXPORT_SYMBOL(__cputime_jiffies_factor); u64 __cputime_usec_factor; EXPORT_SYMBOL(__cputime_usec_factor); -u64 __cputime_sec_factor; -EXPORT_SYMBOL(__cputime_sec_factor); -u64 __cputime_clockt_factor; -EXPORT_SYMBOL(__cputime_clockt_factor); - -cputime_t cputime_one_jiffy; #ifdef CONFIG_PPC_SPLPAR void (*dtl_consumer)(struct dtl_entry *, u64); @@ -181,14 +172,8 @@ static void calc_cputime_factors(void) { struct div_result res; - div128_by_32(HZ, 0, tb_ticks_per_sec, &res); - __cputime_jiffies_factor = res.result_low; div128_by_32(1000000, 0, tb_ticks_per_sec, &res); __cputime_usec_factor = res.result_low; - div128_by_32(1, 0, tb_ticks_per_sec, &res); - __cputime_sec_factor = res.result_low; - div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res); - __cputime_clockt_factor = res.result_low; } /* @@ -271,25 +256,19 @@ void accumulate_stolen_time(void) sst = scan_dispatch_log(acct->starttime_user); ust = scan_dispatch_log(acct->starttime); - acct->system_time -= sst; - acct->user_time -= ust; - local_paca->stolen_time += ust + sst; + acct->stime -= sst; + acct->utime -= ust; + acct->steal_time += ust + sst; local_paca->soft_enabled = save_soft_enabled; } static inline u64 calculate_stolen_time(u64 stop_tb) { - u64 stolen = 0; + if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) + return scan_dispatch_log(stop_tb); - if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) { - stolen = scan_dispatch_log(stop_tb); - get_paca()->accounting.system_time -= stolen; - } - - stolen += get_paca()->stolen_time; - get_paca()->stolen_time = 0; - return stolen; + return 0; } #else /* CONFIG_PPC_SPLPAR */ @@ -305,28 +284,27 @@ static inline u64 calculate_stolen_time(u64 stop_tb) * or soft irq state. */ static unsigned long vtime_delta(struct task_struct *tsk, - unsigned long *sys_scaled, - unsigned long *stolen) + unsigned long *stime_scaled, + unsigned long *steal_time) { unsigned long now, nowscaled, deltascaled; - unsigned long udelta, delta, user_scaled; + unsigned long stime; + unsigned long utime, utime_scaled; struct cpu_accounting_data *acct = get_accounting(tsk); WARN_ON_ONCE(!irqs_disabled()); now = mftb(); nowscaled = read_spurr(now); - acct->system_time += now - acct->starttime; + stime = now - acct->starttime; acct->starttime = now; deltascaled = nowscaled - acct->startspurr; acct->startspurr = nowscaled; - *stolen = calculate_stolen_time(now); + *steal_time = calculate_stolen_time(now); - delta = acct->system_time; - acct->system_time = 0; - udelta = acct->user_time - acct->utime_sspurr; - acct->utime_sspurr = acct->user_time; + utime = acct->utime - acct->utime_sspurr; + acct->utime_sspurr = acct->utime; /* * Because we don't read the SPURR on every kernel entry/exit, @@ -338,62 +316,105 @@ static unsigned long vtime_delta(struct task_struct *tsk, * the user ticks get saved up in paca->user_time_scaled to be * used by account_process_tick. */ - *sys_scaled = delta; - user_scaled = udelta; - if (deltascaled != delta + udelta) { - if (udelta) { - *sys_scaled = deltascaled * delta / (delta + udelta); - user_scaled = deltascaled - *sys_scaled; + *stime_scaled = stime; + utime_scaled = utime; + if (deltascaled != stime + utime) { + if (utime) { + *stime_scaled = deltascaled * stime / (stime + utime); + utime_scaled = deltascaled - *stime_scaled; } else { - *sys_scaled = deltascaled; + *stime_scaled = deltascaled; } } - acct->user_time_scaled += user_scaled; + acct->utime_scaled += utime_scaled; - return delta; + return stime; } void vtime_account_system(struct task_struct *tsk) { - unsigned long delta, sys_scaled, stolen; + unsigned long stime, stime_scaled, steal_time; + struct cpu_accounting_data *acct = get_accounting(tsk); + + stime = vtime_delta(tsk, &stime_scaled, &steal_time); - delta = vtime_delta(tsk, &sys_scaled, &stolen); - account_system_time(tsk, 0, delta); - tsk->stimescaled += sys_scaled; - if (stolen) - account_steal_time(stolen); + stime -= min(stime, steal_time); + acct->steal_time += steal_time; + + if ((tsk->flags & PF_VCPU) && !irq_count()) { + acct->gtime += stime; + acct->utime_scaled += stime_scaled; + } else { + if (hardirq_count()) + acct->hardirq_time += stime; + else if (in_serving_softirq()) + acct->softirq_time += stime; + else + acct->stime += stime; + + acct->stime_scaled += stime_scaled; + } } EXPORT_SYMBOL_GPL(vtime_account_system); void vtime_account_idle(struct task_struct *tsk) { - unsigned long delta, sys_scaled, stolen; + unsigned long stime, stime_scaled, steal_time; + struct cpu_accounting_data *acct = get_accounting(tsk); - delta = vtime_delta(tsk, &sys_scaled, &stolen); - account_idle_time(delta + stolen); + stime = vtime_delta(tsk, &stime_scaled, &steal_time); + acct->idle_time += stime + steal_time; } /* - * Transfer the user time accumulated in the paca - * by the exception entry and exit code to the generic - * process user time records. + * Account the whole cputime accumulated in the paca * Must be called with interrupts disabled. * Assumes that vtime_account_system/idle() has been called * recently (i.e. since the last entry from usermode) so that * get_paca()->user_time_scaled is up to date. */ -void vtime_account_user(struct task_struct *tsk) +void vtime_flush(struct task_struct *tsk) { - cputime_t utime, utimescaled; struct cpu_accounting_data *acct = get_accounting(tsk); - utime = acct->user_time; - utimescaled = acct->user_time_scaled; - acct->user_time = 0; - acct->user_time_scaled = 0; + if (acct->utime) + account_user_time(tsk, cputime_to_nsecs(acct->utime)); + + if (acct->utime_scaled) + tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled); + + if (acct->gtime) + account_guest_time(tsk, cputime_to_nsecs(acct->gtime)); + + if (acct->steal_time) + account_steal_time(cputime_to_nsecs(acct->steal_time)); + + if (acct->idle_time) + account_idle_time(cputime_to_nsecs(acct->idle_time)); + + if (acct->stime) + account_system_index_time(tsk, cputime_to_nsecs(acct->stime), + CPUTIME_SYSTEM); + if (acct->stime_scaled) + tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled); + + if (acct->hardirq_time) + account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time), + CPUTIME_IRQ); + if (acct->softirq_time) + account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time), + CPUTIME_SOFTIRQ); + + acct->utime = 0; + acct->utime_scaled = 0; acct->utime_sspurr = 0; - account_user_time(tsk, utime); - tsk->utimescaled += utimescaled; + acct->gtime = 0; + acct->steal_time = 0; + acct->idle_time = 0; + acct->stime = 0; + acct->stime_scaled = 0; + acct->hardirq_time = 0; + acct->softirq_time = 0; } #ifdef CONFIG_PPC32 @@ -407,8 +428,7 @@ void arch_vtime_task_switch(struct task_struct *prev) struct cpu_accounting_data *acct = get_accounting(current); acct->starttime = get_accounting(prev)->starttime; - acct->system_time = 0; - acct->user_time = 0; + acct->startspurr = get_accounting(prev)->startspurr; } #endif /* CONFIG_PPC32 */ @@ -1018,7 +1038,6 @@ void __init time_init(void) tb_ticks_per_sec = ppc_tb_freq; tb_ticks_per_usec = ppc_tb_freq / 1000000; calc_cputime_factors(); - setup_cputime_one_jiffy(); /* * Compute scale factor for sched_clock. diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 93abf8a9813d..8e1588021d1c 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -347,7 +347,8 @@ early_param("disable_radix", parse_disable_radix); void __init mmu_early_init_devtree(void) { /* Disable radix mode based on kernel command line. */ - if (disable_radix) + /* We don't yet have the machinery to do radix as a guest. */ + if (disable_radix || !(mfmsr() & MSR_HV)) cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; if (early_radix_enabled()) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 9c0e17cf6886..3f864c36d847 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2287,14 +2287,14 @@ static void dump_one_paca(int cpu) DUMP(p, subcore_sibling_mask, "x"); #endif - DUMP(p, accounting.user_time, "llx"); - DUMP(p, accounting.system_time, "llx"); - DUMP(p, accounting.user_time_scaled, "llx"); + DUMP(p, accounting.utime, "llx"); + DUMP(p, accounting.stime, "llx"); + DUMP(p, accounting.utime_scaled, "llx"); DUMP(p, accounting.starttime, "llx"); DUMP(p, accounting.starttime_user, "llx"); DUMP(p, accounting.startspurr, "llx"); DUMP(p, accounting.utime_sspurr, "llx"); - DUMP(p, stolen_time, "llx"); + DUMP(p, accounting.steal_time, "llx"); #undef DUMP catch_memory_errors = 0; diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c index 69b23b25ac34..08b9e942a262 100644 --- a/arch/s390/appldata/appldata_os.c +++ b/arch/s390/appldata/appldata_os.c @@ -113,21 +113,21 @@ static void appldata_get_os_data(void *data) j = 0; for_each_online_cpu(i) { os_data->os_cpu[j].per_cpu_user = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]); os_data->os_cpu[j].per_cpu_nice = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]); os_data->os_cpu[j].per_cpu_system = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]); os_data->os_cpu[j].per_cpu_idle = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]); os_data->os_cpu[j].per_cpu_irq = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]); os_data->os_cpu[j].per_cpu_softirq = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]); os_data->os_cpu[j].per_cpu_iowait = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]); os_data->os_cpu[j].per_cpu_steal = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]); os_data->os_cpu[j].cpu_id = i; j++; } diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 221b454c734a..d1c407ddf703 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -25,33 +25,6 @@ static inline unsigned long __div(unsigned long long n, unsigned long base) return n / base; } -#define cputime_one_jiffy jiffies_to_cputime(1) - -/* - * Convert cputime to jiffies and back. - */ -static inline unsigned long cputime_to_jiffies(const cputime_t cputime) -{ - return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / HZ); -} - -static inline cputime_t jiffies_to_cputime(const unsigned int jif) -{ - return (__force cputime_t)(jif * (CPUTIME_PER_SEC / HZ)); -} - -static inline u64 cputime64_to_jiffies64(cputime64_t cputime) -{ - unsigned long long jif = (__force unsigned long long) cputime; - do_div(jif, CPUTIME_PER_SEC / HZ); - return jif; -} - -static inline cputime64_t jiffies64_to_cputime64(const u64 jif) -{ - return (__force cputime64_t)(jif * (CPUTIME_PER_SEC / HZ)); -} - /* * Convert cputime to microseconds and back. */ @@ -60,88 +33,8 @@ static inline unsigned int cputime_to_usecs(const cputime_t cputime) return (__force unsigned long long) cputime >> 12; } -static inline cputime_t usecs_to_cputime(const unsigned int m) -{ - return (__force cputime_t)(m * CPUTIME_PER_USEC); -} - -#define usecs_to_cputime64(m) usecs_to_cputime(m) - -/* - * Convert cputime to milliseconds and back. - */ -static inline unsigned int cputime_to_secs(const cputime_t cputime) -{ - return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / 2) >> 1; -} - -static inline cputime_t secs_to_cputime(const unsigned int s) -{ - return (__force cputime_t)(s * CPUTIME_PER_SEC); -} - -/* - * Convert cputime to timespec and back. - */ -static inline cputime_t timespec_to_cputime(const struct timespec *value) -{ - unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC; - return (__force cputime_t)(ret + __div(value->tv_nsec * CPUTIME_PER_USEC, NSEC_PER_USEC)); -} - -static inline void cputime_to_timespec(const cputime_t cputime, - struct timespec *value) -{ - unsigned long long __cputime = (__force unsigned long long) cputime; - value->tv_nsec = (__cputime % CPUTIME_PER_SEC) * NSEC_PER_USEC / CPUTIME_PER_USEC; - value->tv_sec = __cputime / CPUTIME_PER_SEC; -} - -/* - * Convert cputime to timeval and back. - * Since cputime and timeval have the same resolution (microseconds) - * this is easy. - */ -static inline cputime_t timeval_to_cputime(const struct timeval *value) -{ - unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC; - return (__force cputime_t)(ret + value->tv_usec * CPUTIME_PER_USEC); -} - -static inline void cputime_to_timeval(const cputime_t cputime, - struct timeval *value) -{ - unsigned long long __cputime = (__force unsigned long long) cputime; - value->tv_usec = (__cputime % CPUTIME_PER_SEC) / CPUTIME_PER_USEC; - value->tv_sec = __cputime / CPUTIME_PER_SEC; -} - -/* - * Convert cputime to clock and back. - */ -static inline clock_t cputime_to_clock_t(cputime_t cputime) -{ - unsigned long long clock = (__force unsigned long long) cputime; - do_div(clock, CPUTIME_PER_SEC / USER_HZ); - return clock; -} - -static inline cputime_t clock_t_to_cputime(unsigned long x) -{ - return (__force cputime_t)(x * (CPUTIME_PER_SEC / USER_HZ)); -} - -/* - * Convert cputime64 to clock. - */ -static inline clock_t cputime64_to_clock_t(cputime64_t cputime) -{ - unsigned long long clock = (__force unsigned long long) cputime; - do_div(clock, CPUTIME_PER_SEC / USER_HZ); - return clock; -} -cputime64_t arch_cpu_idle_time(int cpu); +u64 arch_cpu_idle_time(int cpu); #define arch_idle_time(cpu) arch_cpu_idle_time(cpu) diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 9bfad2ad6312..61261e0e95c0 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -85,53 +85,56 @@ struct lowcore { __u64 mcck_enter_timer; /* 0x02c0 */ __u64 exit_timer; /* 0x02c8 */ __u64 user_timer; /* 0x02d0 */ - __u64 system_timer; /* 0x02d8 */ - __u64 steal_timer; /* 0x02e0 */ - __u64 last_update_timer; /* 0x02e8 */ - __u64 last_update_clock; /* 0x02f0 */ - __u64 int_clock; /* 0x02f8 */ - __u64 mcck_clock; /* 0x0300 */ - __u64 clock_comparator; /* 0x0308 */ + __u64 guest_timer; /* 0x02d8 */ + __u64 system_timer; /* 0x02e0 */ + __u64 hardirq_timer; /* 0x02e8 */ + __u64 softirq_timer; /* 0x02f0 */ + __u64 steal_timer; /* 0x02f8 */ + __u64 last_update_timer; /* 0x0300 */ + __u64 last_update_clock; /* 0x0308 */ + __u64 int_clock; /* 0x0310 */ + __u64 mcck_clock; /* 0x0318 */ + __u64 clock_comparator; /* 0x0320 */ /* Current process. */ - __u64 current_task; /* 0x0310 */ - __u8 pad_0x318[0x320-0x318]; /* 0x0318 */ - __u64 kernel_stack; /* 0x0320 */ + __u64 current_task; /* 0x0328 */ + __u8 pad_0x318[0x320-0x318]; /* 0x0330 */ + __u64 kernel_stack; /* 0x0338 */ /* Interrupt, panic and restart stack. */ - __u64 async_stack; /* 0x0328 */ - __u64 panic_stack; /* 0x0330 */ - __u64 restart_stack; /* 0x0338 */ + __u64 async_stack; /* 0x0340 */ + __u64 panic_stack; /* 0x0348 */ + __u64 restart_stack; /* 0x0350 */ /* Restart function and parameter. */ - __u64 restart_fn; /* 0x0340 */ - __u64 restart_data; /* 0x0348 */ - __u64 restart_source; /* 0x0350 */ + __u64 restart_fn; /* 0x0358 */ + __u64 restart_data; /* 0x0360 */ + __u64 restart_source; /* 0x0368 */ /* Address space pointer. */ - __u64 kernel_asce; /* 0x0358 */ - __u64 user_asce; /* 0x0360 */ + __u64 kernel_asce; /* 0x0370 */ + __u64 user_asce; /* 0x0378 */ /* * The lpp and current_pid fields form a * 64-bit value that is set as program * parameter with the LPP instruction. */ - __u32 lpp; /* 0x0368 */ - __u32 current_pid; /* 0x036c */ + __u32 lpp; /* 0x0380 */ + __u32 current_pid; /* 0x0384 */ /* SMP info area */ - __u32 cpu_nr; /* 0x0370 */ - __u32 softirq_pending; /* 0x0374 */ - __u64 percpu_offset; /* 0x0378 */ - __u64 vdso_per_cpu_data; /* 0x0380 */ - __u64 machine_flags; /* 0x0388 */ - __u32 preempt_count; /* 0x0390 */ - __u8 pad_0x0394[0x0398-0x0394]; /* 0x0394 */ - __u64 gmap; /* 0x0398 */ - __u32 spinlock_lockval; /* 0x03a0 */ - __u32 fpu_flags; /* 0x03a4 */ - __u8 pad_0x03a8[0x0400-0x03a8]; /* 0x03a8 */ + __u32 cpu_nr; /* 0x0388 */ + __u32 softirq_pending; /* 0x038c */ + __u64 percpu_offset; /* 0x0390 */ + __u64 vdso_per_cpu_data; /* 0x0398 */ + __u64 machine_flags; /* 0x03a0 */ + __u32 preempt_count; /* 0x03a8 */ + __u8 pad_0x03ac[0x03b0-0x03ac]; /* 0x03ac */ + __u64 gmap; /* 0x03b0 */ + __u32 spinlock_lockval; /* 0x03b8 */ + __u32 fpu_flags; /* 0x03bc */ + __u8 pad_0x03c0[0x0400-0x03c0]; /* 0x03c0 */ /* Per cpu primary space access list */ __u32 paste[16]; /* 0x0400 */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 6bca916a5ba0..977a5b6501b8 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -111,7 +111,10 @@ struct thread_struct { unsigned int acrs[NUM_ACRS]; unsigned long ksp; /* kernel stack pointer */ unsigned long user_timer; /* task cputime in user space */ + unsigned long guest_timer; /* task cputime in kvm guest */ unsigned long system_timer; /* task cputime in kernel space */ + unsigned long hardirq_timer; /* task cputime in hardirq context */ + unsigned long softirq_timer; /* task cputime in softirq context */ unsigned long sys_call_table; /* system call table address */ mm_segment_t mm_segment; unsigned long gmap_addr; /* address of last gmap fault. */ diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index 7a55c29b0b33..d3bf69ef42cf 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -12,7 +12,7 @@ #include <linux/notifier.h> #include <linux/init.h> #include <linux/cpu.h> -#include <asm/cputime.h> +#include <linux/cputime.h> #include <asm/nmi.h> #include <asm/smp.h> #include "entry.h" @@ -43,7 +43,7 @@ void enabled_wait(void) idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; idle->idle_time += idle_time; idle->idle_count++; - account_idle_time(idle_time); + account_idle_time(cputime_to_nsecs(idle_time)); write_seqcount_end(&idle->seqcount); } NOKPROBE_SYMBOL(enabled_wait); @@ -84,7 +84,7 @@ static ssize_t show_idle_time(struct device *dev, } DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); -cputime64_t arch_cpu_idle_time(int cpu) +u64 arch_cpu_idle_time(int cpu) { struct s390_idle_data *idle = &per_cpu(s390_idle, cpu); unsigned long long now, idle_enter, idle_exit; @@ -96,7 +96,8 @@ cputime64_t arch_cpu_idle_time(int cpu) idle_enter = ACCESS_ONCE(idle->clock_idle_enter); idle_exit = ACCESS_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0; + + return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0); } void arch_cpu_idle_enter(void) diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 1b5c5ee9fc1b..b4a3e9e06ef2 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -6,13 +6,13 @@ */ #include <linux/kernel_stat.h> +#include <linux/cputime.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/timex.h> #include <linux/types.h> #include <linux/time.h> -#include <asm/cputime.h> #include <asm/vtimer.h> #include <asm/vtime.h> #include <asm/cpu_mf.h> @@ -90,14 +90,41 @@ static void update_mt_scaling(void) __this_cpu_write(mt_scaling_jiffies, jiffies_64); } +static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new) +{ + u64 delta; + + delta = new - *tsk_vtime; + *tsk_vtime = new; + return delta; +} + + +static inline u64 scale_vtime(u64 vtime) +{ + u64 mult = __this_cpu_read(mt_scaling_mult); + u64 div = __this_cpu_read(mt_scaling_div); + + if (smp_cpu_mtid) + return vtime * mult / div; + return vtime; +} + +static void account_system_index_scaled(struct task_struct *p, + cputime_t cputime, cputime_t scaled, + enum cpu_usage_stat index) +{ + p->stimescaled += cputime_to_nsecs(scaled); + account_system_index_time(p, cputime_to_nsecs(cputime), index); +} + /* * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. */ static int do_account_vtime(struct task_struct *tsk) { - u64 timer, clock, user, system, steal; - u64 user_scaled, system_scaled; + u64 timer, clock, user, guest, system, hardirq, softirq, steal; timer = S390_lowcore.last_update_timer; clock = S390_lowcore.last_update_clock; @@ -110,53 +137,76 @@ static int do_account_vtime(struct task_struct *tsk) #endif : "=m" (S390_lowcore.last_update_timer), "=m" (S390_lowcore.last_update_clock)); - S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; - S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock; + clock = S390_lowcore.last_update_clock - clock; + timer -= S390_lowcore.last_update_timer; + + if (hardirq_count()) + S390_lowcore.hardirq_timer += timer; + else + S390_lowcore.system_timer += timer; /* Update MT utilization calculation */ if (smp_cpu_mtid && time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies))) update_mt_scaling(); - user = S390_lowcore.user_timer - tsk->thread.user_timer; - S390_lowcore.steal_timer -= user; - tsk->thread.user_timer = S390_lowcore.user_timer; - - system = S390_lowcore.system_timer - tsk->thread.system_timer; - S390_lowcore.steal_timer -= system; - tsk->thread.system_timer = S390_lowcore.system_timer; - - user_scaled = user; - system_scaled = system; - /* Do MT utilization scaling */ - if (smp_cpu_mtid) { - u64 mult = __this_cpu_read(mt_scaling_mult); - u64 div = __this_cpu_read(mt_scaling_div); + /* Calculate cputime delta */ + user = update_tsk_timer(&tsk->thread.user_timer, + READ_ONCE(S390_lowcore.user_timer)); + guest = update_tsk_timer(&tsk->thread.guest_timer, + READ_ONCE(S390_lowcore.guest_timer)); + system = update_tsk_timer(&tsk->thread.system_timer, + READ_ONCE(S390_lowcore.system_timer)); + hardirq = update_tsk_timer(&tsk->thread.hardirq_timer, + READ_ONCE(S390_lowcore.hardirq_timer)); + softirq = update_tsk_timer(&tsk->thread.softirq_timer, + READ_ONCE(S390_lowcore.softirq_timer)); + S390_lowcore.steal_timer += + clock - user - guest - system - hardirq - softirq; + + /* Push account value */ + if (user) { + account_user_time(tsk, cputime_to_nsecs(user)); + tsk->utimescaled += cputime_to_nsecs(scale_vtime(user)); + } - user_scaled = (user_scaled * mult) / div; - system_scaled = (system_scaled * mult) / div; + if (guest) { + account_guest_time(tsk, cputime_to_nsecs(guest)); + tsk->utimescaled += cputime_to_nsecs(scale_vtime(guest)); } - account_user_time(tsk, user); - tsk->utimescaled += user_scaled; - account_system_time(tsk, 0, system); - tsk->stimescaled += system_scaled; + + if (system) + account_system_index_scaled(tsk, system, scale_vtime(system), + CPUTIME_SYSTEM); + if (hardirq) + account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq), + CPUTIME_IRQ); + if (softirq) + account_system_index_scaled(tsk, softirq, scale_vtime(softirq), + CPUTIME_SOFTIRQ); steal = S390_lowcore.steal_timer; if ((s64) steal > 0) { S390_lowcore.steal_timer = 0; - account_steal_time(steal); + account_steal_time(cputime_to_nsecs(steal)); } - return virt_timer_forward(user + system); + return virt_timer_forward(user + guest + system + hardirq + softirq); } void vtime_task_switch(struct task_struct *prev) { do_account_vtime(prev); prev->thread.user_timer = S390_lowcore.user_timer; + prev->thread.guest_timer = S390_lowcore.guest_timer; prev->thread.system_timer = S390_lowcore.system_timer; + prev->thread.hardirq_timer = S390_lowcore.hardirq_timer; + prev->thread.softirq_timer = S390_lowcore.softirq_timer; S390_lowcore.user_timer = current->thread.user_timer; + S390_lowcore.guest_timer = current->thread.guest_timer; S390_lowcore.system_timer = current->thread.system_timer; + S390_lowcore.hardirq_timer = current->thread.hardirq_timer; + S390_lowcore.softirq_timer = current->thread.softirq_timer; } /* @@ -164,7 +214,7 @@ void vtime_task_switch(struct task_struct *prev) * accounting system time in order to correctly compute * the stolen time accounting. */ -void vtime_account_user(struct task_struct *tsk) +void vtime_flush(struct task_struct *tsk) { if (do_account_vtime(tsk)) virt_timer_expire(); @@ -176,32 +226,22 @@ void vtime_account_user(struct task_struct *tsk) */ void vtime_account_irq_enter(struct task_struct *tsk) { - u64 timer, system, system_scaled; + u64 timer; timer = S390_lowcore.last_update_timer; S390_lowcore.last_update_timer = get_vtimer(); - S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; - - /* Update MT utilization calculation */ - if (smp_cpu_mtid && - time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies))) - update_mt_scaling(); - - system = S390_lowcore.system_timer - tsk->thread.system_timer; - S390_lowcore.steal_timer -= system; - tsk->thread.system_timer = S390_lowcore.system_timer; - system_scaled = system; - /* Do MT utilization scaling */ - if (smp_cpu_mtid) { - u64 mult = __this_cpu_read(mt_scaling_mult); - u64 div = __this_cpu_read(mt_scaling_div); - - system_scaled = (system_scaled * mult) / div; - } - account_system_time(tsk, 0, system); - tsk->stimescaled += system_scaled; - - virt_timer_forward(system); + timer -= S390_lowcore.last_update_timer; + + if ((tsk->flags & PF_VCPU) && (irq_count() == 0)) + S390_lowcore.guest_timer += timer; + else if (hardirq_count()) + S390_lowcore.hardirq_timer += timer; + else if (in_serving_softirq()) + S390_lowcore.softirq_timer += timer; + else + S390_lowcore.system_timer += timer; + + virt_timer_forward(timer); } EXPORT_SYMBOL_GPL(vtime_account_irq_enter); diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild index a05218ff3fe4..51970bb6c4fe 100644 --- a/arch/score/include/asm/Kbuild +++ b/arch/score/include/asm/Kbuild @@ -4,7 +4,6 @@ header-y += generic-y += barrier.h generic-y += clkdev.h -generic-y += cputime.h generic-y += irq_work.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 751c3373a92c..cf2a75063b53 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += bitsperlong.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += delay.h generic-y += div64.h diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 0569bfac4afb..e9e837bc3158 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += div64.h generic-y += emergency-restart.h generic-y += exec.h diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild index 2d1f5638974c..aa48b6eaff2d 100644 --- a/arch/tile/include/asm/Kbuild +++ b/arch/tile/include/asm/Kbuild @@ -4,8 +4,6 @@ header-y += ../arch/ generic-y += bug.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h -generic-y += div64.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h diff --git a/arch/tile/include/asm/div64.h b/arch/tile/include/asm/div64.h new file mode 100644 index 000000000000..9f765cdf09a5 --- /dev/null +++ b/arch/tile/include/asm/div64.h @@ -0,0 +1,16 @@ +#ifndef _ASM_TILE_DIV64_H +#define _ASM_TILE_DIV64_H + +#include <linux/types.h> + +#ifdef __tilegx__ +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + return __insn_mul_lu_lu(a, b); +} +#define mul_u32_u32 mul_u32_u32 +#endif + +#include <asm-generic/div64.h> + +#endif /* _ASM_TILE_DIV64_H */ diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c index 05523f14d7b2..57f03050c850 100644 --- a/arch/um/drivers/random.c +++ b/arch/um/drivers/random.c @@ -76,7 +76,7 @@ static ssize_t rng_dev_read (struct file *filp, char __user *buf, size_t size, add_sigio_fd(random_fd); add_wait_queue(&host_read_wait, &wait); - set_task_state(current, TASK_INTERRUPTIBLE); + set_current_state(TASK_INTERRUPTIBLE); schedule(); remove_wait_queue(&host_read_wait, &wait); diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index 052f7f6d0551..90c281cd7e1d 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += barrier.h generic-y += bug.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += delay.h generic-y += device.h diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 256c45b3ae34..5d51ade89f4c 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -4,7 +4,6 @@ generic-y += auxvec.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e487493bbd47..f8fbfc5a98ba 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1070,7 +1070,7 @@ config X86_MCE_THRESHOLD def_bool y config X86_MCE_INJECT - depends on X86_MCE + depends on X86_MCE && X86_LOCAL_APIC tristate "Machine check injector support" ---help--- Provide support for injecting machine checks for testing purposes. @@ -1994,10 +1994,6 @@ config RANDOMIZE_BASE theoretically possible, but the implementations are further limited due to memory layouts. - If CONFIG_HIBERNATE is also enabled, KASLR is disabled at boot - time. To enable it, boot with "kaslr" on the kernel command - line (which will also disable hibernation). - If unsure, say N. # Relocation on x86 needs some additional build support diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index e5612f3e3b57..9b42b6d1e902 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -333,6 +333,7 @@ size_t strnlen(const char *s, size_t maxlen); unsigned int atou(const char *s); unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base); size_t strlen(const char *s); +char *strchr(const char *s, int c); /* tty.c */ void puts(const char *); diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ff01c8fc76f7..801c7a158e55 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -32,160 +32,13 @@ 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; \ } BOOT_SERVICES(32); BOOT_SERVICES(64); -void efi_char16_printk(efi_system_table_t *, efi_char16_t *); - -static efi_status_t -__file_size32(void *__fh, efi_char16_t *filename_16, - void **handle, u64 *file_sz) -{ - efi_file_handle_32_t *h, *fh = __fh; - efi_file_info_t *info; - efi_status_t status; - efi_guid_t info_guid = EFI_FILE_INFO_ID; - u32 info_sz; - - status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16, - EFI_FILE_MODE_READ, (u64)0); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to open file: "); - efi_char16_printk(sys_table, filename_16); - efi_printk(sys_table, "\n"); - return status; - } - - *handle = h; - - info_sz = 0; - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, NULL); - if (status != EFI_BUFFER_TOO_SMALL) { - efi_printk(sys_table, "Failed to get file info size\n"); - return status; - } - -grow: - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - info_sz, (void **)&info); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for file info\n"); - return status; - } - - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, info); - if (status == EFI_BUFFER_TOO_SMALL) { - efi_call_early(free_pool, info); - goto grow; - } - - *file_sz = info->file_size; - efi_call_early(free_pool, info); - - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to get initrd info\n"); - - return status; -} - -static efi_status_t -__file_size64(void *__fh, efi_char16_t *filename_16, - void **handle, u64 *file_sz) -{ - efi_file_handle_64_t *h, *fh = __fh; - efi_file_info_t *info; - efi_status_t status; - efi_guid_t info_guid = EFI_FILE_INFO_ID; - u64 info_sz; - - status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16, - EFI_FILE_MODE_READ, (u64)0); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to open file: "); - efi_char16_printk(sys_table, filename_16); - efi_printk(sys_table, "\n"); - return status; - } - - *handle = h; - - info_sz = 0; - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, NULL); - if (status != EFI_BUFFER_TOO_SMALL) { - efi_printk(sys_table, "Failed to get file info size\n"); - return status; - } - -grow: - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - info_sz, (void **)&info); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for file info\n"); - return status; - } - - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, info); - if (status == EFI_BUFFER_TOO_SMALL) { - efi_call_early(free_pool, info); - goto grow; - } - - *file_sz = info->file_size; - efi_call_early(free_pool, info); - - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to get initrd info\n"); - - return status; -} -efi_status_t -efi_file_size(efi_system_table_t *sys_table, void *__fh, - efi_char16_t *filename_16, void **handle, u64 *file_sz) -{ - if (efi_early->is64) - return __file_size64(__fh, filename_16, handle, file_sz); - - return __file_size32(__fh, filename_16, handle, file_sz); -} - -efi_status_t -efi_file_read(void *handle, unsigned long *size, void *addr) -{ - unsigned long func; - - if (efi_early->is64) { - efi_file_handle_64_t *fh = handle; - - func = (unsigned long)fh->read; - return efi_early->call(func, handle, size, addr); - } else { - efi_file_handle_32_t *fh = handle; - - func = (unsigned long)fh->read; - return efi_early->call(func, handle, size, addr); - } -} - -efi_status_t efi_file_close(void *handle) -{ - if (efi_early->is64) { - efi_file_handle_64_t *fh = handle; - - return efi_early->call((unsigned long)fh->close, handle); - } else { - efi_file_handle_32_t *fh = handle; - - return efi_early->call((unsigned long)fh->close, handle); - } -} - static inline efi_status_t __open_volume32(void *__image, void **__fh) { efi_file_io_interface_t *io; @@ -249,30 +102,8 @@ efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) { - unsigned long output_string; - size_t offset; - - if (efi_early->is64) { - struct efi_simple_text_output_protocol_64 *out; - u64 *func; - - offset = offsetof(typeof(*out), output_string); - output_string = efi_early->text_output + offset; - out = (typeof(out))(unsigned long)efi_early->text_output; - func = (u64 *)output_string; - - efi_early->call(*func, out, str); - } else { - struct efi_simple_text_output_protocol_32 *out; - u32 *func; - - offset = offsetof(typeof(*out), output_string); - output_string = efi_early->text_output + offset; - out = (typeof(out))(unsigned long)efi_early->text_output; - func = (u32 *)output_string; - - efi_early->call(*func, out, str); - } + efi_call_proto(efi_simple_text_output_protocol, output_string, + efi_early->text_output, str); } static efi_status_t @@ -1157,6 +988,13 @@ struct boot_params *efi_main(struct efi_config *c, else setup_boot_services32(efi_early); + /* + * If the boot loader gave us a value for secure_boot then we use that, + * otherwise we ask the BIOS. + */ + if (boot_params->secure_boot == efi_secureboot_mode_unset) + boot_params->secure_boot = efi_get_secureboot(sys_table); + setup_graphics(boot_params); setup_efi_pci(boot_params); diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index fd0b6a272dd5..d85b9625e836 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -82,7 +82,7 @@ ENTRY(efi_pe_entry) /* Relocate efi_config->call() */ leal efi32_config(%esi), %eax - add %esi, 32(%eax) + add %esi, 40(%eax) pushl %eax call make_boot_params @@ -108,7 +108,7 @@ ENTRY(efi32_stub_entry) /* Relocate efi_config->call() */ leal efi32_config(%esi), %eax - add %esi, 32(%eax) + add %esi, 40(%eax) pushl %eax 2: call efi_main @@ -264,7 +264,7 @@ relocated: #ifdef CONFIG_EFI_STUB .data efi32_config: - .fill 4,8,0 + .fill 5,8,0 .long efi_call_phys .long 0 .byte 0 diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 4d85e600db78..d2ae1f821e0c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -264,7 +264,7 @@ ENTRY(efi_pe_entry) /* * Relocate efi_config->call(). */ - addq %rbp, efi64_config+32(%rip) + addq %rbp, efi64_config+40(%rip) movq %rax, %rdi call make_boot_params @@ -284,7 +284,7 @@ handover_entry: * Relocate efi_config->call(). */ movq efi_config(%rip), %rax - addq %rbp, 32(%rax) + addq %rbp, 40(%rax) 2: movq efi_config(%rip), %rdi call efi_main @@ -456,14 +456,14 @@ efi_config: #ifdef CONFIG_EFI_MIXED .global efi32_config efi32_config: - .fill 4,8,0 + .fill 5,8,0 .quad efi64_thunk .byte 0 #endif .global efi64_config efi64_config: - .fill 4,8,0 + .fill 5,8,0 .quad efi_call .byte 1 #endif /* CONFIG_EFI_STUB */ diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index a66854d99ee1..8b7c9e75edcb 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -11,6 +11,7 @@ */ #include "misc.h" #include "error.h" +#include "../boot.h" #include <generated/compile.h> #include <linux/module.h> @@ -52,15 +53,22 @@ static unsigned long get_boot_seed(void) #include "../../lib/kaslr.c" struct mem_vector { - unsigned long start; - unsigned long size; + unsigned long long start; + unsigned long long size; }; +/* Only supporting at most 4 unusable memmap regions with kaslr */ +#define MAX_MEMMAP_REGIONS 4 + +static bool memmap_too_large; + enum mem_avoid_index { MEM_AVOID_ZO_RANGE = 0, MEM_AVOID_INITRD, MEM_AVOID_CMDLINE, MEM_AVOID_BOOTPARAMS, + MEM_AVOID_MEMMAP_BEGIN, + MEM_AVOID_MEMMAP_END = MEM_AVOID_MEMMAP_BEGIN + MAX_MEMMAP_REGIONS - 1, MEM_AVOID_MAX, }; @@ -77,6 +85,123 @@ static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two) return true; } +/** + * _memparse - Parse a string with mem suffixes into a number + * @ptr: Where parse begins + * @retptr: (output) Optional pointer to next char after parse completes + * + * Parses a string into a number. The number stored at @ptr is + * potentially suffixed with K, M, G, T, P, E. + */ +static unsigned long long _memparse(const char *ptr, char **retptr) +{ + char *endptr; /* Local pointer to end of parsed string */ + + unsigned long long ret = simple_strtoull(ptr, &endptr, 0); + + switch (*endptr) { + case 'E': + case 'e': + ret <<= 10; + case 'P': + case 'p': + ret <<= 10; + case 'T': + case 't': + ret <<= 10; + case 'G': + case 'g': + ret <<= 10; + case 'M': + case 'm': + ret <<= 10; + case 'K': + case 'k': + ret <<= 10; + endptr++; + default: + break; + } + + if (retptr) + *retptr = endptr; + + return ret; +} + +static int +parse_memmap(char *p, unsigned long long *start, unsigned long long *size) +{ + char *oldp; + + if (!p) + return -EINVAL; + + /* We don't care about this option here */ + if (!strncmp(p, "exactmap", 8)) + return -EINVAL; + + oldp = p; + *size = _memparse(p, &p); + if (p == oldp) + return -EINVAL; + + switch (*p) { + case '@': + /* Skip this region, usable */ + *start = 0; + *size = 0; + return 0; + case '#': + case '$': + case '!': + *start = _memparse(p + 1, &p); + return 0; + } + + return -EINVAL; +} + +static void mem_avoid_memmap(void) +{ + char arg[128]; + int rc; + int i; + char *str; + + /* See if we have any memmap areas */ + rc = cmdline_find_option("memmap", arg, sizeof(arg)); + if (rc <= 0) + return; + + i = 0; + str = arg; + while (str && (i < MAX_MEMMAP_REGIONS)) { + int rc; + unsigned long long start, size; + char *k = strchr(str, ','); + + if (k) + *k++ = 0; + + rc = parse_memmap(str, &start, &size); + if (rc < 0) + break; + str = k; + /* A usable region that should not be skipped */ + if (size == 0) + continue; + + mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].start = start; + mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].size = size; + i++; + } + + /* More than 4 memmaps, fail kaslr */ + if ((i >= MAX_MEMMAP_REGIONS) && str) + memmap_too_large = true; +} + /* * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T). * The mem_avoid array is used to store the ranges that need to be avoided @@ -197,6 +322,9 @@ 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 */ + mem_avoid_memmap(); + #ifdef CONFIG_X86_VERBOSE_BOOTUP /* Make sure video RAM can be used. */ add_identity_map(0, PMD_SIZE); @@ -379,6 +507,12 @@ static unsigned long find_random_phys_addr(unsigned long minimum, int i; unsigned long addr; + /* Check if we had too many memmaps. */ + if (memmap_too_large) { + debug_putstr("Aborted e820 scan (more than 4 memmap= args)!\n"); + return 0; + } + /* Make sure minimum is aligned. */ minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); @@ -456,7 +590,7 @@ void choose_random_location(unsigned long input, /* Walk e820 and find a random address. */ random_addr = find_random_phys_addr(min_addr, output_size); if (!random_addr) { - warn("KASLR disabled: could not find suitable E820 region!"); + warn("Physical KASLR disabled: no suitable memory region!"); } else { /* Update the new physical address location. */ if (*output != random_addr) { diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 9e240fcba784..5457b02fc050 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -156,3 +156,16 @@ char *strstr(const char *s1, const char *s2) } return NULL; } + +/** + * strchr - Find the first occurrence of the character c in the string s. + * @s: the string to be searched + * @c: the character to search for + */ +char *strchr(const char *s, int c) +{ + while (*s != (char)c) + if (*s++ == '\0') + return NULL; + return (char *)s; +} diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index 1d392c39fe56..b8ccdb5c9244 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -1,11 +1,4 @@ -obj-y += core.o - -obj-$(CONFIG_CPU_SUP_AMD) += amd/core.o amd/uncore.o -obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += amd/power.o -obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o -ifdef CONFIG_AMD_IOMMU -obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o -endif - -obj-$(CONFIG_CPU_SUP_INTEL) += msr.o +obj-y += core.o +obj-y += amd/ +obj-$(CONFIG_X86_LOCAL_APIC) += msr.o obj-$(CONFIG_CPU_SUP_INTEL) += intel/ diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile new file mode 100644 index 000000000000..b1da46f396e0 --- /dev/null +++ b/arch/x86/events/amd/Makefile @@ -0,0 +1,7 @@ +obj-$(CONFIG_CPU_SUP_AMD) += core.o uncore.o +obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o +obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o +ifdef CONFIG_AMD_IOMMU +obj-$(CONFIG_CPU_SUP_AMD) += iommu.o +endif + diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index a0b1bdb3ad42..4d1f7f2d9aff 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -22,13 +22,17 @@ #define NUM_COUNTERS_NB 4 #define NUM_COUNTERS_L2 4 -#define MAX_COUNTERS NUM_COUNTERS_NB +#define NUM_COUNTERS_L3 6 +#define MAX_COUNTERS 6 #define RDPMC_BASE_NB 6 -#define RDPMC_BASE_L2 10 +#define RDPMC_BASE_LLC 10 #define COUNTER_SHIFT 16 +static int num_counters_llc; +static int num_counters_nb; + static HLIST_HEAD(uncore_unused_list); struct amd_uncore { @@ -45,30 +49,30 @@ struct amd_uncore { }; static struct amd_uncore * __percpu *amd_uncore_nb; -static struct amd_uncore * __percpu *amd_uncore_l2; +static struct amd_uncore * __percpu *amd_uncore_llc; static struct pmu amd_nb_pmu; -static struct pmu amd_l2_pmu; +static struct pmu amd_llc_pmu; static cpumask_t amd_nb_active_mask; -static cpumask_t amd_l2_active_mask; +static cpumask_t amd_llc_active_mask; static bool is_nb_event(struct perf_event *event) { return event->pmu->type == amd_nb_pmu.type; } -static bool is_l2_event(struct perf_event *event) +static bool is_llc_event(struct perf_event *event) { - return event->pmu->type == amd_l2_pmu.type; + return event->pmu->type == amd_llc_pmu.type; } static struct amd_uncore *event_to_amd_uncore(struct perf_event *event) { if (is_nb_event(event) && amd_uncore_nb) return *per_cpu_ptr(amd_uncore_nb, event->cpu); - else if (is_l2_event(event) && amd_uncore_l2) - return *per_cpu_ptr(amd_uncore_l2, event->cpu); + else if (is_llc_event(event) && amd_uncore_llc) + return *per_cpu_ptr(amd_uncore_llc, event->cpu); return NULL; } @@ -183,16 +187,16 @@ static int amd_uncore_event_init(struct perf_event *event) return -ENOENT; /* - * NB and L2 counters (MSRs) are shared across all cores that share the - * same NB / L2 cache. Interrupts can be directed to a single target - * core, however, event counts generated by processes running on other - * cores cannot be masked out. So we do not support sampling and - * per-thread events. + * NB and Last level cache counters (MSRs) are shared across all cores + * that share the same NB / Last level cache. Interrupts can be directed + * to a single target core, however, event counts generated by processes + * running on other cores cannot be masked out. So we do not support + * sampling and per-thread events. */ if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) return -EINVAL; - /* NB and L2 counters do not have usr/os/guest/host bits */ + /* NB and Last level cache counters do not have usr/os/guest/host bits */ if (event->attr.exclude_user || event->attr.exclude_kernel || event->attr.exclude_host || event->attr.exclude_guest) return -EINVAL; @@ -226,8 +230,8 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev, if (pmu->type == amd_nb_pmu.type) active_mask = &amd_nb_active_mask; - else if (pmu->type == amd_l2_pmu.type) - active_mask = &amd_l2_active_mask; + else if (pmu->type == amd_llc_pmu.type) + active_mask = &amd_llc_active_mask; else return 0; @@ -244,30 +248,47 @@ static struct attribute_group amd_uncore_attr_group = { .attrs = amd_uncore_attrs, }; -PMU_FORMAT_ATTR(event, "config:0-7,32-35"); -PMU_FORMAT_ATTR(umask, "config:8-15"); - -static struct attribute *amd_uncore_format_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - NULL, -}; - -static struct attribute_group amd_uncore_format_group = { - .name = "format", - .attrs = amd_uncore_format_attr, +/* + * Similar to PMU_FORMAT_ATTR but allowing for format_attr to be assigned based + * on family + */ +#define AMD_FORMAT_ATTR(_dev, _name, _format) \ +static ssize_t \ +_dev##_show##_name(struct device *dev, \ + struct device_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct device_attribute format_attr_##_dev##_name = __ATTR_RO(_dev); + +/* Used for each uncore counter type */ +#define AMD_ATTRIBUTE(_name) \ +static struct attribute *amd_uncore_format_attr_##_name[] = { \ + &format_attr_event_##_name.attr, \ + &format_attr_umask.attr, \ + NULL, \ +}; \ +static struct attribute_group amd_uncore_format_group_##_name = { \ + .name = "format", \ + .attrs = amd_uncore_format_attr_##_name, \ +}; \ +static const struct attribute_group *amd_uncore_attr_groups_##_name[] = { \ + &amd_uncore_attr_group, \ + &amd_uncore_format_group_##_name, \ + NULL, \ }; -static const struct attribute_group *amd_uncore_attr_groups[] = { - &amd_uncore_attr_group, - &amd_uncore_format_group, - NULL, -}; +AMD_FORMAT_ATTR(event, , "config:0-7,32-35"); +AMD_FORMAT_ATTR(umask, , "config:8-15"); +AMD_FORMAT_ATTR(event, _df, "config:0-7,32-35,59-60"); +AMD_FORMAT_ATTR(event, _l3, "config:0-7"); +AMD_ATTRIBUTE(df); +AMD_ATTRIBUTE(l3); static struct pmu amd_nb_pmu = { .task_ctx_nr = perf_invalid_context, - .attr_groups = amd_uncore_attr_groups, - .name = "amd_nb", .event_init = amd_uncore_event_init, .add = amd_uncore_add, .del = amd_uncore_del, @@ -276,10 +297,8 @@ static struct pmu amd_nb_pmu = { .read = amd_uncore_read, }; -static struct pmu amd_l2_pmu = { +static struct pmu amd_llc_pmu = { .task_ctx_nr = perf_invalid_context, - .attr_groups = amd_uncore_attr_groups, - .name = "amd_l2", .event_init = amd_uncore_event_init, .add = amd_uncore_add, .del = amd_uncore_del, @@ -296,14 +315,14 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) static int amd_uncore_cpu_up_prepare(unsigned int cpu) { - struct amd_uncore *uncore_nb = NULL, *uncore_l2; + struct amd_uncore *uncore_nb = NULL, *uncore_llc; if (amd_uncore_nb) { uncore_nb = amd_uncore_alloc(cpu); if (!uncore_nb) goto fail; uncore_nb->cpu = cpu; - uncore_nb->num_counters = NUM_COUNTERS_NB; + uncore_nb->num_counters = num_counters_nb; uncore_nb->rdpmc_base = RDPMC_BASE_NB; uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL; uncore_nb->active_mask = &amd_nb_active_mask; @@ -312,18 +331,18 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu) *per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb; } - if (amd_uncore_l2) { - uncore_l2 = amd_uncore_alloc(cpu); - if (!uncore_l2) + if (amd_uncore_llc) { + uncore_llc = amd_uncore_alloc(cpu); + if (!uncore_llc) goto fail; - uncore_l2->cpu = cpu; - uncore_l2->num_counters = NUM_COUNTERS_L2; - uncore_l2->rdpmc_base = RDPMC_BASE_L2; - uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL; - uncore_l2->active_mask = &amd_l2_active_mask; - uncore_l2->pmu = &amd_l2_pmu; - uncore_l2->id = -1; - *per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2; + uncore_llc->cpu = cpu; + uncore_llc->num_counters = num_counters_llc; + uncore_llc->rdpmc_base = RDPMC_BASE_LLC; + uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL; + uncore_llc->active_mask = &amd_llc_active_mask; + uncore_llc->pmu = &amd_llc_pmu; + uncore_llc->id = -1; + *per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc; } return 0; @@ -376,17 +395,17 @@ static int amd_uncore_cpu_starting(unsigned int cpu) *per_cpu_ptr(amd_uncore_nb, cpu) = uncore; } - if (amd_uncore_l2) { + if (amd_uncore_llc) { unsigned int apicid = cpu_data(cpu).apicid; unsigned int nshared; - uncore = *per_cpu_ptr(amd_uncore_l2, cpu); + uncore = *per_cpu_ptr(amd_uncore_llc, cpu); cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx); nshared = ((eax >> 14) & 0xfff) + 1; uncore->id = apicid - (apicid % nshared); - uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2); - *per_cpu_ptr(amd_uncore_l2, cpu) = uncore; + uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc); + *per_cpu_ptr(amd_uncore_llc, cpu) = uncore; } return 0; @@ -419,8 +438,8 @@ static int amd_uncore_cpu_online(unsigned int cpu) if (amd_uncore_nb) uncore_online(cpu, amd_uncore_nb); - if (amd_uncore_l2) - uncore_online(cpu, amd_uncore_l2); + if (amd_uncore_llc) + uncore_online(cpu, amd_uncore_llc); return 0; } @@ -456,8 +475,8 @@ static int amd_uncore_cpu_down_prepare(unsigned int cpu) if (amd_uncore_nb) uncore_down_prepare(cpu, amd_uncore_nb); - if (amd_uncore_l2) - uncore_down_prepare(cpu, amd_uncore_l2); + if (amd_uncore_llc) + uncore_down_prepare(cpu, amd_uncore_llc); return 0; } @@ -479,8 +498,8 @@ static int amd_uncore_cpu_dead(unsigned int cpu) if (amd_uncore_nb) uncore_dead(cpu, amd_uncore_nb); - if (amd_uncore_l2) - uncore_dead(cpu, amd_uncore_l2); + if (amd_uncore_llc) + uncore_dead(cpu, amd_uncore_llc); return 0; } @@ -492,6 +511,47 @@ static int __init amd_uncore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) goto fail_nodev; + switch(boot_cpu_data.x86) { + case 23: + /* Family 17h: */ + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L3; + /* + * For Family17h, the NorthBridge counters are + * re-purposed as Data Fabric counters. Also, support is + * added for L3 counters. The pmus are exported based on + * family as either L2 or L3 and NB or DF. + */ + amd_nb_pmu.name = "amd_df"; + amd_llc_pmu.name = "amd_l3"; + format_attr_event_df.show = &event_show_df; + format_attr_event_l3.show = &event_show_l3; + break; + case 22: + /* Family 16h - may change: */ + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L2; + amd_nb_pmu.name = "amd_nb"; + amd_llc_pmu.name = "amd_l2"; + format_attr_event_df = format_attr_event; + format_attr_event_l3 = format_attr_event; + break; + default: + /* + * All prior families have the same number of + * NorthBridge and Last Level Cache counters + */ + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L2; + amd_nb_pmu.name = "amd_nb"; + amd_llc_pmu.name = "amd_l2"; + format_attr_event_df = format_attr_event; + format_attr_event_l3 = format_attr_event; + break; + } + amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df; + amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3; + if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) goto fail_nodev; @@ -510,16 +570,16 @@ static int __init amd_uncore_init(void) } if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) { - amd_uncore_l2 = alloc_percpu(struct amd_uncore *); - if (!amd_uncore_l2) { + amd_uncore_llc = alloc_percpu(struct amd_uncore *); + if (!amd_uncore_llc) { ret = -ENOMEM; - goto fail_l2; + goto fail_llc; } - ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1); + ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1); if (ret) - goto fail_l2; + goto fail_llc; - pr_info("perf: AMD L2I counters detected\n"); + pr_info("perf: AMD LLC counters detected\n"); ret = 0; } @@ -529,7 +589,7 @@ static int __init amd_uncore_init(void) if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP, "perf/x86/amd/uncore:prepare", amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead)) - goto fail_l2; + goto fail_llc; if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, "perf/x86/amd/uncore:starting", @@ -546,11 +606,11 @@ fail_start: cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING); fail_prep: cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP); -fail_l2: +fail_llc: if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) perf_pmu_unregister(&amd_nb_pmu); - if (amd_uncore_l2) - free_percpu(amd_uncore_l2); + if (amd_uncore_llc) + free_percpu(amd_uncore_llc); fail_nb: if (amd_uncore_nb) free_percpu(amd_uncore_nb); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 1076c9a77292..aff4b5b69d40 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -541,6 +541,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), { }, diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 1c1b9fe705c8..5900471ee508 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -99,18 +99,24 @@ static struct attribute_group pt_cap_group = { }; PMU_FORMAT_ATTR(cyc, "config:1" ); +PMU_FORMAT_ATTR(pwr_evt, "config:4" ); +PMU_FORMAT_ATTR(fup_on_ptw, "config:5" ); PMU_FORMAT_ATTR(mtc, "config:9" ); PMU_FORMAT_ATTR(tsc, "config:10" ); PMU_FORMAT_ATTR(noretcomp, "config:11" ); +PMU_FORMAT_ATTR(ptw, "config:12" ); PMU_FORMAT_ATTR(mtc_period, "config:14-17" ); PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" ); PMU_FORMAT_ATTR(psb_period, "config:24-27" ); static struct attribute *pt_formats_attr[] = { &format_attr_cyc.attr, + &format_attr_pwr_evt.attr, + &format_attr_fup_on_ptw.attr, &format_attr_mtc.attr, &format_attr_tsc.attr, &format_attr_noretcomp.attr, + &format_attr_ptw.attr, &format_attr_mtc_period.attr, &format_attr_cyc_thresh.attr, &format_attr_psb_period.attr, diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 22ef4f72cf32..22054ca49026 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -771,6 +771,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init), {}, }; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 1ab45976474d..758c1aa5009d 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1328,6 +1328,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init), {}, }; diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 2b892e2313a9..5d6a53fd7521 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -7,7 +7,6 @@ generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h generic-y += clkdev.h -generic-y += cputime.h generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 0c5fbc68e82d..eff8e36aaf72 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -195,7 +195,7 @@ static inline void native_apic_msr_write(u32 reg, u32 v) static inline void native_apic_msr_eoi_write(u32 reg, u32 v) { - wrmsr_notrace(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0); + __wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0); } static inline u32 native_apic_msr_read(u32 reg) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index eafee3161d1c..4e7772387c6e 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -100,7 +100,7 @@ #define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ #define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ #define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */ +#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ #define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ #define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ #define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ @@ -186,7 +186,7 @@ * * Reuse free bits when adding new feature flags! */ - +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ @@ -288,6 +288,7 @@ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ @@ -320,5 +321,4 @@ #define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ - #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h index ced283ac79df..af95c47d5c9e 100644 --- a/arch/x86/include/asm/div64.h +++ b/arch/x86/include/asm/div64.h @@ -59,6 +59,17 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) } #define div_u64_rem div_u64_rem +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + u32 high, low; + + asm ("mull %[b]" : "=a" (low), "=d" (high) + : [a] "a" (a), [b] "rm" (b) ); + + return low | ((u64)high) << 32; +} +#define mul_u32_u32 mul_u32_u32 + #else # include <asm-generic/div64.h> #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index ec23d8e1297c..67313f3a9874 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -30,8 +30,6 @@ extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type, int checktype); extern void update_e820(void); extern void e820_setup_gap(void); -extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, - unsigned long start_addr, unsigned long long end_addr); struct setup_data; extern void parse_e820_ext(u64 phys_addr, u32 data_len); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index e99675b9c861..2f77bcefe6b4 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -191,6 +191,7 @@ static inline efi_status_t efi_thunk_set_virtual_address_map( struct efi_config { u64 image_handle; u64 table; + u64 runtime_services; u64 boot_services; u64 text_output; efi_status_t (*call)(unsigned long, ...); @@ -226,6 +227,10 @@ static inline bool efi_is_64bit(void) #define __efi_call_early(f, ...) \ __efi_early()->call((unsigned long)f, __VA_ARGS__); +#define efi_call_runtime(f, ...) \ + __efi_early()->call(efi_table_attr(efi_runtime_services, f, \ + __efi_early()->runtime_services), __VA_ARGS__) + extern bool efi_reboot_required(void); #else diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index e7f155c3045e..9d49c18b5ea9 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -258,6 +258,15 @@ extern int force_personality32; #define ELF_HWCAP (boot_cpu_data.x86_capability[CPUID_1_EDX]) +extern u32 elf_hwcap2; + +/* + * HWCAP2 supplies mask with kernel enabled CPU features, so that + * the application can discover that it can safely use them. + * The bits are defined in uapi/asm/hwcap2.h. + */ +#define ELF_HWCAP2 (elf_hwcap2) + /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in intent than poking at uname or /proc/cpuinfo. diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index d4a684997497..255645f60ca2 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -87,6 +87,16 @@ extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif + +static inline void fpstate_init_xstate(struct xregs_state *xsave) +{ + /* + * XRSTORS requires these bits set in xcomp_bv, or it will + * trigger #GP: + */ + xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask; +} + static inline void fpstate_init_fxstate(struct fxregs_state *fx) { fx->cwd = 0x37f; diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 5132f2a6c0a2..e63873683d4a 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -97,10 +97,6 @@ #define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */ -/* Software defined banks */ -#define MCE_EXTENDED_BANK 128 -#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0) - #define MCE_LOG_LEN 32 #define MCE_LOG_SIGNATURE "MACHINECHECK" @@ -193,6 +189,15 @@ extern struct mce_vendor_flags mce_flags; extern struct mca_config mca_cfg; extern struct mca_msr_regs msr_ops; + +enum mce_notifier_prios { + MCE_PRIO_SRAO = INT_MAX, + MCE_PRIO_EXTLOG = INT_MAX - 1, + MCE_PRIO_NFIT = INT_MAX - 2, + MCE_PRIO_EDAC = INT_MAX - 3, + MCE_PRIO_LOWEST = 0, +}; + extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -306,8 +311,6 @@ extern void (*deferred_error_int_vector)(void); void intel_init_thermal(struct cpuinfo_x86 *c); -void mce_log_therm_throt_event(__u64 status); - /* Interrupt Handler for core thermal thresholds */ extern int (*platform_thermal_notify)(__u64 msr_val); @@ -362,12 +365,13 @@ struct smca_hwid { unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */ u32 hwid_mcatype; /* (hwid,mcatype) tuple */ u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */ + u8 count; /* Number of instances. */ }; struct smca_bank { struct smca_hwid *hwid; - /* Instance ID */ - u32 id; + u32 id; /* Value of MCA_IPID[InstanceId]. */ + u8 sysfs_id; /* Value used for sysfs name. */ }; extern struct smca_bank smca_banks[MAX_NR_BANKS]; diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 2266f864b747..daadeeea00b1 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -7,18 +7,17 @@ #define native_rdmsr(msr, val1, val2) \ do { \ - u64 __val = native_read_msr((msr)); \ + u64 __val = __rdmsr((msr)); \ (void)((val1) = (u32)__val); \ (void)((val2) = (u32)(__val >> 32)); \ } while (0) #define native_wrmsr(msr, low, high) \ - native_write_msr(msr, low, high) + __wrmsr(msr, low, high) #define native_wrmsrl(msr, val) \ - native_write_msr((msr), \ - (u32)((u64)(val)), \ - (u32)((u64)(val) >> 32)) + __wrmsr((msr), (u32)((u64)(val)), \ + (u32)((u64)(val) >> 32)) struct ucode_patch { struct list_head plist; diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 3e3e20be829a..3d57009e168b 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -54,6 +54,4 @@ static inline int __init save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } void reload_ucode_amd(void) {} #endif - -extern bool check_current_patch_level(u32 *rev, bool early); #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 710273c617b8..00293a94ffaf 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -543,6 +543,11 @@ #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT) +/* MISC_FEATURE_ENABLES non-architectural features */ +#define MSR_MISC_FEATURE_ENABLES 0x00000140 + +#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT 1 + #define MSR_IA32_TSC_DEADLINE 0x000006E0 /* P4/Xeon+ specific */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index db0b90c3b03e..898dba2e2e2c 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -80,7 +80,14 @@ static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {} static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} #endif -static inline unsigned long long native_read_msr(unsigned int msr) +/* + * __rdmsr() and __wrmsr() are the two primitives which are the bare minimum MSR + * accessors and should not have any tracing or other functionality piggybacking + * on them - those are *purely* for accessing MSRs and nothing more. So don't even + * think of extending them - you will be slapped with a stinking trout or a frozen + * shark will reach you, wherever you are! You've been warned. + */ +static inline unsigned long long notrace __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -88,11 +95,30 @@ static inline unsigned long long native_read_msr(unsigned int msr) "2:\n" _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe) : EAX_EDX_RET(val, low, high) : "c" (msr)); - if (msr_tracepoint_active(__tracepoint_read_msr)) - do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0); + return EAX_EDX_VAL(val, low, high); } +static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +{ + asm volatile("1: wrmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe) + : : "c" (msr), "a"(low), "d" (high) : "memory"); +} + +static inline unsigned long long native_read_msr(unsigned int msr) +{ + unsigned long long val; + + val = __rdmsr(msr); + + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, val, 0); + + return val; +} + static inline unsigned long long native_read_msr_safe(unsigned int msr, int *err) { @@ -116,29 +142,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, /* Can be uninlined because referenced by paravirt */ static inline void notrace -__native_write_msr_notrace(unsigned int msr, u32 low, u32 high) -{ - asm volatile("1: wrmsr\n" - "2:\n" - _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe) - : : "c" (msr), "a"(low), "d" (high) : "memory"); -} - -/* Can be uninlined because referenced by paravirt */ -static inline void notrace native_write_msr(unsigned int msr, u32 low, u32 high) { - __native_write_msr_notrace(msr, low, high); + __wrmsr(msr, low, high); + if (msr_tracepoint_active(__tracepoint_write_msr)) do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } -static inline void -wrmsr_notrace(unsigned int msr, u32 low, u32 high) -{ - __native_write_msr_notrace(msr, low, high); -} - /* Can be uninlined because referenced by paravirt */ static inline int notrace native_write_msr_safe(unsigned int msr, u32 low, u32 high) diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index b6c0b404898a..fbc73360aea0 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -27,6 +27,7 @@ struct vm_area_struct; extern pgd_t swapper_pg_dir[1024]; extern pgd_t initial_page_table[1024]; +extern pmd_t initial_pg_pmd[]; static inline void pgtable_cache_init(void) { } static inline void check_pgt_cache(void) { } @@ -75,4 +76,35 @@ do { \ #define kern_addr_valid(kaddr) (0) #endif +/* + * This is how much memory in addition to the memory covered up to + * and including _end we need mapped initially. + * We need: + * (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE) + * (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE) + * + * Modulo rounding, each megabyte assigned here requires a kilobyte of + * memory, which is currently unreclaimed. + * + * This should be a multiple of a page. + * + * KERNEL_IMAGE_SIZE should be greater than pa(_end) + * and small than max_low_pfn, otherwise will waste some page table entries + */ +#if PTRS_PER_PMD > 1 +#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD) +#else +#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) +#endif + +/* + * Number of possible pages in the lowmem region. + * + * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a + * gas warning about overflowing shift count when gas has been compiled + * with only a host target support using a 32-bit type for internal + * representation. + */ +#define LOWMEM_PAGES ((((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)) + #endif /* _ASM_X86_PGTABLE_32_H */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 921bea7a2708..6d391909e864 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -23,9 +23,6 @@ /* How long a lock should spin before we consider blocking */ #define SPIN_THRESHOLD (1 << 15) -extern struct static_key paravirt_ticketlocks_enabled; -static __always_inline bool static_key_false(struct static_key *key); - #include <asm/qspinlock.h> /* diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index b10bf319ed20..5138dacf8bb8 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -135,7 +135,8 @@ struct boot_params { __u8 eddbuf_entries; /* 0x1e9 */ __u8 edd_mbr_sig_buf_entries; /* 0x1ea */ __u8 kbd_status; /* 0x1eb */ - __u8 _pad5[3]; /* 0x1ec */ + __u8 secure_boot; /* 0x1ec */ + __u8 _pad5[2]; /* 0x1ed */ /* * The sentinel is set to a nonzero value (0xff) in header.S. * diff --git a/arch/x86/include/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h new file mode 100644 index 000000000000..0bd2be5c7617 --- /dev/null +++ b/arch/x86/include/uapi/asm/hwcap2.h @@ -0,0 +1,7 @@ +#ifndef _ASM_X86_HWCAP2_H +#define _ASM_X86_HWCAP2_H + +/* MONITOR/MWAIT enabled in Ring 3 */ +#define HWCAP2_RING3MWAIT (1 << 0) + +#endif diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 64422f850e95..7ff007ed899d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -35,6 +35,7 @@ #include <linux/bootmem.h> #include <linux/ioport.h> #include <linux/pci.h> +#include <linux/efi-bgrt.h> #include <asm/irqdomain.h> #include <asm/pci_x86.h> @@ -1557,6 +1558,12 @@ int __init early_acpi_boot_init(void) return 0; } +static int __init acpi_parse_bgrt(struct acpi_table_header *table) +{ + efi_bgrt_init(table); + return 0; +} + int __init acpi_boot_init(void) { /* those are executed after early-quirks are executed */ @@ -1581,6 +1588,8 @@ int __init acpi_boot_init(void) acpi_process_madt(); acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet); + if (IS_ENABLED(CONFIG_ACPI_BGRT)) + acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); if (!acpi_noirq) x86_init.pci.init = pci_acpi_init; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 5b7e43eff139..8567c851172c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -529,18 +529,19 @@ static void lapic_timer_broadcast(const struct cpumask *mask) * The local apic timer can be used for any function which is CPU local. */ static struct clock_event_device lapic_clockevent = { - .name = "lapic", - .features = CLOCK_EVT_FEAT_PERIODIC | - CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP - | CLOCK_EVT_FEAT_DUMMY, - .shift = 32, - .set_state_shutdown = lapic_timer_shutdown, - .set_state_periodic = lapic_timer_set_periodic, - .set_state_oneshot = lapic_timer_set_oneshot, - .set_next_event = lapic_next_event, - .broadcast = lapic_timer_broadcast, - .rating = 100, - .irq = -1, + .name = "lapic", + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP + | CLOCK_EVT_FEAT_DUMMY, + .shift = 32, + .set_state_shutdown = lapic_timer_shutdown, + .set_state_periodic = lapic_timer_set_periodic, + .set_state_oneshot = lapic_timer_set_oneshot, + .set_state_oneshot_stopped = lapic_timer_shutdown, + .set_next_event = lapic_next_event, + .broadcast = lapic_timer_broadcast, + .rating = 100, + .irq = -1, }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); @@ -1245,7 +1246,7 @@ static void lapic_setup_esr(void) /** * setup_local_APIC - setup the local APIC * - * Used to setup local APIC while initializing BSP or bringin up APs. + * Used to setup local APIC while initializing BSP or bringing up APs. * Always called with preemption disabled. */ void setup_local_APIC(void) @@ -2028,8 +2029,8 @@ void disconnect_bsp_APIC(int virt_wire_setup) /* * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated * contiguously, it equals to current allocated max logical CPU ID plus 1. - * All allocated CPU ID should be in [0, nr_logical_cpuidi), so the maximum of - * nr_logical_cpuids is nr_cpu_ids. + * All allocated CPU IDs should be in the [0, nr_logical_cpuids) range, + * so the maximum of nr_logical_cpuids is nr_cpu_ids. * * NOTE: Reserve 0 for BSP. */ @@ -2094,7 +2095,7 @@ int __generic_processor_info(int apicid, int version, bool enabled) * Since fixing handling of boot_cpu_physical_apicid requires * another discussion and tests on each platform, we leave it * for now and here we use read_apic_id() directly in this - * function, generic_processor_info(). + * function, __generic_processor_info(). */ if (disabled_cpu_apicid != BAD_APICID && disabled_cpu_apicid != read_apic_id() && diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index bd6b8c270c24..52f352b063fd 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1875,6 +1875,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_ack = irq_chip_ack_parent, .irq_eoi = ioapic_ack_level, .irq_set_affinity = ioapic_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -1886,6 +1887,7 @@ static struct irq_chip ioapic_ir_chip __read_mostly = { .irq_ack = irq_chip_ack_parent, .irq_eoi = ioapic_ir_ack_level, .irq_set_affinity = ioapic_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 45d44c173cf9..4a7080c84a5a 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -905,8 +905,8 @@ static int apm_cpu_idle(struct cpuidle_device *dev, { static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ - static unsigned int last_stime; /* = 0 */ - cputime_t stime, utime; + static u64 last_stime; /* = 0 */ + u64 stime, utime; int apm_idle_done = 0; unsigned int jiffies_since_last_check = jiffies - last_jiffies; @@ -919,7 +919,7 @@ recalc: } else if (jiffies_since_last_check > idle_period) { unsigned int idle_percentage; - idle_percentage = cputime_to_jiffies(stime - last_stime); + idle_percentage = nsecs_to_jiffies(stime - last_stime); idle_percentage *= 100; idle_percentage /= jiffies_since_last_check; use_apm_idle = (idle_percentage > idle_threshold); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index c62e015b126c..de827d6ac8c2 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -81,6 +81,7 @@ void common(void) { BLANK(); OFFSET(BP_scratch, boot_params, scratch); + OFFSET(BP_secure_boot, boot_params, secure_boot); OFFSET(BP_loadflags, boot_params, hdr.loadflags); OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); OFFSET(BP_version, boot_params, hdr.version); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2b4cf04239b6..4e95b2e0d95f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -555,8 +555,10 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 1661d8ec9280..2c234a6d94c4 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,5 +1,5 @@ -#include <linux/bitops.h> -#include <linux/kernel.h> + +#include <linux/sched.h> #include <asm/cpufeature.h> #include <asm/e820.h> @@ -104,6 +104,8 @@ static void early_init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #endif + + clear_sched_clock_stable(); } static void init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ede03e849a8b..f07005e6f461 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -35,6 +35,7 @@ #include <asm/desc.h> #include <asm/fpu/internal.h> #include <asm/mtrr.h> +#include <asm/hwcap2.h> #include <linux/numa.h> #include <asm/asm.h> #include <asm/bugs.h> @@ -51,6 +52,8 @@ #include "cpu.h" +u32 elf_hwcap2 __read_mostly; + /* all of these masks are initialized in setup_cpu_local_masks() */ cpumask_var_t cpu_initialized_mask; cpumask_var_t cpu_callout_mask; @@ -83,6 +86,7 @@ static void default_init(struct cpuinfo_x86 *c) strcpy(c->x86_model_id, "386"); } #endif + clear_sched_clock_stable(); } static const struct cpu_dev default_cpu = { @@ -655,6 +659,16 @@ void cpu_detect(struct cpuinfo_x86 *c) } } +static void apply_forced_caps(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < NCAPINTS; i++) { + c->x86_capability[i] &= ~cpu_caps_cleared[i]; + c->x86_capability[i] |= cpu_caps_set[i]; + } +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -748,6 +762,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + + /* + * Clear/Set all flags overridden by options, after probe. + * This needs to happen each time we re-probe, which may happen + * several times during CPU initialization. + */ + apply_forced_caps(c); } static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -801,14 +822,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) memset(&c->x86_capability, 0, sizeof c->x86_capability); c->extended_cpuid_level = 0; - if (!have_cpuid_p()) - identify_cpu_without_cpuid(c); - /* cyrix could have cpuid enabled via c_identify()*/ if (have_cpuid_p()) { cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); + setup_force_cpu_cap(X86_FEATURE_CPUID); if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -818,6 +837,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_bsp_init) this_cpu->c_bsp_init(c); + } else { + identify_cpu_without_cpuid(c); + setup_clear_cpu_cap(X86_FEATURE_CPUID); } setup_force_cpu_cap(X86_FEATURE_ALWAYS); @@ -1035,10 +1057,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_identify(c); /* Clear/Set all flags overridden by options, after probe */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + apply_forced_caps(c); #ifdef CONFIG_X86_64 c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); @@ -1056,6 +1075,8 @@ static void identify_cpu(struct cpuinfo_x86 *c) */ if (this_cpu->c_init) this_cpu->c_init(c); + else + clear_sched_clock_stable(); /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); @@ -1097,10 +1118,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) * Clear/Set all flags overridden by options, need do it * before following smp all cpus cap AND. */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + apply_forced_caps(c); /* * On SMP, boot_cpu_data holds the common feature set between diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index bd9dcd6b712d..47416f959a48 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -9,6 +9,7 @@ #include <asm/pci-direct.h> #include <asm/tsc.h> #include <asm/cpufeature.h> +#include <linux/sched.h> #include "cpu.h" @@ -183,6 +184,7 @@ static void early_init_cyrix(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); break; } + clear_sched_clock_stable(); } static void init_cyrix(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 203f860d2ab3..017ecd3bb553 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -15,6 +15,8 @@ #include <asm/cpu.h> #include <asm/intel-family.h> #include <asm/microcode_intel.h> +#include <asm/hwcap2.h> +#include <asm/elf.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -62,6 +64,46 @@ void check_mpx_erratum(struct cpuinfo_x86 *c) } } +static bool ring3mwait_disabled __read_mostly; + +static int __init ring3mwait_disable(char *__unused) +{ + ring3mwait_disabled = true; + return 0; +} +__setup("ring3mwait=disable", ring3mwait_disable); + +static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) +{ + /* + * Ring 3 MONITOR/MWAIT feature cannot be detected without + * cpu model and family comparison. + */ + if (c->x86 != 6) + return; + switch (c->x86_model) { + case INTEL_FAM6_XEON_PHI_KNL: + case INTEL_FAM6_XEON_PHI_KNM: + break; + default: + return; + } + + if (ring3mwait_disabled) { + msr_clear_bit(MSR_MISC_FEATURE_ENABLES, + MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); + return; + } + + msr_set_bit(MSR_MISC_FEATURE_ENABLES, + MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); + + set_cpu_cap(c, X86_FEATURE_RING3MWAIT); + + if (c == &boot_cpu_data) + ELF_HWCAP2 |= HWCAP2_RING3MWAIT; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -119,8 +161,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ @@ -560,6 +604,8 @@ static void init_intel(struct cpuinfo_x86 *c) detect_vmx_virtcap(c); init_intel_energy_perf(c); + + probe_xeon_phi_r3mwait(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index 83f1a98d37db..2eee85379689 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -52,8 +52,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) if (severity >= GHES_SEV_RECOVERABLE) m.status |= MCI_STATUS_UC; - if (severity >= GHES_SEV_PANIC) + + if (severity >= GHES_SEV_PANIC) { m.status |= MCI_STATUS_PCC; + m.tsc = rdtsc(); + } m.addr = mem_err->physical_addr; mce_log(&m); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 93d824ec3120..1e5a50c11d3c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -72,7 +72,7 @@ struct llist_node *mce_gen_pool_prepare_records(void) return new_head.first; } -void mce_gen_pool_process(void) +void mce_gen_pool_process(struct work_struct *__unused) { struct llist_node *head; struct mce_evt_llist *node, *tmp; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 517619ea6498..99165b206df3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -152,7 +152,6 @@ static void raise_mce(struct mce *m) if (context == MCJ_CTX_RANDOM) return; -#ifdef CONFIG_X86_LOCAL_APIC if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) { unsigned long start; int cpu; @@ -192,9 +191,7 @@ static void raise_mce(struct mce *m) raise_local(); put_cpu(); put_online_cpus(); - } else -#endif - { + } else { preempt_disable(); raise_local(); preempt_enable(); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index cd74a3f00aea..903043e6a62b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -31,7 +31,7 @@ struct mce_evt_llist { struct mce mce; }; -void mce_gen_pool_process(void); +void mce_gen_pool_process(struct work_struct *__unused); bool mce_gen_pool_empty(void); int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 537c6647d84c..8e9725c607ea 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -128,7 +128,6 @@ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - m->tsc = rdtsc(); /* We hope get_seconds stays lockless */ m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; @@ -217,9 +216,7 @@ void mce_register_decode_chain(struct notifier_block *nb) { atomic_inc(&num_notifiers); - /* Ensure SRAO notifier has the highest priority in the decode chain. */ - if (nb != &mce_srao_nb && nb->priority == INT_MAX) - nb->priority -= 1; + WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC); atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); } @@ -583,7 +580,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, } static struct notifier_block mce_srao_nb = { .notifier_call = srao_decode_notifier, - .priority = INT_MAX, + .priority = MCE_PRIO_SRAO, }; static int mce_default_notifier(struct notifier_block *nb, unsigned long val, @@ -609,7 +606,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val, static struct notifier_block mce_default_nb = { .notifier_call = mce_default_notifier, /* lowest prio, we want it to run last. */ - .priority = 0, + .priority = MCE_PRIO_LOWEST, }; /* @@ -710,14 +707,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_gather_info(&m, NULL); - /* - * m.tsc was set in mce_setup(). Clear it if not requested. - * - * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid - * that dance. - */ - if (!(flags & MCP_TIMESTAMP)) - m.tsc = 0; + if (flags & MCP_TIMESTAMP) + m.tsc = rdtsc(); for (i = 0; i < mca_cfg.banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) @@ -1156,6 +1147,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) goto out; mce_gather_info(&m, regs); + m.tsc = rdtsc(); final = this_cpu_ptr(&mces_seen); *final = m; @@ -1322,41 +1314,6 @@ int memory_failure(unsigned long pfn, int vector, int flags) #endif /* - * Action optional processing happens here (picking up - * from the list of faulting pages that do_machine_check() - * placed into the genpool). - */ -static void mce_process_work(struct work_struct *dummy) -{ - mce_gen_pool_process(); -} - -#ifdef CONFIG_X86_MCE_INTEL -/*** - * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog - * @cpu: The CPU on which the event occurred. - * @status: Event status information - * - * This function should be called by the thermal interrupt after the - * event has been processed and the decision was made to log the event - * further. - * - * The status parameter will be saved to the 'status' field of 'struct mce' - * and historically has been the register value of the - * MSR_IA32_THERMAL_STATUS (Intel) msr. - */ -void mce_log_therm_throt_event(__u64 status) -{ - struct mce m; - - mce_setup(&m); - m.bank = MCE_THERMAL_BANK; - m.status = status; - mce_log(&m); -} -#endif /* CONFIG_X86_MCE_INTEL */ - -/* * Periodic polling timer for "silent" machine check errors. If the * poller finds an MCE, poll 2x faster. When the poller finds no more * errors, poll 2x slower (up to check_interval seconds). @@ -2189,7 +2146,7 @@ int __init mcheck_init(void) mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); - INIT_WORK(&mce_work, mce_process_work); + INIT_WORK(&mce_work, mce_gen_pool_process); init_irq_work(&mce_irq_work, mce_irq_work_cb); return 0; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index a5fd137417a2..9e5427df3243 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -192,6 +192,7 @@ static void get_smca_bank_info(unsigned int bank) smca_banks[bank].hwid = s_hwid; smca_banks[bank].id = instance_id; + smca_banks[bank].sysfs_id = s_hwid->count++; break; } } @@ -777,7 +778,8 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) mce_setup(&m); m.status = status; - m.bank = bank; + m.bank = bank; + m.tsc = rdtsc(); if (threshold_err) m.misc = misc; @@ -1064,9 +1066,12 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return NULL; } + if (smca_banks[bank].hwid->count == 1) + return smca_get_name(bank_type); + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "%s_%x", smca_get_name(bank_type), - smca_banks[bank].id); + smca_banks[bank].sysfs_id); return buf_mcatype; } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 465aca8be009..85469f84c921 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -6,7 +6,7 @@ * * Maintains a counter in /sys that keeps track of the number of thermal * events, such that the user knows how bad the thermal problem might be - * (since the logging to syslog and mcelog is rate limited). + * (since the logging to syslog is rate limited). * * Author: Dmitriy Zavin (dmitriyz@google.com) * @@ -141,13 +141,8 @@ static struct attribute_group thermal_attr_group = { * IRQ has been acknowledged. * * It will take care of rate limiting and printing messages to the syslog. - * - * Returns: 0 : Event should NOT be further logged, i.e. still in - * "timeout" from previous log message. - * 1 : Event should be logged further, and a message has been - * printed to the syslog. */ -static int therm_throt_process(bool new_event, int event, int level) +static void therm_throt_process(bool new_event, int event, int level) { struct _thermal_state *state; unsigned int this_cpu = smp_processor_id(); @@ -162,16 +157,16 @@ static int therm_throt_process(bool new_event, int event, int level) else if (event == POWER_LIMIT_EVENT) state = &pstate->core_power_limit; else - return 0; + return; } else if (level == PACKAGE_LEVEL) { if (event == THERMAL_THROTTLING_EVENT) state = &pstate->package_throttle; else if (event == POWER_LIMIT_EVENT) state = &pstate->package_power_limit; else - return 0; + return; } else - return 0; + return; old_event = state->new_event; state->new_event = new_event; @@ -181,7 +176,7 @@ static int therm_throt_process(bool new_event, int event, int level) if (time_before64(now, state->next_check) && state->count != state->last_count) - return 0; + return; state->next_check = now + CHECK_INTERVAL; state->last_count = state->count; @@ -193,16 +188,14 @@ static int therm_throt_process(bool new_event, int event, int level) this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); - return 1; + return; } if (old_event) { if (event == THERMAL_THROTTLING_EVENT) pr_info("CPU%d: %s temperature/speed normal\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package"); - return 1; + return; } - - return 0; } static int thresh_event_valid(int level, int event) @@ -365,10 +358,9 @@ static void intel_thermal_interrupt(void) /* Check for violation of core thermal thresholds*/ notify_thresholds(msr_val); - if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, - THERMAL_THROTTLING_EVENT, - CORE_LEVEL) != 0) - mce_log_therm_throt_event(msr_val); + therm_throt_process(msr_val & THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + CORE_LEVEL); if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 079e81733a58..7889ae492af0 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -42,16 +42,19 @@ static struct equiv_cpu_entry *equiv_cpu_table; /* * This points to the current valid container of microcode patches which we will - * save from the initrd/builtin before jettisoning its contents. + * save from the initrd/builtin before jettisoning its contents. @mc is the + * microcode patch we found to match. */ -struct container { - u8 *data; - size_t size; -} cont; +struct cont_desc { + struct microcode_amd *mc; + u32 cpuid_1_eax; + u32 psize; + u8 *data; + size_t size; +}; static u32 ucode_new_rev; static u8 amd_ucode_patch[PATCH_MAX_SIZE]; -static u16 this_equiv_id; /* * Microcode patch container file is prepended to the initrd in cpio @@ -60,57 +63,13 @@ static u16 this_equiv_id; static const char ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin"; -static size_t compute_container_size(u8 *data, u32 total_size) +static u16 find_equiv_id(struct equiv_cpu_entry *equiv_table, u32 sig) { - size_t size = 0; - u32 *header = (u32 *)data; - - if (header[0] != UCODE_MAGIC || - header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ - header[2] == 0) /* size */ - return size; - - size = header[2] + CONTAINER_HDR_SZ; - total_size -= size; - data += size; - - while (total_size) { - u16 patch_size; - - header = (u32 *)data; - - if (header[0] != UCODE_UCODE_TYPE) - break; - - /* - * Sanity-check patch size. - */ - patch_size = header[1]; - if (patch_size > PATCH_MAX_SIZE) - break; - - size += patch_size + SECTION_HDR_SIZE; - data += patch_size + SECTION_HDR_SIZE; - total_size -= patch_size + SECTION_HDR_SIZE; + for (; equiv_table && equiv_table->installed_cpu; equiv_table++) { + if (sig == equiv_table->installed_cpu) + return equiv_table->equiv_cpu; } - return size; -} - -static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, - unsigned int sig) -{ - int i = 0; - - if (!equiv_cpu_table) - return 0; - - while (equiv_cpu_table[i].installed_cpu != 0) { - if (sig == equiv_cpu_table[i].installed_cpu) - return equiv_cpu_table[i].equiv_cpu; - - i++; - } return 0; } @@ -118,91 +77,109 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, * This scans the ucode blob for the proper container as we can have multiple * containers glued together. Returns the equivalence ID from the equivalence * table or 0 if none found. + * Returns the amount of bytes consumed while scanning. @desc contains all the + * data we're going to use in later stages of the application. */ -static u16 -find_proper_container(u8 *ucode, size_t size, struct container *ret_cont) +static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc) { - struct container ret = { NULL, 0 }; - u32 eax, ebx, ecx, edx; struct equiv_cpu_entry *eq; - int offset, left; - u16 eq_id = 0; - u32 *header; - u8 *data; + ssize_t orig_size = size; + u32 *hdr = (u32 *)ucode; + u16 eq_id; + u8 *buf; - data = ucode; - left = size; - header = (u32 *)data; + /* Am I looking at an equivalence table header? */ + if (hdr[0] != UCODE_MAGIC || + hdr[1] != UCODE_EQUIV_CPU_TABLE_TYPE || + hdr[2] == 0) + return CONTAINER_HDR_SZ; + buf = ucode; - /* find equiv cpu table */ - if (header[0] != UCODE_MAGIC || - header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ - header[2] == 0) /* size */ - return eq_id; + eq = (struct equiv_cpu_entry *)(buf + CONTAINER_HDR_SZ); - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); + /* Find the equivalence ID of our CPU in this table: */ + eq_id = find_equiv_id(eq, desc->cpuid_1_eax); - while (left > 0) { - eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ); + buf += hdr[2] + CONTAINER_HDR_SZ; + size -= hdr[2] + CONTAINER_HDR_SZ; + + /* + * Scan through the rest of the container to find where it ends. We do + * some basic sanity-checking too. + */ + while (size > 0) { + struct microcode_amd *mc; + u32 patch_size; - ret.data = data; + hdr = (u32 *)buf; - /* Advance past the container header */ - offset = header[2] + CONTAINER_HDR_SZ; - data += offset; - left -= offset; + if (hdr[0] != UCODE_UCODE_TYPE) + break; - eq_id = find_equiv_id(eq, eax); - if (eq_id) { - ret.size = compute_container_size(ret.data, left + offset); + /* Sanity-check patch size. */ + patch_size = hdr[1]; + if (patch_size > PATCH_MAX_SIZE) + break; - /* - * truncate how much we need to iterate over in the - * ucode update loop below - */ - left = ret.size - offset; + /* Skip patch section header: */ + buf += SECTION_HDR_SIZE; + size -= SECTION_HDR_SIZE; - *ret_cont = ret; - return eq_id; + mc = (struct microcode_amd *)buf; + if (eq_id == mc->hdr.processor_rev_id) { + desc->psize = patch_size; + desc->mc = mc; } - /* - * support multiple container files appended together. if this - * one does not have a matching equivalent cpu entry, we fast - * forward to the next container file. - */ - while (left > 0) { - header = (u32 *)data; - - if (header[0] == UCODE_MAGIC && - header[1] == UCODE_EQUIV_CPU_TABLE_TYPE) - break; - - offset = header[1] + SECTION_HDR_SIZE; - data += offset; - left -= offset; - } + buf += patch_size; + size -= patch_size; + } - /* mark where the next microcode container file starts */ - offset = data - (u8 *)ucode; - ucode = data; + /* + * If we have found a patch (desc->mc), it means we're looking at the + * container which has a patch for this CPU so return 0 to mean, @ucode + * already points to the proper container. Otherwise, we return the size + * we scanned so that we can advance to the next container in the + * buffer. + */ + if (desc->mc) { + desc->data = ucode; + desc->size = orig_size - size; + + return 0; } - return eq_id; + return orig_size - size; } -static int __apply_microcode_amd(struct microcode_amd *mc_amd) +/* + * Scan the ucode blob for the proper container as we can have multiple + * containers glued together. + */ +static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc) +{ + ssize_t rem = size; + + while (rem >= 0) { + ssize_t s = parse_container(ucode, rem, desc); + if (!s) + return; + + ucode += s; + rem -= s; + } +} + +static int __apply_microcode_amd(struct microcode_amd *mc) { u32 rev, dummy; - native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code); + native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc->hdr.data_code); /* verify patch application was successful */ native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (rev != mc_amd->hdr.patch_id) + if (rev != mc->hdr.patch_id) return -1; return 0; @@ -217,17 +194,16 @@ static int __apply_microcode_amd(struct microcode_amd *mc_amd) * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. * - * Returns true if container found (sets @ret_cont), false otherwise. + * Returns true if container found (sets @desc), false otherwise. */ -static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch, - struct container *ret_cont) +static bool +apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch) { + struct cont_desc desc = { 0 }; u8 (*patch)[PATCH_MAX_SIZE]; - u32 rev, *header, *new_rev; - struct container ret; - int offset, left; - u16 eq_id = 0; - u8 *data; + struct microcode_amd *mc; + u32 rev, dummy, *new_rev; + bool ret = false; #ifdef CONFIG_X86_32 new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); @@ -237,50 +213,27 @@ static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch, patch = &amd_ucode_patch; #endif - if (check_current_patch_level(&rev, true)) - return false; - - eq_id = find_proper_container(ucode, size, &ret); - if (!eq_id) - return false; - - this_equiv_id = eq_id; - header = (u32 *)ret.data; - - /* We're pointing to an equiv table, skip over it. */ - data = ret.data + header[2] + CONTAINER_HDR_SZ; - left = ret.size - (header[2] + CONTAINER_HDR_SZ); - - while (left > 0) { - struct microcode_amd *mc; - - header = (u32 *)data; - if (header[0] != UCODE_UCODE_TYPE || /* type */ - header[1] == 0) /* size */ - break; + desc.cpuid_1_eax = cpuid_1_eax; - mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE); + scan_containers(ucode, size, &desc); - if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) { + mc = desc.mc; + if (!mc) + return ret; - if (!__apply_microcode_amd(mc)) { - rev = mc->hdr.patch_id; - *new_rev = rev; + native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + if (rev >= mc->hdr.patch_id) + return ret; - if (save_patch) - memcpy(patch, mc, min_t(u32, header[1], PATCH_MAX_SIZE)); - } - } + if (!__apply_microcode_amd(mc)) { + *new_rev = mc->hdr.patch_id; + ret = true; - offset = header[1] + SECTION_HDR_SIZE; - data += offset; - left -= offset; + if (save_patch) + memcpy(patch, mc, min_t(u32, desc.psize, PATCH_MAX_SIZE)); } - if (ret_cont) - *ret_cont = ret; - - return true; + return ret; } static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) @@ -298,10 +251,9 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) #endif } -void __init load_ucode_amd_bsp(unsigned int family) +void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) { struct ucode_cpu_info *uci; - u32 eax, ebx, ecx, edx; struct cpio_data cp; const char *path; bool use_pa; @@ -316,184 +268,95 @@ void __init load_ucode_amd_bsp(unsigned int family) use_pa = false; } - if (!get_builtin_microcode(&cp, family)) + if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax))) cp = find_microcode_in_initrd(path, use_pa); - if (!(cp.data && cp.size)) - return; - - /* Get BSP's CPUID.EAX(1), needed in load_microcode_amd() */ - eax = 1; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - uci->cpu_sig.sig = eax; + /* Needed in load_microcode_amd() */ + uci->cpu_sig.sig = cpuid_1_eax; - apply_microcode_early_amd(cp.data, cp.size, true, NULL); + *ret = cp; } -#ifdef CONFIG_X86_32 -/* - * On 32-bit, since AP's early load occurs before paging is turned on, we - * cannot traverse cpu_equiv_table and microcode_cache in kernel heap memory. - * So during cold boot, AP will apply_ucode_in_initrd() just like the BSP. - * In save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch, - * which is used upon resume from suspend. - */ -void load_ucode_amd_ap(unsigned int family) +void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax) { - struct microcode_amd *mc; - struct cpio_data cp; - - mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); - if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { - __apply_microcode_amd(mc); - return; - } - - if (!get_builtin_microcode(&cp, family)) - cp = find_microcode_in_initrd((const char *)__pa_nodebug(ucode_path), true); + struct cpio_data cp = { }; + __load_ucode_amd(cpuid_1_eax, &cp); if (!(cp.data && cp.size)) return; - /* - * This would set amd_ucode_patch above so that the following APs can - * use it directly instead of going down this path again. - */ - apply_microcode_early_amd(cp.data, cp.size, true, NULL); + apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, true); } -#else -void load_ucode_amd_ap(unsigned int family) + +void load_ucode_amd_ap(unsigned int cpuid_1_eax) { - struct equiv_cpu_entry *eq; struct microcode_amd *mc; - u32 rev, eax; - u16 eq_id; - - /* 64-bit runs with paging enabled, thus early==false. */ - if (check_current_patch_level(&rev, false)) - return; - - /* First AP hasn't cached it yet, go through the blob. */ - if (!cont.data) { - struct cpio_data cp = { NULL, 0, "" }; + struct cpio_data cp; + u32 *new_rev, rev, dummy; - if (cont.size == -1) - return; + if (IS_ENABLED(CONFIG_X86_32)) { + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); + new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); + } else { + mc = (struct microcode_amd *)amd_ucode_patch; + new_rev = &ucode_new_rev; + } -reget: - if (!get_builtin_microcode(&cp, family)) { -#ifdef CONFIG_BLK_DEV_INITRD - if (!initrd_gone) - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); -#endif - if (!(cp.data && cp.size)) { - /* - * Mark it so that other APs do not scan again - * for no real reason and slow down boot - * needlessly. - */ - cont.size = -1; - return; - } - } + native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (!apply_microcode_early_amd(cp.data, cp.size, false, &cont)) { - cont.size = -1; + /* Check whether we have saved a new patch already: */ + if (*new_rev && rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) { + *new_rev = mc->hdr.patch_id; return; } } - eax = cpuid_eax(0x00000001); - eq = (struct equiv_cpu_entry *)(cont.data + CONTAINER_HDR_SZ); - - eq_id = find_equiv_id(eq, eax); - if (!eq_id) + __load_ucode_amd(cpuid_1_eax, &cp); + if (!(cp.data && cp.size)) return; - if (eq_id == this_equiv_id) { - mc = (struct microcode_amd *)amd_ucode_patch; - - if (mc && rev < mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc)) - ucode_new_rev = mc->hdr.patch_id; - } - - } else { - - /* - * AP has a different equivalence ID than BSP, looks like - * mixed-steppings silicon so go through the ucode blob anew. - */ - goto reget; - } + apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, false); } -#endif /* CONFIG_X86_32 */ static enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size); -int __init save_microcode_in_initrd_amd(unsigned int fam) +int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) { + struct cont_desc desc = { 0 }; enum ucode_state ret; - int retval = 0; - u16 eq_id; - - if (!cont.data) { - if (IS_ENABLED(CONFIG_X86_32) && (cont.size != -1)) { - struct cpio_data cp = { NULL, 0, "" }; - -#ifdef CONFIG_BLK_DEV_INITRD - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); -#endif + struct cpio_data cp; - if (!(cp.data && cp.size)) { - cont.size = -1; - return -EINVAL; - } + cp = find_microcode_in_initrd(ucode_path, false); + if (!(cp.data && cp.size)) + return -EINVAL; - eq_id = find_proper_container(cp.data, cp.size, &cont); - if (!eq_id) { - cont.size = -1; - return -EINVAL; - } + desc.cpuid_1_eax = cpuid_1_eax; - } else - return -EINVAL; - } + scan_containers(cp.data, cp.size, &desc); + if (!desc.mc) + return -EINVAL; - ret = load_microcode_amd(smp_processor_id(), fam, cont.data, cont.size); + ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax), + desc.data, desc.size); if (ret != UCODE_OK) - retval = -EINVAL; - - /* - * This will be freed any msec now, stash patches for the current - * family and switch to patch cache for cpu hotplug, etc later. - */ - cont.data = NULL; - cont.size = 0; + return -EINVAL; - return retval; + return 0; } void reload_ucode_amd(void) { struct microcode_amd *mc; - u32 rev; - - /* - * early==false because this is a syscore ->resume path and by - * that time paging is long enabled. - */ - if (check_current_patch_level(&rev, false)) - return; + u32 rev, dummy; mc = (struct microcode_amd *)amd_ucode_patch; if (!mc) return; + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + if (rev < mc->hdr.patch_id) { if (!__apply_microcode_amd(mc)) { ucode_new_rev = mc->hdr.patch_id; @@ -631,60 +494,13 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, return patch_size; } -/* - * Those patch levels cannot be updated to newer ones and thus should be final. - */ -static u32 final_levels[] = { - 0x01000098, - 0x0100009f, - 0x010000af, - 0, /* T-101 terminator */ -}; - -/* - * Check the current patch level on this CPU. - * - * @rev: Use it to return the patch level. It is set to 0 in the case of - * error. - * - * Returns: - * - true: if update should stop - * - false: otherwise - */ -bool check_current_patch_level(u32 *rev, bool early) -{ - u32 lvl, dummy, i; - bool ret = false; - u32 *levels; - - native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); - - if (IS_ENABLED(CONFIG_X86_32) && early) - levels = (u32 *)__pa_nodebug(&final_levels); - else - levels = final_levels; - - for (i = 0; levels[i]; i++) { - if (lvl == levels[i]) { - lvl = 0; - ret = true; - break; - } - } - - if (rev) - *rev = lvl; - - return ret; -} - static int apply_microcode_amd(int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; - u32 rev; + u32 rev, dummy; BUG_ON(raw_smp_processor_id() != cpu); @@ -697,8 +513,7 @@ static int apply_microcode_amd(int cpu) mc_amd = p->data; uci->mc = p->data; - if (check_current_patch_level(&rev, false)) - return -1; + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 73102d932760..b4a4cd39b358 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -66,19 +66,50 @@ static DEFINE_MUTEX(microcode_mutex); struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; -/* - * Operations that are run on a target cpu: - */ - struct cpu_info_ctx { struct cpu_signature *cpu_sig; int err; }; +/* + * Those patch levels cannot be updated to newer ones and thus should be final. + */ +static u32 final_levels[] = { + 0x01000098, + 0x0100009f, + 0x010000af, + 0, /* T-101 terminator */ +}; + +/* + * Check the current patch level on this CPU. + * + * Returns: + * - true: if update should stop + * - false: otherwise + */ +static bool amd_check_current_patch_level(void) +{ + u32 lvl, dummy, i; + u32 *levels; + + native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); + + if (IS_ENABLED(CONFIG_X86_32)) + levels = (u32 *)__pa_nodebug(&final_levels); + else + levels = final_levels; + + for (i = 0; levels[i]; i++) { + if (lvl == levels[i]) + return true; + } + return false; +} + static bool __init check_loader_disabled_bsp(void) { static const char *__dis_opt_str = "dis_ucode_ldr"; - u32 a, b, c, d; #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); @@ -94,18 +125,19 @@ static bool __init check_loader_disabled_bsp(void) if (!have_cpuid_p()) return *res; - a = 1; - c = 0; - native_cpuid(&a, &b, &c, &d); - /* * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not * completely accurate as xen pv guests don't see that CPUID bit set but * that's good enough as they don't land on the BSP path anyway. */ - if (c & BIT(31)) + if (native_cpuid_ecx(1) & BIT(31)) return *res; + if (x86_cpuid_vendor() == X86_VENDOR_AMD) { + if (amd_check_current_patch_level()) + return *res; + } + if (cmdline_find_option_bool(cmdline, option) <= 0) *res = false; @@ -133,23 +165,21 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name) void __init load_ucode_bsp(void) { - int vendor; - unsigned int family; + unsigned int cpuid_1_eax; if (check_loader_disabled_bsp()) return; - vendor = x86_cpuid_vendor(); - family = x86_cpuid_family(); + cpuid_1_eax = native_cpuid_eax(1); - switch (vendor) { + switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (family >= 6) + if (x86_family(cpuid_1_eax) >= 6) load_ucode_intel_bsp(); break; case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(family); + if (x86_family(cpuid_1_eax) >= 0x10) + load_ucode_amd_bsp(cpuid_1_eax); break; default: break; @@ -167,22 +197,21 @@ static bool check_loader_disabled_ap(void) void load_ucode_ap(void) { - int vendor, family; + unsigned int cpuid_1_eax; if (check_loader_disabled_ap()) return; - vendor = x86_cpuid_vendor(); - family = x86_cpuid_family(); + cpuid_1_eax = native_cpuid_eax(1); - switch (vendor) { + switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (family >= 6) + if (x86_family(cpuid_1_eax) >= 6) load_ucode_intel_ap(); break; case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_ap(family); + if (x86_family(cpuid_1_eax) >= 0x10) + load_ucode_amd_ap(cpuid_1_eax); break; default: break; @@ -201,7 +230,7 @@ static int __init save_microcode_in_initrd(void) break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - ret = save_microcode_in_initrd_amd(c->x86); + return save_microcode_in_initrd_amd(cpuid_eax(1)); break; default: break; diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 34178564be2a..c1ea5b999839 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,4 +1,5 @@ #include <linux/kernel.h> +#include <linux/sched.h> #include <linux/mm.h> #include <asm/cpufeature.h> #include <asm/msr.h> @@ -14,6 +15,8 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) if (xlvl >= 0x80860001) c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } + + clear_sched_clock_stable(); } static void init_transmeta(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 90e8dde3ec26..b2bbad6ebe4d 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -580,24 +580,19 @@ static void __init update_e820_saved(void) } #define MAX_GAP_END 0x100000000ull /* - * Search for a gap in the e820 memory space from start_addr to end_addr. + * Search for a gap in the e820 memory space from 0 to MAX_GAP_END. */ -__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, - unsigned long start_addr, unsigned long long end_addr) +static int __init e820_search_gap(unsigned long *gapstart, + unsigned long *gapsize) { - unsigned long long last; + unsigned long long last = MAX_GAP_END; int i = e820->nr_map; int found = 0; - last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END; - while (--i >= 0) { unsigned long long start = e820->map[i].addr; unsigned long long end = start + e820->map[i].size; - if (end < start_addr) - continue; - /* * Since "last" is at most 4GB, we know we'll * fit in 32 bits if this condition is true @@ -628,18 +623,19 @@ __init void e820_setup_gap(void) unsigned long gapstart, gapsize; int found; - gapstart = 0x10000000; gapsize = 0x400000; - found = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END); + found = e820_search_gap(&gapstart, &gapsize); -#ifdef CONFIG_X86_64 if (!found) { +#ifdef CONFIG_X86_64 gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024; printk(KERN_ERR "e820: cannot find a gap in the 32bit address range\n" "e820: PCI devices with unassigned 32bit BARs may break!\n"); - } +#else + gapstart = 0x10000000; #endif + } /* * e820_reserve_resources_late protect stolen RAM already diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index de7234401275..e1114f070c2d 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -9,7 +9,6 @@ #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> -#include <asm/fpu/xstate.h> #include <asm/traps.h> #include <linux/hardirq.h> @@ -179,14 +178,8 @@ void fpstate_init(union fpregs_state *state) memset(state, 0, fpu_kernel_xstate_size); - /* - * XRSTORS requires that this bit is set in xcomp_bv, or - * it will #GP. Make sure it is replaced after the memset(). - */ if (static_cpu_has(X86_FEATURE_XSAVES)) - state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | - xfeatures_mask; - + fpstate_init_xstate(&state->xsave); if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 60dece392b3a..19bdd1bf8160 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -48,13 +48,7 @@ void fpu__init_cpu(void) fpu__init_cpu_xstate(); } -/* - * The earliest FPU detection code. - * - * Set the X86_FEATURE_FPU CPU-capability bit based on - * trying to execute an actual sequence of FPU instructions: - */ -static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +static bool fpu__probe_without_cpuid(void) { unsigned long cr0; u16 fsw, fcw; @@ -65,18 +59,25 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) cr0 &= ~(X86_CR0_TS | X86_CR0_EM); write_cr0(cr0); - if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" : "+m" (fsw), "+m" (fcw)); + + pr_info("x86/fpu: Probing for FPU: FSW=0x%04hx FCW=0x%04hx\n", fsw, fcw); - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); + return fsw == 0 && (fcw & 0x103f) == 0x003f; +} + +static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +{ + if (!boot_cpu_has(X86_FEATURE_CPUID) && + !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { + if (fpu__probe_without_cpuid()) + setup_force_cpu_cap(X86_FEATURE_FPU); else - clear_cpu_cap(c, X86_FEATURE_FPU); + setup_clear_cpu_cap(X86_FEATURE_FPU); } #ifndef CONFIG_MATH_EMULATION - if (!boot_cpu_has(X86_FEATURE_FPU)) { + if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_FPU)) { pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n"); for (;;) asm volatile("hlt"); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 1d7770447b3e..c24ac1efb12d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -78,6 +78,7 @@ void fpu__xstate_clear_all_cpu_caps(void) setup_clear_cpu_cap(X86_FEATURE_PKU); setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW); setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS); + setup_clear_cpu_cap(X86_FEATURE_AVX512_VPOPCNTDQ); } /* @@ -705,8 +706,14 @@ void __init fpu__init_system_xstate(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; + if (!boot_cpu_has(X86_FEATURE_FPU)) { + pr_info("x86/fpu: No FPU detected\n"); + return; + } + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { - pr_info("x86/fpu: Legacy x87 FPU detected.\n"); + pr_info("x86/fpu: x87 FPU will use %s\n", + boot_cpu_has(X86_FEATURE_FXSR) ? "FXSAVE" : "FSAVE"); return; } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index f16c55bfc090..e5fb436a6548 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -49,3 +49,65 @@ asmlinkage __visible void __init i386_start_kernel(void) start_kernel(); } + +/* + * Initialize page tables. This creates a PDE and a set of page + * tables, which are located immediately beyond __brk_base. The variable + * _brk_end is set up to point to the first "safe" location. + * Mappings are created both at virtual address 0 (identity mapping) + * and PAGE_OFFSET for up to _end. + * + * In PAE mode initial_page_table is statically defined to contain + * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3 + * entries). The identity mapping is handled by pointing two PGD entries + * to the first kernel PMD. Note the upper half of each PMD or PTE are + * always zero at this stage. + */ +void __init mk_early_pgtbl_32(void) +{ +#ifdef __pa +#undef __pa +#endif +#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET) + pte_t pte, *ptep; + int i; + unsigned long *ptr; + /* Enough space to fit pagetables for the low memory linear map */ + const unsigned long limit = __pa(_end) + + (PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT); +#ifdef CONFIG_X86_PAE + pmd_t pl2, *pl2p = (pmd_t *)__pa(initial_pg_pmd); +#define SET_PL2(pl2, val) { (pl2).pmd = (val); } +#else + pgd_t pl2, *pl2p = (pgd_t *)__pa(initial_page_table); +#define SET_PL2(pl2, val) { (pl2).pgd = (val); } +#endif + + ptep = (pte_t *)__pa(__brk_base); + pte.pte = PTE_IDENT_ATTR; + + while ((pte.pte & PTE_PFN_MASK) < limit) { + + SET_PL2(pl2, (unsigned long)ptep | PDE_IDENT_ATTR); + *pl2p = pl2; +#ifndef CONFIG_X86_PAE + /* Kernel PDE entry */ + *(pl2p + ((PAGE_OFFSET >> PGDIR_SHIFT))) = pl2; +#endif + for (i = 0; i < PTRS_PER_PTE; i++) { + *ptep = pte; + pte.pte += PAGE_SIZE; + ptep++; + } + + pl2p++; + } + + ptr = (unsigned long *)__pa(&max_pfn_mapped); + /* Can't use pte_pfn() since it's a call with CONFIG_PARAVIRT */ + *ptr = (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT; + + ptr = (unsigned long *)__pa(&_brk_end); + *ptr = (unsigned long)ptep + PAGE_OFFSET; +} + diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 4e8577d03372..1f85ee8f9439 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -24,6 +24,7 @@ #include <asm/nops.h> #include <asm/bootparam.h> #include <asm/export.h> +#include <asm/pgtable_32.h> /* Physical address */ #define pa(X) ((X) - __PAGE_OFFSET) @@ -41,44 +42,10 @@ #define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability #define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id -/* - * This is how much memory in addition to the memory covered up to - * and including _end we need mapped initially. - * We need: - * (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE) - * (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE) - * - * Modulo rounding, each megabyte assigned here requires a kilobyte of - * memory, which is currently unreclaimed. - * - * This should be a multiple of a page. - * - * KERNEL_IMAGE_SIZE should be greater than pa(_end) - * and small than max_low_pfn, otherwise will waste some page table entries - */ - -#if PTRS_PER_PMD > 1 -#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD) -#else -#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) -#endif #define SIZEOF_PTREGS 17*4 /* - * Number of possible pages in the lowmem region. - * - * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a - * gas warning about overflowing shift count when gas has been compiled - * with only a host target support using a 32-bit type for internal - * representation. - */ -LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT) - -/* Enough space to fit pagetables for the low memory linear map */ -MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT - -/* * Worst-case size of the kernel mapping we need to make: * a relocatable kernel can live anywhere in lowmem, so we need to be able * to map all of lowmem. @@ -160,90 +127,15 @@ ENTRY(startup_32) call load_ucode_bsp #endif -/* - * Initialize page tables. This creates a PDE and a set of page - * tables, which are located immediately beyond __brk_base. The variable - * _brk_end is set up to point to the first "safe" location. - * Mappings are created both at virtual address 0 (identity mapping) - * and PAGE_OFFSET for up to _end. - */ -#ifdef CONFIG_X86_PAE - - /* - * In PAE mode initial_page_table is statically defined to contain - * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3 - * entries). The identity mapping is handled by pointing two PGD entries - * to the first kernel PMD. - * - * Note the upper half of each PMD or PTE are always zero at this stage. - */ - -#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */ - - xorl %ebx,%ebx /* %ebx is kept at zero */ - - movl $pa(__brk_base), %edi - movl $pa(initial_pg_pmd), %edx - movl $PTE_IDENT_ATTR, %eax -10: - leal PDE_IDENT_ATTR(%edi),%ecx /* Create PMD entry */ - movl %ecx,(%edx) /* Store PMD entry */ - /* Upper half already zero */ - addl $8,%edx - movl $512,%ecx -11: - stosl - xchgl %eax,%ebx - stosl - xchgl %eax,%ebx - addl $0x1000,%eax - loop 11b - - /* - * End condition: we must map up to the end + MAPPING_BEYOND_END. - */ - movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp - cmpl %ebp,%eax - jb 10b -1: - addl $__PAGE_OFFSET, %edi - movl %edi, pa(_brk_end) - shrl $12, %eax - movl %eax, pa(max_pfn_mapped) + /* Create early pagetables. */ + call mk_early_pgtbl_32 /* Do early initialization of the fixmap area */ movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax +#ifdef CONFIG_X86_PAE +#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */ movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8) -#else /* Not PAE */ - -page_pde_offset = (__PAGE_OFFSET >> 20); - - movl $pa(__brk_base), %edi - movl $pa(initial_page_table), %edx - movl $PTE_IDENT_ATTR, %eax -10: - leal PDE_IDENT_ATTR(%edi),%ecx /* Create PDE entry */ - movl %ecx,(%edx) /* Store identity PDE entry */ - movl %ecx,page_pde_offset(%edx) /* Store kernel PDE entry */ - addl $4,%edx - movl $1024, %ecx -11: - stosl - addl $0x1000,%eax - loop 11b - /* - * End condition: we must map up to the end + MAPPING_BEYOND_END. - */ - movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp - cmpl %ebp,%eax - jb 10b - addl $__PAGE_OFFSET, %edi - movl %edi, pa(_brk_end) - shrl $12, %eax - movl %eax, pa(max_pfn_mapped) - - /* Do early initialization of the fixmap area */ - movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax +#else movl %eax,pa(initial_page_table+0xffc) #endif @@ -666,6 +558,7 @@ ENTRY(setup_once_ref) __PAGE_ALIGNED_BSS .align PAGE_SIZE #ifdef CONFIG_X86_PAE +.globl initial_pg_pmd initial_pg_pmd: .fill 1024*KPMDS,4,0 #else diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index cb9c1ed1d391..f73f475d0573 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -132,10 +132,8 @@ int sched_set_itmt_support(void) sysctl_sched_itmt_enabled = 1; - if (sysctl_sched_itmt_enabled) { - x86_topology_update = true; - rebuild_sched_domains(); - } + x86_topology_update = true; + rebuild_sched_domains(); mutex_unlock(&itmt_update_mutex); diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index fc25f698d792..c37bd0f39c70 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -32,8 +32,7 @@ static void bug_at(unsigned char *ip, int line) * Something went wrong. Crash the box, as something could be * corrupting the kernel. */ - pr_warning("Unexpected op at %pS [%p] (%02x %02x %02x %02x %02x) %s:%d\n", - ip, ip, ip[0], ip[1], ip[2], ip[3], ip[4], __FILE__, line); + pr_crit("jump_label: Fatal kernel bug, unexpected op at %pS [%p] (%5ph) %d\n", ip, ip, ip, line); BUG(); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index eb3509338ae0..520b8dfe1640 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -745,7 +745,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) * will be the real return address, and all the rest will * point to kretprobe_trampoline. */ - hlist_for_each_entry_safe(ri, tmp, head, hlist) { + hlist_for_each_entry(ri, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 36bc66416021..099fcba4981d 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -620,18 +620,4 @@ void __init kvm_spinlock_init(void) } } -static __init int kvm_spinlock_init_jump(void) -{ - if (!kvm_para_available()) - return 0; - if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) - return 0; - - static_key_slow_inc(¶virt_ticketlocks_enabled); - printk(KERN_INFO "KVM setup paravirtual spinlock\n"); - - return 0; -} -early_initcall(kvm_spinlock_init_jump); - #endif /* CONFIG_PARAVIRT_SPINLOCKS */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2a5cafdf8808..542710b99f52 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -107,12 +107,12 @@ static inline void kvm_sched_clock_init(bool stable) { if (!stable) { pv_time_ops.sched_clock = kvm_clock_read; + clear_sched_clock_stable(); return; } kvm_sched_clock_offset = kvm_clock_read(); pv_time_ops.sched_clock = kvm_sched_clock_read; - set_sched_clock_stable(); printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n", kvm_sched_clock_offset); diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 6d4bf812af45..6259327f3454 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -42,6 +42,3 @@ struct pv_lock_ops pv_lock_ops = { #endif /* SMP */ }; EXPORT_SYMBOL(pv_lock_ops); - -struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE; -EXPORT_SYMBOL(paravirt_ticketlocks_enabled); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 5d400ba1349d..d47517941bbc 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -296,7 +296,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, /* were we called with bad_dma_address? */ badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE); - if (unlikely((dma_addr >= DMA_ERROR_CODE) && (dma_addr < badend))) { + if (unlikely(dma_addr < badend)) { WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA " "address 0x%Lx\n", dma_addr); return; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4cfba947d774..69780edf0dde 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1176,6 +1176,20 @@ void __init setup_arch(char **cmdline_p) /* Allocate bigger log buffer */ setup_log_buf(1); + if (efi_enabled(EFI_BOOT)) { + switch (boot_params.secure_boot) { + case efi_secureboot_mode_disabled: + pr_info("Secure boot disabled\n"); + break; + case efi_secureboot_mode_enabled: + pr_info("Secure boot enabled\n"); + break; + default: + pr_info("Secure boot could not be determined\n"); + break; + } + } + reserve_initrd(); acpi_table_upgrade(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index bf0c6d049080..1dc86ee60a03 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -563,11 +563,9 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) * as we may switch to the interrupt stack. */ debug_stack_usage_inc(); - preempt_disable(); cond_local_irq_enable(regs); do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); cond_local_irq_disable(regs); - preempt_enable_no_resched(); debug_stack_usage_dec(); exit: ist_exit(regs); @@ -742,14 +740,12 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_inc(); /* It's safe to allow irq's after DR6 has been saved */ - preempt_disable(); cond_local_irq_enable(regs); if (v8086_mode(regs)) { handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, X86_TRAP_DB); cond_local_irq_disable(regs); - preempt_enable_no_resched(); debug_stack_usage_dec(); goto exit; } @@ -769,7 +765,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); cond_local_irq_disable(regs); - preempt_enable_no_resched(); debug_stack_usage_dec(); exit: diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 37e7cf544e51..2724dc82f992 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1107,6 +1107,16 @@ static u64 read_tsc(struct clocksource *cs) return (u64)rdtsc_ordered(); } +static void tsc_cs_mark_unstable(struct clocksource *cs) +{ + if (tsc_unstable) + return; + tsc_unstable = 1; + clear_sched_clock_stable(); + disable_sched_clock_irqtime(); + pr_info("Marking TSC unstable due to clocksource watchdog\n"); +} + /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ @@ -1119,6 +1129,7 @@ static struct clocksource clocksource_tsc = { CLOCK_SOURCE_MUST_VERIFY, .archdata = { .vclock_mode = VCLOCK_TSC }, .resume = tsc_resume, + .mark_unstable = tsc_cs_mark_unstable, }; void mark_tsc_unstable(char *reason) diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index ec5d7545e6dc..0442d98367ae 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -160,11 +160,12 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) static void mark_screen_rdonly(struct mm_struct *mm) { + struct vm_area_struct *vma; + spinlock_t *ptl; pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - spinlock_t *ptl; int i; down_write(&mm->mmap_sem); @@ -177,7 +178,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pmd = pmd_offset(pud, 0xA0000); if (pmd_trans_huge(*pmd)) { - struct vm_area_struct *vma = find_vma(mm, 0xA0000); + vma = find_vma(mm, 0xA0000); split_huge_pmd(vma, pmd, 0xA0000); } if (pmd_none_or_clear_bad(pmd)) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 1572c35b4f1a..2ecd7dab4631 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -964,10 +964,11 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, /* Calculate cpu time spent by current task in 100ns units */ static u64 current_task_runtime_100ns(void) { - cputime_t utime, stime; + u64 utime, stime; task_cputime_adjusted(current, &utime, &stime); - return div_u64(cputime_to_nsecs(utime + stime), 100); + + return div_u64(utime + stime, 100); } static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 073d1f1a620b..a8e91ae89fb3 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -156,13 +156,13 @@ EXPORT_SYMBOL(__delay); inline void __const_udelay(unsigned long xloops) { + unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy; int d0; xloops *= 4; asm("mull %%edx" :"=d" (xloops), "=&a" (d0) - :"1" (xloops), "0" - (this_cpu_read(cpu_info.loops_per_jiffy) * (HZ/4))); + :"1" (xloops), "0" (lpj * (HZ / 4))); __delay(++xloops); } diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index 6aad870e8962..04ca8764f0c0 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -19,8 +19,7 @@ #include <linux/efi.h> #include <linux/efi-bgrt.h> -struct acpi_table_bgrt *bgrt_tab; -void *__initdata bgrt_image; +struct acpi_table_bgrt bgrt_tab; size_t __initdata bgrt_image_size; struct bmp_header { @@ -28,66 +27,58 @@ struct bmp_header { u32 size; } __packed; -void __init efi_bgrt_init(void) +void __init efi_bgrt_init(struct acpi_table_header *table) { - acpi_status status; void *image; struct bmp_header bmp_header; + struct acpi_table_bgrt *bgrt = &bgrt_tab; if (acpi_disabled) return; - status = acpi_get_table("BGRT", 0, - (struct acpi_table_header **)&bgrt_tab); - if (ACPI_FAILURE(status)) - return; - - if (bgrt_tab->header.length < sizeof(*bgrt_tab)) { + if (table->length < sizeof(bgrt_tab)) { pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n", - bgrt_tab->header.length, sizeof(*bgrt_tab)); + table->length, sizeof(bgrt_tab)); return; } - if (bgrt_tab->version != 1) { + *bgrt = *(struct acpi_table_bgrt *)table; + if (bgrt->version != 1) { pr_notice("Ignoring BGRT: invalid version %u (expected 1)\n", - bgrt_tab->version); - return; + bgrt->version); + goto out; } - if (bgrt_tab->status & 0xfe) { + if (bgrt->status & 0xfe) { pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n", - bgrt_tab->status); - return; + bgrt->status); + goto out; } - if (bgrt_tab->image_type != 0) { + if (bgrt->image_type != 0) { pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n", - bgrt_tab->image_type); - return; + bgrt->image_type); + goto out; } - if (!bgrt_tab->image_address) { + if (!bgrt->image_address) { pr_notice("Ignoring BGRT: null image address\n"); - return; + goto out; } - image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB); + image = early_memremap(bgrt->image_address, sizeof(bmp_header)); if (!image) { pr_notice("Ignoring BGRT: failed to map image header memory\n"); - return; + goto out; } memcpy(&bmp_header, image, sizeof(bmp_header)); - memunmap(image); + early_memunmap(image, sizeof(bmp_header)); if (bmp_header.id != 0x4d42) { pr_notice("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n", bmp_header.id); - return; + goto out; } bgrt_image_size = bmp_header.size; + efi_mem_reserve(bgrt->image_address, bgrt_image_size); - bgrt_image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB); - if (!bgrt_image) { - pr_notice("Ignoring BGRT: failed to map image memory\n"); - bgrt_image = NULL; - return; - } - - efi_mem_reserve(bgrt_tab->image_address, bgrt_image_size); + return; +out: + memset(bgrt, 0, sizeof(bgrt_tab)); } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 274dfc481849..565dff3c9a12 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -542,11 +542,6 @@ void __init efi_init(void) efi_print_memmap(); } -void __init efi_late_init(void) -{ - efi_bgrt_init(); -} - void __init efi_set_executable(efi_memory_desc_t *md, bool executable) { u64 addr, npages; @@ -960,6 +955,11 @@ static void __init __efi_enter_virtual_mode(void) return; } + if (efi_enabled(EFI_DBG)) { + pr_info("EFI runtime memory map:\n"); + efi_print_memmap(); + } + BUG_ON(!efi.systab); if (efi_setup_page_tables(pa, 1 << pg_shift)) { diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 2f25a363068c..a4695da42d77 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -414,10 +414,44 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len) efi_setup = phys_addr + sizeof(struct setup_data); } -void __init efi_runtime_update_mappings(void) +static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf) { unsigned long pfn; pgd_t *pgd = efi_pgd; + int err1, err2; + + /* Update the 1:1 mapping */ + pfn = md->phys_addr >> PAGE_SHIFT; + err1 = kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf); + if (err1) { + pr_err("Error while updating 1:1 mapping PA 0x%llx -> VA 0x%llx!\n", + md->phys_addr, md->virt_addr); + } + + err2 = kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf); + if (err2) { + pr_err("Error while updating VA mapping PA 0x%llx -> VA 0x%llx!\n", + md->phys_addr, md->virt_addr); + } + + return err1 || err2; +} + +static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md) +{ + unsigned long pf = 0; + + if (md->attribute & EFI_MEMORY_XP) + pf |= _PAGE_NX; + + if (!(md->attribute & EFI_MEMORY_RO)) + pf |= _PAGE_RW; + + return efi_update_mappings(md, pf); +} + +void __init efi_runtime_update_mappings(void) +{ efi_memory_desc_t *md; if (efi_enabled(EFI_OLD_MEMMAP)) { @@ -426,6 +460,24 @@ void __init efi_runtime_update_mappings(void) return; } + /* + * Use the EFI Memory Attribute Table for mapping permissions if it + * exists, since it is intended to supersede EFI_PROPERTIES_TABLE. + */ + if (efi_enabled(EFI_MEM_ATTR)) { + efi_memattr_apply_permissions(NULL, efi_update_mem_attr); + return; + } + + /* + * EFI_MEMORY_ATTRIBUTES_TABLE is intended to replace + * EFI_PROPERTIES_TABLE. So, use EFI_PROPERTIES_TABLE to update + * permissions only if EFI_MEMORY_ATTRIBUTES_TABLE is not + * published by the firmware. Even if we find a buggy implementation of + * EFI_MEMORY_ATTRIBUTES_TABLE, don't fall back to + * EFI_PROPERTIES_TABLE, because of the same reason. + */ + if (!efi_enabled(EFI_NX_PE_DATA)) return; @@ -446,15 +498,7 @@ void __init efi_runtime_update_mappings(void) (md->type != EFI_RUNTIME_SERVICES_CODE)) pf |= _PAGE_RW; - /* Update the 1:1 mapping */ - pfn = md->phys_addr >> PAGE_SHIFT; - if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf)) - pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", - md->phys_addr, md->virt_addr); - - if (kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf)) - pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", - md->phys_addr, md->virt_addr); + efi_update_mappings(md, pf); } } diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig index d957d5f21a86..0bc60a308730 100644 --- a/arch/x86/ras/Kconfig +++ b/arch/x86/ras/Kconfig @@ -1,6 +1,6 @@ config MCE_AMD_INJ tristate "Simple MCE injection interface for AMD processors" - depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB + depends on RAS && X86_MCE && DEBUG_FS && AMD_NB default n help This is a simple debugfs interface to inject MCEs and test different diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index e8a9ea7d7a21..25a7c4302ce7 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -141,25 +141,6 @@ void __init xen_init_spinlocks(void) pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen); } -/* - * While the jump_label init code needs to happend _after_ the jump labels are - * enabled and before SMP is started. Hence we use pre-SMP initcall level - * init. We cannot do it in xen_init_spinlocks as that is done before - * jump labels are activated. - */ -static __init int xen_init_spinlocks_jump(void) -{ - if (!xen_pvspin) - return 0; - - if (!xen_domain()) - return 0; - - static_key_slow_inc(¶virt_ticketlocks_enabled); - return 0; -} -early_initcall(xen_init_spinlocks_jump); - static __init int xen_parse_nopvspin(char *arg) { xen_pvspin = false; diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index b7fbaa56b51a..9e9760b20be5 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += bitsperlong.h generic-y += bug.h generic-y += clkdev.h -generic-y += cputime.h generic-y += div64.h generic-y += dma-contiguous.h generic-y += emergency-restart.h diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index c73a6fcaeb9d..838f07e2b64a 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3758,7 +3758,7 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq, } #ifdef CONFIG_CFQ_GROUP_IOSCHED -static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) +static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { struct cfq_data *cfqd = cic_to_cfqd(cic); struct cfq_queue *cfqq; @@ -3775,15 +3775,7 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) * spuriously on a newly created cic but there's no harm. */ if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr)) - return; - - /* - * If we have a non-root cgroup, we can depend on that to - * do proper throttling of writes. Turn off wbt for that - * case, if it was enabled by default. - */ - if (nonroot_cg) - wbt_disable_default(cfqd->queue); + return nonroot_cg; /* * Drop reference to queues. New queues will be assigned in new @@ -3804,9 +3796,13 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) } cic->blkcg_serial_nr = serial_nr; + return nonroot_cg; } #else -static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { } +static inline bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) +{ + return false; +} #endif /* CONFIG_CFQ_GROUP_IOSCHED */ static struct cfq_queue ** @@ -4448,11 +4444,12 @@ cfq_set_request(struct request_queue *q, struct request *rq, struct bio *bio, const int rw = rq_data_dir(rq); const bool is_sync = rq_is_sync(rq); struct cfq_queue *cfqq; + bool disable_wbt; spin_lock_irq(q->queue_lock); check_ioprio_changed(cic, bio); - check_blkcg_changed(cic, bio); + disable_wbt = check_blkcg_changed(cic, bio); new_queue: cfqq = cic_to_cfqq(cic, is_sync); if (!cfqq || cfqq == &cfqd->oom_cfqq) { @@ -4488,6 +4485,10 @@ new_queue: rq->elv.priv[0] = cfqq; rq->elv.priv[1] = cfqq->cfqg; spin_unlock_irq(q->queue_lock); + + if (disable_wbt) + wbt_disable_default(q); + return 0; } diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 9ed087853dee..a391bbc48105 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -55,7 +55,7 @@ acpi-$(CONFIG_DEBUG_FS) += debugfs.o acpi-$(CONFIG_ACPI_NUMA) += numa.o acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o acpi-y += acpi_lpat.o -acpi-$(CONFIG_ACPI_GENERIC_GSI) += gsi.o +acpi-$(CONFIG_ACPI_GENERIC_GSI) += irq.o acpi-$(CONFIG_ACPI_WATCHDOG) += acpi_watchdog.o # These are (potentially) separate modules diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index b3842ffc19ba..a15270a806fc 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -212,6 +212,7 @@ static bool __init extlog_get_l1addr(void) } static struct notifier_block extlog_mce_dec = { .notifier_call = extlog_print, + .priority = MCE_PRIO_EXTLOG, }; static int __init extlog_init(void) diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c index 75f128e766a9..ca28aa572aa9 100644 --- a/drivers/acpi/bgrt.c +++ b/drivers/acpi/bgrt.c @@ -15,40 +15,41 @@ #include <linux/sysfs.h> #include <linux/efi-bgrt.h> +static void *bgrt_image; static struct kobject *bgrt_kobj; static ssize_t show_version(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->version); + return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.version); } static DEVICE_ATTR(version, S_IRUGO, show_version, NULL); static ssize_t show_status(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->status); + return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.status); } static DEVICE_ATTR(status, S_IRUGO, show_status, NULL); static ssize_t show_type(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_type); + return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_type); } static DEVICE_ATTR(type, S_IRUGO, show_type, NULL); static ssize_t show_xoffset(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_offset_x); + return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_offset_x); } static DEVICE_ATTR(xoffset, S_IRUGO, show_xoffset, NULL); static ssize_t show_yoffset(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_offset_y); + return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_offset_y); } static DEVICE_ATTR(yoffset, S_IRUGO, show_yoffset, NULL); @@ -84,15 +85,24 @@ static int __init bgrt_init(void) { int ret; - if (!bgrt_image) + if (!bgrt_tab.image_address) return -ENODEV; + bgrt_image = memremap(bgrt_tab.image_address, bgrt_image_size, + MEMREMAP_WB); + if (!bgrt_image) { + pr_notice("Ignoring BGRT: failed to map image memory\n"); + return -ENOMEM; + } + bin_attr_image.private = bgrt_image; bin_attr_image.size = bgrt_image_size; bgrt_kobj = kobject_create_and_add("bgrt", acpi_kobj); - if (!bgrt_kobj) - return -EINVAL; + if (!bgrt_kobj) { + ret = -EINVAL; + goto out_memmap; + } ret = sysfs_create_group(bgrt_kobj, &bgrt_attribute_group); if (ret) @@ -102,6 +112,8 @@ static int __init bgrt_init(void) out_kobject: kobject_put(bgrt_kobj); +out_memmap: + memunmap(bgrt_image); return ret; } device_initcall(bgrt_init); diff --git a/drivers/acpi/gsi.c b/drivers/acpi/gsi.c deleted file mode 100644 index ee9e0f27b2bf..000000000000 --- a/drivers/acpi/gsi.c +++ /dev/null @@ -1,98 +0,0 @@ -/* - * ACPI GSI IRQ layer - * - * Copyright (C) 2015 ARM Ltd. - * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> - * - * 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. - */ -#include <linux/acpi.h> -#include <linux/irq.h> -#include <linux/irqdomain.h> -#include <linux/of.h> - -enum acpi_irq_model_id acpi_irq_model; - -static struct fwnode_handle *acpi_gsi_domain_id; - -/** - * acpi_gsi_to_irq() - Retrieve the linux irq number for a given GSI - * @gsi: GSI IRQ number to map - * @irq: pointer where linux IRQ number is stored - * - * irq location updated with irq value [>0 on success, 0 on failure] - * - * Returns: linux IRQ number on success (>0) - * -EINVAL on failure - */ -int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) -{ - struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id, - DOMAIN_BUS_ANY); - - *irq = irq_find_mapping(d, gsi); - /* - * *irq == 0 means no mapping, that should - * be reported as a failure - */ - return (*irq > 0) ? *irq : -EINVAL; -} -EXPORT_SYMBOL_GPL(acpi_gsi_to_irq); - -/** - * acpi_register_gsi() - Map a GSI to a linux IRQ number - * @dev: device for which IRQ has to be mapped - * @gsi: GSI IRQ number - * @trigger: trigger type of the GSI number to be mapped - * @polarity: polarity of the GSI to be mapped - * - * Returns: a valid linux IRQ number on success - * -EINVAL on failure - */ -int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, - int polarity) -{ - struct irq_fwspec fwspec; - - if (WARN_ON(!acpi_gsi_domain_id)) { - pr_warn("GSI: No registered irqchip, giving up\n"); - return -EINVAL; - } - - fwspec.fwnode = acpi_gsi_domain_id; - fwspec.param[0] = gsi; - fwspec.param[1] = acpi_dev_get_irq_type(trigger, polarity); - fwspec.param_count = 2; - - return irq_create_fwspec_mapping(&fwspec); -} -EXPORT_SYMBOL_GPL(acpi_register_gsi); - -/** - * acpi_unregister_gsi() - Free a GSI<->linux IRQ number mapping - * @gsi: GSI IRQ number - */ -void acpi_unregister_gsi(u32 gsi) -{ - struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id, - DOMAIN_BUS_ANY); - int irq = irq_find_mapping(d, gsi); - - irq_dispose_mapping(irq); -} -EXPORT_SYMBOL_GPL(acpi_unregister_gsi); - -/** - * acpi_set_irq_model - Setup the GSI irqdomain information - * @model: the value assigned to acpi_irq_model - * @fwnode: the irq_domain identifier for mapping and looking up - * GSI interrupts - */ -void __init acpi_set_irq_model(enum acpi_irq_model_id model, - struct fwnode_handle *fwnode) -{ - acpi_irq_model = model; - acpi_gsi_domain_id = fwnode; -} diff --git a/drivers/acpi/irq.c b/drivers/acpi/irq.c new file mode 100644 index 000000000000..830299a74b84 --- /dev/null +++ b/drivers/acpi/irq.c @@ -0,0 +1,297 @@ +/* + * ACPI GSI IRQ layer + * + * Copyright (C) 2015 ARM Ltd. + * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + * + * 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. + */ +#include <linux/acpi.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/of.h> + +enum acpi_irq_model_id acpi_irq_model; + +static struct fwnode_handle *acpi_gsi_domain_id; + +/** + * acpi_gsi_to_irq() - Retrieve the linux irq number for a given GSI + * @gsi: GSI IRQ number to map + * @irq: pointer where linux IRQ number is stored + * + * irq location updated with irq value [>0 on success, 0 on failure] + * + * Returns: linux IRQ number on success (>0) + * -EINVAL on failure + */ +int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) +{ + struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id, + DOMAIN_BUS_ANY); + + *irq = irq_find_mapping(d, gsi); + /* + * *irq == 0 means no mapping, that should + * be reported as a failure + */ + return (*irq > 0) ? *irq : -EINVAL; +} +EXPORT_SYMBOL_GPL(acpi_gsi_to_irq); + +/** + * acpi_register_gsi() - Map a GSI to a linux IRQ number + * @dev: device for which IRQ has to be mapped + * @gsi: GSI IRQ number + * @trigger: trigger type of the GSI number to be mapped + * @polarity: polarity of the GSI to be mapped + * + * Returns: a valid linux IRQ number on success + * -EINVAL on failure + */ +int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, + int polarity) +{ + struct irq_fwspec fwspec; + + if (WARN_ON(!acpi_gsi_domain_id)) { + pr_warn("GSI: No registered irqchip, giving up\n"); + return -EINVAL; + } + + fwspec.fwnode = acpi_gsi_domain_id; + fwspec.param[0] = gsi; + fwspec.param[1] = acpi_dev_get_irq_type(trigger, polarity); + fwspec.param_count = 2; + + return irq_create_fwspec_mapping(&fwspec); +} +EXPORT_SYMBOL_GPL(acpi_register_gsi); + +/** + * acpi_unregister_gsi() - Free a GSI<->linux IRQ number mapping + * @gsi: GSI IRQ number + */ +void acpi_unregister_gsi(u32 gsi) +{ + struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id, + DOMAIN_BUS_ANY); + int irq = irq_find_mapping(d, gsi); + + irq_dispose_mapping(irq); +} +EXPORT_SYMBOL_GPL(acpi_unregister_gsi); + +/** + * acpi_get_irq_source_fwhandle() - Retrieve fwhandle from IRQ resource source. + * @source: acpi_resource_source to use for the lookup. + * + * Description: + * Retrieve the fwhandle of the device referenced by the given IRQ resource + * source. + * + * Return: + * The referenced device fwhandle or NULL on failure + */ +static struct fwnode_handle * +acpi_get_irq_source_fwhandle(const struct acpi_resource_source *source) +{ + struct fwnode_handle *result; + struct acpi_device *device; + acpi_handle handle; + acpi_status status; + + if (!source->string_length) + return acpi_gsi_domain_id; + + status = acpi_get_handle(NULL, source->string_ptr, &handle); + if (WARN_ON(ACPI_FAILURE(status))) + return NULL; + + device = acpi_bus_get_acpi_device(handle); + if (WARN_ON(!device)) + return NULL; + + result = &device->fwnode; + acpi_bus_put_acpi_device(device); + return result; +} + +/* + * Context for the resource walk used to lookup IRQ resources. + * Contains a return code, the lookup index, and references to the flags + * and fwspec where the result is returned. + */ +struct acpi_irq_parse_one_ctx { + int rc; + unsigned int index; + unsigned long *res_flags; + struct irq_fwspec *fwspec; +}; + +/** + * acpi_irq_parse_one_match - Handle a matching IRQ resource. + * @fwnode: matching fwnode + * @hwirq: hardware IRQ number + * @triggering: triggering attributes of hwirq + * @polarity: polarity attributes of hwirq + * @polarity: polarity attributes of hwirq + * @shareable: shareable attributes of hwirq + * @ctx: acpi_irq_parse_one_ctx updated by this function + * + * Description: + * Handle a matching IRQ resource by populating the given ctx with + * the information passed. + */ +static inline void acpi_irq_parse_one_match(struct fwnode_handle *fwnode, + u32 hwirq, u8 triggering, + u8 polarity, u8 shareable, + struct acpi_irq_parse_one_ctx *ctx) +{ + if (!fwnode) + return; + ctx->rc = 0; + *ctx->res_flags = acpi_dev_irq_flags(triggering, polarity, shareable); + ctx->fwspec->fwnode = fwnode; + ctx->fwspec->param[0] = hwirq; + ctx->fwspec->param[1] = acpi_dev_get_irq_type(triggering, polarity); + ctx->fwspec->param_count = 2; +} + +/** + * acpi_irq_parse_one_cb - Handle the given resource. + * @ares: resource to handle + * @context: context for the walk + * + * Description: + * This is called by acpi_walk_resources passing each resource returned by + * the _CRS method. We only inspect IRQ resources. Since IRQ resources + * might contain multiple interrupts we check if the index is within this + * one's interrupt array, otherwise we subtract the current resource IRQ + * count from the lookup index to prepare for the next resource. + * Once a match is found we call acpi_irq_parse_one_match to populate + * the result and end the walk by returning AE_CTRL_TERMINATE. + * + * Return: + * AE_OK if the walk should continue, AE_CTRL_TERMINATE if a matching + * IRQ resource was found. + */ +static acpi_status acpi_irq_parse_one_cb(struct acpi_resource *ares, + void *context) +{ + struct acpi_irq_parse_one_ctx *ctx = context; + struct acpi_resource_irq *irq; + struct acpi_resource_extended_irq *eirq; + struct fwnode_handle *fwnode; + + switch (ares->type) { + case ACPI_RESOURCE_TYPE_IRQ: + irq = &ares->data.irq; + if (ctx->index >= irq->interrupt_count) { + ctx->index -= irq->interrupt_count; + return AE_OK; + } + fwnode = acpi_gsi_domain_id; + acpi_irq_parse_one_match(fwnode, irq->interrupts[ctx->index], + irq->triggering, irq->polarity, + irq->sharable, ctx); + return AE_CTRL_TERMINATE; + case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: + eirq = &ares->data.extended_irq; + if (eirq->producer_consumer == ACPI_PRODUCER) + return AE_OK; + if (ctx->index >= eirq->interrupt_count) { + ctx->index -= eirq->interrupt_count; + return AE_OK; + } + fwnode = acpi_get_irq_source_fwhandle(&eirq->resource_source); + acpi_irq_parse_one_match(fwnode, eirq->interrupts[ctx->index], + eirq->triggering, eirq->polarity, + eirq->sharable, ctx); + return AE_CTRL_TERMINATE; + } + + return AE_OK; +} + +/** + * acpi_irq_parse_one - Resolve an interrupt for a device + * @handle: the device whose interrupt is to be resolved + * @index: index of the interrupt to resolve + * @fwspec: structure irq_fwspec filled by this function + * @flags: resource flags filled by this function + * + * Description: + * Resolves an interrupt for a device by walking its CRS resources to find + * the appropriate ACPI IRQ resource and populating the given struct irq_fwspec + * and flags. + * + * Return: + * The result stored in ctx.rc by the callback, or the default -EINVAL value + * if an error occurs. + */ +static int acpi_irq_parse_one(acpi_handle handle, unsigned int index, + struct irq_fwspec *fwspec, unsigned long *flags) +{ + struct acpi_irq_parse_one_ctx ctx = { -EINVAL, index, flags, fwspec }; + + acpi_walk_resources(handle, METHOD_NAME__CRS, acpi_irq_parse_one_cb, &ctx); + return ctx.rc; +} + +/** + * acpi_irq_get - Lookup an ACPI IRQ resource and use it to initialize resource. + * @handle: ACPI device handle + * @index: ACPI IRQ resource index to lookup + * @res: Linux IRQ resource to initialize + * + * Description: + * Look for the ACPI IRQ resource with the given index and use it to initialize + * the given Linux IRQ resource. + * + * Return: + * 0 on success + * -EINVAL if an error occurs + * -EPROBE_DEFER if the IRQ lookup/conversion failed + */ +int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) +{ + struct irq_fwspec fwspec; + struct irq_domain *domain; + unsigned long flags; + int rc; + + rc = acpi_irq_parse_one(handle, index, &fwspec, &flags); + if (rc) + return rc; + + domain = irq_find_matching_fwnode(fwspec.fwnode, DOMAIN_BUS_ANY); + if (!domain) + return -EPROBE_DEFER; + + rc = irq_create_fwspec_mapping(&fwspec); + if (rc <= 0) + return -EINVAL; + + res->start = rc; + res->end = rc; + res->flags = flags; + + return 0; +} +EXPORT_SYMBOL_GPL(acpi_irq_get); + +/** + * acpi_set_irq_model - Setup the GSI irqdomain information + * @model: the value assigned to acpi_irq_model + * @fwnode: the irq_domain identifier for mapping and looking up + * GSI interrupts + */ +void __init acpi_set_irq_model(enum acpi_irq_model_id model, + struct fwnode_handle *fwnode) +{ + acpi_irq_model = model; + acpi_gsi_domain_id = fwnode; +} diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c index e5ce81c38eed..3ba1c3472cf9 100644 --- a/drivers/acpi/nfit/mce.c +++ b/drivers/acpi/nfit/mce.c @@ -90,6 +90,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val, static struct notifier_block nfit_mce_dec = { .notifier_call = nfit_handle_mce, + .priority = MCE_PRIO_NFIT, }; void nfit_mce_register(void) diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index cb57962ef7c4..8b11d6d385dc 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -43,6 +43,19 @@ static inline bool acpi_iospace_resource_valid(struct resource *res) { return true; } #endif +#if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) +static inline bool is_gsi(struct acpi_resource_extended_irq *ext_irq) +{ + return ext_irq->resource_source.string_length == 0 && + ext_irq->producer_consumer == ACPI_CONSUMER; +} +#else +static inline bool is_gsi(struct acpi_resource_extended_irq *ext_irq) +{ + return true; +} +#endif + static bool acpi_dev_resource_len_valid(u64 start, u64 end, u64 len, bool io) { u64 reslen = end - start + 1; @@ -470,9 +483,12 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, acpi_dev_irqresource_disabled(res, 0); return false; } - acpi_dev_get_irqresource(res, ext_irq->interrupts[index], + if (is_gsi(ext_irq)) + acpi_dev_get_irqresource(res, ext_irq->interrupts[index], ext_irq->triggering, ext_irq->polarity, ext_irq->sharable, false); + else + acpi_dev_irqresource_disabled(res, 0); break; default: res->flags = 0; diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index be6a599bc0c1..0fc7c4da7756 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -206,7 +206,7 @@ platform_msi_alloc_priv_data(struct device *dev, unsigned int nvec, { struct platform_msi_priv_data *datap; /* - * Limit the number of interrupts to 256 per device. Should we + * Limit the number of interrupts to 2048 per device. Should we * need to bump this up, DEV_ID_SHIFT should be adjusted * accordingly (which would impact the max number of MSI * capable devices). diff --git a/drivers/base/platform.c b/drivers/base/platform.c index c4af00385502..647e4761dbf3 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -102,6 +102,16 @@ int platform_get_irq(struct platform_device *dev, unsigned int num) } r = platform_get_resource(dev, IORESOURCE_IRQ, num); + if (has_acpi_companion(&dev->dev)) { + if (r && r->flags & IORESOURCE_DISABLED) { + int ret; + + ret = acpi_irq_get(ACPI_HANDLE(&dev->dev), num, r); + if (ret) + return ret; + } + } + /* * The resources may pass trigger flags to the irqs that need * to be set up. It so happens that the trigger flags for diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index ab62b81c2ca7..dece26f119d4 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -1070,7 +1070,7 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned .done = 0, .flags = flags, .error = 0, - .kref = { ATOMIC_INIT(2) }, + .kref = KREF_INIT(2), }; if (!get_ldev_if_state(device, D_ATTACHING)) { /* put is in drbd_bm_aio_ctx_destroy() */ diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 83482721bc01..c3ff60c30dde 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2948,7 +2948,6 @@ void drbd_delete_device(struct drbd_device *device) struct drbd_resource *resource = device->resource; struct drbd_connection *connection; struct drbd_peer_device *peer_device; - int refs = 3; /* move to free_peer_device() */ for_each_peer_device(peer_device, device) @@ -2956,13 +2955,15 @@ void drbd_delete_device(struct drbd_device *device) drbd_debugfs_device_cleanup(device); for_each_connection(connection, resource) { idr_remove(&connection->peer_devices, device->vnr); - refs++; + kref_put(&device->kref, drbd_destroy_device); } idr_remove(&resource->devices, device->vnr); + kref_put(&device->kref, drbd_destroy_device); idr_remove(&drbd_devices, device_to_minor(device)); + kref_put(&device->kref, drbd_destroy_device); del_gendisk(device->vdisk); synchronize_rcu(); - kref_sub(&device->kref, refs, drbd_destroy_device); + kref_put(&device->kref, drbd_destroy_device); } static int __init drbd_init(void) diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index de279fe4e4fd..b489ac2e9c44 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -421,7 +421,6 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m, struct drbd_peer_device *peer_device = first_peer_device(device); unsigned s = req->rq_state; int c_put = 0; - int k_put = 0; if (drbd_suspended(device) && !((s | clear) & RQ_COMPLETION_SUSP)) set |= RQ_COMPLETION_SUSP; @@ -437,6 +436,8 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m, /* intent: get references */ + kref_get(&req->kref); + if (!(s & RQ_LOCAL_PENDING) && (set & RQ_LOCAL_PENDING)) atomic_inc(&req->completion_ref); @@ -473,15 +474,12 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m, if (!(s & RQ_LOCAL_ABORTED) && (set & RQ_LOCAL_ABORTED)) { D_ASSERT(device, req->rq_state & RQ_LOCAL_PENDING); - /* local completion may still come in later, - * we need to keep the req object around. */ - kref_get(&req->kref); ++c_put; } if ((s & RQ_LOCAL_PENDING) && (clear & RQ_LOCAL_PENDING)) { if (req->rq_state & RQ_LOCAL_ABORTED) - ++k_put; + kref_put(&req->kref, drbd_req_destroy); else ++c_put; list_del_init(&req->req_pending_local); @@ -503,7 +501,7 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m, if (s & RQ_NET_SENT) atomic_sub(req->i.size >> 9, &device->ap_in_flight); if (s & RQ_EXP_BARR_ACK) - ++k_put; + kref_put(&req->kref, drbd_req_destroy); req->net_done_jif = jiffies; /* in ahead/behind mode, or just in case, @@ -516,25 +514,16 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m, /* potentially complete and destroy */ - if (k_put || c_put) { - /* Completion does it's own kref_put. If we are going to - * kref_sub below, we need req to be still around then. */ - int at_least = k_put + !!c_put; - int refcount = atomic_read(&req->kref.refcount); - if (refcount < at_least) - drbd_err(device, - "mod_rq_state: Logic BUG: %x -> %x: refcount = %d, should be >= %d\n", - s, req->rq_state, refcount, at_least); - } - /* If we made progress, retry conflicting peer requests, if any. */ if (req->i.waiting) wake_up(&device->misc_wait); - if (c_put) - k_put += drbd_req_put_completion_ref(req, m, c_put); - if (k_put) - kref_sub(&req->kref, k_put, drbd_req_destroy); + if (c_put) { + if (drbd_req_put_completion_ref(req, m, c_put)) + kref_put(&req->kref, drbd_req_destroy); + } else { + kref_put(&req->kref, drbd_req_destroy); + } } static void drbd_report_io_error(struct drbd_device *device, struct drbd_request *req) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 36d2b9f4e836..436baa66f701 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1535,7 +1535,7 @@ static bool obj_request_overlaps_parent(struct rbd_obj_request *obj_request) static void rbd_obj_request_get(struct rbd_obj_request *obj_request) { dout("%s: obj %p (was %d)\n", __func__, obj_request, - atomic_read(&obj_request->kref.refcount)); + kref_read(&obj_request->kref)); kref_get(&obj_request->kref); } @@ -1544,14 +1544,14 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request) { rbd_assert(obj_request != NULL); dout("%s: obj %p (was %d)\n", __func__, obj_request, - atomic_read(&obj_request->kref.refcount)); + kref_read(&obj_request->kref)); kref_put(&obj_request->kref, rbd_obj_request_destroy); } static void rbd_img_request_get(struct rbd_img_request *img_request) { dout("%s: img %p (was %d)\n", __func__, img_request, - atomic_read(&img_request->kref.refcount)); + kref_read(&img_request->kref)); kref_get(&img_request->kref); } @@ -1562,7 +1562,7 @@ static void rbd_img_request_put(struct rbd_img_request *img_request) { rbd_assert(img_request != NULL); dout("%s: img %p (was %d)\n", __func__, img_request, - atomic_read(&img_request->kref.refcount)); + kref_read(&img_request->kref)); if (img_request_child_test(img_request)) kref_put(&img_request->kref, rbd_parent_request_destroy); else diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 10332c24f961..264c5eac12b0 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -770,7 +770,7 @@ static void virtblk_remove(struct virtio_device *vdev) /* Stop all the virtqueues. */ vdev->config->reset(vdev); - refc = atomic_read(&disk_to_dev(vblk->disk)->kobj.kref.refcount); + refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref); put_disk(vblk->disk); vdev->config->del_vqs(vdev); kfree(vblk->vqs); diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 4866f7aa32e6..3356ab821624 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -5,6 +5,10 @@ config CLKSRC_OF bool select CLKSRC_PROBE +config CLKEVT_OF + bool + select CLKEVT_PROBE + config CLKSRC_ACPI bool select CLKSRC_PROBE @@ -12,6 +16,9 @@ config CLKSRC_ACPI config CLKSRC_PROBE bool +config CLKEVT_PROBE + bool + config CLKSRC_I8253 bool @@ -60,6 +67,16 @@ config DW_APB_TIMER_OF select DW_APB_TIMER select CLKSRC_OF +config GEMINI_TIMER + bool "Cortina Gemini timer driver" if COMPILE_TEST + depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM + select CLKSRC_MMIO + select CLKSRC_OF + select MFD_SYSCON + help + Enables support for the Gemini timer + config ROCKCHIP_TIMER bool "Rockchip timer driver" if COMPILE_TEST depends on ARM || ARM64 @@ -325,16 +342,30 @@ config ARM_ARCH_TIMER_EVTSTREAM This must be disabled for hardware validation purposes to detect any hardware anomalies of missing events. +config ARM_ARCH_TIMER_OOL_WORKAROUND + bool + config FSL_ERRATUM_A008585 bool "Workaround for Freescale/NXP Erratum A-008585" default y depends on ARM_ARCH_TIMER && ARM64 + select ARM_ARCH_TIMER_OOL_WORKAROUND help This option enables a workaround for Freescale/NXP Erratum A-008585 ("ARM generic timer may contain an erroneous value"). The workaround will only be active if the fsl,erratum-a008585 property is found in the timer node. +config HISILICON_ERRATUM_161010101 + bool "Workaround for Hisilicon Erratum 161010101" + default y + select ARM_ARCH_TIMER_OOL_WORKAROUND + depends on ARM_ARCH_TIMER && ARM64 + help + This option enables a workaround for Hisilicon Erratum + 161010101. The workaround will be active if the hisilicon,erratum-161010101 + property is found in the timer node. + config ARM_GLOBAL_TIMER bool "Support for the ARM global timer" if COMPILE_TEST select CLKSRC_OF if OF @@ -467,6 +498,13 @@ config SH_TIMER_MTU2 Timer Pulse Unit 2 (MTU2) hardware available on SoCs from Renesas. This hardware comes with 16 bit-timer registers. +config RENESAS_OSTM + bool "Renesas OSTM timer driver" if COMPILE_TEST + depends on GENERIC_CLOCKEVENTS + select CLKSRC_MMIO + help + Enables the support for the Renesas OSTM. + config SH_TIMER_TMU bool "Renesas TMU timer driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index a14111e1f087..d227d1314f14 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_CLKSRC_PROBE) += clksrc-probe.o +obj-$(CONFIG_CLKEVT_PROBE) += clkevt-probe.o obj-$(CONFIG_ATMEL_PIT) += timer-atmel-pit.o obj-$(CONFIG_ATMEL_ST) += timer-atmel-st.o obj-$(CONFIG_ATMEL_TCB_CLKSRC) += tcb_clksrc.o @@ -8,6 +9,7 @@ obj-$(CONFIG_CS5535_CLOCK_EVENT_SRC) += cs5535-clockevt.o obj-$(CONFIG_CLKSRC_JCORE_PIT) += jcore-pit.o obj-$(CONFIG_SH_TIMER_CMT) += sh_cmt.o obj-$(CONFIG_SH_TIMER_MTU2) += sh_mtu2.o +obj-$(CONFIG_RENESAS_OSTM) += renesas-ostm.o obj-$(CONFIG_SH_TIMER_TMU) += sh_tmu.o obj-$(CONFIG_EM_TIMER_STI) += em_sti.o obj-$(CONFIG_CLKBLD_I8253) += i8253.o @@ -15,6 +17,7 @@ obj-$(CONFIG_CLKSRC_MMIO) += mmio.o obj-$(CONFIG_DIGICOLOR_TIMER) += timer-digicolor.o obj-$(CONFIG_DW_APB_TIMER) += dw_apb_timer.o obj-$(CONFIG_DW_APB_TIMER_OF) += dw_apb_timer_of.o +obj-$(CONFIG_GEMINI_TIMER) += timer-gemini.o obj-$(CONFIG_ROCKCHIP_TIMER) += rockchip_timer.o obj-$(CONFIG_CLKSRC_NOMADIK_MTU) += nomadik-mtu.o obj-$(CONFIG_CLKSRC_DBX500_PRCMU) += clksrc-dbx500-prcmu.o diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 4c8c3fb2e8b2..93aa1364376a 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -96,41 +96,107 @@ early_param("clocksource.arm_arch_timer.evtstrm", early_evtstrm_cfg); */ #ifdef CONFIG_FSL_ERRATUM_A008585 -DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled); -EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled); - -static int fsl_a008585_enable = -1; - -static int __init early_fsl_a008585_cfg(char *buf) +/* + * The number of retries is an arbitrary value well beyond the highest number + * of iterations the loop has been observed to take. + */ +#define __fsl_a008585_read_reg(reg) ({ \ + u64 _old, _new; \ + int _retries = 200; \ + \ + do { \ + _old = read_sysreg(reg); \ + _new = read_sysreg(reg); \ + _retries--; \ + } while (unlikely(_old != _new) && _retries); \ + \ + WARN_ON_ONCE(!_retries); \ + _new; \ +}) + +static u32 notrace fsl_a008585_read_cntp_tval_el0(void) { - int ret; - bool val; + return __fsl_a008585_read_reg(cntp_tval_el0); +} - ret = strtobool(buf, &val); - if (ret) - return ret; +static u32 notrace fsl_a008585_read_cntv_tval_el0(void) +{ + return __fsl_a008585_read_reg(cntv_tval_el0); +} - fsl_a008585_enable = val; - return 0; +static u64 notrace fsl_a008585_read_cntvct_el0(void) +{ + return __fsl_a008585_read_reg(cntvct_el0); } -early_param("clocksource.arm_arch_timer.fsl-a008585", early_fsl_a008585_cfg); +#endif -u32 __fsl_a008585_read_cntp_tval_el0(void) +#ifdef CONFIG_HISILICON_ERRATUM_161010101 +/* + * Verify whether the value of the second read is larger than the first by + * less than 32 is the only way to confirm the value is correct, so clear the + * lower 5 bits to check whether the difference is greater than 32 or not. + * Theoretically the erratum should not occur more than twice in succession + * when reading the system counter, but it is possible that some interrupts + * may lead to more than twice read errors, triggering the warning, so setting + * the number of retries far beyond the number of iterations the loop has been + * observed to take. + */ +#define __hisi_161010101_read_reg(reg) ({ \ + u64 _old, _new; \ + int _retries = 50; \ + \ + do { \ + _old = read_sysreg(reg); \ + _new = read_sysreg(reg); \ + _retries--; \ + } while (unlikely((_new - _old) >> 5) && _retries); \ + \ + WARN_ON_ONCE(!_retries); \ + _new; \ +}) + +static u32 notrace hisi_161010101_read_cntp_tval_el0(void) { - return __fsl_a008585_read_reg(cntp_tval_el0); + return __hisi_161010101_read_reg(cntp_tval_el0); } -u32 __fsl_a008585_read_cntv_tval_el0(void) +static u32 notrace hisi_161010101_read_cntv_tval_el0(void) { - return __fsl_a008585_read_reg(cntv_tval_el0); + return __hisi_161010101_read_reg(cntv_tval_el0); } -u64 __fsl_a008585_read_cntvct_el0(void) +static u64 notrace hisi_161010101_read_cntvct_el0(void) { - return __fsl_a008585_read_reg(cntvct_el0); + return __hisi_161010101_read_reg(cntvct_el0); } -EXPORT_SYMBOL(__fsl_a008585_read_cntvct_el0); -#endif /* CONFIG_FSL_ERRATUM_A008585 */ +#endif + +#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND +const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround = NULL; +EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround); + +DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled); +EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled); + +static const struct arch_timer_erratum_workaround ool_workarounds[] = { +#ifdef CONFIG_FSL_ERRATUM_A008585 + { + .id = "fsl,erratum-a008585", + .read_cntp_tval_el0 = fsl_a008585_read_cntp_tval_el0, + .read_cntv_tval_el0 = fsl_a008585_read_cntv_tval_el0, + .read_cntvct_el0 = fsl_a008585_read_cntvct_el0, + }, +#endif +#ifdef CONFIG_HISILICON_ERRATUM_161010101 + { + .id = "hisilicon,erratum-161010101", + .read_cntp_tval_el0 = hisi_161010101_read_cntp_tval_el0, + .read_cntv_tval_el0 = hisi_161010101_read_cntv_tval_el0, + .read_cntvct_el0 = hisi_161010101_read_cntvct_el0, + }, +#endif +}; +#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */ static __always_inline void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val, @@ -281,8 +347,8 @@ static __always_inline void set_next_event(const int access, unsigned long evt, arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); } -#ifdef CONFIG_FSL_ERRATUM_A008585 -static __always_inline void fsl_a008585_set_next_event(const int access, +#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND +static __always_inline void erratum_set_next_event_generic(const int access, unsigned long evt, struct clock_event_device *clk) { unsigned long ctrl; @@ -300,20 +366,20 @@ static __always_inline void fsl_a008585_set_next_event(const int access, arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); } -static int fsl_a008585_set_next_event_virt(unsigned long evt, +static int erratum_set_next_event_virt(unsigned long evt, struct clock_event_device *clk) { - fsl_a008585_set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk); + erratum_set_next_event_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk); return 0; } -static int fsl_a008585_set_next_event_phys(unsigned long evt, +static int erratum_set_next_event_phys(unsigned long evt, struct clock_event_device *clk) { - fsl_a008585_set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk); + erratum_set_next_event_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk); return 0; } -#endif /* CONFIG_FSL_ERRATUM_A008585 */ +#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */ static int arch_timer_set_next_event_virt(unsigned long evt, struct clock_event_device *clk) @@ -343,16 +409,16 @@ static int arch_timer_set_next_event_phys_mem(unsigned long evt, return 0; } -static void fsl_a008585_set_sne(struct clock_event_device *clk) +static void erratum_workaround_set_sne(struct clock_event_device *clk) { -#ifdef CONFIG_FSL_ERRATUM_A008585 +#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND if (!static_branch_unlikely(&arch_timer_read_ool_enabled)) return; if (arch_timer_uses_ppi == VIRT_PPI) - clk->set_next_event = fsl_a008585_set_next_event_virt; + clk->set_next_event = erratum_set_next_event_virt; else - clk->set_next_event = fsl_a008585_set_next_event_phys; + clk->set_next_event = erratum_set_next_event_phys; #endif } @@ -385,7 +451,7 @@ static void __arch_timer_setup(unsigned type, BUG(); } - fsl_a008585_set_sne(clk); + erratum_workaround_set_sne(clk); } else { clk->features |= CLOCK_EVT_FEAT_DYNIRQ; clk->name = "arch_mem_timer"; @@ -580,7 +646,7 @@ static struct clocksource clocksource_counter = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static struct cyclecounter cyclecounter = { +static struct cyclecounter cyclecounter __ro_after_init = { .read = arch_counter_read_cc, .mask = CLOCKSOURCE_MASK(56), }; @@ -605,7 +671,7 @@ static void __init arch_counter_register(unsigned type) clocksource_counter.archdata.vdso_direct = true; -#ifdef CONFIG_FSL_ERRATUM_A008585 +#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND /* * Don't use the vdso fastpath if errata require using * the out-of-line counter accessor. @@ -893,12 +959,15 @@ static int __init arch_timer_of_init(struct device_node *np) arch_timer_c3stop = !of_property_read_bool(np, "always-on"); -#ifdef CONFIG_FSL_ERRATUM_A008585 - if (fsl_a008585_enable < 0) - fsl_a008585_enable = of_property_read_bool(np, "fsl,erratum-a008585"); - if (fsl_a008585_enable) { - static_branch_enable(&arch_timer_read_ool_enabled); - pr_info("Enabling workaround for FSL erratum A-008585\n"); +#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND + for (i = 0; i < ARRAY_SIZE(ool_workarounds); i++) { + if (of_property_read_bool(np, ool_workarounds[i].id)) { + timer_unstable_counter_workaround = &ool_workarounds[i]; + static_branch_enable(&arch_timer_read_ool_enabled); + pr_info("arch_timer: Enabling workaround for %s\n", + timer_unstable_counter_workaround->id); + break; + } } #endif diff --git a/drivers/clocksource/clkevt-probe.c b/drivers/clocksource/clkevt-probe.c new file mode 100644 index 000000000000..8c30fec86094 --- /dev/null +++ b/drivers/clocksource/clkevt-probe.c @@ -0,0 +1,56 @@ +/* + * Copyright (c) 2016, Linaro Ltd. All rights reserved. + * Daniel Lezcano <daniel.lezcano@linaro.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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/init.h> +#include <linux/of.h> +#include <linux/clockchip.h> + +extern struct of_device_id __clkevt_of_table[]; + +static const struct of_device_id __clkevt_of_table_sentinel + __used __section(__clkevt_of_table_end); + +int __init clockevent_probe(void) +{ + struct device_node *np; + const struct of_device_id *match; + of_init_fn_1_ret init_func; + int ret, clockevents = 0; + + for_each_matching_node_and_match(np, __clkevt_of_table, &match) { + if (!of_device_is_available(np)) + continue; + + init_func = match->data; + + ret = init_func(np); + if (ret) { + pr_warn("Failed to initialize '%s' (%d)\n", + np->name, ret); + continue; + } + + clockevents++; + } + + if (!clockevents) { + pr_crit("%s: no matching clockevent found\n", __func__); + return -ENODEV; + } + + return 0; +} diff --git a/drivers/clocksource/renesas-ostm.c b/drivers/clocksource/renesas-ostm.c new file mode 100644 index 000000000000..c76f57668fb2 --- /dev/null +++ b/drivers/clocksource/renesas-ostm.c @@ -0,0 +1,265 @@ +/* + * Renesas Timer Support - OSTM + * + * Copyright (C) 2017 Renesas Electronics America, Inc. + * Copyright (C) 2017 Chris Brandt + * + * 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 + * + * 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. + * + */ + +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/clk.h> +#include <linux/clockchips.h> +#include <linux/interrupt.h> +#include <linux/sched_clock.h> +#include <linux/slab.h> + +/* + * The OSTM contains independent channels. + * The first OSTM channel probed will be set up as a free running + * clocksource. Additionally we will use this clocksource for the system + * schedule timer sched_clock(). + * + * The second (or more) channel probed will be set up as an interrupt + * driven clock event. + */ + +struct ostm_device { + void __iomem *base; + unsigned long ticks_per_jiffy; + struct clock_event_device ced; +}; + +static void __iomem *system_clock; /* For sched_clock() */ + +/* OSTM REGISTERS */ +#define OSTM_CMP 0x000 /* RW,32 */ +#define OSTM_CNT 0x004 /* R,32 */ +#define OSTM_TE 0x010 /* R,8 */ +#define OSTM_TS 0x014 /* W,8 */ +#define OSTM_TT 0x018 /* W,8 */ +#define OSTM_CTL 0x020 /* RW,8 */ + +#define TE 0x01 +#define TS 0x01 +#define TT 0x01 +#define CTL_PERIODIC 0x00 +#define CTL_ONESHOT 0x02 +#define CTL_FREERUN 0x02 + +static struct ostm_device *ced_to_ostm(struct clock_event_device *ced) +{ + return container_of(ced, struct ostm_device, ced); +} + +static void ostm_timer_stop(struct ostm_device *ostm) +{ + if (readb(ostm->base + OSTM_TE) & TE) { + writeb(TT, ostm->base + OSTM_TT); + + /* + * Read back the register simply to confirm the write operation + * has completed since I/O writes can sometimes get queued by + * the bus architecture. + */ + while (readb(ostm->base + OSTM_TE) & TE) + ; + } +} + +static int __init ostm_init_clksrc(struct ostm_device *ostm, unsigned long rate) +{ + /* + * irq not used (clock sources don't use interrupts) + */ + + ostm_timer_stop(ostm); + + writel(0, ostm->base + OSTM_CMP); + writeb(CTL_FREERUN, ostm->base + OSTM_CTL); + writeb(TS, ostm->base + OSTM_TS); + + return clocksource_mmio_init(ostm->base + OSTM_CNT, + "ostm", rate, + 300, 32, clocksource_mmio_readl_up); +} + +static u64 notrace ostm_read_sched_clock(void) +{ + return readl(system_clock); +} + +static void __init ostm_init_sched_clock(struct ostm_device *ostm, + unsigned long rate) +{ + system_clock = ostm->base + OSTM_CNT; + sched_clock_register(ostm_read_sched_clock, 32, rate); +} + +static int ostm_clock_event_next(unsigned long delta, + struct clock_event_device *ced) +{ + struct ostm_device *ostm = ced_to_ostm(ced); + + ostm_timer_stop(ostm); + + writel(delta, ostm->base + OSTM_CMP); + writeb(CTL_ONESHOT, ostm->base + OSTM_CTL); + writeb(TS, ostm->base + OSTM_TS); + + return 0; +} + +static int ostm_shutdown(struct clock_event_device *ced) +{ + struct ostm_device *ostm = ced_to_ostm(ced); + + ostm_timer_stop(ostm); + + return 0; +} +static int ostm_set_periodic(struct clock_event_device *ced) +{ + struct ostm_device *ostm = ced_to_ostm(ced); + + if (clockevent_state_oneshot(ced) || clockevent_state_periodic(ced)) + ostm_timer_stop(ostm); + + writel(ostm->ticks_per_jiffy - 1, ostm->base + OSTM_CMP); + writeb(CTL_PERIODIC, ostm->base + OSTM_CTL); + writeb(TS, ostm->base + OSTM_TS); + + return 0; +} + +static int ostm_set_oneshot(struct clock_event_device *ced) +{ + struct ostm_device *ostm = ced_to_ostm(ced); + + ostm_timer_stop(ostm); + + return 0; +} + +static irqreturn_t ostm_timer_interrupt(int irq, void *dev_id) +{ + struct ostm_device *ostm = dev_id; + + if (clockevent_state_oneshot(&ostm->ced)) + ostm_timer_stop(ostm); + + /* notify clockevent layer */ + if (ostm->ced.event_handler) + ostm->ced.event_handler(&ostm->ced); + + return IRQ_HANDLED; +} + +static int __init ostm_init_clkevt(struct ostm_device *ostm, int irq, + unsigned long rate) +{ + struct clock_event_device *ced = &ostm->ced; + int ret = -ENXIO; + + ret = request_irq(irq, ostm_timer_interrupt, + IRQF_TIMER | IRQF_IRQPOLL, + "ostm", ostm); + if (ret) { + pr_err("ostm: failed to request irq\n"); + return ret; + } + + ced->name = "ostm"; + ced->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC; + ced->set_state_shutdown = ostm_shutdown; + ced->set_state_periodic = ostm_set_periodic; + ced->set_state_oneshot = ostm_set_oneshot; + ced->set_next_event = ostm_clock_event_next; + ced->shift = 32; + ced->rating = 300; + ced->cpumask = cpumask_of(0); + clockevents_config_and_register(ced, rate, 0xf, 0xffffffff); + + return 0; +} + +static int __init ostm_init(struct device_node *np) +{ + struct ostm_device *ostm; + int ret = -EFAULT; + struct clk *ostm_clk = NULL; + int irq; + unsigned long rate; + + ostm = kzalloc(sizeof(*ostm), GFP_KERNEL); + if (!ostm) + return -ENOMEM; + + ostm->base = of_iomap(np, 0); + if (!ostm->base) { + pr_err("ostm: failed to remap I/O memory\n"); + goto err; + } + + irq = irq_of_parse_and_map(np, 0); + if (irq < 0) { + pr_err("ostm: Failed to get irq\n"); + goto err; + } + + ostm_clk = of_clk_get(np, 0); + if (IS_ERR(ostm_clk)) { + pr_err("ostm: Failed to get clock\n"); + ostm_clk = NULL; + goto err; + } + + ret = clk_prepare_enable(ostm_clk); + if (ret) { + pr_err("ostm: Failed to enable clock\n"); + goto err; + } + + rate = clk_get_rate(ostm_clk); + ostm->ticks_per_jiffy = (rate + HZ / 2) / HZ; + + /* + * First probed device will be used as system clocksource. Any + * additional devices will be used as clock events. + */ + if (!system_clock) { + ret = ostm_init_clksrc(ostm, rate); + + if (!ret) { + ostm_init_sched_clock(ostm, rate); + pr_info("ostm: used for clocksource\n"); + } + + } else { + ret = ostm_init_clkevt(ostm, irq, rate); + + if (!ret) + pr_info("ostm: used for clock events\n"); + } + +err: + if (ret) { + clk_disable_unprepare(ostm_clk); + iounmap(ostm->base); + kfree(ostm); + return ret; + } + + return 0; +} + +CLOCKSOURCE_OF_DECLARE(ostm, "renesas,ostm", ostm_init); diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c index d4ca9962a759..745844ee973e 100644 --- a/drivers/clocksource/tcb_clksrc.c +++ b/drivers/clocksource/tcb_clksrc.c @@ -10,6 +10,7 @@ #include <linux/io.h> #include <linux/platform_device.h> #include <linux/atmel_tc.h> +#include <linux/sched_clock.h> /* @@ -56,11 +57,16 @@ static u64 tc_get_cycles(struct clocksource *cs) return (upper << 16) | lower; } -static u64 tc_get_cycles32(struct clocksource *cs) +static u32 tc_get_cv32(void) { return __raw_readl(tcaddr + ATMEL_TC_REG(0, CV)); } +static u64 tc_get_cycles32(struct clocksource *cs) +{ + return tc_get_cv32(); +} + static struct clocksource clksrc = { .name = "tcb_clksrc", .rating = 200, @@ -69,6 +75,11 @@ static struct clocksource clksrc = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +static u64 notrace tc_read_sched_clock(void) +{ + return tc_get_cv32(); +} + #ifdef CONFIG_GENERIC_CLOCKEVENTS struct tc_clkevt_device { @@ -339,6 +350,9 @@ static int __init tcb_clksrc_init(void) clksrc.read = tc_get_cycles32; /* setup ony channel 0 */ tcb_setup_single_chan(tc, best_divisor_idx); + + /* register sched_clock on chips with single 32 bit counter */ + sched_clock_register(tc_read_sched_clock, 32, divided_rate); } else { /* tclib will give us three clocks no matter what the * underlying platform supports. diff --git a/drivers/clocksource/timer-gemini.c b/drivers/clocksource/timer-gemini.c new file mode 100644 index 000000000000..dda27b7bf1a1 --- /dev/null +++ b/drivers/clocksource/timer-gemini.c @@ -0,0 +1,277 @@ +/* + * Gemini timer driver + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * + * Based on a rewrite of arch/arm/mach-gemini/timer.c: + * Copyright (C) 2001-2006 Storlink, Corp. + * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt> + */ +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> +#include <linux/clockchips.h> +#include <linux/clocksource.h> +#include <linux/sched_clock.h> + +/* + * Relevant registers in the global syscon + */ +#define GLOBAL_STATUS 0x04 +#define CPU_AHB_RATIO_MASK (0x3 << 18) +#define CPU_AHB_1_1 (0x0 << 18) +#define CPU_AHB_3_2 (0x1 << 18) +#define CPU_AHB_24_13 (0x2 << 18) +#define CPU_AHB_2_1 (0x3 << 18) +#define REG_TO_AHB_SPEED(reg) ((((reg) >> 15) & 0x7) * 10 + 130) + +/* + * Register definitions for the timers + */ +#define TIMER1_COUNT (0x00) +#define TIMER1_LOAD (0x04) +#define TIMER1_MATCH1 (0x08) +#define TIMER1_MATCH2 (0x0c) +#define TIMER2_COUNT (0x10) +#define TIMER2_LOAD (0x14) +#define TIMER2_MATCH1 (0x18) +#define TIMER2_MATCH2 (0x1c) +#define TIMER3_COUNT (0x20) +#define TIMER3_LOAD (0x24) +#define TIMER3_MATCH1 (0x28) +#define TIMER3_MATCH2 (0x2c) +#define TIMER_CR (0x30) +#define TIMER_INTR_STATE (0x34) +#define TIMER_INTR_MASK (0x38) + +#define TIMER_1_CR_ENABLE (1 << 0) +#define TIMER_1_CR_CLOCK (1 << 1) +#define TIMER_1_CR_INT (1 << 2) +#define TIMER_2_CR_ENABLE (1 << 3) +#define TIMER_2_CR_CLOCK (1 << 4) +#define TIMER_2_CR_INT (1 << 5) +#define TIMER_3_CR_ENABLE (1 << 6) +#define TIMER_3_CR_CLOCK (1 << 7) +#define TIMER_3_CR_INT (1 << 8) +#define TIMER_1_CR_UPDOWN (1 << 9) +#define TIMER_2_CR_UPDOWN (1 << 10) +#define TIMER_3_CR_UPDOWN (1 << 11) +#define TIMER_DEFAULT_FLAGS (TIMER_1_CR_UPDOWN | \ + TIMER_3_CR_ENABLE | \ + TIMER_3_CR_UPDOWN) + +#define TIMER_1_INT_MATCH1 (1 << 0) +#define TIMER_1_INT_MATCH2 (1 << 1) +#define TIMER_1_INT_OVERFLOW (1 << 2) +#define TIMER_2_INT_MATCH1 (1 << 3) +#define TIMER_2_INT_MATCH2 (1 << 4) +#define TIMER_2_INT_OVERFLOW (1 << 5) +#define TIMER_3_INT_MATCH1 (1 << 6) +#define TIMER_3_INT_MATCH2 (1 << 7) +#define TIMER_3_INT_OVERFLOW (1 << 8) +#define TIMER_INT_ALL_MASK 0x1ff + +static unsigned int tick_rate; +static void __iomem *base; + +static u64 notrace gemini_read_sched_clock(void) +{ + return readl(base + TIMER3_COUNT); +} + +static int gemini_timer_set_next_event(unsigned long cycles, + struct clock_event_device *evt) +{ + u32 cr; + + /* Setup the match register */ + cr = readl(base + TIMER1_COUNT); + writel(cr + cycles, base + TIMER1_MATCH1); + if (readl(base + TIMER1_COUNT) - cr > cycles) + return -ETIME; + + return 0; +} + +static int gemini_timer_shutdown(struct clock_event_device *evt) +{ + u32 cr; + + /* + * Disable also for oneshot: the set_next() call will arm the timer + * instead. + */ + /* Stop timer and interrupt. */ + cr = readl(base + TIMER_CR); + cr &= ~(TIMER_1_CR_ENABLE | TIMER_1_CR_INT); + writel(cr, base + TIMER_CR); + + /* Setup counter start from 0 */ + writel(0, base + TIMER1_COUNT); + writel(0, base + TIMER1_LOAD); + + /* enable interrupt */ + cr = readl(base + TIMER_INTR_MASK); + cr &= ~(TIMER_1_INT_OVERFLOW | TIMER_1_INT_MATCH2); + cr |= TIMER_1_INT_MATCH1; + writel(cr, base + TIMER_INTR_MASK); + + /* start the timer */ + cr = readl(base + TIMER_CR); + cr |= TIMER_1_CR_ENABLE; + writel(cr, base + TIMER_CR); + + return 0; +} + +static int gemini_timer_set_periodic(struct clock_event_device *evt) +{ + u32 period = DIV_ROUND_CLOSEST(tick_rate, HZ); + u32 cr; + + /* Stop timer and interrupt */ + cr = readl(base + TIMER_CR); + cr &= ~(TIMER_1_CR_ENABLE | TIMER_1_CR_INT); + writel(cr, base + TIMER_CR); + + /* Setup timer to fire at 1/HT intervals. */ + cr = 0xffffffff - (period - 1); + writel(cr, base + TIMER1_COUNT); + writel(cr, base + TIMER1_LOAD); + + /* enable interrupt on overflow */ + cr = readl(base + TIMER_INTR_MASK); + cr &= ~(TIMER_1_INT_MATCH1 | TIMER_1_INT_MATCH2); + cr |= TIMER_1_INT_OVERFLOW; + writel(cr, base + TIMER_INTR_MASK); + + /* Start the timer */ + cr = readl(base + TIMER_CR); + cr |= TIMER_1_CR_ENABLE; + cr |= TIMER_1_CR_INT; + writel(cr, base + TIMER_CR); + + return 0; +} + +/* Use TIMER1 as clock event */ +static struct clock_event_device gemini_clockevent = { + .name = "TIMER1", + /* Reasonably fast and accurate clock event */ + .rating = 300, + .shift = 32, + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT, + .set_next_event = gemini_timer_set_next_event, + .set_state_shutdown = gemini_timer_shutdown, + .set_state_periodic = gemini_timer_set_periodic, + .set_state_oneshot = gemini_timer_shutdown, + .tick_resume = gemini_timer_shutdown, +}; + +/* + * IRQ handler for the timer + */ +static irqreturn_t gemini_timer_interrupt(int irq, void *dev_id) +{ + struct clock_event_device *evt = &gemini_clockevent; + + evt->event_handler(evt); + return IRQ_HANDLED; +} + +static struct irqaction gemini_timer_irq = { + .name = "Gemini Timer Tick", + .flags = IRQF_TIMER, + .handler = gemini_timer_interrupt, +}; + +static int __init gemini_timer_of_init(struct device_node *np) +{ + static struct regmap *map; + int irq; + int ret; + u32 val; + + map = syscon_regmap_lookup_by_phandle(np, "syscon"); + if (IS_ERR(map)) { + pr_err("Can't get regmap for syscon handle"); + return -ENODEV; + } + ret = regmap_read(map, GLOBAL_STATUS, &val); + if (ret) { + pr_err("Can't read syscon status register"); + return -ENXIO; + } + + base = of_iomap(np, 0); + if (!base) { + pr_err("Can't remap registers"); + return -ENXIO; + } + /* IRQ for timer 1 */ + irq = irq_of_parse_and_map(np, 0); + if (irq <= 0) { + pr_err("Can't parse IRQ"); + return -EINVAL; + } + + tick_rate = REG_TO_AHB_SPEED(val) * 1000000; + printk(KERN_INFO "Bus: %dMHz", tick_rate / 1000000); + + tick_rate /= 6; /* APB bus run AHB*(1/6) */ + + switch (val & CPU_AHB_RATIO_MASK) { + case CPU_AHB_1_1: + printk(KERN_CONT "(1/1)\n"); + break; + case CPU_AHB_3_2: + printk(KERN_CONT "(3/2)\n"); + break; + case CPU_AHB_24_13: + printk(KERN_CONT "(24/13)\n"); + break; + case CPU_AHB_2_1: + printk(KERN_CONT "(2/1)\n"); + break; + } + + /* + * Reset the interrupt mask and status + */ + writel(TIMER_INT_ALL_MASK, base + TIMER_INTR_MASK); + writel(0, base + TIMER_INTR_STATE); + writel(TIMER_DEFAULT_FLAGS, base + TIMER_CR); + + /* + * Setup free-running clocksource timer (interrupts + * disabled.) + */ + writel(0, base + TIMER3_COUNT); + writel(0, base + TIMER3_LOAD); + writel(0, base + TIMER3_MATCH1); + writel(0, base + TIMER3_MATCH2); + clocksource_mmio_init(base + TIMER3_COUNT, + "gemini_clocksource", tick_rate, + 300, 32, clocksource_mmio_readl_up); + sched_clock_register(gemini_read_sched_clock, 32, tick_rate); + + /* + * Setup clockevent timer (interrupt-driven.) + */ + writel(0, base + TIMER1_COUNT); + writel(0, base + TIMER1_LOAD); + writel(0, base + TIMER1_MATCH1); + writel(0, base + TIMER1_MATCH2); + setup_irq(irq, &gemini_timer_irq); + gemini_clockevent.cpumask = cpumask_of(0); + clockevents_config_and_register(&gemini_clockevent, tick_rate, + 1, 0xffffffff); + + return 0; +} +CLOCKSOURCE_OF_DECLARE(nomadik_mtu, "cortina,gemini-timer", + gemini_timer_of_init); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index cc475eff90b3..3e9b319a2e79 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -132,7 +132,7 @@ static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall) u64 cur_wall_time; u64 busy_time; - cur_wall_time = jiffies64_to_cputime64(get_jiffies_64()); + cur_wall_time = jiffies64_to_nsecs(get_jiffies_64()); busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER]; busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM]; @@ -143,9 +143,9 @@ static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall) idle_time = cur_wall_time - busy_time; if (wall) - *wall = cputime_to_usecs(cur_wall_time); + *wall = div_u64(cur_wall_time, NSEC_PER_USEC); - return cputime_to_usecs(idle_time); + return div_u64(idle_time, NSEC_PER_USEC); } u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy) diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 0196467280bd..631bd2c86c5e 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -152,7 +152,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy) if (ignore_nice) { u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE]; - idle_time += cputime_to_usecs(cur_nice - j_cdbs->prev_cpu_nice); + idle_time += div_u64(cur_nice - j_cdbs->prev_cpu_nice, NSEC_PER_USEC); j_cdbs->prev_cpu_nice = cur_nice; } diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index ac284e66839c..17048bbec287 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -13,7 +13,6 @@ #include <linux/cpufreq.h> #include <linux/module.h> #include <linux/slab.h> -#include <linux/cputime.h> static DEFINE_SPINLOCK(cpufreq_stats_lock); diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 260251177830..82dab1692264 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -3065,6 +3065,8 @@ static bool ecc_enabled(struct pci_dev *F3, u16 nid) /* Check whether at least one UMC is enabled: */ if (umc_en_mask) ecc_en = umc_en_mask == ecc_en_mask; + else + edac_dbg(0, "Node %d: No enabled UMCs.\n", nid); /* Assume UMC MCA banks are enabled. */ nb_mce_en = true; @@ -3075,14 +3077,15 @@ static bool ecc_enabled(struct pci_dev *F3, u16 nid) nb_mce_en = nb_mce_bank_enabled_on_node(nid); if (!nb_mce_en) - amd64_notice("NB MCE bank disabled, set MSR 0x%08x[4] on node %d to enable.\n", + edac_dbg(0, "NB MCE bank disabled, set MSR 0x%08x[4] on node %d to enable.\n", MSR_IA32_MCG_CTL, nid); } - amd64_info("DRAM ECC %s.\n", (ecc_en ? "enabled" : "disabled")); + amd64_info("Node %d: DRAM ECC %s.\n", + nid, (ecc_en ? "enabled" : "disabled")); if (!ecc_en || !nb_mce_en) { - amd64_notice("%s", ecc_msg); + amd64_info("%s", ecc_msg); return false; } return true; @@ -3300,15 +3303,6 @@ static int init_one_instance(unsigned int nid) goto err_add_mc; } - /* register stuff with EDAC MCE */ - if (report_gart_errors) - amd_report_gart_errors(true); - - if (pvt->umc) - amd_register_ecc_decoder(decode_umc_error); - else - amd_register_ecc_decoder(decode_bus_error); - return 0; err_add_mc: @@ -3342,7 +3336,7 @@ static int probe_one_instance(unsigned int nid) ecc_stngs[nid] = s; if (!ecc_enabled(F3, nid)) { - ret = -ENODEV; + ret = 0; if (!ecc_enable_override) goto err_enable; @@ -3363,6 +3357,8 @@ static int probe_one_instance(unsigned int nid) if (boot_cpu_data.x86 < 0x17) restore_ecc_error_reporting(s, nid, F3); + + goto err_enable; } return ret; @@ -3396,14 +3392,6 @@ static void remove_one_instance(unsigned int nid) free_mc_sibling_devs(pvt); - /* unregister from EDAC MCE */ - amd_report_gart_errors(false); - - if (pvt->umc) - amd_unregister_ecc_decoder(decode_umc_error); - else - amd_unregister_ecc_decoder(decode_bus_error); - kfree(ecc_stngs[nid]); ecc_stngs[nid] = NULL; @@ -3452,8 +3440,11 @@ static int __init amd64_edac_init(void) int err = -ENODEV; int i; + if (!x86_match_cpu(amd64_cpuids)) + return -ENODEV; + if (amd_cache_northbridges() < 0) - goto err_ret; + return -ENODEV; opstate_init(); @@ -3466,14 +3457,30 @@ static int __init amd64_edac_init(void) if (!msrs) goto err_free; - for (i = 0; i < amd_nb_num(); i++) - if (probe_one_instance(i)) { + for (i = 0; i < amd_nb_num(); i++) { + err = probe_one_instance(i); + if (err) { /* unwind properly */ while (--i >= 0) remove_one_instance(i); goto err_pci; } + } + + if (!edac_has_mcs()) { + err = -ENODEV; + goto err_pci; + } + + /* register stuff with EDAC MCE */ + if (report_gart_errors) + amd_report_gart_errors(true); + + if (boot_cpu_data.x86 >= 0x17) + amd_register_ecc_decoder(decode_umc_error); + else + amd_register_ecc_decoder(decode_bus_error); setup_pci_device(); @@ -3493,7 +3500,6 @@ err_free: kfree(ecc_stngs); ecc_stngs = NULL; -err_ret: return err; } @@ -3504,6 +3510,14 @@ static void __exit amd64_edac_exit(void) if (pci_ctl) edac_pci_release_generic_ctl(pci_ctl); + /* unregister from EDAC MCE */ + amd_report_gart_errors(false); + + if (boot_cpu_data.x86 >= 0x17) + amd_unregister_ecc_decoder(decode_umc_error); + else + amd_unregister_ecc_decoder(decode_bus_error); + for (i = 0; i < amd_nb_num(); i++) remove_one_instance(i); diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index 496603d8f3d2..1d4b74e9a037 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -16,19 +16,14 @@ #include <linux/slab.h> #include <linux/mmzone.h> #include <linux/edac.h> +#include <asm/cpu_device_id.h> #include <asm/msr.h> #include "edac_module.h" #include "mce_amd.h" -#define amd64_debug(fmt, arg...) \ - edac_printk(KERN_DEBUG, "amd64", fmt, ##arg) - #define amd64_info(fmt, arg...) \ edac_printk(KERN_INFO, "amd64", fmt, ##arg) -#define amd64_notice(fmt, arg...) \ - edac_printk(KERN_NOTICE, "amd64", fmt, ##arg) - #define amd64_warn(fmt, arg...) \ edac_printk(KERN_WARNING, "amd64", "Warning: " fmt, ##arg) @@ -90,7 +85,7 @@ * sections 3.5.4 and 3.5.5 for more information. */ -#define EDAC_AMD64_VERSION "3.4.0" +#define EDAC_AMD64_VERSION "3.5.0" #define EDAC_MOD_STR "amd64_edac" /* Extended Model from CPUID, for CPU Revision numbers */ diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 750891ea07de..e5573c56b15e 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -453,6 +453,20 @@ void edac_mc_free(struct mem_ctl_info *mci) } EXPORT_SYMBOL_GPL(edac_mc_free); +bool edac_has_mcs(void) +{ + bool ret; + + mutex_lock(&mem_ctls_mutex); + + ret = list_empty(&mc_devices); + + mutex_unlock(&mem_ctls_mutex); + + return !ret; +} +EXPORT_SYMBOL_GPL(edac_has_mcs); + /* Caller must hold mem_ctls_mutex */ static struct mem_ctl_info *__find_mci_by_dev(struct device *dev) { diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h index 50fc1dc9c0d8..5357800e418d 100644 --- a/drivers/edac/edac_mc.h +++ b/drivers/edac/edac_mc.h @@ -149,6 +149,15 @@ extern int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci, extern void edac_mc_free(struct mem_ctl_info *mci); /** + * edac_has_mcs() - Check if any MCs have been allocated. + * + * Returns: + * True if MC instances have been registered successfully. + * False otherwise. + */ +extern bool edac_has_mcs(void); + +/** * edac_mc_find() - Search for a mem_ctl_info structure whose index is @idx. * * @idx: index to be seek diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 39dbab7d62f1..445862dac273 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -569,6 +569,40 @@ static ssize_t dimmdev_edac_mode_show(struct device *dev, return sprintf(data, "%s\n", edac_caps[dimm->edac_mode]); } +static ssize_t dimmdev_ce_count_show(struct device *dev, + struct device_attribute *mattr, + char *data) +{ + struct dimm_info *dimm = to_dimm(dev); + u32 count; + int off; + + off = EDAC_DIMM_OFF(dimm->mci->layers, + dimm->mci->n_layers, + dimm->location[0], + dimm->location[1], + dimm->location[2]); + count = dimm->mci->ce_per_layer[dimm->mci->n_layers-1][off]; + return sprintf(data, "%u\n", count); +} + +static ssize_t dimmdev_ue_count_show(struct device *dev, + struct device_attribute *mattr, + char *data) +{ + struct dimm_info *dimm = to_dimm(dev); + u32 count; + int off; + + off = EDAC_DIMM_OFF(dimm->mci->layers, + dimm->mci->n_layers, + dimm->location[0], + dimm->location[1], + dimm->location[2]); + count = dimm->mci->ue_per_layer[dimm->mci->n_layers-1][off]; + return sprintf(data, "%u\n", count); +} + /* dimm/rank attribute files */ static DEVICE_ATTR(dimm_label, S_IRUGO | S_IWUSR, dimmdev_label_show, dimmdev_label_store); @@ -577,6 +611,8 @@ static DEVICE_ATTR(size, S_IRUGO, dimmdev_size_show, NULL); static DEVICE_ATTR(dimm_mem_type, S_IRUGO, dimmdev_mem_type_show, NULL); static DEVICE_ATTR(dimm_dev_type, S_IRUGO, dimmdev_dev_type_show, NULL); static DEVICE_ATTR(dimm_edac_mode, S_IRUGO, dimmdev_edac_mode_show, NULL); +static DEVICE_ATTR(dimm_ce_count, S_IRUGO, dimmdev_ce_count_show, NULL); +static DEVICE_ATTR(dimm_ue_count, S_IRUGO, dimmdev_ue_count_show, NULL); /* attributes of the dimm<id>/rank<id> object */ static struct attribute *dimm_attrs[] = { @@ -586,6 +622,8 @@ static struct attribute *dimm_attrs[] = { &dev_attr_dimm_mem_type.attr, &dev_attr_dimm_dev_type.attr, &dev_attr_dimm_edac_mode.attr, + &dev_attr_dimm_ce_count.attr, + &dev_attr_dimm_ue_count.attr, NULL, }; @@ -831,7 +869,7 @@ static DEVICE_ATTR(ce_count, S_IRUGO, mci_ce_count_show, NULL); static DEVICE_ATTR(max_location, S_IRUGO, mci_max_location_show, NULL); /* memory scrubber attribute file */ -DEVICE_ATTR(sdram_scrub_rate, 0, mci_sdram_scrub_rate_show, +static DEVICE_ATTR(sdram_scrub_rate, 0, mci_sdram_scrub_rate_show, mci_sdram_scrub_rate_store); /* umode set later in is_visible */ static struct attribute *mci_attrs[] = { diff --git a/drivers/edac/fsl_ddr_edac.c b/drivers/edac/fsl_ddr_edac.c index 4e9608a958e7..efc8276d1d9c 100644 --- a/drivers/edac/fsl_ddr_edac.c +++ b/drivers/edac/fsl_ddr_edac.c @@ -145,12 +145,12 @@ static ssize_t fsl_mc_inject_ctrl_store(struct device *dev, return 0; } -DEVICE_ATTR(inject_data_hi, S_IRUGO | S_IWUSR, - fsl_mc_inject_data_hi_show, fsl_mc_inject_data_hi_store); -DEVICE_ATTR(inject_data_lo, S_IRUGO | S_IWUSR, - fsl_mc_inject_data_lo_show, fsl_mc_inject_data_lo_store); -DEVICE_ATTR(inject_ctrl, S_IRUGO | S_IWUSR, - fsl_mc_inject_ctrl_show, fsl_mc_inject_ctrl_store); +static DEVICE_ATTR(inject_data_hi, S_IRUGO | S_IWUSR, + fsl_mc_inject_data_hi_show, fsl_mc_inject_data_hi_store); +static DEVICE_ATTR(inject_data_lo, S_IRUGO | S_IWUSR, + fsl_mc_inject_data_lo_show, fsl_mc_inject_data_lo_store); +static DEVICE_ATTR(inject_ctrl, S_IRUGO | S_IWUSR, + fsl_mc_inject_ctrl_show, fsl_mc_inject_ctrl_store); static struct attribute *fsl_ddr_dev_attrs[] = { &dev_attr_inject_data_hi.attr, diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c index 0a912bf6de00..e391f5a716be 100644 --- a/drivers/edac/i7300_edac.c +++ b/drivers/edac/i7300_edac.c @@ -304,7 +304,6 @@ static const char *ferr_global_lo_name[] = { #define REDMEMA 0xdc #define REDMEMB 0x7c - #define IS_SECOND_CH(v) ((v) * (1 << 17)) #define RECMEMA 0xe0 #define RECMEMA_BANK(v) (((v) >> 12) & 7) @@ -483,8 +482,9 @@ static void i7300_process_fbd_error(struct mem_ctl_info *mci) pci_read_config_dword(pvt->pci_dev_16_1_fsb_addr_map, REDMEMB, &value); channel = (branch << 1); - if (IS_SECOND_CH(value)) - channel++; + + /* Second channel ? */ + channel += !!(value & BIT(17)); /* Clear the error bit */ pci_write_config_dword(pvt->pci_dev_16_1_fsb_addr_map, diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 69b5adead0ad..75ad847593b7 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1835,6 +1835,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val, static struct notifier_block i7_mce_dec = { .notifier_call = i7core_mce_check_error, + .priority = MCE_PRIO_EDAC, }; struct memdev_dmi_entry { diff --git a/drivers/edac/i82975x_edac.c b/drivers/edac/i82975x_edac.c index 7baa8ace267b..9dcdab28f665 100644 --- a/drivers/edac/i82975x_edac.c +++ b/drivers/edac/i82975x_edac.c @@ -494,6 +494,10 @@ static int i82975x_probe1(struct pci_dev *pdev, int dev_idx) } mchbar &= 0xffffc000; /* bits 31:14 used for 16K window */ mch_window = ioremap_nocache(mchbar, 0x1000); + if (!mch_window) { + edac_dbg(3, "error ioremapping MCHBAR!\n"); + goto fail0; + } #ifdef i82975x_DEBUG_IOMEM i82975x_printk(KERN_INFO, "MCHBAR real = %0x, remapped = %p\n", diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index 34208f38c5b1..ba35b7ea3686 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -937,12 +937,13 @@ static const char *decode_error_status(struct mce *m) } if (m->status & MCI_STATUS_DEFERRED) - return "Deferred error."; + return "Deferred error, no action required."; return "Corrected error, no action required."; } -int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) +static int +amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) { struct mce *m = (struct mce *)data; struct cpuinfo_x86 *c = &cpu_data(m->extcpu); @@ -991,20 +992,22 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) pr_cont("]: 0x%016llx\n", m->status); if (m->status & MCI_STATUS_ADDRV) - pr_emerg(HW_ERR "Error Addr: 0x%016llx", m->addr); + pr_emerg(HW_ERR "Error Addr: 0x%016llx\n", m->addr); if (boot_cpu_has(X86_FEATURE_SMCA)) { + pr_emerg(HW_ERR "IPID: 0x%016llx", m->ipid); + if (m->status & MCI_STATUS_SYNDV) pr_cont(", Syndrome: 0x%016llx", m->synd); - pr_cont(", IPID: 0x%016llx", m->ipid); - pr_cont("\n"); decode_smca_errors(m); goto err_code; - } else - pr_cont("\n"); + } + + if (m->tsc) + pr_emerg(HW_ERR "TSC: %llu\n", m->tsc); if (!fam_ops) goto err_code; @@ -1047,10 +1050,10 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) return NOTIFY_STOP; } -EXPORT_SYMBOL_GPL(amd_decode_mce); static struct notifier_block amd_mce_dec_nb = { .notifier_call = amd_decode_mce, + .priority = MCE_PRIO_EDAC, }; static int __init mce_amd_init(void) diff --git a/drivers/edac/mce_amd.h b/drivers/edac/mce_amd.h index c2359a1ea6b3..0b6a68673e0e 100644 --- a/drivers/edac/mce_amd.h +++ b/drivers/edac/mce_amd.h @@ -79,6 +79,5 @@ struct amd_decoder_ops { void amd_report_gart_errors(bool); void amd_register_ecc_decoder(void (*f)(int, struct mce *)); void amd_unregister_ecc_decoder(void (*f)(int, struct mce *)); -int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data); #endif /* _EDAC_MCE_AMD_H */ diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index 8f66cbed70b7..67f7bc3fe5b3 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -629,6 +629,7 @@ static const struct of_device_id mpc85xx_l2_err_of_match[] = { { .compatible = "fsl,p1020-l2-cache-controller", }, { .compatible = "fsl,p1021-l2-cache-controller", }, { .compatible = "fsl,p2020-l2-cache-controller", }, + { .compatible = "fsl,t2080-l2-cache-controller", }, {}, }; MODULE_DEVICE_TABLE(of, mpc85xx_l2_err_of_match); diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 54ae6dc45ab2..a65ea44e3b0b 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -304,7 +304,6 @@ struct sbridge_info { u64 (*rir_limit)(u32 reg); u64 (*sad_limit)(u32 reg); u32 (*interleave_mode)(u32 reg); - char* (*show_interleave_mode)(u32 reg); u32 (*dram_attr)(u32 reg); const u32 *dram_rule; const u32 *interleave_list; @@ -811,11 +810,6 @@ static u32 interleave_mode(u32 reg) return GET_BITFIELD(reg, 1, 1); } -char *show_interleave_mode(u32 reg) -{ - return interleave_mode(reg) ? "8:6" : "[8:6]XOR[18:16]"; -} - static u32 dram_attr(u32 reg) { return GET_BITFIELD(reg, 2, 3); @@ -831,29 +825,16 @@ static u32 knl_interleave_mode(u32 reg) return GET_BITFIELD(reg, 1, 2); } -static char *knl_show_interleave_mode(u32 reg) -{ - char *s; - - switch (knl_interleave_mode(reg)) { - case 0: - s = "use address bits [8:6]"; - break; - case 1: - s = "use address bits [10:8]"; - break; - case 2: - s = "use address bits [14:12]"; - break; - case 3: - s = "use address bits [32:30]"; - break; - default: - WARN_ON(1); - break; - } +static const char * const knl_intlv_mode[] = { + "[8:6]", "[10:8]", "[14:12]", "[32:30]" +}; - return s; +static const char *get_intlv_mode_str(u32 reg, enum type t) +{ + if (t == KNIGHTS_LANDING) + return knl_intlv_mode[knl_interleave_mode(reg)]; + else + return interleave_mode(reg) ? "[8:6]" : "[8:6]XOR[18:16]"; } static u32 dram_attr_knl(u32 reg) @@ -1810,7 +1791,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci) show_dram_attr(pvt->info.dram_attr(reg)), gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, - pvt->info.show_interleave_mode(reg), + get_intlv_mode_str(reg, pvt->info.type), reg); prv = limit; @@ -3136,7 +3117,8 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val, } static struct notifier_block sbridge_mce_dec = { - .notifier_call = sbridge_mce_check_error, + .notifier_call = sbridge_mce_check_error, + .priority = MCE_PRIO_EDAC, }; /**************************************************************************** @@ -3227,7 +3209,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.rir_limit = rir_limit; pvt->info.sad_limit = sad_limit; pvt->info.interleave_mode = interleave_mode; - pvt->info.show_interleave_mode = show_interleave_mode; pvt->info.dram_attr = dram_attr; pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule); pvt->info.interleave_list = ibridge_interleave_list; @@ -3251,7 +3232,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.rir_limit = rir_limit; pvt->info.sad_limit = sad_limit; pvt->info.interleave_mode = interleave_mode; - pvt->info.show_interleave_mode = show_interleave_mode; pvt->info.dram_attr = dram_attr; pvt->info.max_sad = ARRAY_SIZE(sbridge_dram_rule); pvt->info.interleave_list = sbridge_interleave_list; @@ -3275,7 +3255,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.rir_limit = haswell_rir_limit; pvt->info.sad_limit = sad_limit; pvt->info.interleave_mode = interleave_mode; - pvt->info.show_interleave_mode = show_interleave_mode; pvt->info.dram_attr = dram_attr; pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule); pvt->info.interleave_list = ibridge_interleave_list; @@ -3299,7 +3278,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.rir_limit = haswell_rir_limit; pvt->info.sad_limit = sad_limit; pvt->info.interleave_mode = interleave_mode; - pvt->info.show_interleave_mode = show_interleave_mode; pvt->info.dram_attr = dram_attr; pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule); pvt->info.interleave_list = ibridge_interleave_list; @@ -3323,7 +3301,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.rir_limit = NULL; pvt->info.sad_limit = knl_sad_limit; pvt->info.interleave_mode = knl_interleave_mode; - pvt->info.show_interleave_mode = knl_show_interleave_mode; pvt->info.dram_attr = dram_attr_knl; pvt->info.max_sad = ARRAY_SIZE(knl_dram_rule); pvt->info.interleave_list = knl_interleave_list; diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c index 79ef675e4d6f..1159dba4671f 100644 --- a/drivers/edac/skx_edac.c +++ b/drivers/edac/skx_edac.c @@ -1007,7 +1007,8 @@ static int skx_mce_check_error(struct notifier_block *nb, unsigned long val, } static struct notifier_block skx_mce_dec = { - .notifier_call = skx_mce_check_error, + .notifier_call = skx_mce_check_error, + .priority = MCE_PRIO_EDAC, }; static void skx_remove(void) diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c index f853ad2c4ca0..1027d7b44358 100644 --- a/drivers/firmware/efi/arm-init.c +++ b/drivers/firmware/efi/arm-init.c @@ -250,7 +250,6 @@ void __init efi_init(void) } reserve_regions(); - efi_memattr_init(); efi_esrt_init(); efi_memmap_unmap(); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 92914801e388..e7d404059b73 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -529,6 +529,8 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, } } + efi_memattr_init(); + /* Parse the EFI Properties table if it exists */ if (efi.properties_table != EFI_INVALID_TABLE_ADDR) { efi_properties_table_t *tbl; diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c index 14914074f716..08b026864d4e 100644 --- a/drivers/firmware/efi/esrt.c +++ b/drivers/firmware/efi/esrt.c @@ -269,7 +269,7 @@ void __init efi_esrt_init(void) max -= efi.esrt; if (max < size) { - pr_err("ESRT header doen't fit on single memory map entry. (size: %zu max: %zu)\n", + pr_err("ESRT header doesn't fit on single memory map entry. (size: %zu max: %zu)\n", size, max); return; } diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index d564d25df8ab..f7425960f6a5 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -11,7 +11,7 @@ cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ -O2 \ -mno-mmx -mno-sse cflags-$(CONFIG_ARM64) := $(subst -pg,,$(KBUILD_CFLAGS)) -cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) -g0 \ +cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \ -fno-builtin -fpic -mno-single-pic-base cflags-$(CONFIG_EFI_ARMSTUB) += -I$(srctree)/scripts/dtc/libfdt @@ -28,7 +28,7 @@ OBJECT_FILES_NON_STANDARD := y # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n -lib-y := efi-stub-helper.o gop.o +lib-y := efi-stub-helper.o gop.o secureboot.o # include the stub's generic dependencies from lib/ when building for ARM/arm64 arm-deps := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c sort.c @@ -60,7 +60,7 @@ CFLAGS_arm64-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) extra-$(CONFIG_EFI_ARMSTUB) := $(lib-y) lib-$(CONFIG_EFI_ARMSTUB) := $(patsubst %.o,%.stub.o,$(lib-y)) -STUBCOPY_FLAGS-y := -R .debug* -R *ksymtab* -R *kcrctab* +STUBCOPY_RM-y := -R *ksymtab* -R *kcrctab* STUBCOPY_FLAGS-$(CONFIG_ARM64) += --prefix-alloc-sections=.init \ --prefix-symbols=__efistub_ STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS @@ -68,17 +68,25 @@ STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS $(obj)/%.stub.o: $(obj)/%.o FORCE $(call if_changed,stubcopy) +# +# Strip debug sections and some other sections that may legally contain +# absolute relocations, so that we can inspect the remaining sections for +# such relocations. If none are found, regenerate the output object, but +# this time, use objcopy and leave all sections in place. +# quiet_cmd_stubcopy = STUBCPY $@ - cmd_stubcopy = if $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@; then \ - $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y) \ - && (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \ - rm -f $@; /bin/false); else /bin/false; fi + cmd_stubcopy = if $(STRIP) --strip-debug $(STUBCOPY_RM-y) -o $@ $<; \ + then if $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y); \ + then (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \ + rm -f $@; /bin/false); \ + else $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@; fi \ + else /bin/false; fi # # ARM discards the .data section because it disallows r/w data in the # decompressor. So move our .data to .data.efistub, which is preserved # explicitly by the decompressor linker script. # -STUBCOPY_FLAGS-$(CONFIG_ARM) += --rename-section .data=.data.efistub \ - -R ___ksymtab+sort -R ___kcrctab+sort +STUBCOPY_FLAGS-$(CONFIG_ARM) += --rename-section .data=.data.efistub +STUBCOPY_RM-$(CONFIG_ARM) += -R ___ksymtab+sort -R ___kcrctab+sort STUBCOPY_RELOC-$(CONFIG_ARM) := R_ARM_ABS diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index b4f7d78f9e8b..d4056c6be1ec 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -20,52 +20,6 @@ bool __nokaslr; -static int efi_get_secureboot(efi_system_table_t *sys_table_arg) -{ - static efi_char16_t const sb_var_name[] = { - 'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0 }; - static efi_char16_t const sm_var_name[] = { - 'S', 'e', 't', 'u', 'p', 'M', 'o', 'd', 'e', 0 }; - - efi_guid_t var_guid = EFI_GLOBAL_VARIABLE_GUID; - efi_get_variable_t *f_getvar = sys_table_arg->runtime->get_variable; - u8 val; - unsigned long size = sizeof(val); - efi_status_t status; - - status = f_getvar((efi_char16_t *)sb_var_name, (efi_guid_t *)&var_guid, - NULL, &size, &val); - - if (status != EFI_SUCCESS) - goto out_efi_err; - - if (val == 0) - return 0; - - status = f_getvar((efi_char16_t *)sm_var_name, (efi_guid_t *)&var_guid, - NULL, &size, &val); - - if (status != EFI_SUCCESS) - goto out_efi_err; - - if (val == 1) - return 0; - - return 1; - -out_efi_err: - switch (status) { - case EFI_NOT_FOUND: - return 0; - case EFI_DEVICE_ERROR: - return -EIO; - case EFI_SECURITY_VIOLATION: - return -EACCES; - default: - return -EINVAL; - } -} - efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image, void **__fh) { @@ -91,75 +45,6 @@ efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, return status; } -efi_status_t efi_file_close(void *handle) -{ - efi_file_handle_t *fh = handle; - - return fh->close(handle); -} - -efi_status_t -efi_file_read(void *handle, unsigned long *size, void *addr) -{ - efi_file_handle_t *fh = handle; - - return fh->read(handle, size, addr); -} - - -efi_status_t -efi_file_size(efi_system_table_t *sys_table_arg, void *__fh, - efi_char16_t *filename_16, void **handle, u64 *file_sz) -{ - efi_file_handle_t *h, *fh = __fh; - efi_file_info_t *info; - efi_status_t status; - efi_guid_t info_guid = EFI_FILE_INFO_ID; - unsigned long info_sz; - - status = fh->open(fh, &h, filename_16, EFI_FILE_MODE_READ, (u64)0); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to open file: "); - efi_char16_printk(sys_table_arg, filename_16); - efi_printk(sys_table_arg, "\n"); - return status; - } - - *handle = h; - - info_sz = 0; - status = h->get_info(h, &info_guid, &info_sz, NULL); - if (status != EFI_BUFFER_TOO_SMALL) { - efi_printk(sys_table_arg, "Failed to get file info size\n"); - return status; - } - -grow: - status = sys_table_arg->boottime->allocate_pool(EFI_LOADER_DATA, - info_sz, (void **)&info); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to alloc mem for file info\n"); - return status; - } - - status = h->get_info(h, &info_guid, &info_sz, - info); - if (status == EFI_BUFFER_TOO_SMALL) { - sys_table_arg->boottime->free_pool(info); - goto grow; - } - - *file_sz = info->file_size; - sys_table_arg->boottime->free_pool(info); - - if (status != EFI_SUCCESS) - efi_printk(sys_table_arg, "Failed to get initrd info\n"); - - return status; -} - - - void efi_char16_printk(efi_system_table_t *sys_table_arg, efi_char16_t *str) { @@ -226,7 +111,7 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, efi_guid_t loaded_image_proto = LOADED_IMAGE_PROTOCOL_GUID; unsigned long reserve_addr = 0; unsigned long reserve_size = 0; - int secure_boot = 0; + enum efi_secureboot_mode secure_boot; struct screen_info *si; /* Check if we were booted by the EFI firmware */ @@ -296,19 +181,14 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, pr_efi_err(sys_table, "Failed to parse EFI cmdline options\n"); secure_boot = efi_get_secureboot(sys_table); - if (secure_boot > 0) - pr_efi(sys_table, "UEFI Secure Boot is enabled.\n"); - - if (secure_boot < 0) { - pr_efi_err(sys_table, - "could not determine UEFI Secure Boot status.\n"); - } /* - * Unauthenticated device tree data is a security hazard, so - * ignore 'dtb=' unless UEFI Secure Boot is disabled. + * Unauthenticated device tree data is a security hazard, so ignore + * 'dtb=' unless UEFI Secure Boot is disabled. We assume that secure + * boot is enabled if we can't determine its state. */ - if (secure_boot != 0 && strstr(cmdline_ptr, "dtb=")) { + if (secure_boot != efi_secureboot_mode_disabled && + strstr(cmdline_ptr, "dtb=")) { pr_efi(sys_table, "Ignoring DTB from command line.\n"); } else { status = handle_cmdline_files(sys_table, image, cmdline_ptr, diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 757badc1debb..919822b7773d 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -338,6 +338,69 @@ void efi_free(efi_system_table_t *sys_table_arg, unsigned long size, efi_call_early(free_pages, addr, nr_pages); } +static efi_status_t efi_file_size(efi_system_table_t *sys_table_arg, void *__fh, + efi_char16_t *filename_16, void **handle, + u64 *file_sz) +{ + efi_file_handle_t *h, *fh = __fh; + efi_file_info_t *info; + efi_status_t status; + efi_guid_t info_guid = EFI_FILE_INFO_ID; + unsigned long info_sz; + + status = efi_call_proto(efi_file_handle, open, fh, &h, filename_16, + EFI_FILE_MODE_READ, (u64)0); + if (status != EFI_SUCCESS) { + efi_printk(sys_table_arg, "Failed to open file: "); + efi_char16_printk(sys_table_arg, filename_16); + efi_printk(sys_table_arg, "\n"); + return status; + } + + *handle = h; + + info_sz = 0; + status = efi_call_proto(efi_file_handle, get_info, h, &info_guid, + &info_sz, NULL); + if (status != EFI_BUFFER_TOO_SMALL) { + efi_printk(sys_table_arg, "Failed to get file info size\n"); + return status; + } + +grow: + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + info_sz, (void **)&info); + if (status != EFI_SUCCESS) { + efi_printk(sys_table_arg, "Failed to alloc mem for file info\n"); + return status; + } + + status = efi_call_proto(efi_file_handle, get_info, h, &info_guid, + &info_sz, info); + if (status == EFI_BUFFER_TOO_SMALL) { + efi_call_early(free_pool, info); + goto grow; + } + + *file_sz = info->file_size; + efi_call_early(free_pool, info); + + if (status != EFI_SUCCESS) + efi_printk(sys_table_arg, "Failed to get initrd info\n"); + + return status; +} + +static efi_status_t efi_file_read(void *handle, unsigned long *size, void *addr) +{ + return efi_call_proto(efi_file_handle, read, handle, size, addr); +} + +static efi_status_t efi_file_close(void *handle) +{ + return efi_call_proto(efi_file_handle, close, handle); +} + /* * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi= * option, e.g. efi=nochunk. @@ -351,6 +414,14 @@ efi_status_t efi_parse_options(char *cmdline) char *str; /* + * Currently, the only efi= option we look for is 'nochunk', which + * is intended to work around known issues on certain x86 UEFI + * versions. So ignore for now on other architectures. + */ + if (!IS_ENABLED(CONFIG_X86)) + return EFI_SUCCESS; + + /* * If no EFI parameters were specified on the cmdline we've got * nothing to do. */ @@ -523,7 +594,8 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, size = files[j].size; while (size) { unsigned long chunksize; - if (size > __chunk_size) + + if (IS_ENABLED(CONFIG_X86) && size > __chunk_size) chunksize = __chunk_size; else chunksize = size; diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 0e2a96b12cb3..71c4d0e3c4ed 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -29,14 +29,6 @@ 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); -efi_status_t efi_file_size(efi_system_table_t *sys_table_arg, void *__fh, - efi_char16_t *filename_16, void **handle, - u64 *file_sz); - -efi_status_t efi_file_read(void *handle, unsigned long *size, void *addr); - -efi_status_t efi_file_close(void *handle); - 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/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c new file mode 100644 index 000000000000..6def402bf569 --- /dev/null +++ b/drivers/firmware/efi/libstub/secureboot.c @@ -0,0 +1,84 @@ +/* + * Secure boot handling. + * + * Copyright (C) 2013,2014 Linaro Limited + * Roy Franz <roy.franz@linaro.org + * Copyright (C) 2013 Red Hat, Inc. + * Mark Salter <msalter@redhat.com> + * + * This file is part of the Linux kernel, and is made available under the + * terms of the GNU General Public License version 2. + */ +#include <linux/efi.h> +#include <asm/efi.h> + +/* BIOS variables */ +static const efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID; +static const efi_char16_t const efi_SecureBoot_name[] = { + 'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0 +}; +static const efi_char16_t const efi_SetupMode_name[] = { + 'S', 'e', 't', 'u', 'p', 'M', 'o', 'd', 'e', 0 +}; + +/* SHIM variables */ +static const efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID; +static efi_char16_t const shim_MokSBState_name[] = { + 'M', 'o', 'k', 'S', 'B', 'S', 't', 'a', 't', 'e', 0 +}; + +#define get_efi_var(name, vendor, ...) \ + efi_call_runtime(get_variable, \ + (efi_char16_t *)(name), (efi_guid_t *)(vendor), \ + __VA_ARGS__); + +/* + * Determine whether we're in secure boot mode. + */ +enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg) +{ + u32 attr; + u8 secboot, setupmode, moksbstate; + unsigned long size; + efi_status_t status; + + size = sizeof(secboot); + status = get_efi_var(efi_SecureBoot_name, &efi_variable_guid, + NULL, &size, &secboot); + if (status != EFI_SUCCESS) + goto out_efi_err; + + size = sizeof(setupmode); + status = get_efi_var(efi_SetupMode_name, &efi_variable_guid, + NULL, &size, &setupmode); + if (status != EFI_SUCCESS) + goto out_efi_err; + + if (secboot == 0 || setupmode == 1) + return efi_secureboot_mode_disabled; + + /* + * See if a user has put the shim into insecure mode. If so, and if the + * variable doesn't have the runtime attribute set, we might as well + * honor that. + */ + size = sizeof(moksbstate); + status = get_efi_var(shim_MokSBState_name, &shim_guid, + &attr, &size, &moksbstate); + + /* If it fails, we don't care why. Default to secure */ + if (status != EFI_SUCCESS) + goto secure_boot_enabled; + if (!(attr & EFI_VARIABLE_RUNTIME_ACCESS) && moksbstate == 1) + return efi_secureboot_mode_disabled; + +secure_boot_enabled: + pr_efi(sys_table_arg, "UEFI Secure Boot is enabled.\n"); + return efi_secureboot_mode_enabled; + +out_efi_err: + pr_efi_err(sys_table_arg, "Could not determine UEFI Secure Boot status.\n"); + if (status == EFI_NOT_FOUND) + return efi_secureboot_mode_disabled; + return efi_secureboot_mode_unknown; +} diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c index 236004b9a50d..8986757eafaf 100644 --- a/drivers/firmware/efi/memattr.c +++ b/drivers/firmware/efi/memattr.c @@ -43,6 +43,7 @@ int __init efi_memattr_init(void) tbl_size = sizeof(*tbl) + tbl->num_entries * tbl->desc_size; memblock_reserve(efi.mem_attr_table, tbl_size); + set_bit(EFI_MEM_ATTR, &efi.flags); unmap: early_memunmap(tbl, sizeof(*tbl)); @@ -174,8 +175,11 @@ int __init efi_memattr_apply_permissions(struct mm_struct *mm, md.phys_addr + size - 1, efi_md_typeattr_format(buf, sizeof(buf), &md)); - if (valid) + if (valid) { ret = fn(mm, &md); + if (ret) + pr_err("Error updating mappings, skipping subsequent md's\n"); + } } memunmap(tbl); return ret; diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index aa644487749c..f59771da52ee 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1817,7 +1817,7 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) mgr->payloads[i].vcpi = req_payload.vcpi; } else if (mgr->payloads[i].num_slots) { mgr->payloads[i].num_slots = 0; - drm_dp_destroy_payload_step1(mgr, port, port->vcpi.vcpi, &mgr->payloads[i]); + drm_dp_destroy_payload_step1(mgr, port, mgr->payloads[i].vcpi, &mgr->payloads[i]); req_payload.payload_state = mgr->payloads[i].payload_state; mgr->payloads[i].start_slot = 0; } diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c index 1d6c335584ec..33cd51632721 100644 --- a/drivers/gpu/drm/drm_gem_cma_helper.c +++ b/drivers/gpu/drm/drm_gem_cma_helper.c @@ -376,7 +376,7 @@ void drm_gem_cma_describe(struct drm_gem_cma_object *cma_obj, off = drm_vma_node_start(&obj->vma_node); seq_printf(m, "%2d (%2d) %08llx %pad %p %zu", - obj->name, obj->refcount.refcount.counter, + obj->name, kref_read(&obj->refcount), off, &cma_obj->paddr, cma_obj->vaddr, obj->size); seq_printf(m, "\n"); diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c index ffb2ab389d1d..6b68e9088436 100644 --- a/drivers/gpu/drm/drm_info.c +++ b/drivers/gpu/drm/drm_info.c @@ -118,7 +118,7 @@ static int drm_gem_one_name_info(int id, void *ptr, void *data) seq_printf(m, "%6d %8zd %7d %8d\n", obj->name, obj->size, obj->handle_count, - atomic_read(&obj->refcount.refcount)); + kref_read(&obj->refcount)); return 0; } diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c index 9f17085b1fdd..c6885a4911c0 100644 --- a/drivers/gpu/drm/drm_mode_object.c +++ b/drivers/gpu/drm/drm_mode_object.c @@ -159,7 +159,7 @@ EXPORT_SYMBOL(drm_mode_object_find); void drm_mode_object_unreference(struct drm_mode_object *obj) { if (obj->free_cb) { - DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, atomic_read(&obj->refcount.refcount)); + DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, kref_read(&obj->refcount)); kref_put(&obj->refcount, obj->free_cb); } } @@ -176,7 +176,7 @@ EXPORT_SYMBOL(drm_mode_object_unreference); void drm_mode_object_reference(struct drm_mode_object *obj) { if (obj->free_cb) { - DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, atomic_read(&obj->refcount.refcount)); + DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, kref_read(&obj->refcount)); kref_get(&obj->refcount); } } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 114dddbd297b..aa6e35ddc87f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -486,7 +486,7 @@ static void etnaviv_gem_describe(struct drm_gem_object *obj, struct seq_file *m) seq_printf(m, "%08x: %c %2d (%2d) %08lx %p %zd\n", etnaviv_obj->flags, is_active(etnaviv_obj) ? 'A' : 'I', - obj->name, obj->refcount.refcount.counter, + obj->name, kref_read(&obj->refcount), off, etnaviv_obj->vaddr, obj->size); rcu_read_lock(); diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h index 6a368de9d81e..ecfefb9d42e4 100644 --- a/drivers/gpu/drm/i915/i915_gem_object.h +++ b/drivers/gpu/drm/i915/i915_gem_object.h @@ -256,7 +256,7 @@ extern void drm_gem_object_unreference_unlocked(struct drm_gem_object *); static inline bool i915_gem_object_is_dead(const struct drm_i915_gem_object *obj) { - return atomic_read(&obj->base.refcount.refcount) == 0; + return kref_read(&obj->base.refcount) == 0; } static inline bool diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 8098677a3916..1974ccb781de 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -642,7 +642,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m) seq_printf(m, "%08x: %c %2d (%2d) %08llx %p\t", msm_obj->flags, is_active(msm_obj) ? 'A' : 'I', - obj->name, obj->refcount.refcount.counter, + obj->name, kref_read(&obj->refcount), off, msm_obj->vaddr); for (id = 0; id < priv->num_aspaces; id++) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index a6126c93f215..88ee60d1b907 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -527,7 +527,7 @@ static bool nouveau_fence_no_signaling(struct dma_fence *f) * caller should have a reference on the fence, * else fence could get freed here */ - WARN_ON(atomic_read(&fence->base.refcount.refcount) <= 1); + WARN_ON(kref_read(&fence->base.refcount) <= 1); /* * This needs uevents to work correctly, but dma_fence_add_callback relies on diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index 4a90c690f09e..74a9968df421 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -1033,7 +1033,7 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m) off = drm_vma_node_start(&obj->vma_node); seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d", - omap_obj->flags, obj->name, obj->refcount.refcount.counter, + omap_obj->flags, obj->name, kref_read(&obj->refcount), off, &omap_obj->paddr, omap_obj->paddr_cnt, omap_obj->vaddr, omap_obj->roll); diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c index fb16070b266e..4a4f9533c53b 100644 --- a/drivers/gpu/drm/radeon/radeon_cursor.c +++ b/drivers/gpu/drm/radeon/radeon_cursor.c @@ -205,8 +205,8 @@ static int radeon_cursor_move_locked(struct drm_crtc *crtc, int x, int y) } if (x <= (crtc->x - w) || y <= (crtc->y - radeon_crtc->cursor_height) || - x >= (crtc->x + crtc->mode.crtc_hdisplay) || - y >= (crtc->y + crtc->mode.crtc_vdisplay)) + x >= (crtc->x + crtc->mode.hdisplay) || + y >= (crtc->y + crtc->mode.vdisplay)) goto out_of_bounds; x += xorigin; diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index d5063618efa7..ffc6cb55c78c 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -140,8 +140,8 @@ static void ttm_bo_release_list(struct kref *list_kref) struct ttm_bo_device *bdev = bo->bdev; size_t acc_size = bo->acc_size; - BUG_ON(atomic_read(&bo->list_kref.refcount)); - BUG_ON(atomic_read(&bo->kref.refcount)); + BUG_ON(kref_read(&bo->list_kref)); + BUG_ON(kref_read(&bo->kref)); BUG_ON(atomic_read(&bo->cpu_writers)); BUG_ON(bo->mem.mm_node != NULL); BUG_ON(!list_empty(&bo->lru)); @@ -181,61 +181,46 @@ void ttm_bo_add_to_lru(struct ttm_buffer_object *bo) } EXPORT_SYMBOL(ttm_bo_add_to_lru); -int ttm_bo_del_from_lru(struct ttm_buffer_object *bo) +static void ttm_bo_ref_bug(struct kref *list_kref) +{ + BUG(); +} + +void ttm_bo_del_from_lru(struct ttm_buffer_object *bo) { struct ttm_bo_device *bdev = bo->bdev; - int put_count = 0; if (bdev->driver->lru_removal) bdev->driver->lru_removal(bo); if (!list_empty(&bo->swap)) { list_del_init(&bo->swap); - ++put_count; + kref_put(&bo->list_kref, ttm_bo_ref_bug); } if (!list_empty(&bo->lru)) { list_del_init(&bo->lru); - ++put_count; + kref_put(&bo->list_kref, ttm_bo_ref_bug); } - - return put_count; -} - -static void ttm_bo_ref_bug(struct kref *list_kref) -{ - BUG(); -} - -void ttm_bo_list_ref_sub(struct ttm_buffer_object *bo, int count, - bool never_free) -{ - kref_sub(&bo->list_kref, count, - (never_free) ? ttm_bo_ref_bug : ttm_bo_release_list); } void ttm_bo_del_sub_from_lru(struct ttm_buffer_object *bo) { - int put_count; - spin_lock(&bo->glob->lru_lock); - put_count = ttm_bo_del_from_lru(bo); + ttm_bo_del_from_lru(bo); spin_unlock(&bo->glob->lru_lock); - ttm_bo_list_ref_sub(bo, put_count, true); } EXPORT_SYMBOL(ttm_bo_del_sub_from_lru); void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo) { struct ttm_bo_device *bdev = bo->bdev; - int put_count = 0; lockdep_assert_held(&bo->resv->lock.base); if (bdev->driver->lru_removal) bdev->driver->lru_removal(bo); - put_count = ttm_bo_del_from_lru(bo); - ttm_bo_list_ref_sub(bo, put_count, true); + ttm_bo_del_from_lru(bo); ttm_bo_add_to_lru(bo); } EXPORT_SYMBOL(ttm_bo_move_to_lru_tail); @@ -447,7 +432,6 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo) { struct ttm_bo_device *bdev = bo->bdev; struct ttm_bo_global *glob = bo->glob; - int put_count; int ret; spin_lock(&glob->lru_lock); @@ -455,13 +439,10 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo) if (!ret) { if (!ttm_bo_wait(bo, false, true)) { - put_count = ttm_bo_del_from_lru(bo); - + ttm_bo_del_from_lru(bo); spin_unlock(&glob->lru_lock); ttm_bo_cleanup_memtype_use(bo); - ttm_bo_list_ref_sub(bo, put_count, true); - return; } else ttm_bo_flush_all_fences(bo); @@ -504,7 +485,6 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo, bool no_wait_gpu) { struct ttm_bo_global *glob = bo->glob; - int put_count; int ret; ret = ttm_bo_wait(bo, false, true); @@ -554,15 +534,13 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo, return ret; } - put_count = ttm_bo_del_from_lru(bo); + ttm_bo_del_from_lru(bo); list_del_init(&bo->ddestroy); - ++put_count; + kref_put(&bo->list_kref, ttm_bo_ref_bug); spin_unlock(&glob->lru_lock); ttm_bo_cleanup_memtype_use(bo); - ttm_bo_list_ref_sub(bo, put_count, true); - return 0; } @@ -740,7 +718,7 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev, struct ttm_bo_global *glob = bdev->glob; struct ttm_mem_type_manager *man = &bdev->man[mem_type]; struct ttm_buffer_object *bo; - int ret = -EBUSY, put_count; + int ret = -EBUSY; spin_lock(&glob->lru_lock); list_for_each_entry(bo, &man->lru, lru) { @@ -771,13 +749,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev, return ret; } - put_count = ttm_bo_del_from_lru(bo); + ttm_bo_del_from_lru(bo); spin_unlock(&glob->lru_lock); BUG_ON(ret != 0); - ttm_bo_list_ref_sub(bo, put_count, true); - ret = ttm_bo_evict(bo, interruptible, no_wait_gpu); ttm_bo_unreserve(bo); @@ -1669,7 +1645,6 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink) container_of(shrink, struct ttm_bo_global, shrink); struct ttm_buffer_object *bo; int ret = -EBUSY; - int put_count; uint32_t swap_placement = (TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM); spin_lock(&glob->lru_lock); @@ -1692,11 +1667,9 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink) return ret; } - put_count = ttm_bo_del_from_lru(bo); + ttm_bo_del_from_lru(bo); spin_unlock(&glob->lru_lock); - ttm_bo_list_ref_sub(bo, put_count, true); - /** * Move to system cached */ diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c index d35bc491e8de..5e1bcabffef5 100644 --- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c +++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c @@ -48,9 +48,7 @@ static void ttm_eu_del_from_lru_locked(struct list_head *list) list_for_each_entry(entry, list, head) { struct ttm_buffer_object *bo = entry->bo; - unsigned put_count = ttm_bo_del_from_lru(bo); - - ttm_bo_list_ref_sub(bo, put_count, true); + ttm_bo_del_from_lru(bo); } } diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c index 4f5fa8d65fe9..fdb451e3ec01 100644 --- a/drivers/gpu/drm/ttm/ttm_object.c +++ b/drivers/gpu/drm/ttm/ttm_object.c @@ -304,7 +304,7 @@ bool ttm_ref_object_exists(struct ttm_object_file *tfile, * Verify that the ref->obj pointer was actually valid! */ rmb(); - if (unlikely(atomic_read(&ref->kref.refcount) == 0)) + if (unlikely(kref_read(&ref->kref) == 0)) goto out_false; rcu_read_unlock(); diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 190d270b20a2..0649d53f3d16 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -1459,6 +1459,16 @@ config SENSORS_SCH5636 This driver can also be built as a module. If so, the module will be called sch5636. +config SENSORS_STTS751 + tristate "ST Microelectronics STTS751" + depends on I2C + help + If you say yes here you get support for STTS751 + temperature sensor chips. + + This driver can also be built as a module. If so, the module + will be called stts751. + config SENSORS_SMM665 tristate "Summit Microelectronics SMM665" depends on I2C diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index d2cb7e804a0f..5509edf6186a 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -148,6 +148,7 @@ obj-$(CONFIG_SENSORS_SMM665) += smm665.o obj-$(CONFIG_SENSORS_SMSC47B397)+= smsc47b397.o obj-$(CONFIG_SENSORS_SMSC47M1) += smsc47m1.o obj-$(CONFIG_SENSORS_SMSC47M192)+= smsc47m192.o +obj-$(CONFIG_SENSORS_STTS751) += stts751.o obj-$(CONFIG_SENSORS_AMC6821) += amc6821.o obj-$(CONFIG_SENSORS_TC74) += tc74.o obj-$(CONFIG_SENSORS_THMC50) += thmc50.o diff --git a/drivers/hwmon/adc128d818.c b/drivers/hwmon/adc128d818.c index ad2b47e40345..bbe3a5c5b3f5 100644 --- a/drivers/hwmon/adc128d818.c +++ b/drivers/hwmon/adc128d818.c @@ -28,6 +28,7 @@ #include <linux/regulator/consumer.h> #include <linux/mutex.h> #include <linux/bitops.h> +#include <linux/of.h> /* Addresses to scan * The chip also supports addresses 0x35..0x37. Don't scan those addresses @@ -58,15 +59,22 @@ static const unsigned short normal_i2c[] = { #define ADC128_REG_MAN_ID 0x3e #define ADC128_REG_DEV_ID 0x3f +/* No. of voltage entries in adc128_attrs */ +#define ADC128_ATTR_NUM_VOLT (8 * 4) + +/* Voltage inputs visible per operation mode */ +static const u8 num_inputs[] = { 7, 8, 4, 6 }; + struct adc128_data { struct i2c_client *client; struct regulator *regulator; int vref; /* Reference voltage in mV */ struct mutex update_lock; + u8 mode; /* Operation mode */ bool valid; /* true if following fields are valid */ unsigned long last_updated; /* In jiffies */ - u16 in[3][7]; /* Register value, normalized to 12 bit + u16 in[3][8]; /* Register value, normalized to 12 bit * 0: input voltage * 1: min limit * 2: max limit @@ -87,7 +95,7 @@ static struct adc128_data *adc128_update_device(struct device *dev) mutex_lock(&data->update_lock); if (time_after(jiffies, data->last_updated + HZ) || !data->valid) { - for (i = 0; i < 7; i++) { + for (i = 0; i < num_inputs[data->mode]; i++) { rv = i2c_smbus_read_word_swapped(client, ADC128_REG_IN(i)); if (rv < 0) @@ -107,20 +115,25 @@ static struct adc128_data *adc128_update_device(struct device *dev) data->in[2][i] = rv << 4; } - rv = i2c_smbus_read_word_swapped(client, ADC128_REG_TEMP); - if (rv < 0) - goto abort; - data->temp[0] = rv >> 7; + if (data->mode != 1) { + rv = i2c_smbus_read_word_swapped(client, + ADC128_REG_TEMP); + if (rv < 0) + goto abort; + data->temp[0] = rv >> 7; - rv = i2c_smbus_read_byte_data(client, ADC128_REG_TEMP_MAX); - if (rv < 0) - goto abort; - data->temp[1] = rv << 1; + rv = i2c_smbus_read_byte_data(client, + ADC128_REG_TEMP_MAX); + if (rv < 0) + goto abort; + data->temp[1] = rv << 1; - rv = i2c_smbus_read_byte_data(client, ADC128_REG_TEMP_HYST); - if (rv < 0) - goto abort; - data->temp[2] = rv << 1; + rv = i2c_smbus_read_byte_data(client, + ADC128_REG_TEMP_HYST); + if (rv < 0) + goto abort; + data->temp[2] = rv << 1; + } rv = i2c_smbus_read_byte_data(client, ADC128_REG_ALARM); if (rv < 0) @@ -240,6 +253,25 @@ static ssize_t adc128_show_alarm(struct device *dev, return sprintf(buf, "%u\n", !!(alarms & mask)); } +static umode_t adc128_is_visible(struct kobject *kobj, + struct attribute *attr, int index) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct adc128_data *data = dev_get_drvdata(dev); + + if (index < ADC128_ATTR_NUM_VOLT) { + /* Voltage, visible according to num_inputs[] */ + if (index >= num_inputs[data->mode] * 4) + return 0; + } else { + /* Temperature, visible if not in mode 1 */ + if (data->mode == 1) + return 0; + } + + return attr->mode; +} + static SENSOR_DEVICE_ATTR_2(in0_input, S_IRUGO, adc128_show_in, NULL, 0, 0); static SENSOR_DEVICE_ATTR_2(in0_min, S_IWUSR | S_IRUGO, @@ -289,6 +321,13 @@ static SENSOR_DEVICE_ATTR_2(in6_min, S_IWUSR | S_IRUGO, static SENSOR_DEVICE_ATTR_2(in6_max, S_IWUSR | S_IRUGO, adc128_show_in, adc128_set_in, 6, 2); +static SENSOR_DEVICE_ATTR_2(in7_input, S_IRUGO, + adc128_show_in, NULL, 7, 0); +static SENSOR_DEVICE_ATTR_2(in7_min, S_IWUSR | S_IRUGO, + adc128_show_in, adc128_set_in, 7, 1); +static SENSOR_DEVICE_ATTR_2(in7_max, S_IWUSR | S_IRUGO, + adc128_show_in, adc128_set_in, 7, 2); + static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, adc128_show_temp, NULL, 0); static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, adc128_show_temp, adc128_set_temp, 1); @@ -302,44 +341,54 @@ static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, adc128_show_alarm, NULL, 3); static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, adc128_show_alarm, NULL, 4); static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, adc128_show_alarm, NULL, 5); static SENSOR_DEVICE_ATTR(in6_alarm, S_IRUGO, adc128_show_alarm, NULL, 6); +static SENSOR_DEVICE_ATTR(in7_alarm, S_IRUGO, adc128_show_alarm, NULL, 7); static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, adc128_show_alarm, NULL, 7); static struct attribute *adc128_attrs[] = { - &sensor_dev_attr_in0_min.dev_attr.attr, - &sensor_dev_attr_in1_min.dev_attr.attr, - &sensor_dev_attr_in2_min.dev_attr.attr, - &sensor_dev_attr_in3_min.dev_attr.attr, - &sensor_dev_attr_in4_min.dev_attr.attr, - &sensor_dev_attr_in5_min.dev_attr.attr, - &sensor_dev_attr_in6_min.dev_attr.attr, - &sensor_dev_attr_in0_max.dev_attr.attr, - &sensor_dev_attr_in1_max.dev_attr.attr, - &sensor_dev_attr_in2_max.dev_attr.attr, - &sensor_dev_attr_in3_max.dev_attr.attr, - &sensor_dev_attr_in4_max.dev_attr.attr, - &sensor_dev_attr_in5_max.dev_attr.attr, - &sensor_dev_attr_in6_max.dev_attr.attr, + &sensor_dev_attr_in0_alarm.dev_attr.attr, &sensor_dev_attr_in0_input.dev_attr.attr, + &sensor_dev_attr_in0_max.dev_attr.attr, + &sensor_dev_attr_in0_min.dev_attr.attr, + &sensor_dev_attr_in1_alarm.dev_attr.attr, &sensor_dev_attr_in1_input.dev_attr.attr, + &sensor_dev_attr_in1_max.dev_attr.attr, + &sensor_dev_attr_in1_min.dev_attr.attr, + &sensor_dev_attr_in2_alarm.dev_attr.attr, &sensor_dev_attr_in2_input.dev_attr.attr, + &sensor_dev_attr_in2_max.dev_attr.attr, + &sensor_dev_attr_in2_min.dev_attr.attr, + &sensor_dev_attr_in3_alarm.dev_attr.attr, &sensor_dev_attr_in3_input.dev_attr.attr, + &sensor_dev_attr_in3_max.dev_attr.attr, + &sensor_dev_attr_in3_min.dev_attr.attr, + &sensor_dev_attr_in4_alarm.dev_attr.attr, &sensor_dev_attr_in4_input.dev_attr.attr, + &sensor_dev_attr_in4_max.dev_attr.attr, + &sensor_dev_attr_in4_min.dev_attr.attr, + &sensor_dev_attr_in5_alarm.dev_attr.attr, &sensor_dev_attr_in5_input.dev_attr.attr, + &sensor_dev_attr_in5_max.dev_attr.attr, + &sensor_dev_attr_in5_min.dev_attr.attr, + &sensor_dev_attr_in6_alarm.dev_attr.attr, &sensor_dev_attr_in6_input.dev_attr.attr, + &sensor_dev_attr_in6_max.dev_attr.attr, + &sensor_dev_attr_in6_min.dev_attr.attr, + &sensor_dev_attr_in7_alarm.dev_attr.attr, + &sensor_dev_attr_in7_input.dev_attr.attr, + &sensor_dev_attr_in7_max.dev_attr.attr, + &sensor_dev_attr_in7_min.dev_attr.attr, &sensor_dev_attr_temp1_input.dev_attr.attr, &sensor_dev_attr_temp1_max.dev_attr.attr, - &sensor_dev_attr_temp1_max_hyst.dev_attr.attr, - &sensor_dev_attr_in0_alarm.dev_attr.attr, - &sensor_dev_attr_in1_alarm.dev_attr.attr, - &sensor_dev_attr_in2_alarm.dev_attr.attr, - &sensor_dev_attr_in3_alarm.dev_attr.attr, - &sensor_dev_attr_in4_alarm.dev_attr.attr, - &sensor_dev_attr_in5_alarm.dev_attr.attr, - &sensor_dev_attr_in6_alarm.dev_attr.attr, &sensor_dev_attr_temp1_max_alarm.dev_attr.attr, + &sensor_dev_attr_temp1_max_hyst.dev_attr.attr, NULL }; -ATTRIBUTE_GROUPS(adc128); + +static struct attribute_group adc128_group = { + .attrs = adc128_attrs, + .is_visible = adc128_is_visible, +}; +__ATTRIBUTE_GROUPS(adc128); static int adc128_detect(struct i2c_client *client, struct i2c_board_info *info) { @@ -387,6 +436,15 @@ static int adc128_init_client(struct adc128_data *data) if (err) return err; + /* Set operation mode, if non-default */ + if (data->mode != 0) { + err = i2c_smbus_write_byte_data(client, + ADC128_REG_CONFIG_ADV, + data->mode << 1); + if (err) + return err; + } + /* Start monitoring */ err = i2c_smbus_write_byte_data(client, ADC128_REG_CONFIG, 0x01); if (err) @@ -433,6 +491,21 @@ static int adc128_probe(struct i2c_client *client, data->vref = 2560; /* 2.56V, in mV */ } + /* Operation mode is optional. If unspecified, keep current mode */ + if (of_property_read_u8(dev->of_node, "ti,mode", &data->mode) == 0) { + if (data->mode > 3) { + dev_err(dev, "invalid operation mode %d\n", + data->mode); + err = -EINVAL; + goto error; + } + } else { + err = i2c_smbus_read_byte_data(client, ADC128_REG_CONFIG_ADV); + if (err < 0) + goto error; + data->mode = (err >> 1) & ADC128_REG_MASK; + } + data->client = client; i2c_set_clientdata(client, data); mutex_init(&data->update_lock); diff --git a/drivers/hwmon/adm1021.c b/drivers/hwmon/adm1021.c index 1fdcc3e703b9..eacf10fadbc6 100644 --- a/drivers/hwmon/adm1021.c +++ b/drivers/hwmon/adm1021.c @@ -191,7 +191,7 @@ static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%u\n", (data->alarms >> index) & 1); } -static ssize_t show_alarms(struct device *dev, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -251,16 +251,16 @@ static ssize_t set_temp_min(struct device *dev, return count; } -static ssize_t show_low_power(struct device *dev, +static ssize_t low_power_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct adm1021_data *data = adm1021_update_device(dev); return sprintf(buf, "%d\n", data->low_power); } -static ssize_t set_low_power(struct device *dev, - struct device_attribute *devattr, - const char *buf, size_t count) +static ssize_t low_power_store(struct device *dev, + struct device_attribute *devattr, + const char *buf, size_t count) { struct adm1021_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -303,8 +303,8 @@ static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 4); static SENSOR_DEVICE_ATTR(temp2_min_alarm, S_IRUGO, show_alarm, NULL, 3); static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 2); -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); -static DEVICE_ATTR(low_power, S_IWUSR | S_IRUGO, show_low_power, set_low_power); +static DEVICE_ATTR_RO(alarms); +static DEVICE_ATTR_RW(low_power); static struct attribute *adm1021_attributes[] = { &sensor_dev_attr_temp1_max.dev_attr.attr, diff --git a/drivers/hwmon/adm1025.c b/drivers/hwmon/adm1025.c index 1abb4609b412..1e4dad36f5ef 100644 --- a/drivers/hwmon/adm1025.c +++ b/drivers/hwmon/adm1025.c @@ -333,12 +333,12 @@ set_temp(1); set_temp(2); static ssize_t -show_alarms(struct device *dev, struct device_attribute *attr, char *buf) +alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct adm1025_data *data = adm1025_update_device(dev); return sprintf(buf, "%u\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) @@ -358,21 +358,21 @@ static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 4); static SENSOR_DEVICE_ATTR(temp1_fault, S_IRUGO, show_alarm, NULL, 14); static ssize_t -show_vid(struct device *dev, struct device_attribute *attr, char *buf) +cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct adm1025_data *data = adm1025_update_device(dev); return sprintf(buf, "%u\n", vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); static ssize_t -show_vrm(struct device *dev, struct device_attribute *attr, char *buf) +vrm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct adm1025_data *data = dev_get_drvdata(dev); return sprintf(buf, "%u\n", data->vrm); } -static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct adm1025_data *data = dev_get_drvdata(dev); unsigned long val; @@ -388,7 +388,7 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, data->vrm = val; return count; } -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm); +static DEVICE_ATTR_RW(vrm); /* * Real code diff --git a/drivers/hwmon/adm1026.c b/drivers/hwmon/adm1026.c index b2a5d9e5c590..e43f09a07cd0 100644 --- a/drivers/hwmon/adm1026.c +++ b/drivers/hwmon/adm1026.c @@ -1034,15 +1034,15 @@ temp_crit_reg(1); temp_crit_reg(2); temp_crit_reg(3); -static ssize_t show_analog_out_reg(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t analog_out_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct adm1026_data *data = adm1026_update_device(dev); return sprintf(buf, "%d\n", DAC_FROM_REG(data->analog_out)); } -static ssize_t set_analog_out_reg(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t analog_out_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct adm1026_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -1060,11 +1060,10 @@ static ssize_t set_analog_out_reg(struct device *dev, return count; } -static DEVICE_ATTR(analog_out, S_IRUGO | S_IWUSR, show_analog_out_reg, - set_analog_out_reg); +static DEVICE_ATTR_RW(analog_out); -static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct adm1026_data *data = adm1026_update_device(dev); int vid = (data->gpio >> 11) & 0x1f; @@ -1073,17 +1072,17 @@ static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%d\n", vid_from_reg(vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL); +static DEVICE_ATTR_RO(cpu0_vid); -static ssize_t show_vrm_reg(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t vrm_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct adm1026_data *data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", data->vrm); } -static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct adm1026_data *data = dev_get_drvdata(dev); unsigned long val; @@ -1100,16 +1099,16 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg); +static DEVICE_ATTR_RW(vrm); -static ssize_t show_alarms_reg(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct adm1026_data *data = adm1026_update_device(dev); return sprintf(buf, "%ld\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) @@ -1148,14 +1147,15 @@ static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 24); static SENSOR_DEVICE_ATTR(in10_alarm, S_IRUGO, show_alarm, NULL, 25); static SENSOR_DEVICE_ATTR(in8_alarm, S_IRUGO, show_alarm, NULL, 26); -static ssize_t show_alarm_mask(struct device *dev, +static ssize_t alarm_mask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct adm1026_data *data = adm1026_update_device(dev); return sprintf(buf, "%ld\n", data->alarm_mask); } -static ssize_t set_alarm_mask(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t alarm_mask_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct adm1026_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -1186,18 +1186,17 @@ static ssize_t set_alarm_mask(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(alarm_mask, S_IRUGO | S_IWUSR, show_alarm_mask, - set_alarm_mask); +static DEVICE_ATTR_RW(alarm_mask); -static ssize_t show_gpio(struct device *dev, struct device_attribute *attr, +static ssize_t gpio_show(struct device *dev, struct device_attribute *attr, char *buf) { struct adm1026_data *data = adm1026_update_device(dev); return sprintf(buf, "%ld\n", data->gpio); } -static ssize_t set_gpio(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t gpio_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct adm1026_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -1221,16 +1220,18 @@ static ssize_t set_gpio(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(gpio, S_IRUGO | S_IWUSR, show_gpio, set_gpio); +static DEVICE_ATTR_RW(gpio); -static ssize_t show_gpio_mask(struct device *dev, struct device_attribute *attr, +static ssize_t gpio_mask_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct adm1026_data *data = adm1026_update_device(dev); return sprintf(buf, "%ld\n", data->gpio_mask); } -static ssize_t set_gpio_mask(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t gpio_mask_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct adm1026_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -1254,17 +1255,17 @@ static ssize_t set_gpio_mask(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(gpio_mask, S_IRUGO | S_IWUSR, show_gpio_mask, set_gpio_mask); +static DEVICE_ATTR_RW(gpio_mask); -static ssize_t show_pwm_reg(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t pwm1_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct adm1026_data *data = adm1026_update_device(dev); return sprintf(buf, "%d\n", PWM_FROM_REG(data->pwm1.pwm)); } -static ssize_t set_pwm_reg(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct adm1026_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -1285,16 +1286,17 @@ static ssize_t set_pwm_reg(struct device *dev, struct device_attribute *attr, return count; } -static ssize_t show_auto_pwm_min(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t temp1_auto_point1_pwm_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct adm1026_data *data = adm1026_update_device(dev); return sprintf(buf, "%d\n", data->pwm1.auto_pwm_min); } -static ssize_t set_auto_pwm_min(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) +static ssize_t temp1_auto_point1_pwm_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct adm1026_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -1316,21 +1318,23 @@ static ssize_t set_auto_pwm_min(struct device *dev, return count; } -static ssize_t show_auto_pwm_max(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t temp1_auto_point2_pwm_show(struct device *dev, + struct device_attribute *attr, + char *buf) { return sprintf(buf, "%d\n", ADM1026_PWM_MAX); } -static ssize_t show_pwm_enable(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t pwm1_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct adm1026_data *data = adm1026_update_device(dev); return sprintf(buf, "%d\n", data->pwm1.enable); } -static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t pwm1_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct adm1026_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -1366,25 +1370,25 @@ static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr, } /* enable PWM fan control */ -static DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm_reg, set_pwm_reg); -static DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, show_pwm_reg, set_pwm_reg); -static DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, show_pwm_reg, set_pwm_reg); -static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, show_pwm_enable, - set_pwm_enable); -static DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR, show_pwm_enable, - set_pwm_enable); -static DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR, show_pwm_enable, - set_pwm_enable); -static DEVICE_ATTR(temp1_auto_point1_pwm, S_IRUGO | S_IWUSR, - show_auto_pwm_min, set_auto_pwm_min); +static DEVICE_ATTR_RW(pwm1); +static DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, pwm1_show, pwm1_store); +static DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, pwm1_show, pwm1_store); +static DEVICE_ATTR_RW(pwm1_enable); +static DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR, pwm1_enable_show, + pwm1_enable_store); +static DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR, pwm1_enable_show, + pwm1_enable_store); +static DEVICE_ATTR_RW(temp1_auto_point1_pwm); static DEVICE_ATTR(temp2_auto_point1_pwm, S_IRUGO | S_IWUSR, - show_auto_pwm_min, set_auto_pwm_min); + temp1_auto_point1_pwm_show, temp1_auto_point1_pwm_store); static DEVICE_ATTR(temp3_auto_point1_pwm, S_IRUGO | S_IWUSR, - show_auto_pwm_min, set_auto_pwm_min); + temp1_auto_point1_pwm_show, temp1_auto_point1_pwm_store); -static DEVICE_ATTR(temp1_auto_point2_pwm, S_IRUGO, show_auto_pwm_max, NULL); -static DEVICE_ATTR(temp2_auto_point2_pwm, S_IRUGO, show_auto_pwm_max, NULL); -static DEVICE_ATTR(temp3_auto_point2_pwm, S_IRUGO, show_auto_pwm_max, NULL); +static DEVICE_ATTR_RO(temp1_auto_point2_pwm); +static DEVICE_ATTR(temp2_auto_point2_pwm, S_IRUGO, temp1_auto_point2_pwm_show, + NULL); +static DEVICE_ATTR(temp3_auto_point2_pwm, S_IRUGO, temp1_auto_point2_pwm_show, + NULL); static struct attribute *adm1026_attributes[] = { &sensor_dev_attr_in0_input.dev_attr.attr, diff --git a/drivers/hwmon/adm1031.c b/drivers/hwmon/adm1031.c index a5818980dad7..bcf508269fd6 100644 --- a/drivers/hwmon/adm1031.c +++ b/drivers/hwmon/adm1031.c @@ -829,14 +829,14 @@ temp_reg(2); temp_reg(3); /* Alarms */ -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct adm1031_data *data = adm1031_update_device(dev); return sprintf(buf, "%d\n", data->alarm); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) @@ -867,7 +867,7 @@ static const unsigned int update_intervals[] = { 16000, 8000, 4000, 2000, 1000, 500, 250, 125, }; -static ssize_t show_update_interval(struct device *dev, +static ssize_t update_interval_show(struct device *dev, struct device_attribute *attr, char *buf) { struct adm1031_data *data = dev_get_drvdata(dev); @@ -875,9 +875,9 @@ static ssize_t show_update_interval(struct device *dev, return sprintf(buf, "%u\n", data->update_interval); } -static ssize_t set_update_interval(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t update_interval_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct adm1031_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -912,8 +912,7 @@ static ssize_t set_update_interval(struct device *dev, return count; } -static DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, show_update_interval, - set_update_interval); +static DEVICE_ATTR_RW(update_interval); static struct attribute *adm1031_attributes[] = { &sensor_dev_attr_fan1_input.dev_attr.attr, diff --git a/drivers/hwmon/adm9240.c b/drivers/hwmon/adm9240.c index 72bf2489511e..255413fdbde9 100644 --- a/drivers/hwmon/adm9240.c +++ b/drivers/hwmon/adm9240.c @@ -262,8 +262,8 @@ static struct adm9240_data *adm9240_update_device(struct device *dev) /*** sysfs accessors ***/ /* temperature */ -static ssize_t show_temp(struct device *dev, struct device_attribute *dummy, - char *buf) +static ssize_t temp1_input_show(struct device *dev, + struct device_attribute *dummy, char *buf) { struct adm9240_data *data = adm9240_update_device(dev); return sprintf(buf, "%d\n", data->temp / 128 * 500); /* 9-bit value */ @@ -298,7 +298,7 @@ static ssize_t set_max(struct device *dev, struct device_attribute *devattr, return count; } -static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL); +static DEVICE_ATTR_RO(temp1_input); static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_max, set_max, 0); static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IWUSR | S_IRUGO, @@ -501,13 +501,13 @@ fan(1); fan(2); /* alarms */ -static ssize_t show_alarms(struct device *dev, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct adm9240_data *data = adm9240_update_device(dev); return sprintf(buf, "%u\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) @@ -527,25 +527,25 @@ static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6); static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7); /* vid */ -static ssize_t show_vid(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct adm9240_data *data = adm9240_update_device(dev); return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); /* analog output */ -static ssize_t show_aout(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t aout_output_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct adm9240_data *data = adm9240_update_device(dev); return sprintf(buf, "%d\n", AOUT_FROM_REG(data->aout)); } -static ssize_t set_aout(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t aout_output_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct adm9240_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -562,7 +562,7 @@ static ssize_t set_aout(struct device *dev, mutex_unlock(&data->update_lock); return count; } -static DEVICE_ATTR(aout_output, S_IRUGO | S_IWUSR, show_aout, set_aout); +static DEVICE_ATTR_RW(aout_output); static ssize_t chassis_clear(struct device *dev, struct device_attribute *attr, diff --git a/drivers/hwmon/adt7411.c b/drivers/hwmon/adt7411.c index bdeaece9641d..b939f8a115ba 100644 --- a/drivers/hwmon/adt7411.c +++ b/drivers/hwmon/adt7411.c @@ -21,6 +21,21 @@ #include <linux/hwmon-sysfs.h> #include <linux/slab.h> +#define ADT7411_REG_STAT_1 0x00 +#define ADT7411_STAT_1_INT_TEMP_HIGH BIT(0) +#define ADT7411_STAT_1_INT_TEMP_LOW BIT(1) +#define ADT7411_STAT_1_EXT_TEMP_HIGH_AIN1 BIT(2) +#define ADT7411_STAT_1_EXT_TEMP_LOW BIT(3) +#define ADT7411_STAT_1_EXT_TEMP_FAULT BIT(4) +#define ADT7411_STAT_1_AIN2 BIT(5) +#define ADT7411_STAT_1_AIN3 BIT(6) +#define ADT7411_STAT_1_AIN4 BIT(7) +#define ADT7411_REG_STAT_2 0x01 +#define ADT7411_STAT_2_AIN5 BIT(0) +#define ADT7411_STAT_2_AIN6 BIT(1) +#define ADT7411_STAT_2_AIN7 BIT(2) +#define ADT7411_STAT_2_AIN8 BIT(3) +#define ADT7411_STAT_2_VDD BIT(4) #define ADT7411_REG_INT_TEMP_VDD_LSB 0x03 #define ADT7411_REG_EXT_TEMP_AIN14_LSB 0x04 #define ADT7411_REG_VDD_MSB 0x06 @@ -28,20 +43,31 @@ #define ADT7411_REG_EXT_TEMP_AIN1_MSB 0x08 #define ADT7411_REG_CFG1 0x18 -#define ADT7411_CFG1_START_MONITOR (1 << 0) -#define ADT7411_CFG1_RESERVED_BIT1 (1 << 1) -#define ADT7411_CFG1_EXT_TDM (1 << 2) -#define ADT7411_CFG1_RESERVED_BIT3 (1 << 3) +#define ADT7411_CFG1_START_MONITOR BIT(0) +#define ADT7411_CFG1_RESERVED_BIT1 BIT(1) +#define ADT7411_CFG1_EXT_TDM BIT(2) +#define ADT7411_CFG1_RESERVED_BIT3 BIT(3) #define ADT7411_REG_CFG2 0x19 -#define ADT7411_CFG2_DISABLE_AVG (1 << 5) +#define ADT7411_CFG2_DISABLE_AVG BIT(5) #define ADT7411_REG_CFG3 0x1a -#define ADT7411_CFG3_ADC_CLK_225 (1 << 0) -#define ADT7411_CFG3_RESERVED_BIT1 (1 << 1) -#define ADT7411_CFG3_RESERVED_BIT2 (1 << 2) -#define ADT7411_CFG3_RESERVED_BIT3 (1 << 3) -#define ADT7411_CFG3_REF_VDD (1 << 4) +#define ADT7411_CFG3_ADC_CLK_225 BIT(0) +#define ADT7411_CFG3_RESERVED_BIT1 BIT(1) +#define ADT7411_CFG3_RESERVED_BIT2 BIT(2) +#define ADT7411_CFG3_RESERVED_BIT3 BIT(3) +#define ADT7411_CFG3_REF_VDD BIT(4) + +#define ADT7411_REG_VDD_HIGH 0x23 +#define ADT7411_REG_VDD_LOW 0x24 +#define ADT7411_REG_TEMP_HIGH(nr) (0x25 + 2 * (nr)) +#define ADT7411_REG_TEMP_LOW(nr) (0x26 + 2 * (nr)) +#define ADT7411_REG_IN_HIGH(nr) ((nr) > 1 \ + ? 0x2b + 2 * ((nr)-2) \ + : 0x27) +#define ADT7411_REG_IN_LOW(nr) ((nr) > 1 \ + ? 0x2c + 2 * ((nr)-2) \ + : 0x28) #define ADT7411_REG_DEVICE_ID 0x4d #define ADT7411_REG_MANUFACTURER_ID 0x4e @@ -51,6 +77,30 @@ static const unsigned short normal_i2c[] = { 0x48, 0x4a, 0x4b, I2C_CLIENT_END }; +static const u8 adt7411_in_alarm_reg[] = { + ADT7411_REG_STAT_2, + ADT7411_REG_STAT_1, + ADT7411_REG_STAT_1, + ADT7411_REG_STAT_1, + ADT7411_REG_STAT_1, + ADT7411_REG_STAT_2, + ADT7411_REG_STAT_2, + ADT7411_REG_STAT_2, + ADT7411_REG_STAT_2, +}; + +static const u8 adt7411_in_alarm_bits[] = { + ADT7411_STAT_2_VDD, + ADT7411_STAT_1_EXT_TEMP_HIGH_AIN1, + ADT7411_STAT_1_AIN2, + ADT7411_STAT_1_AIN3, + ADT7411_STAT_1_AIN4, + ADT7411_STAT_2_AIN5, + ADT7411_STAT_2_AIN6, + ADT7411_STAT_2_AIN7, + ADT7411_STAT_2_AIN8, +}; + struct adt7411_data { struct mutex device_lock; /* for "atomic" device accesses */ struct mutex update_lock; @@ -165,6 +215,19 @@ static struct attribute *adt7411_attrs[] = { }; ATTRIBUTE_GROUPS(adt7411); +static int adt7411_read_in_alarm(struct device *dev, int channel, long *val) +{ + struct adt7411_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + int ret; + + ret = i2c_smbus_read_byte_data(client, adt7411_in_alarm_reg[channel]); + if (ret < 0) + return ret; + *val = !!(ret & adt7411_in_alarm_bits[channel]); + return 0; +} + static int adt7411_read_in_vdd(struct device *dev, u32 attr, long *val) { struct adt7411_data *data = dev_get_drvdata(dev); @@ -179,32 +242,41 @@ static int adt7411_read_in_vdd(struct device *dev, u32 attr, long *val) return ret; *val = ret * 7000 / 1024; return 0; + case hwmon_in_min: + ret = i2c_smbus_read_byte_data(client, ADT7411_REG_VDD_LOW); + if (ret < 0) + return ret; + *val = ret * 7000 / 256; + return 0; + case hwmon_in_max: + ret = i2c_smbus_read_byte_data(client, ADT7411_REG_VDD_HIGH); + if (ret < 0) + return ret; + *val = ret * 7000 / 256; + return 0; + case hwmon_in_alarm: + return adt7411_read_in_alarm(dev, 0, val); default: return -EOPNOTSUPP; } } -static int adt7411_read_in_chan(struct device *dev, u32 attr, int channel, - long *val) +static int adt7411_update_vref(struct device *dev) { struct adt7411_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; + int val; - int ret; - int lsb_reg, lsb_shift; - int nr = channel - 1; - - mutex_lock(&data->update_lock); if (time_after_eq(jiffies, data->next_update)) { - ret = i2c_smbus_read_byte_data(client, ADT7411_REG_CFG3); - if (ret < 0) - goto exit_unlock; + val = i2c_smbus_read_byte_data(client, ADT7411_REG_CFG3); + if (val < 0) + return val; - if (ret & ADT7411_CFG3_REF_VDD) { - ret = adt7411_read_in_vdd(dev, hwmon_in_input, + if (val & ADT7411_CFG3_REF_VDD) { + val = adt7411_read_in_vdd(dev, hwmon_in_input, &data->vref_cached); - if (ret < 0) - goto exit_unlock; + if (val < 0) + return val; } else { data->vref_cached = 2250; } @@ -212,6 +284,24 @@ static int adt7411_read_in_chan(struct device *dev, u32 attr, int channel, data->next_update = jiffies + HZ; } + return 0; +} + +static int adt7411_read_in_chan(struct device *dev, u32 attr, int channel, + long *val) +{ + struct adt7411_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + + int ret; + int reg, lsb_reg, lsb_shift; + int nr = channel - 1; + + mutex_lock(&data->update_lock); + ret = adt7411_update_vref(dev); + if (ret < 0) + goto exit_unlock; + switch (attr) { case hwmon_in_input: lsb_reg = ADT7411_REG_EXT_TEMP_AIN14_LSB + (nr >> 2); @@ -224,6 +314,20 @@ static int adt7411_read_in_chan(struct device *dev, u32 attr, int channel, *val = ret * data->vref_cached / 1024; ret = 0; break; + case hwmon_in_min: + case hwmon_in_max: + reg = (attr == hwmon_in_min) + ? ADT7411_REG_IN_LOW(channel) + : ADT7411_REG_IN_HIGH(channel); + ret = i2c_smbus_read_byte_data(client, reg); + if (ret < 0) + goto exit_unlock; + *val = ret * data->vref_cached / 256; + ret = 0; + break; + case hwmon_in_alarm: + ret = adt7411_read_in_alarm(dev, channel, val); + break; default: ret = -EOPNOTSUPP; break; @@ -242,12 +346,44 @@ static int adt7411_read_in(struct device *dev, u32 attr, int channel, return adt7411_read_in_chan(dev, attr, channel, val); } + +static int adt7411_read_temp_alarm(struct device *dev, u32 attr, int channel, + long *val) +{ + struct adt7411_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + int ret, bit; + + ret = i2c_smbus_read_byte_data(client, ADT7411_REG_STAT_1); + if (ret < 0) + return ret; + + switch (attr) { + case hwmon_temp_min_alarm: + bit = channel ? ADT7411_STAT_1_EXT_TEMP_LOW + : ADT7411_STAT_1_INT_TEMP_LOW; + break; + case hwmon_temp_max_alarm: + bit = channel ? ADT7411_STAT_1_EXT_TEMP_HIGH_AIN1 + : ADT7411_STAT_1_INT_TEMP_HIGH; + break; + case hwmon_temp_fault: + bit = ADT7411_STAT_1_EXT_TEMP_FAULT; + break; + default: + return -EOPNOTSUPP; + } + + *val = !!(ret & bit); + return 0; +} + static int adt7411_read_temp(struct device *dev, u32 attr, int channel, long *val) { struct adt7411_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; - int ret, regl, regh; + int ret, reg, regl, regh; switch (attr) { case hwmon_temp_input: @@ -261,6 +397,21 @@ static int adt7411_read_temp(struct device *dev, u32 attr, int channel, ret = ret & 0x200 ? ret - 0x400 : ret; /* 10 bit signed */ *val = ret * 250; return 0; + case hwmon_temp_min: + case hwmon_temp_max: + reg = (attr == hwmon_temp_min) + ? ADT7411_REG_TEMP_LOW(channel) + : ADT7411_REG_TEMP_HIGH(channel); + ret = i2c_smbus_read_byte_data(client, reg); + if (ret < 0) + return ret; + ret = ret & 0x80 ? ret - 0x100 : ret; /* 8 bit signed */ + *val = ret * 1000; + return 0; + case hwmon_temp_min_alarm: + case hwmon_temp_max_alarm: + case hwmon_temp_fault: + return adt7411_read_temp_alarm(dev, attr, channel, val); default: return -EOPNOTSUPP; } @@ -279,26 +430,143 @@ static int adt7411_read(struct device *dev, enum hwmon_sensor_types type, } } +static int adt7411_write_in_vdd(struct device *dev, u32 attr, long val) +{ + struct adt7411_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + int reg; + + val = clamp_val(val, 0, 255 * 7000 / 256); + val = DIV_ROUND_CLOSEST(val * 256, 7000); + + switch (attr) { + case hwmon_in_min: + reg = ADT7411_REG_VDD_LOW; + break; + case hwmon_in_max: + reg = ADT7411_REG_VDD_HIGH; + break; + default: + return -EOPNOTSUPP; + } + + return i2c_smbus_write_byte_data(client, reg, val); +} + +static int adt7411_write_in_chan(struct device *dev, u32 attr, int channel, + long val) +{ + struct adt7411_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + int ret, reg; + + mutex_lock(&data->update_lock); + ret = adt7411_update_vref(dev); + if (ret < 0) + goto exit_unlock; + val = clamp_val(val, 0, 255 * data->vref_cached / 256); + val = DIV_ROUND_CLOSEST(val * 256, data->vref_cached); + + switch (attr) { + case hwmon_in_min: + reg = ADT7411_REG_IN_LOW(channel); + break; + case hwmon_in_max: + reg = ADT7411_REG_IN_HIGH(channel); + break; + default: + ret = -EOPNOTSUPP; + goto exit_unlock; + } + + ret = i2c_smbus_write_byte_data(client, reg, val); + exit_unlock: + mutex_unlock(&data->update_lock); + return ret; +} + +static int adt7411_write_in(struct device *dev, u32 attr, int channel, + long val) +{ + if (channel == 0) + return adt7411_write_in_vdd(dev, attr, val); + else + return adt7411_write_in_chan(dev, attr, channel, val); +} + +static int adt7411_write_temp(struct device *dev, u32 attr, int channel, + long val) +{ + struct adt7411_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + int reg; + + val = clamp_val(val, -128000, 127000); + val = DIV_ROUND_CLOSEST(val, 1000); + + switch (attr) { + case hwmon_temp_min: + reg = ADT7411_REG_TEMP_LOW(channel); + break; + case hwmon_temp_max: + reg = ADT7411_REG_TEMP_HIGH(channel); + break; + default: + return -EOPNOTSUPP; + } + + return i2c_smbus_write_byte_data(client, reg, val); +} + +static int adt7411_write(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long val) +{ + switch (type) { + case hwmon_in: + return adt7411_write_in(dev, attr, channel, val); + case hwmon_temp: + return adt7411_write_temp(dev, attr, channel, val); + default: + return -EOPNOTSUPP; + } +} + static umode_t adt7411_is_visible(const void *_data, enum hwmon_sensor_types type, u32 attr, int channel) { const struct adt7411_data *data = _data; + bool visible; switch (type) { case hwmon_in: - if (channel > 0 && channel < 3) - return data->use_ext_temp ? 0 : S_IRUGO; - else - return S_IRUGO; + visible = channel == 0 || channel >= 3 || !data->use_ext_temp; + switch (attr) { + case hwmon_in_input: + case hwmon_in_alarm: + return visible ? S_IRUGO : 0; + case hwmon_in_min: + case hwmon_in_max: + return visible ? S_IRUGO | S_IWUSR : 0; + } + break; case hwmon_temp: - if (channel == 1) - return data->use_ext_temp ? S_IRUGO : 0; - else - return S_IRUGO; + visible = channel == 0 || data->use_ext_temp; + switch (attr) { + case hwmon_temp_input: + case hwmon_temp_min_alarm: + case hwmon_temp_max_alarm: + case hwmon_temp_fault: + return visible ? S_IRUGO : 0; + case hwmon_temp_min: + case hwmon_temp_max: + return visible ? S_IRUGO | S_IWUSR : 0; + } + break; default: - return 0; + break; } + return 0; } static int adt7411_detect(struct i2c_client *client, @@ -372,15 +640,15 @@ static int adt7411_init_device(struct adt7411_data *data) } static const u32 adt7411_in_config[] = { - HWMON_I_INPUT, - HWMON_I_INPUT, - HWMON_I_INPUT, - HWMON_I_INPUT, - HWMON_I_INPUT, - HWMON_I_INPUT, - HWMON_I_INPUT, - HWMON_I_INPUT, - HWMON_I_INPUT, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM, 0 }; @@ -390,8 +658,10 @@ static const struct hwmon_channel_info adt7411_in = { }; static const u32 adt7411_temp_config[] = { - HWMON_T_INPUT, - HWMON_T_INPUT, + HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MIN_ALARM | + HWMON_T_MAX | HWMON_T_MAX_ALARM, + HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MIN_ALARM | + HWMON_T_MAX | HWMON_T_MAX_ALARM | HWMON_T_FAULT, 0 }; @@ -409,6 +679,7 @@ static const struct hwmon_channel_info *adt7411_info[] = { static const struct hwmon_ops adt7411_hwmon_ops = { .is_visible = adt7411_is_visible, .read = adt7411_read, + .write = adt7411_write, }; static const struct hwmon_chip_info adt7411_chip_info = { diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c index c9a1d9c25572..2cd920751441 100644 --- a/drivers/hwmon/adt7470.c +++ b/drivers/hwmon/adt7470.c @@ -403,7 +403,7 @@ out: return data; } -static ssize_t show_auto_update_interval(struct device *dev, +static ssize_t auto_update_interval_show(struct device *dev, struct device_attribute *devattr, char *buf) { @@ -411,10 +411,9 @@ static ssize_t show_auto_update_interval(struct device *dev, return sprintf(buf, "%d\n", data->auto_update_interval); } -static ssize_t set_auto_update_interval(struct device *dev, - struct device_attribute *devattr, - const char *buf, - size_t count) +static ssize_t auto_update_interval_store(struct device *dev, + struct device_attribute *devattr, + const char *buf, size_t count) { struct adt7470_data *data = dev_get_drvdata(dev); long temp; @@ -431,7 +430,7 @@ static ssize_t set_auto_update_interval(struct device *dev, return count; } -static ssize_t show_num_temp_sensors(struct device *dev, +static ssize_t num_temp_sensors_show(struct device *dev, struct device_attribute *devattr, char *buf) { @@ -439,10 +438,9 @@ static ssize_t show_num_temp_sensors(struct device *dev, return sprintf(buf, "%d\n", data->num_temp_sensors); } -static ssize_t set_num_temp_sensors(struct device *dev, - struct device_attribute *devattr, - const char *buf, - size_t count) +static ssize_t num_temp_sensors_store(struct device *dev, + struct device_attribute *devattr, + const char *buf, size_t count) { struct adt7470_data *data = dev_get_drvdata(dev); long temp; @@ -537,7 +535,7 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *devattr, return sprintf(buf, "%d\n", 1000 * data->temp[attr->index]); } -static ssize_t show_alarm_mask(struct device *dev, +static ssize_t alarm_mask_show(struct device *dev, struct device_attribute *devattr, char *buf) { @@ -546,10 +544,9 @@ static ssize_t show_alarm_mask(struct device *dev, return sprintf(buf, "%x\n", data->alarms_mask); } -static ssize_t set_alarm_mask(struct device *dev, - struct device_attribute *devattr, - const char *buf, - size_t count) +static ssize_t alarm_mask_store(struct device *dev, + struct device_attribute *devattr, + const char *buf, size_t count) { struct adt7470_data *data = dev_get_drvdata(dev); long mask; @@ -723,8 +720,8 @@ static const int adt7470_freq_map[] = { 11, 15, 22, 29, 35, 44, 59, 88, 1400, 22500 }; -static ssize_t show_pwm_freq(struct device *dev, - struct device_attribute *devattr, char *buf) +static ssize_t pwm1_freq_show(struct device *dev, + struct device_attribute *devattr, char *buf) { struct adt7470_data *data = adt7470_update_device(dev); unsigned char cfg_reg_1; @@ -745,9 +742,9 @@ static ssize_t show_pwm_freq(struct device *dev, return scnprintf(buf, PAGE_SIZE, "%d\n", adt7470_freq_map[index]); } -static ssize_t set_pwm_freq(struct device *dev, - struct device_attribute *devattr, - const char *buf, size_t count) +static ssize_t pwm1_freq_store(struct device *dev, + struct device_attribute *devattr, + const char *buf, size_t count) { struct adt7470_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -1012,12 +1009,9 @@ static ssize_t show_alarm(struct device *dev, return sprintf(buf, "0\n"); } -static DEVICE_ATTR(alarm_mask, S_IWUSR | S_IRUGO, show_alarm_mask, - set_alarm_mask); -static DEVICE_ATTR(num_temp_sensors, S_IWUSR | S_IRUGO, show_num_temp_sensors, - set_num_temp_sensors); -static DEVICE_ATTR(auto_update_interval, S_IWUSR | S_IRUGO, - show_auto_update_interval, set_auto_update_interval); +static DEVICE_ATTR_RW(alarm_mask); +static DEVICE_ATTR_RW(num_temp_sensors); +static DEVICE_ATTR_RW(auto_update_interval); static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_temp_max, set_temp_max, 0); @@ -1133,7 +1127,7 @@ static SENSOR_DEVICE_ATTR(pwm2, S_IWUSR | S_IRUGO, show_pwm, set_pwm, 1); static SENSOR_DEVICE_ATTR(pwm3, S_IWUSR | S_IRUGO, show_pwm, set_pwm, 2); static SENSOR_DEVICE_ATTR(pwm4, S_IWUSR | S_IRUGO, show_pwm, set_pwm, 3); -static DEVICE_ATTR(pwm1_freq, S_IWUSR | S_IRUGO, show_pwm_freq, set_pwm_freq); +static DEVICE_ATTR_RW(pwm1_freq); static SENSOR_DEVICE_ATTR(pwm1_auto_point1_pwm, S_IWUSR | S_IRUGO, show_pwm_min, set_pwm_min, 0); diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index 3cefd1aeb24f..c646670b9ea9 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -856,16 +856,17 @@ static ssize_t set_pwmfreq(struct device *dev, struct device_attribute *attr, return count; } -static ssize_t show_pwm_at_crit(struct device *dev, - struct device_attribute *devattr, char *buf) +static ssize_t pwm_use_point2_pwm_at_crit_show(struct device *dev, + struct device_attribute *devattr, + char *buf) { struct adt7475_data *data = adt7475_update_device(dev); return sprintf(buf, "%d\n", !!(data->config4 & CONFIG4_MAXDUTY)); } -static ssize_t set_pwm_at_crit(struct device *dev, - struct device_attribute *devattr, - const char *buf, size_t count) +static ssize_t pwm_use_point2_pwm_at_crit_store(struct device *dev, + struct device_attribute *devattr, + const char *buf, size_t count) { struct i2c_client *client = to_i2c_client(dev); struct adt7475_data *data = i2c_get_clientdata(client); @@ -888,15 +889,15 @@ static ssize_t set_pwm_at_crit(struct device *dev, return count; } -static ssize_t show_vrm(struct device *dev, struct device_attribute *devattr, +static ssize_t vrm_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct adt7475_data *data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", (int)data->vrm); } -static ssize_t set_vrm(struct device *dev, struct device_attribute *devattr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *devattr, + const char *buf, size_t count) { struct adt7475_data *data = dev_get_drvdata(dev); long val; @@ -910,8 +911,8 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *devattr, return count; } -static ssize_t show_vid(struct device *dev, struct device_attribute *devattr, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *devattr, char *buf) { struct adt7475_data *data = adt7475_update_device(dev); return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); @@ -1057,11 +1058,10 @@ static SENSOR_DEVICE_ATTR_2(pwm3_auto_point2_pwm, S_IRUGO | S_IWUSR, show_pwm, set_pwm, MAX, 2); /* Non-standard name, might need revisiting */ -static DEVICE_ATTR(pwm_use_point2_pwm_at_crit, S_IWUSR | S_IRUGO, - show_pwm_at_crit, set_pwm_at_crit); +static DEVICE_ATTR_RW(pwm_use_point2_pwm_at_crit); -static DEVICE_ATTR(vrm, S_IWUSR | S_IRUGO, show_vrm, set_vrm); -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); +static DEVICE_ATTR_RW(vrm); +static DEVICE_ATTR_RO(cpu0_vid); static struct attribute *adt7475_attrs[] = { &sensor_dev_attr_in1_input.dev_attr.attr, diff --git a/drivers/hwmon/adt7x10.c b/drivers/hwmon/adt7x10.c index 98141f483165..0f538f8be6bf 100644 --- a/drivers/hwmon/adt7x10.c +++ b/drivers/hwmon/adt7x10.c @@ -331,9 +331,8 @@ static ssize_t adt7x10_show_alarm(struct device *dev, return sprintf(buf, "%d\n", !!(ret & attr->index)); } -static ssize_t adt7x10_show_name(struct device *dev, - struct device_attribute *da, - char *buf) +static ssize_t name_show(struct device *dev, struct device_attribute *da, + char *buf) { struct adt7x10_data *data = dev_get_drvdata(dev); @@ -359,7 +358,7 @@ static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, adt7x10_show_alarm, NULL, ADT7X10_STAT_T_HIGH); static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, adt7x10_show_alarm, NULL, ADT7X10_STAT_T_CRIT); -static DEVICE_ATTR(name, S_IRUGO, adt7x10_show_name, NULL); +static DEVICE_ATTR_RO(name); static struct attribute *adt7x10_attributes[] = { &sensor_dev_attr_temp1_input.dev_attr.attr, diff --git a/drivers/hwmon/asb100.c b/drivers/hwmon/asb100.c index 272fcc837ecc..62e191311139 100644 --- a/drivers/hwmon/asb100.c +++ b/drivers/hwmon/asb100.c @@ -483,25 +483,25 @@ sysfs_temp(3); sysfs_temp(4); /* VID */ -static ssize_t show_vid(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct asb100_data *data = asb100_update_device(dev); return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); /* VRM */ -static ssize_t show_vrm(struct device *dev, struct device_attribute *attr, +static ssize_t vrm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct asb100_data *data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", data->vrm); } -static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct asb100_data *data = dev_get_drvdata(dev); unsigned long val; @@ -519,16 +519,16 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, } /* Alarms */ -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm); +static DEVICE_ATTR_RW(vrm); -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct asb100_data *data = asb100_update_device(dev); return sprintf(buf, "%u\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) @@ -550,15 +550,15 @@ static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5); static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 13); /* 1 PWM */ -static ssize_t show_pwm1(struct device *dev, struct device_attribute *attr, +static ssize_t pwm1_show(struct device *dev, struct device_attribute *attr, char *buf) { struct asb100_data *data = asb100_update_device(dev); return sprintf(buf, "%d\n", ASB100_PWM_FROM_REG(data->pwm & 0x0f)); } -static ssize_t set_pwm1(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct i2c_client *client = to_i2c_client(dev); struct asb100_data *data = i2c_get_clientdata(client); @@ -577,15 +577,16 @@ static ssize_t set_pwm1(struct device *dev, struct device_attribute *attr, return count; } -static ssize_t show_pwm_enable1(struct device *dev, +static ssize_t pwm1_enable_show(struct device *dev, struct device_attribute *attr, char *buf) { struct asb100_data *data = asb100_update_device(dev); return sprintf(buf, "%d\n", (data->pwm & 0x80) ? 1 : 0); } -static ssize_t set_pwm_enable1(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) +static ssize_t pwm1_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct i2c_client *client = to_i2c_client(dev); struct asb100_data *data = i2c_get_clientdata(client); @@ -604,9 +605,8 @@ static ssize_t set_pwm_enable1(struct device *dev, return count; } -static DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm1, set_pwm1); -static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, - show_pwm_enable1, set_pwm_enable1); +static DEVICE_ATTR_RW(pwm1); +static DEVICE_ATTR_RW(pwm1_enable); static struct attribute *asb100_attributes[] = { &sensor_dev_attr_in0_input.dev_attr.attr, diff --git a/drivers/hwmon/atxp1.c b/drivers/hwmon/atxp1.c index f2f2f2fc755a..b7eadb54c8cb 100644 --- a/drivers/hwmon/atxp1.c +++ b/drivers/hwmon/atxp1.c @@ -81,8 +81,8 @@ static struct atxp1_data *atxp1_update_device(struct device *dev) } /* sys file functions for cpu0_vid */ -static ssize_t atxp1_showvcore(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { int size; struct atxp1_data *data; @@ -95,9 +95,9 @@ static ssize_t atxp1_showvcore(struct device *dev, return size; } -static ssize_t atxp1_storevcore(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t cpu0_vid_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct atxp1_data *data = atxp1_update_device(dev); struct i2c_client *client = data->client; @@ -154,12 +154,11 @@ static ssize_t atxp1_storevcore(struct device *dev, * CPU core reference voltage * unit: millivolt */ -static DEVICE_ATTR(cpu0_vid, S_IRUGO | S_IWUSR, atxp1_showvcore, - atxp1_storevcore); +static DEVICE_ATTR_RW(cpu0_vid); /* sys file functions for GPIO1 */ -static ssize_t atxp1_showgpio1(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t gpio1_show(struct device *dev, struct device_attribute *attr, + char *buf) { int size; struct atxp1_data *data; @@ -171,9 +170,8 @@ static ssize_t atxp1_showgpio1(struct device *dev, return size; } -static ssize_t atxp1_storegpio1(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) +static ssize_t gpio1_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct atxp1_data *data = atxp1_update_device(dev); struct i2c_client *client = data->client; @@ -201,11 +199,11 @@ static ssize_t atxp1_storegpio1(struct device *dev, * GPIO1 data register * unit: Four bit as hex (e.g. 0x0f) */ -static DEVICE_ATTR(gpio1, S_IRUGO | S_IWUSR, atxp1_showgpio1, atxp1_storegpio1); +static DEVICE_ATTR_RW(gpio1); /* sys file functions for GPIO2 */ -static ssize_t atxp1_showgpio2(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t gpio2_show(struct device *dev, struct device_attribute *attr, + char *buf) { int size; struct atxp1_data *data; @@ -217,9 +215,8 @@ static ssize_t atxp1_showgpio2(struct device *dev, return size; } -static ssize_t atxp1_storegpio2(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t gpio2_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct atxp1_data *data = atxp1_update_device(dev); struct i2c_client *client = data->client; @@ -246,7 +243,7 @@ static ssize_t atxp1_storegpio2(struct device *dev, * GPIO2 data register * unit: Eight bit as hex (e.g. 0xff) */ -static DEVICE_ATTR(gpio2, S_IRUGO | S_IWUSR, atxp1_showgpio2, atxp1_storegpio2); +static DEVICE_ATTR_RW(gpio2); static struct attribute *atxp1_attrs[] = { &dev_attr_gpio1.attr, diff --git a/drivers/hwmon/dme1737.c b/drivers/hwmon/dme1737.c index 8763c4a8280c..aa40a00ad689 100644 --- a/drivers/hwmon/dme1737.c +++ b/drivers/hwmon/dme1737.c @@ -279,7 +279,8 @@ static inline int IN_FROM_REG(int reg, int nominal, int res) static inline int IN_TO_REG(long val, int nominal) { - return clamp_val((val * 192 + nominal / 2) / nominal, 0, 255); + val = clamp_val(val, 0, 255 * nominal / 192); + return DIV_ROUND_CLOSEST(val * 192, nominal); } /* @@ -295,7 +296,8 @@ static inline int TEMP_FROM_REG(int reg, int res) static inline int TEMP_TO_REG(long val) { - return clamp_val((val < 0 ? val - 500 : val + 500) / 1000, -128, 127); + val = clamp_val(val, -128000, 127000); + return DIV_ROUND_CLOSEST(val, 1000); } /* Temperature range */ @@ -331,9 +333,10 @@ static inline int TEMP_HYST_FROM_REG(int reg, int ix) return (((ix == 1) ? reg : reg >> 4) & 0x0f) * 1000; } -static inline int TEMP_HYST_TO_REG(long val, int ix, int reg) +static inline int TEMP_HYST_TO_REG(int temp, long hyst, int ix, int reg) { - int hyst = clamp_val((val + 500) / 1000, 0, 15); + hyst = clamp_val(hyst, temp - 15000, temp); + hyst = DIV_ROUND_CLOSEST(temp - hyst, 1000); return (ix == 1) ? (reg & 0xf0) | hyst : (reg & 0x0f) | (hyst << 4); } @@ -1022,7 +1025,9 @@ static ssize_t set_zone(struct device *dev, struct device_attribute *attr, int ix = sensor_attr_2->index; int fn = sensor_attr_2->nr; long val; + int temp; int err; + u8 reg; err = kstrtol(buf, 10, &val); if (err) @@ -1035,10 +1040,9 @@ static ssize_t set_zone(struct device *dev, struct device_attribute *attr, data->zone_low[ix] = dme1737_read(data, DME1737_REG_ZONE_LOW(ix)); /* Modify the temp hyst value */ - data->zone_hyst[ix == 2] = TEMP_HYST_TO_REG( - TEMP_FROM_REG(data->zone_low[ix], 8) - - val, ix, dme1737_read(data, - DME1737_REG_ZONE_HYST(ix == 2))); + temp = TEMP_FROM_REG(data->zone_low[ix], 8); + reg = dme1737_read(data, DME1737_REG_ZONE_HYST(ix == 2)); + data->zone_hyst[ix == 2] = TEMP_HYST_TO_REG(temp, val, ix, reg); dme1737_write(data, DME1737_REG_ZONE_HYST(ix == 2), data->zone_hyst[ix == 2]); break; @@ -1055,10 +1059,10 @@ static ssize_t set_zone(struct device *dev, struct device_attribute *attr, * Modify the temp range value (which is stored in the upper * nibble of the pwm_freq register) */ - data->pwm_freq[ix] = TEMP_RANGE_TO_REG(val - - TEMP_FROM_REG(data->zone_low[ix], 8), - dme1737_read(data, - DME1737_REG_PWM_FREQ(ix))); + temp = TEMP_FROM_REG(data->zone_low[ix], 8); + val = clamp_val(val, temp, temp + 80000); + reg = dme1737_read(data, DME1737_REG_PWM_FREQ(ix)); + data->pwm_freq[ix] = TEMP_RANGE_TO_REG(val - temp, reg); dme1737_write(data, DME1737_REG_PWM_FREQ(ix), data->pwm_freq[ix]); break; @@ -1468,7 +1472,7 @@ exit: * Miscellaneous sysfs attributes * --------------------------------------------------------------------- */ -static ssize_t show_vrm(struct device *dev, struct device_attribute *attr, +static ssize_t vrm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct i2c_client *client = to_i2c_client(dev); @@ -1477,8 +1481,8 @@ static ssize_t show_vrm(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%d\n", data->vrm); } -static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct dme1737_data *data = dev_get_drvdata(dev); unsigned long val; @@ -1495,15 +1499,15 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, return count; } -static ssize_t show_vid(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct dme1737_data *data = dme1737_update_device(dev); return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); } -static ssize_t show_name(struct device *dev, struct device_attribute *attr, +static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dme1737_data *data = dev_get_drvdata(dev); @@ -1645,9 +1649,9 @@ SENSOR_DEVICE_ATTR_PWM_5TO6(6); /* Misc */ -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm); -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); /* for ISA devices */ +static DEVICE_ATTR_RW(vrm); +static DEVICE_ATTR_RO(cpu0_vid); +static DEVICE_ATTR_RO(name); /* for ISA devices */ /* * This struct holds all the attributes that are always present and need to be diff --git a/drivers/hwmon/ds1621.c b/drivers/hwmon/ds1621.c index 8890870309e4..5c317fc32a4a 100644 --- a/drivers/hwmon/ds1621.c +++ b/drivers/hwmon/ds1621.c @@ -263,7 +263,7 @@ static ssize_t set_temp(struct device *dev, struct device_attribute *da, return count; } -static ssize_t show_alarms(struct device *dev, struct device_attribute *da, +static ssize_t alarms_show(struct device *dev, struct device_attribute *da, char *buf) { struct ds1621_data *data = ds1621_update_client(dev); @@ -278,15 +278,16 @@ static ssize_t show_alarm(struct device *dev, struct device_attribute *da, return sprintf(buf, "%d\n", !!(data->conf & attr->index)); } -static ssize_t show_convrate(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t update_interval_show(struct device *dev, + struct device_attribute *da, char *buf) { struct ds1621_data *data = dev_get_drvdata(dev); return scnprintf(buf, PAGE_SIZE, "%hu\n", data->update_interval); } -static ssize_t set_convrate(struct device *dev, struct device_attribute *da, - const char *buf, size_t count) +static ssize_t update_interval_store(struct device *dev, + struct device_attribute *da, + const char *buf, size_t count) { struct ds1621_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -315,9 +316,8 @@ static ssize_t set_convrate(struct device *dev, struct device_attribute *da, return count; } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); -static DEVICE_ATTR(update_interval, S_IWUSR | S_IRUGO, show_convrate, - set_convrate); +static DEVICE_ATTR_RO(alarms); +static DEVICE_ATTR_RW(update_interval); static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL, 0); static SENSOR_DEVICE_ATTR(temp1_min, S_IWUSR | S_IRUGO, show_temp, set_temp, 1); diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c index 4b870ee9b0d3..1ed9a7aa953d 100644 --- a/drivers/hwmon/emc2103.c +++ b/drivers/hwmon/emc2103.c @@ -284,7 +284,7 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *da, } static ssize_t -show_fan(struct device *dev, struct device_attribute *da, char *buf) +fan1_input_show(struct device *dev, struct device_attribute *da, char *buf) { struct emc2103_data *data = emc2103_update_device(dev); int rpm = 0; @@ -294,7 +294,7 @@ show_fan(struct device *dev, struct device_attribute *da, char *buf) } static ssize_t -show_fan_div(struct device *dev, struct device_attribute *da, char *buf) +fan1_div_show(struct device *dev, struct device_attribute *da, char *buf) { struct emc2103_data *data = emc2103_update_device(dev); int fan_div = 8 / data->fan_multiplier; @@ -307,8 +307,8 @@ show_fan_div(struct device *dev, struct device_attribute *da, char *buf) * of least surprise; the user doesn't expect the fan target to change just * because the divider changed. */ -static ssize_t set_fan_div(struct device *dev, struct device_attribute *da, - const char *buf, size_t count) +static ssize_t fan1_div_store(struct device *dev, struct device_attribute *da, + const char *buf, size_t count) { struct emc2103_data *data = emc2103_update_device(dev); struct i2c_client *client = data->client; @@ -369,7 +369,7 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *da, } static ssize_t -show_fan_target(struct device *dev, struct device_attribute *da, char *buf) +fan1_target_show(struct device *dev, struct device_attribute *da, char *buf) { struct emc2103_data *data = emc2103_update_device(dev); int rpm = 0; @@ -382,8 +382,9 @@ show_fan_target(struct device *dev, struct device_attribute *da, char *buf) return sprintf(buf, "%d\n", rpm); } -static ssize_t set_fan_target(struct device *dev, struct device_attribute *da, - const char *buf, size_t count) +static ssize_t fan1_target_store(struct device *dev, + struct device_attribute *da, const char *buf, + size_t count) { struct emc2103_data *data = emc2103_update_device(dev); struct i2c_client *client = data->client; @@ -412,7 +413,7 @@ static ssize_t set_fan_target(struct device *dev, struct device_attribute *da, } static ssize_t -show_fan_fault(struct device *dev, struct device_attribute *da, char *buf) +fan1_fault_show(struct device *dev, struct device_attribute *da, char *buf) { struct emc2103_data *data = emc2103_update_device(dev); bool fault = ((data->fan_tach & 0x1fe0) == 0x1fe0); @@ -420,14 +421,15 @@ show_fan_fault(struct device *dev, struct device_attribute *da, char *buf) } static ssize_t -show_pwm_enable(struct device *dev, struct device_attribute *da, char *buf) +pwm1_enable_show(struct device *dev, struct device_attribute *da, char *buf) { struct emc2103_data *data = emc2103_update_device(dev); return sprintf(buf, "%d\n", data->fan_rpm_control ? 3 : 0); } -static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *da, - const char *buf, size_t count) +static ssize_t pwm1_enable_store(struct device *dev, + struct device_attribute *da, const char *buf, + size_t count) { struct emc2103_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -512,14 +514,12 @@ static SENSOR_DEVICE_ATTR(temp4_min_alarm, S_IRUGO, show_temp_min_alarm, static SENSOR_DEVICE_ATTR(temp4_max_alarm, S_IRUGO, show_temp_max_alarm, NULL, 3); -static DEVICE_ATTR(fan1_input, S_IRUGO, show_fan, NULL); -static DEVICE_ATTR(fan1_div, S_IRUGO | S_IWUSR, show_fan_div, set_fan_div); -static DEVICE_ATTR(fan1_target, S_IRUGO | S_IWUSR, show_fan_target, - set_fan_target); -static DEVICE_ATTR(fan1_fault, S_IRUGO, show_fan_fault, NULL); +static DEVICE_ATTR_RO(fan1_input); +static DEVICE_ATTR_RW(fan1_div); +static DEVICE_ATTR_RW(fan1_target); +static DEVICE_ATTR_RO(fan1_fault); -static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, show_pwm_enable, - set_pwm_enable); +static DEVICE_ATTR_RW(pwm1_enable); /* sensors present on all models */ static struct attribute *emc2103_attributes[] = { diff --git a/drivers/hwmon/f71805f.c b/drivers/hwmon/f71805f.c index facd05cda26d..73c681162653 100644 --- a/drivers/hwmon/f71805f.c +++ b/drivers/hwmon/f71805f.c @@ -946,7 +946,7 @@ static ssize_t set_temp_hyst(struct device *dev, struct device_attribute return count; } -static ssize_t show_alarms_in(struct device *dev, struct device_attribute +static ssize_t alarms_in_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct f71805f_data *data = f71805f_update_device(dev); @@ -954,7 +954,7 @@ static ssize_t show_alarms_in(struct device *dev, struct device_attribute return sprintf(buf, "%lu\n", data->alarms & 0x7ff); } -static ssize_t show_alarms_fan(struct device *dev, struct device_attribute +static ssize_t alarms_fan_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct f71805f_data *data = f71805f_update_device(dev); @@ -962,7 +962,7 @@ static ssize_t show_alarms_fan(struct device *dev, struct device_attribute return sprintf(buf, "%lu\n", (data->alarms >> 16) & 0x07); } -static ssize_t show_alarms_temp(struct device *dev, struct device_attribute +static ssize_t alarms_temp_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct f71805f_data *data = f71805f_update_device(dev); @@ -980,7 +980,7 @@ static ssize_t show_alarm(struct device *dev, struct device_attribute return sprintf(buf, "%lu\n", (data->alarms >> bitnr) & 1); } -static ssize_t show_name(struct device *dev, struct device_attribute +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct f71805f_data *data = dev_get_drvdata(dev); @@ -1176,11 +1176,11 @@ static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 13); static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 16); static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 17); static SENSOR_DEVICE_ATTR(fan3_alarm, S_IRUGO, show_alarm, NULL, 18); -static DEVICE_ATTR(alarms_in, S_IRUGO, show_alarms_in, NULL); -static DEVICE_ATTR(alarms_fan, S_IRUGO, show_alarms_fan, NULL); -static DEVICE_ATTR(alarms_temp, S_IRUGO, show_alarms_temp, NULL); +static DEVICE_ATTR_RO(alarms_in); +static DEVICE_ATTR_RO(alarms_fan); +static DEVICE_ATTR_RO(alarms_temp); -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static struct attribute *f71805f_attributes[] = { &sensor_dev_attr_in0_input.dev_attr.attr, diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c index cb28e4b4fb10..ca54ce5c8e10 100644 --- a/drivers/hwmon/f71882fg.c +++ b/drivers/hwmon/f71882fg.c @@ -390,7 +390,7 @@ static ssize_t show_pwm_auto_point_temp(struct device *dev, static ssize_t store_pwm_auto_point_temp(struct device *dev, struct device_attribute *devattr, const char *buf, size_t count); /* Sysfs misc */ -static ssize_t show_name(struct device *dev, struct device_attribute *devattr, +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf); static int f71882fg_probe(struct platform_device *pdev); @@ -404,7 +404,7 @@ static struct platform_driver f71882fg_driver = { .remove = f71882fg_remove, }; -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); /* * Temp attr for the f71858fg, the f71858fg is special as it has its @@ -2212,7 +2212,7 @@ static ssize_t store_pwm_auto_point_temp(struct device *dev, return count; } -static ssize_t show_name(struct device *dev, struct device_attribute *devattr, +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct f71882fg_data *data = dev_get_drvdata(dev); diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c index 15aa49d082c4..9545a346044f 100644 --- a/drivers/hwmon/fam15h_power.c +++ b/drivers/hwmon/fam15h_power.c @@ -83,8 +83,8 @@ static bool is_carrizo_or_later(void) return boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model >= 0x60; } -static ssize_t show_power(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t power1_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { u32 val, tdp_limit, running_avg_range; s32 running_avg_capture; @@ -136,16 +136,16 @@ static ssize_t show_power(struct device *dev, curr_pwr_watts = (curr_pwr_watts * 15625) >> (10 + running_avg_range); return sprintf(buf, "%u\n", (unsigned int) curr_pwr_watts); } -static DEVICE_ATTR(power1_input, S_IRUGO, show_power, NULL); +static DEVICE_ATTR_RO(power1_input); -static ssize_t show_power_crit(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t power1_crit_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct fam15h_power_data *data = dev_get_drvdata(dev); return sprintf(buf, "%u\n", data->processor_pwr_watts); } -static DEVICE_ATTR(power1_crit, S_IRUGO, show_power_crit, NULL); +static DEVICE_ATTR_RO(power1_crit); static void do_read_registers_on_cu(void *_data) { @@ -212,9 +212,8 @@ static int read_registers(struct fam15h_power_data *data) return 0; } -static ssize_t acc_show_power(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t power1_average_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct fam15h_power_data *data = dev_get_drvdata(dev); u64 prev_cu_acc_power[MAX_CUS], prev_ptsc[MAX_CUS], @@ -267,20 +266,20 @@ static ssize_t acc_show_power(struct device *dev, return sprintf(buf, "%llu\n", (unsigned long long)avg_acc); } -static DEVICE_ATTR(power1_average, S_IRUGO, acc_show_power, NULL); +static DEVICE_ATTR_RO(power1_average); -static ssize_t acc_show_power_period(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t power1_average_interval_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct fam15h_power_data *data = dev_get_drvdata(dev); return sprintf(buf, "%lu\n", data->power_period); } -static ssize_t acc_set_power_period(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t power1_average_interval_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct fam15h_power_data *data = dev_get_drvdata(dev); unsigned long temp; @@ -301,8 +300,7 @@ static ssize_t acc_set_power_period(struct device *dev, return count; } -static DEVICE_ATTR(power1_average_interval, S_IRUGO | S_IWUSR, - acc_show_power_period, acc_set_power_period); +static DEVICE_ATTR_RW(power1_average_interval); static int fam15h_power_init_attrs(struct pci_dev *pdev, struct fam15h_power_data *data) diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c index d58abdc5a4cf..5e78229ade04 100644 --- a/drivers/hwmon/fschmd.c +++ b/drivers/hwmon/fschmd.c @@ -561,7 +561,7 @@ static ssize_t store_pwm_auto_point1_pwm(struct device *dev, * The FSC hwmon family has the ability to force an attached alert led to flash * from software, we export this as an alert_led sysfs attr */ -static ssize_t show_alert_led(struct device *dev, +static ssize_t alert_led_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct fschmd_data *data = fschmd_update_device(dev); @@ -572,7 +572,7 @@ static ssize_t show_alert_led(struct device *dev, return sprintf(buf, "0\n"); } -static ssize_t store_alert_led(struct device *dev, +static ssize_t alert_led_store(struct device *dev, struct device_attribute *devattr, const char *buf, size_t count) { u8 reg; @@ -602,7 +602,7 @@ static ssize_t store_alert_led(struct device *dev, return count; } -static DEVICE_ATTR(alert_led, 0644, show_alert_led, store_alert_led); +static DEVICE_ATTR_RW(alert_led); static struct sensor_device_attribute fschmd_attr[] = { SENSOR_ATTR(in0_input, 0444, show_in_value, NULL, 0), diff --git a/drivers/hwmon/g760a.c b/drivers/hwmon/g760a.c index ec6a77da411a..7be1371b2c3d 100644 --- a/drivers/hwmon/g760a.c +++ b/drivers/hwmon/g760a.c @@ -107,8 +107,8 @@ static struct g760a_data *g760a_update_client(struct device *dev) return data; } -static ssize_t show_fan(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t fan1_input_show(struct device *dev, + struct device_attribute *da, char *buf) { struct g760a_data *data = g760a_update_client(dev); unsigned int rpm = 0; @@ -121,8 +121,8 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *da, return sprintf(buf, "%d\n", rpm); } -static ssize_t show_fan_alarm(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t fan1_alarm_show(struct device *dev, + struct device_attribute *da, char *buf) { struct g760a_data *data = g760a_update_client(dev); @@ -131,16 +131,16 @@ static ssize_t show_fan_alarm(struct device *dev, struct device_attribute *da, return sprintf(buf, "%d\n", fan_alarm); } -static ssize_t get_pwm(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t pwm1_show(struct device *dev, struct device_attribute *da, + char *buf) { struct g760a_data *data = g760a_update_client(dev); return sprintf(buf, "%d\n", PWM_FROM_CNT(data->set_cnt)); } -static ssize_t set_pwm(struct device *dev, struct device_attribute *da, - const char *buf, size_t count) +static ssize_t pwm1_store(struct device *dev, struct device_attribute *da, + const char *buf, size_t count) { struct g760a_data *data = g760a_update_client(dev); struct i2c_client *client = data->client; @@ -157,9 +157,9 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute *da, return count; } -static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, get_pwm, set_pwm); -static DEVICE_ATTR(fan1_input, S_IRUGO, show_fan, NULL); -static DEVICE_ATTR(fan1_alarm, S_IRUGO, show_fan_alarm, NULL); +static DEVICE_ATTR_RW(pwm1); +static DEVICE_ATTR_RO(fan1_input); +static DEVICE_ATTR_RO(fan1_alarm); static struct attribute *g760a_attrs[] = { &dev_attr_pwm1.attr, diff --git a/drivers/hwmon/g762.c b/drivers/hwmon/g762.c index 628be9c95ff9..6dca2fd3d303 100644 --- a/drivers/hwmon/g762.c +++ b/drivers/hwmon/g762.c @@ -738,8 +738,8 @@ static int g762_pdata_prop_import(struct i2c_client *client) * Read function for fan1_input sysfs file. Return current fan RPM value, or * 0 if fan is out of control. */ -static ssize_t get_fan_rpm(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t fan1_input_show(struct device *dev, + struct device_attribute *da, char *buf) { struct g762_data *data = g762_update_client(dev); unsigned int rpm = 0; @@ -764,8 +764,8 @@ static ssize_t get_fan_rpm(struct device *dev, struct device_attribute *da, * Read and write functions for pwm1_mode sysfs file. Get and set fan speed * control mode i.e. PWM (1) or DC (0). */ -static ssize_t get_pwm_mode(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t pwm1_mode_show(struct device *dev, struct device_attribute *da, + char *buf) { struct g762_data *data = g762_update_client(dev); @@ -776,8 +776,9 @@ static ssize_t get_pwm_mode(struct device *dev, struct device_attribute *da, !!(data->fan_cmd1 & G762_REG_FAN_CMD1_OUT_MODE)); } -static ssize_t set_pwm_mode(struct device *dev, struct device_attribute *da, - const char *buf, size_t count) +static ssize_t pwm1_mode_store(struct device *dev, + struct device_attribute *da, const char *buf, + size_t count) { unsigned long val; int ret; @@ -796,8 +797,8 @@ static ssize_t set_pwm_mode(struct device *dev, struct device_attribute *da, * Read and write functions for fan1_div sysfs file. Get and set fan * controller prescaler value */ -static ssize_t get_fan_div(struct device *dev, - struct device_attribute *da, char *buf) +static ssize_t fan1_div_show(struct device *dev, struct device_attribute *da, + char *buf) { struct g762_data *data = g762_update_client(dev); @@ -807,9 +808,8 @@ static ssize_t get_fan_div(struct device *dev, return sprintf(buf, "%d\n", G762_CLKDIV_FROM_REG(data->fan_cmd1)); } -static ssize_t set_fan_div(struct device *dev, - struct device_attribute *da, - const char *buf, size_t count) +static ssize_t fan1_div_store(struct device *dev, struct device_attribute *da, + const char *buf, size_t count) { unsigned long val; int ret; @@ -828,8 +828,8 @@ static ssize_t set_fan_div(struct device *dev, * Read and write functions for fan1_pulses sysfs file. Get and set number * of tachometer pulses per fan revolution. */ -static ssize_t get_fan_pulses(struct device *dev, - struct device_attribute *da, char *buf) +static ssize_t fan1_pulses_show(struct device *dev, + struct device_attribute *da, char *buf) { struct g762_data *data = g762_update_client(dev); @@ -839,9 +839,9 @@ static ssize_t get_fan_pulses(struct device *dev, return sprintf(buf, "%d\n", G762_PULSE_FROM_REG(data->fan_cmd1)); } -static ssize_t set_fan_pulses(struct device *dev, - struct device_attribute *da, - const char *buf, size_t count) +static ssize_t fan1_pulses_store(struct device *dev, + struct device_attribute *da, const char *buf, + size_t count) { unsigned long val; int ret; @@ -870,8 +870,8 @@ static ssize_t set_fan_pulses(struct device *dev, * but we do not accept 0 as this mode is not natively supported by the chip * and it is not emulated by g762 driver. -EINVAL is returned in this case. */ -static ssize_t get_pwm_enable(struct device *dev, - struct device_attribute *da, char *buf) +static ssize_t pwm1_enable_show(struct device *dev, + struct device_attribute *da, char *buf) { struct g762_data *data = g762_update_client(dev); @@ -882,9 +882,9 @@ static ssize_t get_pwm_enable(struct device *dev, (!!(data->fan_cmd1 & G762_REG_FAN_CMD1_FAN_MODE)) + 1); } -static ssize_t set_pwm_enable(struct device *dev, - struct device_attribute *da, - const char *buf, size_t count) +static ssize_t pwm1_enable_store(struct device *dev, + struct device_attribute *da, const char *buf, + size_t count) { unsigned long val; int ret; @@ -904,8 +904,8 @@ static ssize_t set_pwm_enable(struct device *dev, * (which affects fan speed) in open-loop mode. 0 stops the fan and 255 * makes it run at full speed. */ -static ssize_t get_pwm(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t pwm1_show(struct device *dev, struct device_attribute *da, + char *buf) { struct g762_data *data = g762_update_client(dev); @@ -915,8 +915,8 @@ static ssize_t get_pwm(struct device *dev, struct device_attribute *da, return sprintf(buf, "%d\n", data->set_out); } -static ssize_t set_pwm(struct device *dev, struct device_attribute *da, - const char *buf, size_t count) +static ssize_t pwm1_store(struct device *dev, struct device_attribute *da, + const char *buf, size_t count) { unsigned long val; int ret; @@ -942,8 +942,8 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute *da, * Also note that due to rounding errors it is possible that you don't read * back exactly the value you have set. */ -static ssize_t get_fan_target(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t fan1_target_show(struct device *dev, + struct device_attribute *da, char *buf) { struct g762_data *data = g762_update_client(dev); unsigned int rpm; @@ -961,8 +961,9 @@ static ssize_t get_fan_target(struct device *dev, struct device_attribute *da, return sprintf(buf, "%u\n", rpm); } -static ssize_t set_fan_target(struct device *dev, struct device_attribute *da, - const char *buf, size_t count) +static ssize_t fan1_target_store(struct device *dev, + struct device_attribute *da, const char *buf, + size_t count) { unsigned long val; int ret; @@ -978,7 +979,7 @@ static ssize_t set_fan_target(struct device *dev, struct device_attribute *da, } /* read function for fan1_fault sysfs file. */ -static ssize_t get_fan_failure(struct device *dev, struct device_attribute *da, +static ssize_t fan1_fault_show(struct device *dev, struct device_attribute *da, char *buf) { struct g762_data *data = g762_update_client(dev); @@ -993,8 +994,8 @@ static ssize_t get_fan_failure(struct device *dev, struct device_attribute *da, * read function for fan1_alarm sysfs file. Note that OOC condition is * enabled low */ -static ssize_t get_fan_ooc(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t fan1_alarm_show(struct device *dev, + struct device_attribute *da, char *buf) { struct g762_data *data = g762_update_client(dev); @@ -1004,18 +1005,15 @@ static ssize_t get_fan_ooc(struct device *dev, struct device_attribute *da, return sprintf(buf, "%u\n", !(data->fan_sta & G762_REG_FAN_STA_OOC)); } -static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, get_pwm, set_pwm); -static DEVICE_ATTR(pwm1_mode, S_IWUSR | S_IRUGO, get_pwm_mode, set_pwm_mode); -static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO, - get_pwm_enable, set_pwm_enable); -static DEVICE_ATTR(fan1_input, S_IRUGO, get_fan_rpm, NULL); -static DEVICE_ATTR(fan1_alarm, S_IRUGO, get_fan_ooc, NULL); -static DEVICE_ATTR(fan1_fault, S_IRUGO, get_fan_failure, NULL); -static DEVICE_ATTR(fan1_target, S_IWUSR | S_IRUGO, - get_fan_target, set_fan_target); -static DEVICE_ATTR(fan1_div, S_IWUSR | S_IRUGO, get_fan_div, set_fan_div); -static DEVICE_ATTR(fan1_pulses, S_IWUSR | S_IRUGO, - get_fan_pulses, set_fan_pulses); +static DEVICE_ATTR_RW(pwm1); +static DEVICE_ATTR_RW(pwm1_mode); +static DEVICE_ATTR_RW(pwm1_enable); +static DEVICE_ATTR_RO(fan1_input); +static DEVICE_ATTR_RO(fan1_alarm); +static DEVICE_ATTR_RO(fan1_fault); +static DEVICE_ATTR_RW(fan1_target); +static DEVICE_ATTR_RW(fan1_div); +static DEVICE_ATTR_RW(fan1_pulses); /* Driver data */ static struct attribute *g762_attrs[] = { diff --git a/drivers/hwmon/gl518sm.c b/drivers/hwmon/gl518sm.c index 0212c8317bca..b267510daeb2 100644 --- a/drivers/hwmon/gl518sm.c +++ b/drivers/hwmon/gl518sm.c @@ -86,9 +86,8 @@ enum chips { gl518sm_r00, gl518sm_r80 }; #define BOOL_FROM_REG(val) ((val) ? 0 : 1) #define BOOL_TO_REG(val) ((val) ? 0 : 1) -#define TEMP_TO_REG(val) clamp_val(((((val) < 0 ? \ - (val) - 500 : \ - (val) + 500) / 1000) + 119), 0, 255) +#define TEMP_CLAMP(val) clamp_val(val, -119000, 136000) +#define TEMP_TO_REG(val) (DIV_ROUND_CLOSEST(TEMP_CLAMP(val), 1000) + 119) #define TEMP_FROM_REG(val) (((val) - 119) * 1000) static inline u8 FAN_TO_REG(long rpm, int div) @@ -101,11 +100,13 @@ static inline u8 FAN_TO_REG(long rpm, int div) } #define FAN_FROM_REG(val, div) ((val) == 0 ? 0 : (480000 / ((val) * (div)))) -#define IN_TO_REG(val) clamp_val((((val) + 9) / 19), 0, 255) +#define IN_CLAMP(val) clamp_val(val, 0, 255 * 19) +#define IN_TO_REG(val) DIV_ROUND_CLOSEST(IN_CLAMP(val), 19) #define IN_FROM_REG(val) ((val) * 19) -#define VDD_TO_REG(val) clamp_val((((val) * 4 + 47) / 95), 0, 255) -#define VDD_FROM_REG(val) (((val) * 95 + 2) / 4) +#define VDD_CLAMP(val) clamp_val(val, 0, 255 * 95 / 4) +#define VDD_TO_REG(val) DIV_ROUND_CLOSEST(VDD_CLAMP(val) * 4, 95) +#define VDD_FROM_REG(val) DIV_ROUND_CLOSEST((val) * 95, 4) #define DIV_FROM_REG(val) (1 << (val)) diff --git a/drivers/hwmon/gl520sm.c b/drivers/hwmon/gl520sm.c index dee93ec87d02..4ff32ee67fb6 100644 --- a/drivers/hwmon/gl520sm.c +++ b/drivers/hwmon/gl520sm.c @@ -200,19 +200,21 @@ static struct gl520_data *gl520_update_device(struct device *dev) * Sysfs stuff */ -static ssize_t get_cpu_vid(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct gl520_data *data = gl520_update_device(dev); return sprintf(buf, "%u\n", vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, get_cpu_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); -#define VDD_FROM_REG(val) (((val) * 95 + 2) / 4) -#define VDD_TO_REG(val) clamp_val((((val) * 4 + 47) / 95), 0, 255) +#define VDD_FROM_REG(val) DIV_ROUND_CLOSEST((val) * 95, 4) +#define VDD_CLAMP(val) clamp_val(val, 0, 255 * 95 / 4) +#define VDD_TO_REG(val) DIV_ROUND_CLOSEST(VDD_CLAMP(val) * 4, 95) -#define IN_FROM_REG(val) ((val) * 19) -#define IN_TO_REG(val) clamp_val((((val) + 9) / 19), 0, 255) +#define IN_FROM_REG(val) ((val) * 19) +#define IN_CLAMP(val) clamp_val(val, 0, 255 * 19) +#define IN_TO_REG(val) DIV_ROUND_CLOSEST(IN_CLAMP(val), 19) static ssize_t get_in_input(struct device *dev, struct device_attribute *attr, char *buf) @@ -349,8 +351,13 @@ static SENSOR_DEVICE_ATTR(in4_max, S_IRUGO | S_IWUSR, #define DIV_FROM_REG(val) (1 << (val)) #define FAN_FROM_REG(val, div) ((val) == 0 ? 0 : (480000 / ((val) << (div)))) -#define FAN_TO_REG(val, div) ((val) <= 0 ? 0 : \ - clamp_val((480000 + ((val) << ((div)-1))) / ((val) << (div)), 1, 255)) + +#define FAN_BASE(div) (480000 >> (div)) +#define FAN_CLAMP(val, div) clamp_val(val, FAN_BASE(div) / 255, \ + FAN_BASE(div)) +#define FAN_TO_REG(val, div) ((val) == 0 ? 0 : \ + DIV_ROUND_CLOSEST(480000, \ + FAN_CLAMP(val, div) << (div))) static ssize_t get_fan_input(struct device *dev, struct device_attribute *attr, char *buf) @@ -381,8 +388,8 @@ static ssize_t get_fan_div(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%d\n", DIV_FROM_REG(data->fan_div[n])); } -static ssize_t get_fan_off(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t fan1_off_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct gl520_data *data = gl520_update_device(dev); return sprintf(buf, "%d\n", data->fan_off); @@ -476,8 +483,9 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *attr, return count; } -static ssize_t set_fan_off(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t fan1_off_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct gl520_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -510,12 +518,11 @@ static SENSOR_DEVICE_ATTR(fan1_div, S_IRUGO | S_IWUSR, get_fan_div, set_fan_div, 0); static SENSOR_DEVICE_ATTR(fan2_div, S_IRUGO | S_IWUSR, get_fan_div, set_fan_div, 1); -static DEVICE_ATTR(fan1_off, S_IRUGO | S_IWUSR, - get_fan_off, set_fan_off); +static DEVICE_ATTR_RW(fan1_off); -#define TEMP_FROM_REG(val) (((val) - 130) * 1000) -#define TEMP_TO_REG(val) clamp_val(((((val) < 0 ? \ - (val) - 500 : (val) + 500) / 1000) + 130), 0, 255) +#define TEMP_FROM_REG(val) (((val) - 130) * 1000) +#define TEMP_CLAMP(val) clamp_val(val, -130000, 125000) +#define TEMP_TO_REG(val) (DIV_ROUND_CLOSEST(TEMP_CLAMP(val), 1000) + 130) static ssize_t get_temp_input(struct device *dev, struct device_attribute *attr, char *buf) @@ -596,29 +603,30 @@ static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR, static SENSOR_DEVICE_ATTR(temp2_max_hyst, S_IRUGO | S_IWUSR, get_temp_max_hyst, set_temp_max_hyst, 1); -static ssize_t get_alarms(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct gl520_data *data = gl520_update_device(dev); return sprintf(buf, "%d\n", data->alarms); } -static ssize_t get_beep_enable(struct device *dev, struct device_attribute - *attr, char *buf) +static ssize_t beep_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct gl520_data *data = gl520_update_device(dev); return sprintf(buf, "%d\n", data->beep_enable); } -static ssize_t get_beep_mask(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t beep_mask_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct gl520_data *data = gl520_update_device(dev); return sprintf(buf, "%d\n", data->beep_mask); } -static ssize_t set_beep_enable(struct device *dev, struct device_attribute - *attr, const char *buf, size_t count) +static ssize_t beep_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct gl520_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -641,8 +649,9 @@ static ssize_t set_beep_enable(struct device *dev, struct device_attribute return count; } -static ssize_t set_beep_mask(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t beep_mask_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct gl520_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -661,11 +670,9 @@ static ssize_t set_beep_mask(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(alarms, S_IRUGO, get_alarms, NULL); -static DEVICE_ATTR(beep_enable, S_IRUGO | S_IWUSR, - get_beep_enable, set_beep_enable); -static DEVICE_ATTR(beep_mask, S_IRUGO | S_IWUSR, - get_beep_mask, set_beep_mask); +static DEVICE_ATTR_RO(alarms); +static DEVICE_ATTR_RW(beep_enable); +static DEVICE_ATTR_RW(beep_mask); static ssize_t get_alarm(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index 685568b1236d..9c355b9d31c5 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -77,8 +77,8 @@ static irqreturn_t fan_alarm_irq_handler(int irq, void *dev_id) return IRQ_NONE; } -static ssize_t show_fan_alarm(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t fan1_alarm_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct gpio_fan_data *fan_data = dev_get_drvdata(dev); struct gpio_fan_alarm *alarm = fan_data->alarm; @@ -90,7 +90,7 @@ static ssize_t show_fan_alarm(struct device *dev, return sprintf(buf, "%d\n", value); } -static DEVICE_ATTR(fan1_alarm, S_IRUGO, show_fan_alarm, NULL); +static DEVICE_ATTR_RO(fan1_alarm); static int fan_alarm_init(struct gpio_fan_data *fan_data, struct gpio_fan_alarm *alarm) @@ -188,8 +188,8 @@ static int rpm_to_speed_index(struct gpio_fan_data *fan_data, unsigned long rpm) return fan_data->num_speed - 1; } -static ssize_t show_pwm(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t pwm1_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct gpio_fan_data *fan_data = dev_get_drvdata(dev); u8 pwm = fan_data->speed_index * 255 / (fan_data->num_speed - 1); @@ -197,8 +197,8 @@ static ssize_t show_pwm(struct device *dev, return sprintf(buf, "%d\n", pwm); } -static ssize_t set_pwm(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct gpio_fan_data *fan_data = dev_get_drvdata(dev); unsigned long pwm; @@ -224,16 +224,17 @@ exit_unlock: return ret; } -static ssize_t show_pwm_enable(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t pwm1_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct gpio_fan_data *fan_data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", fan_data->pwm_enable); } -static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t pwm1_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct gpio_fan_data *fan_data = dev_get_drvdata(dev); unsigned long val; @@ -257,22 +258,22 @@ static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr, return count; } -static ssize_t show_pwm_mode(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t pwm1_mode_show(struct device *dev, + struct device_attribute *attr, char *buf) { return sprintf(buf, "0\n"); } -static ssize_t show_rpm_min(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t fan1_min_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct gpio_fan_data *fan_data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", fan_data->speed[0].rpm); } -static ssize_t show_rpm_max(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t fan1_max_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct gpio_fan_data *fan_data = dev_get_drvdata(dev); @@ -280,8 +281,8 @@ static ssize_t show_rpm_max(struct device *dev, fan_data->speed[fan_data->num_speed - 1].rpm); } -static ssize_t show_rpm(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t fan1_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct gpio_fan_data *fan_data = dev_get_drvdata(dev); @@ -313,14 +314,13 @@ exit_unlock: return ret; } -static DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm, set_pwm); -static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, - show_pwm_enable, set_pwm_enable); -static DEVICE_ATTR(pwm1_mode, S_IRUGO, show_pwm_mode, NULL); -static DEVICE_ATTR(fan1_min, S_IRUGO, show_rpm_min, NULL); -static DEVICE_ATTR(fan1_max, S_IRUGO, show_rpm_max, NULL); -static DEVICE_ATTR(fan1_input, S_IRUGO, show_rpm, NULL); -static DEVICE_ATTR(fan1_target, S_IRUGO | S_IWUSR, show_rpm, set_rpm); +static DEVICE_ATTR_RW(pwm1); +static DEVICE_ATTR_RW(pwm1_enable); +static DEVICE_ATTR_RO(pwm1_mode); +static DEVICE_ATTR_RO(fan1_min); +static DEVICE_ATTR_RO(fan1_max); +static DEVICE_ATTR_RO(fan1_input); +static DEVICE_ATTR(fan1_target, S_IRUGO | S_IWUSR, fan1_input_show, set_rpm); static umode_t gpio_fan_is_visible(struct kobject *kobj, struct attribute *attr, int index) diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 3932f9276c07..28375d59cc36 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -63,11 +63,11 @@ struct hwmon_thermal_data { }; static ssize_t -show_name(struct device *dev, struct device_attribute *attr, char *buf) +name_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%s\n", to_hwmon_device(dev)->name); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static struct attribute *hwmon_dev_attrs[] = { &dev_attr_name.attr, @@ -544,9 +544,11 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, struct device *hdev; int i, j, err, id; - /* Do not accept invalid characters in hwmon name attribute */ + /* Complain about invalid characters in hwmon name attribute */ if (name && (!strlen(name) || strpbrk(name, "-* \t\n"))) - return ERR_PTR(-EINVAL); + dev_warn(dev, + "hwmon: '%s' is not a valid name attribute, please fix\n", + name); id = ida_simple_get(&hwmon_ida, 0, 0, GFP_KERNEL); if (id < 0) @@ -606,7 +608,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, if (err) goto free_hwmon; - if (chip && chip->ops->read && + if (dev && chip && chip->ops->read && chip->info[0]->type == hwmon_chip && (chip->info[0]->config[0] & HWMON_C_REGISTER_TZ)) { const struct hwmon_channel_info **info = chip->info; @@ -651,6 +653,9 @@ hwmon_device_register_with_groups(struct device *dev, const char *name, void *drvdata, const struct attribute_group **groups) { + if (!name) + return ERR_PTR(-EINVAL); + return __hwmon_device_register(dev, name, drvdata, NULL, groups); } EXPORT_SYMBOL_GPL(hwmon_device_register_with_groups); @@ -674,6 +679,9 @@ hwmon_device_register_with_info(struct device *dev, const char *name, const struct hwmon_chip_info *chip, const struct attribute_group **extra_groups) { + if (!name) + return ERR_PTR(-EINVAL); + if (chip && (!chip->ops || !chip->ops->is_visible || !chip->info)) return ERR_PTR(-EINVAL); @@ -695,7 +703,7 @@ struct device *hwmon_device_register(struct device *dev) dev_warn(dev, "hwmon_device_register() is deprecated. Please convert the driver to use hwmon_device_register_with_info().\n"); - return hwmon_device_register_with_groups(dev, NULL, NULL, NULL); + return __hwmon_device_register(dev, NULL, NULL, NULL, NULL); } EXPORT_SYMBOL_GPL(hwmon_device_register); diff --git a/drivers/hwmon/i5500_temp.c b/drivers/hwmon/i5500_temp.c index 3e3ccbf18b4e..400e0675a90b 100644 --- a/drivers/hwmon/i5500_temp.c +++ b/drivers/hwmon/i5500_temp.c @@ -43,8 +43,8 @@ */ /* Sensor resolution : 0.5 degree C */ -static ssize_t show_temp(struct device *dev, - struct device_attribute *devattr, char *buf) +static ssize_t temp1_input_show(struct device *dev, + struct device_attribute *devattr, char *buf) { struct pci_dev *pdev = to_pci_dev(dev->parent); long temp; @@ -83,7 +83,7 @@ static ssize_t show_alarm(struct device *dev, return sprintf(buf, "%u\n", (unsigned int)ctsts & (1 << nr)); } -static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL); +static DEVICE_ATTR_RO(temp1_input); static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_thresh, NULL, 0xE2); static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IRUGO, show_thresh, NULL, 0xEC); static SENSOR_DEVICE_ATTR(temp1_max, S_IRUGO, show_thresh, NULL, 0xEE); diff --git a/drivers/hwmon/i5k_amb.c b/drivers/hwmon/i5k_amb.c index 6b3d1972cef7..a5a9f457b7f7 100644 --- a/drivers/hwmon/i5k_amb.c +++ b/drivers/hwmon/i5k_amb.c @@ -114,14 +114,14 @@ struct i5k_amb_data { unsigned int num_attrs; }; -static ssize_t show_name(struct device *dev, struct device_attribute *devattr, +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf) { return sprintf(buf, "%s\n", DRVNAME); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static struct platform_device *amb_pdev; diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index ad82cb28d87a..efb01c247e2d 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -12,6 +12,7 @@ * * Supports: IT8603E Super I/O chip w/LPC interface * IT8620E Super I/O chip w/LPC interface + * IT8622E Super I/O chip w/LPC interface * IT8623E Super I/O chip w/LPC interface * IT8628E Super I/O chip w/LPC interface * IT8705F Super I/O chip w/LPC interface @@ -31,6 +32,7 @@ * IT8783E/F Super I/O chip w/LPC interface * IT8786E Super I/O chip w/LPC interface * IT8790E Super I/O chip w/LPC interface + * IT8792E Super I/O chip w/LPC interface * Sis950 A clone of the IT8705F * * Copyright (C) 2001 Chris Gauthron @@ -69,8 +71,8 @@ #define DRVNAME "it87" enum chips { it87, it8712, it8716, it8718, it8720, it8721, it8728, it8732, - it8771, it8772, it8781, it8782, it8783, it8786, it8790, it8603, - it8620, it8628 }; + it8771, it8772, it8781, it8782, it8783, it8786, it8790, + it8792, it8603, it8620, it8622, it8628 }; static unsigned short force_id; module_param(force_id, ushort, 0); @@ -151,6 +153,7 @@ static inline void superio_exit(int ioreg) #define IT8726F_DEVID 0x8726 #define IT8728F_DEVID 0x8728 #define IT8732F_DEVID 0x8732 +#define IT8792E_DEVID 0x8733 #define IT8771E_DEVID 0x8771 #define IT8772E_DEVID 0x8772 #define IT8781F_DEVID 0x8781 @@ -160,6 +163,7 @@ static inline void superio_exit(int ioreg) #define IT8790E_DEVID 0x8790 #define IT8603E_DEVID 0x8603 #define IT8620E_DEVID 0x8620 +#define IT8622E_DEVID 0x8622 #define IT8623E_DEVID 0x8623 #define IT8628E_DEVID 0x8628 #define IT87_ACT_REG 0x30 @@ -293,9 +297,11 @@ struct it87_devices { #define FEAT_SIX_FANS BIT(11) /* Supports six fans */ #define FEAT_10_9MV_ADC BIT(12) #define FEAT_AVCC3 BIT(13) /* Chip supports in9/AVCC3 */ -#define FEAT_SIX_PWM BIT(14) /* Chip supports 6 pwm chn */ -#define FEAT_PWM_FREQ2 BIT(15) /* Separate pwm freq 2 */ -#define FEAT_SIX_TEMP BIT(16) /* Up to 6 temp sensors */ +#define FEAT_FIVE_PWM BIT(14) /* Chip supports 5 pwm chn */ +#define FEAT_SIX_PWM BIT(15) /* Chip supports 6 pwm chn */ +#define FEAT_PWM_FREQ2 BIT(16) /* Separate pwm freq 2 */ +#define FEAT_SIX_TEMP BIT(17) /* Up to 6 temp sensors */ +#define FEAT_VIN3_5V BIT(18) /* VIN3 connected to +5V */ static const struct it87_devices it87_devices[] = { [it87] = { @@ -419,6 +425,15 @@ static const struct it87_devices it87_devices[] = { | FEAT_PWM_FREQ2, .peci_mask = 0x07, }, + [it8792] = { + .name = "it8792", + .suffix = "E", + .features = FEAT_NEWER_AUTOPWM | FEAT_16BIT_FANS + | FEAT_TEMP_OFFSET | FEAT_TEMP_OLD_PECI | FEAT_TEMP_PECI + | FEAT_10_9MV_ADC | FEAT_IN7_INTERNAL, + .peci_mask = 0x07, + .old_peci_mask = 0x02, /* Actually reports PCH */ + }, [it8603] = { .name = "it8603", .suffix = "E", @@ -433,7 +448,16 @@ static const struct it87_devices it87_devices[] = { .features = FEAT_NEWER_AUTOPWM | FEAT_12MV_ADC | FEAT_16BIT_FANS | FEAT_TEMP_OFFSET | FEAT_TEMP_PECI | FEAT_SIX_FANS | FEAT_IN7_INTERNAL | FEAT_SIX_PWM | FEAT_PWM_FREQ2 - | FEAT_SIX_TEMP, + | FEAT_SIX_TEMP | FEAT_VIN3_5V, + .peci_mask = 0x07, + }, + [it8622] = { + .name = "it8622", + .suffix = "E", + .features = FEAT_NEWER_AUTOPWM | FEAT_12MV_ADC | FEAT_16BIT_FANS + | FEAT_TEMP_OFFSET | FEAT_TEMP_PECI | FEAT_FIVE_FANS + | FEAT_FIVE_PWM | FEAT_IN7_INTERNAL | FEAT_PWM_FREQ2 + | FEAT_AVCC3 | FEAT_VIN3_5V, .peci_mask = 0x07, }, [it8628] = { @@ -442,7 +466,7 @@ static const struct it87_devices it87_devices[] = { .features = FEAT_NEWER_AUTOPWM | FEAT_12MV_ADC | FEAT_16BIT_FANS | FEAT_TEMP_OFFSET | FEAT_TEMP_PECI | FEAT_SIX_FANS | FEAT_IN7_INTERNAL | FEAT_SIX_PWM | FEAT_PWM_FREQ2 - | FEAT_SIX_TEMP, + | FEAT_SIX_TEMP | FEAT_VIN3_5V, .peci_mask = 0x07, }, }; @@ -465,9 +489,12 @@ static const struct it87_devices it87_devices[] = { #define has_in7_internal(data) ((data)->features & FEAT_IN7_INTERNAL) #define has_six_fans(data) ((data)->features & FEAT_SIX_FANS) #define has_avcc3(data) ((data)->features & FEAT_AVCC3) +#define has_five_pwm(data) ((data)->features & (FEAT_FIVE_PWM \ + | FEAT_SIX_PWM)) #define has_six_pwm(data) ((data)->features & FEAT_SIX_PWM) #define has_pwm_freq2(data) ((data)->features & FEAT_PWM_FREQ2) #define has_six_temp(data) ((data)->features & FEAT_SIX_TEMP) +#define has_vin3_5v(data) ((data)->features & FEAT_VIN3_5V) struct it87_sio_data { enum chips type; @@ -1300,25 +1327,35 @@ static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr, it87_write_value(data, IT87_REG_FAN_MAIN_CTRL, data->fan_main_ctrl); } else { + u8 ctrl; + /* No on/off mode, set maximum pwm value */ data->pwm_duty[nr] = pwm_to_reg(data, 0xff); it87_write_value(data, IT87_REG_PWM_DUTY[nr], data->pwm_duty[nr]); /* and set manual mode */ - data->pwm_ctrl[nr] = has_newer_autopwm(data) ? - data->pwm_temp_map[nr] : - data->pwm_duty[nr]; - it87_write_value(data, IT87_REG_PWM[nr], - data->pwm_ctrl[nr]); + if (has_newer_autopwm(data)) { + ctrl = (data->pwm_ctrl[nr] & 0x7c) | + data->pwm_temp_map[nr]; + } else { + ctrl = data->pwm_duty[nr]; + } + data->pwm_ctrl[nr] = ctrl; + it87_write_value(data, IT87_REG_PWM[nr], ctrl); } } else { - if (val == 1) /* Manual mode */ - data->pwm_ctrl[nr] = has_newer_autopwm(data) ? - data->pwm_temp_map[nr] : - data->pwm_duty[nr]; - else /* Automatic mode */ - data->pwm_ctrl[nr] = 0x80 | data->pwm_temp_map[nr]; - it87_write_value(data, IT87_REG_PWM[nr], data->pwm_ctrl[nr]); + u8 ctrl; + + if (has_newer_autopwm(data)) { + ctrl = (data->pwm_ctrl[nr] & 0x7c) | + data->pwm_temp_map[nr]; + if (val != 1) + ctrl |= 0x80; + } else { + ctrl = (val == 1 ? data->pwm_duty[nr] : 0x80); + } + data->pwm_ctrl[nr] = ctrl; + it87_write_value(data, IT87_REG_PWM[nr], ctrl); if (data->type != it8603 && nr < 3) { /* set SmartGuardian mode */ @@ -1344,6 +1381,7 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute *attr, return -EINVAL; mutex_lock(&data->update_lock); + it87_update_pwm_ctrl(data, nr); if (has_newer_autopwm(data)) { /* * If we are in automatic mode, the PWM duty cycle register @@ -1456,13 +1494,15 @@ static ssize_t set_pwm_temp_map(struct device *dev, } mutex_lock(&data->update_lock); + it87_update_pwm_ctrl(data, nr); data->pwm_temp_map[nr] = reg; /* * If we are in automatic mode, write the temp mapping immediately; * otherwise, just store it for later use. */ if (data->pwm_ctrl[nr] & 0x80) { - data->pwm_ctrl[nr] = 0x80 | data->pwm_temp_map[nr]; + data->pwm_ctrl[nr] = (data->pwm_ctrl[nr] & 0xfc) | + data->pwm_temp_map[nr]; it87_write_value(data, IT87_REG_PWM[nr], data->pwm_ctrl[nr]); } mutex_unlock(&data->update_lock); @@ -1762,14 +1802,14 @@ static SENSOR_DEVICE_ATTR(pwm6_auto_slope, S_IRUGO | S_IWUSR, show_auto_pwm_slope, set_auto_pwm_slope, 5); /* Alarms */ -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct it87_data *data = it87_update_device(dev); return sprintf(buf, "%u\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) @@ -1877,16 +1917,16 @@ static SENSOR_DEVICE_ATTR(temp1_beep, S_IRUGO | S_IWUSR, static SENSOR_DEVICE_ATTR(temp2_beep, S_IRUGO, show_beep, NULL, 2); static SENSOR_DEVICE_ATTR(temp3_beep, S_IRUGO, show_beep, NULL, 2); -static ssize_t show_vrm_reg(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t vrm_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct it87_data *data = dev_get_drvdata(dev); return sprintf(buf, "%u\n", data->vrm); } -static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct it87_data *data = dev_get_drvdata(dev); unsigned long val; @@ -1898,16 +1938,16 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg); +static DEVICE_ATTR_RW(vrm); -static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct it87_data *data = it87_update_device(dev); return sprintf(buf, "%ld\n", (long)vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL); +static DEVICE_ATTR_RO(cpu0_vid); static ssize_t show_label(struct device *dev, struct device_attribute *attr, char *buf) @@ -1916,17 +1956,21 @@ static ssize_t show_label(struct device *dev, struct device_attribute *attr, "+5V", "5VSB", "Vbat", + "AVCC", }; static const char * const labels_it8721[] = { "+3.3V", "3VSB", "Vbat", + "+3.3V", }; struct it87_data *data = dev_get_drvdata(dev); int nr = to_sensor_dev_attr(attr)->index; const char *label; - if (has_12mv_adc(data) || has_10_9mv_adc(data)) + if (has_vin3_5v(data) && nr == 0) + label = labels[0]; + else if (has_12mv_adc(data) || has_10_9mv_adc(data)) label = labels_it8721[nr]; else label = labels[nr]; @@ -1937,7 +1981,7 @@ static SENSOR_DEVICE_ATTR(in3_label, S_IRUGO, show_label, NULL, 0); static SENSOR_DEVICE_ATTR(in7_label, S_IRUGO, show_label, NULL, 1); static SENSOR_DEVICE_ATTR(in8_label, S_IRUGO, show_label, NULL, 2); /* AVCC3 */ -static SENSOR_DEVICE_ATTR(in9_label, S_IRUGO, show_label, NULL, 0); +static SENSOR_DEVICE_ATTR(in9_label, S_IRUGO, show_label, NULL, 3); static umode_t it87_in_is_visible(struct kobject *kobj, struct attribute *attr, int index) @@ -2386,6 +2430,9 @@ static int __init it87_find(int sioaddr, unsigned short *address, case IT8732F_DEVID: sio_data->type = it8732; break; + case IT8792E_DEVID: + sio_data->type = it8792; + break; case IT8771E_DEVID: sio_data->type = it8771; break; @@ -2414,6 +2461,9 @@ static int __init it87_find(int sioaddr, unsigned short *address, case IT8620E_DEVID: sio_data->type = it8620; break; + case IT8622E_DEVID: + sio_data->type = it8622; + break; case IT8628E_DEVID: sio_data->type = it8628; break; @@ -2457,8 +2507,10 @@ static int __init it87_find(int sioaddr, unsigned short *address, else sio_data->skip_in |= BIT(9); - if (!has_six_pwm(config)) + if (!has_five_pwm(config)) sio_data->skip_pwm |= BIT(3) | BIT(4) | BIT(5); + else if (!has_six_pwm(config)) + sio_data->skip_pwm |= BIT(5); if (!has_vid(config)) sio_data->skip_vid = 1; @@ -2587,7 +2639,7 @@ static int __init it87_find(int sioaddr, unsigned short *address, /* Check for pwm4 */ reg = superio_inb(sioaddr, IT87_SIO_GPIO4_REG); - if (!(reg & BIT(2))) + if (reg & BIT(2)) sio_data->skip_pwm |= BIT(3); /* Check for pwm2, fan2 */ @@ -2602,6 +2654,50 @@ static int __init it87_find(int sioaddr, unsigned short *address, sio_data->skip_fan |= BIT(5); } + /* Check if AVCC is on VIN3 */ + reg = superio_inb(sioaddr, IT87_SIO_PINX2_REG); + if (reg & BIT(0)) + sio_data->internal |= BIT(0); + else + sio_data->skip_in |= BIT(9); + + sio_data->beep_pin = superio_inb(sioaddr, + IT87_SIO_BEEP_PIN_REG) & 0x3f; + } else if (sio_data->type == it8622) { + int reg; + + superio_select(sioaddr, GPIO); + + /* Check for pwm4, fan4 */ + reg = superio_inb(sioaddr, IT87_SIO_GPIO1_REG); + if (reg & BIT(6)) + sio_data->skip_fan |= BIT(3); + if (reg & BIT(5)) + sio_data->skip_pwm |= BIT(3); + + /* Check for pwm3, fan3, pwm5, fan5 */ + reg = superio_inb(sioaddr, IT87_SIO_GPIO3_REG); + if (reg & BIT(6)) + sio_data->skip_pwm |= BIT(2); + if (reg & BIT(7)) + sio_data->skip_fan |= BIT(2); + if (reg & BIT(3)) + sio_data->skip_pwm |= BIT(4); + if (reg & BIT(1)) + sio_data->skip_fan |= BIT(4); + + /* Check for pwm2, fan2 */ + reg = superio_inb(sioaddr, IT87_SIO_GPIO5_REG); + if (reg & BIT(1)) + sio_data->skip_pwm |= BIT(1); + if (reg & BIT(2)) + sio_data->skip_fan |= BIT(1); + + /* Check for AVCC */ + reg = superio_inb(sioaddr, IT87_SIO_PINX2_REG); + if (!(reg & BIT(0))) + sio_data->skip_in |= BIT(9); + sio_data->beep_pin = superio_inb(sioaddr, IT87_SIO_BEEP_PIN_REG) & 0x3f; } else { diff --git a/drivers/hwmon/jz4740-hwmon.c b/drivers/hwmon/jz4740-hwmon.c index 0621ee1b3c98..2d40a2e771d7 100644 --- a/drivers/hwmon/jz4740-hwmon.c +++ b/drivers/hwmon/jz4740-hwmon.c @@ -44,8 +44,8 @@ static irqreturn_t jz4740_hwmon_irq(int irq, void *data) return IRQ_HANDLED; } -static ssize_t jz4740_hwmon_read_adcin(struct device *dev, - struct device_attribute *dev_attr, char *buf) +static ssize_t in0_input_show(struct device *dev, + struct device_attribute *dev_attr, char *buf) { struct jz4740_hwmon *hwmon = dev_get_drvdata(dev); struct platform_device *pdev = hwmon->pdev; @@ -79,7 +79,7 @@ static ssize_t jz4740_hwmon_read_adcin(struct device *dev, return ret; } -static DEVICE_ATTR(in0_input, S_IRUGO, jz4740_hwmon_read_adcin, NULL); +static DEVICE_ATTR_RO(in0_input); static struct attribute *jz4740_attrs[] = { &dev_attr_in0_input.attr, diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 9cdfde6515ad..ce3b91f22e30 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -72,8 +72,8 @@ static void amd_nb_smu_index_read(struct pci_dev *pdev, unsigned int devfn, mutex_unlock(&nb_smu_ind_mutex); } -static ssize_t show_temp(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t temp1_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { u32 regval; struct pci_dev *pdev = dev_get_drvdata(dev); @@ -88,8 +88,8 @@ static ssize_t show_temp(struct device *dev, return sprintf(buf, "%u\n", (regval >> 21) * 125); } -static ssize_t show_temp_max(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t temp1_max_show(struct device *dev, + struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", 70 * 1000); } @@ -110,8 +110,8 @@ static ssize_t show_temp_crit(struct device *dev, return sprintf(buf, "%d\n", value); } -static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL); -static DEVICE_ATTR(temp1_max, S_IRUGO, show_temp_max, NULL); +static DEVICE_ATTR_RO(temp1_input); +static DEVICE_ATTR_RO(temp1_max); static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp_crit, NULL, 0); static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IRUGO, show_temp_crit, NULL, 1); diff --git a/drivers/hwmon/k8temp.c b/drivers/hwmon/k8temp.c index 734d55d48cc8..5a632bcf869b 100644 --- a/drivers/hwmon/k8temp.c +++ b/drivers/hwmon/k8temp.c @@ -100,7 +100,7 @@ static struct k8temp_data *k8temp_update_device(struct device *dev) * Sysfs stuff */ -static ssize_t show_name(struct device *dev, struct device_attribute +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct k8temp_data *data = dev_get_drvdata(dev); @@ -133,7 +133,7 @@ static SENSOR_DEVICE_ATTR_2(temp1_input, S_IRUGO, show_temp, NULL, 0, 0); static SENSOR_DEVICE_ATTR_2(temp2_input, S_IRUGO, show_temp, NULL, 0, 1); static SENSOR_DEVICE_ATTR_2(temp3_input, S_IRUGO, show_temp, NULL, 1, 0); static SENSOR_DEVICE_ATTR_2(temp4_input, S_IRUGO, show_temp, NULL, 1, 1); -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static const struct pci_device_id k8temp_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, diff --git a/drivers/hwmon/lm63.c b/drivers/hwmon/lm63.c index 33bfdb444138..2e1948699114 100644 --- a/drivers/hwmon/lm63.c +++ b/drivers/hwmon/lm63.c @@ -417,16 +417,16 @@ static ssize_t set_pwm1(struct device *dev, struct device_attribute *devattr, return count; } -static ssize_t show_pwm1_enable(struct device *dev, +static ssize_t pwm1_enable_show(struct device *dev, struct device_attribute *dummy, char *buf) { struct lm63_data *data = lm63_update_device(dev); return sprintf(buf, "%d\n", data->config_fan & 0x20 ? 1 : 2); } -static ssize_t set_pwm1_enable(struct device *dev, - struct device_attribute *dummy, - const char *buf, size_t count) +static ssize_t pwm1_enable_store(struct device *dev, + struct device_attribute *dummy, + const char *buf, size_t count) { struct lm63_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -600,7 +600,7 @@ static ssize_t set_temp11(struct device *dev, struct device_attribute *devattr, * Hysteresis register holds a relative value, while we want to present * an absolute to user-space */ -static ssize_t show_temp2_crit_hyst(struct device *dev, +static ssize_t temp2_crit_hyst_show(struct device *dev, struct device_attribute *dummy, char *buf) { struct lm63_data *data = lm63_update_device(dev); @@ -624,9 +624,9 @@ static ssize_t show_lut_temp_hyst(struct device *dev, * And now the other way around, user-space provides an absolute * hysteresis value and we have to store a relative one */ -static ssize_t set_temp2_crit_hyst(struct device *dev, - struct device_attribute *dummy, - const char *buf, size_t count) +static ssize_t temp2_crit_hyst_store(struct device *dev, + struct device_attribute *dummy, + const char *buf, size_t count) { struct lm63_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -670,7 +670,7 @@ static void lm63_set_convrate(struct lm63_data *data, unsigned int interval) data->update_interval = UPDATE_INTERVAL(data->max_convrate_hz, i); } -static ssize_t show_update_interval(struct device *dev, +static ssize_t update_interval_show(struct device *dev, struct device_attribute *attr, char *buf) { struct lm63_data *data = dev_get_drvdata(dev); @@ -678,9 +678,9 @@ static ssize_t show_update_interval(struct device *dev, return sprintf(buf, "%u\n", data->update_interval); } -static ssize_t set_update_interval(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t update_interval_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct lm63_data *data = dev_get_drvdata(dev); unsigned long val; @@ -697,16 +697,17 @@ static ssize_t set_update_interval(struct device *dev, return count; } -static ssize_t show_type(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t temp2_type_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lm63_data *data = dev_get_drvdata(dev); return sprintf(buf, data->trutherm ? "1\n" : "2\n"); } -static ssize_t set_type(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t temp2_type_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct lm63_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -731,7 +732,7 @@ static ssize_t set_type(struct device *dev, struct device_attribute *attr, return count; } -static ssize_t show_alarms(struct device *dev, struct device_attribute *dummy, +static ssize_t alarms_show(struct device *dev, struct device_attribute *dummy, char *buf) { struct lm63_data *data = lm63_update_device(dev); @@ -753,8 +754,7 @@ static SENSOR_DEVICE_ATTR(fan1_min, S_IWUSR | S_IRUGO, show_fan, set_fan, 1); static SENSOR_DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, show_pwm1, set_pwm1, 0); -static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO, - show_pwm1_enable, set_pwm1_enable); +static DEVICE_ATTR_RW(pwm1_enable); static SENSOR_DEVICE_ATTR(pwm1_auto_point1_pwm, S_IWUSR | S_IRUGO, show_pwm1, set_pwm1, 1); static SENSOR_DEVICE_ATTR(pwm1_auto_point1_temp, S_IWUSR | S_IRUGO, @@ -841,10 +841,9 @@ static SENSOR_DEVICE_ATTR(temp2_offset, S_IWUSR | S_IRUGO, show_temp11, set_temp11, 3); static SENSOR_DEVICE_ATTR(temp2_crit, S_IRUGO, show_remote_temp8, set_temp8, 2); -static DEVICE_ATTR(temp2_crit_hyst, S_IWUSR | S_IRUGO, show_temp2_crit_hyst, - set_temp2_crit_hyst); +static DEVICE_ATTR_RW(temp2_crit_hyst); -static DEVICE_ATTR(temp2_type, S_IWUSR | S_IRUGO, show_type, set_type); +static DEVICE_ATTR_RW(temp2_type); /* Individual alarm files */ static SENSOR_DEVICE_ATTR(fan1_min_alarm, S_IRUGO, show_alarm, NULL, 0); @@ -854,10 +853,9 @@ static SENSOR_DEVICE_ATTR(temp2_min_alarm, S_IRUGO, show_alarm, NULL, 3); static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 4); static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 6); /* Raw alarm file for compatibility */ -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); -static DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, show_update_interval, - set_update_interval); +static DEVICE_ATTR_RW(update_interval); static struct attribute *lm63_attributes[] = { &sensor_dev_attr_pwm1.dev_attr.attr, diff --git a/drivers/hwmon/lm70.c b/drivers/hwmon/lm70.c index 583f883a4cfe..543556dc563b 100644 --- a/drivers/hwmon/lm70.c +++ b/drivers/hwmon/lm70.c @@ -46,6 +46,7 @@ #define LM70_CHIP_TMP121 1 /* TI TMP121/TMP123 */ #define LM70_CHIP_LM71 2 /* NS LM71 */ #define LM70_CHIP_LM74 3 /* NS LM74 */ +#define LM70_CHIP_TMP122 4 /* TI TMP122/TMP124 */ struct lm70 { struct spi_device *spi; @@ -54,8 +55,8 @@ struct lm70 { }; /* sysfs hook function */ -static ssize_t lm70_sense_temp(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t temp1_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lm70 *p_lm70 = dev_get_drvdata(dev); struct spi_device *spi = p_lm70->spi; @@ -72,7 +73,8 @@ static ssize_t lm70_sense_temp(struct device *dev, */ status = spi_write_then_read(spi, NULL, 0, &rxbuf[0], 2); if (status < 0) { - pr_warn("spi_write_then_read failed with status %d\n", status); + dev_warn(dev, "spi_write_then_read failed with status %d\n", + status); goto out; } raw = (rxbuf[0] << 8) + rxbuf[1]; @@ -91,7 +93,7 @@ static ssize_t lm70_sense_temp(struct device *dev, * Celsius. * So it's equivalent to multiplying by 0.25 * 1000 = 250. * - * LM74 and TMP121/TMP123: + * LM74 and TMP121/TMP122/TMP123/TMP124: * 13 bits of 2's complement data, discard LSB 3 bits, * resolution 0.0625 degrees celsius. * @@ -105,6 +107,7 @@ static ssize_t lm70_sense_temp(struct device *dev, break; case LM70_CHIP_TMP121: + case LM70_CHIP_TMP122: case LM70_CHIP_LM74: val = ((int)raw / 8) * 625 / 10; break; @@ -120,7 +123,7 @@ out: return status; } -static DEVICE_ATTR(temp1_input, S_IRUGO, lm70_sense_temp, NULL); +static DEVICE_ATTR_RO(temp1_input); static struct attribute *lm70_attrs[] = { &dev_attr_temp1_input.attr, @@ -142,6 +145,10 @@ static const struct of_device_id lm70_of_ids[] = { .data = (void *) LM70_CHIP_TMP121, }, { + .compatible = "ti,tmp122", + .data = (void *) LM70_CHIP_TMP122, + }, + { .compatible = "ti,lm71", .data = (void *) LM70_CHIP_LM71, }, @@ -190,6 +197,7 @@ static int lm70_probe(struct spi_device *spi) static const struct spi_device_id lm70_ids[] = { { "lm70", LM70_CHIP_LM70 }, { "tmp121", LM70_CHIP_TMP121 }, + { "tmp122", LM70_CHIP_TMP122 }, { "lm71", LM70_CHIP_LM71 }, { "lm74", LM70_CHIP_LM74 }, { }, diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c index 539efe4ad991..0cb7ff613b80 100644 --- a/drivers/hwmon/lm78.c +++ b/drivers/hwmon/lm78.c @@ -236,22 +236,23 @@ show_in_offset(5); show_in_offset(6); /* Temperature */ -static ssize_t show_temp(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t temp1_input_show(struct device *dev, + struct device_attribute *da, char *buf) { struct lm78_data *data = lm78_update_device(dev); return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp)); } -static ssize_t show_temp_over(struct device *dev, struct device_attribute *da, +static ssize_t temp1_max_show(struct device *dev, struct device_attribute *da, char *buf) { struct lm78_data *data = lm78_update_device(dev); return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_over)); } -static ssize_t set_temp_over(struct device *dev, struct device_attribute *da, - const char *buf, size_t count) +static ssize_t temp1_max_store(struct device *dev, + struct device_attribute *da, const char *buf, + size_t count) { struct lm78_data *data = dev_get_drvdata(dev); long val; @@ -268,15 +269,16 @@ static ssize_t set_temp_over(struct device *dev, struct device_attribute *da, return count; } -static ssize_t show_temp_hyst(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t temp1_max_hyst_show(struct device *dev, + struct device_attribute *da, char *buf) { struct lm78_data *data = lm78_update_device(dev); return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_hyst)); } -static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *da, - const char *buf, size_t count) +static ssize_t temp1_max_hyst_store(struct device *dev, + struct device_attribute *da, + const char *buf, size_t count) { struct lm78_data *data = dev_get_drvdata(dev); long val; @@ -293,11 +295,9 @@ static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *da, return count; } -static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL); -static DEVICE_ATTR(temp1_max, S_IRUGO | S_IWUSR, - show_temp_over, set_temp_over); -static DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR, - show_temp_hyst, set_temp_hyst); +static DEVICE_ATTR_RO(temp1_input); +static DEVICE_ATTR_RW(temp1_max); +static DEVICE_ATTR_RW(temp1_max_hyst); /* 3 Fans */ static ssize_t show_fan(struct device *dev, struct device_attribute *da, @@ -431,22 +431,22 @@ static SENSOR_DEVICE_ATTR(fan2_div, S_IRUGO | S_IWUSR, static SENSOR_DEVICE_ATTR(fan3_div, S_IRUGO, show_fan_div, NULL, 2); /* VID */ -static ssize_t show_vid(struct device *dev, struct device_attribute *da, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, struct device_attribute *da, + char *buf) { struct lm78_data *data = lm78_update_device(dev); return sprintf(buf, "%d\n", vid_from_reg(data->vid, 82)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); /* Alarms */ -static ssize_t show_alarms(struct device *dev, struct device_attribute *da, +static ssize_t alarms_show(struct device *dev, struct device_attribute *da, char *buf) { struct lm78_data *data = lm78_update_device(dev); return sprintf(buf, "%u\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *da, char *buf) diff --git a/drivers/hwmon/lm80.c b/drivers/hwmon/lm80.c index 4bcd9b882948..08e3945a6fbf 100644 --- a/drivers/hwmon/lm80.c +++ b/drivers/hwmon/lm80.c @@ -432,7 +432,7 @@ static ssize_t set_temp(struct device *dev, struct device_attribute *devattr, return count; } -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct lm80_data *data = lm80_update_device(dev); @@ -505,7 +505,7 @@ static SENSOR_DEVICE_ATTR(temp1_crit, S_IWUSR | S_IRUGO, show_temp, set_temp, t_os_max); static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IWUSR | S_IRUGO, show_temp, set_temp, t_os_hyst); -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0); static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1); static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2); diff --git a/drivers/hwmon/lm83.c b/drivers/hwmon/lm83.c index 9e4d0e1d3c4b..cbfd0bb7f135 100644 --- a/drivers/hwmon/lm83.c +++ b/drivers/hwmon/lm83.c @@ -188,7 +188,7 @@ static ssize_t set_temp(struct device *dev, struct device_attribute *devattr, return count; } -static ssize_t show_alarms(struct device *dev, struct device_attribute *dummy, +static ssize_t alarms_show(struct device *dev, struct device_attribute *dummy, char *buf) { struct lm83_data *data = lm83_update_device(dev); @@ -236,7 +236,7 @@ static SENSOR_DEVICE_ATTR(temp4_max_alarm, S_IRUGO, show_alarm, NULL, 12); static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 13); static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 15); /* Raw alarm file for compatibility */ -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static struct attribute *lm83_attributes[] = { &sensor_dev_attr_temp1_input.dev_attr.attr, diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c index 29c8136ce9c5..691469ffa24e 100644 --- a/drivers/hwmon/lm85.c +++ b/drivers/hwmon/lm85.c @@ -604,8 +604,8 @@ show_fan_offset(4); /* vid, vrm, alarms */ -static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lm85_data *data = lm85_update_device(dev); int vid; @@ -621,17 +621,17 @@ static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%d\n", vid); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL); +static DEVICE_ATTR_RO(cpu0_vid); -static ssize_t show_vrm_reg(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t vrm_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct lm85_data *data = dev_get_drvdata(dev); return sprintf(buf, "%ld\n", (long) data->vrm); } -static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct lm85_data *data = dev_get_drvdata(dev); unsigned long val; @@ -648,16 +648,16 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg); +static DEVICE_ATTR_RW(vrm); -static ssize_t show_alarms_reg(struct device *dev, struct device_attribute - *attr, char *buf) +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct lm85_data *data = lm85_update_device(dev); return sprintf(buf, "%u\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/drivers/hwmon/lm87.c b/drivers/hwmon/lm87.c index 13cca3606e06..e06faf9d3f0f 100644 --- a/drivers/hwmon/lm87.c +++ b/drivers/hwmon/lm87.c @@ -445,23 +445,23 @@ set_temp(1); set_temp(2); set_temp(3); -static ssize_t show_temp_crit_int(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t temp1_crit_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lm87_data *data = lm87_update_device(dev); return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_crit_int)); } -static ssize_t show_temp_crit_ext(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t temp2_crit_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lm87_data *data = lm87_update_device(dev); return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_crit_ext)); } -static DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp_crit_int, NULL); -static DEVICE_ATTR(temp2_crit, S_IRUGO, show_temp_crit_ext, NULL); -static DEVICE_ATTR(temp3_crit, S_IRUGO, show_temp_crit_ext, NULL); +static DEVICE_ATTR_RO(temp1_crit); +static DEVICE_ATTR_RO(temp2_crit); +static DEVICE_ATTR(temp3_crit, S_IRUGO, temp2_crit_show, NULL); static ssize_t show_fan_input(struct device *dev, struct device_attribute *attr, char *buf) @@ -586,30 +586,30 @@ static SENSOR_DEVICE_ATTR(fan##offset##_div, S_IRUGO | S_IWUSR, \ set_fan(1); set_fan(2); -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct lm87_data *data = lm87_update_device(dev); return sprintf(buf, "%d\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); -static ssize_t show_vid(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lm87_data *data = lm87_update_device(dev); return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); -static ssize_t show_vrm(struct device *dev, struct device_attribute *attr, +static ssize_t vrm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct lm87_data *data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", data->vrm); } -static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct lm87_data *data = dev_get_drvdata(dev); unsigned long val; @@ -625,16 +625,17 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, data->vrm = val; return count; } -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm); +static DEVICE_ATTR_RW(vrm); -static ssize_t show_aout(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t aout_output_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lm87_data *data = lm87_update_device(dev); return sprintf(buf, "%d\n", AOUT_FROM_REG(data->aout)); } -static ssize_t set_aout(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t aout_output_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct i2c_client *client = dev_get_drvdata(dev); struct lm87_data *data = i2c_get_clientdata(client); @@ -651,7 +652,7 @@ static ssize_t set_aout(struct device *dev, struct device_attribute *attr, mutex_unlock(&data->update_lock); return count; } -static DEVICE_ATTR(aout_output, S_IRUGO | S_IWUSR, show_aout, set_aout); +static DEVICE_ATTR_RW(aout_output); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c index 841f2428e84a..aff5297bc2bc 100644 --- a/drivers/hwmon/lm90.c +++ b/drivers/hwmon/lm90.c @@ -830,7 +830,7 @@ static u16 temp_to_u16_adt7461(struct lm90_data *data, long val) } /* pec used for ADM1032 only */ -static ssize_t show_pec(struct device *dev, struct device_attribute *dummy, +static ssize_t pec_show(struct device *dev, struct device_attribute *dummy, char *buf) { struct i2c_client *client = to_i2c_client(dev); @@ -838,8 +838,8 @@ static ssize_t show_pec(struct device *dev, struct device_attribute *dummy, return sprintf(buf, "%d\n", !!(client->flags & I2C_CLIENT_PEC)); } -static ssize_t set_pec(struct device *dev, struct device_attribute *dummy, - const char *buf, size_t count) +static ssize_t pec_store(struct device *dev, struct device_attribute *dummy, + const char *buf, size_t count) { struct i2c_client *client = to_i2c_client(dev); long val; @@ -863,7 +863,7 @@ static ssize_t set_pec(struct device *dev, struct device_attribute *dummy, return count; } -static DEVICE_ATTR(pec, S_IWUSR | S_IRUGO, show_pec, set_pec); +static DEVICE_ATTR_RW(pec); static int lm90_get_temp11(struct lm90_data *data, int index) { diff --git a/drivers/hwmon/lm92.c b/drivers/hwmon/lm92.c index cfaf70b9cba7..2a91974a10bb 100644 --- a/drivers/hwmon/lm92.c +++ b/drivers/hwmon/lm92.c @@ -181,8 +181,8 @@ static ssize_t show_temp_hyst(struct device *dev, - TEMP_FROM_REG(data->temp[t_hyst])); } -static ssize_t show_temp_min_hyst(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t temp1_min_hyst_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lm92_data *data = lm92_update_device(dev); return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp[t_min]) @@ -213,7 +213,7 @@ static ssize_t set_temp_hyst(struct device *dev, return count; } -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct lm92_data *data = lm92_update_device(dev); @@ -235,11 +235,11 @@ static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IWUSR | S_IRUGO, show_temp_hyst, set_temp_hyst, t_crit); static SENSOR_DEVICE_ATTR(temp1_min, S_IWUSR | S_IRUGO, show_temp, set_temp, t_min); -static DEVICE_ATTR(temp1_min_hyst, S_IRUGO, show_temp_min_hyst, NULL); +static DEVICE_ATTR_RO(temp1_min_hyst); static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_temp, set_temp, t_max); static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IRUGO, show_temp_hyst, NULL, t_max); -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, show_alarm, NULL, 2); static SENSOR_DEVICE_ATTR(temp1_min_alarm, S_IRUGO, show_alarm, NULL, 0); static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 1); diff --git a/drivers/hwmon/lm93.c b/drivers/hwmon/lm93.c index 90bb04858117..77a0a83399b3 100644 --- a/drivers/hwmon/lm93.c +++ b/drivers/hwmon/lm93.c @@ -2156,7 +2156,7 @@ static SENSOR_DEVICE_ATTR(pwm2_auto_spinup_time, S_IWUSR | S_IRUGO, show_pwm_auto_spinup_time, store_pwm_auto_spinup_time, 1); -static ssize_t show_pwm_auto_prochot_ramp(struct device *dev, +static ssize_t pwm_auto_prochot_ramp_show(struct device *dev, struct device_attribute *attr, char *buf) { struct lm93_data *data = lm93_update_device(dev); @@ -2164,7 +2164,7 @@ static ssize_t show_pwm_auto_prochot_ramp(struct device *dev, LM93_RAMP_FROM_REG(data->pwm_ramp_ctl >> 4 & 0x0f)); } -static ssize_t store_pwm_auto_prochot_ramp(struct device *dev, +static ssize_t pwm_auto_prochot_ramp_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -2186,11 +2186,9 @@ static ssize_t store_pwm_auto_prochot_ramp(struct device *dev, return count; } -static DEVICE_ATTR(pwm_auto_prochot_ramp, S_IRUGO | S_IWUSR, - show_pwm_auto_prochot_ramp, - store_pwm_auto_prochot_ramp); +static DEVICE_ATTR_RW(pwm_auto_prochot_ramp); -static ssize_t show_pwm_auto_vrdhot_ramp(struct device *dev, +static ssize_t pwm_auto_vrdhot_ramp_show(struct device *dev, struct device_attribute *attr, char *buf) { struct lm93_data *data = lm93_update_device(dev); @@ -2198,7 +2196,7 @@ static ssize_t show_pwm_auto_vrdhot_ramp(struct device *dev, LM93_RAMP_FROM_REG(data->pwm_ramp_ctl & 0x0f)); } -static ssize_t store_pwm_auto_vrdhot_ramp(struct device *dev, +static ssize_t pwm_auto_vrdhot_ramp_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -2220,9 +2218,7 @@ static ssize_t store_pwm_auto_vrdhot_ramp(struct device *dev, return 0; } -static DEVICE_ATTR(pwm_auto_vrdhot_ramp, S_IRUGO | S_IWUSR, - show_pwm_auto_vrdhot_ramp, - store_pwm_auto_vrdhot_ramp); +static DEVICE_ATTR_RW(pwm_auto_vrdhot_ramp); static ssize_t show_vid(struct device *dev, struct device_attribute *attr, char *buf) @@ -2378,7 +2374,7 @@ static SENSOR_DEVICE_ATTR(prochot1_interval, S_IWUSR | S_IRUGO, static SENSOR_DEVICE_ATTR(prochot2_interval, S_IWUSR | S_IRUGO, show_prochot_interval, store_prochot_interval, 1); -static ssize_t show_prochot_override_duty_cycle(struct device *dev, +static ssize_t prochot_override_duty_cycle_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -2386,7 +2382,7 @@ static ssize_t show_prochot_override_duty_cycle(struct device *dev, return sprintf(buf, "%d\n", data->prochot_override & 0x0f); } -static ssize_t store_prochot_override_duty_cycle(struct device *dev, +static ssize_t prochot_override_duty_cycle_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -2408,18 +2404,16 @@ static ssize_t store_prochot_override_duty_cycle(struct device *dev, return count; } -static DEVICE_ATTR(prochot_override_duty_cycle, S_IRUGO | S_IWUSR, - show_prochot_override_duty_cycle, - store_prochot_override_duty_cycle); +static DEVICE_ATTR_RW(prochot_override_duty_cycle); -static ssize_t show_prochot_short(struct device *dev, +static ssize_t prochot_short_show(struct device *dev, struct device_attribute *attr, char *buf) { struct lm93_data *data = lm93_update_device(dev); return sprintf(buf, "%d\n", (data->config & 0x10) ? 1 : 0); } -static ssize_t store_prochot_short(struct device *dev, +static ssize_t prochot_short_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -2442,8 +2436,7 @@ static ssize_t store_prochot_short(struct device *dev, return count; } -static DEVICE_ATTR(prochot_short, S_IRUGO | S_IWUSR, - show_prochot_short, store_prochot_short); +static DEVICE_ATTR_RW(prochot_short); static ssize_t show_vrdhot(struct device *dev, struct device_attribute *attr, char *buf) @@ -2457,23 +2450,23 @@ static ssize_t show_vrdhot(struct device *dev, struct device_attribute *attr, static SENSOR_DEVICE_ATTR(vrdhot1, S_IRUGO, show_vrdhot, NULL, 0); static SENSOR_DEVICE_ATTR(vrdhot2, S_IRUGO, show_vrdhot, NULL, 1); -static ssize_t show_gpio(struct device *dev, struct device_attribute *attr, +static ssize_t gpio_show(struct device *dev, struct device_attribute *attr, char *buf) { struct lm93_data *data = lm93_update_device(dev); return sprintf(buf, "%d\n", LM93_GPI_FROM_REG(data->gpi)); } -static DEVICE_ATTR(gpio, S_IRUGO, show_gpio, NULL); +static DEVICE_ATTR_RO(gpio); -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct lm93_data *data = lm93_update_device(dev); return sprintf(buf, "%d\n", LM93_ALARMS_FROM_REG(data->block1)); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static struct attribute *lm93_attrs[] = { &sensor_dev_attr_in1_input.dev_attr.attr, diff --git a/drivers/hwmon/lm95234.c b/drivers/hwmon/lm95234.c index 8796de39ff9b..c7fcc9e7f57a 100644 --- a/drivers/hwmon/lm95234.c +++ b/drivers/hwmon/lm95234.c @@ -450,8 +450,8 @@ static ssize_t set_offset(struct device *dev, struct device_attribute *attr, return count; } -static ssize_t show_interval(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t update_interval_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lm95234_data *data = dev_get_drvdata(dev); int ret = lm95234_update_device(data); @@ -463,8 +463,9 @@ static ssize_t show_interval(struct device *dev, struct device_attribute *attr, DIV_ROUND_CLOSEST(data->interval * 1000, HZ)); } -static ssize_t set_interval(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t update_interval_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct lm95234_data *data = dev_get_drvdata(dev); int ret = lm95234_update_device(data); @@ -566,8 +567,7 @@ static SENSOR_DEVICE_ATTR(temp4_offset, S_IWUSR | S_IRUGO, show_offset, static SENSOR_DEVICE_ATTR(temp5_offset, S_IWUSR | S_IRUGO, show_offset, set_offset, 3); -static DEVICE_ATTR(update_interval, S_IWUSR | S_IRUGO, show_interval, - set_interval); +static DEVICE_ATTR_RW(update_interval); static struct attribute *lm95234_common_attrs[] = { &sensor_dev_attr_temp1_input.dev_attr.attr, diff --git a/drivers/hwmon/ltc4151.c b/drivers/hwmon/ltc4151.c index 8445c9fd946b..b904cb547ffb 100644 --- a/drivers/hwmon/ltc4151.c +++ b/drivers/hwmon/ltc4151.c @@ -215,6 +215,7 @@ static const struct of_device_id ltc4151_match[] = { { .compatible = "lltc,ltc4151" }, {}, }; +MODULE_DEVICE_TABLE(of, ltc4151_match); /* This is the driver that will be inserted */ static struct i2c_driver ltc4151_driver = { diff --git a/drivers/hwmon/max1111.c b/drivers/hwmon/max1111.c index 303d0c9df907..8ddd4d690652 100644 --- a/drivers/hwmon/max1111.c +++ b/drivers/hwmon/max1111.c @@ -98,7 +98,7 @@ EXPORT_SYMBOL(max1111_read_channel); * likely to be used by hwmon applications to distinguish between * different devices, explicitly add a name attribute here. */ -static ssize_t show_name(struct device *dev, +static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%s\n", to_spi_device(dev)->modalias); @@ -125,7 +125,7 @@ static ssize_t show_adc(struct device *dev, #define MAX1111_ADC_ATTR(_id) \ SENSOR_DEVICE_ATTR(in##_id##_input, S_IRUGO, show_adc, NULL, _id) -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static MAX1111_ADC_ATTR(0); static MAX1111_ADC_ATTR(1); static MAX1111_ADC_ATTR(2); diff --git a/drivers/hwmon/max1619.c b/drivers/hwmon/max1619.c index eda9cf599685..a18278938494 100644 --- a/drivers/hwmon/max1619.c +++ b/drivers/hwmon/max1619.c @@ -173,7 +173,7 @@ static ssize_t set_temp(struct device *dev, struct device_attribute *devattr, return count; } -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct max1619_data *data = max1619_update_device(dev); @@ -199,7 +199,7 @@ static SENSOR_DEVICE_ATTR(temp2_crit, S_IWUSR | S_IRUGO, show_temp, set_temp, static SENSOR_DEVICE_ATTR(temp2_crit_hyst, S_IWUSR | S_IRUGO, show_temp, set_temp, t_hyst2); -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static SENSOR_DEVICE_ATTR(temp2_crit_alarm, S_IRUGO, show_alarm, NULL, 1); static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 2); static SENSOR_DEVICE_ATTR(temp2_min_alarm, S_IRUGO, show_alarm, NULL, 3); diff --git a/drivers/hwmon/max197.c b/drivers/hwmon/max197.c index 07628569547a..638567fb7cd8 100644 --- a/drivers/hwmon/max197.c +++ b/drivers/hwmon/max197.c @@ -207,8 +207,8 @@ unlock: return ret; } -static ssize_t max197_show_name(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t name_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct platform_device *pdev = to_platform_device(dev); return sprintf(buf, "%s\n", pdev->name); @@ -231,7 +231,7 @@ static ssize_t max197_show_name(struct device *dev, &sensor_dev_attr_in##chan##_max.dev_attr.attr, \ &sensor_dev_attr_in##chan##_min.dev_attr.attr -static DEVICE_ATTR(name, S_IRUGO, max197_show_name, NULL); +static DEVICE_ATTR_RO(name); MAX197_SENSOR_DEVICE_ATTR_CH(0); MAX197_SENSOR_DEVICE_ATTR_CH(1); diff --git a/drivers/hwmon/max6650.c b/drivers/hwmon/max6650.c index a993b44ed538..65be4b19fe47 100644 --- a/drivers/hwmon/max6650.c +++ b/drivers/hwmon/max6650.c @@ -270,8 +270,8 @@ static ssize_t get_fan(struct device *dev, struct device_attribute *devattr, * controlled. */ -static ssize_t get_target(struct device *dev, struct device_attribute *devattr, - char *buf) +static ssize_t fan1_target_show(struct device *dev, + struct device_attribute *devattr, char *buf) { struct max6650_data *data = max6650_update_device(dev); int kscale, ktach, rpm; @@ -318,8 +318,9 @@ static int max6650_set_target(struct max6650_data *data, unsigned long rpm) data->speed); } -static ssize_t set_target(struct device *dev, struct device_attribute *devattr, - const char *buf, size_t count) +static ssize_t fan1_target_store(struct device *dev, + struct device_attribute *devattr, + const char *buf, size_t count) { struct max6650_data *data = dev_get_drvdata(dev); unsigned long rpm; @@ -350,8 +351,8 @@ static ssize_t set_target(struct device *dev, struct device_attribute *devattr, * back exactly the value you have set. */ -static ssize_t get_pwm(struct device *dev, struct device_attribute *devattr, - char *buf) +static ssize_t pwm1_show(struct device *dev, struct device_attribute *devattr, + char *buf) { int pwm; struct max6650_data *data = max6650_update_device(dev); @@ -371,8 +372,9 @@ static ssize_t get_pwm(struct device *dev, struct device_attribute *devattr, return sprintf(buf, "%d\n", pwm); } -static ssize_t set_pwm(struct device *dev, struct device_attribute *devattr, - const char *buf, size_t count) +static ssize_t pwm1_store(struct device *dev, + struct device_attribute *devattr, const char *buf, + size_t count) { struct max6650_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -406,8 +408,8 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute *devattr, * 2 = Closed loop, RPM for all fans regulated by fan1 tachometer * 3 = Fan off */ -static ssize_t get_enable(struct device *dev, struct device_attribute *devattr, - char *buf) +static ssize_t pwm1_enable_show(struct device *dev, + struct device_attribute *devattr, char *buf) { struct max6650_data *data = max6650_update_device(dev); int mode = (data->config & MAX6650_CFG_MODE_MASK) >> 4; @@ -416,8 +418,9 @@ static ssize_t get_enable(struct device *dev, struct device_attribute *devattr, return sprintf(buf, "%d\n", sysfs_modes[mode]); } -static ssize_t set_enable(struct device *dev, struct device_attribute *devattr, - const char *buf, size_t count) +static ssize_t pwm1_enable_store(struct device *dev, + struct device_attribute *devattr, + const char *buf, size_t count) { struct max6650_data *data = dev_get_drvdata(dev); unsigned long mode; @@ -458,16 +461,17 @@ static ssize_t set_enable(struct device *dev, struct device_attribute *devattr, * defined for that. See the data sheet for details. */ -static ssize_t get_div(struct device *dev, struct device_attribute *devattr, - char *buf) +static ssize_t fan1_div_show(struct device *dev, + struct device_attribute *devattr, char *buf) { struct max6650_data *data = max6650_update_device(dev); return sprintf(buf, "%d\n", DIV_FROM_REG(data->count)); } -static ssize_t set_div(struct device *dev, struct device_attribute *devattr, - const char *buf, size_t count) +static ssize_t fan1_div_store(struct device *dev, + struct device_attribute *devattr, + const char *buf, size_t count) { struct max6650_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -534,10 +538,10 @@ static SENSOR_DEVICE_ATTR(fan1_input, S_IRUGO, get_fan, NULL, 0); static SENSOR_DEVICE_ATTR(fan2_input, S_IRUGO, get_fan, NULL, 1); static SENSOR_DEVICE_ATTR(fan3_input, S_IRUGO, get_fan, NULL, 2); static SENSOR_DEVICE_ATTR(fan4_input, S_IRUGO, get_fan, NULL, 3); -static DEVICE_ATTR(fan1_target, S_IWUSR | S_IRUGO, get_target, set_target); -static DEVICE_ATTR(fan1_div, S_IWUSR | S_IRUGO, get_div, set_div); -static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO, get_enable, set_enable); -static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, get_pwm, set_pwm); +static DEVICE_ATTR_RW(fan1_target); +static DEVICE_ATTR_RW(fan1_div); +static DEVICE_ATTR_RW(pwm1_enable); +static DEVICE_ATTR_RW(pwm1); static SENSOR_DEVICE_ATTR(fan1_max_alarm, S_IRUGO, get_alarm, NULL, MAX6650_ALRM_MAX); static SENSOR_DEVICE_ATTR(fan1_min_alarm, S_IRUGO, get_alarm, NULL, diff --git a/drivers/hwmon/mc13783-adc.c b/drivers/hwmon/mc13783-adc.c index 0c02f40eb0c1..960a1db6f269 100644 --- a/drivers/hwmon/mc13783-adc.c +++ b/drivers/hwmon/mc13783-adc.c @@ -40,8 +40,8 @@ struct mc13783_adc_priv { char name[PLATFORM_NAME_SIZE]; }; -static ssize_t mc13783_adc_show_name(struct device *dev, struct device_attribute - *devattr, char *buf) +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, + char *buf) { struct mc13783_adc_priv *priv = dev_get_drvdata(dev); @@ -111,7 +111,7 @@ static ssize_t mc13783_adc_read_gp(struct device *dev, return sprintf(buf, "%u\n", val); } -static DEVICE_ATTR(name, S_IRUGO, mc13783_adc_show_name, NULL); +static DEVICE_ATTR_RO(name); static SENSOR_DEVICE_ATTR(in2_input, S_IRUGO, mc13783_adc_read_bp, NULL, 2); static SENSOR_DEVICE_ATTR(in5_input, S_IRUGO, mc13783_adc_read_gp, NULL, 5); static SENSOR_DEVICE_ATTR(in6_input, S_IRUGO, mc13783_adc_read_gp, NULL, 6); diff --git a/drivers/hwmon/mcp3021.c b/drivers/hwmon/mcp3021.c index 1929734c3b1d..de886f82101b 100644 --- a/drivers/hwmon/mcp3021.c +++ b/drivers/hwmon/mcp3021.c @@ -86,8 +86,8 @@ static inline u16 volts_from_reg(struct mcp3021_data *data, u16 val) return DIV_ROUND_CLOSEST(data->vdd * val, 1 << data->output_res); } -static ssize_t show_in_input(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t in0_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct i2c_client *client = to_i2c_client(dev); struct mcp3021_data *data = i2c_get_clientdata(client); @@ -102,7 +102,7 @@ static ssize_t show_in_input(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%d\n", in_input); } -static DEVICE_ATTR(in0_input, 0444, show_in_input, NULL); +static DEVICE_ATTR_RO(in0_input); static int mcp3021_probe(struct i2c_client *client, const struct i2c_device_id *id) diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c index 559c596b24f9..8b0bc4fc06e8 100644 --- a/drivers/hwmon/nct6683.c +++ b/drivers/hwmon/nct6683.c @@ -979,7 +979,7 @@ static const struct sensor_template_group nct6683_pwm_template_group = { }; static ssize_t -show_global_beep(struct device *dev, struct device_attribute *attr, char *buf) +beep_enable_show(struct device *dev, struct device_attribute *attr, char *buf) { struct nct6683_data *data = dev_get_drvdata(dev); int ret; @@ -1004,7 +1004,7 @@ error: } static ssize_t -store_global_beep(struct device *dev, struct device_attribute *attr, +beep_enable_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct nct6683_data *data = dev_get_drvdata(dev); @@ -1039,7 +1039,8 @@ error: /* Case open detection */ static ssize_t -show_caseopen(struct device *dev, struct device_attribute *attr, char *buf) +intrusion0_alarm_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct nct6683_data *data = dev_get_drvdata(dev); int ret; @@ -1064,8 +1065,8 @@ error: } static ssize_t -clear_caseopen(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +intrusion0_alarm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct nct6683_data *data = dev_get_drvdata(dev); unsigned long val; @@ -1102,10 +1103,8 @@ error: return count; } -static DEVICE_ATTR(intrusion0_alarm, S_IWUSR | S_IRUGO, show_caseopen, - clear_caseopen); -static DEVICE_ATTR(beep_enable, S_IWUSR | S_IRUGO, show_global_beep, - store_global_beep); +static DEVICE_ATTR_RW(intrusion0_alarm); +static DEVICE_ATTR_RW(beep_enable); static struct attribute *nct6683_attributes_other[] = { &dev_attr_intrusion0_alarm.attr, diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index ce75dd4db7eb..2458b406f6aa 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -3127,14 +3127,14 @@ static const struct sensor_template_group nct6775_pwm_template_group = { }; static ssize_t -show_vid(struct device *dev, struct device_attribute *attr, char *buf) +cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct nct6775_data *data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); /* Case open detection */ diff --git a/drivers/hwmon/nsa320-hwmon.c b/drivers/hwmon/nsa320-hwmon.c index 0517a265741f..5a16109cdea8 100644 --- a/drivers/hwmon/nsa320-hwmon.c +++ b/drivers/hwmon/nsa320-hwmon.c @@ -122,8 +122,8 @@ static ssize_t show_label(struct device *dev, return sprintf(buf, "%s\n", nsa320_input_names[channel]); } -static ssize_t show_temp(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t temp1_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { s32 mcu_data = nsa320_hwmon_update(dev); @@ -133,8 +133,8 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%d\n", (mcu_data & 0xffff) * 100); } -static ssize_t show_fan(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t fan1_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { s32 mcu_data = nsa320_hwmon_update(dev); @@ -145,9 +145,9 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *attr, } static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, show_label, NULL, NSA320_TEMP); -static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL); +static DEVICE_ATTR_RO(temp1_input); static SENSOR_DEVICE_ATTR(fan1_label, S_IRUGO, show_label, NULL, NSA320_FAN); -static DEVICE_ATTR(fan1_input, S_IRUGO, show_fan, NULL); +static DEVICE_ATTR_RO(fan1_input); static struct attribute *nsa320_attrs[] = { &sensor_dev_attr_temp1_label.dev_attr.attr, diff --git a/drivers/hwmon/pc87360.c b/drivers/hwmon/pc87360.c index d50fbf93a737..7e3697727537 100644 --- a/drivers/hwmon/pc87360.c +++ b/drivers/hwmon/pc87360.c @@ -589,22 +589,22 @@ static struct sensor_device_attribute in_max_alarm[] = { &in_min_alarm[X].dev_attr.attr, \ &in_max_alarm[X].dev_attr.attr -static ssize_t show_vid(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct pc87360_data *data = pc87360_update_device(dev); return sprintf(buf, "%u\n", vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); -static ssize_t show_vrm(struct device *dev, struct device_attribute *attr, +static ssize_t vrm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pc87360_data *data = dev_get_drvdata(dev); return sprintf(buf, "%u\n", data->vrm); } -static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct pc87360_data *data = dev_get_drvdata(dev); unsigned long val; @@ -620,15 +620,15 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, data->vrm = val; return count; } -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm); +static DEVICE_ATTR_RW(vrm); -static ssize_t show_in_alarms(struct device *dev, +static ssize_t alarms_in_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pc87360_data *data = pc87360_update_device(dev); return sprintf(buf, "%u\n", data->in_alarms); } -static DEVICE_ATTR(alarms_in, S_IRUGO, show_in_alarms, NULL); +static DEVICE_ATTR_RO(alarms_in); static struct attribute *pc8736x_vin_attr_array[] = { VIN_UNIT_ATTRS(0), @@ -1006,14 +1006,14 @@ static struct sensor_device_attribute temp_crit[] = { show_temp_crit, set_temp_crit, 2), }; -static ssize_t show_temp_alarms(struct device *dev, +static ssize_t alarms_temp_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pc87360_data *data = pc87360_update_device(dev); return sprintf(buf, "%u\n", data->temp_alarms); } -static DEVICE_ATTR(alarms_temp, S_IRUGO, show_temp_alarms, NULL); +static DEVICE_ATTR_RO(alarms_temp); /* * show_temp_min/max_alarm() reads data from the per-channel status @@ -1106,14 +1106,14 @@ static const struct attribute_group pc8736x_temp_attr_group[] = { { .attrs = pc8736x_temp_attr[2] } }; -static ssize_t show_name(struct device *dev, +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct pc87360_data *data = dev_get_drvdata(dev); return sprintf(buf, "%s\n", data->name); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); /* * Device detection, registration and update diff --git a/drivers/hwmon/pc87427.c b/drivers/hwmon/pc87427.c index cb9fdd37bd0d..dc5a9d5ada51 100644 --- a/drivers/hwmon/pc87427.c +++ b/drivers/hwmon/pc87427.c @@ -943,14 +943,14 @@ static const struct attribute_group pc87427_group_temp[6] = { { .attrs = pc87427_attributes_temp[5] }, }; -static ssize_t show_name(struct device *dev, struct device_attribute +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct pc87427_data *data = dev_get_drvdata(dev); return sprintf(buf, "%s\n", data->name); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); /* diff --git a/drivers/hwmon/pcf8591.c b/drivers/hwmon/pcf8591.c index 5740888c6242..60e25c85e71c 100644 --- a/drivers/hwmon/pcf8591.c +++ b/drivers/hwmon/pcf8591.c @@ -103,16 +103,16 @@ show_in_channel(1); show_in_channel(2); show_in_channel(3); -static ssize_t show_out0_ouput(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t out0_output_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct pcf8591_data *data = i2c_get_clientdata(to_i2c_client(dev)); return sprintf(buf, "%d\n", data->aout * 10); } -static ssize_t set_out0_output(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t out0_output_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { unsigned long val; struct i2c_client *client = to_i2c_client(dev); @@ -132,19 +132,18 @@ static ssize_t set_out0_output(struct device *dev, return count; } -static DEVICE_ATTR(out0_output, S_IWUSR | S_IRUGO, - show_out0_ouput, set_out0_output); +static DEVICE_ATTR_RW(out0_output); -static ssize_t show_out0_enable(struct device *dev, +static ssize_t out0_enable_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pcf8591_data *data = i2c_get_clientdata(to_i2c_client(dev)); return sprintf(buf, "%u\n", !(!(data->control & PCF8591_CONTROL_AOEF))); } -static ssize_t set_out0_enable(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t out0_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct i2c_client *client = to_i2c_client(dev); struct pcf8591_data *data = i2c_get_clientdata(client); @@ -165,8 +164,7 @@ static ssize_t set_out0_enable(struct device *dev, return count; } -static DEVICE_ATTR(out0_enable, S_IWUSR | S_IRUGO, - show_out0_enable, set_out0_enable); +static DEVICE_ATTR_RW(out0_enable); static struct attribute *pcf8591_attributes[] = { &dev_attr_out0_enable.attr, diff --git a/drivers/hwmon/sch5627.c b/drivers/hwmon/sch5627.c index 19f85c0da270..91544f2312e6 100644 --- a/drivers/hwmon/sch5627.c +++ b/drivers/hwmon/sch5627.c @@ -205,7 +205,7 @@ static int reg_to_rpm(u16 reg) return 5400540 / reg; } -static ssize_t show_name(struct device *dev, struct device_attribute *devattr, +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf) { return snprintf(buf, PAGE_SIZE, "%s\n", DEVNAME); @@ -326,7 +326,7 @@ static ssize_t show_in_label(struct device *dev, struct device_attribute SCH5627_IN_LABELS[attr->index]); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL, 0); static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, show_temp, NULL, 1); static SENSOR_DEVICE_ATTR(temp3_input, S_IRUGO, show_temp, NULL, 2); diff --git a/drivers/hwmon/sch56xx-common.c b/drivers/hwmon/sch56xx-common.c index 68c350c704fb..bda3d5285586 100644 --- a/drivers/hwmon/sch56xx-common.c +++ b/drivers/hwmon/sch56xx-common.c @@ -28,7 +28,6 @@ #include <linux/delay.h> #include <linux/fs.h> #include <linux/watchdog.h> -#include <linux/miscdevice.h> #include <linux/uaccess.h> #include <linux/slab.h> #include "sch56xx-common.h" diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c index a2fdbb7d20ed..e4d642b673c6 100644 --- a/drivers/hwmon/sht15.c +++ b/drivers/hwmon/sht15.c @@ -34,6 +34,7 @@ #include <linux/slab.h> #include <linux/atomic.h> #include <linux/bitrev.h> +#include <linux/of_gpio.h> /* Commands */ #define SHT15_MEASURE_TEMP 0x03 @@ -769,7 +770,7 @@ static ssize_t sht15_show_humidity(struct device *dev, return ret ? ret : sprintf(buf, "%d\n", sht15_calc_humid(data)); } -static ssize_t show_name(struct device *dev, +static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -787,7 +788,7 @@ static SENSOR_DEVICE_ATTR(humidity1_fault, S_IRUGO, sht15_show_status, NULL, SHT15_STATUS_LOW_BATTERY); static SENSOR_DEVICE_ATTR(heater_enable, S_IRUGO | S_IWUSR, sht15_show_status, sht15_store_heater, SHT15_STATUS_HEATER); -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static struct attribute *sht15_attrs[] = { &sensor_dev_attr_temp1_input.dev_attr.attr, &sensor_dev_attr_humidity1_input.dev_attr.attr, @@ -911,6 +912,54 @@ static int sht15_invalidate_voltage(struct notifier_block *nb, return NOTIFY_OK; } +#ifdef CONFIG_OF +static const struct of_device_id sht15_dt_match[] = { + { .compatible = "sensirion,sht15" }, + { }, +}; +MODULE_DEVICE_TABLE(of, sht15_dt_match); + +/* + * This function returns NULL if pdev isn't a device instatiated by dt, + * a pointer to pdata if it could successfully get all information + * from dt or a negative ERR_PTR() on error. + */ +static struct sht15_platform_data *sht15_probe_dt(struct device *dev) +{ + struct device_node *np = dev->of_node; + struct sht15_platform_data *pdata; + + /* no device tree device */ + if (!np) + return NULL; + + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return ERR_PTR(-ENOMEM); + + pdata->gpio_data = of_get_named_gpio(np, "data-gpios", 0); + if (pdata->gpio_data < 0) { + if (pdata->gpio_data != -EPROBE_DEFER) + dev_err(dev, "data-gpios not found\n"); + return ERR_PTR(pdata->gpio_data); + } + + pdata->gpio_sck = of_get_named_gpio(np, "clk-gpios", 0); + if (pdata->gpio_sck < 0) { + if (pdata->gpio_sck != -EPROBE_DEFER) + dev_err(dev, "clk-gpios not found\n"); + return ERR_PTR(pdata->gpio_sck); + } + + return pdata; +} +#else +static inline struct sht15_platform_data *sht15_probe_dt(struct device *dev) +{ + return NULL; +} +#endif + static int sht15_probe(struct platform_device *pdev) { int ret; @@ -928,11 +977,17 @@ static int sht15_probe(struct platform_device *pdev) data->dev = &pdev->dev; init_waitqueue_head(&data->wait_queue); - if (dev_get_platdata(&pdev->dev) == NULL) { - dev_err(&pdev->dev, "no platform data supplied\n"); - return -EINVAL; + data->pdata = sht15_probe_dt(&pdev->dev); + if (IS_ERR(data->pdata)) + return PTR_ERR(data->pdata); + if (data->pdata == NULL) { + data->pdata = dev_get_platdata(&pdev->dev); + if (data->pdata == NULL) { + dev_err(&pdev->dev, "no platform data supplied\n"); + return -EINVAL; + } } - data->pdata = dev_get_platdata(&pdev->dev); + data->supply_uv = data->pdata->supply_mv * 1000; if (data->pdata->checksum) data->checksumming = true; @@ -1075,6 +1130,7 @@ MODULE_DEVICE_TABLE(platform, sht15_device_ids); static struct platform_driver sht15_driver = { .driver = { .name = "sht15", + .of_match_table = of_match_ptr(sht15_dt_match), }, .probe = sht15_probe, .remove = sht15_remove, diff --git a/drivers/hwmon/sht21.c b/drivers/hwmon/sht21.c index 84cdb1cf0fb4..06706d288355 100644 --- a/drivers/hwmon/sht21.c +++ b/drivers/hwmon/sht21.c @@ -34,23 +34,29 @@ /* I2C command bytes */ #define SHT21_TRIG_T_MEASUREMENT_HM 0xe3 #define SHT21_TRIG_RH_MEASUREMENT_HM 0xe5 +#define SHT21_READ_SNB_CMD1 0xFA +#define SHT21_READ_SNB_CMD2 0x0F +#define SHT21_READ_SNAC_CMD1 0xFC +#define SHT21_READ_SNAC_CMD2 0xC9 /** * struct sht21 - SHT21 device specific data * @hwmon_dev: device registered with hwmon * @lock: mutex to protect measurement values - * @valid: only 0 before first measurement is taken * @last_update: time of last update (jiffies) * @temperature: cached temperature measurement value * @humidity: cached humidity measurement value + * @valid: only 0 before first measurement is taken + * @eic: cached electronic identification code text */ struct sht21 { struct i2c_client *client; struct mutex lock; - char valid; unsigned long last_update; int temperature; int humidity; + char valid; + char eic[18]; }; /** @@ -165,15 +171,97 @@ static ssize_t sht21_show_humidity(struct device *dev, return sprintf(buf, "%d\n", sht21->humidity); } +static ssize_t eic_read(struct sht21 *sht21) +{ + struct i2c_client *client = sht21->client; + u8 tx[2]; + u8 rx[8]; + u8 eic[8]; + struct i2c_msg msgs[2] = { + { + .addr = client->addr, + .flags = 0, + .len = 2, + .buf = tx, + }, + { + .addr = client->addr, + .flags = I2C_M_RD, + .len = 8, + .buf = rx, + }, + }; + int ret; + + tx[0] = SHT21_READ_SNB_CMD1; + tx[1] = SHT21_READ_SNB_CMD2; + ret = i2c_transfer(client->adapter, msgs, 2); + if (ret < 0) + goto out; + eic[2] = rx[0]; + eic[3] = rx[2]; + eic[4] = rx[4]; + eic[5] = rx[6]; + + tx[0] = SHT21_READ_SNAC_CMD1; + tx[1] = SHT21_READ_SNAC_CMD2; + msgs[1].len = 6; + ret = i2c_transfer(client->adapter, msgs, 2); + if (ret < 0) + goto out; + eic[0] = rx[3]; + eic[1] = rx[4]; + eic[6] = rx[0]; + eic[7] = rx[1]; + + ret = snprintf(sht21->eic, sizeof(sht21->eic), + "%02x%02x%02x%02x%02x%02x%02x%02x\n", + eic[0], eic[1], eic[2], eic[3], + eic[4], eic[5], eic[6], eic[7]); +out: + if (ret < 0) + sht21->eic[0] = 0; + + return ret; +} + +/** + * eic_show() - show Electronic Identification Code in sysfs + * @dev: device + * @attr: device attribute + * @buf: sysfs buffer (PAGE_SIZE) where EIC is written + * + * Will be called on read access to eic sysfs attribute. + * Returns number of bytes written into buffer, negative errno on error. + */ +static ssize_t eic_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct sht21 *sht21 = dev_get_drvdata(dev); + int ret; + + ret = sizeof(sht21->eic) - 1; + mutex_lock(&sht21->lock); + if (!sht21->eic[0]) + ret = eic_read(sht21); + if (ret > 0) + memcpy(buf, sht21->eic, ret); + mutex_unlock(&sht21->lock); + return ret; +} + /* sysfs attributes */ static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, sht21_show_temperature, NULL, 0); static SENSOR_DEVICE_ATTR(humidity1_input, S_IRUGO, sht21_show_humidity, NULL, 0); +static DEVICE_ATTR_RO(eic); static struct attribute *sht21_attrs[] = { &sensor_dev_attr_temp1_input.dev_attr.attr, &sensor_dev_attr_humidity1_input.dev_attr.attr, + &dev_attr_eic.attr, NULL }; diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c index 45a028fb8851..6d789aab54c9 100644 --- a/drivers/hwmon/sis5595.c +++ b/drivers/hwmon/sis5595.c @@ -304,22 +304,23 @@ show_in_offset(3); show_in_offset(4); /* Temperature */ -static ssize_t show_temp(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t temp1_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct sis5595_data *data = sis5595_update_device(dev); return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp)); } -static ssize_t show_temp_over(struct device *dev, struct device_attribute *attr, +static ssize_t temp1_max_show(struct device *dev, struct device_attribute *attr, char *buf) { struct sis5595_data *data = sis5595_update_device(dev); return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_over)); } -static ssize_t set_temp_over(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t temp1_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct sis5595_data *data = dev_get_drvdata(dev); long val; @@ -336,15 +337,16 @@ static ssize_t set_temp_over(struct device *dev, struct device_attribute *attr, return count; } -static ssize_t show_temp_hyst(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t temp1_max_hyst_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct sis5595_data *data = sis5595_update_device(dev); return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_hyst)); } -static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t temp1_max_hyst_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct sis5595_data *data = dev_get_drvdata(dev); long val; @@ -361,11 +363,9 @@ static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL); -static DEVICE_ATTR(temp1_max, S_IRUGO | S_IWUSR, - show_temp_over, set_temp_over); -static DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR, - show_temp_hyst, set_temp_hyst); +static DEVICE_ATTR_RO(temp1_input); +static DEVICE_ATTR_RW(temp1_max); +static DEVICE_ATTR_RW(temp1_max_hyst); /* 2 Fans */ static ssize_t show_fan(struct device *dev, struct device_attribute *da, @@ -492,13 +492,13 @@ show_fan_offset(1); show_fan_offset(2); /* Alarms */ -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct sis5595_data *data = sis5595_update_device(dev); return sprintf(buf, "%d\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *da, char *buf) @@ -516,13 +516,13 @@ static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6); static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7); static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 15); -static ssize_t show_name(struct device *dev, struct device_attribute *attr, +static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct sis5595_data *data = dev_get_drvdata(dev); return sprintf(buf, "%s\n", data->name); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static struct attribute *sis5595_attributes[] = { &sensor_dev_attr_in0_input.dev_attr.attr, diff --git a/drivers/hwmon/smsc47m1.c b/drivers/hwmon/smsc47m1.c index 5d323186d2c1..c7b6a425e2c0 100644 --- a/drivers/hwmon/smsc47m1.c +++ b/drivers/hwmon/smsc47m1.c @@ -264,8 +264,8 @@ static ssize_t get_pwm_en(struct device *dev, struct device_attribute return sprintf(buf, "%d\n", PWM_EN_FROM_REG(data->pwm[attr->index])); } -static ssize_t get_alarms(struct device *dev, struct device_attribute - *devattr, char *buf) +static ssize_t alarms_show(struct device *dev, + struct device_attribute *devattr, char *buf) { struct smsc47m1_data *data = smsc47m1_update_device(dev, 0); return sprintf(buf, "%d\n", data->alarms); @@ -440,16 +440,16 @@ fan_present(1); fan_present(2); fan_present(3); -static DEVICE_ATTR(alarms, S_IRUGO, get_alarms, NULL); +static DEVICE_ATTR_RO(alarms); -static ssize_t show_name(struct device *dev, struct device_attribute +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct smsc47m1_data *data = dev_get_drvdata(dev); return sprintf(buf, "%s\n", data->name); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static struct attribute *smsc47m1_attributes_fan1[] = { &sensor_dev_attr_fan1_input.dev_attr.attr, diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c index 15650f247679..6989408033ec 100644 --- a/drivers/hwmon/smsc47m192.c +++ b/drivers/hwmon/smsc47m192.c @@ -400,23 +400,23 @@ show_temp_index(2) show_temp_index(3) /* VID */ -static ssize_t show_vid(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct smsc47m192_data *data = smsc47m192_update_device(dev); return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); -static ssize_t show_vrm(struct device *dev, struct device_attribute *attr, +static ssize_t vrm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct smsc47m192_data *data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", data->vrm); } -static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct smsc47m192_data *data = dev_get_drvdata(dev); unsigned long val; @@ -431,7 +431,7 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, data->vrm = val; return count; } -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm); +static DEVICE_ATTR_RW(vrm); /* Alarms */ static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, diff --git a/drivers/hwmon/stts751.c b/drivers/hwmon/stts751.c new file mode 100644 index 000000000000..55450680fb58 --- /dev/null +++ b/drivers/hwmon/stts751.c @@ -0,0 +1,834 @@ +/* + * STTS751 sensor driver + * + * Copyright (C) 2016-2017 Istituto Italiano di Tecnologia - RBCS - EDL + * Robotics, Brain and Cognitive Sciences department + * Electronic Design Laboratory + * + * Written by Andrea Merello <andrea.merello@gmail.com> + * + * Based on LM95241 driver and LM90 driver + * + * 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. + */ + +#include <linux/bitops.h> +#include <linux/err.h> +#include <linux/hwmon.h> +#include <linux/hwmon-sysfs.h> +#include <linux/i2c.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/jiffies.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/property.h> +#include <linux/slab.h> +#include <linux/sysfs.h> +#include <linux/util_macros.h> + +#define DEVNAME "stts751" + +static const unsigned short normal_i2c[] = { + 0x48, 0x49, 0x38, 0x39, /* STTS751-0 */ + 0x4A, 0x4B, 0x3A, 0x3B, /* STTS751-1 */ + I2C_CLIENT_END }; + +#define STTS751_REG_TEMP_H 0x00 +#define STTS751_REG_STATUS 0x01 +#define STTS751_STATUS_TRIPT BIT(0) +#define STTS751_STATUS_TRIPL BIT(5) +#define STTS751_STATUS_TRIPH BIT(6) +#define STTS751_REG_TEMP_L 0x02 +#define STTS751_REG_CONF 0x03 +#define STTS751_CONF_RES_MASK 0x0C +#define STTS751_CONF_RES_SHIFT 2 +#define STTS751_CONF_EVENT_DIS BIT(7) +#define STTS751_CONF_STOP BIT(6) +#define STTS751_REG_RATE 0x04 +#define STTS751_REG_HLIM_H 0x05 +#define STTS751_REG_HLIM_L 0x06 +#define STTS751_REG_LLIM_H 0x07 +#define STTS751_REG_LLIM_L 0x08 +#define STTS751_REG_TLIM 0x20 +#define STTS751_REG_HYST 0x21 +#define STTS751_REG_SMBUS_TO 0x22 + +#define STTS751_REG_PROD_ID 0xFD +#define STTS751_REG_MAN_ID 0xFE +#define STTS751_REG_REV_ID 0xFF + +#define STTS751_0_PROD_ID 0x00 +#define STTS751_1_PROD_ID 0x01 +#define ST_MAN_ID 0x53 + +/* + * Possible update intervals are (in mS): + * 16000, 8000, 4000, 2000, 1000, 500, 250, 125, 62.5, 31.25 + * However we are not going to complicate things too much and we stick to the + * approx value in mS. + */ +static const int stts751_intervals[] = { + 16000, 8000, 4000, 2000, 1000, 500, 250, 125, 63, 31 +}; + +static const struct i2c_device_id stts751_id[] = { + { "stts751", 0 }, + { } +}; + +struct stts751_priv { + struct device *dev; + struct i2c_client *client; + struct mutex access_lock; + u8 interval; + int res; + int event_max, event_min; + int therm; + int hyst; + bool smbus_timeout; + int temp; + unsigned long last_update, last_alert_update; + u8 config; + bool min_alert, max_alert, therm_trip; + bool data_valid, alert_valid; + bool notify_max, notify_min; +}; + +/* + * These functions converts temperature from HW format to integer format and + * vice-vers. They are (mostly) taken from lm90 driver. Unit is in mC. + */ +static int stts751_to_deg(s16 hw_val) +{ + return hw_val * 125 / 32; +} + +static s32 stts751_to_hw(int val) +{ + return DIV_ROUND_CLOSEST(val, 125) * 32; +} + +static int stts751_adjust_resolution(struct stts751_priv *priv) +{ + u8 res; + + switch (priv->interval) { + case 9: + /* 10 bits */ + res = 0; + break; + case 8: + /* 11 bits */ + res = 1; + break; + default: + /* 12 bits */ + res = 3; + break; + } + + if (priv->res == res) + return 0; + + priv->config &= ~STTS751_CONF_RES_MASK; + priv->config |= res << STTS751_CONF_RES_SHIFT; + dev_dbg(&priv->client->dev, "setting res %d. config %x", + res, priv->config); + priv->res = res; + + return i2c_smbus_write_byte_data(priv->client, + STTS751_REG_CONF, priv->config); +} + +static int stts751_update_temp(struct stts751_priv *priv) +{ + s32 integer1, integer2, frac; + + /* + * There is a trick here, like in the lm90 driver. We have to read two + * registers to get the sensor temperature, but we have to beware a + * conversion could occur between the readings. We could use the + * one-shot conversion register, but we don't want to do this (disables + * hardware monitoring). So the solution used here is to read the high + * byte once, then the low byte, then the high byte again. If the new + * high byte matches the old one, then we have a valid reading. Else we + * have to read the low byte again, and now we believe we have a correct + * reading. + */ + integer1 = i2c_smbus_read_byte_data(priv->client, STTS751_REG_TEMP_H); + if (integer1 < 0) { + dev_dbg(&priv->client->dev, + "I2C read failed (temp H). ret: %x\n", integer1); + return integer1; + } + + frac = i2c_smbus_read_byte_data(priv->client, STTS751_REG_TEMP_L); + if (frac < 0) { + dev_dbg(&priv->client->dev, + "I2C read failed (temp L). ret: %x\n", frac); + return frac; + } + + integer2 = i2c_smbus_read_byte_data(priv->client, STTS751_REG_TEMP_H); + if (integer2 < 0) { + dev_dbg(&priv->client->dev, + "I2C 2nd read failed (temp H). ret: %x\n", integer2); + return integer2; + } + + if (integer1 != integer2) { + frac = i2c_smbus_read_byte_data(priv->client, + STTS751_REG_TEMP_L); + if (frac < 0) { + dev_dbg(&priv->client->dev, + "I2C 2nd read failed (temp L). ret: %x\n", + frac); + return frac; + } + } + + priv->temp = stts751_to_deg((integer1 << 8) | frac); + return 0; +} + +static int stts751_set_temp_reg16(struct stts751_priv *priv, int temp, + u8 hreg, u8 lreg) +{ + s32 hwval; + int ret; + + hwval = stts751_to_hw(temp); + + ret = i2c_smbus_write_byte_data(priv->client, hreg, hwval >> 8); + if (ret) + return ret; + + return i2c_smbus_write_byte_data(priv->client, lreg, hwval & 0xff); +} + +static int stts751_set_temp_reg8(struct stts751_priv *priv, int temp, u8 reg) +{ + s32 hwval; + + hwval = stts751_to_hw(temp); + return i2c_smbus_write_byte_data(priv->client, reg, hwval >> 8); +} + +static int stts751_read_reg16(struct stts751_priv *priv, int *temp, + u8 hreg, u8 lreg) +{ + int integer, frac; + + integer = i2c_smbus_read_byte_data(priv->client, hreg); + if (integer < 0) + return integer; + + frac = i2c_smbus_read_byte_data(priv->client, lreg); + if (frac < 0) + return frac; + + *temp = stts751_to_deg((integer << 8) | frac); + + return 0; +} + +static int stts751_read_reg8(struct stts751_priv *priv, int *temp, u8 reg) +{ + int integer; + + integer = i2c_smbus_read_byte_data(priv->client, reg); + if (integer < 0) + return integer; + + *temp = stts751_to_deg(integer << 8); + + return 0; +} + +/* + * Update alert flags without waiting for cache to expire. We detects alerts + * immediately for the sake of the alert handler; we still need to deal with + * caching to workaround the fact that alarm flags int the status register, + * despite what the datasheet claims, gets always cleared on read. + */ +static int stts751_update_alert(struct stts751_priv *priv) +{ + int ret; + bool conv_done; + int cache_time = msecs_to_jiffies(stts751_intervals[priv->interval]); + + /* + * Add another 10% because if we run faster than the HW conversion + * rate we will end up in reporting incorrectly alarms. + */ + cache_time += cache_time / 10; + + ret = i2c_smbus_read_byte_data(priv->client, STTS751_REG_STATUS); + if (ret < 0) + return ret; + + dev_dbg(&priv->client->dev, "status reg %x\n", ret); + conv_done = ret & (STTS751_STATUS_TRIPH | STTS751_STATUS_TRIPL); + /* + * Reset the cache if the cache time expired, or if we are sure + * we have valid data from a device conversion, or if we know + * our cache has been never written. + * + * Note that when the cache has been never written the point is + * to correctly initialize the timestamp, rather than clearing + * the cache values. + * + * Note that updating the cache timestamp when we get an alarm flag + * is required, otherwise we could incorrectly report alarms to be zero. + */ + if (time_after(jiffies, priv->last_alert_update + cache_time) || + conv_done || !priv->alert_valid) { + priv->max_alert = false; + priv->min_alert = false; + priv->alert_valid = true; + priv->last_alert_update = jiffies; + dev_dbg(&priv->client->dev, "invalidating alert cache\n"); + } + + priv->max_alert |= !!(ret & STTS751_STATUS_TRIPH); + priv->min_alert |= !!(ret & STTS751_STATUS_TRIPL); + priv->therm_trip = !!(ret & STTS751_STATUS_TRIPT); + + dev_dbg(&priv->client->dev, "max_alert: %d, min_alert: %d, therm_trip: %d\n", + priv->max_alert, priv->min_alert, priv->therm_trip); + + return 0; +} + +static void stts751_alert(struct i2c_client *client, + enum i2c_alert_protocol type, unsigned int data) +{ + int ret; + struct stts751_priv *priv = i2c_get_clientdata(client); + + if (type != I2C_PROTOCOL_SMBUS_ALERT) + return; + + dev_dbg(&client->dev, "alert!"); + + mutex_lock(&priv->access_lock); + ret = stts751_update_alert(priv); + if (ret < 0) { + /* default to worst case */ + priv->max_alert = true; + priv->min_alert = true; + + dev_warn(priv->dev, + "Alert received, but can't communicate to the device. Triggering all alarms!"); + } + + if (priv->max_alert) { + if (priv->notify_max) + dev_notice(priv->dev, "got alert for HIGH temperature"); + priv->notify_max = false; + + /* unblock alert poll */ + sysfs_notify(&priv->dev->kobj, NULL, "temp1_max_alarm"); + } + + if (priv->min_alert) { + if (priv->notify_min) + dev_notice(priv->dev, "got alert for LOW temperature"); + priv->notify_min = false; + + /* unblock alert poll */ + sysfs_notify(&priv->dev->kobj, NULL, "temp1_min_alarm"); + } + + if (priv->min_alert || priv->max_alert) + kobject_uevent(&priv->dev->kobj, KOBJ_CHANGE); + + mutex_unlock(&priv->access_lock); +} + +static int stts751_update(struct stts751_priv *priv) +{ + int ret; + int cache_time = msecs_to_jiffies(stts751_intervals[priv->interval]); + + if (time_after(jiffies, priv->last_update + cache_time) || + !priv->data_valid) { + ret = stts751_update_temp(priv); + if (ret) + return ret; + + ret = stts751_update_alert(priv); + if (ret) + return ret; + priv->data_valid = true; + priv->last_update = jiffies; + } + + return 0; +} + +static ssize_t show_max_alarm(struct device *dev, struct device_attribute *attr, + char *buf) +{ + int ret; + struct stts751_priv *priv = dev_get_drvdata(dev); + + mutex_lock(&priv->access_lock); + ret = stts751_update(priv); + if (!ret) + priv->notify_max = true; + mutex_unlock(&priv->access_lock); + if (ret < 0) + return ret; + + return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->max_alert); +} + +static ssize_t show_min_alarm(struct device *dev, struct device_attribute *attr, + char *buf) +{ + int ret; + struct stts751_priv *priv = dev_get_drvdata(dev); + + mutex_lock(&priv->access_lock); + ret = stts751_update(priv); + if (!ret) + priv->notify_min = true; + mutex_unlock(&priv->access_lock); + if (ret < 0) + return ret; + + return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->min_alert); +} + +static ssize_t show_input(struct device *dev, struct device_attribute *attr, + char *buf) +{ + int ret; + struct stts751_priv *priv = dev_get_drvdata(dev); + + mutex_lock(&priv->access_lock); + ret = stts751_update(priv); + mutex_unlock(&priv->access_lock); + if (ret < 0) + return ret; + + return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->temp); +} + +static ssize_t show_therm(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct stts751_priv *priv = dev_get_drvdata(dev); + + return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->therm); +} + +static ssize_t set_therm(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + int ret; + long temp; + struct stts751_priv *priv = dev_get_drvdata(dev); + + if (kstrtol(buf, 10, &temp) < 0) + return -EINVAL; + + /* HW works in range -64C to +127.937C */ + temp = clamp_val(temp, -64000, 127937); + mutex_lock(&priv->access_lock); + ret = stts751_set_temp_reg8(priv, temp, STTS751_REG_TLIM); + if (ret) + goto exit; + + dev_dbg(&priv->client->dev, "setting therm %ld", temp); + + /* + * hysteresis reg is relative to therm, so the HW does not need to be + * adjusted, we need to update our local copy only. + */ + priv->hyst = temp - (priv->therm - priv->hyst); + priv->therm = temp; + +exit: + mutex_unlock(&priv->access_lock); + if (ret) + return ret; + + return count; +} + +static ssize_t show_hyst(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct stts751_priv *priv = dev_get_drvdata(dev); + + return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->hyst); +} + +static ssize_t set_hyst(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + int ret; + long temp; + + struct stts751_priv *priv = dev_get_drvdata(dev); + + if (kstrtol(buf, 10, &temp) < 0) + return -EINVAL; + + mutex_lock(&priv->access_lock); + /* HW works in range -64C to +127.937C */ + temp = clamp_val(temp, -64000, priv->therm); + priv->hyst = temp; + dev_dbg(&priv->client->dev, "setting hyst %ld", temp); + temp = priv->therm - temp; + ret = stts751_set_temp_reg8(priv, temp, STTS751_REG_HYST); + mutex_unlock(&priv->access_lock); + if (ret) + return ret; + + return count; +} + +static ssize_t show_therm_trip(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int ret; + struct stts751_priv *priv = dev_get_drvdata(dev); + + mutex_lock(&priv->access_lock); + ret = stts751_update(priv); + mutex_unlock(&priv->access_lock); + if (ret < 0) + return ret; + + return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->therm_trip); +} + +static ssize_t show_max(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct stts751_priv *priv = dev_get_drvdata(dev); + + return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->event_max); +} + +static ssize_t set_max(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + int ret; + long temp; + struct stts751_priv *priv = dev_get_drvdata(dev); + + if (kstrtol(buf, 10, &temp) < 0) + return -EINVAL; + + mutex_lock(&priv->access_lock); + /* HW works in range -64C to +127.937C */ + temp = clamp_val(temp, priv->event_min, 127937); + ret = stts751_set_temp_reg16(priv, temp, + STTS751_REG_HLIM_H, STTS751_REG_HLIM_L); + if (ret) + goto exit; + + dev_dbg(&priv->client->dev, "setting event max %ld", temp); + priv->event_max = temp; + ret = count; +exit: + mutex_unlock(&priv->access_lock); + return ret; +} + +static ssize_t show_min(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct stts751_priv *priv = dev_get_drvdata(dev); + + return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->event_min); +} + +static ssize_t set_min(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + int ret; + long temp; + struct stts751_priv *priv = dev_get_drvdata(dev); + + if (kstrtol(buf, 10, &temp) < 0) + return -EINVAL; + + mutex_lock(&priv->access_lock); + /* HW works in range -64C to +127.937C */ + temp = clamp_val(temp, -64000, priv->event_max); + ret = stts751_set_temp_reg16(priv, temp, + STTS751_REG_LLIM_H, STTS751_REG_LLIM_L); + if (ret) + goto exit; + + dev_dbg(&priv->client->dev, "setting event min %ld", temp); + priv->event_min = temp; + ret = count; +exit: + mutex_unlock(&priv->access_lock); + return ret; +} + +static ssize_t show_interval(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct stts751_priv *priv = dev_get_drvdata(dev); + + return snprintf(buf, PAGE_SIZE - 1, "%d\n", + stts751_intervals[priv->interval]); +} + +static ssize_t set_interval(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val; + int idx; + int ret = count; + struct stts751_priv *priv = dev_get_drvdata(dev); + + if (kstrtoul(buf, 10, &val) < 0) + return -EINVAL; + + idx = find_closest_descending(val, stts751_intervals, + ARRAY_SIZE(stts751_intervals)); + + dev_dbg(&priv->client->dev, "setting interval. req:%lu, idx: %d, val: %d", + val, idx, stts751_intervals[idx]); + + mutex_lock(&priv->access_lock); + if (priv->interval == idx) + goto exit; + + /* + * In early development stages I've become suspicious about the chip + * starting to misbehave if I ever set, even briefly, an invalid + * configuration. While I'm not sure this is really needed, be + * conservative and set rate/resolution in such an order that avoids + * passing through an invalid configuration. + */ + + /* speed up: lower the resolution, then modify convrate */ + if (priv->interval < idx) { + dev_dbg(&priv->client->dev, "lower resolution, then modify convrate"); + priv->interval = idx; + ret = stts751_adjust_resolution(priv); + if (ret) + goto exit; + } + + ret = i2c_smbus_write_byte_data(priv->client, STTS751_REG_RATE, idx); + if (ret) + goto exit; + /* slow down: modify convrate, then raise resolution */ + if (priv->interval != idx) { + dev_dbg(&priv->client->dev, "modify convrate, then raise resolution"); + priv->interval = idx; + ret = stts751_adjust_resolution(priv); + if (ret) + goto exit; + } + ret = count; +exit: + mutex_unlock(&priv->access_lock); + + return ret; +} + +static int stts751_detect(struct i2c_client *new_client, + struct i2c_board_info *info) +{ + struct i2c_adapter *adapter = new_client->adapter; + const char *name; + int tmp; + + if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) + return -ENODEV; + + tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_MAN_ID); + if (tmp != ST_MAN_ID) + return -ENODEV; + + /* lower temperaure registers always have bits 0-3 set to zero */ + tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_TEMP_L); + if (tmp & 0xf) + return -ENODEV; + + tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_HLIM_L); + if (tmp & 0xf) + return -ENODEV; + + tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_LLIM_L); + if (tmp & 0xf) + return -ENODEV; + + /* smbus timeout register always have bits 0-7 set to zero */ + tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_SMBUS_TO); + if (tmp & 0x7f) + return -ENODEV; + + tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_PROD_ID); + + switch (tmp) { + case STTS751_0_PROD_ID: + name = "STTS751-0"; + break; + case STTS751_1_PROD_ID: + name = "STTS751-1"; + break; + default: + return -ENODEV; + } + dev_dbg(&new_client->dev, "Chip %s detected", name); + + strlcpy(info->type, stts751_id[0].name, I2C_NAME_SIZE); + return 0; +} + +static int stts751_read_chip_config(struct stts751_priv *priv) +{ + int ret; + int tmp; + + ret = i2c_smbus_read_byte_data(priv->client, STTS751_REG_CONF); + if (ret < 0) + return ret; + priv->config = ret; + priv->res = (ret & STTS751_CONF_RES_MASK) >> STTS751_CONF_RES_SHIFT; + + ret = i2c_smbus_read_byte_data(priv->client, STTS751_REG_RATE); + if (ret < 0) + return ret; + priv->interval = ret; + + ret = stts751_read_reg16(priv, &priv->event_max, + STTS751_REG_HLIM_H, STTS751_REG_HLIM_L); + if (ret) + return ret; + + ret = stts751_read_reg16(priv, &priv->event_min, + STTS751_REG_LLIM_H, STTS751_REG_LLIM_L); + if (ret) + return ret; + + ret = stts751_read_reg8(priv, &priv->therm, STTS751_REG_TLIM); + if (ret) + return ret; + + ret = stts751_read_reg8(priv, &tmp, STTS751_REG_HYST); + if (ret) + return ret; + priv->hyst = priv->therm - tmp; + + return 0; +} + +static SENSOR_DEVICE_ATTR(temp1_input, 0444, show_input, NULL, 0); +static SENSOR_DEVICE_ATTR(temp1_min, 0644, show_min, set_min, 0); +static SENSOR_DEVICE_ATTR(temp1_max, 0644, show_max, set_max, 0); +static SENSOR_DEVICE_ATTR(temp1_min_alarm, 0444, show_min_alarm, NULL, 0); +static SENSOR_DEVICE_ATTR(temp1_max_alarm, 0444, show_max_alarm, NULL, 0); +static SENSOR_DEVICE_ATTR(temp1_crit, 0644, show_therm, set_therm, 0); +static SENSOR_DEVICE_ATTR(temp1_crit_hyst, 0644, show_hyst, set_hyst, 0); +static SENSOR_DEVICE_ATTR(temp1_crit_alarm, 0444, show_therm_trip, NULL, 0); +static SENSOR_DEVICE_ATTR(update_interval, 0644, + show_interval, set_interval, 0); + +static struct attribute *stts751_attrs[] = { + &sensor_dev_attr_temp1_input.dev_attr.attr, + &sensor_dev_attr_temp1_min.dev_attr.attr, + &sensor_dev_attr_temp1_max.dev_attr.attr, + &sensor_dev_attr_temp1_min_alarm.dev_attr.attr, + &sensor_dev_attr_temp1_max_alarm.dev_attr.attr, + &sensor_dev_attr_temp1_crit.dev_attr.attr, + &sensor_dev_attr_temp1_crit_hyst.dev_attr.attr, + &sensor_dev_attr_temp1_crit_alarm.dev_attr.attr, + &sensor_dev_attr_update_interval.dev_attr.attr, + NULL +}; +ATTRIBUTE_GROUPS(stts751); + +static int stts751_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct stts751_priv *priv; + int ret; + bool smbus_nto; + int rev_id; + + priv = devm_kzalloc(&client->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->client = client; + priv->notify_max = true; + priv->notify_min = true; + i2c_set_clientdata(client, priv); + mutex_init(&priv->access_lock); + + if (device_property_present(&client->dev, + "smbus-timeout-disable")) { + smbus_nto = device_property_read_bool(&client->dev, + "smbus-timeout-disable"); + + ret = i2c_smbus_write_byte_data(client, STTS751_REG_SMBUS_TO, + smbus_nto ? 0 : 0x80); + if (ret) + return ret; + } + + rev_id = i2c_smbus_read_byte_data(client, STTS751_REG_REV_ID); + if (rev_id < 0) + return -ENODEV; + if (rev_id != 0x1) { + dev_dbg(&client->dev, "Chip revision 0x%x is untested\n", + rev_id); + } + + ret = stts751_read_chip_config(priv); + if (ret) + return ret; + + priv->config &= ~(STTS751_CONF_STOP | STTS751_CONF_EVENT_DIS); + ret = i2c_smbus_write_byte_data(client, STTS751_REG_CONF, priv->config); + if (ret) + return ret; + + priv->dev = devm_hwmon_device_register_with_groups(&client->dev, + client->name, priv, + stts751_groups); + return PTR_ERR_OR_ZERO(priv->dev); +} + +MODULE_DEVICE_TABLE(i2c, stts751_id); + +static struct i2c_driver stts751_driver = { + .class = I2C_CLASS_HWMON, + .driver = { + .name = DEVNAME, + }, + .probe = stts751_probe, + .id_table = stts751_id, + .detect = stts751_detect, + .alert = stts751_alert, + .address_list = normal_i2c, +}; + +module_i2c_driver(stts751_driver); + +MODULE_AUTHOR("Andrea Merello <andrea.merello@gmail.com>"); +MODULE_DESCRIPTION("STTS751 sensor driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c index eeeed2c7d081..1f2d13dc9439 100644 --- a/drivers/hwmon/tmp401.c +++ b/drivers/hwmon/tmp401.c @@ -82,16 +82,6 @@ static const u8 TMP401_TEMP_MSB_WRITE[7][2] = { { 0, 0x11 }, /* offset */ }; -static const u8 TMP401_TEMP_LSB[7][2] = { - { 0x15, 0x10 }, /* temp */ - { 0x17, 0x14 }, /* low limit */ - { 0x16, 0x13 }, /* high limit */ - { 0, 0 }, /* therm (crit) limit (unused) */ - { 0x31, 0x35 }, /* lowest */ - { 0x33, 0x37 }, /* highest */ - { 0, 0x12 }, /* offset */ -}; - static const u8 TMP432_TEMP_MSB_READ[4][3] = { { 0x00, 0x01, 0x23 }, /* temp */ { 0x06, 0x08, 0x16 }, /* low limit */ @@ -106,12 +96,6 @@ static const u8 TMP432_TEMP_MSB_WRITE[4][3] = { { 0x20, 0x19, 0x1A }, /* therm (crit) limit */ }; -static const u8 TMP432_TEMP_LSB[3][3] = { - { 0x29, 0x10, 0x24 }, /* temp */ - { 0x3E, 0x14, 0x18 }, /* low limit */ - { 0x3D, 0x13, 0x17 }, /* high limit */ -}; - /* [0] = fault, [1] = low, [2] = high, [3] = therm/crit */ static const u8 TMP432_STATUS_REG[] = { 0x1b, 0x36, 0x35, 0x37 }; @@ -213,25 +197,20 @@ static int tmp401_update_device_reg16(struct i2c_client *client, for (i = 0; i < num_sensors; i++) { /* local / r1 / r2 */ for (j = 0; j < num_regs; j++) { /* temp / low / ... */ u8 regaddr; - /* - * High byte must be read first immediately followed - * by the low byte - */ + regaddr = data->kind == tmp432 ? TMP432_TEMP_MSB_READ[j][i] : TMP401_TEMP_MSB_READ[j][i]; - val = i2c_smbus_read_byte_data(client, regaddr); - if (val < 0) - return val; - data->temp[j][i] = val << 8; - if (j == 3) /* crit is msb only */ - continue; - regaddr = data->kind == tmp432 ? TMP432_TEMP_LSB[j][i] - : TMP401_TEMP_LSB[j][i]; - val = i2c_smbus_read_byte_data(client, regaddr); + if (j == 3) { /* crit is msb only */ + val = i2c_smbus_read_byte_data(client, regaddr); + } else { + val = i2c_smbus_read_word_swapped(client, + regaddr); + } if (val < 0) return val; - data->temp[j][i] |= val; + + data->temp[j][i] = j == 3 ? val << 8 : val; } } return 0; @@ -373,11 +352,11 @@ static ssize_t store_temp(struct device *dev, struct device_attribute *devattr, regaddr = data->kind == tmp432 ? TMP432_TEMP_MSB_WRITE[nr][index] : TMP401_TEMP_MSB_WRITE[nr][index]; - i2c_smbus_write_byte_data(client, regaddr, reg >> 8); - if (nr != 3) { - regaddr = data->kind == tmp432 ? TMP432_TEMP_LSB[nr][index] - : TMP401_TEMP_LSB[nr][index]; - i2c_smbus_write_byte_data(client, regaddr, reg & 0xFF); + if (nr == 3) { /* crit is msb only */ + i2c_smbus_write_byte_data(client, regaddr, reg >> 8); + } else { + /* Hardware expects big endian data --> use _swapped */ + i2c_smbus_write_word_swapped(client, regaddr, reg); } data->temp[nr][index] = reg; @@ -449,7 +428,7 @@ static ssize_t reset_temp_history(struct device *dev, return count; } -static ssize_t show_update_interval(struct device *dev, +static ssize_t update_interval_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tmp401_data *data = dev_get_drvdata(dev); @@ -457,9 +436,9 @@ static ssize_t show_update_interval(struct device *dev, return sprintf(buf, "%u\n", data->update_interval); } -static ssize_t set_update_interval(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t update_interval_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct tmp401_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; @@ -521,8 +500,7 @@ static SENSOR_DEVICE_ATTR_2(temp2_max_alarm, S_IRUGO, show_status, NULL, static SENSOR_DEVICE_ATTR_2(temp2_crit_alarm, S_IRUGO, show_status, NULL, 3, TMP432_STATUS_REMOTE1); -static DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, show_update_interval, - set_update_interval); +static DEVICE_ATTR_RW(update_interval); static struct attribute *tmp401_attributes[] = { &sensor_dev_attr_temp1_input.dev_attr.attr, diff --git a/drivers/hwmon/via-cputemp.c b/drivers/hwmon/via-cputemp.c index d1f209a5feac..07a0cb0a1f28 100644 --- a/drivers/hwmon/via-cputemp.c +++ b/drivers/hwmon/via-cputemp.c @@ -88,8 +88,8 @@ static ssize_t show_temp(struct device *dev, return sprintf(buf, "%lu\n", ((unsigned long)eax & 0xffffff) * 1000); } -static ssize_t show_cpu_vid(struct device *dev, - struct device_attribute *devattr, char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *devattr, char *buf) { struct via_cputemp_data *data = dev_get_drvdata(dev); u32 eax, edx; @@ -119,7 +119,7 @@ static const struct attribute_group via_cputemp_group = { }; /* Optional attributes */ -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_cpu_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); static int via_cputemp_probe(struct platform_device *pdev) { diff --git a/drivers/hwmon/via686a.c b/drivers/hwmon/via686a.c index 40dd93c8f9f4..81f35e3a06b8 100644 --- a/drivers/hwmon/via686a.c +++ b/drivers/hwmon/via686a.c @@ -580,14 +580,14 @@ show_fan_offset(1); show_fan_offset(2); /* Alarms */ -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct via686a_data *data = via686a_update_device(dev); return sprintf(buf, "%u\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) @@ -607,13 +607,13 @@ static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 15); static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6); static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7); -static ssize_t show_name(struct device *dev, struct device_attribute +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct via686a_data *data = dev_get_drvdata(dev); return sprintf(buf, "%s\n", data->name); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static struct attribute *via686a_attributes[] = { &sensor_dev_attr_in0_input.dev_attr.attr, diff --git a/drivers/hwmon/vt8231.c b/drivers/hwmon/vt8231.c index cb69a8c2ed5b..367b5eb53fb6 100644 --- a/drivers/hwmon/vt8231.c +++ b/drivers/hwmon/vt8231.c @@ -263,8 +263,8 @@ static ssize_t set_in_max(struct device *dev, struct device_attribute *attr, } /* Special case for input 5 as this has 3.3V scaling built into the chip */ -static ssize_t show_in5(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t in5_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct vt8231_data *data = vt8231_update_device(dev); @@ -272,7 +272,7 @@ static ssize_t show_in5(struct device *dev, struct device_attribute *attr, (((data->in[5] - 3) * 10000 * 54) / (958 * 34))); } -static ssize_t show_in5_min(struct device *dev, struct device_attribute *attr, +static ssize_t in5_min_show(struct device *dev, struct device_attribute *attr, char *buf) { struct vt8231_data *data = vt8231_update_device(dev); @@ -281,7 +281,7 @@ static ssize_t show_in5_min(struct device *dev, struct device_attribute *attr, (((data->in_min[5] - 3) * 10000 * 54) / (958 * 34))); } -static ssize_t show_in5_max(struct device *dev, struct device_attribute *attr, +static ssize_t in5_max_show(struct device *dev, struct device_attribute *attr, char *buf) { struct vt8231_data *data = vt8231_update_device(dev); @@ -290,8 +290,9 @@ static ssize_t show_in5_max(struct device *dev, struct device_attribute *attr, (((data->in_max[5] - 3) * 10000 * 54) / (958 * 34))); } -static ssize_t set_in5_min(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t in5_min_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct vt8231_data *data = dev_get_drvdata(dev); unsigned long val; @@ -309,8 +310,9 @@ static ssize_t set_in5_min(struct device *dev, struct device_attribute *attr, return count; } -static ssize_t set_in5_max(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t in5_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct vt8231_data *data = dev_get_drvdata(dev); unsigned long val; @@ -342,34 +344,35 @@ define_voltage_sysfs(2); define_voltage_sysfs(3); define_voltage_sysfs(4); -static DEVICE_ATTR(in5_input, S_IRUGO, show_in5, NULL); -static DEVICE_ATTR(in5_min, S_IRUGO | S_IWUSR, show_in5_min, set_in5_min); -static DEVICE_ATTR(in5_max, S_IRUGO | S_IWUSR, show_in5_max, set_in5_max); +static DEVICE_ATTR_RO(in5_input); +static DEVICE_ATTR_RW(in5_min); +static DEVICE_ATTR_RW(in5_max); /* Temperatures */ -static ssize_t show_temp0(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t temp1_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct vt8231_data *data = vt8231_update_device(dev); return sprintf(buf, "%d\n", data->temp[0] * 250); } -static ssize_t show_temp0_max(struct device *dev, struct device_attribute *attr, +static ssize_t temp1_max_show(struct device *dev, struct device_attribute *attr, char *buf) { struct vt8231_data *data = vt8231_update_device(dev); return sprintf(buf, "%d\n", data->temp_max[0] * 1000); } -static ssize_t show_temp0_min(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t temp1_max_hyst_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct vt8231_data *data = vt8231_update_device(dev); return sprintf(buf, "%d\n", data->temp_min[0] * 1000); } -static ssize_t set_temp0_max(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t temp1_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct vt8231_data *data = dev_get_drvdata(dev); long val; @@ -385,8 +388,9 @@ static ssize_t set_temp0_max(struct device *dev, struct device_attribute *attr, mutex_unlock(&data->update_lock); return count; } -static ssize_t set_temp0_min(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t temp1_max_hyst_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct vt8231_data *data = dev_get_drvdata(dev); long val; @@ -481,10 +485,9 @@ static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IRUGO | S_IWUSR, \ static SENSOR_DEVICE_ATTR(temp##offset##_max_hyst, S_IRUGO | S_IWUSR, \ show_temp_min, set_temp_min, offset - 1) -static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp0, NULL); -static DEVICE_ATTR(temp1_max, S_IRUGO | S_IWUSR, show_temp0_max, set_temp0_max); -static DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR, show_temp0_min, - set_temp0_min); +static DEVICE_ATTR_RO(temp1_input); +static DEVICE_ATTR_RW(temp1_max); +static DEVICE_ATTR_RW(temp1_max_hyst); define_temperature_sysfs(2); define_temperature_sysfs(3); @@ -603,13 +606,13 @@ define_fan_sysfs(1); define_fan_sysfs(2); /* Alarms */ -static ssize_t show_alarms(struct device *dev, struct device_attribute *attr, +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct vt8231_data *data = vt8231_update_device(dev); return sprintf(buf, "%d\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) @@ -633,13 +636,13 @@ static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 2); static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6); static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7); -static ssize_t show_name(struct device *dev, struct device_attribute +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct vt8231_data *data = dev_get_drvdata(dev); return sprintf(buf, "%s\n", data->name); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static struct attribute *vt8231_attributes_temps[6][5] = { { diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c index 697007afb99c..ab346ed142de 100644 --- a/drivers/hwmon/w83627ehf.c +++ b/drivers/hwmon/w83627ehf.c @@ -1687,14 +1687,14 @@ store_##reg(struct device *dev, struct device_attribute *attr, \ fan_time_functions(fan_stop_time, FAN_STOP_TIME) -static ssize_t show_name(struct device *dev, struct device_attribute *attr, +static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83627ehf_data *data = dev_get_drvdata(dev); return sprintf(buf, "%s\n", data->name); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static struct sensor_device_attribute sda_sf3_arrays_fan4[] = { SENSOR_ATTR(pwm4_stop_time, S_IWUSR | S_IRUGO, show_fan_stop_time, @@ -1754,12 +1754,12 @@ static struct sensor_device_attribute sda_sf3_max_step_arrays[] = { }; static ssize_t -show_vid(struct device *dev, struct device_attribute *attr, char *buf) +cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83627ehf_data *data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL); +static DEVICE_ATTR_RO(cpu0_vid); /* Case open detection */ diff --git a/drivers/hwmon/w83627hf.c b/drivers/hwmon/w83627hf.c index 721295b9a051..8ac89d0781cc 100644 --- a/drivers/hwmon/w83627hf.c +++ b/drivers/hwmon/w83627hf.c @@ -575,26 +575,30 @@ static ssize_t show_in_0(struct w83627hf_data *data, char *buf, u8 reg) return sprintf(buf,"%ld\n", in0); } -static ssize_t show_regs_in_0(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t in0_input_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct w83627hf_data *data = w83627hf_update_device(dev); return show_in_0(data, buf, data->in[0]); } -static ssize_t show_regs_in_min0(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t in0_min_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct w83627hf_data *data = w83627hf_update_device(dev); return show_in_0(data, buf, data->in_min[0]); } -static ssize_t show_regs_in_max0(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t in0_max_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct w83627hf_data *data = w83627hf_update_device(dev); return show_in_0(data, buf, data->in_max[0]); } -static ssize_t store_regs_in_min0(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t in0_min_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct w83627hf_data *data = dev_get_drvdata(dev); unsigned long val; @@ -622,8 +626,9 @@ static ssize_t store_regs_in_min0(struct device *dev, struct device_attribute *a return count; } -static ssize_t store_regs_in_max0(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t in0_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct w83627hf_data *data = dev_get_drvdata(dev); unsigned long val; @@ -651,11 +656,9 @@ static ssize_t store_regs_in_max0(struct device *dev, struct device_attribute *a return count; } -static DEVICE_ATTR(in0_input, S_IRUGO, show_regs_in_0, NULL); -static DEVICE_ATTR(in0_min, S_IRUGO | S_IWUSR, - show_regs_in_min0, store_regs_in_min0); -static DEVICE_ATTR(in0_max, S_IRUGO | S_IWUSR, - show_regs_in_max0, store_regs_in_max0); +static DEVICE_ATTR_RO(in0_input); +static DEVICE_ATTR_RW(in0_min); +static DEVICE_ATTR_RW(in0_max); static ssize_t show_fan_input(struct device *dev, struct device_attribute *devattr, char *buf) @@ -796,21 +799,22 @@ sysfs_temp_decl(2); sysfs_temp_decl(3); static ssize_t -show_vid_reg(struct device *dev, struct device_attribute *attr, char *buf) +cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83627hf_data *data = w83627hf_update_device(dev); return sprintf(buf, "%ld\n", (long) vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL); +static DEVICE_ATTR_RO(cpu0_vid); static ssize_t -show_vrm_reg(struct device *dev, struct device_attribute *attr, char *buf) +vrm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83627hf_data *data = dev_get_drvdata(dev); return sprintf(buf, "%ld\n", (long) data->vrm); } static ssize_t -store_vrm_reg(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) +vrm_store(struct device *dev, struct device_attribute *attr, const char *buf, + size_t count) { struct w83627hf_data *data = dev_get_drvdata(dev); unsigned long val; @@ -826,15 +830,15 @@ store_vrm_reg(struct device *dev, struct device_attribute *attr, const char *buf return count; } -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg); +static DEVICE_ATTR_RW(vrm); static ssize_t -show_alarms_reg(struct device *dev, struct device_attribute *attr, char *buf) +alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83627hf_data *data = w83627hf_update_device(dev); return sprintf(buf, "%ld\n", (long) data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) @@ -860,7 +864,7 @@ static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5); static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 13); static ssize_t -show_beep_mask(struct device *dev, struct device_attribute *attr, char *buf) +beep_mask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83627hf_data *data = w83627hf_update_device(dev); return sprintf(buf, "%ld\n", @@ -868,7 +872,7 @@ show_beep_mask(struct device *dev, struct device_attribute *attr, char *buf) } static ssize_t -store_beep_mask(struct device *dev, struct device_attribute *attr, +beep_mask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct w83627hf_data *data = dev_get_drvdata(dev); @@ -895,8 +899,7 @@ store_beep_mask(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(beep_mask, S_IRUGO | S_IWUSR, - show_beep_mask, store_beep_mask); +static DEVICE_ATTR_RW(beep_mask); static ssize_t show_beep(struct device *dev, struct device_attribute *attr, char *buf) @@ -1264,13 +1267,13 @@ sysfs_temp_type(2); sysfs_temp_type(3); static ssize_t -show_name(struct device *dev, struct device_attribute *devattr, char *buf) +name_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct w83627hf_data *data = dev_get_drvdata(dev); return sprintf(buf, "%s\n", data->name); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static int __init w83627hf_find(int sioaddr, unsigned short *addr, struct w83627hf_sio_data *sio_data) diff --git a/drivers/hwmon/w83781d.c b/drivers/hwmon/w83781d.c index 54848fdd181e..246fb2365126 100644 --- a/drivers/hwmon/w83781d.c +++ b/drivers/hwmon/w83781d.c @@ -416,24 +416,24 @@ sysfs_temp_offsets(2); sysfs_temp_offsets(3); static ssize_t -show_vid_reg(struct device *dev, struct device_attribute *attr, char *buf) +cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83781d_data *data = w83781d_update_device(dev); return sprintf(buf, "%ld\n", (long) vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL); +static DEVICE_ATTR_RO(cpu0_vid); static ssize_t -show_vrm_reg(struct device *dev, struct device_attribute *attr, char *buf) +vrm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83781d_data *data = dev_get_drvdata(dev); return sprintf(buf, "%ld\n", (long) data->vrm); } static ssize_t -store_vrm_reg(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +vrm_store(struct device *dev, struct device_attribute *attr, const char *buf, + size_t count) { struct w83781d_data *data = dev_get_drvdata(dev); unsigned long val; @@ -447,16 +447,16 @@ store_vrm_reg(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg); +static DEVICE_ATTR_RW(vrm); static ssize_t -show_alarms_reg(struct device *dev, struct device_attribute *attr, char *buf) +alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83781d_data *data = w83781d_update_device(dev); return sprintf(buf, "%u\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL); +static DEVICE_ATTR_RO(alarms); static ssize_t show_alarm(struct device *dev, struct device_attribute *attr, char *buf) @@ -491,7 +491,7 @@ static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 4); static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5); static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_temp3_alarm, NULL, 0); -static ssize_t show_beep_mask(struct device *dev, +static ssize_t beep_mask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83781d_data *data = w83781d_update_device(dev); @@ -500,7 +500,7 @@ static ssize_t show_beep_mask(struct device *dev, } static ssize_t -store_beep_mask(struct device *dev, struct device_attribute *attr, +beep_mask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct w83781d_data *data = dev_get_drvdata(dev); @@ -527,8 +527,7 @@ store_beep_mask(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(beep_mask, S_IRUGO | S_IWUSR, - show_beep_mask, store_beep_mask); +static DEVICE_ATTR_RW(beep_mask); static ssize_t show_beep(struct device *dev, struct device_attribute *attr, char *buf) @@ -708,7 +707,7 @@ show_pwm(struct device *dev, struct device_attribute *da, char *buf) } static ssize_t -show_pwm2_enable(struct device *dev, struct device_attribute *da, char *buf) +pwm2_enable_show(struct device *dev, struct device_attribute *da, char *buf) { struct w83781d_data *data = w83781d_update_device(dev); return sprintf(buf, "%d\n", (int)data->pwm2_enable); @@ -736,7 +735,7 @@ store_pwm(struct device *dev, struct device_attribute *da, const char *buf, } static ssize_t -store_pwm2_enable(struct device *dev, struct device_attribute *da, +pwm2_enable_store(struct device *dev, struct device_attribute *da, const char *buf, size_t count) { struct w83781d_data *data = dev_get_drvdata(dev); @@ -778,8 +777,7 @@ static SENSOR_DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 1); static SENSOR_DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 2); static SENSOR_DEVICE_ATTR(pwm4, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 3); /* only PWM2 can be enabled/disabled */ -static DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR, - show_pwm2_enable, store_pwm2_enable); +static DEVICE_ATTR_RW(pwm2_enable); static ssize_t show_sensor(struct device *dev, struct device_attribute *da, char *buf) @@ -1616,12 +1614,12 @@ static unsigned short isa_address = 0x290; * we must create it by ourselves. */ static ssize_t -show_name(struct device *dev, struct device_attribute *devattr, char *buf) +name_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct w83781d_data *data = dev_get_drvdata(dev); return sprintf(buf, "%s\n", data->name); } -static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static DEVICE_ATTR_RO(name); static struct w83781d_data *w83781d_data_if_isa(void) { diff --git a/drivers/hwmon/w83791d.c b/drivers/hwmon/w83791d.c index 001df856913f..8af6081b4ab4 100644 --- a/drivers/hwmon/w83791d.c +++ b/drivers/hwmon/w83791d.c @@ -1041,14 +1041,14 @@ static struct sensor_device_attribute sda_temp_alarm[] = { }; /* get realtime status of all sensors items: voltage, temp, fan */ -static ssize_t show_alarms_reg(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t alarms_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct w83791d_data *data = w83791d_update_device(dev); return sprintf(buf, "%u\n", data->alarms); } -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL); +static DEVICE_ATTR_RO(alarms); /* Beep control */ @@ -1147,25 +1147,24 @@ static struct sensor_device_attribute sda_beep_ctrl[] = { }; /* cpu voltage regulation information */ -static ssize_t show_vid_reg(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t cpu0_vid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct w83791d_data *data = w83791d_update_device(dev); return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); } -static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL); +static DEVICE_ATTR_RO(cpu0_vid); -static ssize_t show_vrm_reg(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t vrm_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct w83791d_data *data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", data->vrm); } -static ssize_t store_vrm_reg(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t vrm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct w83791d_data *data = dev_get_drvdata(dev); unsigned long val; @@ -1188,7 +1187,7 @@ static ssize_t store_vrm_reg(struct device *dev, return count; } -static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg); +static DEVICE_ATTR_RW(vrm); #define IN_UNIT_ATTRS(X) \ &sda_in_input[X].dev_attr.attr, \ diff --git a/drivers/hwmon/w83792d.c b/drivers/hwmon/w83792d.c index 0a8bce726b4b..d764602d70db 100644 --- a/drivers/hwmon/w83792d.c +++ b/drivers/hwmon/w83792d.c @@ -578,7 +578,7 @@ static ssize_t store_temp23(struct device *dev, struct device_attribute *attr, /* get realtime status of all sensors items: voltage, temp, fan */ static ssize_t -show_alarms_reg(struct device *dev, struct device_attribute *attr, char *buf) +alarms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83792d_data *data = w83792d_update_device(dev); return sprintf(buf, "%d\n", data->alarms); @@ -735,16 +735,16 @@ store_pwm_mode(struct device *dev, struct device_attribute *attr, } static ssize_t -show_chassis_clear(struct device *dev, struct device_attribute *attr, - char *buf) +intrusion0_alarm_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct w83792d_data *data = w83792d_update_device(dev); return sprintf(buf, "%d\n", data->chassis); } static ssize_t -store_chassis_clear(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +intrusion0_alarm_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct i2c_client *client = to_i2c_client(dev); struct w83792d_data *data = i2c_get_clientdata(client); @@ -1047,7 +1047,7 @@ static SENSOR_DEVICE_ATTR_2(temp2_max_hyst, S_IRUGO | S_IWUSR, show_temp23, store_temp23, 0, 4); static SENSOR_DEVICE_ATTR_2(temp3_max_hyst, S_IRUGO | S_IWUSR, show_temp23, store_temp23, 1, 4); -static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL); +static DEVICE_ATTR_RO(alarms); static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0); static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1); static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 2); @@ -1067,8 +1067,7 @@ static SENSOR_DEVICE_ATTR(in8_alarm, S_IRUGO, show_alarm, NULL, 20); static SENSOR_DEVICE_ATTR(fan4_alarm, S_IRUGO, show_alarm, NULL, 21); static SENSOR_DEVICE_ATTR(fan5_alarm, S_IRUGO, show_alarm, NULL, 22); static SENSOR_DEVICE_ATTR(fan6_alarm, S_IRUGO, show_alarm, NULL, 23); -static DEVICE_ATTR(intrusion0_alarm, S_IRUGO | S_IWUSR, - show_chassis_clear, store_chassis_clear); +static DEVICE_ATTR_RW(intrusion0_alarm); static SENSOR_DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 0); static SENSOR_DEVICE_ATTR(pwm2, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 1); static SENSOR_DEVICE_ATTR(pwm3, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 2); diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c index 816aa6caf5d5..dab5c515d5a3 100644 --- a/drivers/hwmon/w83793.c +++ b/drivers/hwmon/w83793.c @@ -324,7 +324,7 @@ static struct i2c_driver w83793_driver = { }; static ssize_t -show_vrm(struct device *dev, struct device_attribute *attr, char *buf) +vrm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct w83793_data *data = dev_get_drvdata(dev); return sprintf(buf, "%d\n", data->vrm); @@ -342,7 +342,7 @@ show_vid(struct device *dev, struct device_attribute *attr, char *buf) } static ssize_t -store_vrm(struct device *dev, struct device_attribute *attr, +vrm_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct w83793_data *data = dev_get_drvdata(dev); @@ -1169,7 +1169,7 @@ static struct sensor_device_attribute_2 w83793_vid[] = { SENSOR_ATTR_2(cpu0_vid, S_IRUGO, show_vid, NULL, NOT_USED, 0), SENSOR_ATTR_2(cpu1_vid, S_IRUGO, show_vid, NULL, NOT_USED, 1), }; -static DEVICE_ATTR(vrm, S_IWUSR | S_IRUGO, show_vrm, store_vrm); +static DEVICE_ATTR_RW(vrm); static struct sensor_device_attribute_2 sda_single_files[] = { SENSOR_ATTR_2(intrusion0_alarm, S_IWUSR | S_IRUGO, show_alarm_beep, diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index 6d81c56184d3..e9db857c6226 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -475,30 +475,28 @@ static int i2c_dw_wait_bus_not_busy(struct dw_i2c_dev *dev) static void i2c_dw_xfer_init(struct dw_i2c_dev *dev) { struct i2c_msg *msgs = dev->msgs; - u32 ic_tar = 0; + u32 ic_con, ic_tar = 0; /* Disable the adapter */ __i2c_dw_enable_and_wait(dev, false); /* if the slave address is ten bit address, enable 10BITADDR */ - if (dev->dynamic_tar_update_enabled) { + ic_con = dw_readl(dev, DW_IC_CON); + if (msgs[dev->msg_write_idx].flags & I2C_M_TEN) { + ic_con |= DW_IC_CON_10BITADDR_MASTER; /* * If I2C_DYNAMIC_TAR_UPDATE is set, the 10-bit addressing - * mode has to be enabled via bit 12 of IC_TAR register, - * otherwise bit 4 of IC_CON is used. + * mode has to be enabled via bit 12 of IC_TAR register. + * We set it always as I2C_DYNAMIC_TAR_UPDATE can't be + * detected from registers. */ - if (msgs[dev->msg_write_idx].flags & I2C_M_TEN) - ic_tar = DW_IC_TAR_10BITADDR_MASTER; + ic_tar = DW_IC_TAR_10BITADDR_MASTER; } else { - u32 ic_con = dw_readl(dev, DW_IC_CON); - - if (msgs[dev->msg_write_idx].flags & I2C_M_TEN) - ic_con |= DW_IC_CON_10BITADDR_MASTER; - else - ic_con &= ~DW_IC_CON_10BITADDR_MASTER; - dw_writel(dev, ic_con, DW_IC_CON); + ic_con &= ~DW_IC_CON_10BITADDR_MASTER; } + dw_writel(dev, ic_con, DW_IC_CON); + /* * Set the slave (target) address and enable 10-bit addressing mode * if applicable. @@ -963,7 +961,6 @@ int i2c_dw_probe(struct dw_i2c_dev *dev) { struct i2c_adapter *adap = &dev->adapter; int r; - u32 reg; init_completion(&dev->cmd_complete); @@ -971,26 +968,6 @@ int i2c_dw_probe(struct dw_i2c_dev *dev) if (r) return r; - r = i2c_dw_acquire_lock(dev); - if (r) - return r; - - /* - * Test if dynamic TAR update is enabled in this controller by writing - * to IC_10BITADDR_MASTER field in IC_CON: when it is enabled this - * field is read-only so it should not succeed - */ - reg = dw_readl(dev, DW_IC_CON); - dw_writel(dev, reg ^ DW_IC_CON_10BITADDR_MASTER, DW_IC_CON); - - if ((dw_readl(dev, DW_IC_CON) & DW_IC_CON_10BITADDR_MASTER) == - (reg & DW_IC_CON_10BITADDR_MASTER)) { - dev->dynamic_tar_update_enabled = true; - dev_dbg(dev->dev, "Dynamic TAR update enabled"); - } - - i2c_dw_release_lock(dev); - snprintf(adap->name, sizeof(adap->name), "Synopsys DesignWare I2C adapter"); adap->retries = 3; diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index 26250b425e2f..c1db3a5a340f 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -125,7 +125,6 @@ struct dw_i2c_dev { int (*acquire_lock)(struct dw_i2c_dev *dev); void (*release_lock)(struct dw_i2c_dev *dev); bool pm_runtime_disabled; - bool dynamic_tar_update_enabled; }; #define ACCESS_SWAP 0x00000001 diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.h b/drivers/infiniband/hw/cxgb3/iwch_cm.h index b9efadfffb4f..e66e75921797 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_cm.h +++ b/drivers/infiniband/hw/cxgb3/iwch_cm.h @@ -55,14 +55,14 @@ #define put_ep(ep) { \ PDBG("put_ep (via %s:%u) ep %p refcnt %d\n", __func__, __LINE__, \ - ep, atomic_read(&((ep)->kref.refcount))); \ - WARN_ON(atomic_read(&((ep)->kref.refcount)) < 1); \ + ep, kref_read(&((ep)->kref))); \ + WARN_ON(kref_read(&((ep)->kref)) < 1); \ kref_put(&((ep)->kref), __free_ep); \ } #define get_ep(ep) { \ PDBG("get_ep (via %s:%u) ep %p, refcnt %d\n", __func__, __LINE__, \ - ep, atomic_read(&((ep)->kref.refcount))); \ + ep, kref_read(&((ep)->kref))); \ kref_get(&((ep)->kref)); \ } diff --git a/drivers/infiniband/hw/cxgb3/iwch_qp.c b/drivers/infiniband/hw/cxgb3/iwch_qp.c index d939980a708f..a9194db7f9b8 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_qp.c +++ b/drivers/infiniband/hw/cxgb3/iwch_qp.c @@ -961,7 +961,7 @@ int iwch_modify_qp(struct iwch_dev *rhp, struct iwch_qp *qhp, case IWCH_QP_STATE_RTS: switch (attrs->next_state) { case IWCH_QP_STATE_CLOSING: - BUG_ON(atomic_read(&qhp->ep->com.kref.refcount) < 2); + BUG_ON(kref_read(&qhp->ep->com.kref) < 2); qhp->attr.state = IWCH_QP_STATE_CLOSING; if (!internal) { abort=0; diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index 8cd4d054a87e..d19662f635b1 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -672,14 +672,14 @@ enum c4iw_mmid_state { #define c4iw_put_ep(ep) { \ PDBG("put_ep (via %s:%u) ep %p refcnt %d\n", __func__, __LINE__, \ - ep, atomic_read(&((ep)->kref.refcount))); \ - WARN_ON(atomic_read(&((ep)->kref.refcount)) < 1); \ + ep, kref_read(&((ep)->kref))); \ + WARN_ON(kref_read(&((ep)->kref)) < 1); \ kref_put(&((ep)->kref), _c4iw_free_ep); \ } #define c4iw_get_ep(ep) { \ PDBG("get_ep (via %s:%u) ep %p, refcnt %d\n", __func__, __LINE__, \ - ep, atomic_read(&((ep)->kref.refcount))); \ + ep, kref_read(&((ep)->kref))); \ kref_get(&((ep)->kref)); \ } void _c4iw_free_ep(struct kref *kref); diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 04c1c382dedb..d4fd2f5c8326 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1580,7 +1580,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp, case C4IW_QP_STATE_RTS: switch (attrs->next_state) { case C4IW_QP_STATE_CLOSING: - BUG_ON(atomic_read(&qhp->ep->com.kref.refcount) < 2); + BUG_ON(kref_read(&qhp->ep->com.kref) < 2); t4_set_wq_in_error(&qhp->wq); set_state(qhp, C4IW_QP_STATE_CLOSING); ep = qhp->ep; diff --git a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c index 80ef3f8998c8..04443242e258 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c @@ -80,7 +80,7 @@ usnic_ib_show_config(struct device *device, struct device_attribute *attr, left = PAGE_SIZE; mutex_lock(&us_ibdev->usdev_lock); - if (atomic_read(&us_ibdev->vf_cnt.refcount) > 0) { + if (kref_read(&us_ibdev->vf_cnt) > 0) { char *busname; /* @@ -99,7 +99,7 @@ usnic_ib_show_config(struct device *device, struct device_attribute *attr, PCI_FUNC(us_ibdev->pdev->devfn), netdev_name(us_ibdev->netdev), us_ibdev->ufdev->mac, - atomic_read(&us_ibdev->vf_cnt.refcount)); + kref_read(&us_ibdev->vf_cnt)); UPDATE_PTR_LEFT(n, ptr, left); for (res_type = USNIC_VNIC_RES_TYPE_EOL; @@ -147,7 +147,7 @@ usnic_ib_show_max_vf(struct device *device, struct device_attribute *attr, us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev); return scnprintf(buf, PAGE_SIZE, "%u\n", - atomic_read(&us_ibdev->vf_cnt.refcount)); + kref_read(&us_ibdev->vf_cnt)); } static ssize_t diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c index 74819a7951e2..69df8e353123 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c @@ -291,11 +291,11 @@ int usnic_ib_query_device(struct ib_device *ibdev, qp_per_vf = max(us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_WQ], us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_RQ]); props->max_qp = qp_per_vf * - atomic_read(&us_ibdev->vf_cnt.refcount); + kref_read(&us_ibdev->vf_cnt); props->device_cap_flags = IB_DEVICE_PORT_ACTIVE_EVENT | IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_BLOCK_MULTICAST_LOOPBACK; props->max_cq = us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_CQ] * - atomic_read(&us_ibdev->vf_cnt.refcount); + kref_read(&us_ibdev->vf_cnt); props->max_pd = USNIC_UIOM_MAX_PD_CNT; props->max_mr = USNIC_UIOM_MAX_MR_CNT; props->local_ca_ack_delay = 0; diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index fa598f7f4372..1e1d0ad406f2 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1231,6 +1231,7 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0000", 0 }, { "ELAN0100", 0 }, { "ELAN0600", 0 }, + { "ELAN0605", 0 }, { "ELAN1000", 0 }, { } }; diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index ae96731cd2fb..125528f39e92 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -283,3 +283,12 @@ config EZNPS_GIC config STM32_EXTI bool select IRQ_DOMAIN + +config QCOM_IRQ_COMBINER + bool "QCOM IRQ combiner support" + depends on ARCH_QCOM && ACPI + select IRQ_DOMAIN + select IRQ_DOMAIN_HIERARCHY + help + Say yes here to add support for the IRQ combiner devices embedded + in Qualcomm Technologies chips. diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index 0e55d94065bf..152bc40b6762 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_ATH79) += irq-ath79-misc.o obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2835.o obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2836.o obj-$(CONFIG_ARCH_EXYNOS) += exynos-combiner.o +obj-$(CONFIG_ARCH_GEMINI) += irq-gemini.o obj-$(CONFIG_ARCH_HIP04) += irq-hip04.o obj-$(CONFIG_ARCH_LPC32XX) += irq-lpc32xx.o obj-$(CONFIG_ARCH_MMP) += irq-mmp.o @@ -75,3 +76,4 @@ obj-$(CONFIG_LS_SCFG_MSI) += irq-ls-scfg-msi.o obj-$(CONFIG_EZNPS_GIC) += irq-eznps.o obj-$(CONFIG_ARCH_ASPEED) += irq-aspeed-vic.o obj-$(CONFIG_STM32_EXTI) += irq-stm32-exti.o +obj-$(CONFIG_QCOM_IRQ_COMBINER) += qcom-irq-combiner.o diff --git a/drivers/irqchip/irq-gemini.c b/drivers/irqchip/irq-gemini.c new file mode 100644 index 000000000000..495224c743ee --- /dev/null +++ b/drivers/irqchip/irq-gemini.c @@ -0,0 +1,185 @@ +/* + * irqchip for the Cortina Systems Gemini Copyright (C) 2017 Linus + * Walleij <linus.walleij@linaro.org> + * + * Based on arch/arm/mach-gemini/irq.c + * Copyright (C) 2001-2006 Storlink, Corp. + * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt> + */ +#include <linux/bitops.h> +#include <linux/irq.h> +#include <linux/io.h> +#include <linux/irqchip.h> +#include <linux/irqchip/versatile-fpga.h> +#include <linux/irqdomain.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/cpu.h> + +#include <asm/exception.h> +#include <asm/mach/irq.h> + +#define GEMINI_NUM_IRQS 32 + +#define GEMINI_IRQ_SOURCE(base_addr) (base_addr + 0x00) +#define GEMINI_IRQ_MASK(base_addr) (base_addr + 0x04) +#define GEMINI_IRQ_CLEAR(base_addr) (base_addr + 0x08) +#define GEMINI_IRQ_MODE(base_addr) (base_addr + 0x0C) +#define GEMINI_IRQ_POLARITY(base_addr) (base_addr + 0x10) +#define GEMINI_IRQ_STATUS(base_addr) (base_addr + 0x14) +#define GEMINI_FIQ_SOURCE(base_addr) (base_addr + 0x20) +#define GEMINI_FIQ_MASK(base_addr) (base_addr + 0x24) +#define GEMINI_FIQ_CLEAR(base_addr) (base_addr + 0x28) +#define GEMINI_FIQ_MODE(base_addr) (base_addr + 0x2C) +#define GEMINI_FIQ_POLARITY(base_addr) (base_addr + 0x30) +#define GEMINI_FIQ_STATUS(base_addr) (base_addr + 0x34) + +/** + * struct gemini_irq_data - irq data container for the Gemini IRQ controller + * @base: memory offset in virtual memory + * @chip: chip container for this instance + * @domain: IRQ domain for this instance + */ +struct gemini_irq_data { + void __iomem *base; + struct irq_chip chip; + struct irq_domain *domain; +}; + +static void gemini_irq_mask(struct irq_data *d) +{ + struct gemini_irq_data *g = irq_data_get_irq_chip_data(d); + unsigned int mask; + + mask = readl(GEMINI_IRQ_MASK(g->base)); + mask &= ~BIT(irqd_to_hwirq(d)); + writel(mask, GEMINI_IRQ_MASK(g->base)); +} + +static void gemini_irq_unmask(struct irq_data *d) +{ + struct gemini_irq_data *g = irq_data_get_irq_chip_data(d); + unsigned int mask; + + mask = readl(GEMINI_IRQ_MASK(g->base)); + mask |= BIT(irqd_to_hwirq(d)); + writel(mask, GEMINI_IRQ_MASK(g->base)); +} + +static void gemini_irq_ack(struct irq_data *d) +{ + struct gemini_irq_data *g = irq_data_get_irq_chip_data(d); + + writel(BIT(irqd_to_hwirq(d)), GEMINI_IRQ_CLEAR(g->base)); +} + +static int gemini_irq_set_type(struct irq_data *d, unsigned int trigger) +{ + struct gemini_irq_data *g = irq_data_get_irq_chip_data(d); + int offset = irqd_to_hwirq(d); + u32 mode, polarity; + + mode = readl(GEMINI_IRQ_MODE(g->base)); + polarity = readl(GEMINI_IRQ_POLARITY(g->base)); + + if (trigger & (IRQ_TYPE_LEVEL_HIGH)) { + irq_set_handler_locked(d, handle_level_irq); + /* Disable edge detection */ + mode &= ~BIT(offset); + polarity &= ~BIT(offset); + } else if (trigger & IRQ_TYPE_EDGE_RISING) { + irq_set_handler_locked(d, handle_edge_irq); + mode |= BIT(offset); + polarity |= BIT(offset); + } else if (trigger & IRQ_TYPE_EDGE_FALLING) { + irq_set_handler_locked(d, handle_edge_irq); + mode |= BIT(offset); + polarity &= ~BIT(offset); + } else { + irq_set_handler_locked(d, handle_bad_irq); + pr_warn("GEMINI IRQ: no supported trigger selected for line %d\n", + offset); + } + + writel(mode, GEMINI_IRQ_MODE(g->base)); + writel(polarity, GEMINI_IRQ_POLARITY(g->base)); + + return 0; +} + +static struct irq_chip gemini_irq_chip = { + .name = "GEMINI", + .irq_ack = gemini_irq_ack, + .irq_mask = gemini_irq_mask, + .irq_unmask = gemini_irq_unmask, + .irq_set_type = gemini_irq_set_type, +}; + +/* Local static for the IRQ entry call */ +static struct gemini_irq_data girq; + +asmlinkage void __exception_irq_entry gemini_irqchip_handle_irq(struct pt_regs *regs) +{ + struct gemini_irq_data *g = &girq; + int irq; + u32 status; + + while ((status = readl(GEMINI_IRQ_STATUS(g->base)))) { + irq = ffs(status) - 1; + handle_domain_irq(g->domain, irq, regs); + } +} + +static int gemini_irqdomain_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hwirq) +{ + struct gemini_irq_data *g = d->host_data; + + irq_set_chip_data(irq, g); + /* All IRQs should set up their type, flags as bad by default */ + irq_set_chip_and_handler(irq, &gemini_irq_chip, handle_bad_irq); + irq_set_probe(irq); + + return 0; +} + +static void gemini_irqdomain_unmap(struct irq_domain *d, unsigned int irq) +{ + irq_set_chip_and_handler(irq, NULL, NULL); + irq_set_chip_data(irq, NULL); +} + +static const struct irq_domain_ops gemini_irqdomain_ops = { + .map = gemini_irqdomain_map, + .unmap = gemini_irqdomain_unmap, + .xlate = irq_domain_xlate_onetwocell, +}; + +int __init gemini_of_init_irq(struct device_node *node, + struct device_node *parent) +{ + struct gemini_irq_data *g = &girq; + + /* + * Disable the idle handler by default since it is buggy + * For more info see arch/arm/mach-gemini/idle.c + */ + cpu_idle_poll_ctrl(true); + + g->base = of_iomap(node, 0); + WARN(!g->base, "unable to map gemini irq registers\n"); + + /* Disable all interrupts */ + writel(0, GEMINI_IRQ_MASK(g->base)); + writel(0, GEMINI_FIQ_MASK(g->base)); + + g->domain = irq_domain_add_simple(node, GEMINI_NUM_IRQS, 0, + &gemini_irqdomain_ops, g); + set_handle_irq(gemini_irqchip_handle_irq); + + return 0; +} +IRQCHIP_DECLARE(gemini, "cortina,gemini-interrupt-controller", + gemini_of_init_irq); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 69b040f47d56..4a895c6d6805 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -161,7 +161,7 @@ struct its_cmd_desc { struct its_device *dev; u32 phys_id; u32 event_id; - } its_mapvi_cmd; + } its_mapti_cmd; struct { struct its_device *dev; @@ -193,58 +193,56 @@ struct its_cmd_block { typedef struct its_collection *(*its_cmd_builder_t)(struct its_cmd_block *, struct its_cmd_desc *); +static void its_mask_encode(u64 *raw_cmd, u64 val, int h, int l) +{ + u64 mask = GENMASK_ULL(h, l); + *raw_cmd &= ~mask; + *raw_cmd |= (val << l) & mask; +} + static void its_encode_cmd(struct its_cmd_block *cmd, u8 cmd_nr) { - cmd->raw_cmd[0] &= ~0xffULL; - cmd->raw_cmd[0] |= cmd_nr; + its_mask_encode(&cmd->raw_cmd[0], cmd_nr, 7, 0); } static void its_encode_devid(struct its_cmd_block *cmd, u32 devid) { - cmd->raw_cmd[0] &= BIT_ULL(32) - 1; - cmd->raw_cmd[0] |= ((u64)devid) << 32; + its_mask_encode(&cmd->raw_cmd[0], devid, 63, 32); } static void its_encode_event_id(struct its_cmd_block *cmd, u32 id) { - cmd->raw_cmd[1] &= ~0xffffffffULL; - cmd->raw_cmd[1] |= id; + its_mask_encode(&cmd->raw_cmd[1], id, 31, 0); } static void its_encode_phys_id(struct its_cmd_block *cmd, u32 phys_id) { - cmd->raw_cmd[1] &= 0xffffffffULL; - cmd->raw_cmd[1] |= ((u64)phys_id) << 32; + its_mask_encode(&cmd->raw_cmd[1], phys_id, 63, 32); } static void its_encode_size(struct its_cmd_block *cmd, u8 size) { - cmd->raw_cmd[1] &= ~0x1fULL; - cmd->raw_cmd[1] |= size & 0x1f; + its_mask_encode(&cmd->raw_cmd[1], size, 4, 0); } static void its_encode_itt(struct its_cmd_block *cmd, u64 itt_addr) { - cmd->raw_cmd[2] &= ~0xffffffffffffULL; - cmd->raw_cmd[2] |= itt_addr & 0xffffffffff00ULL; + its_mask_encode(&cmd->raw_cmd[2], itt_addr >> 8, 50, 8); } static void its_encode_valid(struct its_cmd_block *cmd, int valid) { - cmd->raw_cmd[2] &= ~(1ULL << 63); - cmd->raw_cmd[2] |= ((u64)!!valid) << 63; + its_mask_encode(&cmd->raw_cmd[2], !!valid, 63, 63); } static void its_encode_target(struct its_cmd_block *cmd, u64 target_addr) { - cmd->raw_cmd[2] &= ~(0xffffffffULL << 16); - cmd->raw_cmd[2] |= (target_addr & (0xffffffffULL << 16)); + its_mask_encode(&cmd->raw_cmd[2], target_addr >> 16, 50, 16); } static void its_encode_collection(struct its_cmd_block *cmd, u16 col) { - cmd->raw_cmd[2] &= ~0xffffULL; - cmd->raw_cmd[2] |= col; + its_mask_encode(&cmd->raw_cmd[2], col, 15, 0); } static inline void its_fixup_cmd(struct its_cmd_block *cmd) @@ -289,18 +287,18 @@ static struct its_collection *its_build_mapc_cmd(struct its_cmd_block *cmd, return desc->its_mapc_cmd.col; } -static struct its_collection *its_build_mapvi_cmd(struct its_cmd_block *cmd, +static struct its_collection *its_build_mapti_cmd(struct its_cmd_block *cmd, struct its_cmd_desc *desc) { struct its_collection *col; - col = dev_event_to_col(desc->its_mapvi_cmd.dev, - desc->its_mapvi_cmd.event_id); + col = dev_event_to_col(desc->its_mapti_cmd.dev, + desc->its_mapti_cmd.event_id); - its_encode_cmd(cmd, GITS_CMD_MAPVI); - its_encode_devid(cmd, desc->its_mapvi_cmd.dev->device_id); - its_encode_event_id(cmd, desc->its_mapvi_cmd.event_id); - its_encode_phys_id(cmd, desc->its_mapvi_cmd.phys_id); + its_encode_cmd(cmd, GITS_CMD_MAPTI); + its_encode_devid(cmd, desc->its_mapti_cmd.dev->device_id); + its_encode_event_id(cmd, desc->its_mapti_cmd.event_id); + its_encode_phys_id(cmd, desc->its_mapti_cmd.phys_id); its_encode_collection(cmd, col->col_id); its_fixup_cmd(cmd); @@ -413,6 +411,12 @@ static struct its_cmd_block *its_allocate_entry(struct its_node *its) if (its->cmd_write == (its->cmd_base + ITS_CMD_QUEUE_NR_ENTRIES)) its->cmd_write = its->cmd_base; + /* Clear command */ + cmd->raw_cmd[0] = 0; + cmd->raw_cmd[1] = 0; + cmd->raw_cmd[2] = 0; + cmd->raw_cmd[3] = 0; + return cmd; } @@ -531,15 +535,15 @@ static void its_send_mapc(struct its_node *its, struct its_collection *col, its_send_single_command(its, its_build_mapc_cmd, &desc); } -static void its_send_mapvi(struct its_device *dev, u32 irq_id, u32 id) +static void its_send_mapti(struct its_device *dev, u32 irq_id, u32 id) { struct its_cmd_desc desc; - desc.its_mapvi_cmd.dev = dev; - desc.its_mapvi_cmd.phys_id = irq_id; - desc.its_mapvi_cmd.event_id = id; + desc.its_mapti_cmd.dev = dev; + desc.its_mapti_cmd.phys_id = irq_id; + desc.its_mapti_cmd.event_id = id; - its_send_single_command(dev->its, its_build_mapvi_cmd, &desc); + its_send_single_command(dev->its, its_build_mapti_cmd, &desc); } static void its_send_movi(struct its_device *dev, @@ -824,7 +828,7 @@ static int __init its_alloc_lpi_tables(void) static const char *its_base_type_string[] = { [GITS_BASER_TYPE_DEVICE] = "Devices", [GITS_BASER_TYPE_VCPU] = "Virtual CPUs", - [GITS_BASER_TYPE_CPU] = "Physical CPUs", + [GITS_BASER_TYPE_RESERVED3] = "Reserved (3)", [GITS_BASER_TYPE_COLLECTION] = "Interrupt Collections", [GITS_BASER_TYPE_RESERVED5] = "Reserved (5)", [GITS_BASER_TYPE_RESERVED6] = "Reserved (6)", @@ -960,7 +964,7 @@ static bool its_parse_baser_device(struct its_node *its, struct its_baser *baser u32 psz, u32 *order) { u64 esz = GITS_BASER_ENTRY_SIZE(its_read_baser(its, baser)); - u64 val = GITS_BASER_InnerShareable | GITS_BASER_WaWb; + u64 val = GITS_BASER_InnerShareable | GITS_BASER_RaWaWb; u32 ids = its->device_ids; u32 new_order = *order; bool indirect = false; @@ -1025,7 +1029,7 @@ static int its_alloc_tables(struct its_node *its) u64 typer = gic_read_typer(its->base + GITS_TYPER); u32 ids = GITS_TYPER_DEVBITS(typer); u64 shr = GITS_BASER_InnerShareable; - u64 cache = GITS_BASER_WaWb; + u64 cache = GITS_BASER_RaWaWb; u32 psz = SZ_64K; int err, i; @@ -1122,7 +1126,7 @@ static void its_cpu_init_lpis(void) /* set PROPBASE */ val = (page_to_phys(gic_rdists->prop_page) | GICR_PROPBASER_InnerShareable | - GICR_PROPBASER_WaWb | + GICR_PROPBASER_RaWaWb | ((LPI_NRBITS - 1) & GICR_PROPBASER_IDBITS_MASK)); gicr_write_propbaser(val, rbase + GICR_PROPBASER); @@ -1147,7 +1151,7 @@ static void its_cpu_init_lpis(void) /* set PENDBASE */ val = (page_to_phys(pend_page) | GICR_PENDBASER_InnerShareable | - GICR_PENDBASER_WaWb); + GICR_PENDBASER_RaWaWb); gicr_write_pendbaser(val, rbase + GICR_PENDBASER); tmp = gicr_read_pendbaser(rbase + GICR_PENDBASER); @@ -1498,7 +1502,7 @@ static void its_irq_domain_activate(struct irq_domain *domain, its_dev->event_map.col_map[event] = cpumask_first(cpu_mask); /* Map the GIC IRQ and event to the device */ - its_send_mapvi(its_dev, d->hwirq, event); + its_send_mapti(its_dev, d->hwirq, event); } static void its_irq_domain_deactivate(struct irq_domain *domain, @@ -1693,7 +1697,8 @@ static int __init its_probe_one(struct resource *res, its->ite_size = ((gic_read_typer(its_base + GITS_TYPER) >> 4) & 0xf) + 1; its->numa_node = numa_node; - its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL); + its->cmd_base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(ITS_CMD_QUEUE_SZ)); if (!its->cmd_base) { err = -ENOMEM; goto out_free_its; @@ -1711,7 +1716,7 @@ static int __init its_probe_one(struct resource *res, goto out_free_tables; baser = (virt_to_phys(its->cmd_base) | - GITS_CBASER_WaWb | + GITS_CBASER_RaWaWb | GITS_CBASER_InnerShareable | (ITS_CMD_QUEUE_SZ / SZ_4K - 1) | GITS_CBASER_VALID); @@ -1751,7 +1756,7 @@ static int __init its_probe_one(struct resource *res, out_free_tables: its_free_tables(its); out_free_cmd: - kfree(its->cmd_base); + free_pages((unsigned long)its->cmd_base, get_order(ITS_CMD_QUEUE_SZ)); out_free_its: kfree(its); out_unmap: diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index c01c09e9916d..11d12bccc4e7 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -968,6 +968,34 @@ static struct irq_domain_ops gic_ipi_domain_ops = { .match = gic_ipi_domain_match, }; +static void __init gic_map_single_int(struct device_node *node, + unsigned int irq) +{ + unsigned int linux_irq; + struct irq_fwspec local_int_fwspec = { + .fwnode = &node->fwnode, + .param_count = 3, + .param = { + [0] = GIC_LOCAL, + [1] = irq, + [2] = IRQ_TYPE_NONE, + }, + }; + + if (!gic_local_irq_is_routable(irq)) + return; + + linux_irq = irq_create_fwspec_mapping(&local_int_fwspec); + WARN_ON(!linux_irq); +} + +static void __init gic_map_interrupts(struct device_node *node) +{ + gic_map_single_int(node, GIC_LOCAL_INT_TIMER); + gic_map_single_int(node, GIC_LOCAL_INT_PERFCTR); + gic_map_single_int(node, GIC_LOCAL_INT_FDC); +} + static void __init __gic_init(unsigned long gic_base_addr, unsigned long gic_addrspace_size, unsigned int cpu_vec, unsigned int irqbase, @@ -1067,6 +1095,7 @@ static void __init __gic_init(unsigned long gic_base_addr, } gic_basic_init(); + gic_map_interrupts(node); } void __init gic_init(unsigned long gic_base_addr, diff --git a/drivers/irqchip/qcom-irq-combiner.c b/drivers/irqchip/qcom-irq-combiner.c new file mode 100644 index 000000000000..226558698344 --- /dev/null +++ b/drivers/irqchip/qcom-irq-combiner.c @@ -0,0 +1,296 @@ +/* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only 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. + */ + +/* + * Driver for interrupt combiners in the Top-level Control and Status + * Registers (TCSR) hardware block in Qualcomm Technologies chips. + * An interrupt combiner in this block combines a set of interrupts by + * OR'ing the individual interrupt signals into a summary interrupt + * signal routed to a parent interrupt controller, and provides read- + * only, 32-bit registers to query the status of individual interrupts. + * The status bit for IRQ n is bit (n % 32) within register (n / 32) + * of the given combiner. Thus, each combiner can be described as a set + * of register offsets and the number of IRQs managed. + */ + +#define pr_fmt(fmt) "QCOM80B1:" fmt + +#include <linux/acpi.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/platform_device.h> + +#define REG_SIZE 32 + +struct combiner_reg { + void __iomem *addr; + unsigned long enabled; +}; + +struct combiner { + struct irq_domain *domain; + int parent_irq; + u32 nirqs; + u32 nregs; + struct combiner_reg regs[0]; +}; + +static inline int irq_nr(u32 reg, u32 bit) +{ + return reg * REG_SIZE + bit; +} + +/* + * Handler for the cascaded IRQ. + */ +static void combiner_handle_irq(struct irq_desc *desc) +{ + struct combiner *combiner = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + u32 reg; + + chained_irq_enter(chip, desc); + + for (reg = 0; reg < combiner->nregs; reg++) { + int virq; + int hwirq; + u32 bit; + u32 status; + + bit = readl_relaxed(combiner->regs[reg].addr); + status = bit & combiner->regs[reg].enabled; + if (!status) + pr_warn_ratelimited("Unexpected IRQ on CPU%d: (%08x %08lx %p)\n", + smp_processor_id(), bit, + combiner->regs[reg].enabled, + combiner->regs[reg].addr); + + while (status) { + bit = __ffs(status); + status &= ~(1 << bit); + hwirq = irq_nr(reg, bit); + virq = irq_find_mapping(combiner->domain, hwirq); + if (virq > 0) + generic_handle_irq(virq); + + } + } + + chained_irq_exit(chip, desc); +} + +static void combiner_irq_chip_mask_irq(struct irq_data *data) +{ + struct combiner *combiner = irq_data_get_irq_chip_data(data); + struct combiner_reg *reg = combiner->regs + data->hwirq / REG_SIZE; + + clear_bit(data->hwirq % REG_SIZE, ®->enabled); +} + +static void combiner_irq_chip_unmask_irq(struct irq_data *data) +{ + struct combiner *combiner = irq_data_get_irq_chip_data(data); + struct combiner_reg *reg = combiner->regs + data->hwirq / REG_SIZE; + + set_bit(data->hwirq % REG_SIZE, ®->enabled); +} + +static struct irq_chip irq_chip = { + .irq_mask = combiner_irq_chip_mask_irq, + .irq_unmask = combiner_irq_chip_unmask_irq, + .name = "qcom-irq-combiner" +}; + +static int combiner_irq_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + irq_set_noprobe(irq); + return 0; +} + +static void combiner_irq_unmap(struct irq_domain *domain, unsigned int irq) +{ + irq_domain_reset_irq_data(irq_get_irq_data(irq)); +} + +static int combiner_irq_translate(struct irq_domain *d, struct irq_fwspec *fws, + unsigned long *hwirq, unsigned int *type) +{ + struct combiner *combiner = d->host_data; + + if (is_acpi_node(fws->fwnode)) { + if (WARN_ON((fws->param_count != 2) || + (fws->param[0] >= combiner->nirqs) || + (fws->param[1] & IORESOURCE_IRQ_LOWEDGE) || + (fws->param[1] & IORESOURCE_IRQ_HIGHEDGE))) + return -EINVAL; + + *hwirq = fws->param[0]; + *type = fws->param[1]; + return 0; + } + + return -EINVAL; +} + +static const struct irq_domain_ops domain_ops = { + .map = combiner_irq_map, + .unmap = combiner_irq_unmap, + .translate = combiner_irq_translate +}; + +static acpi_status count_registers_cb(struct acpi_resource *ares, void *context) +{ + int *count = context; + + if (ares->type == ACPI_RESOURCE_TYPE_GENERIC_REGISTER) + ++(*count); + return AE_OK; +} + +static int count_registers(struct platform_device *pdev) +{ + acpi_handle ahandle = ACPI_HANDLE(&pdev->dev); + acpi_status status; + int count = 0; + + if (!acpi_has_method(ahandle, METHOD_NAME__CRS)) + return -EINVAL; + + status = acpi_walk_resources(ahandle, METHOD_NAME__CRS, + count_registers_cb, &count); + if (ACPI_FAILURE(status)) + return -EINVAL; + return count; +} + +struct get_registers_context { + struct device *dev; + struct combiner *combiner; + int err; +}; + +static acpi_status get_registers_cb(struct acpi_resource *ares, void *context) +{ + struct get_registers_context *ctx = context; + struct acpi_resource_generic_register *reg; + phys_addr_t paddr; + void __iomem *vaddr; + + if (ares->type != ACPI_RESOURCE_TYPE_GENERIC_REGISTER) + return AE_OK; + + reg = &ares->data.generic_reg; + paddr = reg->address; + if ((reg->space_id != ACPI_SPACE_MEM) || + (reg->bit_offset != 0) || + (reg->bit_width > REG_SIZE)) { + dev_err(ctx->dev, "Bad register resource @%pa\n", &paddr); + ctx->err = -EINVAL; + return AE_ERROR; + } + + vaddr = devm_ioremap(ctx->dev, reg->address, REG_SIZE); + if (!vaddr) { + dev_err(ctx->dev, "Can't map register @%pa\n", &paddr); + ctx->err = -ENOMEM; + return AE_ERROR; + } + + ctx->combiner->regs[ctx->combiner->nregs].addr = vaddr; + ctx->combiner->nirqs += reg->bit_width; + ctx->combiner->nregs++; + return AE_OK; +} + +static int get_registers(struct platform_device *pdev, struct combiner *comb) +{ + acpi_handle ahandle = ACPI_HANDLE(&pdev->dev); + acpi_status status; + struct get_registers_context ctx; + + if (!acpi_has_method(ahandle, METHOD_NAME__CRS)) + return -EINVAL; + + ctx.dev = &pdev->dev; + ctx.combiner = comb; + ctx.err = 0; + + status = acpi_walk_resources(ahandle, METHOD_NAME__CRS, + get_registers_cb, &ctx); + if (ACPI_FAILURE(status)) + return ctx.err; + return 0; +} + +static int __init combiner_probe(struct platform_device *pdev) +{ + struct combiner *combiner; + size_t alloc_sz; + u32 nregs; + int err; + + nregs = count_registers(pdev); + if (nregs <= 0) { + dev_err(&pdev->dev, "Error reading register resources\n"); + return -EINVAL; + } + + alloc_sz = sizeof(*combiner) + sizeof(struct combiner_reg) * nregs; + combiner = devm_kzalloc(&pdev->dev, alloc_sz, GFP_KERNEL); + if (!combiner) + return -ENOMEM; + + err = get_registers(pdev, combiner); + if (err < 0) + return err; + + combiner->parent_irq = platform_get_irq(pdev, 0); + if (combiner->parent_irq <= 0) { + dev_err(&pdev->dev, "Error getting IRQ resource\n"); + return -EPROBE_DEFER; + } + + combiner->domain = irq_domain_create_linear(pdev->dev.fwnode, combiner->nirqs, + &domain_ops, combiner); + if (!combiner->domain) + /* Errors printed by irq_domain_create_linear */ + return -ENODEV; + + irq_set_chained_handler_and_data(combiner->parent_irq, + combiner_handle_irq, combiner); + + dev_info(&pdev->dev, "Initialized with [p=%d,n=%d,r=%p]\n", + combiner->parent_irq, combiner->nirqs, combiner->regs[0].addr); + return 0; +} + +static const struct acpi_device_id qcom_irq_combiner_ids[] = { + { "QCOM80B1", }, + { } +}; + +static struct platform_driver qcom_irq_combiner_probe = { + .driver = { + .name = "qcom-irq-combiner", + .acpi_match_table = ACPI_PTR(qcom_irq_combiner_ids), + }, + .probe = combiner_probe, +}; + +static int __init register_qcom_irq_combiner(void) +{ + return platform_driver_register(&qcom_irq_combiner_probe); +} +device_initcall(register_qcom_irq_combiner); diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c index 9cb4b621fbc3..b324474c0c12 100644 --- a/drivers/isdn/mISDN/stack.c +++ b/drivers/isdn/mISDN/stack.c @@ -203,7 +203,7 @@ mISDNStackd(void *data) { struct mISDNstack *st = data; #ifdef MISDN_MSG_STATS - cputime_t utime, stime; + u64 utime, stime; #endif int err = 0; @@ -308,7 +308,7 @@ mISDNStackd(void *data) st->stopped_cnt); task_cputime(st->thread, &utime, &stime); printk(KERN_DEBUG - "mISDNStackd daemon for %s utime(%ld) stime(%ld)\n", + "mISDNStackd daemon for %s utime(%llu) stime(%llu)\n", dev_name(&st->dev->dev), utime, stime); printk(KERN_DEBUG "mISDNStackd daemon for %s nvcsw(%ld) nivcsw(%ld)\n", diff --git a/drivers/macintosh/rack-meter.c b/drivers/macintosh/rack-meter.c index 775527135b93..e199fd6c71ce 100644 --- a/drivers/macintosh/rack-meter.c +++ b/drivers/macintosh/rack-meter.c @@ -52,8 +52,8 @@ struct rackmeter_dma { struct rackmeter_cpu { struct delayed_work sniffer; struct rackmeter *rm; - cputime64_t prev_wall; - cputime64_t prev_idle; + u64 prev_wall; + u64 prev_idle; int zero; } ____cacheline_aligned; @@ -81,7 +81,7 @@ static int rackmeter_ignore_nice; /* This is copied from cpufreq_ondemand, maybe we should put it in * a common header somewhere */ -static inline cputime64_t get_cpu_idle_time(unsigned int cpu) +static inline u64 get_cpu_idle_time(unsigned int cpu) { u64 retval; @@ -217,23 +217,23 @@ static void rackmeter_do_timer(struct work_struct *work) container_of(work, struct rackmeter_cpu, sniffer.work); struct rackmeter *rm = rcpu->rm; unsigned int cpu = smp_processor_id(); - cputime64_t cur_jiffies, total_idle_ticks; - unsigned int total_ticks, idle_ticks; + u64 cur_nsecs, total_idle_nsecs; + u64 total_nsecs, idle_nsecs; int i, offset, load, cumm, pause; - cur_jiffies = jiffies64_to_cputime64(get_jiffies_64()); - total_ticks = (unsigned int) (cur_jiffies - rcpu->prev_wall); - rcpu->prev_wall = cur_jiffies; + cur_nsecs = jiffies64_to_nsecs(get_jiffies_64()); + total_nsecs = cur_nsecs - rcpu->prev_wall; + rcpu->prev_wall = cur_nsecs; - total_idle_ticks = get_cpu_idle_time(cpu); - idle_ticks = (unsigned int) (total_idle_ticks - rcpu->prev_idle); - idle_ticks = min(idle_ticks, total_ticks); - rcpu->prev_idle = total_idle_ticks; + total_idle_nsecs = get_cpu_idle_time(cpu); + idle_nsecs = total_idle_nsecs - rcpu->prev_idle; + idle_nsecs = min(idle_nsecs, total_nsecs); + rcpu->prev_idle = total_idle_nsecs; /* We do a very dumb calculation to update the LEDs for now, * we'll do better once we have actual PWM implemented */ - load = (9 * (total_ticks - idle_ticks)) / total_ticks; + load = div64_u64(9 * (total_nsecs - idle_nsecs), total_nsecs); offset = cpu << 3; cumm = 0; @@ -278,7 +278,7 @@ static void rackmeter_init_cpu_sniffer(struct rackmeter *rm) continue; rcpu = &rm->cpu[cpu]; rcpu->prev_idle = get_cpu_idle_time(cpu); - rcpu->prev_wall = jiffies64_to_cputime64(get_jiffies_64()); + rcpu->prev_wall = jiffies64_to_nsecs(get_jiffies_64()); schedule_delayed_work_on(cpu, &rm->cpu[cpu].sniffer, msecs_to_jiffies(CPU_SAMPLING_RATE)); } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 84d2f0e4c754..d36d427a9efb 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -794,7 +794,7 @@ static void __wait_for_free_buffer(struct dm_bufio_client *c) DECLARE_WAITQUEUE(wait, current); add_wait_queue(&c->free_buffer_wait, &wait); - set_task_state(current, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); dm_bufio_unlock(c); io_schedule(); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 8a9f742d8ed7..1cb2ca9dfae3 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1210,14 +1210,14 @@ continue_locked: spin_unlock_irq(&cc->write_thread_wait.lock); if (unlikely(kthread_should_stop())) { - set_task_state(current, TASK_RUNNING); + set_current_state(TASK_RUNNING); remove_wait_queue(&cc->write_thread_wait, &wait); break; } schedule(); - set_task_state(current, TASK_RUNNING); + set_current_state(TASK_RUNNING); spin_lock_irq(&cc->write_thread_wait.lock); __remove_wait_queue(&cc->write_thread_wait, &wait); goto continue_locked; diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index a6dde7cab458..758d90cc2733 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -120,7 +120,7 @@ static int __check_holder(struct block_lock *lock) static void __wait(struct waiter *w) { for (;;) { - set_task_state(current, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); if (!w->task) break; @@ -128,7 +128,7 @@ static void __wait(struct waiter *w) schedule(); } - set_task_state(current, TASK_RUNNING); + set_current_state(TASK_RUNNING); } static void __wake_waiter(struct waiter *w) diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index 87a6b65ed3af..ccda41c2c9e4 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -612,8 +612,7 @@ int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg, } memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len); if (msg->len == 1) { - if (cec_msg_initiator(msg) != 0xf || - cec_msg_destination(msg) == 0xf) { + if (cec_msg_destination(msg) == 0xf) { dprintk(1, "cec_transmit_msg: invalid poll message\n"); return -EINVAL; } @@ -638,7 +637,7 @@ int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg, dprintk(1, "cec_transmit_msg: destination is the adapter itself\n"); return -EINVAL; } - if (cec_msg_initiator(msg) != 0xf && + if (msg->len > 1 && adap->is_configured && !cec_has_log_addr(adap, cec_msg_initiator(msg))) { dprintk(1, "cec_transmit_msg: initiator has unknown logical address %d\n", cec_msg_initiator(msg)); @@ -1072,7 +1071,7 @@ static int cec_config_log_addr(struct cec_adapter *adap, /* Send poll message */ msg.len = 1; - msg.msg[0] = 0xf0 | log_addr; + msg.msg[0] = (log_addr << 4) | log_addr; err = cec_transmit_msg_fh(adap, &msg, NULL, true); /* diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c index a4dcaec31d02..8c1f926567ec 100644 --- a/drivers/media/usb/siano/smsusb.c +++ b/drivers/media/usb/siano/smsusb.c @@ -218,22 +218,30 @@ static int smsusb_start_streaming(struct smsusb_device_t *dev) static int smsusb_sendrequest(void *context, void *buffer, size_t size) { struct smsusb_device_t *dev = (struct smsusb_device_t *) context; - struct sms_msg_hdr *phdr = (struct sms_msg_hdr *) buffer; - int dummy; + struct sms_msg_hdr *phdr; + int dummy, ret; if (dev->state != SMSUSB_ACTIVE) { pr_debug("Device not active yet\n"); return -ENOENT; } + phdr = kmalloc(size, GFP_KERNEL); + if (!phdr) + return -ENOMEM; + memcpy(phdr, buffer, size); + pr_debug("sending %s(%d) size: %d\n", smscore_translate_msg(phdr->msg_type), phdr->msg_type, phdr->msg_length); smsendian_handle_tx_message((struct sms_msg_data *) phdr); - smsendian_handle_message_header((struct sms_msg_hdr *)buffer); - return usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2), - buffer, size, &dummy, 1000); + smsendian_handle_message_header((struct sms_msg_hdr *)phdr); + ret = usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2), + phdr, size, &dummy, 1000); + + kfree(phdr); + return ret; } static char *smsusb1_fw_lkup[] = { diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c index 1ef7575547e6..be42957a78e1 100644 --- a/drivers/mfd/lpc_ich.c +++ b/drivers/mfd/lpc_ich.c @@ -56,6 +56,7 @@ * document number TBD : Wildcat Point-LP * document number TBD : 9 Series * document number TBD : Lewisburg + * document number TBD : Apollo Lake SoC */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -83,6 +84,17 @@ #define ACPIBASE_GCS_OFF 0x3410 #define ACPIBASE_GCS_END 0x3414 +#define SPIBASE_BYT 0x54 +#define SPIBASE_BYT_SZ 512 +#define SPIBASE_BYT_EN BIT(1) + +#define SPIBASE_LPT 0x3800 +#define SPIBASE_LPT_SZ 512 +#define BCR 0xdc +#define BCR_WPD BIT(0) + +#define SPIBASE_APL_SZ 4096 + #define GPIOBASE_ICH0 0x58 #define GPIOCTRL_ICH0 0x5C #define GPIOBASE_ICH6 0x48 @@ -133,6 +145,12 @@ static struct resource gpio_ich_res[] = { }, }; +static struct resource intel_spi_res[] = { + { + .flags = IORESOURCE_MEM, + } +}; + static struct mfd_cell lpc_ich_wdt_cell = { .name = "iTCO_wdt", .num_resources = ARRAY_SIZE(wdt_ich_res), @@ -147,6 +165,14 @@ static struct mfd_cell lpc_ich_gpio_cell = { .ignore_resource_conflicts = true, }; + +static struct mfd_cell lpc_ich_spi_cell = { + .name = "intel-spi", + .num_resources = ARRAY_SIZE(intel_spi_res), + .resources = intel_spi_res, + .ignore_resource_conflicts = true, +}; + /* chipset related info */ enum lpc_chipsets { LPC_ICH = 0, /* ICH */ @@ -216,6 +242,7 @@ enum lpc_chipsets { LPC_BRASWELL, /* Braswell SoC */ LPC_LEWISBURG, /* Lewisburg */ LPC_9S, /* 9 Series */ + LPC_APL, /* Apollo Lake SoC */ }; static struct lpc_ich_info lpc_chipset_info[] = { @@ -494,10 +521,12 @@ static struct lpc_ich_info lpc_chipset_info[] = { .name = "Lynx Point", .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, + .spi_type = INTEL_SPI_LPT, }, [LPC_LPT_LP] = { .name = "Lynx Point_LP", .iTCO_version = 2, + .spi_type = INTEL_SPI_LPT, }, [LPC_WBG] = { .name = "Wellsburg", @@ -511,6 +540,7 @@ static struct lpc_ich_info lpc_chipset_info[] = { [LPC_BAYTRAIL] = { .name = "Bay Trail SoC", .iTCO_version = 3, + .spi_type = INTEL_SPI_BYT, }, [LPC_COLETO] = { .name = "Coleto Creek", @@ -519,10 +549,12 @@ static struct lpc_ich_info lpc_chipset_info[] = { [LPC_WPT_LP] = { .name = "Wildcat Point_LP", .iTCO_version = 2, + .spi_type = INTEL_SPI_LPT, }, [LPC_BRASWELL] = { .name = "Braswell SoC", .iTCO_version = 3, + .spi_type = INTEL_SPI_BYT, }, [LPC_LEWISBURG] = { .name = "Lewisburg", @@ -533,6 +565,10 @@ static struct lpc_ich_info lpc_chipset_info[] = { .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, + [LPC_APL] = { + .name = "Apollo Lake SoC", + .spi_type = INTEL_SPI_BXT, + }, }; /* @@ -681,6 +717,7 @@ static const struct pci_device_id lpc_ich_ids[] = { { PCI_VDEVICE(INTEL, 0x3b14), LPC_3420}, { PCI_VDEVICE(INTEL, 0x3b16), LPC_3450}, { PCI_VDEVICE(INTEL, 0x5031), LPC_EP80579}, + { PCI_VDEVICE(INTEL, 0x5ae8), LPC_APL}, { PCI_VDEVICE(INTEL, 0x8c40), LPC_LPT}, { PCI_VDEVICE(INTEL, 0x8c41), LPC_LPT}, { PCI_VDEVICE(INTEL, 0x8c42), LPC_LPT}, @@ -1056,6 +1093,94 @@ wdt_done: return ret; } +static int lpc_ich_init_spi(struct pci_dev *dev) +{ + struct lpc_ich_priv *priv = pci_get_drvdata(dev); + struct resource *res = &intel_spi_res[0]; + struct intel_spi_boardinfo *info; + u32 spi_base, rcba, bcr; + + info = devm_kzalloc(&dev->dev, sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + info->type = lpc_chipset_info[priv->chipset].spi_type; + + switch (info->type) { + case INTEL_SPI_BYT: + pci_read_config_dword(dev, SPIBASE_BYT, &spi_base); + if (spi_base & SPIBASE_BYT_EN) { + res->start = spi_base & ~(SPIBASE_BYT_SZ - 1); + res->end = res->start + SPIBASE_BYT_SZ - 1; + } + break; + + case INTEL_SPI_LPT: + pci_read_config_dword(dev, RCBABASE, &rcba); + if (rcba & 1) { + spi_base = round_down(rcba, SPIBASE_LPT_SZ); + res->start = spi_base + SPIBASE_LPT; + res->end = res->start + SPIBASE_LPT_SZ - 1; + + /* + * Try to make the flash chip writeable now by + * setting BCR_WPD. It it fails we tell the driver + * that it can only read the chip. + */ + pci_read_config_dword(dev, BCR, &bcr); + if (!(bcr & BCR_WPD)) { + bcr |= BCR_WPD; + pci_write_config_dword(dev, BCR, bcr); + pci_read_config_dword(dev, BCR, &bcr); + } + info->writeable = !!(bcr & BCR_WPD); + } + break; + + case INTEL_SPI_BXT: { + unsigned int p2sb = PCI_DEVFN(13, 0); + unsigned int spi = PCI_DEVFN(13, 2); + struct pci_bus *bus = dev->bus; + + /* + * The P2SB is hidden by BIOS and we need to unhide it in + * order to read BAR of the SPI flash device. Once that is + * done we hide it again. + */ + pci_bus_write_config_byte(bus, p2sb, 0xe1, 0x0); + pci_bus_read_config_dword(bus, spi, PCI_BASE_ADDRESS_0, + &spi_base); + if (spi_base != ~0) { + res->start = spi_base & 0xfffffff0; + res->end = res->start + SPIBASE_APL_SZ - 1; + + pci_bus_read_config_dword(bus, spi, BCR, &bcr); + if (!(bcr & BCR_WPD)) { + bcr |= BCR_WPD; + pci_bus_write_config_dword(bus, spi, BCR, bcr); + pci_bus_read_config_dword(bus, spi, BCR, &bcr); + } + info->writeable = !!(bcr & BCR_WPD); + } + + pci_bus_write_config_byte(bus, p2sb, 0xe1, 0x1); + break; + } + + default: + return -EINVAL; + } + + if (!res->start) + return -ENODEV; + + lpc_ich_spi_cell.platform_data = info; + lpc_ich_spi_cell.pdata_size = sizeof(*info); + + return mfd_add_devices(&dev->dev, PLATFORM_DEVID_NONE, + &lpc_ich_spi_cell, 1, NULL, 0, NULL); +} + static int lpc_ich_probe(struct pci_dev *dev, const struct pci_device_id *id) { @@ -1099,6 +1224,12 @@ static int lpc_ich_probe(struct pci_dev *dev, cell_added = true; } + if (lpc_chipset_info[priv->chipset].spi_type) { + ret = lpc_ich_init_spi(dev); + if (!ret) + cell_added = true; + } + /* * We only care if at least one or none of the cells registered * successfully. diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c index 7f1b282d7d96..cb290b8ca0c8 100644 --- a/drivers/misc/genwqe/card_dev.c +++ b/drivers/misc/genwqe/card_dev.c @@ -1396,7 +1396,7 @@ int genwqe_device_remove(struct genwqe_dev *cd) * application which will decrease this reference from * 1/unused to 0/illegal and not from 2/used 1/empty. */ - rc = atomic_read(&cd->cdev_genwqe.kobj.kref.refcount); + rc = kref_read(&cd->cdev_genwqe.kobj.kref); if (rc != 1) { dev_err(&pci_dev->dev, "[%s] err: cdev_genwqe...refcount=%d\n", __func__, rc); diff --git a/drivers/misc/lkdtm.h b/drivers/misc/lkdtm.h index cfa1039c62e7..67d27be60405 100644 --- a/drivers/misc/lkdtm.h +++ b/drivers/misc/lkdtm.h @@ -19,8 +19,12 @@ void lkdtm_SOFTLOCKUP(void); void lkdtm_HARDLOCKUP(void); void lkdtm_SPINLOCKUP(void); void lkdtm_HUNG_TASK(void); -void lkdtm_ATOMIC_UNDERFLOW(void); -void lkdtm_ATOMIC_OVERFLOW(void); +void lkdtm_REFCOUNT_SATURATE_INC(void); +void lkdtm_REFCOUNT_SATURATE_ADD(void); +void lkdtm_REFCOUNT_ZERO_DEC(void); +void lkdtm_REFCOUNT_ZERO_INC(void); +void lkdtm_REFCOUNT_ZERO_SUB(void); +void lkdtm_REFCOUNT_ZERO_ADD(void); void lkdtm_CORRUPT_LIST_ADD(void); void lkdtm_CORRUPT_LIST_DEL(void); diff --git a/drivers/misc/lkdtm_bugs.c b/drivers/misc/lkdtm_bugs.c index 91edd0b55e5c..cba0837aee2e 100644 --- a/drivers/misc/lkdtm_bugs.c +++ b/drivers/misc/lkdtm_bugs.c @@ -6,6 +6,7 @@ */ #include "lkdtm.h" #include <linux/list.h> +#include <linux/refcount.h> #include <linux/sched.h> struct lkdtm_list { @@ -129,28 +130,86 @@ void lkdtm_HUNG_TASK(void) schedule(); } -void lkdtm_ATOMIC_UNDERFLOW(void) +void lkdtm_REFCOUNT_SATURATE_INC(void) { - atomic_t under = ATOMIC_INIT(INT_MIN); + refcount_t over = REFCOUNT_INIT(UINT_MAX - 1); - pr_info("attempting good atomic increment\n"); - atomic_inc(&under); - atomic_dec(&under); + pr_info("attempting good refcount decrement\n"); + refcount_dec(&over); + refcount_inc(&over); - pr_info("attempting bad atomic underflow\n"); - atomic_dec(&under); + pr_info("attempting bad refcount inc overflow\n"); + refcount_inc(&over); + refcount_inc(&over); + if (refcount_read(&over) == UINT_MAX) + pr_err("Correctly stayed saturated, but no BUG?!\n"); + else + pr_err("Fail: refcount wrapped\n"); +} + +void lkdtm_REFCOUNT_SATURATE_ADD(void) +{ + refcount_t over = REFCOUNT_INIT(UINT_MAX - 1); + + pr_info("attempting good refcount decrement\n"); + refcount_dec(&over); + refcount_inc(&over); + + pr_info("attempting bad refcount add overflow\n"); + refcount_add(2, &over); + if (refcount_read(&over) == UINT_MAX) + pr_err("Correctly stayed saturated, but no BUG?!\n"); + else + pr_err("Fail: refcount wrapped\n"); +} + +void lkdtm_REFCOUNT_ZERO_DEC(void) +{ + refcount_t zero = REFCOUNT_INIT(1); + + pr_info("attempting bad refcount decrement to zero\n"); + refcount_dec(&zero); + if (refcount_read(&zero) == 0) + pr_err("Stayed at zero, but no BUG?!\n"); + else + pr_err("Fail: refcount went crazy\n"); } -void lkdtm_ATOMIC_OVERFLOW(void) +void lkdtm_REFCOUNT_ZERO_SUB(void) { - atomic_t over = ATOMIC_INIT(INT_MAX); + refcount_t zero = REFCOUNT_INIT(1); + + pr_info("attempting bad refcount subtract past zero\n"); + if (!refcount_sub_and_test(2, &zero)) + pr_info("wrap attempt was noticed\n"); + if (refcount_read(&zero) == 1) + pr_err("Correctly stayed above 0, but no BUG?!\n"); + else + pr_err("Fail: refcount wrapped\n"); +} - pr_info("attempting good atomic decrement\n"); - atomic_dec(&over); - atomic_inc(&over); +void lkdtm_REFCOUNT_ZERO_INC(void) +{ + refcount_t zero = REFCOUNT_INIT(0); - pr_info("attempting bad atomic overflow\n"); - atomic_inc(&over); + pr_info("attempting bad refcount increment from zero\n"); + refcount_inc(&zero); + if (refcount_read(&zero) == 0) + pr_err("Stayed at zero, but no BUG?!\n"); + else + pr_err("Fail: refcount went past zero\n"); +} + +void lkdtm_REFCOUNT_ZERO_ADD(void) +{ + refcount_t zero = REFCOUNT_INIT(0); + + pr_info("attempting bad refcount addition from zero\n"); + refcount_add(2, &zero); + if (refcount_read(&zero) == 0) + pr_err("Stayed at zero, but no BUG?!\n"); + else + pr_err("Fail: refcount went past zero\n"); } void lkdtm_CORRUPT_LIST_ADD(void) diff --git a/drivers/misc/lkdtm_core.c b/drivers/misc/lkdtm_core.c index 7eeb71a75549..16e4cf110930 100644 --- a/drivers/misc/lkdtm_core.c +++ b/drivers/misc/lkdtm_core.c @@ -220,8 +220,12 @@ struct crashtype crashtypes[] = { CRASHTYPE(WRITE_RO), CRASHTYPE(WRITE_RO_AFTER_INIT), CRASHTYPE(WRITE_KERN), - CRASHTYPE(ATOMIC_UNDERFLOW), - CRASHTYPE(ATOMIC_OVERFLOW), + CRASHTYPE(REFCOUNT_SATURATE_INC), + CRASHTYPE(REFCOUNT_SATURATE_ADD), + CRASHTYPE(REFCOUNT_ZERO_DEC), + CRASHTYPE(REFCOUNT_ZERO_INC), + CRASHTYPE(REFCOUNT_ZERO_SUB), + CRASHTYPE(REFCOUNT_ZERO_ADD), CRASHTYPE(USERCOPY_HEAP_SIZE_TO), CRASHTYPE(USERCOPY_HEAP_SIZE_FROM), CRASHTYPE(USERCOPY_HEAP_FLAG_TO), diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c index c6217a4993ad..a617aa5a3ad8 100644 --- a/drivers/misc/mei/debugfs.c +++ b/drivers/misc/mei/debugfs.c @@ -67,7 +67,7 @@ static ssize_t mei_dbgfs_read_meclients(struct file *fp, char __user *ubuf, me_cl->props.max_number_of_connections, me_cl->props.max_msg_length, me_cl->props.single_recv_buf, - atomic_read(&me_cl->refcnt.refcount)); + kref_read(&me_cl->refcnt)); mei_me_cl_put(me_cl); } diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index b61b52f9da3d..0fccca075e29 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1706,10 +1706,10 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, err = mmc_select_hs400(card); if (err) goto free_card; - } else if (mmc_card_hs(card)) { + } else { /* Select the desired bus width optionally */ err = mmc_select_bus_width(card); - if (err > 0) { + if (err > 0 && mmc_card_hs(card)) { err = mmc_select_hs_ddr(card); if (err) goto free_card; diff --git a/drivers/mtd/bcm47xxpart.c b/drivers/mtd/bcm47xxpart.c index 283ff7e17a0f..d10fa6c8f074 100644 --- a/drivers/mtd/bcm47xxpart.c +++ b/drivers/mtd/bcm47xxpart.c @@ -9,6 +9,7 @@ * */ +#include <linux/bcm47xx_nvram.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> @@ -83,6 +84,91 @@ out_default: return "rootfs"; } +static int bcm47xxpart_parse_trx(struct mtd_info *master, + struct mtd_partition *trx, + struct mtd_partition *parts, + size_t parts_len) +{ + struct trx_header header; + size_t bytes_read; + int curr_part = 0; + int i, err; + + if (parts_len < 3) { + pr_warn("No enough space to add TRX partitions!\n"); + return -ENOMEM; + } + + err = mtd_read(master, trx->offset, sizeof(header), &bytes_read, + (uint8_t *)&header); + if (err && !mtd_is_bitflip(err)) { + pr_err("mtd_read error while reading TRX header: %d\n", err); + return err; + } + + i = 0; + + /* We have LZMA loader if offset[2] points to sth */ + if (header.offset[2]) { + bcm47xxpart_add_part(&parts[curr_part++], "loader", + trx->offset + header.offset[i], 0); + i++; + } + + if (header.offset[i]) { + bcm47xxpart_add_part(&parts[curr_part++], "linux", + trx->offset + header.offset[i], 0); + i++; + } + + if (header.offset[i]) { + size_t offset = trx->offset + header.offset[i]; + const char *name = bcm47xxpart_trx_data_part_name(master, + offset); + + bcm47xxpart_add_part(&parts[curr_part++], name, offset, 0); + i++; + } + + /* + * Assume that every partition ends at the beginning of the one it is + * followed by. + */ + for (i = 0; i < curr_part; i++) { + u64 next_part_offset = (i < curr_part - 1) ? + parts[i + 1].offset : + trx->offset + trx->size; + + parts[i].size = next_part_offset - parts[i].offset; + } + + return curr_part; +} + +/** + * bcm47xxpart_bootpartition - gets index of TRX partition used by bootloader + * + * Some devices may have more than one TRX partition. In such case one of them + * is the main one and another a failsafe one. Bootloader may fallback to the + * failsafe firmware if it detects corruption of the main image. + * + * This function provides info about currently used TRX partition. It's the one + * containing kernel started by the bootloader. + */ +static int bcm47xxpart_bootpartition(void) +{ + char buf[4]; + int bootpartition; + + /* Check CFE environment variable */ + if (bcm47xx_nvram_getenv("bootpartition", buf, sizeof(buf)) > 0) { + if (!kstrtoint(buf, 0, &bootpartition)) + return bootpartition; + } + + return 0; +} + static int bcm47xxpart_parse(struct mtd_info *master, const struct mtd_partition **pparts, struct mtd_part_parser_data *data) @@ -93,9 +179,8 @@ static int bcm47xxpart_parse(struct mtd_info *master, size_t bytes_read; uint32_t offset; uint32_t blocksize = master->erasesize; - struct trx_header *trx; - int trx_part = -1; - int last_trx_part = -1; + int trx_parts[2]; /* Array with indexes of TRX partitions */ + int trx_num = 0; /* Number of found TRX partitions */ int possible_nvram_sizes[] = { 0x8000, 0xF000, 0x10000, }; int err; @@ -182,54 +267,18 @@ static int bcm47xxpart_parse(struct mtd_info *master, /* TRX */ if (buf[0x000 / 4] == TRX_MAGIC) { - if (BCM47XXPART_MAX_PARTS - curr_part < 4) { - pr_warn("Not enough partitions left to register trx, scanning stopped!\n"); - break; - } - - trx = (struct trx_header *)buf; + struct trx_header *trx; - trx_part = curr_part; + if (trx_num >= ARRAY_SIZE(trx_parts)) + pr_warn("No enough space to store another TRX found at 0x%X\n", + offset); + else + trx_parts[trx_num++] = curr_part; bcm47xxpart_add_part(&parts[curr_part++], "firmware", offset, 0); - i = 0; - /* We have LZMA loader if offset[2] points to sth */ - if (trx->offset[2]) { - bcm47xxpart_add_part(&parts[curr_part++], - "loader", - offset + trx->offset[i], - 0); - i++; - } - - if (trx->offset[i]) { - bcm47xxpart_add_part(&parts[curr_part++], - "linux", - offset + trx->offset[i], - 0); - i++; - } - - /* - * Pure rootfs size is known and can be calculated as: - * trx->length - trx->offset[i]. We don't fill it as - * we want to have jffs2 (overlay) in the same mtd. - */ - if (trx->offset[i]) { - const char *name; - - name = bcm47xxpart_trx_data_part_name(master, offset + trx->offset[i]); - bcm47xxpart_add_part(&parts[curr_part++], - name, - offset + trx->offset[i], - 0); - i++; - } - - last_trx_part = curr_part - 1; - /* Jump to the end of TRX */ + trx = (struct trx_header *)buf; offset = roundup(offset + trx->length, blocksize); /* Next loop iteration will increase the offset */ offset -= blocksize; @@ -307,9 +356,23 @@ static int bcm47xxpart_parse(struct mtd_info *master, parts[i + 1].offset : master->size; parts[i].size = next_part_offset - parts[i].offset; - if (i == last_trx_part && trx_part >= 0) - parts[trx_part].size = next_part_offset - - parts[trx_part].offset; + } + + /* If there was TRX parse it now */ + for (i = 0; i < trx_num; i++) { + struct mtd_partition *trx = &parts[trx_parts[i]]; + + if (i == bcm47xxpart_bootpartition()) { + int num_parts; + + num_parts = bcm47xxpart_parse_trx(master, trx, + parts + curr_part, + BCM47XXPART_MAX_PARTS - curr_part); + if (num_parts > 0) + curr_part += num_parts; + } else { + trx->name = "failsafe"; + } } *pparts = parts; diff --git a/drivers/mtd/devices/bcm47xxsflash.c b/drivers/mtd/devices/bcm47xxsflash.c index 514be04c0b6c..e2bd81817df4 100644 --- a/drivers/mtd/devices/bcm47xxsflash.c +++ b/drivers/mtd/devices/bcm47xxsflash.c @@ -105,15 +105,33 @@ static int bcm47xxsflash_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct bcm47xxsflash *b47s = mtd->priv; + size_t orig_len = len; /* Check address range */ if ((from + len) > mtd->size) return -EINVAL; - memcpy_fromio(buf, b47s->window + from, len); - *retlen = len; + /* Read as much as possible using fast MMIO window */ + if (from < BCM47XXSFLASH_WINDOW_SZ) { + size_t memcpy_len; - return len; + memcpy_len = min(len, (size_t)(BCM47XXSFLASH_WINDOW_SZ - from)); + memcpy_fromio(buf, b47s->window + from, memcpy_len); + from += memcpy_len; + len -= memcpy_len; + buf += memcpy_len; + } + + /* Use indirect access for content out of the window */ + for (; len; len--) { + b47s->cc_write(b47s, BCMA_CC_FLASHADDR, from++); + bcm47xxsflash_cmd(b47s, OPCODE_ST_READ4B); + *buf++ = b47s->cc_read(b47s, BCMA_CC_FLASHDATA); + } + + *retlen = orig_len; + + return orig_len; } static int bcm47xxsflash_write_st(struct mtd_info *mtd, u32 offset, size_t len, @@ -284,7 +302,6 @@ static int bcm47xxsflash_bcma_probe(struct platform_device *pdev) b47s = devm_kzalloc(dev, sizeof(*b47s), GFP_KERNEL); if (!b47s) return -ENOMEM; - sflash->priv = b47s; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { @@ -334,6 +351,8 @@ static int bcm47xxsflash_bcma_probe(struct platform_device *pdev) b47s->size = sflash->size; bcm47xxsflash_fill_mtd(b47s, &pdev->dev); + platform_set_drvdata(pdev, b47s); + err = mtd_device_parse_register(&b47s->mtd, probes, NULL, NULL, 0); if (err) { pr_err("Failed to register MTD device: %d\n", err); @@ -349,8 +368,7 @@ static int bcm47xxsflash_bcma_probe(struct platform_device *pdev) static int bcm47xxsflash_bcma_remove(struct platform_device *pdev) { - struct bcma_sflash *sflash = dev_get_platdata(&pdev->dev); - struct bcm47xxsflash *b47s = sflash->priv; + struct bcm47xxsflash *b47s = platform_get_drvdata(pdev); mtd_device_unregister(&b47s->mtd); iounmap(b47s->window); diff --git a/drivers/mtd/devices/bcm47xxsflash.h b/drivers/mtd/devices/bcm47xxsflash.h index 1564b62b412e..b2d7b38f75fd 100644 --- a/drivers/mtd/devices/bcm47xxsflash.h +++ b/drivers/mtd/devices/bcm47xxsflash.h @@ -3,6 +3,8 @@ #include <linux/mtd/mtd.h> +#define BCM47XXSFLASH_WINDOW_SZ SZ_16M + /* Used for ST flashes only. */ #define OPCODE_ST_WREN 0x0006 /* Write Enable */ #define OPCODE_ST_WRDIS 0x0004 /* Write Disable */ @@ -16,6 +18,7 @@ #define OPCODE_ST_RES 0x03ab /* Read Electronic Signature */ #define OPCODE_ST_CSA 0x1000 /* Keep chip select asserted */ #define OPCODE_ST_SSE 0x0220 /* Sub-sector Erase */ +#define OPCODE_ST_READ4B 0x6313 /* Read Data Bytes in 4Byte addressing mode */ /* Used for Atmel flashes only. */ #define OPCODE_AT_READ 0x07e8 diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index 9cf7fcd28034..c4df3b1bded0 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -172,7 +172,8 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len, t[1].rx_buf = buf; t[1].rx_nbits = m25p80_rx_nbits(nor); - t[1].len = min(len, spi_max_transfer_size(spi)); + t[1].len = min3(len, spi_max_transfer_size(spi), + spi_max_message_size(spi) - t[0].len); spi_message_add_tail(&t[1], &m); ret = spi_sync(spi, &m); @@ -288,7 +289,6 @@ static const struct spi_device_id m25p_ids[] = { * should be kept for backward compatibility. */ {"at25df321a"}, {"at25df641"}, {"at26df081a"}, - {"mr25h256"}, {"mx25l4005a"}, {"mx25l1606e"}, {"mx25l6405d"}, {"mx25l12805d"}, {"mx25l25635e"},{"mx66l51235l"}, {"n25q064"}, {"n25q128a11"}, {"n25q128a13"}, {"n25q512a"}, @@ -305,6 +305,11 @@ static const struct spi_device_id m25p_ids[] = { {"m25p40-nonjedec"}, {"m25p80-nonjedec"}, {"m25p16-nonjedec"}, {"m25p32-nonjedec"}, {"m25p64-nonjedec"}, {"m25p128-nonjedec"}, + /* Everspin MRAMs (non-JEDEC) */ + { "mr25h256" }, /* 256 Kib, 40 MHz */ + { "mr25h10" }, /* 1 Mib, 40 MHz */ + { "mr25h40" }, /* 4 Mib, 40 MHz */ + { }, }; MODULE_DEVICE_TABLE(spi, m25p_ids); diff --git a/drivers/mtd/devices/serial_flash_cmds.h b/drivers/mtd/devices/serial_flash_cmds.h index f59a125295d0..8b81e15105dd 100644 --- a/drivers/mtd/devices/serial_flash_cmds.h +++ b/drivers/mtd/devices/serial_flash_cmds.h @@ -18,19 +18,12 @@ #define SPINOR_OP_RDVCR 0x85 /* JEDEC Standard - Serial Flash Discoverable Parmeters (SFDP) Commands */ -#define SPINOR_OP_READ_1_2_2 0xbb /* DUAL I/O READ */ -#define SPINOR_OP_READ_1_4_4 0xeb /* QUAD I/O READ */ - #define SPINOR_OP_WRITE 0x02 /* PAGE PROGRAM */ #define SPINOR_OP_WRITE_1_1_2 0xa2 /* DUAL INPUT PROGRAM */ #define SPINOR_OP_WRITE_1_2_2 0xd2 /* DUAL INPUT EXT PROGRAM */ #define SPINOR_OP_WRITE_1_1_4 0x32 /* QUAD INPUT PROGRAM */ #define SPINOR_OP_WRITE_1_4_4 0x12 /* QUAD INPUT EXT PROGRAM */ -/* READ commands with 32-bit addressing */ -#define SPINOR_OP_READ4_1_2_2 0xbc -#define SPINOR_OP_READ4_1_4_4 0xec - /* Configuration flags */ #define FLASH_FLAG_SINGLE 0x000000ff #define FLASH_FLAG_READ_WRITE 0x00000001 diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c index 5454b4113589..804313a33f2b 100644 --- a/drivers/mtd/devices/st_spi_fsm.c +++ b/drivers/mtd/devices/st_spi_fsm.c @@ -507,13 +507,13 @@ static struct seq_rw_config n25q_read3_configs[] = { * - 'FAST' variants configured for 8 dummy cycles (see note above.) */ static struct seq_rw_config n25q_read4_configs[] = { - {FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ4_1_4_4, 0, 4, 4, 0x00, 0, 8}, - {FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ4_1_1_4, 0, 1, 4, 0x00, 0, 8}, - {FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ4_1_2_2, 0, 2, 2, 0x00, 0, 8}, - {FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ4_1_1_2, 0, 1, 2, 0x00, 0, 8}, - {FLASH_FLAG_READ_FAST, SPINOR_OP_READ4_FAST, 0, 1, 1, 0x00, 0, 8}, - {FLASH_FLAG_READ_WRITE, SPINOR_OP_READ4, 0, 1, 1, 0x00, 0, 0}, - {0x00, 0, 0, 0, 0, 0x00, 0, 0}, + {FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B, 0, 4, 4, 0x00, 0, 8}, + {FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B, 0, 1, 4, 0x00, 0, 8}, + {FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B, 0, 2, 2, 0x00, 0, 8}, + {FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ_1_1_2_4B, 0, 1, 2, 0x00, 0, 8}, + {FLASH_FLAG_READ_FAST, SPINOR_OP_READ_FAST_4B, 0, 1, 1, 0x00, 0, 8}, + {FLASH_FLAG_READ_WRITE, SPINOR_OP_READ_4B, 0, 1, 1, 0x00, 0, 0}, + {0x00, 0, 0, 0, 0, 0x00, 0, 0}, }; /* @@ -553,13 +553,13 @@ static int stfsm_mx25_en_32bit_addr_seq(struct stfsm_seq *seq) * entering a state that is incompatible with the SPIBoot Controller. */ static struct seq_rw_config stfsm_s25fl_read4_configs[] = { - {FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ4_1_4_4, 0, 4, 4, 0x00, 2, 4}, - {FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ4_1_1_4, 0, 1, 4, 0x00, 0, 8}, - {FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ4_1_2_2, 0, 2, 2, 0x00, 4, 0}, - {FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ4_1_1_2, 0, 1, 2, 0x00, 0, 8}, - {FLASH_FLAG_READ_FAST, SPINOR_OP_READ4_FAST, 0, 1, 1, 0x00, 0, 8}, - {FLASH_FLAG_READ_WRITE, SPINOR_OP_READ4, 0, 1, 1, 0x00, 0, 0}, - {0x00, 0, 0, 0, 0, 0x00, 0, 0}, + {FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B, 0, 4, 4, 0x00, 2, 4}, + {FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B, 0, 1, 4, 0x00, 0, 8}, + {FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B, 0, 2, 2, 0x00, 4, 0}, + {FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ_1_1_2_4B, 0, 1, 2, 0x00, 0, 8}, + {FLASH_FLAG_READ_FAST, SPINOR_OP_READ_FAST_4B, 0, 1, 1, 0x00, 0, 8}, + {FLASH_FLAG_READ_WRITE, SPINOR_OP_READ_4B, 0, 1, 1, 0x00, 0, 0}, + {0x00, 0, 0, 0, 0, 0x00, 0, 0}, }; static struct seq_rw_config stfsm_s25fl_write4_configs[] = { diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index 5bcc896a48c3..542fdf8e81fa 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -75,7 +75,7 @@ config MTD_PHYSMAP_OF taken from OF device tree. config MTD_PHYSMAP_OF_VERSATILE - bool "Support ARM Versatile physmap OF" + bool "ARM Versatile OF-based physical memory map handling" depends on MTD_PHYSMAP_OF depends on MFD_SYSCON default y if (ARCH_INTEGRATOR || ARCH_VERSATILE || ARCH_REALVIEW) @@ -84,6 +84,16 @@ config MTD_PHYSMAP_OF_VERSATILE platforms, basically to add a VPP (write protection) callback so the flash can be taken out of write protection. +config MTD_PHYSMAP_OF_GEMINI + bool "Cortina Gemini OF-based physical memory map handling" + depends on MTD_PHYSMAP_OF + depends on MFD_SYSCON + default ARCH_GEMINI + help + This provides some extra DT physmap parsing for the Gemini + platforms, some detection and setting up parallel mode on the + external interface. + config MTD_PMC_MSP_EVM tristate "CFI Flash device mapped on PMC-Sierra MSP" depends on PMC_MSP && MTD_CFI diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile index 644f7d36d35d..aef1846b4de2 100644 --- a/drivers/mtd/maps/Makefile +++ b/drivers/mtd/maps/Makefile @@ -17,10 +17,13 @@ obj-$(CONFIG_MTD_CK804XROM) += ck804xrom.o obj-$(CONFIG_MTD_TSUNAMI) += tsunami_flash.o obj-$(CONFIG_MTD_PXA2XX) += pxa2xx-flash.o obj-$(CONFIG_MTD_PHYSMAP) += physmap.o -obj-$(CONFIG_MTD_PHYSMAP_OF) += physmap_of.o ifdef CONFIG_MTD_PHYSMAP_OF_VERSATILE -obj-$(CONFIG_MTD_PHYSMAP_OF) += physmap_of_versatile.o +physmap_of-objs += physmap_of_versatile.o +endif +ifdef CONFIG_MTD_PHYSMAP_OF_GEMINI +physmap_of-objs += physmap_of_gemini.o endif +obj-$(CONFIG_MTD_PHYSMAP_OF) += physmap_of.o obj-$(CONFIG_MTD_PISMO) += pismo.o obj-$(CONFIG_MTD_PMC_MSP_EVM) += pmcmsp-flash.o obj-$(CONFIG_MTD_PCMCIA) += pcmciamtd.o diff --git a/drivers/mtd/maps/ichxrom.c b/drivers/mtd/maps/ichxrom.c index e17d02ae03f0..976d42f63aef 100644 --- a/drivers/mtd/maps/ichxrom.c +++ b/drivers/mtd/maps/ichxrom.c @@ -57,10 +57,12 @@ static void ichxrom_cleanup(struct ichxrom_window *window) { struct ichxrom_map_info *map, *scratch; u16 word; + int ret; /* Disable writes through the rom window */ - pci_read_config_word(window->pdev, BIOS_CNTL, &word); - pci_write_config_word(window->pdev, BIOS_CNTL, word & ~1); + ret = pci_read_config_word(window->pdev, BIOS_CNTL, &word); + if (!ret) + pci_write_config_word(window->pdev, BIOS_CNTL, word & ~1); pci_dev_put(window->pdev); /* Free all of the mtd devices */ diff --git a/drivers/mtd/maps/lantiq-flash.c b/drivers/mtd/maps/lantiq-flash.c index c8febb326fa6..3e33ab66eb24 100644 --- a/drivers/mtd/maps/lantiq-flash.c +++ b/drivers/mtd/maps/lantiq-flash.c @@ -4,7 +4,7 @@ * by the Free Software Foundation. * * Copyright (C) 2004 Liu Peng Infineon IFAP DC COM CPE - * Copyright (C) 2010 John Crispin <blogic@openwrt.org> + * Copyright (C) 2010 John Crispin <john@phrozen.org> */ #include <linux/err.h> @@ -209,5 +209,5 @@ static struct platform_driver ltq_mtd_driver = { module_platform_driver(ltq_mtd_driver); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("John Crispin <blogic@openwrt.org>"); +MODULE_AUTHOR("John Crispin <john@phrozen.org>"); MODULE_DESCRIPTION("Lantiq SoC NOR"); diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c index 3fad35942895..14e8909c9955 100644 --- a/drivers/mtd/maps/physmap_of.c +++ b/drivers/mtd/maps/physmap_of.c @@ -24,6 +24,7 @@ #include <linux/of_address.h> #include <linux/of_platform.h> #include <linux/slab.h> +#include "physmap_of_gemini.h" #include "physmap_of_versatile.h" struct of_flash_list { @@ -241,11 +242,13 @@ static int of_flash_probe(struct platform_device *dev) info->list[i].map.size = res_size; info->list[i].map.bankwidth = be32_to_cpup(width); info->list[i].map.device_node = dp; + + err = of_flash_probe_gemini(dev, dp, &info->list[i].map); + if (err) + return err; err = of_flash_probe_versatile(dev, dp, &info->list[i].map); - if (err) { - dev_err(&dev->dev, "Can't probe Versatile VPP\n"); + if (err) return err; - } err = -ENOMEM; info->list[i].map.virt = ioremap(info->list[i].map.phys, diff --git a/drivers/mtd/maps/physmap_of_gemini.c b/drivers/mtd/maps/physmap_of_gemini.c new file mode 100644 index 000000000000..9d371cd728ea --- /dev/null +++ b/drivers/mtd/maps/physmap_of_gemini.c @@ -0,0 +1,117 @@ +/* + * Cortina Systems Gemini OF physmap add-on + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * + * This SoC has an elaborate flash control register, so we need to + * detect and set it up when booting on this platform. + */ +#include <linux/export.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/mtd/map.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> +#include <linux/bitops.h> +#include "physmap_of_gemini.h" + +/* + * The Flash-relevant parts of the global status register + * These would also be relevant for a NAND driver. + */ +#define GLOBAL_STATUS 0x04 +#define FLASH_TYPE_MASK (0x3 << 24) +#define FLASH_TYPE_NAND_2K (0x3 << 24) +#define FLASH_TYPE_NAND_512 (0x2 << 24) +#define FLASH_TYPE_PARALLEL (0x1 << 24) +#define FLASH_TYPE_SERIAL (0x0 << 24) +/* if parallel */ +#define FLASH_WIDTH_16BIT (1 << 23) /* else 8 bit */ +/* if serial */ +#define FLASH_ATMEL (1 << 23) /* else STM */ + +#define FLASH_SIZE_MASK (0x3 << 21) +#define NAND_256M (0x3 << 21) /* and more */ +#define NAND_128M (0x2 << 21) +#define NAND_64M (0x1 << 21) +#define NAND_32M (0x0 << 21) +#define ATMEL_16M (0x3 << 21) /* and more */ +#define ATMEL_8M (0x2 << 21) +#define ATMEL_4M_2M (0x1 << 21) +#define ATMEL_1M (0x0 << 21) /* and less */ +#define STM_32M (1 << 22) /* and more */ +#define STM_16M (0 << 22) /* and less */ + +#define FLASH_PARALLEL_HIGH_PIN_CNT (1 << 20) /* else low pin cnt */ + +/* Miscellaneous Control Register */ +#define GLOBAL_MISC_CTRL 0x30 +#define FLASH_PADS_MASK 0x07 +#define NAND_PADS_DISABLE BIT(2) +#define PFLASH_PADS_DISABLE BIT(1) +#define SFLASH_PADS_DISABLE BIT(0) + +static const struct of_device_id syscon_match[] = { + { .compatible = "cortina,gemini-syscon" }, + { }, +}; + +int of_flash_probe_gemini(struct platform_device *pdev, + struct device_node *np, + struct map_info *map) +{ + static struct regmap *rmap; + struct device *dev = &pdev->dev; + u32 val; + int ret; + + /* Multiplatform guard */ + if (!of_device_is_compatible(np, "cortina,gemini-flash")) + return 0; + + rmap = syscon_regmap_lookup_by_phandle(np, "syscon"); + if (IS_ERR(rmap)) { + dev_err(dev, "no syscon\n"); + return PTR_ERR(rmap); + } + + ret = regmap_read(rmap, GLOBAL_STATUS, &val); + if (ret) { + dev_err(dev, "failed to read global status register\n"); + return -ENODEV; + } + dev_dbg(dev, "global status reg: %08x\n", val); + + /* + * It would be contradictory if a physmap flash was NOT parallel. + */ + if ((val & FLASH_TYPE_MASK) != FLASH_TYPE_PARALLEL) { + dev_err(dev, "flash is not parallel\n"); + return -ENODEV; + } + + /* + * Complain if DT data and hardware definition is different. + */ + if (val & FLASH_WIDTH_16BIT) { + if (map->bankwidth != 2) + dev_warn(dev, "flash hardware say flash is 16 bit wide but DT says it is %d bits wide\n", + map->bankwidth * 8); + } else { + if (map->bankwidth != 1) + dev_warn(dev, "flash hardware say flash is 8 bit wide but DT says it is %d bits wide\n", + map->bankwidth * 8); + } + + /* Activate parallel (NOR flash) mode */ + ret = regmap_update_bits(rmap, GLOBAL_MISC_CTRL, + FLASH_PADS_MASK, + SFLASH_PADS_DISABLE | NAND_PADS_DISABLE); + if (ret) { + dev_err(dev, "unable to set up physmap pads\n"); + return -ENODEV; + } + + dev_info(&pdev->dev, "initialized Gemini-specific physmap control\n"); + + return 0; +} diff --git a/drivers/mtd/maps/physmap_of_gemini.h b/drivers/mtd/maps/physmap_of_gemini.h new file mode 100644 index 000000000000..c675025288dd --- /dev/null +++ b/drivers/mtd/maps/physmap_of_gemini.h @@ -0,0 +1,16 @@ +#include <linux/of.h> +#include <linux/mtd/map.h> + +#ifdef CONFIG_MTD_PHYSMAP_OF_GEMINI +int of_flash_probe_gemini(struct platform_device *pdev, + struct device_node *np, + struct map_info *map); +#else +static inline +int of_flash_probe_gemini(struct platform_device *pdev, + struct device_node *np, + struct map_info *map) +{ + return 0; +} +#endif diff --git a/drivers/mtd/maps/physmap_of_versatile.c b/drivers/mtd/maps/physmap_of_versatile.c index 0f39b2a015f4..8c6ccded9be8 100644 --- a/drivers/mtd/maps/physmap_of_versatile.c +++ b/drivers/mtd/maps/physmap_of_versatile.c @@ -252,4 +252,3 @@ int of_flash_probe_versatile(struct platform_device *pdev, return 0; } -EXPORT_SYMBOL_GPL(of_flash_probe_versatile); diff --git a/drivers/mtd/maps/pmcmsp-flash.c b/drivers/mtd/maps/pmcmsp-flash.c index f9fa3fad728e..2051f28ddac6 100644 --- a/drivers/mtd/maps/pmcmsp-flash.c +++ b/drivers/mtd/maps/pmcmsp-flash.c @@ -139,15 +139,13 @@ static int __init init_msp_flash(void) } msp_maps[i].bankwidth = 1; - msp_maps[i].name = kmalloc(7, GFP_KERNEL); + msp_maps[i].name = kstrndup(flash_name, 7, GFP_KERNEL); if (!msp_maps[i].name) { iounmap(msp_maps[i].virt); kfree(msp_parts[i]); goto cleanup_loop; } - msp_maps[i].name = strncpy(msp_maps[i].name, flash_name, 7); - for (j = 0; j < pcnt; j++) { part_name[5] = '0' + i; part_name[7] = '0' + j; diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index ce5ccc573a9c..3568294d4854 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -451,7 +451,7 @@ static int mtdchar_readoob(struct file *file, struct mtd_info *mtd, * data. For our userspace tools it is important to dump areas * with ECC errors! * For kernel internal usage it also might return -EUCLEAN - * to signal the caller that a bitflip has occured and has + * to signal the caller that a bitflip has occurred and has * been corrected by the ECC algorithm. * * Note: currently the standard NAND function, nand_read_oob_std, diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 052772f7caef..66a9dedd1062 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -1128,7 +1128,7 @@ EXPORT_SYMBOL_GPL(mtd_write_oob); * @oobecc: OOB region struct filled with the appropriate ECC position * information * - * This functions return ECC section information in the OOB area. I you want + * This function returns ECC section information in the OOB area. If you want * to get all the ECC bytes information, then you should call * mtd_ooblayout_ecc(mtd, section++, oobecc) until it returns -ERANGE. * @@ -1160,7 +1160,7 @@ EXPORT_SYMBOL_GPL(mtd_ooblayout_ecc); * @oobfree: OOB region struct filled with the appropriate free position * information * - * This functions return free bytes position in the OOB area. I you want + * This function returns free bytes position in the OOB area. If you want * to get all the free bytes information, then you should call * mtd_ooblayout_free(mtd, section++, oobfree) until it returns -ERANGE. * @@ -1190,7 +1190,7 @@ EXPORT_SYMBOL_GPL(mtd_ooblayout_free); * @iter: iterator function. Should be either mtd_ooblayout_free or * mtd_ooblayout_ecc depending on the region type you're searching for * - * This functions returns the section id and oobregion information of a + * This function returns the section id and oobregion information of a * specific byte. For example, say you want to know where the 4th ECC byte is * stored, you'll use: * diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index fccdd49bb964..ea5e5307f667 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -349,6 +349,14 @@ static const struct mtd_ooblayout_ops part_ooblayout_ops = { .free = part_ooblayout_free, }; +static int part_max_bad_blocks(struct mtd_info *mtd, loff_t ofs, size_t len) +{ + struct mtd_part *part = mtd_to_part(mtd); + + return part->master->_max_bad_blocks(part->master, + ofs + part->offset, len); +} + static inline void free_partition(struct mtd_part *p) { kfree(p->mtd.name); @@ -424,6 +432,7 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, slave->mtd.dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) ? &master->dev : master->dev.parent; + slave->mtd.dev.of_node = part->of_node; slave->mtd._read = part_read; slave->mtd._write = part_write; @@ -475,6 +484,8 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, slave->mtd._block_isbad = part_block_isbad; if (master->_block_markbad) slave->mtd._block_markbad = part_block_markbad; + if (master->_max_bad_blocks) + slave->mtd._max_bad_blocks = part_max_bad_blocks; if (master->_get_device) slave->mtd._get_device = part_get_device; diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 9ce5dcb4abd0..6d4d5672d1d8 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -426,6 +426,7 @@ config MTD_NAND_ORION config MTD_NAND_OXNAS tristate "NAND Flash support for Oxford Semiconductor SoC" + depends on ARCH_OXNAS || COMPILE_TEST depends on HAS_IOMEM help This enables the NAND flash controller on Oxford Semiconductor SoCs. @@ -535,6 +536,7 @@ config MTD_NAND_JZ4780 config MTD_NAND_FSMC tristate "Support for NAND on ST Micros FSMC" + depends on OF depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300 help Enables support for NAND Flash chips on the ST Microelectronics diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c index 0a177b1bfe3e..d1570f512f0b 100644 --- a/drivers/mtd/nand/fsl_ifc_nand.c +++ b/drivers/mtd/nand/fsl_ifc_nand.c @@ -258,9 +258,15 @@ static void fsl_ifc_run_command(struct mtd_info *mtd) int bufnum = nctrl->page & priv->bufnum_mask; int sector = bufnum * chip->ecc.steps; int sector_end = sector + chip->ecc.steps - 1; + __be32 *eccstat_regs; + + if (ctrl->version >= FSL_IFC_VERSION_2_0_0) + eccstat_regs = ifc->ifc_nand.v2_nand_eccstat; + else + eccstat_regs = ifc->ifc_nand.v1_nand_eccstat; for (i = sector / 4; i <= sector_end / 4; i++) - eccstat[i] = ifc_in32(&ifc->ifc_nand.nand_eccstat[i]); + eccstat[i] = ifc_in32(&eccstat_regs[i]); for (i = sector; i <= sector_end; i++) { errors = check_read_ecc(mtd, ctrl, eccstat, i); diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c index 4924b43977ef..bda1e4667138 100644 --- a/drivers/mtd/nand/fsmc_nand.c +++ b/drivers/mtd/nand/fsmc_nand.c @@ -35,10 +35,133 @@ #include <linux/mtd/partitions.h> #include <linux/io.h> #include <linux/slab.h> -#include <linux/mtd/fsmc.h> #include <linux/amba/bus.h> #include <mtd/mtd-abi.h> +#define FSMC_NAND_BW8 1 +#define FSMC_NAND_BW16 2 + +#define FSMC_MAX_NOR_BANKS 4 +#define FSMC_MAX_NAND_BANKS 4 + +#define FSMC_FLASH_WIDTH8 1 +#define FSMC_FLASH_WIDTH16 2 + +/* fsmc controller registers for NOR flash */ +#define CTRL 0x0 + /* ctrl register definitions */ + #define BANK_ENABLE (1 << 0) + #define MUXED (1 << 1) + #define NOR_DEV (2 << 2) + #define WIDTH_8 (0 << 4) + #define WIDTH_16 (1 << 4) + #define RSTPWRDWN (1 << 6) + #define WPROT (1 << 7) + #define WRT_ENABLE (1 << 12) + #define WAIT_ENB (1 << 13) + +#define CTRL_TIM 0x4 + /* ctrl_tim register definitions */ + +#define FSMC_NOR_BANK_SZ 0x8 +#define FSMC_NOR_REG_SIZE 0x40 + +#define FSMC_NOR_REG(base, bank, reg) (base + \ + FSMC_NOR_BANK_SZ * (bank) + \ + reg) + +/* fsmc controller registers for NAND flash */ +#define PC 0x00 + /* pc register definitions */ + #define FSMC_RESET (1 << 0) + #define FSMC_WAITON (1 << 1) + #define FSMC_ENABLE (1 << 2) + #define FSMC_DEVTYPE_NAND (1 << 3) + #define FSMC_DEVWID_8 (0 << 4) + #define FSMC_DEVWID_16 (1 << 4) + #define FSMC_ECCEN (1 << 6) + #define FSMC_ECCPLEN_512 (0 << 7) + #define FSMC_ECCPLEN_256 (1 << 7) + #define FSMC_TCLR_1 (1) + #define FSMC_TCLR_SHIFT (9) + #define FSMC_TCLR_MASK (0xF) + #define FSMC_TAR_1 (1) + #define FSMC_TAR_SHIFT (13) + #define FSMC_TAR_MASK (0xF) +#define STS 0x04 + /* sts register definitions */ + #define FSMC_CODE_RDY (1 << 15) +#define COMM 0x08 + /* comm register definitions */ + #define FSMC_TSET_0 0 + #define FSMC_TSET_SHIFT 0 + #define FSMC_TSET_MASK 0xFF + #define FSMC_TWAIT_6 6 + #define FSMC_TWAIT_SHIFT 8 + #define FSMC_TWAIT_MASK 0xFF + #define FSMC_THOLD_4 4 + #define FSMC_THOLD_SHIFT 16 + #define FSMC_THOLD_MASK 0xFF + #define FSMC_THIZ_1 1 + #define FSMC_THIZ_SHIFT 24 + #define FSMC_THIZ_MASK 0xFF +#define ATTRIB 0x0C +#define IOATA 0x10 +#define ECC1 0x14 +#define ECC2 0x18 +#define ECC3 0x1C +#define FSMC_NAND_BANK_SZ 0x20 + +#define FSMC_NAND_REG(base, bank, reg) (base + FSMC_NOR_REG_SIZE + \ + (FSMC_NAND_BANK_SZ * (bank)) + \ + reg) + +#define FSMC_BUSY_WAIT_TIMEOUT (1 * HZ) + +struct fsmc_nand_timings { + uint8_t tclr; + uint8_t tar; + uint8_t thiz; + uint8_t thold; + uint8_t twait; + uint8_t tset; +}; + +enum access_mode { + USE_DMA_ACCESS = 1, + USE_WORD_ACCESS, +}; + +/** + * fsmc_nand_platform_data - platform specific NAND controller config + * @nand_timings: timing setup for the physical NAND interface + * @partitions: partition table for the platform, use a default fallback + * if this is NULL + * @nr_partitions: the number of partitions in the previous entry + * @options: different options for the driver + * @width: bus width + * @bank: default bank + * @select_bank: callback to select a certain bank, this is + * platform-specific. If the controller only supports one bank + * this may be set to NULL + */ +struct fsmc_nand_platform_data { + struct fsmc_nand_timings *nand_timings; + struct mtd_partition *partitions; + unsigned int nr_partitions; + unsigned int options; + unsigned int width; + unsigned int bank; + + enum access_mode mode; + + void (*select_bank)(uint32_t bank, uint32_t busw); + + /* priv structures for dma accesses */ + void *read_dma_priv; + void *write_dma_priv; +}; + static int fsmc_ecc1_ooblayout_ecc(struct mtd_info *mtd, int section, struct mtd_oob_region *oobregion) { @@ -714,7 +837,6 @@ static bool filter(struct dma_chan *chan, void *slave) return true; } -#ifdef CONFIG_OF static int fsmc_nand_probe_config_dt(struct platform_device *pdev, struct device_node *np) { @@ -757,13 +879,6 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev, } return 0; } -#else -static int fsmc_nand_probe_config_dt(struct platform_device *pdev, - struct device_node *np) -{ - return -ENOSYS; -} -#endif /* * fsmc_nand_probe - Probe function @@ -782,19 +897,15 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) u32 pid; int i; - if (np) { - pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); - pdev->dev.platform_data = pdata; - ret = fsmc_nand_probe_config_dt(pdev, np); - if (ret) { - dev_err(&pdev->dev, "no platform data\n"); - return -ENODEV; - } - } + pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return -ENOMEM; - if (!pdata) { - dev_err(&pdev->dev, "platform data is NULL\n"); - return -EINVAL; + pdev->dev.platform_data = pdata; + ret = fsmc_nand_probe_config_dt(pdev, np); + if (ret) { + dev_err(&pdev->dev, "no platform data\n"); + return -ENODEV; } /* Allocate memory for the device structure (and zero it) */ diff --git a/drivers/mtd/nand/lpc32xx_slc.c b/drivers/mtd/nand/lpc32xx_slc.c index 53bafe23ab39..a0669a33f8fe 100644 --- a/drivers/mtd/nand/lpc32xx_slc.c +++ b/drivers/mtd/nand/lpc32xx_slc.c @@ -797,22 +797,17 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) struct resource *rc; int res; - rc = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (rc == NULL) { - dev_err(&pdev->dev, "No memory resource found for device\n"); - return -EBUSY; - } - /* Allocate memory for the device structure (and zero it) */ host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL); if (!host) return -ENOMEM; - host->io_base_dma = rc->start; + rc = platform_get_resource(pdev, IORESOURCE_MEM, 0); host->io_base = devm_ioremap_resource(&pdev->dev, rc); if (IS_ERR(host->io_base)) return PTR_ERR(host->io_base); + host->io_base_dma = rc->start; if (pdev->dev.of_node) host->ncfg = lpc32xx_parse_dt(&pdev->dev); if (!host->ncfg) { diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c index 6c3eed3c2094..6c517c682939 100644 --- a/drivers/mtd/nand/mtk_nand.c +++ b/drivers/mtd/nand/mtk_nand.c @@ -1383,7 +1383,6 @@ static int mtk_nfc_probe(struct platform_device *pdev) nfc->regs = devm_ioremap_resource(dev, res); if (IS_ERR(nfc->regs)) { ret = PTR_ERR(nfc->regs); - dev_err(dev, "no nfi base\n"); goto release_ecc; } diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index ec1c28aaaf23..1492c12906f6 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -3263,6 +3263,42 @@ static int nand_block_markbad(struct mtd_info *mtd, loff_t ofs) } /** + * nand_max_bad_blocks - [MTD Interface] Max number of bad blocks for an mtd + * @mtd: MTD device structure + * @ofs: offset relative to mtd start + * @len: length of mtd + */ +static int nand_max_bad_blocks(struct mtd_info *mtd, loff_t ofs, size_t len) +{ + struct nand_chip *chip = mtd_to_nand(mtd); + u32 part_start_block; + u32 part_end_block; + u32 part_start_die; + u32 part_end_die; + + /* + * max_bb_per_die and blocks_per_die used to determine + * the maximum bad block count. + */ + if (!chip->max_bb_per_die || !chip->blocks_per_die) + return -ENOTSUPP; + + /* Get the start and end of the partition in erase blocks. */ + part_start_block = mtd_div_by_eb(ofs, mtd); + part_end_block = mtd_div_by_eb(len, mtd) + part_start_block - 1; + + /* Get the start and end LUNs of the partition. */ + part_start_die = part_start_block / chip->blocks_per_die; + part_end_die = part_end_block / chip->blocks_per_die; + + /* + * Look up the bad blocks per unit and multiply by the number of units + * that the partition spans. + */ + return chip->max_bb_per_die * (part_end_die - part_start_die + 1); +} + +/** * nand_onfi_set_features- [REPLACEABLE] set features for ONFI nand * @mtd: MTD device structure * @chip: nand chip info structure @@ -3592,6 +3628,9 @@ static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip, chip->chipsize *= (uint64_t)mtd->erasesize * p->lun_count; chip->bits_per_cell = p->bits_per_cell; + chip->max_bb_per_die = le16_to_cpu(p->bb_per_lun); + chip->blocks_per_die = le32_to_cpu(p->blocks_per_lun); + if (onfi_feature(chip) & ONFI_FEATURE_16_BIT_BUS) *busw = NAND_BUSWIDTH_16; else @@ -4815,6 +4854,7 @@ int nand_scan_tail(struct mtd_info *mtd) mtd->_block_isreserved = nand_block_isreserved; mtd->_block_isbad = nand_block_isbad; mtd->_block_markbad = nand_block_markbad; + mtd->_max_bad_blocks = nand_max_bad_blocks; mtd->writebufsize = mtd->writesize; /* diff --git a/drivers/mtd/nand/nand_ids.c b/drivers/mtd/nand/nand_ids.c index b3a332f37e14..4a2f75b0c200 100644 --- a/drivers/mtd/nand/nand_ids.c +++ b/drivers/mtd/nand/nand_ids.c @@ -185,6 +185,7 @@ struct nand_manufacturers nand_manuf_ids[] = { {NAND_MFR_SANDISK, "SanDisk"}, {NAND_MFR_INTEL, "Intel"}, {NAND_MFR_ATO, "ATO"}, + {NAND_MFR_WINBOND, "Winbond"}, {0x0, "Unknown"} }; diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c index e40482a65de6..0eeeb8b889ea 100644 --- a/drivers/mtd/nand/sunxi_nand.c +++ b/drivers/mtd/nand/sunxi_nand.c @@ -321,6 +321,10 @@ static int sunxi_nfc_wait_events(struct sunxi_nfc *nfc, u32 events, ret = wait_for_completion_timeout(&nfc->complete, msecs_to_jiffies(timeout_ms)); + if (!ret) + ret = -ETIMEDOUT; + else + ret = 0; writel(0, nfc->regs + NFC_REG_INT); } else { @@ -518,6 +522,8 @@ static void sunxi_nfc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len) u32 tmp; while (len > offs) { + bool poll = false; + cnt = min(len - offs, NFC_SRAM_SIZE); ret = sunxi_nfc_wait_cmd_fifo_empty(nfc); @@ -528,7 +534,11 @@ static void sunxi_nfc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len) tmp = NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD; writel(tmp, nfc->regs + NFC_REG_CMD); - ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0); + /* Arbitrary limit for polling mode */ + if (cnt < 64) + poll = true; + + ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, poll, 0); if (ret) break; @@ -551,6 +561,8 @@ static void sunxi_nfc_write_buf(struct mtd_info *mtd, const uint8_t *buf, u32 tmp; while (len > offs) { + bool poll = false; + cnt = min(len - offs, NFC_SRAM_SIZE); ret = sunxi_nfc_wait_cmd_fifo_empty(nfc); @@ -563,7 +575,11 @@ static void sunxi_nfc_write_buf(struct mtd_info *mtd, const uint8_t *buf, NFC_ACCESS_DIR; writel(tmp, nfc->regs + NFC_REG_CMD); - ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0); + /* Arbitrary limit for polling mode */ + if (cnt < 64) + poll = true; + + ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, poll, 0); if (ret) break; @@ -588,10 +604,6 @@ static void sunxi_nfc_cmd_ctrl(struct mtd_info *mtd, int dat, struct sunxi_nfc *nfc = to_sunxi_nfc(sunxi_nand->nand.controller); int ret; - ret = sunxi_nfc_wait_cmd_fifo_empty(nfc); - if (ret) - return; - if (dat == NAND_CMD_NONE && (ctrl & NAND_NCE) && !(ctrl & (NAND_CLE | NAND_ALE))) { u32 cmd = 0; @@ -621,6 +633,10 @@ static void sunxi_nfc_cmd_ctrl(struct mtd_info *mtd, int dat, writel(sunxi_nand->addr[1], nfc->regs + NFC_REG_ADDR_HIGH); + ret = sunxi_nfc_wait_cmd_fifo_empty(nfc); + if (ret) + return; + writel(cmd, nfc->regs + NFC_REG_CMD); sunxi_nand->addr[0] = 0; sunxi_nand->addr[1] = 0; @@ -957,7 +973,7 @@ static int sunxi_nfc_hw_ecc_read_chunk(struct mtd_info *mtd, writel(NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD | NFC_ECC_OP, nfc->regs + NFC_REG_CMD); - ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0); + ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0); sunxi_nfc_randomizer_disable(mtd); if (ret) return ret; @@ -1069,7 +1085,7 @@ static int sunxi_nfc_hw_ecc_read_chunks_dma(struct mtd_info *mtd, uint8_t *buf, writel(NFC_PAGE_OP | NFC_DATA_SWAP_METHOD | NFC_DATA_TRANS, nfc->regs + NFC_REG_CMD); - ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0); + ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0); if (ret) dmaengine_terminate_all(nfc->dmac); @@ -1189,7 +1205,7 @@ static int sunxi_nfc_hw_ecc_write_chunk(struct mtd_info *mtd, NFC_ACCESS_DIR | NFC_ECC_OP, nfc->regs + NFC_REG_CMD); - ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0); + ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0); sunxi_nfc_randomizer_disable(mtd); if (ret) return ret; @@ -1428,7 +1444,7 @@ static int sunxi_nfc_hw_ecc_write_page_dma(struct mtd_info *mtd, NFC_DATA_TRANS | NFC_ACCESS_DIR, nfc->regs + NFC_REG_CMD); - ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0); + ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0); if (ret) dmaengine_terminate_all(nfc->dmac); diff --git a/drivers/mtd/nand/xway_nand.c b/drivers/mtd/nand/xway_nand.c index 895101a5e686..ddee4005248c 100644 --- a/drivers/mtd/nand/xway_nand.c +++ b/drivers/mtd/nand/xway_nand.c @@ -3,7 +3,7 @@ * under the terms of the GNU General Public License version 2 as published * by the Free Software Foundation. * - * Copyright © 2012 John Crispin <blogic@openwrt.org> + * Copyright © 2012 John Crispin <john@phrozen.org> * Copyright © 2016 Hauke Mehrtens <hauke@hauke-m.de> */ diff --git a/drivers/mtd/ofpart.c b/drivers/mtd/ofpart.c index ede407d6e106..464470122493 100644 --- a/drivers/mtd/ofpart.c +++ b/drivers/mtd/ofpart.c @@ -108,6 +108,7 @@ static int parse_ofpart_partitions(struct mtd_info *master, parts[i].offset = of_read_number(reg, a_cells); parts[i].size = of_read_number(reg + a_cells, s_cells); + parts[i].of_node = pp; partname = of_get_property(pp, "label", &len); if (!partname) diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig index 4a682ee0f632..7252087ef407 100644 --- a/drivers/mtd/spi-nor/Kconfig +++ b/drivers/mtd/spi-nor/Kconfig @@ -29,6 +29,16 @@ config MTD_SPI_NOR_USE_4K_SECTORS Please note that some tools/drivers/filesystems may not work with 4096 B erase size (e.g. UBIFS requires 15 KiB as a minimum). +config SPI_ASPEED_SMC + tristate "Aspeed flash controllers in SPI mode" + depends on ARCH_ASPEED || COMPILE_TEST + depends on HAS_IOMEM && OF + help + This enables support for the Firmware Memory controller (FMC) + in the Aspeed AST2500/AST2400 SoCs when attached to SPI NOR chips, + and support for the SPI flash memory controller (SPI) for + the host firmware. The implementation only supports SPI NOR. + config SPI_ATMEL_QUADSPI tristate "Atmel Quad SPI Controller" depends on ARCH_AT91 || (ARM && COMPILE_TEST) @@ -40,7 +50,7 @@ config SPI_ATMEL_QUADSPI config SPI_CADENCE_QUADSPI tristate "Cadence Quad SPI controller" - depends on OF && ARM + depends on OF && (ARM || COMPILE_TEST) help Enable support for the Cadence Quad SPI Flash controller. @@ -76,4 +86,24 @@ config SPI_NXP_SPIFI Flash. Enable this option if you have a device with a SPIFI controller and want to access the Flash as a mtd device. +config SPI_INTEL_SPI + tristate + +config SPI_INTEL_SPI_PLATFORM + tristate "Intel PCH/PCU SPI flash platform driver" if EXPERT + depends on X86 + select SPI_INTEL_SPI + help + This enables platform support for the Intel PCH/PCU SPI + controller in master mode. This controller is present in modern + Intel hardware and is used to hold BIOS and other persistent + settings. Using this driver it is possible to upgrade BIOS + directly from Linux. + + Say N here unless you know what you are doing. Overwriting the + SPI flash may render the system unbootable. + + To compile this driver as a module, choose M here: the module + will be called intel-spi-platform. + endif # MTD_SPI_NOR diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile index 121695e83542..72238a793198 100644 --- a/drivers/mtd/spi-nor/Makefile +++ b/drivers/mtd/spi-nor/Makefile @@ -1,7 +1,10 @@ obj-$(CONFIG_MTD_SPI_NOR) += spi-nor.o +obj-$(CONFIG_SPI_ASPEED_SMC) += aspeed-smc.o obj-$(CONFIG_SPI_ATMEL_QUADSPI) += atmel-quadspi.o obj-$(CONFIG_SPI_CADENCE_QUADSPI) += cadence-quadspi.o obj-$(CONFIG_SPI_FSL_QUADSPI) += fsl-quadspi.o obj-$(CONFIG_SPI_HISI_SFC) += hisi-sfc.o obj-$(CONFIG_MTD_MT81xx_NOR) += mtk-quadspi.o obj-$(CONFIG_SPI_NXP_SPIFI) += nxp-spifi.o +obj-$(CONFIG_SPI_INTEL_SPI) += intel-spi.o +obj-$(CONFIG_SPI_INTEL_SPI_PLATFORM) += intel-spi-platform.o diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c new file mode 100644 index 000000000000..56051d30f000 --- /dev/null +++ b/drivers/mtd/spi-nor/aspeed-smc.c @@ -0,0 +1,754 @@ +/* + * ASPEED Static Memory Controller driver + * + * Copyright (c) 2015-2016, IBM Corporation. + * + * 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. + */ + +#include <linux/bug.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/mtd/mtd.h> +#include <linux/mtd/partitions.h> +#include <linux/mtd/spi-nor.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/sysfs.h> + +#define DEVICE_NAME "aspeed-smc" + +/* + * The driver only support SPI flash + */ +enum aspeed_smc_flash_type { + smc_type_nor = 0, + smc_type_nand = 1, + smc_type_spi = 2, +}; + +struct aspeed_smc_chip; + +struct aspeed_smc_info { + u32 maxsize; /* maximum size of chip window */ + u8 nce; /* number of chip enables */ + bool hastype; /* flash type field exists in config reg */ + u8 we0; /* shift for write enable bit for CE0 */ + u8 ctl0; /* offset in regs of ctl for CE0 */ + + void (*set_4b)(struct aspeed_smc_chip *chip); +}; + +static void aspeed_smc_chip_set_4b_spi_2400(struct aspeed_smc_chip *chip); +static void aspeed_smc_chip_set_4b(struct aspeed_smc_chip *chip); + +static const struct aspeed_smc_info fmc_2400_info = { + .maxsize = 64 * 1024 * 1024, + .nce = 5, + .hastype = true, + .we0 = 16, + .ctl0 = 0x10, + .set_4b = aspeed_smc_chip_set_4b, +}; + +static const struct aspeed_smc_info spi_2400_info = { + .maxsize = 64 * 1024 * 1024, + .nce = 1, + .hastype = false, + .we0 = 0, + .ctl0 = 0x04, + .set_4b = aspeed_smc_chip_set_4b_spi_2400, +}; + +static const struct aspeed_smc_info fmc_2500_info = { + .maxsize = 256 * 1024 * 1024, + .nce = 3, + .hastype = true, + .we0 = 16, + .ctl0 = 0x10, + .set_4b = aspeed_smc_chip_set_4b, +}; + +static const struct aspeed_smc_info spi_2500_info = { + .maxsize = 128 * 1024 * 1024, + .nce = 2, + .hastype = false, + .we0 = 16, + .ctl0 = 0x10, + .set_4b = aspeed_smc_chip_set_4b, +}; + +enum aspeed_smc_ctl_reg_value { + smc_base, /* base value without mode for other commands */ + smc_read, /* command reg for (maybe fast) reads */ + smc_write, /* command reg for writes */ + smc_max, +}; + +struct aspeed_smc_controller; + +struct aspeed_smc_chip { + int cs; + struct aspeed_smc_controller *controller; + void __iomem *ctl; /* control register */ + void __iomem *ahb_base; /* base of chip window */ + u32 ctl_val[smc_max]; /* control settings */ + enum aspeed_smc_flash_type type; /* what type of flash */ + struct spi_nor nor; +}; + +struct aspeed_smc_controller { + struct device *dev; + + struct mutex mutex; /* controller access mutex */ + const struct aspeed_smc_info *info; /* type info of controller */ + void __iomem *regs; /* controller registers */ + void __iomem *ahb_base; /* per-chip windows resource */ + + struct aspeed_smc_chip *chips[0]; /* pointers to attached chips */ +}; + +/* + * SPI Flash Configuration Register (AST2500 SPI) + * or + * Type setting Register (AST2500 FMC). + * CE0 and CE1 can only be of type SPI. CE2 can be of type NOR but the + * driver does not support it. + */ +#define CONFIG_REG 0x0 +#define CONFIG_DISABLE_LEGACY BIT(31) /* 1 */ + +#define CONFIG_CE2_WRITE BIT(18) +#define CONFIG_CE1_WRITE BIT(17) +#define CONFIG_CE0_WRITE BIT(16) + +#define CONFIG_CE2_TYPE BIT(4) /* AST2500 FMC only */ +#define CONFIG_CE1_TYPE BIT(2) /* AST2500 FMC only */ +#define CONFIG_CE0_TYPE BIT(0) /* AST2500 FMC only */ + +/* + * CE Control Register + */ +#define CE_CONTROL_REG 0x4 + +/* + * CEx Control Register + */ +#define CONTROL_AAF_MODE BIT(31) +#define CONTROL_IO_MODE_MASK GENMASK(30, 28) +#define CONTROL_IO_DUAL_DATA BIT(29) +#define CONTROL_IO_DUAL_ADDR_DATA (BIT(29) | BIT(28)) +#define CONTROL_IO_QUAD_DATA BIT(30) +#define CONTROL_IO_QUAD_ADDR_DATA (BIT(30) | BIT(28)) +#define CONTROL_CE_INACTIVE_SHIFT 24 +#define CONTROL_CE_INACTIVE_MASK GENMASK(27, \ + CONTROL_CE_INACTIVE_SHIFT) +/* 0 = 16T ... 15 = 1T T=HCLK */ +#define CONTROL_COMMAND_SHIFT 16 +#define CONTROL_DUMMY_COMMAND_OUT BIT(15) +#define CONTROL_IO_DUMMY_HI BIT(14) +#define CONTROL_IO_DUMMY_HI_SHIFT 14 +#define CONTROL_CLK_DIV4 BIT(13) /* others */ +#define CONTROL_IO_ADDRESS_4B BIT(13) /* AST2400 SPI */ +#define CONTROL_RW_MERGE BIT(12) +#define CONTROL_IO_DUMMY_LO_SHIFT 6 +#define CONTROL_IO_DUMMY_LO GENMASK(7, \ + CONTROL_IO_DUMMY_LO_SHIFT) +#define CONTROL_IO_DUMMY_MASK (CONTROL_IO_DUMMY_HI | \ + CONTROL_IO_DUMMY_LO) +#define CONTROL_IO_DUMMY_SET(dummy) \ + (((((dummy) >> 2) & 0x1) << CONTROL_IO_DUMMY_HI_SHIFT) | \ + (((dummy) & 0x3) << CONTROL_IO_DUMMY_LO_SHIFT)) + +#define CONTROL_CLOCK_FREQ_SEL_SHIFT 8 +#define CONTROL_CLOCK_FREQ_SEL_MASK GENMASK(11, \ + CONTROL_CLOCK_FREQ_SEL_SHIFT) +#define CONTROL_LSB_FIRST BIT(5) +#define CONTROL_CLOCK_MODE_3 BIT(4) +#define CONTROL_IN_DUAL_DATA BIT(3) +#define CONTROL_CE_STOP_ACTIVE_CONTROL BIT(2) +#define CONTROL_COMMAND_MODE_MASK GENMASK(1, 0) +#define CONTROL_COMMAND_MODE_NORMAL 0 +#define CONTROL_COMMAND_MODE_FREAD 1 +#define CONTROL_COMMAND_MODE_WRITE 2 +#define CONTROL_COMMAND_MODE_USER 3 + +#define CONTROL_KEEP_MASK \ + (CONTROL_AAF_MODE | CONTROL_CE_INACTIVE_MASK | CONTROL_CLK_DIV4 | \ + CONTROL_IO_DUMMY_MASK | CONTROL_CLOCK_FREQ_SEL_MASK | \ + CONTROL_LSB_FIRST | CONTROL_CLOCK_MODE_3) + +/* + * The Segment Register uses a 8MB unit to encode the start address + * and the end address of the mapping window of a flash SPI slave : + * + * | byte 1 | byte 2 | byte 3 | byte 4 | + * +--------+--------+--------+--------+ + * | end | start | 0 | 0 | + */ +#define SEGMENT_ADDR_REG0 0x30 +#define SEGMENT_ADDR_START(_r) ((((_r) >> 16) & 0xFF) << 23) +#define SEGMENT_ADDR_END(_r) ((((_r) >> 24) & 0xFF) << 23) + +/* + * In user mode all data bytes read or written to the chip decode address + * range are transferred to or from the SPI bus. The range is treated as a + * fifo of arbitratry 1, 2, or 4 byte width but each write has to be aligned + * to its size. The address within the multiple 8kB range is ignored when + * sending bytes to the SPI bus. + * + * On the arm architecture, as of Linux version 4.3, memcpy_fromio and + * memcpy_toio on little endian targets use the optimized memcpy routines + * that were designed for well behavied memory storage. These routines + * have a stutter if the source and destination are not both word aligned, + * once with a duplicate access to the source after aligning to the + * destination to a word boundary, and again with a duplicate access to + * the source when the final byte count is not word aligned. + * + * When writing or reading the fifo this stutter discards data or sends + * too much data to the fifo and can not be used by this driver. + * + * While the low level io string routines that implement the insl family do + * the desired accesses and memory increments, the cross architecture io + * macros make them essentially impossible to use on a memory mapped address + * instead of a a token from the call to iomap of an io port. + * + * These fifo routines use readl and friends to a constant io port and update + * the memory buffer pointer and count via explicit code. The final updates + * to len are optimistically suppressed. + */ +static int aspeed_smc_read_from_ahb(void *buf, void __iomem *src, size_t len) +{ + size_t offset = 0; + + if (IS_ALIGNED((uintptr_t)src, sizeof(uintptr_t)) && + IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) { + ioread32_rep(src, buf, len >> 2); + offset = len & ~0x3; + len -= offset; + } + ioread8_rep(src, (u8 *)buf + offset, len); + return 0; +} + +static int aspeed_smc_write_to_ahb(void __iomem *dst, const void *buf, + size_t len) +{ + size_t offset = 0; + + if (IS_ALIGNED((uintptr_t)dst, sizeof(uintptr_t)) && + IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) { + iowrite32_rep(dst, buf, len >> 2); + offset = len & ~0x3; + len -= offset; + } + iowrite8_rep(dst, (const u8 *)buf + offset, len); + return 0; +} + +static inline u32 aspeed_smc_chip_write_bit(struct aspeed_smc_chip *chip) +{ + return BIT(chip->controller->info->we0 + chip->cs); +} + +static void aspeed_smc_chip_check_config(struct aspeed_smc_chip *chip) +{ + struct aspeed_smc_controller *controller = chip->controller; + u32 reg; + + reg = readl(controller->regs + CONFIG_REG); + + if (reg & aspeed_smc_chip_write_bit(chip)) + return; + + dev_dbg(controller->dev, "config write is not set ! @%p: 0x%08x\n", + controller->regs + CONFIG_REG, reg); + reg |= aspeed_smc_chip_write_bit(chip); + writel(reg, controller->regs + CONFIG_REG); +} + +static void aspeed_smc_start_user(struct spi_nor *nor) +{ + struct aspeed_smc_chip *chip = nor->priv; + u32 ctl = chip->ctl_val[smc_base]; + + /* + * When the chip is controlled in user mode, we need write + * access to send the opcodes to it. So check the config. + */ + aspeed_smc_chip_check_config(chip); + + ctl |= CONTROL_COMMAND_MODE_USER | + CONTROL_CE_STOP_ACTIVE_CONTROL; + writel(ctl, chip->ctl); + + ctl &= ~CONTROL_CE_STOP_ACTIVE_CONTROL; + writel(ctl, chip->ctl); +} + +static void aspeed_smc_stop_user(struct spi_nor *nor) +{ + struct aspeed_smc_chip *chip = nor->priv; + + u32 ctl = chip->ctl_val[smc_read]; + u32 ctl2 = ctl | CONTROL_COMMAND_MODE_USER | + CONTROL_CE_STOP_ACTIVE_CONTROL; + + writel(ctl2, chip->ctl); /* stop user CE control */ + writel(ctl, chip->ctl); /* default to fread or read mode */ +} + +static int aspeed_smc_prep(struct spi_nor *nor, enum spi_nor_ops ops) +{ + struct aspeed_smc_chip *chip = nor->priv; + + mutex_lock(&chip->controller->mutex); + return 0; +} + +static void aspeed_smc_unprep(struct spi_nor *nor, enum spi_nor_ops ops) +{ + struct aspeed_smc_chip *chip = nor->priv; + + mutex_unlock(&chip->controller->mutex); +} + +static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +{ + struct aspeed_smc_chip *chip = nor->priv; + + aspeed_smc_start_user(nor); + aspeed_smc_write_to_ahb(chip->ahb_base, &opcode, 1); + aspeed_smc_read_from_ahb(buf, chip->ahb_base, len); + aspeed_smc_stop_user(nor); + return 0; +} + +static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, + int len) +{ + struct aspeed_smc_chip *chip = nor->priv; + + aspeed_smc_start_user(nor); + aspeed_smc_write_to_ahb(chip->ahb_base, &opcode, 1); + aspeed_smc_write_to_ahb(chip->ahb_base, buf, len); + aspeed_smc_stop_user(nor); + return 0; +} + +static void aspeed_smc_send_cmd_addr(struct spi_nor *nor, u8 cmd, u32 addr) +{ + struct aspeed_smc_chip *chip = nor->priv; + __be32 temp; + u32 cmdaddr; + + switch (nor->addr_width) { + default: + WARN_ONCE(1, "Unexpected address width %u, defaulting to 3\n", + nor->addr_width); + /* FALLTHROUGH */ + case 3: + cmdaddr = addr & 0xFFFFFF; + cmdaddr |= cmd << 24; + + temp = cpu_to_be32(cmdaddr); + aspeed_smc_write_to_ahb(chip->ahb_base, &temp, 4); + break; + case 4: + temp = cpu_to_be32(addr); + aspeed_smc_write_to_ahb(chip->ahb_base, &cmd, 1); + aspeed_smc_write_to_ahb(chip->ahb_base, &temp, 4); + break; + } +} + +static ssize_t aspeed_smc_read_user(struct spi_nor *nor, loff_t from, + size_t len, u_char *read_buf) +{ + struct aspeed_smc_chip *chip = nor->priv; + int i; + u8 dummy = 0xFF; + + aspeed_smc_start_user(nor); + aspeed_smc_send_cmd_addr(nor, nor->read_opcode, from); + for (i = 0; i < chip->nor.read_dummy / 8; i++) + aspeed_smc_write_to_ahb(chip->ahb_base, &dummy, sizeof(dummy)); + + aspeed_smc_read_from_ahb(read_buf, chip->ahb_base, len); + aspeed_smc_stop_user(nor); + return len; +} + +static ssize_t aspeed_smc_write_user(struct spi_nor *nor, loff_t to, + size_t len, const u_char *write_buf) +{ + struct aspeed_smc_chip *chip = nor->priv; + + aspeed_smc_start_user(nor); + aspeed_smc_send_cmd_addr(nor, nor->program_opcode, to); + aspeed_smc_write_to_ahb(chip->ahb_base, write_buf, len); + aspeed_smc_stop_user(nor); + return len; +} + +static int aspeed_smc_unregister(struct aspeed_smc_controller *controller) +{ + struct aspeed_smc_chip *chip; + int n; + + for (n = 0; n < controller->info->nce; n++) { + chip = controller->chips[n]; + if (chip) + mtd_device_unregister(&chip->nor.mtd); + } + + return 0; +} + +static int aspeed_smc_remove(struct platform_device *dev) +{ + return aspeed_smc_unregister(platform_get_drvdata(dev)); +} + +static const struct of_device_id aspeed_smc_matches[] = { + { .compatible = "aspeed,ast2400-fmc", .data = &fmc_2400_info }, + { .compatible = "aspeed,ast2400-spi", .data = &spi_2400_info }, + { .compatible = "aspeed,ast2500-fmc", .data = &fmc_2500_info }, + { .compatible = "aspeed,ast2500-spi", .data = &spi_2500_info }, + { } +}; +MODULE_DEVICE_TABLE(of, aspeed_smc_matches); + +/* + * Each chip has a mapping window defined by a segment address + * register defining a start and an end address on the AHB bus. These + * addresses can be configured to fit the chip size and offer a + * contiguous memory region across chips. For the moment, we only + * check that each chip segment is valid. + */ +static void __iomem *aspeed_smc_chip_base(struct aspeed_smc_chip *chip, + struct resource *res) +{ + struct aspeed_smc_controller *controller = chip->controller; + u32 offset = 0; + u32 reg; + + if (controller->info->nce > 1) { + reg = readl(controller->regs + SEGMENT_ADDR_REG0 + + chip->cs * 4); + + if (SEGMENT_ADDR_START(reg) >= SEGMENT_ADDR_END(reg)) + return NULL; + + offset = SEGMENT_ADDR_START(reg) - res->start; + } + + return controller->ahb_base + offset; +} + +static void aspeed_smc_chip_enable_write(struct aspeed_smc_chip *chip) +{ + struct aspeed_smc_controller *controller = chip->controller; + u32 reg; + + reg = readl(controller->regs + CONFIG_REG); + + reg |= aspeed_smc_chip_write_bit(chip); + writel(reg, controller->regs + CONFIG_REG); +} + +static void aspeed_smc_chip_set_type(struct aspeed_smc_chip *chip, int type) +{ + struct aspeed_smc_controller *controller = chip->controller; + u32 reg; + + chip->type = type; + + reg = readl(controller->regs + CONFIG_REG); + reg &= ~(3 << (chip->cs * 2)); + reg |= chip->type << (chip->cs * 2); + writel(reg, controller->regs + CONFIG_REG); +} + +/* + * The AST2500 FMC flash controller should be strapped by hardware, or + * autodetected, but the AST2500 SPI flash needs to be set. + */ +static void aspeed_smc_chip_set_4b(struct aspeed_smc_chip *chip) +{ + struct aspeed_smc_controller *controller = chip->controller; + u32 reg; + + if (chip->controller->info == &spi_2500_info) { + reg = readl(controller->regs + CE_CONTROL_REG); + reg |= 1 << chip->cs; + writel(reg, controller->regs + CE_CONTROL_REG); + } +} + +/* + * The AST2400 SPI flash controller does not have a CE Control + * register. It uses the CE0 control register to set 4Byte mode at the + * controller level. + */ +static void aspeed_smc_chip_set_4b_spi_2400(struct aspeed_smc_chip *chip) +{ + chip->ctl_val[smc_base] |= CONTROL_IO_ADDRESS_4B; + chip->ctl_val[smc_read] |= CONTROL_IO_ADDRESS_4B; +} + +static int aspeed_smc_chip_setup_init(struct aspeed_smc_chip *chip, + struct resource *res) +{ + struct aspeed_smc_controller *controller = chip->controller; + const struct aspeed_smc_info *info = controller->info; + u32 reg, base_reg; + + /* + * Always turn on the write enable bit to allow opcodes to be + * sent in user mode. + */ + aspeed_smc_chip_enable_write(chip); + + /* The driver only supports SPI type flash */ + if (info->hastype) + aspeed_smc_chip_set_type(chip, smc_type_spi); + + /* + * Configure chip base address in memory + */ + chip->ahb_base = aspeed_smc_chip_base(chip, res); + if (!chip->ahb_base) { + dev_warn(chip->nor.dev, "CE segment window closed.\n"); + return -EINVAL; + } + + /* + * Get value of the inherited control register. U-Boot usually + * does some timing calibration on the FMC chip, so it's good + * to keep them. In the future, we should handle calibration + * from Linux. + */ + reg = readl(chip->ctl); + dev_dbg(controller->dev, "control register: %08x\n", reg); + + base_reg = reg & CONTROL_KEEP_MASK; + if (base_reg != reg) { + dev_dbg(controller->dev, + "control register changed to: %08x\n", + base_reg); + } + chip->ctl_val[smc_base] = base_reg; + + /* + * Retain the prior value of the control register as the + * default if it was normal access mode. Otherwise start with + * the sanitized base value set to read mode. + */ + if ((reg & CONTROL_COMMAND_MODE_MASK) == + CONTROL_COMMAND_MODE_NORMAL) + chip->ctl_val[smc_read] = reg; + else + chip->ctl_val[smc_read] = chip->ctl_val[smc_base] | + CONTROL_COMMAND_MODE_NORMAL; + + dev_dbg(controller->dev, "default control register: %08x\n", + chip->ctl_val[smc_read]); + return 0; +} + +static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip) +{ + struct aspeed_smc_controller *controller = chip->controller; + const struct aspeed_smc_info *info = controller->info; + u32 cmd; + + if (chip->nor.addr_width == 4 && info->set_4b) + info->set_4b(chip); + + /* + * base mode has not been optimized yet. use it for writes. + */ + chip->ctl_val[smc_write] = chip->ctl_val[smc_base] | + chip->nor.program_opcode << CONTROL_COMMAND_SHIFT | + CONTROL_COMMAND_MODE_WRITE; + + dev_dbg(controller->dev, "write control register: %08x\n", + chip->ctl_val[smc_write]); + + /* + * TODO: Adjust clocks if fast read is supported and interpret + * SPI-NOR flags to adjust controller settings. + */ + switch (chip->nor.flash_read) { + case SPI_NOR_NORMAL: + cmd = CONTROL_COMMAND_MODE_NORMAL; + break; + case SPI_NOR_FAST: + cmd = CONTROL_COMMAND_MODE_FREAD; + break; + default: + dev_err(chip->nor.dev, "unsupported SPI read mode\n"); + return -EINVAL; + } + + chip->ctl_val[smc_read] |= cmd | + CONTROL_IO_DUMMY_SET(chip->nor.read_dummy / 8); + + dev_dbg(controller->dev, "base control register: %08x\n", + chip->ctl_val[smc_read]); + return 0; +} + +static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller, + struct device_node *np, struct resource *r) +{ + const struct aspeed_smc_info *info = controller->info; + struct device *dev = controller->dev; + struct device_node *child; + unsigned int cs; + int ret = -ENODEV; + + for_each_available_child_of_node(np, child) { + struct aspeed_smc_chip *chip; + struct spi_nor *nor; + struct mtd_info *mtd; + + /* This driver does not support NAND or NOR flash devices. */ + if (!of_device_is_compatible(child, "jedec,spi-nor")) + continue; + + ret = of_property_read_u32(child, "reg", &cs); + if (ret) { + dev_err(dev, "Couldn't not read chip select.\n"); + break; + } + + if (cs >= info->nce) { + dev_err(dev, "Chip select %d out of range.\n", + cs); + ret = -ERANGE; + break; + } + + if (controller->chips[cs]) { + dev_err(dev, "Chip select %d already in use by %s\n", + cs, dev_name(controller->chips[cs]->nor.dev)); + ret = -EBUSY; + break; + } + + chip = devm_kzalloc(controller->dev, sizeof(*chip), GFP_KERNEL); + if (!chip) { + ret = -ENOMEM; + break; + } + + chip->controller = controller; + chip->ctl = controller->regs + info->ctl0 + cs * 4; + chip->cs = cs; + + nor = &chip->nor; + mtd = &nor->mtd; + + nor->dev = dev; + nor->priv = chip; + spi_nor_set_flash_node(nor, child); + nor->read = aspeed_smc_read_user; + nor->write = aspeed_smc_write_user; + nor->read_reg = aspeed_smc_read_reg; + nor->write_reg = aspeed_smc_write_reg; + nor->prepare = aspeed_smc_prep; + nor->unprepare = aspeed_smc_unprep; + + ret = aspeed_smc_chip_setup_init(chip, r); + if (ret) + break; + + /* + * TODO: Add support for SPI_NOR_QUAD and SPI_NOR_DUAL + * attach when board support is present as determined + * by of property. + */ + ret = spi_nor_scan(nor, NULL, SPI_NOR_NORMAL); + if (ret) + break; + + ret = aspeed_smc_chip_setup_finish(chip); + if (ret) + break; + + ret = mtd_device_register(mtd, NULL, 0); + if (ret) + break; + + controller->chips[cs] = chip; + } + + if (ret) + aspeed_smc_unregister(controller); + + return ret; +} + +static int aspeed_smc_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct device *dev = &pdev->dev; + struct aspeed_smc_controller *controller; + const struct of_device_id *match; + const struct aspeed_smc_info *info; + struct resource *res; + int ret; + + match = of_match_device(aspeed_smc_matches, &pdev->dev); + if (!match || !match->data) + return -ENODEV; + info = match->data; + + controller = devm_kzalloc(&pdev->dev, sizeof(*controller) + + info->nce * sizeof(controller->chips[0]), GFP_KERNEL); + if (!controller) + return -ENOMEM; + controller->info = info; + controller->dev = dev; + + mutex_init(&controller->mutex); + platform_set_drvdata(pdev, controller); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + controller->regs = devm_ioremap_resource(dev, res); + if (IS_ERR(controller->regs)) + return PTR_ERR(controller->regs); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + controller->ahb_base = devm_ioremap_resource(dev, res); + if (IS_ERR(controller->ahb_base)) + return PTR_ERR(controller->ahb_base); + + ret = aspeed_smc_setup_flash(controller, np, res); + if (ret) + dev_err(dev, "Aspeed SMC probe failed %d\n", ret); + + return ret; +} + +static struct platform_driver aspeed_smc_driver = { + .probe = aspeed_smc_probe, + .remove = aspeed_smc_remove, + .driver = { + .name = DEVICE_NAME, + .of_match_table = aspeed_smc_matches, + } +}; + +module_platform_driver(aspeed_smc_driver); + +MODULE_DESCRIPTION("ASPEED Static Memory Controller Driver"); +MODULE_AUTHOR("Cedric Le Goater <clg@kaod.org>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index d489fbd07c12..9f8102de1b16 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -526,7 +526,8 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor, bytes_to_read *= cqspi->fifo_width; bytes_to_read = bytes_to_read > remaining ? remaining : bytes_to_read; - readsl(ahb_base, rxbuf, DIV_ROUND_UP(bytes_to_read, 4)); + ioread32_rep(ahb_base, rxbuf, + DIV_ROUND_UP(bytes_to_read, 4)); rxbuf += bytes_to_read; remaining -= bytes_to_read; bytes_to_read = cqspi_get_rd_sram_level(cqspi); @@ -610,7 +611,8 @@ static int cqspi_indirect_write_execute(struct spi_nor *nor, while (remaining > 0) { write_bytes = remaining > page_size ? page_size : remaining; - writesl(cqspi->ahb_base, txbuf, DIV_ROUND_UP(write_bytes, 4)); + iowrite32_rep(cqspi->ahb_base, txbuf, + DIV_ROUND_UP(write_bytes, 4)); ret = wait_for_completion_timeout(&cqspi->transfer_complete, msecs_to_jiffies @@ -891,7 +893,7 @@ static ssize_t cqspi_write(struct spi_nor *nor, loff_t to, if (ret) return ret; - return (ret < 0) ? ret : len; + return len; } static ssize_t cqspi_read(struct spi_nor *nor, loff_t from, @@ -911,7 +913,7 @@ static ssize_t cqspi_read(struct spi_nor *nor, loff_t from, if (ret) return ret; - return (ret < 0) ? ret : len; + return len; } static int cqspi_erase(struct spi_nor *nor, loff_t offs) diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c index b4d8953fb30a..1476135e0d50 100644 --- a/drivers/mtd/spi-nor/fsl-quadspi.c +++ b/drivers/mtd/spi-nor/fsl-quadspi.c @@ -193,7 +193,7 @@ #define QUADSPI_LUT_NUM 64 /* SEQID -- we can have 16 seqids at most. */ -#define SEQID_QUAD_READ 0 +#define SEQID_READ 0 #define SEQID_WREN 1 #define SEQID_WRDI 2 #define SEQID_RDSR 3 @@ -373,32 +373,26 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q) void __iomem *base = q->iobase; int rxfifo = q->devtype_data->rxfifo; u32 lut_base; - u8 cmd, addrlen, dummy; int i; + struct spi_nor *nor = &q->nor[0]; + u8 addrlen = (nor->addr_width == 3) ? ADDR24BIT : ADDR32BIT; + u8 read_op = nor->read_opcode; + u8 read_dm = nor->read_dummy; + fsl_qspi_unlock_lut(q); /* Clear all the LUT table */ for (i = 0; i < QUADSPI_LUT_NUM; i++) qspi_writel(q, 0, base + QUADSPI_LUT_BASE + i * 4); - /* Quad Read */ - lut_base = SEQID_QUAD_READ * 4; - - if (q->nor_size <= SZ_16M) { - cmd = SPINOR_OP_READ_1_1_4; - addrlen = ADDR24BIT; - dummy = 8; - } else { - /* use the 4-byte address */ - cmd = SPINOR_OP_READ_1_1_4; - addrlen = ADDR32BIT; - dummy = 8; - } + /* Read */ + lut_base = SEQID_READ * 4; - qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen), + qspi_writel(q, LUT0(CMD, PAD1, read_op) | LUT1(ADDR, PAD1, addrlen), base + QUADSPI_LUT(lut_base)); - qspi_writel(q, LUT0(DUMMY, PAD1, dummy) | LUT1(FSL_READ, PAD4, rxfifo), + qspi_writel(q, LUT0(DUMMY, PAD1, read_dm) | + LUT1(FSL_READ, PAD4, rxfifo), base + QUADSPI_LUT(lut_base + 1)); /* Write enable */ @@ -409,16 +403,8 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q) /* Page Program */ lut_base = SEQID_PP * 4; - if (q->nor_size <= SZ_16M) { - cmd = SPINOR_OP_PP; - addrlen = ADDR24BIT; - } else { - /* use the 4-byte address */ - cmd = SPINOR_OP_PP; - addrlen = ADDR32BIT; - } - - qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen), + qspi_writel(q, LUT0(CMD, PAD1, nor->program_opcode) | + LUT1(ADDR, PAD1, addrlen), base + QUADSPI_LUT(lut_base)); qspi_writel(q, LUT0(FSL_WRITE, PAD1, 0), base + QUADSPI_LUT(lut_base + 1)); @@ -432,10 +418,8 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q) /* Erase a sector */ lut_base = SEQID_SE * 4; - cmd = q->nor[0].erase_opcode; - addrlen = q->nor_size <= SZ_16M ? ADDR24BIT : ADDR32BIT; - - qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen), + qspi_writel(q, LUT0(CMD, PAD1, nor->erase_opcode) | + LUT1(ADDR, PAD1, addrlen), base + QUADSPI_LUT(lut_base)); /* Erase the whole chip */ @@ -484,7 +468,7 @@ static int fsl_qspi_get_seqid(struct fsl_qspi *q, u8 cmd) { switch (cmd) { case SPINOR_OP_READ_1_1_4: - return SEQID_QUAD_READ; + return SEQID_READ; case SPINOR_OP_WREN: return SEQID_WREN; case SPINOR_OP_WRDI: diff --git a/drivers/mtd/spi-nor/intel-spi-platform.c b/drivers/mtd/spi-nor/intel-spi-platform.c new file mode 100644 index 000000000000..5c943df9398f --- /dev/null +++ b/drivers/mtd/spi-nor/intel-spi-platform.c @@ -0,0 +1,57 @@ +/* + * Intel PCH/PCU SPI flash platform driver. + * + * Copyright (C) 2016, Intel Corporation + * Author: Mika Westerberg <mika.westerberg@linux.intel.com> + * + * 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. + */ + +#include <linux/ioport.h> +#include <linux/module.h> +#include <linux/platform_device.h> + +#include "intel-spi.h" + +static int intel_spi_platform_probe(struct platform_device *pdev) +{ + struct intel_spi_boardinfo *info; + struct intel_spi *ispi; + struct resource *mem; + + info = dev_get_platdata(&pdev->dev); + if (!info) + return -EINVAL; + + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + ispi = intel_spi_probe(&pdev->dev, mem, info); + if (IS_ERR(ispi)) + return PTR_ERR(ispi); + + platform_set_drvdata(pdev, ispi); + return 0; +} + +static int intel_spi_platform_remove(struct platform_device *pdev) +{ + struct intel_spi *ispi = platform_get_drvdata(pdev); + + return intel_spi_remove(ispi); +} + +static struct platform_driver intel_spi_platform_driver = { + .probe = intel_spi_platform_probe, + .remove = intel_spi_platform_remove, + .driver = { + .name = "intel-spi", + }, +}; + +module_platform_driver(intel_spi_platform_driver); + +MODULE_DESCRIPTION("Intel PCH/PCU SPI flash platform driver"); +MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:intel-spi"); diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c new file mode 100644 index 000000000000..a10f6027b386 --- /dev/null +++ b/drivers/mtd/spi-nor/intel-spi.c @@ -0,0 +1,777 @@ +/* + * Intel PCH/PCU SPI flash driver. + * + * Copyright (C) 2016, Intel Corporation + * Author: Mika Westerberg <mika.westerberg@linux.intel.com> + * + * 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. + */ + +#include <linux/err.h> +#include <linux/io.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/sizes.h> +#include <linux/mtd/mtd.h> +#include <linux/mtd/partitions.h> +#include <linux/mtd/spi-nor.h> +#include <linux/platform_data/intel-spi.h> + +#include "intel-spi.h" + +/* Offsets are from @ispi->base */ +#define BFPREG 0x00 + +#define HSFSTS_CTL 0x04 +#define HSFSTS_CTL_FSMIE BIT(31) +#define HSFSTS_CTL_FDBC_SHIFT 24 +#define HSFSTS_CTL_FDBC_MASK (0x3f << HSFSTS_CTL_FDBC_SHIFT) + +#define HSFSTS_CTL_FCYCLE_SHIFT 17 +#define HSFSTS_CTL_FCYCLE_MASK (0x0f << HSFSTS_CTL_FCYCLE_SHIFT) +/* HW sequencer opcodes */ +#define HSFSTS_CTL_FCYCLE_READ (0x00 << HSFSTS_CTL_FCYCLE_SHIFT) +#define HSFSTS_CTL_FCYCLE_WRITE (0x02 << HSFSTS_CTL_FCYCLE_SHIFT) +#define HSFSTS_CTL_FCYCLE_ERASE (0x03 << HSFSTS_CTL_FCYCLE_SHIFT) +#define HSFSTS_CTL_FCYCLE_ERASE_64K (0x04 << HSFSTS_CTL_FCYCLE_SHIFT) +#define HSFSTS_CTL_FCYCLE_RDID (0x06 << HSFSTS_CTL_FCYCLE_SHIFT) +#define HSFSTS_CTL_FCYCLE_WRSR (0x07 << HSFSTS_CTL_FCYCLE_SHIFT) +#define HSFSTS_CTL_FCYCLE_RDSR (0x08 << HSFSTS_CTL_FCYCLE_SHIFT) + +#define HSFSTS_CTL_FGO BIT(16) +#define HSFSTS_CTL_FLOCKDN BIT(15) +#define HSFSTS_CTL_FDV BIT(14) +#define HSFSTS_CTL_SCIP BIT(5) +#define HSFSTS_CTL_AEL BIT(2) +#define HSFSTS_CTL_FCERR BIT(1) +#define HSFSTS_CTL_FDONE BIT(0) + +#define FADDR 0x08 +#define DLOCK 0x0c +#define FDATA(n) (0x10 + ((n) * 4)) + +#define FRACC 0x50 + +#define FREG(n) (0x54 + ((n) * 4)) +#define FREG_BASE_MASK 0x3fff +#define FREG_LIMIT_SHIFT 16 +#define FREG_LIMIT_MASK (0x03fff << FREG_LIMIT_SHIFT) + +/* Offset is from @ispi->pregs */ +#define PR(n) ((n) * 4) +#define PR_WPE BIT(31) +#define PR_LIMIT_SHIFT 16 +#define PR_LIMIT_MASK (0x3fff << PR_LIMIT_SHIFT) +#define PR_RPE BIT(15) +#define PR_BASE_MASK 0x3fff +/* Last PR is GPR0 */ +#define PR_NUM (5 + 1) + +/* Offsets are from @ispi->sregs */ +#define SSFSTS_CTL 0x00 +#define SSFSTS_CTL_FSMIE BIT(23) +#define SSFSTS_CTL_DS BIT(22) +#define SSFSTS_CTL_DBC_SHIFT 16 +#define SSFSTS_CTL_SPOP BIT(11) +#define SSFSTS_CTL_ACS BIT(10) +#define SSFSTS_CTL_SCGO BIT(9) +#define SSFSTS_CTL_COP_SHIFT 12 +#define SSFSTS_CTL_FRS BIT(7) +#define SSFSTS_CTL_DOFRS BIT(6) +#define SSFSTS_CTL_AEL BIT(4) +#define SSFSTS_CTL_FCERR BIT(3) +#define SSFSTS_CTL_FDONE BIT(2) +#define SSFSTS_CTL_SCIP BIT(0) + +#define PREOP_OPTYPE 0x04 +#define OPMENU0 0x08 +#define OPMENU1 0x0c + +/* CPU specifics */ +#define BYT_PR 0x74 +#define BYT_SSFSTS_CTL 0x90 +#define BYT_BCR 0xfc +#define BYT_BCR_WPD BIT(0) +#define BYT_FREG_NUM 5 + +#define LPT_PR 0x74 +#define LPT_SSFSTS_CTL 0x90 +#define LPT_FREG_NUM 5 + +#define BXT_PR 0x84 +#define BXT_SSFSTS_CTL 0xa0 +#define BXT_FREG_NUM 12 + +#define INTEL_SPI_TIMEOUT 5000 /* ms */ +#define INTEL_SPI_FIFO_SZ 64 + +/** + * struct intel_spi - Driver private data + * @dev: Device pointer + * @info: Pointer to board specific info + * @nor: SPI NOR layer structure + * @base: Beginning of MMIO space + * @pregs: Start of protection registers + * @sregs: Start of software sequencer registers + * @nregions: Maximum number of regions + * @writeable: Is the chip writeable + * @swseq: Use SW sequencer in register reads/writes + * @erase_64k: 64k erase supported + * @opcodes: Opcodes which are supported. This are programmed by BIOS + * before it locks down the controller. + * @preopcodes: Preopcodes which are supported. + */ +struct intel_spi { + struct device *dev; + const struct intel_spi_boardinfo *info; + struct spi_nor nor; + void __iomem *base; + void __iomem *pregs; + void __iomem *sregs; + size_t nregions; + bool writeable; + bool swseq; + bool erase_64k; + u8 opcodes[8]; + u8 preopcodes[2]; +}; + +static bool writeable; +module_param(writeable, bool, 0); +MODULE_PARM_DESC(writeable, "Enable write access to SPI flash chip (default=0)"); + +static void intel_spi_dump_regs(struct intel_spi *ispi) +{ + u32 value; + int i; + + dev_dbg(ispi->dev, "BFPREG=0x%08x\n", readl(ispi->base + BFPREG)); + + value = readl(ispi->base + HSFSTS_CTL); + dev_dbg(ispi->dev, "HSFSTS_CTL=0x%08x\n", value); + if (value & HSFSTS_CTL_FLOCKDN) + dev_dbg(ispi->dev, "-> Locked\n"); + + dev_dbg(ispi->dev, "FADDR=0x%08x\n", readl(ispi->base + FADDR)); + dev_dbg(ispi->dev, "DLOCK=0x%08x\n", readl(ispi->base + DLOCK)); + + for (i = 0; i < 16; i++) + dev_dbg(ispi->dev, "FDATA(%d)=0x%08x\n", + i, readl(ispi->base + FDATA(i))); + + dev_dbg(ispi->dev, "FRACC=0x%08x\n", readl(ispi->base + FRACC)); + + for (i = 0; i < ispi->nregions; i++) + dev_dbg(ispi->dev, "FREG(%d)=0x%08x\n", i, + readl(ispi->base + FREG(i))); + for (i = 0; i < PR_NUM; i++) + dev_dbg(ispi->dev, "PR(%d)=0x%08x\n", i, + readl(ispi->pregs + PR(i))); + + value = readl(ispi->sregs + SSFSTS_CTL); + dev_dbg(ispi->dev, "SSFSTS_CTL=0x%08x\n", value); + dev_dbg(ispi->dev, "PREOP_OPTYPE=0x%08x\n", + readl(ispi->sregs + PREOP_OPTYPE)); + dev_dbg(ispi->dev, "OPMENU0=0x%08x\n", readl(ispi->sregs + OPMENU0)); + dev_dbg(ispi->dev, "OPMENU1=0x%08x\n", readl(ispi->sregs + OPMENU1)); + + if (ispi->info->type == INTEL_SPI_BYT) + dev_dbg(ispi->dev, "BCR=0x%08x\n", readl(ispi->base + BYT_BCR)); + + dev_dbg(ispi->dev, "Protected regions:\n"); + for (i = 0; i < PR_NUM; i++) { + u32 base, limit; + + value = readl(ispi->pregs + PR(i)); + if (!(value & (PR_WPE | PR_RPE))) + continue; + + limit = (value & PR_LIMIT_MASK) >> PR_LIMIT_SHIFT; + base = value & PR_BASE_MASK; + + dev_dbg(ispi->dev, " %02d base: 0x%08x limit: 0x%08x [%c%c]\n", + i, base << 12, (limit << 12) | 0xfff, + value & PR_WPE ? 'W' : '.', + value & PR_RPE ? 'R' : '.'); + } + + dev_dbg(ispi->dev, "Flash regions:\n"); + for (i = 0; i < ispi->nregions; i++) { + u32 region, base, limit; + + region = readl(ispi->base + FREG(i)); + base = region & FREG_BASE_MASK; + limit = (region & FREG_LIMIT_MASK) >> FREG_LIMIT_SHIFT; + + if (base >= limit || (i > 0 && limit == 0)) + dev_dbg(ispi->dev, " %02d disabled\n", i); + else + dev_dbg(ispi->dev, " %02d base: 0x%08x limit: 0x%08x\n", + i, base << 12, (limit << 12) | 0xfff); + } + + dev_dbg(ispi->dev, "Using %cW sequencer for register access\n", + ispi->swseq ? 'S' : 'H'); +} + +/* Reads max INTEL_SPI_FIFO_SZ bytes from the device fifo */ +static int intel_spi_read_block(struct intel_spi *ispi, void *buf, size_t size) +{ + size_t bytes; + int i = 0; + + if (size > INTEL_SPI_FIFO_SZ) + return -EINVAL; + + while (size > 0) { + bytes = min_t(size_t, size, 4); + memcpy_fromio(buf, ispi->base + FDATA(i), bytes); + size -= bytes; + buf += bytes; + i++; + } + + return 0; +} + +/* Writes max INTEL_SPI_FIFO_SZ bytes to the device fifo */ +static int intel_spi_write_block(struct intel_spi *ispi, const void *buf, + size_t size) +{ + size_t bytes; + int i = 0; + + if (size > INTEL_SPI_FIFO_SZ) + return -EINVAL; + + while (size > 0) { + bytes = min_t(size_t, size, 4); + memcpy_toio(ispi->base + FDATA(i), buf, bytes); + size -= bytes; + buf += bytes; + i++; + } + + return 0; +} + +static int intel_spi_wait_hw_busy(struct intel_spi *ispi) +{ + u32 val; + + return readl_poll_timeout(ispi->base + HSFSTS_CTL, val, + !(val & HSFSTS_CTL_SCIP), 0, + INTEL_SPI_TIMEOUT * 1000); +} + +static int intel_spi_wait_sw_busy(struct intel_spi *ispi) +{ + u32 val; + + return readl_poll_timeout(ispi->sregs + SSFSTS_CTL, val, + !(val & SSFSTS_CTL_SCIP), 0, + INTEL_SPI_TIMEOUT * 1000); +} + +static int intel_spi_init(struct intel_spi *ispi) +{ + u32 opmenu0, opmenu1, val; + int i; + + switch (ispi->info->type) { + case INTEL_SPI_BYT: + ispi->sregs = ispi->base + BYT_SSFSTS_CTL; + ispi->pregs = ispi->base + BYT_PR; + ispi->nregions = BYT_FREG_NUM; + + if (writeable) { + /* Disable write protection */ + val = readl(ispi->base + BYT_BCR); + if (!(val & BYT_BCR_WPD)) { + val |= BYT_BCR_WPD; + writel(val, ispi->base + BYT_BCR); + val = readl(ispi->base + BYT_BCR); + } + + ispi->writeable = !!(val & BYT_BCR_WPD); + } + + break; + + case INTEL_SPI_LPT: + ispi->sregs = ispi->base + LPT_SSFSTS_CTL; + ispi->pregs = ispi->base + LPT_PR; + ispi->nregions = LPT_FREG_NUM; + break; + + case INTEL_SPI_BXT: + ispi->sregs = ispi->base + BXT_SSFSTS_CTL; + ispi->pregs = ispi->base + BXT_PR; + ispi->nregions = BXT_FREG_NUM; + ispi->erase_64k = true; + break; + + default: + return -EINVAL; + } + + /* Disable #SMI generation */ + val = readl(ispi->base + HSFSTS_CTL); + val &= ~HSFSTS_CTL_FSMIE; + writel(val, ispi->base + HSFSTS_CTL); + + /* + * BIOS programs allowed opcodes and then locks down the register. + * So read back what opcodes it decided to support. That's the set + * we are going to support as well. + */ + opmenu0 = readl(ispi->sregs + OPMENU0); + opmenu1 = readl(ispi->sregs + OPMENU1); + + /* + * Some controllers can only do basic operations using hardware + * sequencer. All other operations are supposed to be carried out + * using software sequencer. If we find that BIOS has programmed + * opcodes for the software sequencer we use that over the hardware + * sequencer. + */ + if (opmenu0 && opmenu1) { + for (i = 0; i < ARRAY_SIZE(ispi->opcodes) / 2; i++) { + ispi->opcodes[i] = opmenu0 >> i * 8; + ispi->opcodes[i + 4] = opmenu1 >> i * 8; + } + + val = readl(ispi->sregs + PREOP_OPTYPE); + ispi->preopcodes[0] = val; + ispi->preopcodes[1] = val >> 8; + + /* Disable #SMI generation from SW sequencer */ + val = readl(ispi->sregs + SSFSTS_CTL); + val &= ~SSFSTS_CTL_FSMIE; + writel(val, ispi->sregs + SSFSTS_CTL); + + ispi->swseq = true; + } + + intel_spi_dump_regs(ispi); + + return 0; +} + +static int intel_spi_opcode_index(struct intel_spi *ispi, u8 opcode) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(ispi->opcodes); i++) + if (ispi->opcodes[i] == opcode) + return i; + return -EINVAL; +} + +static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf, + int len) +{ + u32 val, status; + int ret; + + val = readl(ispi->base + HSFSTS_CTL); + val &= ~(HSFSTS_CTL_FCYCLE_MASK | HSFSTS_CTL_FDBC_MASK); + + switch (opcode) { + case SPINOR_OP_RDID: + val |= HSFSTS_CTL_FCYCLE_RDID; + break; + case SPINOR_OP_WRSR: + val |= HSFSTS_CTL_FCYCLE_WRSR; + break; + case SPINOR_OP_RDSR: + val |= HSFSTS_CTL_FCYCLE_RDSR; + break; + default: + return -EINVAL; + } + + val |= (len - 1) << HSFSTS_CTL_FDBC_SHIFT; + val |= HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE; + val |= HSFSTS_CTL_FGO; + writel(val, ispi->base + HSFSTS_CTL); + + ret = intel_spi_wait_hw_busy(ispi); + if (ret) + return ret; + + status = readl(ispi->base + HSFSTS_CTL); + if (status & HSFSTS_CTL_FCERR) + return -EIO; + else if (status & HSFSTS_CTL_AEL) + return -EACCES; + + return 0; +} + +static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf, + int len) +{ + u32 val, status; + int ret; + + ret = intel_spi_opcode_index(ispi, opcode); + if (ret < 0) + return ret; + + val = (len << SSFSTS_CTL_DBC_SHIFT) | SSFSTS_CTL_DS; + val |= ret << SSFSTS_CTL_COP_SHIFT; + val |= SSFSTS_CTL_FCERR | SSFSTS_CTL_FDONE; + val |= SSFSTS_CTL_SCGO; + writel(val, ispi->sregs + SSFSTS_CTL); + + ret = intel_spi_wait_sw_busy(ispi); + if (ret) + return ret; + + status = readl(ispi->base + SSFSTS_CTL); + if (status & SSFSTS_CTL_FCERR) + return -EIO; + else if (status & SSFSTS_CTL_AEL) + return -EACCES; + + return 0; +} + +static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +{ + struct intel_spi *ispi = nor->priv; + int ret; + + /* Address of the first chip */ + writel(0, ispi->base + FADDR); + + if (ispi->swseq) + ret = intel_spi_sw_cycle(ispi, opcode, buf, len); + else + ret = intel_spi_hw_cycle(ispi, opcode, buf, len); + + if (ret) + return ret; + + return intel_spi_read_block(ispi, buf, len); +} + +static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +{ + struct intel_spi *ispi = nor->priv; + int ret; + + /* + * This is handled with atomic operation and preop code in Intel + * controller so skip it here now. + */ + if (opcode == SPINOR_OP_WREN) + return 0; + + writel(0, ispi->base + FADDR); + + /* Write the value beforehand */ + ret = intel_spi_write_block(ispi, buf, len); + if (ret) + return ret; + + if (ispi->swseq) + return intel_spi_sw_cycle(ispi, opcode, buf, len); + return intel_spi_hw_cycle(ispi, opcode, buf, len); +} + +static ssize_t intel_spi_read(struct spi_nor *nor, loff_t from, size_t len, + u_char *read_buf) +{ + struct intel_spi *ispi = nor->priv; + size_t block_size, retlen = 0; + u32 val, status; + ssize_t ret; + + switch (nor->read_opcode) { + case SPINOR_OP_READ: + case SPINOR_OP_READ_FAST: + break; + default: + return -EINVAL; + } + + while (len > 0) { + block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ); + + writel(from, ispi->base + FADDR); + + val = readl(ispi->base + HSFSTS_CTL); + val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK); + val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE; + val |= (block_size - 1) << HSFSTS_CTL_FDBC_SHIFT; + val |= HSFSTS_CTL_FCYCLE_READ; + val |= HSFSTS_CTL_FGO; + writel(val, ispi->base + HSFSTS_CTL); + + ret = intel_spi_wait_hw_busy(ispi); + if (ret) + return ret; + + status = readl(ispi->base + HSFSTS_CTL); + if (status & HSFSTS_CTL_FCERR) + ret = -EIO; + else if (status & HSFSTS_CTL_AEL) + ret = -EACCES; + + if (ret < 0) { + dev_err(ispi->dev, "read error: %llx: %#x\n", from, + status); + return ret; + } + + ret = intel_spi_read_block(ispi, read_buf, block_size); + if (ret) + return ret; + + len -= block_size; + from += block_size; + retlen += block_size; + read_buf += block_size; + } + + return retlen; +} + +static ssize_t intel_spi_write(struct spi_nor *nor, loff_t to, size_t len, + const u_char *write_buf) +{ + struct intel_spi *ispi = nor->priv; + size_t block_size, retlen = 0; + u32 val, status; + ssize_t ret; + + while (len > 0) { + block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ); + + writel(to, ispi->base + FADDR); + + val = readl(ispi->base + HSFSTS_CTL); + val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK); + val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE; + val |= (block_size - 1) << HSFSTS_CTL_FDBC_SHIFT; + val |= HSFSTS_CTL_FCYCLE_WRITE; + + /* Write enable */ + if (ispi->preopcodes[1] == SPINOR_OP_WREN) + val |= SSFSTS_CTL_SPOP; + val |= SSFSTS_CTL_ACS; + writel(val, ispi->base + HSFSTS_CTL); + + ret = intel_spi_write_block(ispi, write_buf, block_size); + if (ret) { + dev_err(ispi->dev, "failed to write block\n"); + return ret; + } + + /* Start the write now */ + val = readl(ispi->base + HSFSTS_CTL); + writel(val | HSFSTS_CTL_FGO, ispi->base + HSFSTS_CTL); + + ret = intel_spi_wait_hw_busy(ispi); + if (ret) { + dev_err(ispi->dev, "timeout\n"); + return ret; + } + + status = readl(ispi->base + HSFSTS_CTL); + if (status & HSFSTS_CTL_FCERR) + ret = -EIO; + else if (status & HSFSTS_CTL_AEL) + ret = -EACCES; + + if (ret < 0) { + dev_err(ispi->dev, "write error: %llx: %#x\n", to, + status); + return ret; + } + + len -= block_size; + to += block_size; + retlen += block_size; + write_buf += block_size; + } + + return retlen; +} + +static int intel_spi_erase(struct spi_nor *nor, loff_t offs) +{ + size_t erase_size, len = nor->mtd.erasesize; + struct intel_spi *ispi = nor->priv; + u32 val, status, cmd; + int ret; + + /* If the hardware can do 64k erase use that when possible */ + if (len >= SZ_64K && ispi->erase_64k) { + cmd = HSFSTS_CTL_FCYCLE_ERASE_64K; + erase_size = SZ_64K; + } else { + cmd = HSFSTS_CTL_FCYCLE_ERASE; + erase_size = SZ_4K; + } + + while (len > 0) { + writel(offs, ispi->base + FADDR); + + val = readl(ispi->base + HSFSTS_CTL); + val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK); + val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE; + val |= cmd; + val |= HSFSTS_CTL_FGO; + writel(val, ispi->base + HSFSTS_CTL); + + ret = intel_spi_wait_hw_busy(ispi); + if (ret) + return ret; + + status = readl(ispi->base + HSFSTS_CTL); + if (status & HSFSTS_CTL_FCERR) + return -EIO; + else if (status & HSFSTS_CTL_AEL) + return -EACCES; + + offs += erase_size; + len -= erase_size; + } + + return 0; +} + +static bool intel_spi_is_protected(const struct intel_spi *ispi, + unsigned int base, unsigned int limit) +{ + int i; + + for (i = 0; i < PR_NUM; i++) { + u32 pr_base, pr_limit, pr_value; + + pr_value = readl(ispi->pregs + PR(i)); + if (!(pr_value & (PR_WPE | PR_RPE))) + continue; + + pr_limit = (pr_value & PR_LIMIT_MASK) >> PR_LIMIT_SHIFT; + pr_base = pr_value & PR_BASE_MASK; + + if (pr_base >= base && pr_limit <= limit) + return true; + } + + return false; +} + +/* + * There will be a single partition holding all enabled flash regions. We + * call this "BIOS". + */ +static void intel_spi_fill_partition(struct intel_spi *ispi, + struct mtd_partition *part) +{ + u64 end; + int i; + + memset(part, 0, sizeof(*part)); + + /* Start from the mandatory descriptor region */ + part->size = 4096; + part->name = "BIOS"; + + /* + * Now try to find where this partition ends based on the flash + * region registers. + */ + for (i = 1; i < ispi->nregions; i++) { + u32 region, base, limit; + + region = readl(ispi->base + FREG(i)); + base = region & FREG_BASE_MASK; + limit = (region & FREG_LIMIT_MASK) >> FREG_LIMIT_SHIFT; + + if (base >= limit || limit == 0) + continue; + + /* + * If any of the regions have protection bits set, make the + * whole partition read-only to be on the safe side. + */ + if (intel_spi_is_protected(ispi, base, limit)) + ispi->writeable = 0; + + end = (limit << 12) + 4096; + if (end > part->size) + part->size = end; + } +} + +struct intel_spi *intel_spi_probe(struct device *dev, + struct resource *mem, const struct intel_spi_boardinfo *info) +{ + struct mtd_partition part; + struct intel_spi *ispi; + int ret; + + if (!info || !mem) + return ERR_PTR(-EINVAL); + + ispi = devm_kzalloc(dev, sizeof(*ispi), GFP_KERNEL); + if (!ispi) + return ERR_PTR(-ENOMEM); + + ispi->base = devm_ioremap_resource(dev, mem); + if (IS_ERR(ispi->base)) + return ispi->base; + + ispi->dev = dev; + ispi->info = info; + ispi->writeable = info->writeable; + + ret = intel_spi_init(ispi); + if (ret) + return ERR_PTR(ret); + + ispi->nor.dev = ispi->dev; + ispi->nor.priv = ispi; + ispi->nor.read_reg = intel_spi_read_reg; + ispi->nor.write_reg = intel_spi_write_reg; + ispi->nor.read = intel_spi_read; + ispi->nor.write = intel_spi_write; + ispi->nor.erase = intel_spi_erase; + + ret = spi_nor_scan(&ispi->nor, NULL, SPI_NOR_NORMAL); + if (ret) { + dev_info(dev, "failed to locate the chip\n"); + return ERR_PTR(ret); + } + + intel_spi_fill_partition(ispi, &part); + + /* Prevent writes if not explicitly enabled */ + if (!ispi->writeable || !writeable) + ispi->nor.mtd.flags &= ~MTD_WRITEABLE; + + ret = mtd_device_parse_register(&ispi->nor.mtd, NULL, NULL, &part, 1); + if (ret) + return ERR_PTR(ret); + + return ispi; +} +EXPORT_SYMBOL_GPL(intel_spi_probe); + +int intel_spi_remove(struct intel_spi *ispi) +{ + return mtd_device_unregister(&ispi->nor.mtd); +} +EXPORT_SYMBOL_GPL(intel_spi_remove); + +MODULE_DESCRIPTION("Intel PCH/PCU SPI flash core driver"); +MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mtd/spi-nor/intel-spi.h b/drivers/mtd/spi-nor/intel-spi.h new file mode 100644 index 000000000000..5ab7dc250050 --- /dev/null +++ b/drivers/mtd/spi-nor/intel-spi.h @@ -0,0 +1,24 @@ +/* + * Intel PCH/PCU SPI flash driver. + * + * Copyright (C) 2016, Intel Corporation + * Author: Mika Westerberg <mika.westerberg@linux.intel.com> + * + * 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. + */ + +#ifndef INTEL_SPI_H +#define INTEL_SPI_H + +#include <linux/platform_data/intel-spi.h> + +struct intel_spi; +struct resource; + +struct intel_spi *intel_spi_probe(struct device *dev, + struct resource *mem, const struct intel_spi_boardinfo *info); +int intel_spi_remove(struct intel_spi *ispi); + +#endif /* INTEL_SPI_H */ diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index da7cd69d4857..1ae872bfc3ba 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -75,6 +75,16 @@ struct flash_info { * bit. Must be used with * SPI_NOR_HAS_LOCK. */ +#define SPI_S3AN BIT(10) /* + * Xilinx Spartan 3AN In-System Flash + * (MFR cannot be used for probing + * because it has the same value as + * ATMEL flashes) + */ +#define SPI_NOR_4B_OPCODES BIT(11) /* + * Use dedicated 4byte address op codes + * to support memory size above 128Mib. + */ }; #define JEDEC_MFR(info) ((info)->id[0]) @@ -122,7 +132,7 @@ static int read_fsr(struct spi_nor *nor) /* * Read configuration register, returning its value in the * location. Return the configuration register value. - * Returns negative if error occured. + * Returns negative if error occurred. */ static int read_cr(struct spi_nor *nor) { @@ -188,6 +198,78 @@ static inline struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd) return mtd->priv; } + +static u8 spi_nor_convert_opcode(u8 opcode, const u8 table[][2], size_t size) +{ + size_t i; + + for (i = 0; i < size; i++) + if (table[i][0] == opcode) + return table[i][1]; + + /* No conversion found, keep input op code. */ + return opcode; +} + +static inline u8 spi_nor_convert_3to4_read(u8 opcode) +{ + static const u8 spi_nor_3to4_read[][2] = { + { SPINOR_OP_READ, SPINOR_OP_READ_4B }, + { SPINOR_OP_READ_FAST, SPINOR_OP_READ_FAST_4B }, + { SPINOR_OP_READ_1_1_2, SPINOR_OP_READ_1_1_2_4B }, + { SPINOR_OP_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B }, + { SPINOR_OP_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B }, + { SPINOR_OP_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B }, + }; + + return spi_nor_convert_opcode(opcode, spi_nor_3to4_read, + ARRAY_SIZE(spi_nor_3to4_read)); +} + +static inline u8 spi_nor_convert_3to4_program(u8 opcode) +{ + static const u8 spi_nor_3to4_program[][2] = { + { SPINOR_OP_PP, SPINOR_OP_PP_4B }, + { SPINOR_OP_PP_1_1_4, SPINOR_OP_PP_1_1_4_4B }, + { SPINOR_OP_PP_1_4_4, SPINOR_OP_PP_1_4_4_4B }, + }; + + return spi_nor_convert_opcode(opcode, spi_nor_3to4_program, + ARRAY_SIZE(spi_nor_3to4_program)); +} + +static inline u8 spi_nor_convert_3to4_erase(u8 opcode) +{ + static const u8 spi_nor_3to4_erase[][2] = { + { SPINOR_OP_BE_4K, SPINOR_OP_BE_4K_4B }, + { SPINOR_OP_BE_32K, SPINOR_OP_BE_32K_4B }, + { SPINOR_OP_SE, SPINOR_OP_SE_4B }, + }; + + return spi_nor_convert_opcode(opcode, spi_nor_3to4_erase, + ARRAY_SIZE(spi_nor_3to4_erase)); +} + +static void spi_nor_set_4byte_opcodes(struct spi_nor *nor, + const struct flash_info *info) +{ + /* Do some manufacturer fixups first */ + switch (JEDEC_MFR(info)) { + case SNOR_MFR_SPANSION: + /* No small sector erase for 4-byte command set */ + nor->erase_opcode = SPINOR_OP_SE; + nor->mtd.erasesize = info->sector_size; + break; + + default: + break; + } + + nor->read_opcode = spi_nor_convert_3to4_read(nor->read_opcode); + nor->program_opcode = spi_nor_convert_3to4_program(nor->program_opcode); + nor->erase_opcode = spi_nor_convert_3to4_erase(nor->erase_opcode); +} + /* Enable/disable 4-byte addressing mode. */ static inline int set_4byte(struct spi_nor *nor, const struct flash_info *info, int enable) @@ -217,6 +299,21 @@ static inline int set_4byte(struct spi_nor *nor, const struct flash_info *info, return nor->write_reg(nor, SPINOR_OP_BRWR, nor->cmd_buf, 1); } } + +static int s3an_sr_ready(struct spi_nor *nor) +{ + int ret; + u8 val; + + ret = nor->read_reg(nor, SPINOR_OP_XRDSR, &val, 1); + if (ret < 0) { + dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret); + return ret; + } + + return !!(val & XSR_RDY); +} + static inline int spi_nor_sr_ready(struct spi_nor *nor) { int sr = read_sr(nor); @@ -238,7 +335,11 @@ static inline int spi_nor_fsr_ready(struct spi_nor *nor) static int spi_nor_ready(struct spi_nor *nor) { int sr, fsr; - sr = spi_nor_sr_ready(nor); + + if (nor->flags & SNOR_F_READY_XSR_RDY) + sr = s3an_sr_ready(nor); + else + sr = spi_nor_sr_ready(nor); if (sr < 0) return sr; fsr = nor->flags & SNOR_F_USE_FSR ? spi_nor_fsr_ready(nor) : 1; @@ -320,6 +421,27 @@ static void spi_nor_unlock_and_unprep(struct spi_nor *nor, enum spi_nor_ops ops) } /* + * This code converts an address to the Default Address Mode, that has non + * power of two page sizes. We must support this mode because it is the default + * mode supported by Xilinx tools, it can access the whole flash area and + * changing over to the Power-of-two mode is irreversible and corrupts the + * original data. + * Addr can safely be unsigned int, the biggest S3AN device is smaller than + * 4 MiB. + */ +static loff_t spi_nor_s3an_addr_convert(struct spi_nor *nor, unsigned int addr) +{ + unsigned int offset; + unsigned int page; + + offset = addr % nor->page_size; + page = addr / nor->page_size; + page <<= (nor->page_size > 512) ? 10 : 9; + + return page | offset; +} + +/* * Initiate the erasure of a single sector */ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr) @@ -327,6 +449,9 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr) u8 buf[SPI_NOR_MAX_ADDR_WIDTH]; int i; + if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT) + addr = spi_nor_s3an_addr_convert(nor, addr); + if (nor->erase) return nor->erase(nor, addr); @@ -368,7 +493,7 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr) return ret; /* whole-chip erase? */ - if (len == mtd->size) { + if (len == mtd->size && !(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) { unsigned long timeout; write_enable(nor); @@ -782,6 +907,19 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len) .addr_width = (_addr_width), \ .flags = (_flags), +#define S3AN_INFO(_jedec_id, _n_sectors, _page_size) \ + .id = { \ + ((_jedec_id) >> 16) & 0xff, \ + ((_jedec_id) >> 8) & 0xff, \ + (_jedec_id) & 0xff \ + }, \ + .id_len = 3, \ + .sector_size = (8*_page_size), \ + .n_sectors = (_n_sectors), \ + .page_size = _page_size, \ + .addr_width = 3, \ + .flags = SPI_NOR_NO_FR | SPI_S3AN, + /* NOTE: double check command sets and memory organization when you add * more nor chips. This current list focusses on newer chips, which * have been converging on command sets which including JEDEC ID. @@ -821,7 +959,7 @@ static const struct flash_info spi_nor_ids[] = { { "en25s64", INFO(0x1c3817, 0, 64 * 1024, 128, SECT_4K) }, /* ESMT */ - { "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K) }, + { "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K | SPI_NOR_HAS_LOCK) }, /* Everspin */ { "mr25h256", CAT25_INFO( 32 * 1024, 1, 256, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) }, @@ -833,6 +971,11 @@ static const struct flash_info spi_nor_ids[] = { /* GigaDevice */ { + "gd25q16", INFO(0xc84015, 0, 64 * 1024, 32, + SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | + SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB) + }, + { "gd25q32", INFO(0xc84016, 0, 64 * 1024, 64, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB) @@ -1014,6 +1157,13 @@ static const struct flash_info spi_nor_ids[] = { { "cat25c09", CAT25_INFO( 128, 8, 32, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) }, { "cat25c17", CAT25_INFO( 256, 8, 32, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) }, { "cat25128", CAT25_INFO(2048, 8, 64, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) }, + + /* Xilinx S3AN Internal Flash */ + { "3S50AN", S3AN_INFO(0x1f2200, 64, 264) }, + { "3S200AN", S3AN_INFO(0x1f2400, 256, 264) }, + { "3S400AN", S3AN_INFO(0x1f2400, 256, 264) }, + { "3S700AN", S3AN_INFO(0x1f2500, 512, 264) }, + { "3S1400AN", S3AN_INFO(0x1f2600, 512, 528) }, { }, }; @@ -1054,7 +1204,12 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len, return ret; while (len) { - ret = nor->read(nor, from, len, buf); + loff_t addr = from; + + if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT) + addr = spi_nor_s3an_addr_convert(nor, addr); + + ret = nor->read(nor, addr, len, buf); if (ret == 0) { /* We shouldn't see 0-length reads */ ret = -EIO; @@ -1175,17 +1330,32 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len, for (i = 0; i < len; ) { ssize_t written; + loff_t addr = to + i; + + /* + * If page_size is a power of two, the offset can be quickly + * calculated with an AND operation. On the other cases we + * need to do a modulus operation (more expensive). + * Power of two numbers have only one bit set and we can use + * the instruction hweight32 to detect if we need to do a + * modulus (do_div()) or not. + */ + if (hweight32(nor->page_size) == 1) { + page_offset = addr & (nor->page_size - 1); + } else { + uint64_t aux = addr; - page_offset = (to + i) & (nor->page_size - 1); - WARN_ONCE(page_offset, - "Writing at offset %zu into a NOR page. Writing partial pages may decrease reliability and increase wear of NOR flash.", - page_offset); + page_offset = do_div(aux, nor->page_size); + } /* the size of data remaining on the first page */ page_remain = min_t(size_t, nor->page_size - page_offset, len - i); + if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT) + addr = spi_nor_s3an_addr_convert(nor, addr); + write_enable(nor); - ret = nor->write(nor, to + i, page_remain, buf + i); + ret = nor->write(nor, addr, page_remain, buf + i); if (ret < 0) goto write_err; written = ret; @@ -1216,6 +1386,9 @@ static int macronix_quad_enable(struct spi_nor *nor) val = read_sr(nor); if (val < 0) return val; + if (val & SR_QUAD_EN_MX) + return 0; + write_enable(nor); write_sr(nor, val | SR_QUAD_EN_MX); @@ -1236,7 +1409,7 @@ static int macronix_quad_enable(struct spi_nor *nor) * Write status Register and configuration register with 2 bytes * The first byte will be written to the status register, while the * second byte will be written to the configuration register. - * Return negative if error occured. + * Return negative if error occurred. */ static int write_sr_cr(struct spi_nor *nor, u16 val) { @@ -1312,6 +1485,47 @@ static int spi_nor_check(struct spi_nor *nor) return 0; } +static int s3an_nor_scan(const struct flash_info *info, struct spi_nor *nor) +{ + int ret; + u8 val; + + ret = nor->read_reg(nor, SPINOR_OP_XRDSR, &val, 1); + if (ret < 0) { + dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret); + return ret; + } + + nor->erase_opcode = SPINOR_OP_XSE; + nor->program_opcode = SPINOR_OP_XPP; + nor->read_opcode = SPINOR_OP_READ; + nor->flags |= SNOR_F_NO_OP_CHIP_ERASE; + + /* + * This flashes have a page size of 264 or 528 bytes (known as + * Default addressing mode). It can be changed to a more standard + * Power of two mode where the page size is 256/512. This comes + * with a price: there is 3% less of space, the data is corrupted + * and the page size cannot be changed back to default addressing + * mode. + * + * The current addressing mode can be read from the XRDSR register + * and should not be changed, because is a destructive operation. + */ + if (val & XSR_PAGESIZE) { + /* Flash in Power of 2 mode */ + nor->page_size = (nor->page_size == 264) ? 256 : 512; + nor->mtd.writebufsize = nor->page_size; + nor->mtd.size = 8 * nor->page_size * info->n_sectors; + nor->mtd.erasesize = 8 * nor->page_size; + } else { + /* Flash in Default addressing mode */ + nor->flags |= SNOR_F_S3AN_ADDR_DEFAULT; + } + + return 0; +} + int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) { const struct flash_info *info = NULL; @@ -1360,6 +1574,14 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) mutex_init(&nor->lock); /* + * Make sure the XSR_RDY flag is set before calling + * spi_nor_wait_till_ready(). Xilinx S3AN share MFR + * with Atmel spi-nor + */ + if (info->flags & SPI_S3AN) + nor->flags |= SNOR_F_READY_XSR_RDY; + + /* * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up * with the software protection bits set */ @@ -1483,27 +1705,10 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) else if (mtd->size > 0x1000000) { /* enable 4-byte addressing if the device exceeds 16MiB */ nor->addr_width = 4; - if (JEDEC_MFR(info) == SNOR_MFR_SPANSION) { - /* Dedicated 4-byte command set */ - switch (nor->flash_read) { - case SPI_NOR_QUAD: - nor->read_opcode = SPINOR_OP_READ4_1_1_4; - break; - case SPI_NOR_DUAL: - nor->read_opcode = SPINOR_OP_READ4_1_1_2; - break; - case SPI_NOR_FAST: - nor->read_opcode = SPINOR_OP_READ4_FAST; - break; - case SPI_NOR_NORMAL: - nor->read_opcode = SPINOR_OP_READ4; - break; - } - nor->program_opcode = SPINOR_OP_PP_4B; - /* No small sector erase for 4-byte command set */ - nor->erase_opcode = SPINOR_OP_SE_4B; - mtd->erasesize = info->sector_size; - } else + if (JEDEC_MFR(info) == SNOR_MFR_SPANSION || + info->flags & SPI_NOR_4B_OPCODES) + spi_nor_set_4byte_opcodes(nor, info); + else set_4byte(nor, info, 1); } else { nor->addr_width = 3; @@ -1517,6 +1722,12 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) nor->read_dummy = spi_nor_read_dummy_cycles(nor); + if (info->flags & SPI_S3AN) { + ret = s3an_nor_scan(info, nor); + if (ret) + return ret; + } + dev_info(dev, "%s (%lld Kbytes)\n", info->name, (long long)mtd->size >> 10); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index c9b7ad65e563..726b5693ae8a 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1668,7 +1668,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, free_buffers: /* compensate sw bpool counter changes */ - for (i--; i > 0; i--) { + for (i--; i >= 0; i--) { dpaa_bp = dpaa_bpid2pool(sgt[i].bpid); if (dpaa_bp) { count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 38160c2bebcb..8be7034b2e7b 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2910,6 +2910,7 @@ static void set_multicast_list(struct net_device *ndev) struct netdev_hw_addr *ha; unsigned int i, bit, data, crc, tmp; unsigned char hash; + unsigned int hash_high = 0, hash_low = 0; if (ndev->flags & IFF_PROMISC) { tmp = readl(fep->hwp + FEC_R_CNTRL); @@ -2932,11 +2933,7 @@ static void set_multicast_list(struct net_device *ndev) return; } - /* Clear filter and add the addresses in hash register - */ - writel(0, fep->hwp + FEC_GRP_HASH_TABLE_HIGH); - writel(0, fep->hwp + FEC_GRP_HASH_TABLE_LOW); - + /* Add the addresses in hash register */ netdev_for_each_mc_addr(ha, ndev) { /* calculate crc32 value of mac address */ crc = 0xffffffff; @@ -2954,16 +2951,14 @@ static void set_multicast_list(struct net_device *ndev) */ hash = (crc >> (32 - FEC_HASH_BITS)) & 0x3f; - if (hash > 31) { - tmp = readl(fep->hwp + FEC_GRP_HASH_TABLE_HIGH); - tmp |= 1 << (hash - 32); - writel(tmp, fep->hwp + FEC_GRP_HASH_TABLE_HIGH); - } else { - tmp = readl(fep->hwp + FEC_GRP_HASH_TABLE_LOW); - tmp |= 1 << hash; - writel(tmp, fep->hwp + FEC_GRP_HASH_TABLE_LOW); - } + if (hash > 31) + hash_high |= 1 << (hash - 32); + else + hash_low |= 1 << hash; } + + writel(hash_high, fep->hwp + FEC_GRP_HASH_TABLE_HIGH); + writel(hash_low, fep->hwp + FEC_GRP_HASH_TABLE_LOW); } /* Set a MAC change in hardware. */ diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index c12596676bbb..a07b8d79174c 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -189,9 +189,10 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter, } ltb->map_id = adapter->map_id; adapter->map_id++; + + init_completion(&adapter->fw_done); send_request_map(adapter, ltb->addr, ltb->size, ltb->map_id); - init_completion(&adapter->fw_done); wait_for_completion(&adapter->fw_done); return 0; } @@ -505,7 +506,7 @@ rx_pool_alloc_failed: adapter->rx_pool = NULL; rx_pool_arr_alloc_failed: for (i = 0; i < adapter->req_rx_queues; i++) - napi_enable(&adapter->napi[i]); + napi_disable(&adapter->napi[i]); alloc_napi_failed: return -ENOMEM; } @@ -1121,10 +1122,10 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev, crq.request_statistics.ioba = cpu_to_be32(adapter->stats_token); crq.request_statistics.len = cpu_to_be32(sizeof(struct ibmvnic_statistics)); - ibmvnic_send_crq(adapter, &crq); /* Wait for data to be written */ init_completion(&adapter->stats_done); + ibmvnic_send_crq(adapter, &crq); wait_for_completion(&adapter->stats_done); for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++) @@ -1496,7 +1497,7 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) adapter->req_rx_queues = adapter->opt_rx_comp_queues; adapter->req_rx_add_queues = adapter->max_rx_add_queues; - adapter->req_mtu = adapter->max_mtu; + adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN; } total_queues = adapter->req_tx_queues + adapter->req_rx_queues; @@ -2185,12 +2186,12 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq, if (!found) { dev_err(dev, "Couldn't find error id %x\n", - crq->request_error_rsp.error_id); + be32_to_cpu(crq->request_error_rsp.error_id)); return; } dev_err(dev, "Detailed info for error id %x:", - crq->request_error_rsp.error_id); + be32_to_cpu(crq->request_error_rsp.error_id)); for (i = 0; i < error_buff->len; i++) { pr_cont("%02x", (int)error_buff->buff[i]); @@ -2269,8 +2270,8 @@ static void handle_error_indication(union ibmvnic_crq *crq, dev_err(dev, "Firmware reports %serror id %x, cause %d\n", crq->error_indication. flags & IBMVNIC_FATAL_ERROR ? "FATAL " : "", - crq->error_indication.error_id, - crq->error_indication.error_cause); + be32_to_cpu(crq->error_indication.error_id), + be16_to_cpu(crq->error_indication.error_cause)); error_buff = kmalloc(sizeof(*error_buff), GFP_ATOMIC); if (!error_buff) @@ -2388,10 +2389,10 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq, case PARTIALSUCCESS: dev_info(dev, "req=%lld, rsp=%ld in %s queue, retrying.\n", *req_value, - (long int)be32_to_cpu(crq->request_capability_rsp. + (long int)be64_to_cpu(crq->request_capability_rsp. number), name); release_sub_crqs_no_irqs(adapter); - *req_value = be32_to_cpu(crq->request_capability_rsp.number); + *req_value = be64_to_cpu(crq->request_capability_rsp.number); init_sub_crqs(adapter, 1); return; default: @@ -2626,12 +2627,12 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, break; case MIN_MTU: adapter->min_mtu = be64_to_cpu(crq->query_capability.number); - netdev->min_mtu = adapter->min_mtu; + netdev->min_mtu = adapter->min_mtu - ETH_HLEN; netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu); break; case MAX_MTU: adapter->max_mtu = be64_to_cpu(crq->query_capability.number); - netdev->max_mtu = adapter->max_mtu; + netdev->max_mtu = adapter->max_mtu - ETH_HLEN; netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu); break; case MAX_MULTICAST_FILTERS: @@ -2799,9 +2800,9 @@ static ssize_t trace_read(struct file *file, char __user *user_buf, size_t len, crq.collect_fw_trace.correlator = adapter->ras_comps[num].correlator; crq.collect_fw_trace.ioba = cpu_to_be32(trace_tok); crq.collect_fw_trace.len = adapter->ras_comps[num].trace_buff_size; - ibmvnic_send_crq(adapter, &crq); init_completion(&adapter->fw_done); + ibmvnic_send_crq(adapter, &crq); wait_for_completion(&adapter->fw_done); if (*ppos + len > be32_to_cpu(adapter->ras_comps[num].trace_buff_size)) @@ -3581,9 +3582,9 @@ static int ibmvnic_dump_show(struct seq_file *seq, void *v) memset(&crq, 0, sizeof(crq)); crq.request_dump_size.first = IBMVNIC_CRQ_CMD; crq.request_dump_size.cmd = REQUEST_DUMP_SIZE; - ibmvnic_send_crq(adapter, &crq); init_completion(&adapter->fw_done); + ibmvnic_send_crq(adapter, &crq); wait_for_completion(&adapter->fw_done); seq_write(seq, adapter->dump_data, adapter->dump_data_size); @@ -3629,8 +3630,8 @@ static void handle_crq_init_rsp(struct work_struct *work) } } - send_version_xchg(adapter); reinit_completion(&adapter->init_done); + send_version_xchg(adapter); if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { dev_err(dev, "Passive init timeout\n"); goto task_failed; @@ -3640,9 +3641,9 @@ static void handle_crq_init_rsp(struct work_struct *work) if (adapter->renegotiate) { adapter->renegotiate = false; release_sub_crqs_no_irqs(adapter); - send_cap_queries(adapter); reinit_completion(&adapter->init_done); + send_cap_queries(adapter); if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { dev_err(dev, "Passive init timeout\n"); @@ -3656,9 +3657,7 @@ static void handle_crq_init_rsp(struct work_struct *work) goto task_failed; netdev->real_num_tx_queues = adapter->req_tx_queues; - netdev->mtu = adapter->req_mtu; - netdev->min_mtu = adapter->min_mtu; - netdev->max_mtu = adapter->max_mtu; + netdev->mtu = adapter->req_mtu - ETH_HLEN; if (adapter->failover) { adapter->failover = false; @@ -3772,9 +3771,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) adapter->debugfs_dump = ent; } } - ibmvnic_send_crq_init(adapter); init_completion(&adapter->init_done); + ibmvnic_send_crq_init(adapter); if (!wait_for_completion_timeout(&adapter->init_done, timeout)) return 0; @@ -3782,9 +3781,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) if (adapter->renegotiate) { adapter->renegotiate = false; release_sub_crqs_no_irqs(adapter); - send_cap_queries(adapter); reinit_completion(&adapter->init_done); + send_cap_queries(adapter); if (!wait_for_completion_timeout(&adapter->init_done, timeout)) return 0; @@ -3798,7 +3797,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) } netdev->real_num_tx_queues = adapter->req_tx_queues; - netdev->mtu = adapter->req_mtu; + netdev->mtu = adapter->req_mtu - ETH_HLEN; rc = register_netdev(netdev); if (rc) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index c5282b6aba8b..2ebbe80d8126 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1087,10 +1087,14 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); + preempt_disable(); + tcf_exts_to_list(f->exts, &actions); list_for_each_entry(a, &actions, list) tcf_action_stats_update(a, bytes, packets, lastuse); + preempt_enable(); + return 0; } diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index b203143647e6..65088224c207 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -3160,7 +3160,7 @@ static int cpsw_resume(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct net_device *ndev = platform_get_drvdata(pdev); - struct cpsw_common *cpsw = netdev_priv(ndev); + struct cpsw_common *cpsw = ndev_to_cpsw(ndev); /* Select default pin state */ pinctrl_pm_select_default_state(dev); diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 93dc10b10c09..aa02a03a6d8d 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -100,6 +100,14 @@ /* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */ #define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT) +#ifdef __BIG_ENDIAN +#define xemaclite_readl ioread32be +#define xemaclite_writel iowrite32be +#else +#define xemaclite_readl ioread32 +#define xemaclite_writel iowrite32 +#endif + /** * struct net_local - Our private per device data * @ndev: instance of the network device @@ -156,15 +164,15 @@ static void xemaclite_enable_interrupts(struct net_local *drvdata) u32 reg_data; /* Enable the Tx interrupts for the first Buffer */ - reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET); - __raw_writel(reg_data | XEL_TSR_XMIT_IE_MASK, - drvdata->base_addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET); + xemaclite_writel(reg_data | XEL_TSR_XMIT_IE_MASK, + drvdata->base_addr + XEL_TSR_OFFSET); /* Enable the Rx interrupts for the first buffer */ - __raw_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET); + xemaclite_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET); /* Enable the Global Interrupt Enable */ - __raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET); + xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET); } /** @@ -179,17 +187,17 @@ static void xemaclite_disable_interrupts(struct net_local *drvdata) u32 reg_data; /* Disable the Global Interrupt Enable */ - __raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET); + xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET); /* Disable the Tx interrupts for the first buffer */ - reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET); - __raw_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK), - drvdata->base_addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET); + xemaclite_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK), + drvdata->base_addr + XEL_TSR_OFFSET); /* Disable the Rx interrupts for the first buffer */ - reg_data = __raw_readl(drvdata->base_addr + XEL_RSR_OFFSET); - __raw_writel(reg_data & (~XEL_RSR_RECV_IE_MASK), - drvdata->base_addr + XEL_RSR_OFFSET); + reg_data = xemaclite_readl(drvdata->base_addr + XEL_RSR_OFFSET); + xemaclite_writel(reg_data & (~XEL_RSR_RECV_IE_MASK), + drvdata->base_addr + XEL_RSR_OFFSET); } /** @@ -321,7 +329,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, byte_count = ETH_FRAME_LEN; /* Check if the expected buffer is available */ - reg_data = __raw_readl(addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET); if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK)) == 0) { @@ -334,7 +342,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, addr = (void __iomem __force *)((u32 __force)addr ^ XEL_BUFFER_OFFSET); - reg_data = __raw_readl(addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET); if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK)) != 0) @@ -345,16 +353,16 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, /* Write the frame to the buffer */ xemaclite_aligned_write(data, (u32 __force *) addr, byte_count); - __raw_writel((byte_count & XEL_TPLR_LENGTH_MASK), - addr + XEL_TPLR_OFFSET); + xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK), + addr + XEL_TPLR_OFFSET); /* Update the Tx Status Register to indicate that there is a * frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which * is used by the interrupt handler to check whether a frame * has been transmitted */ - reg_data = __raw_readl(addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET); reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK); - __raw_writel(reg_data, addr + XEL_TSR_OFFSET); + xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET); return 0; } @@ -369,7 +377,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, * * Return: Total number of bytes received */ -static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data) +static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen) { void __iomem *addr; u16 length, proto_type; @@ -379,7 +387,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data) addr = (drvdata->base_addr + drvdata->next_rx_buf_to_use); /* Verify which buffer has valid data */ - reg_data = __raw_readl(addr + XEL_RSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET); if ((reg_data & XEL_RSR_RECV_DONE_MASK) == XEL_RSR_RECV_DONE_MASK) { if (drvdata->rx_ping_pong != 0) @@ -396,27 +404,28 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data) return 0; /* No data was available */ /* Verify that buffer has valid data */ - reg_data = __raw_readl(addr + XEL_RSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET); if ((reg_data & XEL_RSR_RECV_DONE_MASK) != XEL_RSR_RECV_DONE_MASK) return 0; /* No data was available */ } /* Get the protocol type of the ethernet frame that arrived */ - proto_type = ((ntohl(__raw_readl(addr + XEL_HEADER_OFFSET + + proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET + XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) & XEL_RPLR_LENGTH_MASK); /* Check if received ethernet frame is a raw ethernet frame * or an IP packet or an ARP packet */ - if (proto_type > (ETH_FRAME_LEN + ETH_FCS_LEN)) { + if (proto_type > ETH_DATA_LEN) { if (proto_type == ETH_P_IP) { - length = ((ntohl(__raw_readl(addr + + length = ((ntohl(xemaclite_readl(addr + XEL_HEADER_IP_LENGTH_OFFSET + XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) & XEL_RPLR_LENGTH_MASK); + length = min_t(u16, length, ETH_DATA_LEN); length += ETH_HLEN + ETH_FCS_LEN; } else if (proto_type == ETH_P_ARP) @@ -429,14 +438,17 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data) /* Use the length in the frame, plus the header and trailer */ length = proto_type + ETH_HLEN + ETH_FCS_LEN; + if (WARN_ON(length > maxlen)) + length = maxlen; + /* Read from the EmacLite device */ xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET), data, length); /* Acknowledge the frame */ - reg_data = __raw_readl(addr + XEL_RSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET); reg_data &= ~XEL_RSR_RECV_DONE_MASK; - __raw_writel(reg_data, addr + XEL_RSR_OFFSET); + xemaclite_writel(reg_data, addr + XEL_RSR_OFFSET); return length; } @@ -463,14 +475,14 @@ static void xemaclite_update_address(struct net_local *drvdata, xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN); - __raw_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET); + xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET); /* Update the MAC address in the EmacLite */ - reg_data = __raw_readl(addr + XEL_TSR_OFFSET); - __raw_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET); + xemaclite_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET); /* Wait for EmacLite to finish with the MAC address update */ - while ((__raw_readl(addr + XEL_TSR_OFFSET) & + while ((xemaclite_readl(addr + XEL_TSR_OFFSET) & XEL_TSR_PROG_MAC_ADDR) != 0) ; } @@ -603,7 +615,7 @@ static void xemaclite_rx_handler(struct net_device *dev) skb_reserve(skb, 2); - len = xemaclite_recv_data(lp, (u8 *) skb->data); + len = xemaclite_recv_data(lp, (u8 *) skb->data, len); if (!len) { dev->stats.rx_errors++; @@ -640,32 +652,32 @@ static irqreturn_t xemaclite_interrupt(int irq, void *dev_id) u32 tx_status; /* Check if there is Rx Data available */ - if ((__raw_readl(base_addr + XEL_RSR_OFFSET) & + if ((xemaclite_readl(base_addr + XEL_RSR_OFFSET) & XEL_RSR_RECV_DONE_MASK) || - (__raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET) + (xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET) & XEL_RSR_RECV_DONE_MASK)) xemaclite_rx_handler(dev); /* Check if the Transmission for the first buffer is completed */ - tx_status = __raw_readl(base_addr + XEL_TSR_OFFSET); + tx_status = xemaclite_readl(base_addr + XEL_TSR_OFFSET); if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) && (tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) { tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK; - __raw_writel(tx_status, base_addr + XEL_TSR_OFFSET); + xemaclite_writel(tx_status, base_addr + XEL_TSR_OFFSET); tx_complete = true; } /* Check if the Transmission for the second buffer is completed */ - tx_status = __raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET); + tx_status = xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET); if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) && (tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) { tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK; - __raw_writel(tx_status, base_addr + XEL_BUFFER_OFFSET + - XEL_TSR_OFFSET); + xemaclite_writel(tx_status, base_addr + XEL_BUFFER_OFFSET + + XEL_TSR_OFFSET); tx_complete = true; } @@ -698,7 +710,7 @@ static int xemaclite_mdio_wait(struct net_local *lp) /* wait for the MDIO interface to not be busy or timeout after some time. */ - while (__raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) & + while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) & XEL_MDIOCTRL_MDIOSTS_MASK) { if (time_before_eq(end, jiffies)) { WARN_ON(1); @@ -734,17 +746,17 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg) * MDIO Address register. Set the Status bit in the MDIO Control * register to start a MDIO read transaction. */ - ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET); - __raw_writel(XEL_MDIOADDR_OP_MASK | - ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg), - lp->base_addr + XEL_MDIOADDR_OFFSET); - __raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK, - lp->base_addr + XEL_MDIOCTRL_OFFSET); + ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET); + xemaclite_writel(XEL_MDIOADDR_OP_MASK | + ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg), + lp->base_addr + XEL_MDIOADDR_OFFSET); + xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK, + lp->base_addr + XEL_MDIOCTRL_OFFSET); if (xemaclite_mdio_wait(lp)) return -ETIMEDOUT; - rc = __raw_readl(lp->base_addr + XEL_MDIORD_OFFSET); + rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET); dev_dbg(&lp->ndev->dev, "xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n", @@ -781,13 +793,13 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg, * Data register. Finally, set the Status bit in the MDIO Control * register to start a MDIO write transaction. */ - ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET); - __raw_writel(~XEL_MDIOADDR_OP_MASK & - ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg), - lp->base_addr + XEL_MDIOADDR_OFFSET); - __raw_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET); - __raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK, - lp->base_addr + XEL_MDIOCTRL_OFFSET); + ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET); + xemaclite_writel(~XEL_MDIOADDR_OP_MASK & + ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg), + lp->base_addr + XEL_MDIOADDR_OFFSET); + xemaclite_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET); + xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK, + lp->base_addr + XEL_MDIOCTRL_OFFSET); return 0; } @@ -834,8 +846,8 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) /* Enable the MDIO bus by asserting the enable bit in MDIO Control * register. */ - __raw_writel(XEL_MDIOCTRL_MDIOEN_MASK, - lp->base_addr + XEL_MDIOCTRL_OFFSET); + xemaclite_writel(XEL_MDIOCTRL_MDIOEN_MASK, + lp->base_addr + XEL_MDIOCTRL_OFFSET); bus = mdiobus_alloc(); if (!bus) { @@ -1140,8 +1152,8 @@ static int xemaclite_of_probe(struct platform_device *ofdev) } /* Clear the Tx CSR's in case this is a restart */ - __raw_writel(0, lp->base_addr + XEL_TSR_OFFSET); - __raw_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET); + xemaclite_writel(0, lp->base_addr + XEL_TSR_OFFSET); + xemaclite_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET); /* Set the MAC address in the EmacLite device */ xemaclite_update_address(lp, ndev->dev_addr); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 50b62db213b0..30b04cf2bb1e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2439,7 +2439,8 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) rt = vxlan_get_route(vxlan, dev, sock4, skb, 0, info->key.tos, info->key.u.ipv4.dst, - &info->key.u.ipv4.src, dport, sport, NULL, info); + &info->key.u.ipv4.src, dport, sport, + &info->dst_cache, info); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); @@ -2450,7 +2451,8 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) ndst = vxlan6_get_route(vxlan, dev, sock6, skb, 0, info->key.tos, info->key.label, &info->key.u.ipv6.dst, - &info->key.u.ipv6.src, dport, sport, NULL, info); + &info->key.u.ipv6.src, dport, sport, + &info->dst_cache, info); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 3ce1f7da8647..530586be05b4 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -113,10 +113,10 @@ struct xenvif_stats { * A subset of struct net_device_stats that contains only the * fields that are updated in netback.c for each queue. */ - unsigned int rx_bytes; - unsigned int rx_packets; - unsigned int tx_bytes; - unsigned int tx_packets; + u64 rx_bytes; + u64 rx_packets; + u64 tx_bytes; + u64 tx_packets; /* Additional stats used by xenvif */ unsigned long rx_gso_checksum_fixup; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 579521327b03..50fa1692d985 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -221,10 +221,10 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); struct xenvif_queue *queue = NULL; - unsigned long rx_bytes = 0; - unsigned long rx_packets = 0; - unsigned long tx_bytes = 0; - unsigned long tx_packets = 0; + u64 rx_bytes = 0; + u64 rx_packets = 0; + u64 tx_bytes = 0; + u64 tx_packets = 0; unsigned int index; spin_lock(&vif->lock); diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c index eca9688bf9d9..c00238491673 100644 --- a/drivers/ntb/hw/intel/ntb_hw_intel.c +++ b/drivers/ntb/hw/intel/ntb_hw_intel.c @@ -1629,6 +1629,28 @@ static void atom_deinit_dev(struct intel_ntb_dev *ndev) /* Skylake Xeon NTB */ +static int skx_poll_link(struct intel_ntb_dev *ndev) +{ + u16 reg_val; + int rc; + + ndev->reg->db_iowrite(ndev->db_link_mask, + ndev->self_mmio + + ndev->self_reg->db_clear); + + rc = pci_read_config_word(ndev->ntb.pdev, + SKX_LINK_STATUS_OFFSET, ®_val); + if (rc) + return 0; + + if (reg_val == ndev->lnk_sta) + return 0; + + ndev->lnk_sta = reg_val; + + return 1; +} + static u64 skx_db_ioread(void __iomem *mmio) { return ioread64(mmio); @@ -2852,7 +2874,7 @@ static struct intel_b2b_addr xeon_b2b_dsd_addr = { }; static const struct intel_ntb_reg skx_reg = { - .poll_link = xeon_poll_link, + .poll_link = skx_poll_link, .link_is_up = xeon_link_is_up, .db_ioread = skx_db_ioread, .db_iowrite = skx_db_iowrite, diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index f81aa4b18d9f..02ca45fdd892 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -1802,7 +1802,7 @@ ntb_transport_create_queue(void *data, struct device *client_dev, node = dev_to_node(&ndev->dev); - free_queue = ffs(nt->qp_bitmap); + free_queue = ffs(nt->qp_bitmap_free); if (!free_queue) goto err; @@ -2273,9 +2273,8 @@ module_init(ntb_transport_init); static void __exit ntb_transport_exit(void) { - debugfs_remove_recursive(nt_debugfs_dir); - ntb_unregister_client(&ntb_transport_client); bus_unregister(&ntb_transport_bus); + debugfs_remove_recursive(nt_debugfs_dir); } module_exit(ntb_transport_exit); diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index e75d4fdc0866..434e1d474f33 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -265,6 +265,8 @@ static ssize_t perf_copy(struct pthr_ctx *pctx, char __iomem *dst, if (dma_submit_error(cookie)) goto err_set_unmap; + dmaengine_unmap_put(unmap); + atomic_inc(&pctx->dma_sync); dma_async_issue_pending(chan); diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index 56efaf72d08e..d2961ef39a3a 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -155,7 +155,7 @@ static void pnv_php_detach_device_nodes(struct device_node *parent) pnv_php_detach_device_nodes(dn); of_node_put(dn); - refcount = atomic_read(&dn->kobj.kref.refcount); + refcount = kref_read(&dn->kobj.kref); if (refcount != 1) pr_warn("Invalid refcount %d on <%s>\n", refcount, of_node_full_name(dn)); diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c index 717529331dac..2dd1c68e6de8 100644 --- a/drivers/pci/pcie/pme.c +++ b/drivers/pci/pcie/pme.c @@ -433,6 +433,17 @@ static int pcie_pme_resume(struct pcie_device *srv) return 0; } +/** + * pcie_pme_remove - Prepare PCIe PME service device for removal. + * @srv - PCIe service device to remove. + */ +static void pcie_pme_remove(struct pcie_device *srv) +{ + pcie_pme_suspend(srv); + free_irq(srv->irq, srv); + kfree(get_service_data(srv)); +} + static struct pcie_port_service_driver pcie_pme_driver = { .name = "pcie_pme", .port_type = PCI_EXP_TYPE_ROOT_PORT, @@ -441,6 +452,7 @@ static struct pcie_port_service_driver pcie_pme_driver = { .probe = pcie_pme_probe, .suspend = pcie_pme_suspend, .resume = pcie_pme_resume, + .remove = pcie_pme_remove, }; /** diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c index 429d34c348b9..e42909524dee 100644 --- a/drivers/pci/slot.c +++ b/drivers/pci/slot.c @@ -345,7 +345,7 @@ EXPORT_SYMBOL_GPL(pci_create_slot); void pci_destroy_slot(struct pci_slot *slot) { dev_dbg(&slot->bus->dev, "dev %02x, dec refcount to %d\n", - slot->number, atomic_read(&slot->kobj.kref.refcount) - 1); + slot->number, kref_read(&slot->kobj.kref) - 1); mutex_lock(&pci_slot_mutex); kobject_put(&slot->kobj); diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig index abeb77217a21..b8cacccf18c8 100644 --- a/drivers/power/reset/Kconfig +++ b/drivers/power/reset/Kconfig @@ -32,7 +32,7 @@ config POWER_RESET_AT91_RESET config POWER_RESET_AT91_SAMA5D2_SHDWC tristate "Atmel AT91 SAMA5D2-Compatible shutdown controller driver" - depends on ARCH_AT91 || COMPILE_TEST + depends on ARCH_AT91 default SOC_SAMA5 help This driver supports the alternate shutdown controller for some Atmel diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c index a85dd4d233af..c6c3beea72f9 100644 --- a/drivers/power/reset/at91-poweroff.c +++ b/drivers/power/reset/at91-poweroff.c @@ -14,9 +14,12 @@ #include <linux/io.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/platform_device.h> #include <linux/printk.h> +#include <soc/at91/at91sam9_ddrsdr.h> + #define AT91_SHDW_CR 0x00 /* Shut Down Control Register */ #define AT91_SHDW_SHDW BIT(0) /* Shut Down command */ #define AT91_SHDW_KEY (0xa5 << 24) /* KEY Password */ @@ -50,6 +53,7 @@ static const char *shdwc_wakeup_modes[] = { static void __iomem *at91_shdwc_base; static struct clk *sclk; +static void __iomem *mpddrc_base; static void __init at91_wakeup_status(void) { @@ -73,6 +77,29 @@ static void at91_poweroff(void) writel(AT91_SHDW_KEY | AT91_SHDW_SHDW, at91_shdwc_base + AT91_SHDW_CR); } +static void at91_lpddr_poweroff(void) +{ + asm volatile( + /* Align to cache lines */ + ".balign 32\n\t" + + /* Ensure AT91_SHDW_CR is in the TLB by reading it */ + " ldr r6, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t" + + /* Power down SDRAM0 */ + " str %1, [%0, #" __stringify(AT91_DDRSDRC_LPR) "]\n\t" + /* Shutdown CPU */ + " str %3, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t" + + " b .\n\t" + : + : "r" (mpddrc_base), + "r" cpu_to_le32(AT91_DDRSDRC_LPDDR2_PWOFF), + "r" (at91_shdwc_base), + "r" cpu_to_le32(AT91_SHDW_KEY | AT91_SHDW_SHDW) + : "r0"); +} + static int at91_poweroff_get_wakeup_mode(struct device_node *np) { const char *pm; @@ -124,6 +151,8 @@ static void at91_poweroff_dt_set_wakeup_mode(struct platform_device *pdev) static int __init at91_poweroff_probe(struct platform_device *pdev) { struct resource *res; + struct device_node *np; + u32 ddr_type; int ret; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -150,12 +179,30 @@ static int __init at91_poweroff_probe(struct platform_device *pdev) pm_power_off = at91_poweroff; + np = of_find_compatible_node(NULL, NULL, "atmel,sama5d3-ddramc"); + if (!np) + return 0; + + mpddrc_base = of_iomap(np, 0); + of_node_put(np); + + if (!mpddrc_base) + return 0; + + ddr_type = readl(mpddrc_base + AT91_DDRSDRC_MDR) & AT91_DDRSDRC_MD; + if ((ddr_type == AT91_DDRSDRC_MD_LPDDR2) || + (ddr_type == AT91_DDRSDRC_MD_LPDDR3)) + pm_power_off = at91_lpddr_poweroff; + else + iounmap(mpddrc_base); + return 0; } static int __exit at91_poweroff_remove(struct platform_device *pdev) { - if (pm_power_off == at91_poweroff) + if (pm_power_off == at91_poweroff || + pm_power_off == at91_lpddr_poweroff) pm_power_off = NULL; clk_disable_unprepare(sclk); @@ -163,6 +210,11 @@ static int __exit at91_poweroff_remove(struct platform_device *pdev) return 0; } +static const struct of_device_id at91_ramc_of_match[] = { + { .compatible = "atmel,sama5d3-ddramc", }, + { /* sentinel */ } +}; + static const struct of_device_id at91_poweroff_of_match[] = { { .compatible = "atmel,at91sam9260-shdwc", }, { .compatible = "atmel,at91sam9rl-shdwc", }, diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c index 568580cf0655..b99769f8ab15 100644 --- a/drivers/power/reset/at91-reset.c +++ b/drivers/power/reset/at91-reset.c @@ -134,6 +134,15 @@ static int sama5d3_restart(struct notifier_block *this, unsigned long mode, return NOTIFY_DONE; } +static int samx7_restart(struct notifier_block *this, unsigned long mode, + void *cmd) +{ + writel(cpu_to_le32(AT91_RSTC_KEY | AT91_RSTC_PROCRST), + at91_rstc_base); + + return NOTIFY_DONE; +} + static void __init at91_reset_status(struct platform_device *pdev) { u32 reg = readl(at91_rstc_base + AT91_RSTC_SR); @@ -173,6 +182,7 @@ static const struct of_device_id at91_reset_of_match[] = { { .compatible = "atmel,at91sam9260-rstc", .data = at91sam9260_restart }, { .compatible = "atmel,at91sam9g45-rstc", .data = at91sam9g45_restart }, { .compatible = "atmel,sama5d3-rstc", .data = sama5d3_restart }, + { .compatible = "atmel,samx7-rstc", .data = samx7_restart }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, at91_reset_of_match); @@ -238,20 +248,12 @@ static int __exit at91_reset_remove(struct platform_device *pdev) return 0; } -static const struct platform_device_id at91_reset_plat_match[] = { - { "at91-sam9260-reset", (unsigned long)at91sam9260_restart }, - { "at91-sam9g45-reset", (unsigned long)at91sam9g45_restart }, - { /* sentinel */ } -}; -MODULE_DEVICE_TABLE(platform, at91_reset_plat_match); - static struct platform_driver at91_reset_driver = { .remove = __exit_p(at91_reset_remove), .driver = { .name = "at91-reset", .of_match_table = at91_reset_of_match, }, - .id_table = at91_reset_plat_match, }; module_platform_driver_probe(at91_reset_driver, at91_reset_probe); diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c index 8a5ac9706c9c..90b0b5a70ce5 100644 --- a/drivers/power/reset/at91-sama5d2_shdwc.c +++ b/drivers/power/reset/at91-sama5d2_shdwc.c @@ -22,9 +22,12 @@ #include <linux/io.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/platform_device.h> #include <linux/printk.h> +#include <soc/at91/at91sam9_ddrsdr.h> + #define SLOW_CLOCK_FREQ 32768 #define AT91_SHDW_CR 0x00 /* Shut Down Control Register */ @@ -75,6 +78,7 @@ struct shdwc { */ static struct shdwc *at91_shdwc; static struct clk *sclk; +static void __iomem *mpddrc_base; static const unsigned long long sdwc_dbc_period[] = { 0, 3, 32, 512, 4096, 32768, @@ -108,6 +112,29 @@ static void at91_poweroff(void) at91_shdwc->at91_shdwc_base + AT91_SHDW_CR); } +static void at91_lpddr_poweroff(void) +{ + asm volatile( + /* Align to cache lines */ + ".balign 32\n\t" + + /* Ensure AT91_SHDW_CR is in the TLB by reading it */ + " ldr r6, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t" + + /* Power down SDRAM0 */ + " str %1, [%0, #" __stringify(AT91_DDRSDRC_LPR) "]\n\t" + /* Shutdown CPU */ + " str %3, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t" + + " b .\n\t" + : + : "r" (mpddrc_base), + "r" cpu_to_le32(AT91_DDRSDRC_LPDDR2_PWOFF), + "r" (at91_shdwc->at91_shdwc_base), + "r" cpu_to_le32(AT91_SHDW_KEY | AT91_SHDW_SHDW) + : "r0"); +} + static u32 at91_shdwc_debouncer_value(struct platform_device *pdev, u32 in_period_us) { @@ -212,6 +239,8 @@ static int __init at91_shdwc_probe(struct platform_device *pdev) { struct resource *res; const struct of_device_id *match; + struct device_node *np; + u32 ddr_type; int ret; if (!pdev->dev.of_node) @@ -249,6 +278,23 @@ static int __init at91_shdwc_probe(struct platform_device *pdev) pm_power_off = at91_poweroff; + np = of_find_compatible_node(NULL, NULL, "atmel,sama5d3-ddramc"); + if (!np) + return 0; + + mpddrc_base = of_iomap(np, 0); + of_node_put(np); + + if (!mpddrc_base) + return 0; + + ddr_type = readl(mpddrc_base + AT91_DDRSDRC_MDR) & AT91_DDRSDRC_MD; + if ((ddr_type == AT91_DDRSDRC_MD_LPDDR2) || + (ddr_type == AT91_DDRSDRC_MD_LPDDR3)) + pm_power_off = at91_lpddr_poweroff; + else + iounmap(mpddrc_base); + return 0; } @@ -256,7 +302,8 @@ static int __exit at91_shdwc_remove(struct platform_device *pdev) { struct shdwc *shdw = platform_get_drvdata(pdev); - if (pm_power_off == at91_poweroff) + if (pm_power_off == at91_poweroff || + pm_power_off == at91_lpddr_poweroff) pm_power_off = NULL; /* Reset values to disable wake-up features */ diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index 76806a0be820..da54ac88f068 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -164,6 +164,12 @@ config BATTERY_SBS Say Y to include support for SBS battery driver for SBS-compliant gas gauges. +config CHARGER_SBS + tristate "SBS Compliant charger" + depends on I2C + help + Say Y to include support for SBS compilant battery chargers. + config BATTERY_BQ27XXX tristate "BQ27xxx battery driver" help @@ -214,6 +220,18 @@ config BATTERY_DA9150 This driver can also be built as a module. If so, the module will be called da9150-fg. +config CHARGER_AXP20X + tristate "X-Powers AXP20X and AXP22X AC power supply driver" + depends on MFD_AXP20X + depends on AXP20X_ADC + depends on IIO + help + Say Y here to enable support for X-Powers AXP20X and AXP22X PMICs' AC + power supply. + + This driver can also be built as a module. If so, the module will be + called axp20x_ac_power. + config AXP288_CHARGER tristate "X-Powers AXP288 Charger" depends on MFD_AXP20X && EXTCON_AXP288 @@ -292,13 +310,6 @@ config BATTERY_JZ4740 This driver can be build as a module. If so, the module will be called jz4740-battery. -config BATTERY_INTEL_MID - tristate "Battery driver for Intel MID platforms" - depends on INTEL_SCU_IPC && SPI - help - Say Y here to enable the battery driver on Intel MID - platforms. - config BATTERY_RX51 tristate "Nokia RX-51 (N900) battery driver" depends on TWL4030_MADC @@ -370,6 +381,16 @@ config CHARGER_MAX14577 Say Y to enable support for the battery charger control sysfs and platform data of MAX14577/77836 MUICs. +config CHARGER_DETECTOR_MAX14656 + tristate "Maxim MAX14656 USB charger detector" + depends on I2C + depends on OF + help + Say Y to enable support for the Maxim MAX14656 USB charger detector. + The device is compliant with the USB Battery Charging Specification + Revision 1.2 and can be found e.g. in Kindle 4/5th generation + readers and certain LG devices. + config CHARGER_MAX77693 tristate "Maxim MAX77693 battery charger driver" depends on MFD_MAX77693 @@ -395,6 +416,7 @@ config CHARGER_QCOM_SMBB depends on MFD_SPMI_PMIC || COMPILE_TEST depends on OF depends on EXTCON + depends on REGULATOR help Say Y to include support for the Switch-Mode Battery Charger and Boost (SMBB) hardware found in Qualcomm PM8941 PMICs. The charger diff --git a/drivers/power/supply/Makefile b/drivers/power/supply/Makefile index 36c599d9a495..3789a2c06fdf 100644 --- a/drivers/power/supply/Makefile +++ b/drivers/power/supply/Makefile @@ -18,6 +18,7 @@ obj-$(CONFIG_TEST_POWER) += test_power.o obj-$(CONFIG_BATTERY_88PM860X) += 88pm860x_battery.o obj-$(CONFIG_BATTERY_ACT8945A) += act8945a_charger.o +obj-$(CONFIG_CHARGER_AXP20X) += axp20x_ac_power.o obj-$(CONFIG_BATTERY_DS2760) += ds2760_battery.o obj-$(CONFIG_BATTERY_DS2780) += ds2780_battery.o obj-$(CONFIG_BATTERY_DS2781) += ds2781_battery.o @@ -31,6 +32,7 @@ obj-$(CONFIG_BATTERY_COLLIE) += collie_battery.o obj-$(CONFIG_BATTERY_IPAQ_MICRO) += ipaq_micro_battery.o obj-$(CONFIG_BATTERY_WM97XX) += wm97xx_battery.o obj-$(CONFIG_BATTERY_SBS) += sbs-battery.o +obj-$(CONFIG_CHARGER_SBS) += sbs-charger.o obj-$(CONFIG_BATTERY_BQ27XXX) += bq27xxx_battery.o obj-$(CONFIG_BATTERY_BQ27XXX_I2C) += bq27xxx_battery_i2c.o obj-$(CONFIG_BATTERY_DA9030) += da9030_battery.o @@ -47,7 +49,6 @@ obj-$(CONFIG_BATTERY_TWL4030_MADC) += twl4030_madc_battery.o obj-$(CONFIG_CHARGER_88PM860X) += 88pm860x_charger.o obj-$(CONFIG_CHARGER_PCF50633) += pcf50633-charger.o obj-$(CONFIG_BATTERY_JZ4740) += jz4740-battery.o -obj-$(CONFIG_BATTERY_INTEL_MID) += intel_mid_battery.o obj-$(CONFIG_BATTERY_RX51) += rx51_battery.o obj-$(CONFIG_AB8500_BM) += ab8500_bmdata.o ab8500_charger.o ab8500_fg.o ab8500_btemp.o abx500_chargalg.o pm2301_charger.o obj-$(CONFIG_CHARGER_ISP1704) += isp1704_charger.o @@ -58,6 +59,7 @@ obj-$(CONFIG_CHARGER_LP8788) += lp8788-charger.o obj-$(CONFIG_CHARGER_GPIO) += gpio-charger.o obj-$(CONFIG_CHARGER_MANAGER) += charger-manager.o obj-$(CONFIG_CHARGER_MAX14577) += max14577_charger.o +obj-$(CONFIG_CHARGER_DETECTOR_MAX14656) += max14656_charger_detector.o obj-$(CONFIG_CHARGER_MAX77693) += max77693_charger.o obj-$(CONFIG_CHARGER_MAX8997) += max8997_charger.o obj-$(CONFIG_CHARGER_MAX8998) += max8998_charger.o diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 6ffdc18f2599..f7a35ebfbab2 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -76,8 +76,8 @@ struct ab8500_btemp_ranges { * @dev: Pointer to the structure device * @node: List of AB8500 BTEMPs, hence prepared for reentrance * @curr_source: What current source we use, in uA - * @bat_temp: Dispatched battery temperature in degree Celcius - * @prev_bat_temp Last measured battery temperature in degree Celcius + * @bat_temp: Dispatched battery temperature in degree Celsius + * @prev_bat_temp Last measured battery temperature in degree Celsius * @parent: Pointer to the struct ab8500 * @gpadc: Pointer to the struct gpadc * @fg: Pointer to the struct fg @@ -123,10 +123,7 @@ static LIST_HEAD(ab8500_btemp_list); */ struct ab8500_btemp *ab8500_btemp_get(void) { - struct ab8500_btemp *btemp; - btemp = list_first_entry(&ab8500_btemp_list, struct ab8500_btemp, node); - - return btemp; + return list_first_entry(&ab8500_btemp_list, struct ab8500_btemp, node); } EXPORT_SYMBOL(ab8500_btemp_get); @@ -464,13 +461,13 @@ static int ab8500_btemp_get_batctrl_res(struct ab8500_btemp *di) * @tbl_size: size of the resistance to temperature table * @res: resistance to calculate the temperature from * - * This function returns the battery temperature in degrees Celcius + * This function returns the battery temperature in degrees Celsius * based on the NTC resistance. */ static int ab8500_btemp_res_to_temp(struct ab8500_btemp *di, const struct abx500_res_to_temp *tbl, int tbl_size, int res) { - int i, temp; + int i; /* * Calculate the formula for the straight line * Simple interpolation if we are within @@ -488,9 +485,8 @@ static int ab8500_btemp_res_to_temp(struct ab8500_btemp *di, i++; } - temp = tbl[i].temp + ((tbl[i + 1].temp - tbl[i].temp) * + return tbl[i].temp + ((tbl[i + 1].temp - tbl[i].temp) * (res - tbl[i].resist)) / (tbl[i + 1].resist - tbl[i].resist); - return temp; } /** diff --git a/drivers/power/supply/axp20x_ac_power.c b/drivers/power/supply/axp20x_ac_power.c new file mode 100644 index 000000000000..38f4e87cf24d --- /dev/null +++ b/drivers/power/supply/axp20x_ac_power.c @@ -0,0 +1,253 @@ +/* + * AXP20X and AXP22X PMICs' ACIN power supply driver + * + * Copyright (C) 2016 Free Electrons + * Quentin Schulz <quentin.schulz@free-electrons.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. + */ + +#include <linux/device.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/mfd/axp20x.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/power_supply.h> +#include <linux/regmap.h> +#include <linux/slab.h> +#include <linux/iio/consumer.h> + +#define AXP20X_PWR_STATUS_ACIN_PRESENT BIT(7) +#define AXP20X_PWR_STATUS_ACIN_AVAIL BIT(6) + +#define DRVNAME "axp20x-ac-power-supply" + +struct axp20x_ac_power { + struct regmap *regmap; + struct power_supply *supply; + struct iio_channel *acin_v; + struct iio_channel *acin_i; +}; + +static irqreturn_t axp20x_ac_power_irq(int irq, void *devid) +{ + struct axp20x_ac_power *power = devid; + + power_supply_changed(power->supply); + + return IRQ_HANDLED; +} + +static int axp20x_ac_power_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct axp20x_ac_power *power = power_supply_get_drvdata(psy); + int ret, reg; + + switch (psp) { + case POWER_SUPPLY_PROP_HEALTH: + ret = regmap_read(power->regmap, AXP20X_PWR_INPUT_STATUS, ®); + if (ret) + return ret; + + if (reg & AXP20X_PWR_STATUS_ACIN_PRESENT) { + val->intval = POWER_SUPPLY_HEALTH_GOOD; + return 0; + } + + val->intval = POWER_SUPPLY_HEALTH_UNKNOWN; + return 0; + + case POWER_SUPPLY_PROP_PRESENT: + ret = regmap_read(power->regmap, AXP20X_PWR_INPUT_STATUS, ®); + if (ret) + return ret; + + val->intval = !!(reg & AXP20X_PWR_STATUS_ACIN_PRESENT); + return 0; + + case POWER_SUPPLY_PROP_ONLINE: + ret = regmap_read(power->regmap, AXP20X_PWR_INPUT_STATUS, ®); + if (ret) + return ret; + + val->intval = !!(reg & AXP20X_PWR_STATUS_ACIN_AVAIL); + return 0; + + case POWER_SUPPLY_PROP_VOLTAGE_NOW: + ret = iio_read_channel_processed(power->acin_v, &val->intval); + if (ret) + return ret; + + /* IIO framework gives mV but Power Supply framework gives uV */ + val->intval *= 1000; + + return 0; + + case POWER_SUPPLY_PROP_CURRENT_NOW: + ret = iio_read_channel_processed(power->acin_i, &val->intval); + if (ret) + return ret; + + /* IIO framework gives mA but Power Supply framework gives uA */ + val->intval *= 1000; + + return 0; + + default: + return -EINVAL; + } + + return -EINVAL; +} + +static enum power_supply_property axp20x_ac_power_properties[] = { + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_ONLINE, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, +}; + +static enum power_supply_property axp22x_ac_power_properties[] = { + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_ONLINE, +}; + +static const struct power_supply_desc axp20x_ac_power_desc = { + .name = "axp20x-ac", + .type = POWER_SUPPLY_TYPE_MAINS, + .properties = axp20x_ac_power_properties, + .num_properties = ARRAY_SIZE(axp20x_ac_power_properties), + .get_property = axp20x_ac_power_get_property, +}; + +static const struct power_supply_desc axp22x_ac_power_desc = { + .name = "axp22x-ac", + .type = POWER_SUPPLY_TYPE_MAINS, + .properties = axp22x_ac_power_properties, + .num_properties = ARRAY_SIZE(axp22x_ac_power_properties), + .get_property = axp20x_ac_power_get_property, +}; + +struct axp_data { + const struct power_supply_desc *power_desc; + bool acin_adc; +}; + +static const struct axp_data axp20x_data = { + .power_desc = &axp20x_ac_power_desc, + .acin_adc = true, +}; + +static const struct axp_data axp22x_data = { + .power_desc = &axp22x_ac_power_desc, + .acin_adc = false, +}; + +static int axp20x_ac_power_probe(struct platform_device *pdev) +{ + struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent); + struct power_supply_config psy_cfg = {}; + struct axp20x_ac_power *power; + struct axp_data *axp_data; + static const char * const irq_names[] = { "ACIN_PLUGIN", "ACIN_REMOVAL", + NULL }; + int i, irq, ret; + + if (!of_device_is_available(pdev->dev.of_node)) + return -ENODEV; + + if (!axp20x) { + dev_err(&pdev->dev, "Parent drvdata not set\n"); + return -EINVAL; + } + + power = devm_kzalloc(&pdev->dev, sizeof(*power), GFP_KERNEL); + if (!power) + return -ENOMEM; + + axp_data = (struct axp_data *)of_device_get_match_data(&pdev->dev); + + if (axp_data->acin_adc) { + power->acin_v = devm_iio_channel_get(&pdev->dev, "acin_v"); + if (IS_ERR(power->acin_v)) { + if (PTR_ERR(power->acin_v) == -ENODEV) + return -EPROBE_DEFER; + return PTR_ERR(power->acin_v); + } + + power->acin_i = devm_iio_channel_get(&pdev->dev, "acin_i"); + if (IS_ERR(power->acin_i)) { + if (PTR_ERR(power->acin_i) == -ENODEV) + return -EPROBE_DEFER; + return PTR_ERR(power->acin_i); + } + } + + power->regmap = dev_get_regmap(pdev->dev.parent, NULL); + + platform_set_drvdata(pdev, power); + + psy_cfg.of_node = pdev->dev.of_node; + psy_cfg.drv_data = power; + + power->supply = devm_power_supply_register(&pdev->dev, + axp_data->power_desc, + &psy_cfg); + if (IS_ERR(power->supply)) + return PTR_ERR(power->supply); + + /* Request irqs after registering, as irqs may trigger immediately */ + for (i = 0; irq_names[i]; i++) { + irq = platform_get_irq_byname(pdev, irq_names[i]); + if (irq < 0) { + dev_warn(&pdev->dev, "No IRQ for %s: %d\n", + irq_names[i], irq); + continue; + } + irq = regmap_irq_get_virq(axp20x->regmap_irqc, irq); + ret = devm_request_any_context_irq(&pdev->dev, irq, + axp20x_ac_power_irq, 0, + DRVNAME, power); + if (ret < 0) + dev_warn(&pdev->dev, "Error requesting %s IRQ: %d\n", + irq_names[i], ret); + } + + return 0; +} + +static const struct of_device_id axp20x_ac_power_match[] = { + { + .compatible = "x-powers,axp202-ac-power-supply", + .data = (void *)&axp20x_data, + }, { + .compatible = "x-powers,axp221-ac-power-supply", + .data = (void *)&axp22x_data, + }, { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, axp20x_ac_power_match); + +static struct platform_driver axp20x_ac_power_driver = { + .probe = axp20x_ac_power_probe, + .driver = { + .name = DRVNAME, + .of_match_table = axp20x_ac_power_match, + }, +}; + +module_platform_driver(axp20x_ac_power_driver); + +MODULE_AUTHOR("Quentin Schulz <quentin.schulz@free-electrons.com>"); +MODULE_DESCRIPTION("AXP20X and AXP22X PMICs' AC power supply driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/power/supply/axp20x_usb_power.c b/drivers/power/supply/axp20x_usb_power.c index 6af6feb7058d..2397c482656e 100644 --- a/drivers/power/supply/axp20x_usb_power.c +++ b/drivers/power/supply/axp20x_usb_power.c @@ -17,10 +17,12 @@ #include <linux/mfd/axp20x.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/power_supply.h> #include <linux/regmap.h> #include <linux/slab.h> +#include <linux/iio/consumer.h> #define DRVNAME "axp20x-usb-power-supply" @@ -30,6 +32,8 @@ #define AXP20X_USB_STATUS_VBUS_VALID BIT(2) #define AXP20X_VBUS_VHOLD_uV(b) (4000000 + (((b) >> 3) & 7) * 100000) +#define AXP20X_VBUS_VHOLD_MASK GENMASK(5, 3) +#define AXP20X_VBUS_VHOLD_OFFSET 3 #define AXP20X_VBUS_CLIMIT_MASK 3 #define AXP20X_VBUC_CLIMIT_900mA 0 #define AXP20X_VBUC_CLIMIT_500mA 1 @@ -45,6 +49,9 @@ struct axp20x_usb_power { struct device_node *np; struct regmap *regmap; struct power_supply *supply; + enum axp20x_variants axp20x_id; + struct iio_channel *vbus_v; + struct iio_channel *vbus_i; }; static irqreturn_t axp20x_usb_power_irq(int irq, void *devid) @@ -72,6 +79,20 @@ static int axp20x_usb_power_get_property(struct power_supply *psy, val->intval = AXP20X_VBUS_VHOLD_uV(v); return 0; case POWER_SUPPLY_PROP_VOLTAGE_NOW: + if (IS_ENABLED(CONFIG_AXP20X_ADC)) { + ret = iio_read_channel_processed(power->vbus_v, + &val->intval); + if (ret) + return ret; + + /* + * IIO framework gives mV but Power Supply framework + * gives uV. + */ + val->intval *= 1000; + return 0; + } + ret = axp20x_read_variable_width(power->regmap, AXP20X_VBUS_V_ADC_H, 12); if (ret < 0) @@ -86,12 +107,10 @@ static int axp20x_usb_power_get_property(struct power_supply *psy, switch (v & AXP20X_VBUS_CLIMIT_MASK) { case AXP20X_VBUC_CLIMIT_100mA: - if (of_device_is_compatible(power->np, - "x-powers,axp202-usb-power-supply")) { - val->intval = 100000; - } else { + if (power->axp20x_id == AXP221_ID) val->intval = -1; /* No 100mA limit */ - } + else + val->intval = 100000; break; case AXP20X_VBUC_CLIMIT_500mA: val->intval = 500000; @@ -105,6 +124,20 @@ static int axp20x_usb_power_get_property(struct power_supply *psy, } return 0; case POWER_SUPPLY_PROP_CURRENT_NOW: + if (IS_ENABLED(CONFIG_AXP20X_ADC)) { + ret = iio_read_channel_processed(power->vbus_i, + &val->intval); + if (ret) + return ret; + + /* + * IIO framework gives mA but Power Supply framework + * gives uA. + */ + val->intval *= 1000; + return 0; + } + ret = axp20x_read_variable_width(power->regmap, AXP20X_VBUS_I_ADC_H, 12); if (ret < 0) @@ -130,8 +163,7 @@ static int axp20x_usb_power_get_property(struct power_supply *psy, val->intval = POWER_SUPPLY_HEALTH_GOOD; - if (of_device_is_compatible(power->np, - "x-powers,axp202-usb-power-supply")) { + if (power->axp20x_id == AXP202_ID) { ret = regmap_read(power->regmap, AXP20X_USB_OTG_STATUS, &v); if (ret) @@ -155,6 +187,81 @@ static int axp20x_usb_power_get_property(struct power_supply *psy, return 0; } +static int axp20x_usb_power_set_voltage_min(struct axp20x_usb_power *power, + int intval) +{ + int val; + + switch (intval) { + case 4000000: + case 4100000: + case 4200000: + case 4300000: + case 4400000: + case 4500000: + case 4600000: + case 4700000: + val = (intval - 4000000) / 100000; + return regmap_update_bits(power->regmap, + AXP20X_VBUS_IPSOUT_MGMT, + AXP20X_VBUS_VHOLD_MASK, + val << AXP20X_VBUS_VHOLD_OFFSET); + default: + return -EINVAL; + } + + return -EINVAL; +} + +static int axp20x_usb_power_set_current_max(struct axp20x_usb_power *power, + int intval) +{ + int val; + + switch (intval) { + case 100000: + if (power->axp20x_id == AXP221_ID) + return -EINVAL; + case 500000: + case 900000: + val = (900000 - intval) / 400000; + return regmap_update_bits(power->regmap, + AXP20X_VBUS_IPSOUT_MGMT, + AXP20X_VBUS_CLIMIT_MASK, val); + default: + return -EINVAL; + } + + return -EINVAL; +} + +static int axp20x_usb_power_set_property(struct power_supply *psy, + enum power_supply_property psp, + const union power_supply_propval *val) +{ + struct axp20x_usb_power *power = power_supply_get_drvdata(psy); + + switch (psp) { + case POWER_SUPPLY_PROP_VOLTAGE_MIN: + return axp20x_usb_power_set_voltage_min(power, val->intval); + + case POWER_SUPPLY_PROP_CURRENT_MAX: + return axp20x_usb_power_set_current_max(power, val->intval); + + default: + return -EINVAL; + } + + return -EINVAL; +} + +static int axp20x_usb_power_prop_writeable(struct power_supply *psy, + enum power_supply_property psp) +{ + return psp == POWER_SUPPLY_PROP_VOLTAGE_MIN || + psp == POWER_SUPPLY_PROP_CURRENT_MAX; +} + static enum power_supply_property axp20x_usb_power_properties[] = { POWER_SUPPLY_PROP_HEALTH, POWER_SUPPLY_PROP_PRESENT, @@ -178,7 +285,9 @@ static const struct power_supply_desc axp20x_usb_power_desc = { .type = POWER_SUPPLY_TYPE_USB, .properties = axp20x_usb_power_properties, .num_properties = ARRAY_SIZE(axp20x_usb_power_properties), + .property_is_writeable = axp20x_usb_power_prop_writeable, .get_property = axp20x_usb_power_get_property, + .set_property = axp20x_usb_power_set_property, }; static const struct power_supply_desc axp22x_usb_power_desc = { @@ -186,9 +295,41 @@ static const struct power_supply_desc axp22x_usb_power_desc = { .type = POWER_SUPPLY_TYPE_USB, .properties = axp22x_usb_power_properties, .num_properties = ARRAY_SIZE(axp22x_usb_power_properties), + .property_is_writeable = axp20x_usb_power_prop_writeable, .get_property = axp20x_usb_power_get_property, + .set_property = axp20x_usb_power_set_property, }; +static int configure_iio_channels(struct platform_device *pdev, + struct axp20x_usb_power *power) +{ + power->vbus_v = devm_iio_channel_get(&pdev->dev, "vbus_v"); + if (IS_ERR(power->vbus_v)) { + if (PTR_ERR(power->vbus_v) == -ENODEV) + return -EPROBE_DEFER; + return PTR_ERR(power->vbus_v); + } + + power->vbus_i = devm_iio_channel_get(&pdev->dev, "vbus_i"); + if (IS_ERR(power->vbus_i)) { + if (PTR_ERR(power->vbus_i) == -ENODEV) + return -EPROBE_DEFER; + return PTR_ERR(power->vbus_i); + } + + return 0; +} + +static int configure_adc_registers(struct axp20x_usb_power *power) +{ + /* Enable vbus voltage and current measurement */ + return regmap_update_bits(power->regmap, AXP20X_ADC_EN1, + AXP20X_ADC_EN1_VBUS_CURR | + AXP20X_ADC_EN1_VBUS_VOLT, + AXP20X_ADC_EN1_VBUS_CURR | + AXP20X_ADC_EN1_VBUS_VOLT); +} + static int axp20x_usb_power_probe(struct platform_device *pdev) { struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent); @@ -214,11 +355,13 @@ static int axp20x_usb_power_probe(struct platform_device *pdev) if (!power) return -ENOMEM; + power->axp20x_id = (enum axp20x_variants)of_device_get_match_data( + &pdev->dev); + power->np = pdev->dev.of_node; power->regmap = axp20x->regmap; - if (of_device_is_compatible(power->np, - "x-powers,axp202-usb-power-supply")) { + if (power->axp20x_id == AXP202_ID) { /* Enable vbus valid checking */ ret = regmap_update_bits(power->regmap, AXP20X_VBUS_MON, AXP20X_VBUS_MON_VBUS_VALID, @@ -226,17 +369,18 @@ static int axp20x_usb_power_probe(struct platform_device *pdev) if (ret) return ret; - /* Enable vbus voltage and current measurement */ - ret = regmap_update_bits(power->regmap, AXP20X_ADC_EN1, - AXP20X_ADC_EN1_VBUS_CURR | AXP20X_ADC_EN1_VBUS_VOLT, - AXP20X_ADC_EN1_VBUS_CURR | AXP20X_ADC_EN1_VBUS_VOLT); + if (IS_ENABLED(CONFIG_AXP20X_ADC)) + ret = configure_iio_channels(pdev, power); + else + ret = configure_adc_registers(power); + if (ret) return ret; usb_power_desc = &axp20x_usb_power_desc; irq_names = axp20x_irq_names; - } else if (of_device_is_compatible(power->np, - "x-powers,axp221-usb-power-supply")) { + } else if (power->axp20x_id == AXP221_ID || + power->axp20x_id == AXP223_ID) { usb_power_desc = &axp22x_usb_power_desc; irq_names = axp22x_irq_names; } else { @@ -273,9 +417,16 @@ static int axp20x_usb_power_probe(struct platform_device *pdev) } static const struct of_device_id axp20x_usb_power_match[] = { - { .compatible = "x-powers,axp202-usb-power-supply" }, - { .compatible = "x-powers,axp221-usb-power-supply" }, - { } + { + .compatible = "x-powers,axp202-usb-power-supply", + .data = (void *)AXP202_ID, + }, { + .compatible = "x-powers,axp221-usb-power-supply", + .data = (void *)AXP221_ID, + }, { + .compatible = "x-powers,axp223-usb-power-supply", + .data = (void *)AXP223_ID, + }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, axp20x_usb_power_match); diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c index 75b8e0c7402b..6be2fe27bb07 100644 --- a/drivers/power/supply/axp288_charger.c +++ b/drivers/power/supply/axp288_charger.c @@ -90,20 +90,6 @@ #define CHRG_VLTFC_0C 0xA5 /* 0 DegC */ #define CHRG_VHTFC_45C 0x1F /* 45 DegC */ -#define BAT_IRQ_CFG_CHRG_DONE (1 << 2) -#define BAT_IRQ_CFG_CHRG_START (1 << 3) -#define BAT_IRQ_CFG_BAT_SAFE_EXIT (1 << 4) -#define BAT_IRQ_CFG_BAT_SAFE_ENTER (1 << 5) -#define BAT_IRQ_CFG_BAT_DISCON (1 << 6) -#define BAT_IRQ_CFG_BAT_CONN (1 << 7) -#define BAT_IRQ_CFG_BAT_MASK 0xFC - -#define TEMP_IRQ_CFG_QCBTU (1 << 4) -#define TEMP_IRQ_CFG_CBTU (1 << 5) -#define TEMP_IRQ_CFG_QCBTO (1 << 6) -#define TEMP_IRQ_CFG_CBTO (1 << 7) -#define TEMP_IRQ_CFG_MASK 0xF0 - #define FG_CNTL_OCV_ADJ_EN (1 << 3) #define CV_4100MV 4100 /* 4100mV */ @@ -127,6 +113,10 @@ #define ILIM_3000MA 3000 /* 3000mA */ #define AXP288_EXTCON_DEV_NAME "axp288_extcon" +#define USB_HOST_EXTCON_DEV_NAME "INT3496:00" + +static const unsigned int cable_ids[] = + { EXTCON_CHG_USB_SDP, EXTCON_CHG_USB_CDP, EXTCON_CHG_USB_DCP }; enum { VBUS_OV_IRQ = 0, @@ -143,7 +133,6 @@ enum { struct axp288_chrg_info { struct platform_device *pdev; - struct axp20x_chrg_pdata *pdata; struct regmap *regmap; struct regmap_irq_chip_data *regmap_irqc; int irq[CHRG_INTR_END]; @@ -163,20 +152,16 @@ struct axp288_chrg_info { struct extcon_dev *edev; bool connected; enum power_supply_type chg_type; - struct notifier_block nb; + struct notifier_block nb[ARRAY_SIZE(cable_ids)]; struct work_struct work; } cable; - int health; int inlmt; int cc; int cv; int max_cc; int max_cv; - bool online; - bool present; - bool enable_charger; - bool is_charger_enabled; + int is_charger_enabled; }; static inline int axp288_charger_set_cc(struct axp288_chrg_info *info, int cc) @@ -305,6 +290,9 @@ static int axp288_charger_enable_charger(struct axp288_chrg_info *info, { int ret; + if ((int)enable == info->is_charger_enabled) + return 0; + if (enable) ret = regmap_update_bits(info->regmap, AXP20X_CHRG_CTRL1, CHRG_CCCV_CHG_EN, CHRG_CCCV_CHG_EN); @@ -430,8 +418,7 @@ static int axp288_charger_usb_get_property(struct power_supply *psy, ret = axp288_charger_is_present(info); if (ret < 0) goto psy_get_prop_fail; - info->present = ret; - val->intval = info->present; + val->intval = ret; break; case POWER_SUPPLY_PROP_ONLINE: /* Check for OTG case first */ @@ -442,8 +429,7 @@ static int axp288_charger_usb_get_property(struct power_supply *psy, ret = axp288_charger_is_online(info); if (ret < 0) goto psy_get_prop_fail; - info->online = ret; - val->intval = info->online; + val->intval = ret; break; case POWER_SUPPLY_PROP_HEALTH: val->intval = axp288_get_charger_health(info); @@ -576,20 +562,20 @@ static void axp288_charger_extcon_evt_worker(struct work_struct *work) struct axp288_chrg_info *info = container_of(work, struct axp288_chrg_info, cable.work); int ret, current_limit; - bool changed = false; struct extcon_dev *edev = info->cable.edev; bool old_connected = info->cable.connected; + enum power_supply_type old_chg_type = info->cable.chg_type; /* Determine cable/charger type */ - if (extcon_get_cable_state_(edev, EXTCON_CHG_USB_SDP) > 0) { + if (extcon_get_state(edev, EXTCON_CHG_USB_SDP) > 0) { dev_dbg(&info->pdev->dev, "USB SDP charger is connected"); info->cable.connected = true; info->cable.chg_type = POWER_SUPPLY_TYPE_USB; - } else if (extcon_get_cable_state_(edev, EXTCON_CHG_USB_CDP) > 0) { + } else if (extcon_get_state(edev, EXTCON_CHG_USB_CDP) > 0) { dev_dbg(&info->pdev->dev, "USB CDP charger is connected"); info->cable.connected = true; info->cable.chg_type = POWER_SUPPLY_TYPE_USB_CDP; - } else if (extcon_get_cable_state_(edev, EXTCON_CHG_USB_DCP) > 0) { + } else if (extcon_get_state(edev, EXTCON_CHG_USB_DCP) > 0) { dev_dbg(&info->pdev->dev, "USB DCP charger is connected"); info->cable.connected = true; info->cable.chg_type = POWER_SUPPLY_TYPE_USB_DCP; @@ -601,22 +587,15 @@ static void axp288_charger_extcon_evt_worker(struct work_struct *work) } /* Cable status changed */ - if (old_connected != info->cable.connected) - changed = true; - - if (!changed) + if (old_connected == info->cable.connected && + old_chg_type == info->cable.chg_type) return; mutex_lock(&info->lock); - if (info->is_charger_enabled && !info->cable.connected) { - info->enable_charger = false; - ret = axp288_charger_enable_charger(info, info->enable_charger); - if (ret < 0) - dev_err(&info->pdev->dev, - "cannot disable charger (%d)", ret); + if (info->cable.connected) { + axp288_charger_enable_charger(info, false); - } else if (!info->is_charger_enabled && info->cable.connected) { switch (info->cable.chg_type) { case POWER_SUPPLY_TYPE_USB: current_limit = ILIM_500MA; @@ -635,36 +614,49 @@ static void axp288_charger_extcon_evt_worker(struct work_struct *work) /* Set vbus current limit first, then enable charger */ ret = axp288_charger_set_vbus_inlmt(info, current_limit); - if (ret < 0) { + if (ret == 0) + axp288_charger_enable_charger(info, true); + else dev_err(&info->pdev->dev, "error setting current limit (%d)", ret); - } else { - info->enable_charger = (current_limit > 0); - ret = axp288_charger_enable_charger(info, - info->enable_charger); - if (ret < 0) - dev_err(&info->pdev->dev, - "cannot enable charger (%d)", ret); - } + } else { + axp288_charger_enable_charger(info, false); } - if (changed) - info->health = axp288_get_charger_health(info); - mutex_unlock(&info->lock); - if (changed) - power_supply_changed(info->psy_usb); + power_supply_changed(info->psy_usb); } -static int axp288_charger_handle_cable_evt(struct notifier_block *nb, - unsigned long event, void *param) +/* + * We need 3 copies of this, because there is no way to find out for which + * cable id we are being called from the passed in arguments; and we must + * have a separate nb for each extcon_register_notifier call. + */ +static int axp288_charger_handle_cable0_evt(struct notifier_block *nb, + unsigned long event, void *param) { struct axp288_chrg_info *info = - container_of(nb, struct axp288_chrg_info, cable.nb); + container_of(nb, struct axp288_chrg_info, cable.nb[0]); + schedule_work(&info->cable.work); + return NOTIFY_OK; +} +static int axp288_charger_handle_cable1_evt(struct notifier_block *nb, + unsigned long event, void *param) +{ + struct axp288_chrg_info *info = + container_of(nb, struct axp288_chrg_info, cable.nb[1]); schedule_work(&info->cable.work); + return NOTIFY_OK; +} +static int axp288_charger_handle_cable2_evt(struct notifier_block *nb, + unsigned long event, void *param) +{ + struct axp288_chrg_info *info = + container_of(nb, struct axp288_chrg_info, cable.nb[2]); + schedule_work(&info->cable.work); return NOTIFY_OK; } @@ -672,7 +664,17 @@ static void axp288_charger_otg_evt_worker(struct work_struct *work) { struct axp288_chrg_info *info = container_of(work, struct axp288_chrg_info, otg.work); - int ret; + struct extcon_dev *edev = info->otg.cable; + int ret, usb_host = extcon_get_state(edev, EXTCON_USB_HOST); + + dev_dbg(&info->pdev->dev, "external connector USB-Host is %s\n", + usb_host ? "attached" : "detached"); + + /* + * Set usb_id_short flag to avoid running charger detection logic + * in case usb host. + */ + info->otg.id_short = usb_host; /* Disable VBUS path before enabling the 5V boost */ ret = axp288_charger_vbus_path_select(info, !info->otg.id_short); @@ -685,135 +687,109 @@ static int axp288_charger_handle_otg_evt(struct notifier_block *nb, { struct axp288_chrg_info *info = container_of(nb, struct axp288_chrg_info, otg.id_nb); - struct extcon_dev *edev = info->otg.cable; - int usb_host = extcon_get_cable_state_(edev, EXTCON_USB_HOST); - dev_dbg(&info->pdev->dev, "external connector USB-Host is %s\n", - usb_host ? "attached" : "detached"); - - /* - * Set usb_id_short flag to avoid running charger detection logic - * in case usb host. - */ - info->otg.id_short = usb_host; schedule_work(&info->otg.work); return NOTIFY_OK; } -static void charger_init_hw_regs(struct axp288_chrg_info *info) +static int charger_init_hw_regs(struct axp288_chrg_info *info) { int ret, cc, cv; unsigned int val; /* Program temperature thresholds */ ret = regmap_write(info->regmap, AXP20X_V_LTF_CHRG, CHRG_VLTFC_0C); - if (ret < 0) - dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n", + if (ret < 0) { + dev_err(&info->pdev->dev, "register(%x) write error(%d)\n", AXP20X_V_LTF_CHRG, ret); + return ret; + } ret = regmap_write(info->regmap, AXP20X_V_HTF_CHRG, CHRG_VHTFC_45C); - if (ret < 0) - dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n", + if (ret < 0) { + dev_err(&info->pdev->dev, "register(%x) write error(%d)\n", AXP20X_V_HTF_CHRG, ret); + return ret; + } /* Do not turn-off charger o/p after charge cycle ends */ ret = regmap_update_bits(info->regmap, AXP20X_CHRG_CTRL2, - CNTL2_CHG_OUT_TURNON, 1); - if (ret < 0) - dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n", + CNTL2_CHG_OUT_TURNON, CNTL2_CHG_OUT_TURNON); + if (ret < 0) { + dev_err(&info->pdev->dev, "register(%x) write error(%d)\n", AXP20X_CHRG_CTRL2, ret); - - /* Enable interrupts */ - ret = regmap_update_bits(info->regmap, - AXP20X_IRQ2_EN, - BAT_IRQ_CFG_BAT_MASK, 1); - if (ret < 0) - dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n", - AXP20X_IRQ2_EN, ret); - - ret = regmap_update_bits(info->regmap, AXP20X_IRQ3_EN, - TEMP_IRQ_CFG_MASK, 1); - if (ret < 0) - dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n", - AXP20X_IRQ3_EN, ret); + return ret; + } /* Setup ending condition for charging to be 10% of I(chrg) */ ret = regmap_update_bits(info->regmap, AXP20X_CHRG_CTRL1, CHRG_CCCV_ITERM_20P, 0); - if (ret < 0) - dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n", + if (ret < 0) { + dev_err(&info->pdev->dev, "register(%x) write error(%d)\n", AXP20X_CHRG_CTRL1, ret); + return ret; + } /* Disable OCV-SOC curve calibration */ ret = regmap_update_bits(info->regmap, AXP20X_CC_CTRL, FG_CNTL_OCV_ADJ_EN, 0); - if (ret < 0) - dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n", + if (ret < 0) { + dev_err(&info->pdev->dev, "register(%x) write error(%d)\n", AXP20X_CC_CTRL, ret); - - /* Init charging current and voltage */ - info->max_cc = info->pdata->max_cc; - info->max_cv = info->pdata->max_cv; + return ret; + } /* Read current charge voltage and current limit */ ret = regmap_read(info->regmap, AXP20X_CHRG_CTRL1, &val); if (ret < 0) { - /* Assume default if cannot read */ - info->cc = info->pdata->def_cc; - info->cv = info->pdata->def_cv; - } else { - /* Determine charge voltage */ - cv = (val & CHRG_CCCV_CV_MASK) >> CHRG_CCCV_CV_BIT_POS; - switch (cv) { - case CHRG_CCCV_CV_4100MV: - info->cv = CV_4100MV; - break; - case CHRG_CCCV_CV_4150MV: - info->cv = CV_4150MV; - break; - case CHRG_CCCV_CV_4200MV: - info->cv = CV_4200MV; - break; - case CHRG_CCCV_CV_4350MV: - info->cv = CV_4350MV; - break; - default: - info->cv = INT_MAX; - break; - } + dev_err(&info->pdev->dev, "register(%x) read error(%d)\n", + AXP20X_CHRG_CTRL1, ret); + return ret; + } - /* Determine charge current limit */ - cc = (ret & CHRG_CCCV_CC_MASK) >> CHRG_CCCV_CC_BIT_POS; - cc = (cc * CHRG_CCCV_CC_LSB_RES) + CHRG_CCCV_CC_OFFSET; - info->cc = cc; + /* Determine charge voltage */ + cv = (val & CHRG_CCCV_CV_MASK) >> CHRG_CCCV_CV_BIT_POS; + switch (cv) { + case CHRG_CCCV_CV_4100MV: + info->cv = CV_4100MV; + break; + case CHRG_CCCV_CV_4150MV: + info->cv = CV_4150MV; + break; + case CHRG_CCCV_CV_4200MV: + info->cv = CV_4200MV; + break; + case CHRG_CCCV_CV_4350MV: + info->cv = CV_4350MV; + break; + } - /* Program default charging voltage and current */ - cc = min(info->pdata->def_cc, info->max_cc); - cv = min(info->pdata->def_cv, info->max_cv); + /* Determine charge current limit */ + cc = (ret & CHRG_CCCV_CC_MASK) >> CHRG_CCCV_CC_BIT_POS; + cc = (cc * CHRG_CCCV_CC_LSB_RES) + CHRG_CCCV_CC_OFFSET; + info->cc = cc; - ret = axp288_charger_set_cc(info, cc); - if (ret < 0) - dev_warn(&info->pdev->dev, - "error(%d) in setting CC\n", ret); + /* + * Do not allow the user to configure higher settings then those + * set by the firmware + */ + info->max_cv = info->cv; + info->max_cc = info->cc; - ret = axp288_charger_set_cv(info, cv); - if (ret < 0) - dev_warn(&info->pdev->dev, - "error(%d) in setting CV\n", ret); - } + return 0; } static int axp288_charger_probe(struct platform_device *pdev) { int ret, i, pirq; struct axp288_chrg_info *info; + struct device *dev = &pdev->dev; struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent); struct power_supply_config charger_cfg = {}; - info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; @@ -821,15 +797,8 @@ static int axp288_charger_probe(struct platform_device *pdev) info->pdev = pdev; info->regmap = axp20x->regmap; info->regmap_irqc = axp20x->regmap_irqc; - info->pdata = pdev->dev.platform_data; - - if (!info->pdata) { - /* Try ACPI provided pdata via device properties */ - if (!device_property_present(&pdev->dev, - "axp288_charger_data\n")) - dev_err(&pdev->dev, "failed to get platform data\n"); - return -ENODEV; - } + info->cable.chg_type = -1; + info->is_charger_enabled = -1; info->cable.edev = extcon_get_extcon_dev(AXP288_EXTCON_DEV_NAME); if (info->cable.edev == NULL) { @@ -838,63 +807,55 @@ static int axp288_charger_probe(struct platform_device *pdev) return -EPROBE_DEFER; } - /* Register for extcon notification */ - INIT_WORK(&info->cable.work, axp288_charger_extcon_evt_worker); - info->cable.nb.notifier_call = axp288_charger_handle_cable_evt; - ret = extcon_register_notifier(info->cable.edev, EXTCON_CHG_USB_SDP, - &info->cable.nb); - if (ret) { - dev_err(&info->pdev->dev, - "failed to register extcon notifier for SDP %d\n", ret); - return ret; - } - - ret = extcon_register_notifier(info->cable.edev, EXTCON_CHG_USB_CDP, - &info->cable.nb); - if (ret) { - dev_err(&info->pdev->dev, - "failed to register extcon notifier for CDP %d\n", ret); - extcon_unregister_notifier(info->cable.edev, - EXTCON_CHG_USB_SDP, &info->cable.nb); - return ret; - } - - ret = extcon_register_notifier(info->cable.edev, EXTCON_CHG_USB_DCP, - &info->cable.nb); - if (ret) { - dev_err(&info->pdev->dev, - "failed to register extcon notifier for DCP %d\n", ret); - extcon_unregister_notifier(info->cable.edev, - EXTCON_CHG_USB_SDP, &info->cable.nb); - extcon_unregister_notifier(info->cable.edev, - EXTCON_CHG_USB_CDP, &info->cable.nb); - return ret; + info->otg.cable = extcon_get_extcon_dev(USB_HOST_EXTCON_DEV_NAME); + if (info->otg.cable == NULL) { + dev_dbg(dev, "EXTCON_USB_HOST is not ready, probe deferred\n"); + return -EPROBE_DEFER; } platform_set_drvdata(pdev, info); mutex_init(&info->lock); + ret = charger_init_hw_regs(info); + if (ret) + return ret; + /* Register with power supply class */ charger_cfg.drv_data = info; - info->psy_usb = power_supply_register(&pdev->dev, &axp288_charger_desc, - &charger_cfg); + info->psy_usb = devm_power_supply_register(dev, &axp288_charger_desc, + &charger_cfg); if (IS_ERR(info->psy_usb)) { - dev_err(&pdev->dev, "failed to register power supply charger\n"); ret = PTR_ERR(info->psy_usb); - goto psy_reg_failed; + dev_err(dev, "failed to register power supply: %d\n", ret); + return ret; + } + + /* Register for extcon notification */ + INIT_WORK(&info->cable.work, axp288_charger_extcon_evt_worker); + info->cable.nb[0].notifier_call = axp288_charger_handle_cable0_evt; + info->cable.nb[1].notifier_call = axp288_charger_handle_cable1_evt; + info->cable.nb[2].notifier_call = axp288_charger_handle_cable2_evt; + for (i = 0; i < ARRAY_SIZE(cable_ids); i++) { + ret = devm_extcon_register_notifier(dev, info->cable.edev, + cable_ids[i], &info->cable.nb[i]); + if (ret) { + dev_err(dev, "failed to register extcon notifier for %u: %d\n", + cable_ids[i], ret); + return ret; + } } + schedule_work(&info->cable.work); /* Register for OTG notification */ INIT_WORK(&info->otg.work, axp288_charger_otg_evt_worker); info->otg.id_nb.notifier_call = axp288_charger_handle_otg_evt; - ret = extcon_register_notifier(info->otg.cable, EXTCON_USB_HOST, - &info->otg.id_nb); - if (ret) - dev_warn(&pdev->dev, "failed to register otg notifier\n"); - - if (info->otg.cable) - info->otg.id_short = extcon_get_cable_state_( - info->otg.cable, EXTCON_USB_HOST); + ret = devm_extcon_register_notifier(&pdev->dev, info->otg.cable, + EXTCON_USB_HOST, &info->otg.id_nb); + if (ret) { + dev_err(dev, "failed to register EXTCON_USB_HOST notifier\n"); + return ret; + } + schedule_work(&info->otg.work); /* Register charger interrupts */ for (i = 0; i < CHRG_INTR_END; i++) { @@ -903,8 +864,7 @@ static int axp288_charger_probe(struct platform_device *pdev) if (info->irq[i] < 0) { dev_warn(&info->pdev->dev, "failed to get virtual interrupt=%d\n", pirq); - ret = info->irq[i]; - goto intr_reg_failed; + return info->irq[i]; } ret = devm_request_threaded_irq(&info->pdev->dev, info->irq[i], NULL, axp288_charger_irq_thread_handler, @@ -912,51 +872,22 @@ static int axp288_charger_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to request interrupt=%d\n", info->irq[i]); - goto intr_reg_failed; + return ret; } } - charger_init_hw_regs(info); - return 0; - -intr_reg_failed: - if (info->otg.cable) - extcon_unregister_notifier(info->otg.cable, EXTCON_USB_HOST, - &info->otg.id_nb); - power_supply_unregister(info->psy_usb); -psy_reg_failed: - extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_SDP, - &info->cable.nb); - extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_CDP, - &info->cable.nb); - extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_DCP, - &info->cable.nb); - return ret; } -static int axp288_charger_remove(struct platform_device *pdev) -{ - struct axp288_chrg_info *info = dev_get_drvdata(&pdev->dev); - - if (info->otg.cable) - extcon_unregister_notifier(info->otg.cable, EXTCON_USB_HOST, - &info->otg.id_nb); - - extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_SDP, - &info->cable.nb); - extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_CDP, - &info->cable.nb); - extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_DCP, - &info->cable.nb); - power_supply_unregister(info->psy_usb); - - return 0; -} +static const struct platform_device_id axp288_charger_id_table[] = { + { .name = "axp288_charger" }, + {}, +}; +MODULE_DEVICE_TABLE(platform, axp288_charger_id_table); static struct platform_driver axp288_charger_driver = { .probe = axp288_charger_probe, - .remove = axp288_charger_remove, + .id_table = axp288_charger_id_table, .driver = { .name = "axp288_charger", }, diff --git a/drivers/power/supply/axp288_fuel_gauge.c b/drivers/power/supply/axp288_fuel_gauge.c index 539eb41504bb..a8dcabc32721 100644 --- a/drivers/power/supply/axp288_fuel_gauge.c +++ b/drivers/power/supply/axp288_fuel_gauge.c @@ -29,6 +29,7 @@ #include <linux/iio/consumer.h> #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <asm/unaligned.h> #define CHRG_STAT_BAT_SAFE_MODE (1 << 3) #define CHRG_STAT_BAT_VALID (1 << 4) @@ -49,23 +50,6 @@ #define CHRG_CCCV_CV_4350MV 0x3 /* 4.35V */ #define CHRG_CCCV_CHG_EN (1 << 7) -#define CV_4100 4100 /* 4100mV */ -#define CV_4150 4150 /* 4150mV */ -#define CV_4200 4200 /* 4200mV */ -#define CV_4350 4350 /* 4350mV */ - -#define TEMP_IRQ_CFG_QWBTU (1 << 0) -#define TEMP_IRQ_CFG_WBTU (1 << 1) -#define TEMP_IRQ_CFG_QWBTO (1 << 2) -#define TEMP_IRQ_CFG_WBTO (1 << 3) -#define TEMP_IRQ_CFG_MASK 0xf - -#define FG_IRQ_CFG_LOWBATT_WL2 (1 << 0) -#define FG_IRQ_CFG_LOWBATT_WL1 (1 << 1) -#define FG_IRQ_CFG_LOWBATT_MASK 0x3 -#define LOWBAT_IRQ_STAT_LOWBATT_WL2 (1 << 0) -#define LOWBAT_IRQ_STAT_LOWBATT_WL1 (1 << 1) - #define FG_CNTL_OCV_ADJ_STAT (1 << 2) #define FG_CNTL_OCV_ADJ_EN (1 << 3) #define FG_CNTL_CAP_ADJ_STAT (1 << 4) @@ -73,17 +57,15 @@ #define FG_CNTL_CC_EN (1 << 6) #define FG_CNTL_GAUGE_EN (1 << 7) +#define FG_15BIT_WORD_VALID (1 << 15) +#define FG_15BIT_VAL_MASK 0x7fff + #define FG_REP_CAP_VALID (1 << 7) #define FG_REP_CAP_VAL_MASK 0x7F #define FG_DES_CAP1_VALID (1 << 7) -#define FG_DES_CAP1_VAL_MASK 0x7F -#define FG_DES_CAP0_VAL_MASK 0xFF #define FG_DES_CAP_RES_LSB 1456 /* 1.456mAhr */ -#define FG_CC_MTR1_VALID (1 << 7) -#define FG_CC_MTR1_VAL_MASK 0x7F -#define FG_CC_MTR0_VAL_MASK 0xFF #define FG_DES_CC_RES_LSB 1456 /* 1.456mAhr */ #define FG_OCV_CAP_VALID (1 << 7) @@ -104,9 +86,7 @@ /* 1.1mV per LSB expressed in uV */ #define VOLTAGE_FROM_ADC(a) ((a * 11) / 10) -/* properties converted to tenths of degrees, uV, uA, uW */ -#define PROP_TEMP(a) ((a) * 10) -#define UNPROP_TEMP(a) ((a) / 10) +/* properties converted to uV, uA */ #define PROP_VOLT(a) ((a) * 1000) #define PROP_CURR(a) ((a) * 1000) @@ -122,13 +102,13 @@ enum { struct axp288_fg_info { struct platform_device *pdev; - struct axp20x_fg_pdata *pdata; struct regmap *regmap; struct regmap_irq_chip_data *regmap_irqc; int irq[AXP288_FG_INTR_NUM]; struct power_supply *bat; struct mutex lock; int status; + int max_volt; struct delayed_work status_monitor; struct dentry *debug_file; }; @@ -138,22 +118,14 @@ static enum power_supply_property fuel_gauge_props[] = { POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_HEALTH, POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN, - POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN, POWER_SUPPLY_PROP_VOLTAGE_NOW, POWER_SUPPLY_PROP_VOLTAGE_OCV, POWER_SUPPLY_PROP_CURRENT_NOW, POWER_SUPPLY_PROP_CAPACITY, POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN, - POWER_SUPPLY_PROP_TEMP, - POWER_SUPPLY_PROP_TEMP_MAX, - POWER_SUPPLY_PROP_TEMP_MIN, - POWER_SUPPLY_PROP_TEMP_ALERT_MIN, - POWER_SUPPLY_PROP_TEMP_ALERT_MAX, POWER_SUPPLY_PROP_TECHNOLOGY, POWER_SUPPLY_PROP_CHARGE_FULL, POWER_SUPPLY_PROP_CHARGE_NOW, - POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, - POWER_SUPPLY_PROP_MODEL_NAME, }; static int fuel_gauge_reg_readb(struct axp288_fg_info *info, int reg) @@ -169,8 +141,10 @@ static int fuel_gauge_reg_readb(struct axp288_fg_info *info, int reg) break; } - if (ret < 0) + if (ret < 0) { dev_err(&info->pdev->dev, "axp288 reg read err:%d\n", ret); + return ret; + } return val; } @@ -187,6 +161,44 @@ static int fuel_gauge_reg_writeb(struct axp288_fg_info *info, int reg, u8 val) return ret; } +static int fuel_gauge_read_15bit_word(struct axp288_fg_info *info, int reg) +{ + unsigned char buf[2]; + int ret; + + ret = regmap_bulk_read(info->regmap, reg, buf, 2); + if (ret < 0) { + dev_err(&info->pdev->dev, "Error reading reg 0x%02x err: %d\n", + reg, ret); + return ret; + } + + ret = get_unaligned_be16(buf); + if (!(ret & FG_15BIT_WORD_VALID)) { + dev_err(&info->pdev->dev, "Error reg 0x%02x contents not valid\n", + reg); + return -ENXIO; + } + + return ret & FG_15BIT_VAL_MASK; +} + +static int fuel_gauge_read_12bit_word(struct axp288_fg_info *info, int reg) +{ + unsigned char buf[2]; + int ret; + + ret = regmap_bulk_read(info->regmap, reg, buf, 2); + if (ret < 0) { + dev_err(&info->pdev->dev, "Error reading reg 0x%02x err: %d\n", + reg, ret); + return ret; + } + + /* 12-bit data values have upper 8 bits in buf[0], lower 4 in buf[1] */ + return (buf[0] << 4) | ((buf[1] >> 4) & 0x0f); +} + static int pmic_read_adc_val(const char *name, int *raw_val, struct axp288_fg_info *info) { @@ -247,24 +259,15 @@ static int fuel_gauge_debug_show(struct seq_file *s, void *data) seq_printf(s, " FG_RDC0[%02x] : %02x\n", AXP288_FG_RDC0_REG, fuel_gauge_reg_readb(info, AXP288_FG_RDC0_REG)); - seq_printf(s, " FG_OCVH[%02x] : %02x\n", + seq_printf(s, " FG_OCV[%02x] : %04x\n", AXP288_FG_OCVH_REG, - fuel_gauge_reg_readb(info, AXP288_FG_OCVH_REG)); - seq_printf(s, " FG_OCVL[%02x] : %02x\n", - AXP288_FG_OCVL_REG, - fuel_gauge_reg_readb(info, AXP288_FG_OCVL_REG)); - seq_printf(s, "FG_DES_CAP1[%02x] : %02x\n", + fuel_gauge_read_12bit_word(info, AXP288_FG_OCVH_REG)); + seq_printf(s, " FG_DES_CAP[%02x] : %04x\n", AXP288_FG_DES_CAP1_REG, - fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG)); - seq_printf(s, "FG_DES_CAP0[%02x] : %02x\n", - AXP288_FG_DES_CAP0_REG, - fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP0_REG)); - seq_printf(s, " FG_CC_MTR1[%02x] : %02x\n", + fuel_gauge_read_15bit_word(info, AXP288_FG_DES_CAP1_REG)); + seq_printf(s, " FG_CC_MTR[%02x] : %04x\n", AXP288_FG_CC_MTR1_REG, - fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR1_REG)); - seq_printf(s, " FG_CC_MTR0[%02x] : %02x\n", - AXP288_FG_CC_MTR0_REG, - fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR0_REG)); + fuel_gauge_read_15bit_word(info, AXP288_FG_CC_MTR1_REG)); seq_printf(s, " FG_OCV_CAP[%02x] : %02x\n", AXP288_FG_OCV_CAP_REG, fuel_gauge_reg_readb(info, AXP288_FG_OCV_CAP_REG)); @@ -417,143 +420,27 @@ current_read_fail: return ret; } -static int temp_to_adc(struct axp288_fg_info *info, int tval) -{ - int rntc = 0, i, ret, adc_val; - int rmin, rmax, tmin, tmax; - int tcsz = info->pdata->tcsz; - - /* get the Rntc resitance value for this temp */ - if (tval > info->pdata->thermistor_curve[0][1]) { - rntc = info->pdata->thermistor_curve[0][0]; - } else if (tval <= info->pdata->thermistor_curve[tcsz-1][1]) { - rntc = info->pdata->thermistor_curve[tcsz-1][0]; - } else { - for (i = 1; i < tcsz; i++) { - if (tval > info->pdata->thermistor_curve[i][1]) { - rmin = info->pdata->thermistor_curve[i-1][0]; - rmax = info->pdata->thermistor_curve[i][0]; - tmin = info->pdata->thermistor_curve[i-1][1]; - tmax = info->pdata->thermistor_curve[i][1]; - rntc = rmin + ((rmax - rmin) * - (tval - tmin) / (tmax - tmin)); - break; - } - } - } - - /* we need the current to calculate the proper adc voltage */ - ret = fuel_gauge_reg_readb(info, AXP20X_ADC_RATE); - if (ret < 0) { - dev_err(&info->pdev->dev, "%s:read err:%d\n", __func__, ret); - ret = 0x30; - } - - /* - * temperature is proportional to NTS thermistor resistance - * ADC_RATE[5-4] determines current, 00=20uA,01=40uA,10=60uA,11=80uA - * [12-bit ADC VAL] = R_NTC(Ω) * current / 800 - */ - adc_val = rntc * (20 + (20 * ((ret >> 4) & 0x3))) / 800; - - return adc_val; -} - -static int adc_to_temp(struct axp288_fg_info *info, int adc_val) -{ - int ret, r, i, tval = 0; - int rmin, rmax, tmin, tmax; - int tcsz = info->pdata->tcsz; - - ret = fuel_gauge_reg_readb(info, AXP20X_ADC_RATE); - if (ret < 0) { - dev_err(&info->pdev->dev, "%s:read err:%d\n", __func__, ret); - ret = 0x30; - } - - /* - * temperature is proportional to NTS thermistor resistance - * ADC_RATE[5-4] determines current, 00=20uA,01=40uA,10=60uA,11=80uA - * R_NTC(Ω) = [12-bit ADC VAL] * 800 / current - */ - r = adc_val * 800 / (20 + (20 * ((ret >> 4) & 0x3))); - - if (r < info->pdata->thermistor_curve[0][0]) { - tval = info->pdata->thermistor_curve[0][1]; - } else if (r >= info->pdata->thermistor_curve[tcsz-1][0]) { - tval = info->pdata->thermistor_curve[tcsz-1][1]; - } else { - for (i = 1; i < tcsz; i++) { - if (r < info->pdata->thermistor_curve[i][0]) { - rmin = info->pdata->thermistor_curve[i-1][0]; - rmax = info->pdata->thermistor_curve[i][0]; - tmin = info->pdata->thermistor_curve[i-1][1]; - tmax = info->pdata->thermistor_curve[i][1]; - tval = tmin + ((tmax - tmin) * - (r - rmin) / (rmax - rmin)); - break; - } - } - } - - return tval; -} - -static int fuel_gauge_get_btemp(struct axp288_fg_info *info, int *btemp) -{ - int ret, raw_val = 0; - - ret = pmic_read_adc_val("axp288-batt-temp", &raw_val, info); - if (ret < 0) - goto temp_read_fail; - - *btemp = adc_to_temp(info, raw_val); - -temp_read_fail: - return ret; -} - static int fuel_gauge_get_vocv(struct axp288_fg_info *info, int *vocv) { - int ret, value; - - /* 12-bit data value, upper 8 in OCVH, lower 4 in OCVL */ - ret = fuel_gauge_reg_readb(info, AXP288_FG_OCVH_REG); - if (ret < 0) - goto vocv_read_fail; - value = ret << 4; + int ret; - ret = fuel_gauge_reg_readb(info, AXP288_FG_OCVL_REG); - if (ret < 0) - goto vocv_read_fail; - value |= (ret & 0xf); + ret = fuel_gauge_read_12bit_word(info, AXP288_FG_OCVH_REG); + if (ret >= 0) + *vocv = VOLTAGE_FROM_ADC(ret); - *vocv = VOLTAGE_FROM_ADC(value); -vocv_read_fail: return ret; } static int fuel_gauge_battery_health(struct axp288_fg_info *info) { - int temp, vocv; - int ret, health = POWER_SUPPLY_HEALTH_UNKNOWN; - - ret = fuel_gauge_get_btemp(info, &temp); - if (ret < 0) - goto health_read_fail; + int ret, vocv, health = POWER_SUPPLY_HEALTH_UNKNOWN; ret = fuel_gauge_get_vocv(info, &vocv); if (ret < 0) goto health_read_fail; - if (vocv > info->pdata->max_volt) + if (vocv > info->max_volt) health = POWER_SUPPLY_HEALTH_OVERVOLTAGE; - else if (temp > info->pdata->max_temp) - health = POWER_SUPPLY_HEALTH_OVERHEAT; - else if (temp < info->pdata->min_temp) - health = POWER_SUPPLY_HEALTH_COLD; - else if (vocv < info->pdata->min_volt) - health = POWER_SUPPLY_HEALTH_DEAD; else health = POWER_SUPPLY_HEALTH_GOOD; @@ -561,28 +448,6 @@ health_read_fail: return health; } -static int fuel_gauge_set_high_btemp_alert(struct axp288_fg_info *info) -{ - int ret, adc_val; - - /* program temperature threshold as 1/16 ADC value */ - adc_val = temp_to_adc(info, info->pdata->max_temp); - ret = fuel_gauge_reg_writeb(info, AXP20X_V_HTF_DISCHRG, adc_val >> 4); - - return ret; -} - -static int fuel_gauge_set_low_btemp_alert(struct axp288_fg_info *info) -{ - int ret, adc_val; - - /* program temperature threshold as 1/16 ADC value */ - adc_val = temp_to_adc(info, info->pdata->min_temp); - ret = fuel_gauge_reg_writeb(info, AXP20X_V_LTF_DISCHRG, adc_val >> 4); - - return ret; -} - static int fuel_gauge_get_property(struct power_supply *ps, enum power_supply_property prop, union power_supply_propval *val) @@ -643,58 +508,25 @@ static int fuel_gauge_get_property(struct power_supply *ps, goto fuel_gauge_read_err; val->intval = (ret & 0x0f); break; - case POWER_SUPPLY_PROP_TEMP: - ret = fuel_gauge_get_btemp(info, &value); - if (ret < 0) - goto fuel_gauge_read_err; - val->intval = PROP_TEMP(value); - break; - case POWER_SUPPLY_PROP_TEMP_MAX: - case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: - val->intval = PROP_TEMP(info->pdata->max_temp); - break; - case POWER_SUPPLY_PROP_TEMP_MIN: - case POWER_SUPPLY_PROP_TEMP_ALERT_MIN: - val->intval = PROP_TEMP(info->pdata->min_temp); - break; case POWER_SUPPLY_PROP_TECHNOLOGY: val->intval = POWER_SUPPLY_TECHNOLOGY_LION; break; case POWER_SUPPLY_PROP_CHARGE_NOW: - ret = fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR1_REG); + ret = fuel_gauge_read_15bit_word(info, AXP288_FG_CC_MTR1_REG); if (ret < 0) goto fuel_gauge_read_err; - value = (ret & FG_CC_MTR1_VAL_MASK) << 8; - ret = fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR0_REG); - if (ret < 0) - goto fuel_gauge_read_err; - value |= (ret & FG_CC_MTR0_VAL_MASK); - val->intval = value * FG_DES_CAP_RES_LSB; + val->intval = ret * FG_DES_CAP_RES_LSB; break; case POWER_SUPPLY_PROP_CHARGE_FULL: - ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG); + ret = fuel_gauge_read_15bit_word(info, AXP288_FG_DES_CAP1_REG); if (ret < 0) goto fuel_gauge_read_err; - value = (ret & FG_DES_CAP1_VAL_MASK) << 8; - ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP0_REG); - if (ret < 0) - goto fuel_gauge_read_err; - value |= (ret & FG_DES_CAP0_VAL_MASK); - val->intval = value * FG_DES_CAP_RES_LSB; - break; - case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: - val->intval = PROP_CURR(info->pdata->design_cap); + val->intval = ret * FG_DES_CAP_RES_LSB; break; case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: - val->intval = PROP_VOLT(info->pdata->max_volt); - break; - case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: - val->intval = PROP_VOLT(info->pdata->min_volt); - break; - case POWER_SUPPLY_PROP_MODEL_NAME: - val->strval = info->pdata->battid; + val->intval = PROP_VOLT(info->max_volt); break; default: mutex_unlock(&info->lock); @@ -718,35 +550,6 @@ static int fuel_gauge_set_property(struct power_supply *ps, mutex_lock(&info->lock); switch (prop) { - case POWER_SUPPLY_PROP_STATUS: - info->status = val->intval; - break; - case POWER_SUPPLY_PROP_TEMP_MIN: - case POWER_SUPPLY_PROP_TEMP_ALERT_MIN: - if ((val->intval < PD_DEF_MIN_TEMP) || - (val->intval > PD_DEF_MAX_TEMP)) { - ret = -EINVAL; - break; - } - info->pdata->min_temp = UNPROP_TEMP(val->intval); - ret = fuel_gauge_set_low_btemp_alert(info); - if (ret < 0) - dev_err(&info->pdev->dev, - "temp alert min set fail:%d\n", ret); - break; - case POWER_SUPPLY_PROP_TEMP_MAX: - case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: - if ((val->intval < PD_DEF_MIN_TEMP) || - (val->intval > PD_DEF_MAX_TEMP)) { - ret = -EINVAL; - break; - } - info->pdata->max_temp = UNPROP_TEMP(val->intval); - ret = fuel_gauge_set_high_btemp_alert(info); - if (ret < 0) - dev_err(&info->pdev->dev, - "temp alert max set fail:%d\n", ret); - break; case POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN: if ((val->intval < 0) || (val->intval > 15)) { ret = -EINVAL; @@ -774,11 +577,6 @@ static int fuel_gauge_property_is_writeable(struct power_supply *psy, int ret; switch (psp) { - case POWER_SUPPLY_PROP_STATUS: - case POWER_SUPPLY_PROP_TEMP_MIN: - case POWER_SUPPLY_PROP_TEMP_ALERT_MIN: - case POWER_SUPPLY_PROP_TEMP_MAX: - case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: case POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN: ret = 1; break; @@ -863,158 +661,6 @@ static const struct power_supply_desc fuel_gauge_desc = { .external_power_changed = fuel_gauge_external_power_changed, }; -static int fuel_gauge_set_lowbatt_thresholds(struct axp288_fg_info *info) -{ - int ret; - u8 reg_val; - - ret = fuel_gauge_reg_readb(info, AXP20X_FG_RES); - if (ret < 0) { - dev_err(&info->pdev->dev, "%s:read err:%d\n", __func__, ret); - return ret; - } - ret = (ret & FG_REP_CAP_VAL_MASK); - - if (ret > FG_LOW_CAP_WARN_THR) - reg_val = FG_LOW_CAP_WARN_THR; - else if (ret > FG_LOW_CAP_CRIT_THR) - reg_val = FG_LOW_CAP_CRIT_THR; - else - reg_val = FG_LOW_CAP_SHDN_THR; - - reg_val |= FG_LOW_CAP_THR1_VAL; - ret = fuel_gauge_reg_writeb(info, AXP288_FG_LOW_CAP_REG, reg_val); - if (ret < 0) - dev_err(&info->pdev->dev, "%s:write err:%d\n", __func__, ret); - - return ret; -} - -static int fuel_gauge_program_vbatt_full(struct axp288_fg_info *info) -{ - int ret; - u8 val; - - ret = fuel_gauge_reg_readb(info, AXP20X_CHRG_CTRL1); - if (ret < 0) - goto fg_prog_ocv_fail; - else - val = (ret & ~CHRG_CCCV_CV_MASK); - - switch (info->pdata->max_volt) { - case CV_4100: - val |= (CHRG_CCCV_CV_4100MV << CHRG_CCCV_CV_BIT_POS); - break; - case CV_4150: - val |= (CHRG_CCCV_CV_4150MV << CHRG_CCCV_CV_BIT_POS); - break; - case CV_4200: - val |= (CHRG_CCCV_CV_4200MV << CHRG_CCCV_CV_BIT_POS); - break; - case CV_4350: - val |= (CHRG_CCCV_CV_4350MV << CHRG_CCCV_CV_BIT_POS); - break; - default: - val |= (CHRG_CCCV_CV_4200MV << CHRG_CCCV_CV_BIT_POS); - break; - } - - ret = fuel_gauge_reg_writeb(info, AXP20X_CHRG_CTRL1, val); -fg_prog_ocv_fail: - return ret; -} - -static int fuel_gauge_program_design_cap(struct axp288_fg_info *info) -{ - int ret; - - ret = fuel_gauge_reg_writeb(info, - AXP288_FG_DES_CAP1_REG, info->pdata->cap1); - if (ret < 0) - goto fg_prog_descap_fail; - - ret = fuel_gauge_reg_writeb(info, - AXP288_FG_DES_CAP0_REG, info->pdata->cap0); - -fg_prog_descap_fail: - return ret; -} - -static int fuel_gauge_program_ocv_curve(struct axp288_fg_info *info) -{ - int ret = 0, i; - - for (i = 0; i < OCV_CURVE_SIZE; i++) { - ret = fuel_gauge_reg_writeb(info, - AXP288_FG_OCV_CURVE_REG + i, info->pdata->ocv_curve[i]); - if (ret < 0) - goto fg_prog_ocv_fail; - } - -fg_prog_ocv_fail: - return ret; -} - -static int fuel_gauge_program_rdc_vals(struct axp288_fg_info *info) -{ - int ret; - - ret = fuel_gauge_reg_writeb(info, - AXP288_FG_RDC1_REG, info->pdata->rdc1); - if (ret < 0) - goto fg_prog_ocv_fail; - - ret = fuel_gauge_reg_writeb(info, - AXP288_FG_RDC0_REG, info->pdata->rdc0); - -fg_prog_ocv_fail: - return ret; -} - -static void fuel_gauge_init_config_regs(struct axp288_fg_info *info) -{ - int ret; - - /* - * check if the config data is already - * programmed and if so just return. - */ - - ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG); - if (ret < 0) { - dev_warn(&info->pdev->dev, "CAP1 reg read err!!\n"); - } else if (!(ret & FG_DES_CAP1_VALID)) { - dev_info(&info->pdev->dev, "FG data needs to be initialized\n"); - } else { - dev_info(&info->pdev->dev, "FG data is already initialized\n"); - return; - } - - ret = fuel_gauge_program_vbatt_full(info); - if (ret < 0) - dev_err(&info->pdev->dev, "set vbatt full fail:%d\n", ret); - - ret = fuel_gauge_program_design_cap(info); - if (ret < 0) - dev_err(&info->pdev->dev, "set design cap fail:%d\n", ret); - - ret = fuel_gauge_program_rdc_vals(info); - if (ret < 0) - dev_err(&info->pdev->dev, "set rdc fail:%d\n", ret); - - ret = fuel_gauge_program_ocv_curve(info); - if (ret < 0) - dev_err(&info->pdev->dev, "set ocv curve fail:%d\n", ret); - - ret = fuel_gauge_set_lowbatt_thresholds(info); - if (ret < 0) - dev_err(&info->pdev->dev, "lowbatt thr set fail:%d\n", ret); - - ret = fuel_gauge_reg_writeb(info, AXP20X_CC_CTRL, 0xef); - if (ret < 0) - dev_err(&info->pdev->dev, "gauge cntl set fail:%d\n", ret); -} - static void fuel_gauge_init_irq(struct axp288_fg_info *info) { int ret, i, pirq; @@ -1052,29 +698,6 @@ intr_failed: } } -static void fuel_gauge_init_hw_regs(struct axp288_fg_info *info) -{ - int ret; - unsigned int val; - - ret = fuel_gauge_set_high_btemp_alert(info); - if (ret < 0) - dev_err(&info->pdev->dev, "high batt temp set fail:%d\n", ret); - - ret = fuel_gauge_set_low_btemp_alert(info); - if (ret < 0) - dev_err(&info->pdev->dev, "low batt temp set fail:%d\n", ret); - - /* enable interrupts */ - val = fuel_gauge_reg_readb(info, AXP20X_IRQ3_EN); - val |= TEMP_IRQ_CFG_MASK; - fuel_gauge_reg_writeb(info, AXP20X_IRQ3_EN, val); - - val = fuel_gauge_reg_readb(info, AXP20X_IRQ4_EN); - val |= FG_IRQ_CFG_LOWBATT_MASK; - val = fuel_gauge_reg_writeb(info, AXP20X_IRQ4_EN, val); -} - static int axp288_fuel_gauge_probe(struct platform_device *pdev) { int ret = 0; @@ -1090,15 +713,39 @@ static int axp288_fuel_gauge_probe(struct platform_device *pdev) info->regmap = axp20x->regmap; info->regmap_irqc = axp20x->regmap_irqc; info->status = POWER_SUPPLY_STATUS_UNKNOWN; - info->pdata = pdev->dev.platform_data; - if (!info->pdata) - return -ENODEV; platform_set_drvdata(pdev, info); mutex_init(&info->lock); INIT_DELAYED_WORK(&info->status_monitor, fuel_gauge_status_monitor); + ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG); + if (ret < 0) + return ret; + + if (!(ret & FG_DES_CAP1_VALID)) { + dev_err(&pdev->dev, "axp288 not configured by firmware\n"); + return -ENODEV; + } + + ret = fuel_gauge_reg_readb(info, AXP20X_CHRG_CTRL1); + if (ret < 0) + return ret; + switch ((ret & CHRG_CCCV_CV_MASK) >> CHRG_CCCV_CV_BIT_POS) { + case CHRG_CCCV_CV_4100MV: + info->max_volt = 4100; + break; + case CHRG_CCCV_CV_4150MV: + info->max_volt = 4150; + break; + case CHRG_CCCV_CV_4200MV: + info->max_volt = 4200; + break; + case CHRG_CCCV_CV_4350MV: + info->max_volt = 4350; + break; + } + psy_cfg.drv_data = info; info->bat = power_supply_register(&pdev->dev, &fuel_gauge_desc, &psy_cfg); if (IS_ERR(info->bat)) { @@ -1108,12 +755,10 @@ static int axp288_fuel_gauge_probe(struct platform_device *pdev) } fuel_gauge_create_debugfs(info); - fuel_gauge_init_config_regs(info); fuel_gauge_init_irq(info); - fuel_gauge_init_hw_regs(info); schedule_delayed_work(&info->status_monitor, STATUS_MON_DELAY_JIFFIES); - return ret; + return 0; } static const struct platform_device_id axp288_fg_id_table[] = { diff --git a/drivers/power/supply/bq2415x_charger.c b/drivers/power/supply/bq2415x_charger.c index 73e2f0b79dd4..c4770a94cc8e 100644 --- a/drivers/power/supply/bq2415x_charger.c +++ b/drivers/power/supply/bq2415x_charger.c @@ -1569,6 +1569,11 @@ static int bq2415x_probe(struct i2c_client *client, acpi_id = acpi_match_device(client->dev.driver->acpi_match_table, &client->dev); + if (!acpi_id) { + dev_err(&client->dev, "failed to match device name\n"); + ret = -ENODEV; + goto error_1; + } name = kasprintf(GFP_KERNEL, "%s-%d", acpi_id->id, num); } if (!name) { diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index e9584330aeed..a4f08492abeb 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -144,10 +144,7 @@ * so the first read after a fault returns the latched value and subsequent * reads return the current value. In order to return the fault status * to the user, have the interrupt handler save the reg's value and retrieve - * it in the appropriate health/status routine. Each routine has its own - * flag indicating whether it should use the value stored by the last run - * of the interrupt handler or do an actual reg read. That way each routine - * can report back whatever fault may have occured. + * it in the appropriate health/status routine. */ struct bq24190_dev_info { struct i2c_client *client; @@ -159,10 +156,6 @@ struct bq24190_dev_info { unsigned int gpio_int; unsigned int irq; struct mutex f_reg_lock; - bool first_time; - bool charger_health_valid; - bool battery_health_valid; - bool battery_status_valid; u8 f_reg; u8 ss_reg; u8 watchdog; @@ -199,7 +192,7 @@ static const int bq24190_cvc_vreg_values[] = { 4400000 }; -/* REG06[1:0] (TREG) in tenths of degrees Celcius */ +/* REG06[1:0] (TREG) in tenths of degrees Celsius */ static const int bq24190_ictrc_treg_values[] = { 600, 800, 1000, 1200 }; @@ -636,21 +629,11 @@ static int bq24190_charger_get_health(struct bq24190_dev_info *bdi, union power_supply_propval *val) { u8 v; - int health, ret; + int health; mutex_lock(&bdi->f_reg_lock); - - if (bdi->charger_health_valid) { - v = bdi->f_reg; - bdi->charger_health_valid = false; - mutex_unlock(&bdi->f_reg_lock); - } else { - mutex_unlock(&bdi->f_reg_lock); - - ret = bq24190_read(bdi, BQ24190_REG_F, &v); - if (ret < 0) - return ret; - } + v = bdi->f_reg; + mutex_unlock(&bdi->f_reg_lock); if (v & BQ24190_REG_F_BOOST_FAULT_MASK) { /* @@ -937,18 +920,8 @@ static int bq24190_battery_get_status(struct bq24190_dev_info *bdi, int status, ret; mutex_lock(&bdi->f_reg_lock); - - if (bdi->battery_status_valid) { - chrg_fault = bdi->f_reg; - bdi->battery_status_valid = false; - mutex_unlock(&bdi->f_reg_lock); - } else { - mutex_unlock(&bdi->f_reg_lock); - - ret = bq24190_read(bdi, BQ24190_REG_F, &chrg_fault); - if (ret < 0) - return ret; - } + chrg_fault = bdi->f_reg; + mutex_unlock(&bdi->f_reg_lock); chrg_fault &= BQ24190_REG_F_CHRG_FAULT_MASK; chrg_fault >>= BQ24190_REG_F_CHRG_FAULT_SHIFT; @@ -996,21 +969,11 @@ static int bq24190_battery_get_health(struct bq24190_dev_info *bdi, union power_supply_propval *val) { u8 v; - int health, ret; + int health; mutex_lock(&bdi->f_reg_lock); - - if (bdi->battery_health_valid) { - v = bdi->f_reg; - bdi->battery_health_valid = false; - mutex_unlock(&bdi->f_reg_lock); - } else { - mutex_unlock(&bdi->f_reg_lock); - - ret = bq24190_read(bdi, BQ24190_REG_F, &v); - if (ret < 0) - return ret; - } + v = bdi->f_reg; + mutex_unlock(&bdi->f_reg_lock); if (v & BQ24190_REG_F_BAT_FAULT_MASK) { health = POWER_SUPPLY_HEALTH_OVERVOLTAGE; @@ -1197,9 +1160,12 @@ static const struct power_supply_desc bq24190_battery_desc = { static irqreturn_t bq24190_irq_handler_thread(int irq, void *data) { struct bq24190_dev_info *bdi = data; - bool alert_userspace = false; + const u8 battery_mask_ss = BQ24190_REG_SS_CHRG_STAT_MASK; + const u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK + | BQ24190_REG_F_NTC_FAULT_MASK; + bool alert_charger = false, alert_battery = false; u8 ss_reg = 0, f_reg = 0; - int ret; + int i, ret; pm_runtime_get_sync(bdi->dev); @@ -1209,6 +1175,32 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data) goto out; } + i = 0; + do { + ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg); + if (ret < 0) { + dev_err(bdi->dev, "Can't read F reg: %d\n", ret); + goto out; + } + } while (f_reg && ++i < 2); + + if (f_reg != bdi->f_reg) { + dev_info(bdi->dev, + "Fault: boost %d, charge %d, battery %d, ntc %d\n", + !!(f_reg & BQ24190_REG_F_BOOST_FAULT_MASK), + !!(f_reg & BQ24190_REG_F_CHRG_FAULT_MASK), + !!(f_reg & BQ24190_REG_F_BAT_FAULT_MASK), + !!(f_reg & BQ24190_REG_F_NTC_FAULT_MASK)); + + mutex_lock(&bdi->f_reg_lock); + if ((bdi->f_reg & battery_mask_f) != (f_reg & battery_mask_f)) + alert_battery = true; + if ((bdi->f_reg & ~battery_mask_f) != (f_reg & ~battery_mask_f)) + alert_charger = true; + bdi->f_reg = f_reg; + mutex_unlock(&bdi->f_reg_lock); + } + if (ss_reg != bdi->ss_reg) { /* * The device is in host mode so when PG_STAT goes from 1->0 @@ -1225,47 +1217,17 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data) ret); } + if ((bdi->ss_reg & battery_mask_ss) != (ss_reg & battery_mask_ss)) + alert_battery = true; + if ((bdi->ss_reg & ~battery_mask_ss) != (ss_reg & ~battery_mask_ss)) + alert_charger = true; bdi->ss_reg = ss_reg; - alert_userspace = true; - } - - mutex_lock(&bdi->f_reg_lock); - - ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg); - if (ret < 0) { - mutex_unlock(&bdi->f_reg_lock); - dev_err(bdi->dev, "Can't read F reg: %d\n", ret); - goto out; - } - - if (f_reg != bdi->f_reg) { - bdi->f_reg = f_reg; - bdi->charger_health_valid = true; - bdi->battery_health_valid = true; - bdi->battery_status_valid = true; - - alert_userspace = true; } - mutex_unlock(&bdi->f_reg_lock); - - /* - * Sometimes bq24190 gives a steady trickle of interrupts even - * though the watchdog timer is turned off and neither the STATUS - * nor FAULT registers have changed. Weed out these sprurious - * interrupts so userspace isn't alerted for no reason. - * In addition, the chip always generates an interrupt after - * register reset so we should ignore that one (the very first - * interrupt received). - */ - if (alert_userspace) { - if (!bdi->first_time) { - power_supply_changed(bdi->charger); - power_supply_changed(bdi->battery); - } else { - bdi->first_time = false; - } - } + if (alert_charger) + power_supply_changed(bdi->charger); + if (alert_battery) + power_supply_changed(bdi->battery); out: pm_runtime_put_sync(bdi->dev); @@ -1300,6 +1262,10 @@ static int bq24190_hw_init(struct bq24190_dev_info *bdi) goto out; ret = bq24190_set_mode_host(bdi); + if (ret < 0) + goto out; + + ret = bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg); out: pm_runtime_put_sync(bdi->dev); return ret; @@ -1375,10 +1341,8 @@ static int bq24190_probe(struct i2c_client *client, bdi->model = id->driver_data; strncpy(bdi->model_name, id->name, I2C_NAME_SIZE); mutex_init(&bdi->f_reg_lock); - bdi->first_time = true; - bdi->charger_health_valid = false; - bdi->battery_health_valid = false; - bdi->battery_status_valid = false; + bdi->f_reg = 0; + bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */ i2c_set_clientdata(client, bdi); @@ -1392,22 +1356,13 @@ static int bq24190_probe(struct i2c_client *client, return -EINVAL; } - ret = devm_request_threaded_irq(dev, bdi->irq, NULL, - bq24190_irq_handler_thread, - IRQF_TRIGGER_RISING | IRQF_ONESHOT, - "bq24190-charger", bdi); - if (ret < 0) { - dev_err(dev, "Can't set up irq handler\n"); - goto out1; - } - pm_runtime_enable(dev); pm_runtime_resume(dev); ret = bq24190_hw_init(bdi); if (ret < 0) { dev_err(dev, "Hardware init failed\n"); - goto out2; + goto out1; } charger_cfg.drv_data = bdi; @@ -1418,7 +1373,7 @@ static int bq24190_probe(struct i2c_client *client, if (IS_ERR(bdi->charger)) { dev_err(dev, "Can't register charger\n"); ret = PTR_ERR(bdi->charger); - goto out2; + goto out1; } battery_cfg.drv_data = bdi; @@ -1427,27 +1382,39 @@ static int bq24190_probe(struct i2c_client *client, if (IS_ERR(bdi->battery)) { dev_err(dev, "Can't register battery\n"); ret = PTR_ERR(bdi->battery); - goto out3; + goto out2; } ret = bq24190_sysfs_create_group(bdi); if (ret) { dev_err(dev, "Can't create sysfs entries\n"); + goto out3; + } + + ret = devm_request_threaded_irq(dev, bdi->irq, NULL, + bq24190_irq_handler_thread, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + "bq24190-charger", bdi); + if (ret < 0) { + dev_err(dev, "Can't set up irq handler\n"); goto out4; } return 0; out4: - power_supply_unregister(bdi->battery); + bq24190_sysfs_remove_group(bdi); + out3: - power_supply_unregister(bdi->charger); + power_supply_unregister(bdi->battery); + out2: - pm_runtime_disable(dev); + power_supply_unregister(bdi->charger); + out1: + pm_runtime_disable(dev); if (bdi->gpio_int) gpio_free(bdi->gpio_int); - return ret; } @@ -1488,12 +1455,13 @@ static int bq24190_pm_resume(struct device *dev) struct i2c_client *client = to_i2c_client(dev); struct bq24190_dev_info *bdi = i2c_get_clientdata(client); - bdi->charger_health_valid = false; - bdi->battery_health_valid = false; - bdi->battery_status_valid = false; + bdi->f_reg = 0; + bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */ pm_runtime_get_sync(bdi->dev); bq24190_register_reset(bdi); + bq24190_set_mode_host(bdi); + bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg); pm_runtime_put_sync(bdi->dev); /* Things may have changed while suspended so alert upper layer */ diff --git a/drivers/power/supply/bq24735-charger.c b/drivers/power/supply/bq24735-charger.c index eb7783b42e0a..eb0145380def 100644 --- a/drivers/power/supply/bq24735-charger.c +++ b/drivers/power/supply/bq24735-charger.c @@ -50,6 +50,8 @@ struct bq24735 { struct bq24735_platform *pdata; struct mutex lock; struct gpio_desc *status_gpio; + struct delayed_work poll; + u32 poll_interval; bool charging; }; @@ -105,26 +107,6 @@ static int bq24735_update_word(struct i2c_client *client, u8 reg, return bq24735_write_word(client, reg, tmp); } -static inline int bq24735_enable_charging(struct bq24735 *charger) -{ - if (charger->pdata->ext_control) - return 0; - - return bq24735_update_word(charger->client, BQ24735_CHG_OPT, - BQ24735_CHG_OPT_CHARGE_DISABLE, - ~BQ24735_CHG_OPT_CHARGE_DISABLE); -} - -static inline int bq24735_disable_charging(struct bq24735 *charger) -{ - if (charger->pdata->ext_control) - return 0; - - return bq24735_update_word(charger->client, BQ24735_CHG_OPT, - BQ24735_CHG_OPT_CHARGE_DISABLE, - BQ24735_CHG_OPT_CHARGE_DISABLE); -} - static int bq24735_config_charger(struct bq24735 *charger) { struct bq24735_platform *pdata = charger->pdata; @@ -176,6 +158,31 @@ static int bq24735_config_charger(struct bq24735 *charger) return 0; } +static inline int bq24735_enable_charging(struct bq24735 *charger) +{ + int ret; + + if (charger->pdata->ext_control) + return 0; + + ret = bq24735_config_charger(charger); + if (ret) + return ret; + + return bq24735_update_word(charger->client, BQ24735_CHG_OPT, + BQ24735_CHG_OPT_CHARGE_DISABLE, 0); +} + +static inline int bq24735_disable_charging(struct bq24735 *charger) +{ + if (charger->pdata->ext_control) + return 0; + + return bq24735_update_word(charger->client, BQ24735_CHG_OPT, + BQ24735_CHG_OPT_CHARGE_DISABLE, + BQ24735_CHG_OPT_CHARGE_DISABLE); +} + static bool bq24735_charger_is_present(struct bq24735 *charger) { if (charger->status_gpio) { @@ -185,7 +192,7 @@ static bool bq24735_charger_is_present(struct bq24735 *charger) ac = bq24735_read_word(charger->client, BQ24735_CHG_OPT); if (ac < 0) { - dev_err(&charger->client->dev, + dev_dbg(&charger->client->dev, "Failed to read charger options : %d\n", ac); return false; @@ -210,11 +217,8 @@ static int bq24735_charger_is_charging(struct bq24735 *charger) return !(ret & BQ24735_CHG_OPT_CHARGE_DISABLE); } -static irqreturn_t bq24735_charger_isr(int irq, void *devid) +static void bq24735_update(struct bq24735 *charger) { - struct power_supply *psy = devid; - struct bq24735 *charger = to_bq24735(psy); - mutex_lock(&charger->lock); if (charger->charging && bq24735_charger_is_present(charger)) @@ -224,11 +228,29 @@ static irqreturn_t bq24735_charger_isr(int irq, void *devid) mutex_unlock(&charger->lock); - power_supply_changed(psy); + power_supply_changed(charger->charger); +} + +static irqreturn_t bq24735_charger_isr(int irq, void *devid) +{ + struct power_supply *psy = devid; + struct bq24735 *charger = to_bq24735(psy); + + bq24735_update(charger); return IRQ_HANDLED; } +static void bq24735_poll(struct work_struct *work) +{ + struct bq24735 *charger = container_of(work, struct bq24735, poll.work); + + bq24735_update(charger); + + schedule_delayed_work(&charger->poll, + msecs_to_jiffies(charger->poll_interval)); +} + static int bq24735_charger_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val) @@ -276,7 +298,6 @@ static int bq24735_charger_set_property(struct power_supply *psy, mutex_unlock(&charger->lock); if (ret) return ret; - bq24735_config_charger(charger); break; case POWER_SUPPLY_STATUS_DISCHARGING: case POWER_SUPPLY_STATUS_NOT_CHARGING: @@ -395,7 +416,7 @@ static int bq24735_charger_probe(struct i2c_client *client, return ret; } - if (!charger->status_gpio || bq24735_charger_is_present(charger)) { + if (bq24735_charger_is_present(charger)) { ret = bq24735_read_word(client, BQ24735_MANUFACTURER_ID); if (ret < 0) { dev_err(&client->dev, "Failed to read manufacturer id : %d\n", @@ -416,16 +437,7 @@ static int bq24735_charger_probe(struct i2c_client *client, "device id mismatch. 0x000b != 0x%04x\n", ret); return -ENODEV; } - } - - ret = bq24735_config_charger(charger); - if (ret < 0) { - dev_err(&client->dev, "failed in configuring charger"); - return ret; - } - /* check for AC adapter presence */ - if (bq24735_charger_is_present(charger)) { ret = bq24735_enable_charging(charger); if (ret < 0) { dev_err(&client->dev, "Failed to enable charging\n"); @@ -456,11 +468,32 @@ static int bq24735_charger_probe(struct i2c_client *client, client->irq, ret); return ret; } + } else { + ret = device_property_read_u32(&client->dev, "poll-interval", + &charger->poll_interval); + if (ret) + return 0; + if (!charger->poll_interval) + return 0; + + INIT_DELAYED_WORK(&charger->poll, bq24735_poll); + schedule_delayed_work(&charger->poll, + msecs_to_jiffies(charger->poll_interval)); } return 0; } +static int bq24735_charger_remove(struct i2c_client *client) +{ + struct bq24735 *charger = i2c_get_clientdata(client); + + if (charger->poll_interval) + cancel_delayed_work_sync(&charger->poll); + + return 0; +} + static const struct i2c_device_id bq24735_charger_id[] = { { "bq24735-charger", 0 }, {} @@ -479,6 +512,7 @@ static struct i2c_driver bq24735_charger_driver = { .of_match_table = bq24735_match_ids, }, .probe = bq24735_charger_probe, + .remove = bq24735_charger_remove, .id_table = bq24735_charger_id, }; diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 08c36b8e04bd..398801a21b86 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -22,8 +22,14 @@ * http://www.ti.com/product/bq27010 * http://www.ti.com/product/bq27210 * http://www.ti.com/product/bq27500 + * http://www.ti.com/product/bq27510-g1 + * http://www.ti.com/product/bq27510-g2 * http://www.ti.com/product/bq27510-g3 * http://www.ti.com/product/bq27520-g4 + * http://www.ti.com/product/bq27520-g1 + * http://www.ti.com/product/bq27520-g2 + * http://www.ti.com/product/bq27520-g3 + * http://www.ti.com/product/bq27520-g4 * http://www.ti.com/product/bq27530-g1 * http://www.ti.com/product/bq27531-g1 * http://www.ti.com/product/bq27541-g1 @@ -145,7 +151,7 @@ static u8 bq27xxx_regs[][BQ27XXX_REG_MAX] = { [BQ27XXX_REG_DCAP] = 0x76, [BQ27XXX_REG_AP] = INVALID_REG_ADDR, }, - [BQ27500] = { + [BQ2750X] = { [BQ27XXX_REG_CTRL] = 0x00, [BQ27XXX_REG_TEMP] = 0x06, [BQ27XXX_REG_INT_TEMP] = 0x28, @@ -164,7 +170,83 @@ static u8 bq27xxx_regs[][BQ27XXX_REG_MAX] = { [BQ27XXX_REG_DCAP] = 0x3c, [BQ27XXX_REG_AP] = INVALID_REG_ADDR, }, - [BQ27510] = { + [BQ2751X] = { + [BQ27XXX_REG_CTRL] = 0x00, + [BQ27XXX_REG_TEMP] = 0x06, + [BQ27XXX_REG_INT_TEMP] = 0x28, + [BQ27XXX_REG_VOLT] = 0x08, + [BQ27XXX_REG_AI] = 0x14, + [BQ27XXX_REG_FLAGS] = 0x0a, + [BQ27XXX_REG_TTE] = 0x16, + [BQ27XXX_REG_TTF] = INVALID_REG_ADDR, + [BQ27XXX_REG_TTES] = 0x1a, + [BQ27XXX_REG_TTECP] = INVALID_REG_ADDR, + [BQ27XXX_REG_NAC] = 0x0c, + [BQ27XXX_REG_FCC] = 0x12, + [BQ27XXX_REG_CYCT] = 0x1e, + [BQ27XXX_REG_AE] = INVALID_REG_ADDR, + [BQ27XXX_REG_SOC] = 0x20, + [BQ27XXX_REG_DCAP] = 0x2e, + [BQ27XXX_REG_AP] = INVALID_REG_ADDR, + }, + [BQ27500] = { + [BQ27XXX_REG_CTRL] = 0x00, + [BQ27XXX_REG_TEMP] = 0x06, + [BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR, + [BQ27XXX_REG_VOLT] = 0x08, + [BQ27XXX_REG_AI] = 0x14, + [BQ27XXX_REG_FLAGS] = 0x0a, + [BQ27XXX_REG_TTE] = 0x16, + [BQ27XXX_REG_TTF] = 0x18, + [BQ27XXX_REG_TTES] = 0x1c, + [BQ27XXX_REG_TTECP] = 0x26, + [BQ27XXX_REG_NAC] = 0x0c, + [BQ27XXX_REG_FCC] = 0x12, + [BQ27XXX_REG_CYCT] = 0x2a, + [BQ27XXX_REG_AE] = 0x22, + [BQ27XXX_REG_SOC] = 0x2c, + [BQ27XXX_REG_DCAP] = 0x3c, + [BQ27XXX_REG_AP] = 0x24, + }, + [BQ27510G1] = { + [BQ27XXX_REG_CTRL] = 0x00, + [BQ27XXX_REG_TEMP] = 0x06, + [BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR, + [BQ27XXX_REG_VOLT] = 0x08, + [BQ27XXX_REG_AI] = 0x14, + [BQ27XXX_REG_FLAGS] = 0x0a, + [BQ27XXX_REG_TTE] = 0x16, + [BQ27XXX_REG_TTF] = 0x18, + [BQ27XXX_REG_TTES] = 0x1c, + [BQ27XXX_REG_TTECP] = 0x26, + [BQ27XXX_REG_NAC] = 0x0c, + [BQ27XXX_REG_FCC] = 0x12, + [BQ27XXX_REG_CYCT] = 0x2a, + [BQ27XXX_REG_AE] = 0x22, + [BQ27XXX_REG_SOC] = 0x2c, + [BQ27XXX_REG_DCAP] = 0x3c, + [BQ27XXX_REG_AP] = 0x24, + }, + [BQ27510G2] = { + [BQ27XXX_REG_CTRL] = 0x00, + [BQ27XXX_REG_TEMP] = 0x06, + [BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR, + [BQ27XXX_REG_VOLT] = 0x08, + [BQ27XXX_REG_AI] = 0x14, + [BQ27XXX_REG_FLAGS] = 0x0a, + [BQ27XXX_REG_TTE] = 0x16, + [BQ27XXX_REG_TTF] = 0x18, + [BQ27XXX_REG_TTES] = 0x1c, + [BQ27XXX_REG_TTECP] = 0x26, + [BQ27XXX_REG_NAC] = 0x0c, + [BQ27XXX_REG_FCC] = 0x12, + [BQ27XXX_REG_CYCT] = 0x2a, + [BQ27XXX_REG_AE] = 0x22, + [BQ27XXX_REG_SOC] = 0x2c, + [BQ27XXX_REG_DCAP] = 0x3c, + [BQ27XXX_REG_AP] = 0x24, + }, + [BQ27510G3] = { [BQ27XXX_REG_CTRL] = 0x00, [BQ27XXX_REG_TEMP] = 0x06, [BQ27XXX_REG_INT_TEMP] = 0x28, @@ -183,6 +265,82 @@ static u8 bq27xxx_regs[][BQ27XXX_REG_MAX] = { [BQ27XXX_REG_DCAP] = 0x2e, [BQ27XXX_REG_AP] = INVALID_REG_ADDR, }, + [BQ27520G1] = { + [BQ27XXX_REG_CTRL] = 0x00, + [BQ27XXX_REG_TEMP] = 0x06, + [BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR, + [BQ27XXX_REG_VOLT] = 0x08, + [BQ27XXX_REG_AI] = 0x14, + [BQ27XXX_REG_FLAGS] = 0x0a, + [BQ27XXX_REG_TTE] = 0x16, + [BQ27XXX_REG_TTF] = 0x18, + [BQ27XXX_REG_TTES] = 0x1c, + [BQ27XXX_REG_TTECP] = 0x26, + [BQ27XXX_REG_NAC] = 0x0c, + [BQ27XXX_REG_FCC] = 0x12, + [BQ27XXX_REG_CYCT] = INVALID_REG_ADDR, + [BQ27XXX_REG_AE] = 0x22, + [BQ27XXX_REG_SOC] = 0x2c, + [BQ27XXX_REG_DCAP] = 0x3c, + [BQ27XXX_REG_AP] = 0x24, + }, + [BQ27520G2] = { + [BQ27XXX_REG_CTRL] = 0x00, + [BQ27XXX_REG_TEMP] = 0x06, + [BQ27XXX_REG_INT_TEMP] = 0x36, + [BQ27XXX_REG_VOLT] = 0x08, + [BQ27XXX_REG_AI] = 0x14, + [BQ27XXX_REG_FLAGS] = 0x0a, + [BQ27XXX_REG_TTE] = 0x16, + [BQ27XXX_REG_TTF] = 0x18, + [BQ27XXX_REG_TTES] = 0x1c, + [BQ27XXX_REG_TTECP] = 0x26, + [BQ27XXX_REG_NAC] = 0x0c, + [BQ27XXX_REG_FCC] = 0x12, + [BQ27XXX_REG_CYCT] = 0x2a, + [BQ27XXX_REG_AE] = 0x22, + [BQ27XXX_REG_SOC] = 0x2c, + [BQ27XXX_REG_DCAP] = 0x3c, + [BQ27XXX_REG_AP] = 0x24, + }, + [BQ27520G3] = { + [BQ27XXX_REG_CTRL] = 0x00, + [BQ27XXX_REG_TEMP] = 0x06, + [BQ27XXX_REG_INT_TEMP] = 0x36, + [BQ27XXX_REG_VOLT] = 0x08, + [BQ27XXX_REG_AI] = 0x14, + [BQ27XXX_REG_FLAGS] = 0x0a, + [BQ27XXX_REG_TTE] = 0x16, + [BQ27XXX_REG_TTF] = INVALID_REG_ADDR, + [BQ27XXX_REG_TTES] = 0x1c, + [BQ27XXX_REG_TTECP] = 0x26, + [BQ27XXX_REG_NAC] = 0x0c, + [BQ27XXX_REG_FCC] = 0x12, + [BQ27XXX_REG_CYCT] = 0x2a, + [BQ27XXX_REG_AE] = 0x22, + [BQ27XXX_REG_SOC] = 0x2c, + [BQ27XXX_REG_DCAP] = 0x3c, + [BQ27XXX_REG_AP] = 0x24, + }, + [BQ27520G4] = { + [BQ27XXX_REG_CTRL] = 0x00, + [BQ27XXX_REG_TEMP] = 0x06, + [BQ27XXX_REG_INT_TEMP] = 0x28, + [BQ27XXX_REG_VOLT] = 0x08, + [BQ27XXX_REG_AI] = 0x14, + [BQ27XXX_REG_FLAGS] = 0x0a, + [BQ27XXX_REG_TTE] = 0x16, + [BQ27XXX_REG_TTF] = INVALID_REG_ADDR, + [BQ27XXX_REG_TTES] = 0x1c, + [BQ27XXX_REG_TTECP] = INVALID_REG_ADDR, + [BQ27XXX_REG_NAC] = 0x0c, + [BQ27XXX_REG_FCC] = 0x12, + [BQ27XXX_REG_CYCT] = 0x1e, + [BQ27XXX_REG_AE] = INVALID_REG_ADDR, + [BQ27XXX_REG_SOC] = 0x20, + [BQ27XXX_REG_DCAP] = INVALID_REG_ADDR, + [BQ27XXX_REG_AP] = INVALID_REG_ADDR, + }, [BQ27530] = { [BQ27XXX_REG_CTRL] = 0x00, [BQ27XXX_REG_TEMP] = 0x06, @@ -303,6 +461,42 @@ static enum power_supply_property bq27010_battery_props[] = { POWER_SUPPLY_PROP_MANUFACTURER, }; +static enum power_supply_property bq2750x_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CAPACITY_LEVEL, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, + POWER_SUPPLY_PROP_TECHNOLOGY, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_CHARGE_NOW, + POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, + POWER_SUPPLY_PROP_CYCLE_COUNT, + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_MANUFACTURER, +}; + +static enum power_supply_property bq2751x_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CAPACITY_LEVEL, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, + POWER_SUPPLY_PROP_TECHNOLOGY, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_CHARGE_NOW, + POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, + POWER_SUPPLY_PROP_CYCLE_COUNT, + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_MANUFACTURER, +}; + static enum power_supply_property bq27500_battery_props[] = { POWER_SUPPLY_PROP_STATUS, POWER_SUPPLY_PROP_PRESENT, @@ -312,6 +506,69 @@ static enum power_supply_property bq27500_battery_props[] = { POWER_SUPPLY_PROP_CAPACITY_LEVEL, POWER_SUPPLY_PROP_TEMP, POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, + POWER_SUPPLY_PROP_TIME_TO_FULL_NOW, + POWER_SUPPLY_PROP_TECHNOLOGY, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_CHARGE_NOW, + POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, + POWER_SUPPLY_PROP_CYCLE_COUNT, + POWER_SUPPLY_PROP_ENERGY_NOW, + POWER_SUPPLY_PROP_POWER_AVG, + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_MANUFACTURER, +}; + +static enum power_supply_property bq27510g1_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CAPACITY_LEVEL, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, + POWER_SUPPLY_PROP_TIME_TO_FULL_NOW, + POWER_SUPPLY_PROP_TECHNOLOGY, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_CHARGE_NOW, + POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, + POWER_SUPPLY_PROP_CYCLE_COUNT, + POWER_SUPPLY_PROP_ENERGY_NOW, + POWER_SUPPLY_PROP_POWER_AVG, + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_MANUFACTURER, +}; + +static enum power_supply_property bq27510g2_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CAPACITY_LEVEL, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, + POWER_SUPPLY_PROP_TIME_TO_FULL_NOW, + POWER_SUPPLY_PROP_TECHNOLOGY, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_CHARGE_NOW, + POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, + POWER_SUPPLY_PROP_CYCLE_COUNT, + POWER_SUPPLY_PROP_ENERGY_NOW, + POWER_SUPPLY_PROP_POWER_AVG, + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_MANUFACTURER, +}; + +static enum power_supply_property bq27510g3_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CAPACITY_LEVEL, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, POWER_SUPPLY_PROP_TECHNOLOGY, POWER_SUPPLY_PROP_CHARGE_FULL, POWER_SUPPLY_PROP_CHARGE_NOW, @@ -321,7 +578,27 @@ static enum power_supply_property bq27500_battery_props[] = { POWER_SUPPLY_PROP_MANUFACTURER, }; -static enum power_supply_property bq27510_battery_props[] = { +static enum power_supply_property bq27520g1_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CAPACITY_LEVEL, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, + POWER_SUPPLY_PROP_TIME_TO_FULL_NOW, + POWER_SUPPLY_PROP_TECHNOLOGY, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_CHARGE_NOW, + POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, + POWER_SUPPLY_PROP_ENERGY_NOW, + POWER_SUPPLY_PROP_POWER_AVG, + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_MANUFACTURER, +}; + +static enum power_supply_property bq27520g2_battery_props[] = { POWER_SUPPLY_PROP_STATUS, POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_VOLTAGE_NOW, @@ -330,11 +607,51 @@ static enum power_supply_property bq27510_battery_props[] = { POWER_SUPPLY_PROP_CAPACITY_LEVEL, POWER_SUPPLY_PROP_TEMP, POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, + POWER_SUPPLY_PROP_TIME_TO_FULL_NOW, POWER_SUPPLY_PROP_TECHNOLOGY, POWER_SUPPLY_PROP_CHARGE_FULL, POWER_SUPPLY_PROP_CHARGE_NOW, POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, POWER_SUPPLY_PROP_CYCLE_COUNT, + POWER_SUPPLY_PROP_ENERGY_NOW, + POWER_SUPPLY_PROP_POWER_AVG, + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_MANUFACTURER, +}; + +static enum power_supply_property bq27520g3_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CAPACITY_LEVEL, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, + POWER_SUPPLY_PROP_TECHNOLOGY, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_CHARGE_NOW, + POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, + POWER_SUPPLY_PROP_CYCLE_COUNT, + POWER_SUPPLY_PROP_ENERGY_NOW, + POWER_SUPPLY_PROP_POWER_AVG, + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_MANUFACTURER, +}; + +static enum power_supply_property bq27520g4_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CAPACITY_LEVEL, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, + POWER_SUPPLY_PROP_TECHNOLOGY, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_CHARGE_NOW, + POWER_SUPPLY_PROP_CYCLE_COUNT, POWER_SUPPLY_PROP_HEALTH, POWER_SUPPLY_PROP_MANUFACTURER, }; @@ -421,8 +738,16 @@ static struct { } bq27xxx_battery_props[] = { BQ27XXX_PROP(BQ27000, bq27000_battery_props), BQ27XXX_PROP(BQ27010, bq27010_battery_props), + BQ27XXX_PROP(BQ2750X, bq2750x_battery_props), + BQ27XXX_PROP(BQ2751X, bq2751x_battery_props), BQ27XXX_PROP(BQ27500, bq27500_battery_props), - BQ27XXX_PROP(BQ27510, bq27510_battery_props), + BQ27XXX_PROP(BQ27510G1, bq27510g1_battery_props), + BQ27XXX_PROP(BQ27510G2, bq27510g2_battery_props), + BQ27XXX_PROP(BQ27510G3, bq27510g3_battery_props), + BQ27XXX_PROP(BQ27520G1, bq27520g1_battery_props), + BQ27XXX_PROP(BQ27520G2, bq27520g2_battery_props), + BQ27XXX_PROP(BQ27520G3, bq27520g3_battery_props), + BQ27XXX_PROP(BQ27520G4, bq27520g4_battery_props), BQ27XXX_PROP(BQ27530, bq27530_battery_props), BQ27XXX_PROP(BQ27541, bq27541_battery_props), BQ27XXX_PROP(BQ27545, bq27545_battery_props), @@ -674,13 +999,26 @@ static int bq27xxx_battery_read_pwr_avg(struct bq27xxx_device_info *di) */ static bool bq27xxx_battery_overtemp(struct bq27xxx_device_info *di, u16 flags) { - if (di->chip == BQ27500 || di->chip == BQ27510 || - di->chip == BQ27541 || di->chip == BQ27545) + switch (di->chip) { + case BQ2750X: + case BQ2751X: + case BQ27500: + case BQ27510G1: + case BQ27510G2: + case BQ27510G3: + case BQ27520G1: + case BQ27520G2: + case BQ27520G3: + case BQ27520G4: + case BQ27541: + case BQ27545: return flags & (BQ27XXX_FLAG_OTC | BQ27XXX_FLAG_OTD); - if (di->chip == BQ27530 || di->chip == BQ27421) + case BQ27530: + case BQ27421: return flags & BQ27XXX_FLAG_OT; - - return false; + default: + return false; + } } /* diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index 5c5c3a6f9923..c68fbc3fe50a 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -148,9 +148,17 @@ static int bq27xxx_battery_i2c_remove(struct i2c_client *client) static const struct i2c_device_id bq27xxx_i2c_id_table[] = { { "bq27200", BQ27000 }, { "bq27210", BQ27010 }, - { "bq27500", BQ27500 }, - { "bq27510", BQ27510 }, - { "bq27520", BQ27510 }, + { "bq27500", BQ2750X }, + { "bq27510", BQ2751X }, + { "bq27520", BQ2751X }, + { "bq27500-1", BQ27500 }, + { "bq27510g1", BQ27510G1 }, + { "bq27510g2", BQ27510G2 }, + { "bq27510g3", BQ27510G3 }, + { "bq27520g1", BQ27520G1 }, + { "bq27520g2", BQ27520G2 }, + { "bq27520g3", BQ27520G3 }, + { "bq27520g4", BQ27520G4 }, { "bq27530", BQ27530 }, { "bq27531", BQ27530 }, { "bq27541", BQ27541 }, @@ -173,6 +181,14 @@ static const struct of_device_id bq27xxx_battery_i2c_of_match_table[] = { { .compatible = "ti,bq27500" }, { .compatible = "ti,bq27510" }, { .compatible = "ti,bq27520" }, + { .compatible = "ti,bq27500-1" }, + { .compatible = "ti,bq27510g1" }, + { .compatible = "ti,bq27510g2" }, + { .compatible = "ti,bq27510g3" }, + { .compatible = "ti,bq27520g1" }, + { .compatible = "ti,bq27520g2" }, + { .compatible = "ti,bq27520g3" }, + { .compatible = "ti,bq27520g4" }, { .compatible = "ti,bq27530" }, { .compatible = "ti,bq27531" }, { .compatible = "ti,bq27541" }, diff --git a/drivers/power/supply/gpio-charger.c b/drivers/power/supply/gpio-charger.c index c5869b1941ac..001731e88718 100644 --- a/drivers/power/supply/gpio-charger.c +++ b/drivers/power/supply/gpio-charger.c @@ -14,7 +14,7 @@ */ #include <linux/device.h> -#include <linux/gpio.h> +#include <linux/gpio.h> /* For legacy platform data */ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> @@ -23,7 +23,7 @@ #include <linux/power_supply.h> #include <linux/slab.h> #include <linux/of.h> -#include <linux/of_gpio.h> +#include <linux/gpio/consumer.h> #include <linux/power/gpio-charger.h> @@ -34,6 +34,8 @@ struct gpio_charger { struct power_supply *charger; struct power_supply_desc charger_desc; + struct gpio_desc *gpiod; + bool legacy_gpio_requested; }; static irqreturn_t gpio_charger_irq(int irq, void *devid) @@ -58,7 +60,8 @@ static int gpio_charger_get_property(struct power_supply *psy, switch (psp) { case POWER_SUPPLY_PROP_ONLINE: - val->intval = !!gpio_get_value_cansleep(pdata->gpio); + val->intval = gpiod_get_value_cansleep(gpio_charger->gpiod); + /* This xor is only ever used with legacy pdata GPIO */ val->intval ^= pdata->gpio_active_low; break; default: @@ -78,7 +81,6 @@ struct gpio_charger_platform_data *gpio_charger_parse_dt(struct device *dev) struct device_node *np = dev->of_node; struct gpio_charger_platform_data *pdata; const char *chargetype; - enum of_gpio_flags flags; int ret; if (!np) @@ -89,16 +91,6 @@ struct gpio_charger_platform_data *gpio_charger_parse_dt(struct device *dev) return ERR_PTR(-ENOMEM); pdata->name = np->name; - - pdata->gpio = of_get_gpio_flags(np, 0, &flags); - if (pdata->gpio < 0) { - if (pdata->gpio != -EPROBE_DEFER) - dev_err(dev, "could not get charger gpio\n"); - return ERR_PTR(pdata->gpio); - } - - pdata->gpio_active_low = !!(flags & OF_GPIO_ACTIVE_LOW); - pdata->type = POWER_SUPPLY_TYPE_UNKNOWN; ret = of_property_read_string(np, "charger-type", &chargetype); if (ret >= 0) { @@ -144,11 +136,6 @@ static int gpio_charger_probe(struct platform_device *pdev) } } - if (!gpio_is_valid(pdata->gpio)) { - dev_err(&pdev->dev, "Invalid gpio pin\n"); - return -EINVAL; - } - gpio_charger = devm_kzalloc(&pdev->dev, sizeof(*gpio_charger), GFP_KERNEL); if (!gpio_charger) { @@ -156,6 +143,45 @@ static int gpio_charger_probe(struct platform_device *pdev) return -ENOMEM; } + /* + * This will fetch a GPIO descriptor from device tree, ACPI or + * boardfile descriptor tables. It's good to try this first. + */ + gpio_charger->gpiod = devm_gpiod_get(&pdev->dev, NULL, GPIOD_IN); + + /* + * If this fails and we're not using device tree, try the + * legacy platform data method. + */ + if (IS_ERR(gpio_charger->gpiod) && !pdev->dev.of_node) { + /* Non-DT: use legacy GPIO numbers */ + if (!gpio_is_valid(pdata->gpio)) { + dev_err(&pdev->dev, "Invalid gpio pin in pdata\n"); + return -EINVAL; + } + ret = gpio_request(pdata->gpio, dev_name(&pdev->dev)); + if (ret) { + dev_err(&pdev->dev, "Failed to request gpio pin: %d\n", + ret); + return ret; + } + gpio_charger->legacy_gpio_requested = true; + ret = gpio_direction_input(pdata->gpio); + if (ret) { + dev_err(&pdev->dev, "Failed to set gpio to input: %d\n", + ret); + goto err_gpio_free; + } + /* Then convert this to gpiod for now */ + gpio_charger->gpiod = gpio_to_desc(pdata->gpio); + } else if (IS_ERR(gpio_charger->gpiod)) { + /* Just try again if this happens */ + if (PTR_ERR(gpio_charger->gpiod) == -EPROBE_DEFER) + return -EPROBE_DEFER; + dev_err(&pdev->dev, "error getting GPIO descriptor\n"); + return PTR_ERR(gpio_charger->gpiod); + } + charger_desc = &gpio_charger->charger_desc; charger_desc->name = pdata->name ? pdata->name : "gpio-charger"; @@ -169,17 +195,6 @@ static int gpio_charger_probe(struct platform_device *pdev) psy_cfg.of_node = pdev->dev.of_node; psy_cfg.drv_data = gpio_charger; - ret = gpio_request(pdata->gpio, dev_name(&pdev->dev)); - if (ret) { - dev_err(&pdev->dev, "Failed to request gpio pin: %d\n", ret); - goto err_free; - } - ret = gpio_direction_input(pdata->gpio); - if (ret) { - dev_err(&pdev->dev, "Failed to set gpio to input: %d\n", ret); - goto err_gpio_free; - } - gpio_charger->pdata = pdata; gpio_charger->charger = power_supply_register(&pdev->dev, @@ -191,7 +206,7 @@ static int gpio_charger_probe(struct platform_device *pdev) goto err_gpio_free; } - irq = gpio_to_irq(pdata->gpio); + irq = gpiod_to_irq(gpio_charger->gpiod); if (irq > 0) { ret = request_any_context_irq(irq, gpio_charger_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, @@ -209,8 +224,8 @@ static int gpio_charger_probe(struct platform_device *pdev) return 0; err_gpio_free: - gpio_free(pdata->gpio); -err_free: + if (gpio_charger->legacy_gpio_requested) + gpio_free(pdata->gpio); return ret; } @@ -223,7 +238,8 @@ static int gpio_charger_remove(struct platform_device *pdev) power_supply_unregister(gpio_charger->charger); - gpio_free(gpio_charger->pdata->gpio); + if (gpio_charger->legacy_gpio_requested) + gpio_free(gpio_charger->pdata->gpio); return 0; } diff --git a/drivers/power/supply/intel_mid_battery.c b/drivers/power/supply/intel_mid_battery.c deleted file mode 100644 index dc7feef1bea4..000000000000 --- a/drivers/power/supply/intel_mid_battery.c +++ /dev/null @@ -1,795 +0,0 @@ -/* - * intel_mid_battery.c - Intel MID PMIC Battery Driver - * - * Copyright (C) 2009 Intel Corporation - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * 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; version 2 of the License. - * - * 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. - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * Author: Nithish Mahalingam <nithish.mahalingam@intel.com> - */ - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/err.h> -#include <linux/interrupt.h> -#include <linux/workqueue.h> -#include <linux/jiffies.h> -#include <linux/param.h> -#include <linux/device.h> -#include <linux/spi/spi.h> -#include <linux/platform_device.h> -#include <linux/power_supply.h> - -#include <asm/intel_scu_ipc.h> - -#define DRIVER_NAME "pmic_battery" - -/********************************************************************* - * Generic defines - *********************************************************************/ - -static int debug; -module_param(debug, int, 0444); -MODULE_PARM_DESC(debug, "Flag to enable PMIC Battery debug messages."); - -#define PMIC_BATT_DRV_INFO_UPDATED 1 -#define PMIC_BATT_PRESENT 1 -#define PMIC_BATT_NOT_PRESENT 0 -#define PMIC_USB_PRESENT PMIC_BATT_PRESENT -#define PMIC_USB_NOT_PRESENT PMIC_BATT_NOT_PRESENT - -/* pmic battery register related */ -#define PMIC_BATT_CHR_SCHRGINT_ADDR 0xD2 -#define PMIC_BATT_CHR_SBATOVP_MASK (1 << 1) -#define PMIC_BATT_CHR_STEMP_MASK (1 << 2) -#define PMIC_BATT_CHR_SCOMP_MASK (1 << 3) -#define PMIC_BATT_CHR_SUSBDET_MASK (1 << 4) -#define PMIC_BATT_CHR_SBATDET_MASK (1 << 5) -#define PMIC_BATT_CHR_SDCLMT_MASK (1 << 6) -#define PMIC_BATT_CHR_SUSBOVP_MASK (1 << 7) -#define PMIC_BATT_CHR_EXCPT_MASK 0x86 - -#define PMIC_BATT_ADC_ACCCHRG_MASK (1 << 31) -#define PMIC_BATT_ADC_ACCCHRGVAL_MASK 0x7FFFFFFF - -/* pmic ipc related */ -#define PMIC_BATT_CHR_IPC_FCHRG_SUBID 0x4 -#define PMIC_BATT_CHR_IPC_TCHRG_SUBID 0x6 - -/* types of battery charging */ -enum batt_charge_type { - BATT_USBOTG_500MA_CHARGE, - BATT_USBOTG_TRICKLE_CHARGE, -}; - -/* valid battery events */ -enum batt_event { - BATT_EVENT_BATOVP_EXCPT, - BATT_EVENT_USBOVP_EXCPT, - BATT_EVENT_TEMP_EXCPT, - BATT_EVENT_DCLMT_EXCPT, - BATT_EVENT_EXCPT -}; - - -/********************************************************************* - * Battery properties - *********************************************************************/ - -/* - * pmic battery info - */ -struct pmic_power_module_info { - bool is_dev_info_updated; - struct device *dev; - /* pmic battery data */ - unsigned long update_time; /* jiffies when data read */ - unsigned int usb_is_present; - unsigned int batt_is_present; - unsigned int batt_health; - unsigned int usb_health; - unsigned int batt_status; - unsigned int batt_charge_now; /* in mAS */ - unsigned int batt_prev_charge_full; /* in mAS */ - unsigned int batt_charge_rate; /* in units per second */ - - struct power_supply *usb; - struct power_supply *batt; - int irq; /* GPE_ID or IRQ# */ - struct workqueue_struct *monitor_wqueue; - struct delayed_work monitor_battery; - struct work_struct handler; -}; - -static unsigned int delay_time = 2000; /* in ms */ - -/* - * pmic ac properties - */ -static enum power_supply_property pmic_usb_props[] = { - POWER_SUPPLY_PROP_PRESENT, - POWER_SUPPLY_PROP_HEALTH, -}; - -/* - * pmic battery properties - */ -static enum power_supply_property pmic_battery_props[] = { - POWER_SUPPLY_PROP_STATUS, - POWER_SUPPLY_PROP_HEALTH, - POWER_SUPPLY_PROP_PRESENT, - POWER_SUPPLY_PROP_CHARGE_NOW, - POWER_SUPPLY_PROP_CHARGE_FULL, -}; - - -/* - * Glue functions for talking to the IPC - */ - -struct battery_property { - u32 capacity; /* Charger capacity */ - u8 crnt; /* Quick charge current value*/ - u8 volt; /* Fine adjustment of constant charge voltage */ - u8 prot; /* CHRGPROT register value */ - u8 prot2; /* CHRGPROT1 register value */ - u8 timer; /* Charging timer */ -}; - -#define IPCMSG_BATTERY 0xEF - -/* Battery coulomb counter accumulator commands */ -#define IPC_CMD_CC_WR 0 /* Update coulomb counter value */ -#define IPC_CMD_CC_RD 1 /* Read coulomb counter value */ -#define IPC_CMD_BATTERY_PROPERTY 2 /* Read Battery property */ - -/** - * pmic_scu_ipc_battery_cc_read - read battery cc - * @value: battery coulomb counter read - * - * Reads the battery couloumb counter value, returns 0 on success, or - * an error code - * - * This function may sleep. Locking for SCU accesses is handled for - * the caller. - */ -static int pmic_scu_ipc_battery_cc_read(u32 *value) -{ - return intel_scu_ipc_command(IPCMSG_BATTERY, IPC_CMD_CC_RD, - NULL, 0, value, 1); -} - -/** - * pmic_scu_ipc_battery_property_get - fetch properties - * @prop: battery properties - * - * Retrieve the battery properties from the power management - * - * This function may sleep. Locking for SCU accesses is handled for - * the caller. - */ -static int pmic_scu_ipc_battery_property_get(struct battery_property *prop) -{ - u32 data[3]; - u8 *p = (u8 *)&data[1]; - int err = intel_scu_ipc_command(IPCMSG_BATTERY, - IPC_CMD_BATTERY_PROPERTY, NULL, 0, data, 3); - - prop->capacity = data[0]; - prop->crnt = *p++; - prop->volt = *p++; - prop->prot = *p++; - prop->prot2 = *p++; - prop->timer = *p++; - - return err; -} - -/** - * pmic_scu_ipc_set_charger - set charger - * @charger: charger to select - * - * Switch the charging mode for the SCU - */ - -static int pmic_scu_ipc_set_charger(int charger) -{ - return intel_scu_ipc_simple_command(IPCMSG_BATTERY, charger); -} - -/** - * pmic_battery_log_event - log battery events - * @event: battery event to be logged - * Context: can sleep - * - * There are multiple battery events which may be of interest to users; - * this battery function logs the different battery events onto the - * kernel log messages. - */ -static void pmic_battery_log_event(enum batt_event event) -{ - printk(KERN_WARNING "pmic-battery: "); - switch (event) { - case BATT_EVENT_BATOVP_EXCPT: - printk(KERN_CONT "battery overvoltage condition\n"); - break; - case BATT_EVENT_USBOVP_EXCPT: - printk(KERN_CONT "usb charger overvoltage condition\n"); - break; - case BATT_EVENT_TEMP_EXCPT: - printk(KERN_CONT "high battery temperature condition\n"); - break; - case BATT_EVENT_DCLMT_EXCPT: - printk(KERN_CONT "over battery charge current condition\n"); - break; - default: - printk(KERN_CONT "charger/battery exception %d\n", event); - break; - } -} - -/** - * pmic_battery_read_status - read battery status information - * @pbi: device info structure to update the read information - * Context: can sleep - * - * PMIC power source information need to be updated based on the data read - * from the PMIC battery registers. - * - */ -static void pmic_battery_read_status(struct pmic_power_module_info *pbi) -{ - unsigned int update_time_intrvl; - unsigned int chrg_val; - u32 ccval; - u8 r8; - struct battery_property batt_prop; - int batt_present = 0; - int usb_present = 0; - int batt_exception = 0; - - /* make sure the last batt_status read happened delay_time before */ - if (pbi->update_time && time_before(jiffies, pbi->update_time + - msecs_to_jiffies(delay_time))) - return; - - update_time_intrvl = jiffies_to_msecs(jiffies - pbi->update_time); - pbi->update_time = jiffies; - - /* read coulomb counter registers and schrgint register */ - if (pmic_scu_ipc_battery_cc_read(&ccval)) { - dev_warn(pbi->dev, "%s(): ipc config cmd failed\n", - __func__); - return; - } - - if (intel_scu_ipc_ioread8(PMIC_BATT_CHR_SCHRGINT_ADDR, &r8)) { - dev_warn(pbi->dev, "%s(): ipc pmic read failed\n", - __func__); - return; - } - - /* - * set pmic_power_module_info members based on pmic register values - * read. - */ - - /* set batt_is_present */ - if (r8 & PMIC_BATT_CHR_SBATDET_MASK) { - pbi->batt_is_present = PMIC_BATT_PRESENT; - batt_present = 1; - } else { - pbi->batt_is_present = PMIC_BATT_NOT_PRESENT; - pbi->batt_health = POWER_SUPPLY_HEALTH_UNKNOWN; - pbi->batt_status = POWER_SUPPLY_STATUS_UNKNOWN; - } - - /* set batt_health */ - if (batt_present) { - if (r8 & PMIC_BATT_CHR_SBATOVP_MASK) { - pbi->batt_health = POWER_SUPPLY_HEALTH_OVERVOLTAGE; - pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING; - pmic_battery_log_event(BATT_EVENT_BATOVP_EXCPT); - batt_exception = 1; - } else if (r8 & PMIC_BATT_CHR_STEMP_MASK) { - pbi->batt_health = POWER_SUPPLY_HEALTH_OVERHEAT; - pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING; - pmic_battery_log_event(BATT_EVENT_TEMP_EXCPT); - batt_exception = 1; - } else { - pbi->batt_health = POWER_SUPPLY_HEALTH_GOOD; - if (r8 & PMIC_BATT_CHR_SDCLMT_MASK) { - /* PMIC will change charging current automatically */ - pmic_battery_log_event(BATT_EVENT_DCLMT_EXCPT); - } - } - } - - /* set usb_is_present */ - if (r8 & PMIC_BATT_CHR_SUSBDET_MASK) { - pbi->usb_is_present = PMIC_USB_PRESENT; - usb_present = 1; - } else { - pbi->usb_is_present = PMIC_USB_NOT_PRESENT; - pbi->usb_health = POWER_SUPPLY_HEALTH_UNKNOWN; - } - - if (usb_present) { - if (r8 & PMIC_BATT_CHR_SUSBOVP_MASK) { - pbi->usb_health = POWER_SUPPLY_HEALTH_OVERVOLTAGE; - pmic_battery_log_event(BATT_EVENT_USBOVP_EXCPT); - } else { - pbi->usb_health = POWER_SUPPLY_HEALTH_GOOD; - } - } - - chrg_val = ccval & PMIC_BATT_ADC_ACCCHRGVAL_MASK; - - /* set batt_prev_charge_full to battery capacity the first time */ - if (!pbi->is_dev_info_updated) { - if (pmic_scu_ipc_battery_property_get(&batt_prop)) { - dev_warn(pbi->dev, "%s(): ipc config cmd failed\n", - __func__); - return; - } - pbi->batt_prev_charge_full = batt_prop.capacity; - } - - /* set batt_status */ - if (batt_present && !batt_exception) { - if (r8 & PMIC_BATT_CHR_SCOMP_MASK) { - pbi->batt_status = POWER_SUPPLY_STATUS_FULL; - pbi->batt_prev_charge_full = chrg_val; - } else if (ccval & PMIC_BATT_ADC_ACCCHRG_MASK) { - pbi->batt_status = POWER_SUPPLY_STATUS_DISCHARGING; - } else { - pbi->batt_status = POWER_SUPPLY_STATUS_CHARGING; - } - } - - /* set batt_charge_rate */ - if (pbi->is_dev_info_updated && batt_present && !batt_exception) { - if (pbi->batt_status == POWER_SUPPLY_STATUS_DISCHARGING) { - if (pbi->batt_charge_now - chrg_val) { - pbi->batt_charge_rate = ((pbi->batt_charge_now - - chrg_val) * 1000 * 60) / - update_time_intrvl; - } - } else if (pbi->batt_status == POWER_SUPPLY_STATUS_CHARGING) { - if (chrg_val - pbi->batt_charge_now) { - pbi->batt_charge_rate = ((chrg_val - - pbi->batt_charge_now) * 1000 * 60) / - update_time_intrvl; - } - } else - pbi->batt_charge_rate = 0; - } else { - pbi->batt_charge_rate = -1; - } - - /* batt_charge_now */ - if (batt_present && !batt_exception) - pbi->batt_charge_now = chrg_val; - else - pbi->batt_charge_now = -1; - - pbi->is_dev_info_updated = PMIC_BATT_DRV_INFO_UPDATED; -} - -/** - * pmic_usb_get_property - usb power source get property - * @psy: usb power supply context - * @psp: usb power source property - * @val: usb power source property value - * Context: can sleep - * - * PMIC usb power source property needs to be provided to power_supply - * subsytem for it to provide the information to users. - */ -static int pmic_usb_get_property(struct power_supply *psy, - enum power_supply_property psp, - union power_supply_propval *val) -{ - struct pmic_power_module_info *pbi = power_supply_get_drvdata(psy); - - /* update pmic_power_module_info members */ - pmic_battery_read_status(pbi); - - switch (psp) { - case POWER_SUPPLY_PROP_PRESENT: - val->intval = pbi->usb_is_present; - break; - case POWER_SUPPLY_PROP_HEALTH: - val->intval = pbi->usb_health; - break; - default: - return -EINVAL; - } - - return 0; -} - -static inline unsigned long mAStouAh(unsigned long v) -{ - /* seconds to hours, mA to µA */ - return (v * 1000) / 3600; -} - -/** - * pmic_battery_get_property - battery power source get property - * @psy: battery power supply context - * @psp: battery power source property - * @val: battery power source property value - * Context: can sleep - * - * PMIC battery power source property needs to be provided to power_supply - * subsytem for it to provide the information to users. - */ -static int pmic_battery_get_property(struct power_supply *psy, - enum power_supply_property psp, - union power_supply_propval *val) -{ - struct pmic_power_module_info *pbi = power_supply_get_drvdata(psy); - - /* update pmic_power_module_info members */ - pmic_battery_read_status(pbi); - - switch (psp) { - case POWER_SUPPLY_PROP_STATUS: - val->intval = pbi->batt_status; - break; - case POWER_SUPPLY_PROP_HEALTH: - val->intval = pbi->batt_health; - break; - case POWER_SUPPLY_PROP_PRESENT: - val->intval = pbi->batt_is_present; - break; - case POWER_SUPPLY_PROP_CHARGE_NOW: - val->intval = mAStouAh(pbi->batt_charge_now); - break; - case POWER_SUPPLY_PROP_CHARGE_FULL: - val->intval = mAStouAh(pbi->batt_prev_charge_full); - break; - default: - return -EINVAL; - } - - return 0; -} - -/** - * pmic_battery_monitor - monitor battery status - * @work: work structure - * Context: can sleep - * - * PMIC battery status needs to be monitored for any change - * and information needs to be frequently updated. - */ -static void pmic_battery_monitor(struct work_struct *work) -{ - struct pmic_power_module_info *pbi = container_of(work, - struct pmic_power_module_info, monitor_battery.work); - - /* update pmic_power_module_info members */ - pmic_battery_read_status(pbi); - queue_delayed_work(pbi->monitor_wqueue, &pbi->monitor_battery, HZ * 10); -} - -/** - * pmic_battery_set_charger - set battery charger - * @pbi: device info structure - * @chrg: charge mode to set battery charger in - * Context: can sleep - * - * PMIC battery charger needs to be enabled based on the usb charge - * capabilities connected to the platform. - */ -static int pmic_battery_set_charger(struct pmic_power_module_info *pbi, - enum batt_charge_type chrg) -{ - int retval; - - /* set usblmt bits and chrgcntl register bits appropriately */ - switch (chrg) { - case BATT_USBOTG_500MA_CHARGE: - retval = pmic_scu_ipc_set_charger(PMIC_BATT_CHR_IPC_FCHRG_SUBID); - break; - case BATT_USBOTG_TRICKLE_CHARGE: - retval = pmic_scu_ipc_set_charger(PMIC_BATT_CHR_IPC_TCHRG_SUBID); - break; - default: - dev_warn(pbi->dev, "%s(): out of range usb charger " - "charge detected\n", __func__); - return -EINVAL; - } - - if (retval) { - dev_warn(pbi->dev, "%s(): ipc pmic read failed\n", - __func__); - return retval; - } - - return 0; -} - -/** - * pmic_battery_interrupt_handler - pmic battery interrupt handler - * Context: interrupt context - * - * PMIC battery interrupt handler which will be called with either - * battery full condition occurs or usb otg & battery connect - * condition occurs. - */ -static irqreturn_t pmic_battery_interrupt_handler(int id, void *dev) -{ - struct pmic_power_module_info *pbi = dev; - - schedule_work(&pbi->handler); - - return IRQ_HANDLED; -} - -/** - * pmic_battery_handle_intrpt - pmic battery service interrupt - * @work: work structure - * Context: can sleep - * - * PMIC battery needs to either update the battery status as full - * if it detects battery full condition caused the interrupt or needs - * to enable battery charger if it detects usb and battery detect - * caused the source of interrupt. - */ -static void pmic_battery_handle_intrpt(struct work_struct *work) -{ - struct pmic_power_module_info *pbi = container_of(work, - struct pmic_power_module_info, handler); - enum batt_charge_type chrg; - u8 r8; - - if (intel_scu_ipc_ioread8(PMIC_BATT_CHR_SCHRGINT_ADDR, &r8)) { - dev_warn(pbi->dev, "%s(): ipc pmic read failed\n", - __func__); - return; - } - /* find the cause of the interrupt */ - if (r8 & PMIC_BATT_CHR_SBATDET_MASK) { - pbi->batt_is_present = PMIC_BATT_PRESENT; - } else { - pbi->batt_is_present = PMIC_BATT_NOT_PRESENT; - pbi->batt_health = POWER_SUPPLY_HEALTH_UNKNOWN; - pbi->batt_status = POWER_SUPPLY_STATUS_UNKNOWN; - return; - } - - if (r8 & PMIC_BATT_CHR_EXCPT_MASK) { - pbi->batt_health = POWER_SUPPLY_HEALTH_UNKNOWN; - pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING; - pbi->usb_health = POWER_SUPPLY_HEALTH_UNKNOWN; - pmic_battery_log_event(BATT_EVENT_EXCPT); - return; - } else { - pbi->batt_health = POWER_SUPPLY_HEALTH_GOOD; - pbi->usb_health = POWER_SUPPLY_HEALTH_GOOD; - } - - if (r8 & PMIC_BATT_CHR_SCOMP_MASK) { - u32 ccval; - pbi->batt_status = POWER_SUPPLY_STATUS_FULL; - - if (pmic_scu_ipc_battery_cc_read(&ccval)) { - dev_warn(pbi->dev, "%s(): ipc config cmd " - "failed\n", __func__); - return; - } - pbi->batt_prev_charge_full = ccval & - PMIC_BATT_ADC_ACCCHRGVAL_MASK; - return; - } - - if (r8 & PMIC_BATT_CHR_SUSBDET_MASK) { - pbi->usb_is_present = PMIC_USB_PRESENT; - } else { - pbi->usb_is_present = PMIC_USB_NOT_PRESENT; - pbi->usb_health = POWER_SUPPLY_HEALTH_UNKNOWN; - return; - } - - /* setup battery charging */ - -#if 0 - /* check usb otg power capability and set charger accordingly */ - retval = langwell_udc_maxpower(&power); - if (retval) { - dev_warn(pbi->dev, - "%s(): usb otg power query failed with error code %d\n", - __func__, retval); - return; - } - - if (power >= 500) - chrg = BATT_USBOTG_500MA_CHARGE; - else -#endif - chrg = BATT_USBOTG_TRICKLE_CHARGE; - - /* enable battery charging */ - if (pmic_battery_set_charger(pbi, chrg)) { - dev_warn(pbi->dev, - "%s(): failed to set up battery charging\n", __func__); - return; - } - - dev_dbg(pbi->dev, - "pmic-battery: %s() - setting up battery charger successful\n", - __func__); -} - -/* - * Description of power supplies - */ -static const struct power_supply_desc pmic_usb_desc = { - .name = "pmic-usb", - .type = POWER_SUPPLY_TYPE_USB, - .properties = pmic_usb_props, - .num_properties = ARRAY_SIZE(pmic_usb_props), - .get_property = pmic_usb_get_property, -}; - -static const struct power_supply_desc pmic_batt_desc = { - .name = "pmic-batt", - .type = POWER_SUPPLY_TYPE_BATTERY, - .properties = pmic_battery_props, - .num_properties = ARRAY_SIZE(pmic_battery_props), - .get_property = pmic_battery_get_property, -}; - -/** - * pmic_battery_probe - pmic battery initialize - * @irq: pmic battery device irq - * @dev: pmic battery device structure - * Context: can sleep - * - * PMIC battery initializes its internal data structue and other - * infrastructure components for it to work as expected. - */ -static int probe(int irq, struct device *dev) -{ - int retval = 0; - struct pmic_power_module_info *pbi; - struct power_supply_config psy_cfg = {}; - - dev_dbg(dev, "pmic-battery: found pmic battery device\n"); - - pbi = kzalloc(sizeof(*pbi), GFP_KERNEL); - if (!pbi) { - dev_err(dev, "%s(): memory allocation failed\n", - __func__); - return -ENOMEM; - } - - pbi->dev = dev; - pbi->irq = irq; - dev_set_drvdata(dev, pbi); - psy_cfg.drv_data = pbi; - - /* initialize all required framework before enabling interrupts */ - INIT_WORK(&pbi->handler, pmic_battery_handle_intrpt); - INIT_DELAYED_WORK(&pbi->monitor_battery, pmic_battery_monitor); - pbi->monitor_wqueue = alloc_workqueue(dev_name(dev), WQ_MEM_RECLAIM, 0); - if (!pbi->monitor_wqueue) { - dev_err(dev, "%s(): wqueue init failed\n", __func__); - retval = -ESRCH; - goto wqueue_failed; - } - - /* register interrupt */ - retval = request_irq(pbi->irq, pmic_battery_interrupt_handler, - 0, DRIVER_NAME, pbi); - if (retval) { - dev_err(dev, "%s(): cannot get IRQ\n", __func__); - goto requestirq_failed; - } - - /* register pmic-batt with power supply subsystem */ - pbi->batt = power_supply_register(dev, &pmic_usb_desc, &psy_cfg); - if (IS_ERR(pbi->batt)) { - dev_err(dev, - "%s(): failed to register pmic battery device with power supply subsystem\n", - __func__); - retval = PTR_ERR(pbi->batt); - goto power_reg_failed; - } - - dev_dbg(dev, "pmic-battery: %s() - pmic battery device " - "registration with power supply subsystem successful\n", - __func__); - - queue_delayed_work(pbi->monitor_wqueue, &pbi->monitor_battery, HZ * 1); - - /* register pmic-usb with power supply subsystem */ - pbi->usb = power_supply_register(dev, &pmic_batt_desc, &psy_cfg); - if (IS_ERR(pbi->usb)) { - dev_err(dev, - "%s(): failed to register pmic usb device with power supply subsystem\n", - __func__); - retval = PTR_ERR(pbi->usb); - goto power_reg_failed_1; - } - - if (debug) - printk(KERN_INFO "pmic-battery: %s() - pmic usb device " - "registration with power supply subsystem successful\n", - __func__); - - return retval; - -power_reg_failed_1: - power_supply_unregister(pbi->batt); -power_reg_failed: - cancel_delayed_work_sync(&pbi->monitor_battery); -requestirq_failed: - destroy_workqueue(pbi->monitor_wqueue); -wqueue_failed: - kfree(pbi); - - return retval; -} - -static int platform_pmic_battery_probe(struct platform_device *pdev) -{ - return probe(pdev->id, &pdev->dev); -} - -/** - * pmic_battery_remove - pmic battery finalize - * @dev: pmic battery device structure - * Context: can sleep - * - * PMIC battery finalizes its internal data structue and other - * infrastructure components that it initialized in - * pmic_battery_probe. - */ - -static int platform_pmic_battery_remove(struct platform_device *pdev) -{ - struct pmic_power_module_info *pbi = platform_get_drvdata(pdev); - - free_irq(pbi->irq, pbi); - cancel_delayed_work_sync(&pbi->monitor_battery); - destroy_workqueue(pbi->monitor_wqueue); - - power_supply_unregister(pbi->usb); - power_supply_unregister(pbi->batt); - - cancel_work_sync(&pbi->handler); - kfree(pbi); - return 0; -} - -static struct platform_driver platform_pmic_battery_driver = { - .driver = { - .name = DRIVER_NAME, - }, - .probe = platform_pmic_battery_probe, - .remove = platform_pmic_battery_remove, -}; - -module_platform_driver(platform_pmic_battery_driver); - -MODULE_AUTHOR("Nithish Mahalingam <nithish.mahalingam@intel.com>"); -MODULE_DESCRIPTION("Intel Moorestown PMIC Battery Driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/power/supply/max14656_charger_detector.c b/drivers/power/supply/max14656_charger_detector.c new file mode 100644 index 000000000000..b91b1d2999dc --- /dev/null +++ b/drivers/power/supply/max14656_charger_detector.c @@ -0,0 +1,327 @@ +/* + * Maxim MAX14656 / AL32 USB Charger Detector driver + * + * Copyright (C) 2014 LG Electronics, Inc + * Copyright (C) 2016 Alexander Kurz <akurz@blala.de> + * + * Components from Maxim AL32 Charger detection Driver for MX50 Yoshi Board + * Copyright (C) Amazon Technologies Inc. All rights reserved. + * Manish Lachwani (lachwani@lab126.com) + * + * This package is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + */ +#include <linux/module.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/i2c.h> +#include <linux/interrupt.h> +#include <linux/slab.h> +#include <linux/gpio.h> +#include <linux/of_gpio.h> +#include <linux/of_device.h> +#include <linux/workqueue.h> +#include <linux/power_supply.h> + +#define MAX14656_MANUFACTURER "Maxim Integrated" +#define MAX14656_NAME "max14656" + +#define MAX14656_DEVICE_ID 0x00 +#define MAX14656_INTERRUPT_1 0x01 +#define MAX14656_INTERRUPT_2 0x02 +#define MAX14656_STATUS_1 0x03 +#define MAX14656_STATUS_2 0x04 +#define MAX14656_INTMASK_1 0x05 +#define MAX14656_INTMASK_2 0x06 +#define MAX14656_CONTROL_1 0x07 +#define MAX14656_CONTROL_2 0x08 +#define MAX14656_CONTROL_3 0x09 + +#define DEVICE_VENDOR_MASK 0xf0 +#define DEVICE_REV_MASK 0x0f +#define INT_EN_REG_MASK BIT(4) +#define CHG_TYPE_INT_MASK BIT(0) +#define STATUS1_VB_VALID_MASK BIT(4) +#define STATUS1_CHG_TYPE_MASK 0xf +#define INT1_DCD_TIMEOUT_MASK BIT(7) +#define CONTROL1_DEFAULT 0x0d +#define CONTROL1_INT_EN BIT(4) +#define CONTROL1_INT_ACTIVE_HIGH BIT(5) +#define CONTROL1_EDGE BIT(7) +#define CONTROL2_DEFAULT 0x8e +#define CONTROL2_ADC_EN BIT(0) +#define CONTROL3_DEFAULT 0x8d + +enum max14656_chg_type { + MAX14656_NO_CHARGER = 0, + MAX14656_SDP_CHARGER, + MAX14656_CDP_CHARGER, + MAX14656_DCP_CHARGER, + MAX14656_APPLE_500MA_CHARGER, + MAX14656_APPLE_1A_CHARGER, + MAX14656_APPLE_2A_CHARGER, + MAX14656_SPECIAL_500MA_CHARGER, + MAX14656_APPLE_12W, + MAX14656_CHARGER_LAST +}; + +static const struct max14656_chg_type_props { + enum power_supply_type type; +} chg_type_props[] = { + { POWER_SUPPLY_TYPE_UNKNOWN }, + { POWER_SUPPLY_TYPE_USB }, + { POWER_SUPPLY_TYPE_USB_CDP }, + { POWER_SUPPLY_TYPE_USB_DCP }, + { POWER_SUPPLY_TYPE_USB_DCP }, + { POWER_SUPPLY_TYPE_USB_DCP }, + { POWER_SUPPLY_TYPE_USB_DCP }, + { POWER_SUPPLY_TYPE_USB_DCP }, + { POWER_SUPPLY_TYPE_USB }, +}; + +struct max14656_chip { + struct i2c_client *client; + struct power_supply *detect_psy; + struct power_supply_desc psy_desc; + struct delayed_work irq_work; + + int irq; + int online; +}; + +static int max14656_read_reg(struct i2c_client *client, int reg, u8 *val) +{ + s32 ret; + + ret = i2c_smbus_read_byte_data(client, reg); + if (ret < 0) { + dev_err(&client->dev, + "i2c read fail: can't read from %02x: %d\n", + reg, ret); + return ret; + } + *val = ret; + return 0; +} + +static int max14656_write_reg(struct i2c_client *client, int reg, u8 val) +{ + s32 ret; + + ret = i2c_smbus_write_byte_data(client, reg, val); + if (ret < 0) { + dev_err(&client->dev, + "i2c write fail: can't write %02x to %02x: %d\n", + val, reg, ret); + return ret; + } + return 0; +} + +static int max14656_read_block_reg(struct i2c_client *client, u8 reg, + u8 length, u8 *val) +{ + int ret; + + ret = i2c_smbus_read_i2c_block_data(client, reg, length, val); + if (ret < 0) { + dev_err(&client->dev, "failed to block read reg 0x%x: %d\n", + reg, ret); + return ret; + } + + return 0; +} + +#define REG_TOTAL_NUM 5 +static void max14656_irq_worker(struct work_struct *work) +{ + struct max14656_chip *chip = + container_of(work, struct max14656_chip, irq_work.work); + + u8 buf[REG_TOTAL_NUM]; + u8 chg_type; + int ret = 0; + + ret = max14656_read_block_reg(chip->client, MAX14656_DEVICE_ID, + REG_TOTAL_NUM, buf); + + if ((buf[MAX14656_STATUS_1] & STATUS1_VB_VALID_MASK) && + (buf[MAX14656_STATUS_1] & STATUS1_CHG_TYPE_MASK)) { + chg_type = buf[MAX14656_STATUS_1] & STATUS1_CHG_TYPE_MASK; + if (chg_type < MAX14656_CHARGER_LAST) + chip->psy_desc.type = chg_type_props[chg_type].type; + else + chip->psy_desc.type = POWER_SUPPLY_TYPE_UNKNOWN; + chip->online = 1; + } else { + chip->online = 0; + chip->psy_desc.type = POWER_SUPPLY_TYPE_UNKNOWN; + } + + power_supply_changed(chip->detect_psy); +} + +static irqreturn_t max14656_irq(int irq, void *dev_id) +{ + struct max14656_chip *chip = dev_id; + + schedule_delayed_work(&chip->irq_work, msecs_to_jiffies(100)); + + return IRQ_HANDLED; +} + +static int max14656_hw_init(struct max14656_chip *chip) +{ + uint8_t val = 0; + uint8_t rev; + struct i2c_client *client = chip->client; + + if (max14656_read_reg(client, MAX14656_DEVICE_ID, &val)) + return -ENODEV; + + if ((val & DEVICE_VENDOR_MASK) != 0x20) { + dev_err(&client->dev, "wrong vendor ID %d\n", + ((val & DEVICE_VENDOR_MASK) >> 4)); + return -ENODEV; + } + rev = val & DEVICE_REV_MASK; + + /* Turn on ADC_EN */ + if (max14656_write_reg(client, MAX14656_CONTROL_2, CONTROL2_ADC_EN)) + return -EINVAL; + + /* turn on interrupts and low power mode */ + if (max14656_write_reg(client, MAX14656_CONTROL_1, + CONTROL1_DEFAULT | + CONTROL1_INT_EN | + CONTROL1_INT_ACTIVE_HIGH | + CONTROL1_EDGE)) + return -EINVAL; + + if (max14656_write_reg(client, MAX14656_INTMASK_1, 0x3)) + return -EINVAL; + + if (max14656_write_reg(client, MAX14656_INTMASK_2, 0x1)) + return -EINVAL; + + dev_info(&client->dev, "detected revision %d\n", rev); + return 0; +} + +static int max14656_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct max14656_chip *chip = power_supply_get_drvdata(psy); + + switch (psp) { + case POWER_SUPPLY_PROP_ONLINE: + val->intval = chip->online; + break; + case POWER_SUPPLY_PROP_MODEL_NAME: + val->strval = MAX14656_NAME; + break; + case POWER_SUPPLY_PROP_MANUFACTURER: + val->strval = MAX14656_MANUFACTURER; + break; + default: + return -EINVAL; + } + + return 0; +} + +static enum power_supply_property max14656_battery_props[] = { + POWER_SUPPLY_PROP_ONLINE, + POWER_SUPPLY_PROP_MODEL_NAME, + POWER_SUPPLY_PROP_MANUFACTURER, +}; + +static int max14656_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent); + struct device *dev = &client->dev; + struct power_supply_config psy_cfg = {}; + struct max14656_chip *chip; + int irq = client->irq; + int ret = 0; + + if (irq <= 0) { + dev_err(dev, "invalid irq number: %d\n", irq); + return -ENODEV; + } + + if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) { + dev_err(dev, "No support for SMBUS_BYTE_DATA\n"); + return -ENODEV; + } + + chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + psy_cfg.drv_data = chip; + chip->client = client; + chip->online = 0; + chip->psy_desc.name = MAX14656_NAME; + chip->psy_desc.type = POWER_SUPPLY_TYPE_UNKNOWN; + chip->psy_desc.properties = max14656_battery_props; + chip->psy_desc.num_properties = ARRAY_SIZE(max14656_battery_props); + chip->psy_desc.get_property = max14656_get_property; + chip->irq = irq; + + ret = max14656_hw_init(chip); + if (ret) + return -ENODEV; + + INIT_DELAYED_WORK(&chip->irq_work, max14656_irq_worker); + + ret = devm_request_irq(dev, chip->irq, max14656_irq, + IRQF_TRIGGER_FALLING, + MAX14656_NAME, chip); + if (ret) { + dev_err(dev, "request_irq %d failed\n", chip->irq); + return -EINVAL; + } + enable_irq_wake(chip->irq); + + chip->detect_psy = devm_power_supply_register(dev, + &chip->psy_desc, &psy_cfg); + if (IS_ERR(chip->detect_psy)) { + dev_err(dev, "power_supply_register failed\n"); + return -EINVAL; + } + + schedule_delayed_work(&chip->irq_work, msecs_to_jiffies(2000)); + + return 0; +} + +static const struct i2c_device_id max14656_id[] = { + { "max14656", 0 }, + {} +}; +MODULE_DEVICE_TABLE(i2c, max14656_id); + +static const struct of_device_id max14656_match_table[] = { + { .compatible = "maxim,max14656", }, + {} +}; +MODULE_DEVICE_TABLE(of, max14656_match_table); + +static struct i2c_driver max14656_i2c_driver = { + .driver = { + .name = "max14656", + .of_match_table = max14656_match_table, + }, + .probe = max14656_probe, + .id_table = max14656_id, +}; +module_i2c_driver(max14656_i2c_driver); + +MODULE_DESCRIPTION("MAX14656 USB charger detector"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/power/supply/max8997_charger.c b/drivers/power/supply/max8997_charger.c index 290ddc12b040..fa861003fece 100644 --- a/drivers/power/supply/max8997_charger.c +++ b/drivers/power/supply/max8997_charger.c @@ -148,10 +148,8 @@ static int max8997_battery_probe(struct platform_device *pdev) charger = devm_kzalloc(&pdev->dev, sizeof(struct charger_data), GFP_KERNEL); - if (charger == NULL) { - dev_err(&pdev->dev, "Cannot allocate memory.\n"); + if (!charger) return -ENOMEM; - } platform_set_drvdata(pdev, charger); @@ -161,7 +159,7 @@ static int max8997_battery_probe(struct platform_device *pdev) psy_cfg.drv_data = charger; - charger->battery = power_supply_register(&pdev->dev, + charger->battery = devm_power_supply_register(&pdev->dev, &max8997_battery_desc, &psy_cfg); if (IS_ERR(charger->battery)) { @@ -172,14 +170,6 @@ static int max8997_battery_probe(struct platform_device *pdev) return 0; } -static int max8997_battery_remove(struct platform_device *pdev) -{ - struct charger_data *charger = platform_get_drvdata(pdev); - - power_supply_unregister(charger->battery); - return 0; -} - static const struct platform_device_id max8997_battery_id[] = { { "max8997-battery", 0 }, { } @@ -191,7 +181,6 @@ static struct platform_driver max8997_battery_driver = { .name = "max8997-battery", }, .probe = max8997_battery_probe, - .remove = max8997_battery_remove, .id_table = max8997_battery_id, }; diff --git a/drivers/power/supply/pcf50633-charger.c b/drivers/power/supply/pcf50633-charger.c index d05597b4e40f..b3c1873ad84d 100644 --- a/drivers/power/supply/pcf50633-charger.c +++ b/drivers/power/supply/pcf50633-charger.c @@ -393,7 +393,6 @@ static int pcf50633_mbc_probe(struct platform_device *pdev) { struct power_supply_config psy_cfg = {}; struct pcf50633_mbc *mbc; - int ret; int i; u8 mbcs1; @@ -419,8 +418,7 @@ static int pcf50633_mbc_probe(struct platform_device *pdev) &psy_cfg); if (IS_ERR(mbc->adapter)) { dev_err(mbc->pcf->dev, "failed to register adapter\n"); - ret = PTR_ERR(mbc->adapter); - return ret; + return PTR_ERR(mbc->adapter); } mbc->usb = power_supply_register(&pdev->dev, &pcf50633_mbc_usb_desc, @@ -428,8 +426,7 @@ static int pcf50633_mbc_probe(struct platform_device *pdev) if (IS_ERR(mbc->usb)) { dev_err(mbc->pcf->dev, "failed to register usb\n"); power_supply_unregister(mbc->adapter); - ret = PTR_ERR(mbc->usb); - return ret; + return PTR_ERR(mbc->usb); } mbc->ac = power_supply_register(&pdev->dev, &pcf50633_mbc_ac_desc, @@ -438,12 +435,10 @@ static int pcf50633_mbc_probe(struct platform_device *pdev) dev_err(mbc->pcf->dev, "failed to register ac\n"); power_supply_unregister(mbc->adapter); power_supply_unregister(mbc->usb); - ret = PTR_ERR(mbc->ac); - return ret; + return PTR_ERR(mbc->ac); } - ret = sysfs_create_group(&pdev->dev.kobj, &mbc_attr_group); - if (ret) + if (sysfs_create_group(&pdev->dev.kobj, &mbc_attr_group)) dev_err(mbc->pcf->dev, "failed to create sysfs entries\n"); mbcs1 = pcf50633_reg_read(mbc->pcf, PCF50633_REG_MBCS1); diff --git a/drivers/power/supply/qcom_smbb.c b/drivers/power/supply/qcom_smbb.c index b5896ba2a602..f6a0d245731d 100644 --- a/drivers/power/supply/qcom_smbb.c +++ b/drivers/power/supply/qcom_smbb.c @@ -35,6 +35,7 @@ #include <linux/regmap.h> #include <linux/slab.h> #include <linux/extcon.h> +#include <linux/regulator/driver.h> #define SMBB_CHG_VMAX 0x040 #define SMBB_CHG_VSAFE 0x041 @@ -72,6 +73,8 @@ #define BTC_CTRL_HOT_EXT_N BIT(0) #define SMBB_USB_IMAX 0x344 +#define SMBB_USB_OTG_CTL 0x348 +#define OTG_CTL_EN BIT(0) #define SMBB_USB_ENUM_TIMER_STOP 0x34e #define ENUM_TIMER_STOP BIT(0) #define SMBB_USB_SEC_ACCESS 0x3d0 @@ -125,6 +128,9 @@ struct smbb_charger { struct power_supply *dc_psy; struct power_supply *bat_psy; struct regmap *regmap; + + struct regulator_desc otg_rdesc; + struct regulator_dev *otg_reg; }; static const unsigned int smbb_usb_extcon_cable[] = { @@ -378,7 +384,7 @@ static irqreturn_t smbb_usb_valid_handler(int irq, void *_data) struct smbb_charger *chg = _data; smbb_set_line_flag(chg, irq, STATUS_USBIN_VALID); - extcon_set_cable_state_(chg->edev, EXTCON_USB, + extcon_set_state_sync(chg->edev, EXTCON_USB, chg->status & STATUS_USBIN_VALID); power_supply_changed(chg->usb_psy); @@ -787,12 +793,56 @@ static const struct power_supply_desc dc_psy_desc = { .property_is_writeable = smbb_charger_writable_property, }; +static int smbb_chg_otg_enable(struct regulator_dev *rdev) +{ + struct smbb_charger *chg = rdev_get_drvdata(rdev); + int rc; + + rc = regmap_update_bits(chg->regmap, chg->addr + SMBB_USB_OTG_CTL, + OTG_CTL_EN, OTG_CTL_EN); + if (rc) + dev_err(chg->dev, "failed to update OTG_CTL\n"); + return rc; +} + +static int smbb_chg_otg_disable(struct regulator_dev *rdev) +{ + struct smbb_charger *chg = rdev_get_drvdata(rdev); + int rc; + + rc = regmap_update_bits(chg->regmap, chg->addr + SMBB_USB_OTG_CTL, + OTG_CTL_EN, 0); + if (rc) + dev_err(chg->dev, "failed to update OTG_CTL\n"); + return rc; +} + +static int smbb_chg_otg_is_enabled(struct regulator_dev *rdev) +{ + struct smbb_charger *chg = rdev_get_drvdata(rdev); + unsigned int value = 0; + int rc; + + rc = regmap_read(chg->regmap, chg->addr + SMBB_USB_OTG_CTL, &value); + if (rc) + dev_err(chg->dev, "failed to read OTG_CTL\n"); + + return !!(value & OTG_CTL_EN); +} + +static const struct regulator_ops smbb_chg_otg_ops = { + .enable = smbb_chg_otg_enable, + .disable = smbb_chg_otg_disable, + .is_enabled = smbb_chg_otg_is_enabled, +}; + static int smbb_charger_probe(struct platform_device *pdev) { struct power_supply_config bat_cfg = {}; struct power_supply_config usb_cfg = {}; struct power_supply_config dc_cfg = {}; struct smbb_charger *chg; + struct regulator_config config = { }; int rc, i; chg = devm_kzalloc(&pdev->dev, sizeof(*chg), GFP_KERNEL); @@ -905,6 +955,26 @@ static int smbb_charger_probe(struct platform_device *pdev) } } + /* + * otg regulator is used to control VBUS voltage direction + * when USB switches between host and gadget mode + */ + chg->otg_rdesc.id = -1; + chg->otg_rdesc.name = "otg-vbus"; + chg->otg_rdesc.ops = &smbb_chg_otg_ops; + chg->otg_rdesc.owner = THIS_MODULE; + chg->otg_rdesc.type = REGULATOR_VOLTAGE; + chg->otg_rdesc.supply_name = "usb-otg-in"; + chg->otg_rdesc.of_match = "otg-vbus"; + + config.dev = &pdev->dev; + config.driver_data = chg; + + chg->otg_reg = devm_regulator_register(&pdev->dev, &chg->otg_rdesc, + &config); + if (IS_ERR(chg->otg_reg)) + return PTR_ERR(chg->otg_reg); + chg->jeita_ext_temp = of_property_read_bool(pdev->dev.of_node, "qcom,jeita-extended-temp-range"); diff --git a/drivers/power/supply/sbs-charger.c b/drivers/power/supply/sbs-charger.c new file mode 100644 index 000000000000..353765a5f44c --- /dev/null +++ b/drivers/power/supply/sbs-charger.c @@ -0,0 +1,274 @@ +/* + * Copyright (c) 2016, Prodys S.L. + * + * 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 adds support for sbs-charger compilant chips as defined here: + * http://sbs-forum.org/specs/sbc110.pdf + * + * Implemetation based on sbs-battery.c + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/err.h> +#include <linux/power_supply.h> +#include <linux/i2c.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <linux/gpio.h> +#include <linux/regmap.h> +#include <linux/of_gpio.h> +#include <linux/bitops.h> + +#define SBS_CHARGER_REG_SPEC_INFO 0x11 +#define SBS_CHARGER_REG_STATUS 0x13 +#define SBS_CHARGER_REG_ALARM_WARNING 0x16 + +#define SBS_CHARGER_STATUS_CHARGE_INHIBITED BIT(1) +#define SBS_CHARGER_STATUS_RES_COLD BIT(9) +#define SBS_CHARGER_STATUS_RES_HOT BIT(10) +#define SBS_CHARGER_STATUS_BATTERY_PRESENT BIT(14) +#define SBS_CHARGER_STATUS_AC_PRESENT BIT(15) + +#define SBS_CHARGER_POLL_TIME 500 + +struct sbs_info { + struct i2c_client *client; + struct power_supply *power_supply; + struct regmap *regmap; + struct delayed_work work; + unsigned int last_state; +}; + +static int sbs_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct sbs_info *chip = power_supply_get_drvdata(psy); + unsigned int reg; + + reg = chip->last_state; + + switch (psp) { + case POWER_SUPPLY_PROP_PRESENT: + val->intval = !!(reg & SBS_CHARGER_STATUS_BATTERY_PRESENT); + break; + + case POWER_SUPPLY_PROP_ONLINE: + val->intval = !!(reg & SBS_CHARGER_STATUS_AC_PRESENT); + break; + + case POWER_SUPPLY_PROP_STATUS: + val->intval = POWER_SUPPLY_STATUS_UNKNOWN; + + if (!(reg & SBS_CHARGER_STATUS_BATTERY_PRESENT)) + val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING; + else if (reg & SBS_CHARGER_STATUS_AC_PRESENT && + !(reg & SBS_CHARGER_STATUS_CHARGE_INHIBITED)) + val->intval = POWER_SUPPLY_STATUS_CHARGING; + else + val->intval = POWER_SUPPLY_STATUS_DISCHARGING; + + break; + + case POWER_SUPPLY_PROP_HEALTH: + if (reg & SBS_CHARGER_STATUS_RES_COLD) + val->intval = POWER_SUPPLY_HEALTH_COLD; + if (reg & SBS_CHARGER_STATUS_RES_HOT) + val->intval = POWER_SUPPLY_HEALTH_OVERHEAT; + else + val->intval = POWER_SUPPLY_HEALTH_GOOD; + + break; + + default: + return -EINVAL; + } + + return 0; +} + +static int sbs_check_state(struct sbs_info *chip) +{ + unsigned int reg; + int ret; + + ret = regmap_read(chip->regmap, SBS_CHARGER_REG_STATUS, ®); + if (!ret && reg != chip->last_state) { + chip->last_state = reg; + power_supply_changed(chip->power_supply); + return 1; + } + + return 0; +} + +static void sbs_delayed_work(struct work_struct *work) +{ + struct sbs_info *chip = container_of(work, struct sbs_info, work.work); + + sbs_check_state(chip); + + schedule_delayed_work(&chip->work, + msecs_to_jiffies(SBS_CHARGER_POLL_TIME)); +} + +static irqreturn_t sbs_irq_thread(int irq, void *data) +{ + struct sbs_info *chip = data; + int ret; + + ret = sbs_check_state(chip); + + return ret ? IRQ_HANDLED : IRQ_NONE; +} + +static enum power_supply_property sbs_properties[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_ONLINE, + POWER_SUPPLY_PROP_HEALTH, +}; + +static bool sbs_readable_reg(struct device *dev, unsigned int reg) +{ + if (reg < SBS_CHARGER_REG_SPEC_INFO) + return false; + else + return true; +} + +static bool sbs_volatile_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case SBS_CHARGER_REG_STATUS: + return true; + } + + return false; +} + +static const struct regmap_config sbs_regmap = { + .reg_bits = 8, + .val_bits = 16, + .max_register = SBS_CHARGER_REG_ALARM_WARNING, + .readable_reg = sbs_readable_reg, + .volatile_reg = sbs_volatile_reg, + .val_format_endian = REGMAP_ENDIAN_LITTLE, /* since based on SMBus */ +}; + +static const struct power_supply_desc sbs_desc = { + .name = "sbs-charger", + .type = POWER_SUPPLY_TYPE_MAINS, + .properties = sbs_properties, + .num_properties = ARRAY_SIZE(sbs_properties), + .get_property = sbs_get_property, +}; + +static int sbs_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct power_supply_config psy_cfg = {}; + struct sbs_info *chip; + int ret, val; + + chip = devm_kzalloc(&client->dev, sizeof(struct sbs_info), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + chip->client = client; + psy_cfg.of_node = client->dev.of_node; + psy_cfg.drv_data = chip; + + i2c_set_clientdata(client, chip); + + chip->regmap = devm_regmap_init_i2c(client, &sbs_regmap); + if (IS_ERR(chip->regmap)) + return PTR_ERR(chip->regmap); + + /* + * Before we register, we need to make sure we can actually talk + * to the battery. + */ + ret = regmap_read(chip->regmap, SBS_CHARGER_REG_STATUS, &val); + if (ret) { + dev_err(&client->dev, "Failed to get device status\n"); + return ret; + } + chip->last_state = val; + + chip->power_supply = devm_power_supply_register(&client->dev, &sbs_desc, + &psy_cfg); + if (IS_ERR(chip->power_supply)) { + dev_err(&client->dev, "Failed to register power supply\n"); + return PTR_ERR(chip->power_supply); + } + + /* + * The sbs-charger spec doesn't impose the use of an interrupt. So in + * the case it wasn't provided we use polling in order get the charger's + * status. + */ + if (client->irq) { + ret = devm_request_threaded_irq(&client->dev, client->irq, + NULL, sbs_irq_thread, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + dev_name(&client->dev), chip); + if (ret) { + dev_err(&client->dev, "Failed to request irq, %d\n", ret); + return ret; + } + } else { + INIT_DELAYED_WORK(&chip->work, sbs_delayed_work); + schedule_delayed_work(&chip->work, + msecs_to_jiffies(SBS_CHARGER_POLL_TIME)); + } + + dev_info(&client->dev, + "%s: smart charger device registered\n", client->name); + + return 0; +} + +static int sbs_remove(struct i2c_client *client) +{ + struct sbs_info *chip = i2c_get_clientdata(client); + + cancel_delayed_work_sync(&chip->work); + + return 0; +} + +#ifdef CONFIG_OF +static const struct of_device_id sbs_dt_ids[] = { + { .compatible = "sbs,sbs-charger" }, + { }, +}; +MODULE_DEVICE_TABLE(of, sbs_dt_ids); +#endif + +static const struct i2c_device_id sbs_id[] = { + { "sbs-charger", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, sbs_id); + +static struct i2c_driver sbs_driver = { + .probe = sbs_probe, + .remove = sbs_remove, + .id_table = sbs_id, + .driver = { + .name = "sbs-charger", + .of_match_table = of_match_ptr(sbs_dt_ids), + }, +}; +module_i2c_driver(sbs_driver); + +MODULE_AUTHOR("Nicolas Saenz Julienne <nicolassaenzj@gmail.com>"); +MODULE_DESCRIPTION("SBS smart charger driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/power/supply/tps65217_charger.c b/drivers/power/supply/tps65217_charger.c index 9fd019f9b88c..29b61e81b385 100644 --- a/drivers/power/supply/tps65217_charger.c +++ b/drivers/power/supply/tps65217_charger.c @@ -35,22 +35,22 @@ #include <linux/mfd/core.h> #include <linux/mfd/tps65217.h> +#define CHARGER_STATUS_PRESENT (TPS65217_STATUS_ACPWR | TPS65217_STATUS_USBPWR) +#define NUM_CHARGER_IRQS 2 #define POLL_INTERVAL (HZ * 2) struct tps65217_charger { struct tps65217 *tps; struct device *dev; - struct power_supply *ac; + struct power_supply *psy; - int ac_online; - int prev_ac_online; + int online; + int prev_online; struct task_struct *poll_task; - - int irq; }; -static enum power_supply_property tps65217_ac_props[] = { +static enum power_supply_property tps65217_charger_props[] = { POWER_SUPPLY_PROP_ONLINE, }; @@ -95,7 +95,7 @@ static int tps65217_enable_charging(struct tps65217_charger *charger) int ret; /* charger already enabled */ - if (charger->ac_online) + if (charger->online) return 0; dev_dbg(charger->dev, "%s: enable charging\n", __func__); @@ -110,19 +110,19 @@ static int tps65217_enable_charging(struct tps65217_charger *charger) return ret; } - charger->ac_online = 1; + charger->online = 1; return 0; } -static int tps65217_ac_get_property(struct power_supply *psy, - enum power_supply_property psp, - union power_supply_propval *val) +static int tps65217_charger_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) { struct tps65217_charger *charger = power_supply_get_drvdata(psy); if (psp == POWER_SUPPLY_PROP_ONLINE) { - val->intval = charger->ac_online; + val->intval = charger->online; return 0; } return -EINVAL; @@ -133,7 +133,7 @@ static irqreturn_t tps65217_charger_irq(int irq, void *dev) int ret, val; struct tps65217_charger *charger = dev; - charger->prev_ac_online = charger->ac_online; + charger->prev_online = charger->online; ret = tps65217_reg_read(charger->tps, TPS65217_REG_STATUS, &val); if (ret < 0) { @@ -144,8 +144,8 @@ static irqreturn_t tps65217_charger_irq(int irq, void *dev) dev_dbg(charger->dev, "%s: 0x%x\n", __func__, val); - /* check for AC status bit */ - if (val & TPS65217_STATUS_ACPWR) { + /* check for charger status bit */ + if (val & CHARGER_STATUS_PRESENT) { ret = tps65217_enable_charging(charger); if (ret) { dev_err(charger->dev, @@ -153,11 +153,11 @@ static irqreturn_t tps65217_charger_irq(int irq, void *dev) return IRQ_HANDLED; } } else { - charger->ac_online = 0; + charger->online = 0; } - if (charger->prev_ac_online != charger->ac_online) - power_supply_changed(charger->ac); + if (charger->prev_online != charger->online) + power_supply_changed(charger->psy); ret = tps65217_reg_read(charger->tps, TPS65217_REG_CHGCONFIG0, &val); if (ret < 0) { @@ -188,11 +188,11 @@ static int tps65217_charger_poll_task(void *data) } static const struct power_supply_desc tps65217_charger_desc = { - .name = "tps65217-ac", + .name = "tps65217-charger", .type = POWER_SUPPLY_TYPE_MAINS, - .get_property = tps65217_ac_get_property, - .properties = tps65217_ac_props, - .num_properties = ARRAY_SIZE(tps65217_ac_props), + .get_property = tps65217_charger_get_property, + .properties = tps65217_charger_props, + .num_properties = ARRAY_SIZE(tps65217_charger_props), }; static int tps65217_charger_probe(struct platform_device *pdev) @@ -200,8 +200,10 @@ static int tps65217_charger_probe(struct platform_device *pdev) struct tps65217 *tps = dev_get_drvdata(pdev->dev.parent); struct tps65217_charger *charger; struct power_supply_config cfg = {}; - int irq; + struct task_struct *poll_task; + int irq[NUM_CHARGER_IRQS]; int ret; + int i; dev_dbg(&pdev->dev, "%s\n", __func__); @@ -216,18 +218,16 @@ static int tps65217_charger_probe(struct platform_device *pdev) cfg.of_node = pdev->dev.of_node; cfg.drv_data = charger; - charger->ac = devm_power_supply_register(&pdev->dev, - &tps65217_charger_desc, - &cfg); - if (IS_ERR(charger->ac)) { + charger->psy = devm_power_supply_register(&pdev->dev, + &tps65217_charger_desc, + &cfg); + if (IS_ERR(charger->psy)) { dev_err(&pdev->dev, "failed: power supply register\n"); - return PTR_ERR(charger->ac); + return PTR_ERR(charger->psy); } - irq = platform_get_irq_byname(pdev, "AC"); - if (irq < 0) - irq = -ENXIO; - charger->irq = irq; + irq[0] = platform_get_irq_byname(pdev, "USB"); + irq[1] = platform_get_irq_byname(pdev, "AC"); ret = tps65217_config_charger(charger); if (ret < 0) { @@ -235,29 +235,36 @@ static int tps65217_charger_probe(struct platform_device *pdev) return ret; } - if (irq != -ENXIO) { - ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, + /* Create a polling thread if an interrupt is invalid */ + if (irq[0] < 0 || irq[1] < 0) { + poll_task = kthread_run(tps65217_charger_poll_task, + charger, "ktps65217charger"); + if (IS_ERR(poll_task)) { + ret = PTR_ERR(poll_task); + dev_err(charger->dev, + "Unable to run kthread err %d\n", ret); + return ret; + } + + charger->poll_task = poll_task; + return 0; + } + + /* Create IRQ threads for charger interrupts */ + for (i = 0; i < NUM_CHARGER_IRQS; i++) { + ret = devm_request_threaded_irq(&pdev->dev, irq[i], NULL, tps65217_charger_irq, 0, "tps65217-charger", charger); if (ret) { dev_err(charger->dev, - "Unable to register irq %d err %d\n", irq, + "Unable to register irq %d err %d\n", irq[i], ret); return ret; } /* Check current state */ - tps65217_charger_irq(irq, charger); - } else { - charger->poll_task = kthread_run(tps65217_charger_poll_task, - charger, "ktps65217charger"); - if (IS_ERR(charger->poll_task)) { - ret = PTR_ERR(charger->poll_task); - dev_err(charger->dev, - "Unable to run kthread err %d\n", ret); - return ret; - } + tps65217_charger_irq(-1, charger); } return 0; @@ -267,7 +274,7 @@ static int tps65217_charger_remove(struct platform_device *pdev) { struct tps65217_charger *charger = platform_get_drvdata(pdev); - if (charger->irq == -ENXIO) + if (charger->poll_task) kthread_stop(charger->poll_task); return 0; diff --git a/drivers/power/supply/wm97xx_battery.c b/drivers/power/supply/wm97xx_battery.c index e3edb31ac880..bd4f66651513 100644 --- a/drivers/power/supply/wm97xx_battery.c +++ b/drivers/power/supply/wm97xx_battery.c @@ -175,11 +175,6 @@ static int wm97xx_bat_probe(struct platform_device *dev) if (dev->id != -1) return -EINVAL; - if (!pdata) { - dev_err(&dev->dev, "No platform_data supplied\n"); - return -EINVAL; - } - if (gpio_is_valid(pdata->charge_gpio)) { ret = gpio_request(pdata->charge_gpio, "BATT CHRG"); if (ret) diff --git a/drivers/reset/core.c b/drivers/reset/core.c index 10368ed8fd13..b6f5f1e1826c 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -163,7 +163,7 @@ int reset_control_reset(struct reset_control *rstc) } ret = rstc->rcdev->ops->reset(rstc->rcdev, rstc->id); - if (rstc->shared && !ret) + if (rstc->shared && ret) atomic_dec(&rstc->triggered_count); return ret; diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index f501095f91ac..898461b146cc 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -74,7 +74,7 @@ static void bnx2fc_cmd_timeout(struct work_struct *work) &io_req->req_flags)) { /* Handle internally generated ABTS timeout */ BNX2FC_IO_DBG(io_req, "ABTS timed out refcnt = %d\n", - io_req->refcount.refcount.counter); + kref_read(&io_req->refcount)); if (!(test_and_set_bit(BNX2FC_FLAG_ABTS_DONE, &io_req->req_flags))) { /* @@ -1141,7 +1141,7 @@ int bnx2fc_eh_abort(struct scsi_cmnd *sc_cmd) return SUCCESS; } BNX2FC_IO_DBG(io_req, "eh_abort - refcnt = %d\n", - io_req->refcount.refcount.counter); + kref_read(&io_req->refcount)); /* Hold IO request across abort processing */ kref_get(&io_req->refcount); @@ -1299,7 +1299,7 @@ void bnx2fc_process_cleanup_compl(struct bnx2fc_cmd *io_req, { BNX2FC_IO_DBG(io_req, "Entered process_cleanup_compl " "refcnt = %d, cmd_type = %d\n", - io_req->refcount.refcount.counter, io_req->cmd_type); + kref_read(&io_req->refcount), io_req->cmd_type); bnx2fc_scsi_done(io_req, DID_ERROR); kref_put(&io_req->refcount, bnx2fc_cmd_release); if (io_req->wait_for_comp) @@ -1318,7 +1318,7 @@ void bnx2fc_process_abts_compl(struct bnx2fc_cmd *io_req, BNX2FC_IO_DBG(io_req, "Entered process_abts_compl xid = 0x%x" "refcnt = %d, cmd_type = %d\n", io_req->xid, - io_req->refcount.refcount.counter, io_req->cmd_type); + kref_read(&io_req->refcount), io_req->cmd_type); if (test_and_set_bit(BNX2FC_FLAG_ABTS_DONE, &io_req->req_flags)) { diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h index 95ba99044c3e..18e0ea83d361 100644 --- a/drivers/scsi/cxgbi/libcxgbi.h +++ b/drivers/scsi/cxgbi/libcxgbi.h @@ -301,7 +301,7 @@ static inline void __cxgbi_sock_put(const char *fn, struct cxgbi_sock *csk) { log_debug(1 << CXGBI_DBG_SOCK, "%s, put csk 0x%p, ref %u-1.\n", - fn, csk, atomic_read(&csk->refcnt.refcount)); + fn, csk, kref_read(&csk->refcnt)); kref_put(&csk->refcnt, cxgbi_sock_free); } #define cxgbi_sock_put(csk) __cxgbi_sock_put(__func__, csk) @@ -310,7 +310,7 @@ static inline void __cxgbi_sock_get(const char *fn, struct cxgbi_sock *csk) { log_debug(1 << CXGBI_DBG_SOCK, "%s, get csk 0x%p, ref %u+1.\n", - fn, csk, atomic_read(&csk->refcnt.refcount)); + fn, csk, kref_read(&csk->refcnt)); kref_get(&csk->refcnt); } #define cxgbi_sock_get(csk) __cxgbi_sock_get(__func__, csk) diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index a63542bac153..caa7a7b0ec53 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -607,7 +607,7 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size) len += snprintf(buf+len, size-len, "usgmap:%x ", ndlp->nlp_usg_map); len += snprintf(buf+len, size-len, "refcnt:%x", - atomic_read(&ndlp->kref.refcount)); + kref_read(&ndlp->kref)); len += snprintf(buf+len, size-len, "\n"); } spin_unlock_irq(shost->host_lock); diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 7b6bd8ed0d0b..63bef4566548 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -3690,7 +3690,7 @@ lpfc_mbx_cmpl_dflt_rpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, "0006 rpi%x DID:%x flg:%x %d map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, - atomic_read(&ndlp->kref.refcount), + kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); if (NLP_CHK_NODE_ACT(ndlp)) { lpfc_nlp_put(ndlp); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index ed223937798a..82047070cdc9 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -3440,7 +3440,7 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, "0002 rpi:%x DID:%x flg:%x %d map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, - atomic_read(&ndlp->kref.refcount), + kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND) ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND; @@ -3861,7 +3861,7 @@ out: lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, "0003 rpi:%x DID:%x flg:%x %d map%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, - atomic_read(&ndlp->kref.refcount), + kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); if (vport->port_state < LPFC_VPORT_READY) { @@ -4238,7 +4238,7 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, "0277 lpfc_enable_node: ndlp:x%p " "usgmap:x%x refcnt:%d\n", (void *)ndlp, ndlp->nlp_usg_map, - atomic_read(&ndlp->kref.refcount)); + kref_read(&ndlp->kref)); return NULL; } /* The ndlp should not already be in active mode */ @@ -4248,7 +4248,7 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, "0278 lpfc_enable_node: ndlp:x%p " "usgmap:x%x refcnt:%d\n", (void *)ndlp, ndlp->nlp_usg_map, - atomic_read(&ndlp->kref.refcount)); + kref_read(&ndlp->kref)); return NULL; } @@ -4272,7 +4272,7 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, "0008 rpi:%x DID:%x flg:%x refcnt:%d " "map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, - atomic_read(&ndlp->kref.refcount), + kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); } @@ -4546,7 +4546,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) == LPFC_SLI_INTF_IF_TYPE_2) && - (atomic_read(&ndlp->kref.refcount) > 0)) { + (kref_read(&ndlp->kref) > 0)) { mbox->context1 = lpfc_nlp_get(ndlp); mbox->mbox_cmpl = lpfc_sli4_unreg_rpi_cmpl_clr; @@ -4695,14 +4695,14 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) "0280 lpfc_cleanup_node: ndlp:x%p " "usgmap:x%x refcnt:%d\n", (void *)ndlp, ndlp->nlp_usg_map, - atomic_read(&ndlp->kref.refcount)); + kref_read(&ndlp->kref)); lpfc_dequeue_node(vport, ndlp); } else { lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE, "0281 lpfc_cleanup_node: ndlp:x%p " "usgmap:x%x refcnt:%d\n", (void *)ndlp, ndlp->nlp_usg_map, - atomic_read(&ndlp->kref.refcount)); + kref_read(&ndlp->kref)); lpfc_disable_node(vport, ndlp); } @@ -4791,7 +4791,7 @@ lpfc_nlp_remove(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, "0005 rpi:%x DID:%x flg:%x %d map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, - atomic_read(&ndlp->kref.refcount), + kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); if ((mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL)) != NULL) { @@ -5557,7 +5557,7 @@ lpfc_mbx_cmpl_fdmi_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, "0004 rpi:%x DID:%x flg:%x %d map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, - atomic_read(&ndlp->kref.refcount), + kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); /* * Start issuing Fabric-Device Management Interface (FDMI) command to @@ -5728,7 +5728,7 @@ lpfc_nlp_init(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, "0007 rpi:%x DID:%x flg:%x refcnt:%d " "map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag, - atomic_read(&ndlp->kref.refcount), + kref_read(&ndlp->kref), ndlp->nlp_usg_map, ndlp); ndlp->active_rrqs_xri_bitmap = @@ -5767,7 +5767,7 @@ lpfc_nlp_release(struct kref *kref) "0279 lpfc_nlp_release: ndlp:x%p did %x " "usgmap:x%x refcnt:%d rpi:%x\n", (void *)ndlp, ndlp->nlp_DID, ndlp->nlp_usg_map, - atomic_read(&ndlp->kref.refcount), ndlp->nlp_rpi); + kref_read(&ndlp->kref), ndlp->nlp_rpi); /* remove ndlp from action. */ lpfc_nlp_remove(ndlp->vport, ndlp); @@ -5804,7 +5804,7 @@ lpfc_nlp_get(struct lpfc_nodelist *ndlp) lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE, "node get: did:x%x flg:x%x refcnt:x%x", ndlp->nlp_DID, ndlp->nlp_flag, - atomic_read(&ndlp->kref.refcount)); + kref_read(&ndlp->kref)); /* The check of ndlp usage to prevent incrementing the * ndlp reference count that is in the process of being * released. @@ -5817,7 +5817,7 @@ lpfc_nlp_get(struct lpfc_nodelist *ndlp) "0276 lpfc_nlp_get: ndlp:x%p " "usgmap:x%x refcnt:%d\n", (void *)ndlp, ndlp->nlp_usg_map, - atomic_read(&ndlp->kref.refcount)); + kref_read(&ndlp->kref)); return NULL; } else kref_get(&ndlp->kref); @@ -5844,7 +5844,7 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp) lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE, "node put: did:x%x flg:x%x refcnt:x%x", ndlp->nlp_DID, ndlp->nlp_flag, - atomic_read(&ndlp->kref.refcount)); + kref_read(&ndlp->kref)); phba = ndlp->phba; spin_lock_irqsave(&phba->ndlp_lock, flags); /* Check the ndlp memory free acknowledge flag to avoid the @@ -5857,7 +5857,7 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp) "0274 lpfc_nlp_put: ndlp:x%p " "usgmap:x%x refcnt:%d\n", (void *)ndlp, ndlp->nlp_usg_map, - atomic_read(&ndlp->kref.refcount)); + kref_read(&ndlp->kref)); return 1; } /* Check the ndlp inactivate log flag to avoid the possible @@ -5870,7 +5870,7 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp) "0275 lpfc_nlp_put: ndlp:x%p " "usgmap:x%x refcnt:%d\n", (void *)ndlp, ndlp->nlp_usg_map, - atomic_read(&ndlp->kref.refcount)); + kref_read(&ndlp->kref)); return 1; } /* For last put, mark the ndlp usage flags to make sure no @@ -5878,7 +5878,7 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp) * in between the process when the final kref_put has been * invoked on this ndlp. */ - if (atomic_read(&ndlp->kref.refcount) == 1) { + if (kref_read(&ndlp->kref) == 1) { /* Indicate ndlp is put to inactive state. */ NLP_SET_IACT_REQ(ndlp); /* Acknowledge ndlp memory free has been seen. */ @@ -5906,8 +5906,8 @@ lpfc_nlp_not_used(struct lpfc_nodelist *ndlp) lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE, "node not used: did:x%x flg:x%x refcnt:x%x", ndlp->nlp_DID, ndlp->nlp_flag, - atomic_read(&ndlp->kref.refcount)); - if (atomic_read(&ndlp->kref.refcount) == 1) + kref_read(&ndlp->kref)); + if (kref_read(&ndlp->kref) == 1) if (lpfc_nlp_put(ndlp)) return 1; return 0; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 4776fd85514f..64717c171b15 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -2660,8 +2660,7 @@ lpfc_cleanup(struct lpfc_vport *vport) "usgmap:x%x refcnt:%d\n", ndlp->nlp_DID, (void *)ndlp, ndlp->nlp_usg_map, - atomic_read( - &ndlp->kref.refcount)); + kref_read(&ndlp->kref)); } break; } diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index d925910be761..3084983c1287 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -371,7 +371,7 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd) */ pr_debug("write_pending aborted cmd[%p] refcount %d " "transport_state %x, t_state %x, se_cmd_flags %x\n", - cmd,cmd->se_cmd.cmd_kref.refcount.counter, + cmd, kref_read(&cmd->se_cmd.cmd_kref), cmd->se_cmd.transport_state, cmd->se_cmd.t_state, cmd->se_cmd.se_cmd_flags); @@ -584,7 +584,7 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) */ pr_debug("queue_data_in aborted cmd[%p] refcount %d " "transport_state %x, t_state %x, se_cmd_flags %x\n", - cmd,cmd->se_cmd.cmd_kref.refcount.counter, + cmd, kref_read(&cmd->se_cmd.cmd_kref), cmd->se_cmd.transport_state, cmd->se_cmd.t_state, cmd->se_cmd.se_cmd_flags); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index e9e1e141af9c..78db07fd8055 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1040,7 +1040,8 @@ int scsi_init_io(struct scsi_cmnd *cmd) bool is_mq = (rq->mq_ctx != NULL); int error; - BUG_ON(!blk_rq_nr_phys_segments(rq)); + if (WARN_ON_ONCE(!blk_rq_nr_phys_segments(rq))) + return -EINVAL; error = scsi_init_sgtable(rq, &cmd->sdb); if (error) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index dbe5b4b95df0..121de0aaa6ad 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1753,6 +1753,10 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) return res; iov_iter_truncate(&i, hp->dxfer_len); + if (!iov_iter_count(&i)) { + kfree(iov); + return -EINVAL; + } res = blk_rq_map_user_iov(q, rq, md, &i, GFP_ATOMIC); kfree(iov); diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 14f9dea3173f..d7843fd8c610 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -371,7 +371,7 @@ static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi, int width, /* default mode, does not need flex_cmd */ flex_mode = 0; else - command = SPINOR_OP_READ4_FAST; + command = SPINOR_OP_READ_FAST_4B; break; case SPI_NBITS_DUAL: bpc = 0x00000001; @@ -384,7 +384,7 @@ static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi, int width, } else { command = SPINOR_OP_READ_1_1_2; if (spans_4byte) - command = SPINOR_OP_READ4_1_1_2; + command = SPINOR_OP_READ_1_1_2_4B; } break; case SPI_NBITS_QUAD: @@ -399,7 +399,7 @@ static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi, int width, } else { command = SPINOR_OP_READ_1_1_4; if (spans_4byte) - command = SPINOR_OP_READ4_1_1_4; + command = SPINOR_OP_READ_1_1_4_4B; } break; default: diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c index b653451843c8..937c2d5d7ec3 100644 --- a/drivers/staging/android/ion/ion.c +++ b/drivers/staging/android/ion/ion.c @@ -1300,7 +1300,7 @@ static int ion_debug_heap_show(struct seq_file *s, void *unused) seq_printf(s, "%16s %16u %16zu %d %d\n", buffer->task_comm, buffer->pid, buffer->size, buffer->kmap_cnt, - atomic_read(&buffer->ref.refcount)); + kref_read(&buffer->ref)); total_orphaned_size += buffer->size; } } diff --git a/drivers/staging/comedi/comedi_buf.c b/drivers/staging/comedi/comedi_buf.c index c7d7682b1412..1e1df89b5018 100644 --- a/drivers/staging/comedi/comedi_buf.c +++ b/drivers/staging/comedi/comedi_buf.c @@ -188,7 +188,7 @@ bool comedi_buf_is_mmapped(struct comedi_subdevice *s) { struct comedi_buf_map *bm = s->async->buf_map; - return bm && (atomic_read(&bm->refcount.refcount) > 1); + return bm && (kref_read(&bm->refcount) > 1); } int comedi_buf_alloc(struct comedi_device *dev, struct comedi_subdevice *s, diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c index 39a72e3f0c18..7035356e56b3 100644 --- a/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c @@ -107,7 +107,7 @@ void __noreturn lbug_with_loc(struct libcfs_debug_msg_data *msgdata) libcfs_debug_dumplog(); if (libcfs_panic_on_lbug) panic("LBUG"); - set_task_state(current, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); while (1) schedule(); } diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index d761025144f9..e18051185846 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -788,7 +788,7 @@ static struct t10_pr_registration *__core_scsi3_alloc_registration( * __core_scsi3_add_registration() */ dest_lun = rcu_dereference_check(deve_tmp->se_lun, - atomic_read(&deve_tmp->pr_kref.refcount) != 0); + kref_read(&deve_tmp->pr_kref) != 0); pr_reg_atp = __core_scsi3_do_alloc_registration(dev, nacl_tmp, dest_lun, deve_tmp, @@ -1463,7 +1463,7 @@ static int core_scsi3_lunacl_depend_item(struct se_dev_entry *se_deve) * For nacl->dynamic_node_acl=1 */ lun_acl = rcu_dereference_check(se_deve->se_lun_acl, - atomic_read(&se_deve->pr_kref.refcount) != 0); + kref_read(&se_deve->pr_kref) != 0); if (!lun_acl) return 0; @@ -1478,7 +1478,7 @@ static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve) * For nacl->dynamic_node_acl=1 */ lun_acl = rcu_dereference_check(se_deve->se_lun_acl, - atomic_read(&se_deve->pr_kref.refcount) != 0); + kref_read(&se_deve->pr_kref) != 0); if (!lun_acl) { kref_put(&se_deve->pr_kref, target_pr_kref_release); return; @@ -1759,7 +1759,7 @@ core_scsi3_decode_spec_i_port( * 2nd loop which will never fail. */ dest_lun = rcu_dereference_check(dest_se_deve->se_lun, - atomic_read(&dest_se_deve->pr_kref.refcount) != 0); + kref_read(&dest_se_deve->pr_kref) != 0); dest_pr_reg = __core_scsi3_alloc_registration(cmd->se_dev, dest_node_acl, dest_lun, dest_se_deve, @@ -3466,7 +3466,7 @@ after_iport_check: iport_ptr); if (!dest_pr_reg) { struct se_lun *dest_lun = rcu_dereference_check(dest_se_deve->se_lun, - atomic_read(&dest_se_deve->pr_kref.refcount) != 0); + kref_read(&dest_se_deve->pr_kref) != 0); spin_unlock(&dev->dev_reservation_lock); if (core_scsi3_alloc_registration(cmd->se_dev, dest_node_acl, diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c index fd5c3de79470..c91979c1463d 100644 --- a/drivers/target/tcm_fc/tfc_sess.c +++ b/drivers/target/tcm_fc/tfc_sess.c @@ -454,7 +454,7 @@ static void ft_sess_free(struct kref *kref) void ft_sess_put(struct ft_sess *sess) { - int sess_held = atomic_read(&sess->kref.refcount); + int sess_held = kref_read(&sess->kref); BUG_ON(!sess_held); kref_put(&sess->kref, ft_sess_free); diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c index 1bf8ed13f827..9229de43e19d 100644 --- a/drivers/tty/tty_ldsem.c +++ b/drivers/tty/tty_ldsem.c @@ -200,7 +200,6 @@ static struct ld_semaphore __sched * down_read_failed(struct ld_semaphore *sem, long count, long timeout) { struct ldsem_waiter waiter; - struct task_struct *tsk = current; long adjust = -LDSEM_ACTIVE_BIAS + LDSEM_WAIT_BIAS; /* set up my own style of waitqueue */ @@ -221,8 +220,8 @@ down_read_failed(struct ld_semaphore *sem, long count, long timeout) list_add_tail(&waiter.list, &sem->read_wait); sem->wait_readers++; - waiter.task = tsk; - get_task_struct(tsk); + waiter.task = current; + get_task_struct(current); /* if there are no active locks, wake the new lock owner(s) */ if ((count & LDSEM_ACTIVE_MASK) == 0) @@ -232,7 +231,7 @@ down_read_failed(struct ld_semaphore *sem, long count, long timeout) /* wait to be given the lock */ for (;;) { - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); if (!waiter.task) break; @@ -241,7 +240,7 @@ down_read_failed(struct ld_semaphore *sem, long count, long timeout) timeout = schedule_timeout(timeout); } - __set_task_state(tsk, TASK_RUNNING); + __set_current_state(TASK_RUNNING); if (!timeout) { /* lock timed out but check if this task was just @@ -268,7 +267,6 @@ static struct ld_semaphore __sched * down_write_failed(struct ld_semaphore *sem, long count, long timeout) { struct ldsem_waiter waiter; - struct task_struct *tsk = current; long adjust = -LDSEM_ACTIVE_BIAS; int locked = 0; @@ -289,16 +287,16 @@ down_write_failed(struct ld_semaphore *sem, long count, long timeout) list_add_tail(&waiter.list, &sem->write_wait); - waiter.task = tsk; + waiter.task = current; - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); for (;;) { if (!timeout) break; raw_spin_unlock_irq(&sem->wait_lock); timeout = schedule_timeout(timeout); raw_spin_lock_irq(&sem->wait_lock); - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); locked = writer_trylock(sem); if (locked) break; @@ -309,7 +307,7 @@ down_write_failed(struct ld_semaphore *sem, long count, long timeout) list_del(&waiter.list); raw_spin_unlock_irq(&sem->wait_lock); - __set_task_state(tsk, TASK_RUNNING); + __set_current_state(TASK_RUNNING); /* lock wait may have timed out */ if (!locked) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index fd80c1b9c823..e6a17455adac 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3698,7 +3698,7 @@ static void ffs_closed(struct ffs_data *ffs) goto done; if (opts->no_configfs || !opts->func_inst.group.cg_item.ci_parent - || !atomic_read(&opts->func_inst.group.cg_item.ci_kref.refcount)) + || !kref_read(&opts->func_inst.group.cg_item.ci_kref)) goto done; ci = opts->func_inst.group.cg_item.ci_parent->ci_parent; diff --git a/drivers/usb/mon/mon_main.c b/drivers/usb/mon/mon_main.c index 33ff49c4cea4..46847340b819 100644 --- a/drivers/usb/mon/mon_main.c +++ b/drivers/usb/mon/mon_main.c @@ -409,7 +409,7 @@ static void __exit mon_exit(void) printk(KERN_ERR TAG ": Outstanding opens (%d) on usb%d, leaking...\n", mbus->nreaders, mbus->u_bus->busnum); - atomic_set(&mbus->ref.refcount, 2); /* Force leak */ + kref_get(&mbus->ref); /* Force leak */ } mon_dissolve(mbus, mbus->u_bus); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 422370293cfd..e7bf01373bc4 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1428,17 +1428,18 @@ static void fill_prstatus(struct elf_prstatus *prstatus, * group-wide total, not its individual thread total. */ thread_group_cputime(p, &cputime); - cputime_to_timeval(cputime.utime, &prstatus->pr_utime); - cputime_to_timeval(cputime.stime, &prstatus->pr_stime); + prstatus->pr_utime = ns_to_timeval(cputime.utime); + prstatus->pr_stime = ns_to_timeval(cputime.stime); } else { - cputime_t utime, stime; + u64 utime, stime; task_cputime(p, &utime, &stime); - cputime_to_timeval(utime, &prstatus->pr_utime); - cputime_to_timeval(stime, &prstatus->pr_stime); + prstatus->pr_utime = ns_to_timeval(utime); + prstatus->pr_stime = ns_to_timeval(stime); } - cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime); - cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime); + + prstatus->pr_cutime = ns_to_timeval(p->signal->cutime); + prstatus->pr_cstime = ns_to_timeval(p->signal->cstime); } static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index d2e36f82c35d..ffca4bbc3d63 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1349,17 +1349,17 @@ static void fill_prstatus(struct elf_prstatus *prstatus, * group-wide total, not its individual thread total. */ thread_group_cputime(p, &cputime); - cputime_to_timeval(cputime.utime, &prstatus->pr_utime); - cputime_to_timeval(cputime.stime, &prstatus->pr_stime); + prstatus->pr_utime = ns_to_timeval(cputime.utime); + prstatus->pr_stime = ns_to_timeval(cputime.stime); } else { - cputime_t utime, stime; + u64 utime, stime; task_cputime(p, &utime, &stime); - cputime_to_timeval(utime, &prstatus->pr_utime); - cputime_to_timeval(stime, &prstatus->pr_stime); + prstatus->pr_utime = ns_to_timeval(utime); + prstatus->pr_stime = ns_to_timeval(stime); } - cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime); - cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime); + prstatus->pr_cutime = ns_to_timeval(p->signal->cutime); + prstatus->pr_cstime = ns_to_timeval(p->signal->cstime); prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap; prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap; diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index 4d24d17bcfc1..504b3c3539dc 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -51,22 +51,8 @@ #define elf_prstatus compat_elf_prstatus #define elf_prpsinfo compat_elf_prpsinfo -/* - * Compat version of cputime_to_compat_timeval, perhaps this - * should be an inline in <linux/compat.h>. - */ -static void cputime_to_compat_timeval(const cputime_t cputime, - struct compat_timeval *value) -{ - struct timeval tv; - cputime_to_timeval(cputime, &tv); - value->tv_sec = tv.tv_sec; - value->tv_usec = tv.tv_usec; -} - -#undef cputime_to_timeval -#define cputime_to_timeval cputime_to_compat_timeval - +#undef ns_to_timeval +#define ns_to_timeval ns_to_compat_timeval /* * To use this file, asm/elf.h must define compat_elf_check_arch. diff --git a/fs/exofs/sys.c b/fs/exofs/sys.c index 5e6a2c0a1f0b..1f7d5e46cdda 100644 --- a/fs/exofs/sys.c +++ b/fs/exofs/sys.c @@ -122,7 +122,7 @@ void exofs_sysfs_dbg_print(void) list_for_each_entry_safe(k_name, k_tmp, &exofs_kset->list, entry) { printk(KERN_INFO "%s: name %s ref %d\n", __func__, kobject_name(k_name), - (int)atomic_read(&k_name->kref.refcount)); + (int)kref_read(&k_name->kref)); } #endif } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 4e06a27ed7f8..f11792672977 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -399,6 +399,10 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) { spin_lock(&fiq->waitq.lock); + if (test_bit(FR_FINISHED, &req->flags)) { + spin_unlock(&fiq->waitq.lock); + return; + } if (list_empty(&req->intr_entry)) { list_add_tail(&req->intr_entry, &fiq->interrupts); wake_up_locked(&fiq->waitq); @@ -1372,6 +1376,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos, * code can Oops if the buffer persists after module unload. */ bufs[page_nr].ops = &nosteal_pipe_buf_ops; + bufs[page_nr].flags = 0; ret = add_to_pipe(pipe, &bufs[page_nr++]); if (unlikely(ret < 0)) break; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 91307940c8ac..052f8d3c41cb 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -256,7 +256,7 @@ struct fuse_io_priv { #define FUSE_IO_PRIV_SYNC(f) \ { \ - .refcnt = { ATOMIC_INIT(1) }, \ + .refcnt = KREF_INIT(1), \ .async = 0, \ .file = f, \ } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 8c514367ba5a..b6b194ec1b4f 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -393,7 +393,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) /* Do we need to erase the effects of a prior jbd2_journal_flush? */ if (journal->j_flags & JBD2_FLUSHED) { jbd_debug(3, "super block updated\n"); - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); /* * We hold j_checkpoint_mutex so tail cannot change under us. * We don't need any special data guarantees for writing sb diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index a097048ed1a3..d8a5d0a08f07 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -944,7 +944,7 @@ out: */ void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); if (tid_gt(tid, journal->j_tail_sequence)) __jbd2_update_log_tail(journal, tid, block); mutex_unlock(&journal->j_checkpoint_mutex); @@ -1304,7 +1304,7 @@ static int journal_reset(journal_t *journal) journal->j_flags |= JBD2_FLUSHED; } else { /* Lock here to make assertions happy... */ - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); /* * Update log tail information. We use REQ_FUA since new * transaction will start reusing journal space and so we @@ -1691,7 +1691,7 @@ int jbd2_journal_destroy(journal_t *journal) spin_lock(&journal->j_list_lock); while (journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); err = jbd2_log_do_checkpoint(journal); mutex_unlock(&journal->j_checkpoint_mutex); /* @@ -1713,7 +1713,7 @@ int jbd2_journal_destroy(journal_t *journal) if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); write_lock(&journal->j_state_lock); journal->j_tail_sequence = @@ -1955,7 +1955,7 @@ int jbd2_journal_flush(journal_t *journal) spin_lock(&journal->j_list_lock); while (!err && journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); err = jbd2_log_do_checkpoint(journal); mutex_unlock(&journal->j_checkpoint_mutex); spin_lock(&journal->j_list_lock); @@ -1965,7 +1965,7 @@ int jbd2_journal_flush(journal_t *journal) if (is_journal_aborted(journal)) return -EIO; - mutex_lock(&journal->j_checkpoint_mutex); + mutex_lock_io(&journal->j_checkpoint_mutex); if (!err) { err = jbd2_cleanup_journal_tail(journal); if (err < 0) { diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c index 27d1242c8383..564c504d6efd 100644 --- a/fs/ocfs2/cluster/netdebug.c +++ b/fs/ocfs2/cluster/netdebug.c @@ -349,7 +349,7 @@ static void sc_show_sock_container(struct seq_file *seq, " func key: 0x%08x\n" " func type: %u\n", sc, - atomic_read(&sc->sc_kref.refcount), + kref_read(&sc->sc_kref), &saddr, inet ? ntohs(sport) : 0, &daddr, inet ? ntohs(dport) : 0, sc->sc_node->nd_name, diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index d4b5c81f0445..ec000575e863 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -97,7 +97,7 @@ typeof(sc) __sc = (sc); \ mlog(ML_SOCKET, "[sc %p refs %d sock %p node %u page %p " \ "pg_off %zu] " fmt, __sc, \ - atomic_read(&__sc->sc_kref.refcount), __sc->sc_sock, \ + kref_read(&__sc->sc_kref), __sc->sc_sock, \ __sc->sc_node->nd_num, __sc->sc_page, __sc->sc_page_off , \ ##args); \ } while (0) diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index e7b760deefae..9b984cae4c4e 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -81,7 +81,7 @@ static void __dlm_print_lock(struct dlm_lock *lock) lock->ml.type, lock->ml.convert_type, lock->ml.node, dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)), dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)), - atomic_read(&lock->lock_refs.refcount), + kref_read(&lock->lock_refs), (list_empty(&lock->ast_list) ? 'y' : 'n'), (lock->ast_pending ? 'y' : 'n'), (list_empty(&lock->bast_list) ? 'y' : 'n'), @@ -106,7 +106,7 @@ void __dlm_print_one_lock_resource(struct dlm_lock_resource *res) printk("lockres: %s, owner=%u, state=%u\n", buf, res->owner, res->state); printk(" last used: %lu, refcnt: %u, on purge list: %s\n", - res->last_used, atomic_read(&res->refs.refcount), + res->last_used, kref_read(&res->refs), list_empty(&res->purge) ? "no" : "yes"); printk(" on dirty list: %s, on reco list: %s, " "migrating pending: %s\n", @@ -298,7 +298,7 @@ static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len) mle_type, mle->master, mle->new_master, !list_empty(&mle->hb_events), !!mle->inuse, - atomic_read(&mle->mle_refs.refcount)); + kref_read(&mle->mle_refs)); out += snprintf(buf + out, len - out, "Maybe="); out += stringify_nodemap(mle->maybe_map, O2NM_MAX_NODES, @@ -494,7 +494,7 @@ static int dump_lock(struct dlm_lock *lock, int list_type, char *buf, int len) lock->ast_pending, lock->bast_pending, lock->convert_pending, lock->lock_pending, lock->cancel_pending, lock->unlock_pending, - atomic_read(&lock->lock_refs.refcount)); + kref_read(&lock->lock_refs)); spin_unlock(&lock->spinlock); return out; @@ -521,7 +521,7 @@ static int dump_lockres(struct dlm_lock_resource *res, char *buf, int len) !list_empty(&res->recovering), res->inflight_locks, res->migration_pending, atomic_read(&res->asts_reserved), - atomic_read(&res->refs.refcount)); + kref_read(&res->refs)); /* refmap */ out += snprintf(buf + out, len - out, "RMAP:"); @@ -777,7 +777,7 @@ static int debug_state_print(struct dlm_ctxt *dlm, char *buf, int len) /* Purge Count: xxx Refs: xxx */ out += snprintf(buf + out, len - out, "Purge Count: %d Refs: %d\n", dlm->purge_count, - atomic_read(&dlm->dlm_refs.refcount)); + kref_read(&dlm->dlm_refs)); /* Dead Node: xxx */ out += snprintf(buf + out, len - out, diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 733e4e79c8e2..32fd261ae13d 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -2072,7 +2072,7 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain, INIT_LIST_HEAD(&dlm->dlm_eviction_callbacks); mlog(0, "context init: refcount %u\n", - atomic_read(&dlm->dlm_refs.refcount)); + kref_read(&dlm->dlm_refs)); leave: if (ret < 0 && dlm) { diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index a464c8088170..7025d8c27999 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -233,7 +233,7 @@ static void __dlm_put_mle(struct dlm_master_list_entry *mle) assert_spin_locked(&dlm->spinlock); assert_spin_locked(&dlm->master_lock); - if (!atomic_read(&mle->mle_refs.refcount)) { + if (!kref_read(&mle->mle_refs)) { /* this may or may not crash, but who cares. * it's a BUG. */ mlog(ML_ERROR, "bad mle: %p\n", mle); @@ -1124,9 +1124,9 @@ recheck: unsigned long timeo = msecs_to_jiffies(DLM_MASTERY_TIMEOUT_MS); /* - if (atomic_read(&mle->mle_refs.refcount) < 2) + if (kref_read(&mle->mle_refs) < 2) mlog(ML_ERROR, "mle (%p) refs=%d, name=%.*s\n", mle, - atomic_read(&mle->mle_refs.refcount), + kref_read(&mle->mle_refs), res->lockname.len, res->lockname.name); */ atomic_set(&mle->woken, 0); @@ -1979,7 +1979,7 @@ ok: * on this mle. */ spin_lock(&dlm->master_lock); - rr = atomic_read(&mle->mle_refs.refcount); + rr = kref_read(&mle->mle_refs); if (mle->inuse > 0) { if (extra_ref && rr < 3) err = 1; diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 1082b2c3014b..63d701cd1e2e 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -251,7 +251,7 @@ leave: mlog(0, "lock %u:%llu should be gone now! refs=%d\n", dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)), dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)), - atomic_read(&lock->lock_refs.refcount)-1); + kref_read(&lock->lock_refs)-1); dlm_lock_put(lock); } if (actions & DLM_UNLOCK_CALL_AST) diff --git a/fs/proc/array.c b/fs/proc/array.c index 51a4213afa2e..fe12b519d09b 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -401,8 +401,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, unsigned long long start_time; unsigned long cmin_flt = 0, cmaj_flt = 0; unsigned long min_flt = 0, maj_flt = 0; - cputime_t cutime, cstime, utime, stime; - cputime_t cgtime, gtime; + u64 cutime, cstime, utime, stime; + u64 cgtime, gtime; unsigned long rsslim = 0; char tcomm[sizeof(task->comm)]; unsigned long flags; @@ -497,10 +497,10 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_put_decimal_ull(m, " ", cmin_flt); seq_put_decimal_ull(m, " ", maj_flt); seq_put_decimal_ull(m, " ", cmaj_flt); - seq_put_decimal_ull(m, " ", cputime_to_clock_t(utime)); - seq_put_decimal_ull(m, " ", cputime_to_clock_t(stime)); - seq_put_decimal_ll(m, " ", cputime_to_clock_t(cutime)); - seq_put_decimal_ll(m, " ", cputime_to_clock_t(cstime)); + seq_put_decimal_ull(m, " ", nsec_to_clock_t(utime)); + seq_put_decimal_ull(m, " ", nsec_to_clock_t(stime)); + seq_put_decimal_ll(m, " ", nsec_to_clock_t(cutime)); + seq_put_decimal_ll(m, " ", nsec_to_clock_t(cstime)); seq_put_decimal_ll(m, " ", priority); seq_put_decimal_ll(m, " ", nice); seq_put_decimal_ll(m, " ", num_threads); @@ -542,8 +542,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_put_decimal_ull(m, " ", task->rt_priority); seq_put_decimal_ull(m, " ", task->policy); seq_put_decimal_ull(m, " ", delayacct_blkio_ticks(task)); - seq_put_decimal_ull(m, " ", cputime_to_clock_t(gtime)); - seq_put_decimal_ll(m, " ", cputime_to_clock_t(cgtime)); + seq_put_decimal_ull(m, " ", nsec_to_clock_t(gtime)); + seq_put_decimal_ll(m, " ", nsec_to_clock_t(cgtime)); if (mm && permitted) { seq_put_decimal_ull(m, " ", mm->start_data); diff --git a/fs/proc/base.c b/fs/proc/base.c index 87c9a9aacda3..b1f7d30e96c2 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2179,7 +2179,7 @@ static const struct file_operations proc_map_files_operations = { .llseek = generic_file_llseek, }; -#ifdef CONFIG_CHECKPOINT_RESTORE +#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) struct timers_private { struct pid *pid; struct task_struct *task; @@ -2936,7 +2936,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif -#ifdef CONFIG_CHECKPOINT_RESTORE +#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) REG("timers", S_IRUGO, proc_timers_operations), #endif REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations), diff --git a/fs/proc/stat.c b/fs/proc/stat.c index d700c42b3572..e47c3e8c4dfe 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -21,9 +21,9 @@ #ifdef arch_idle_time -static cputime64_t get_idle_time(int cpu) +static u64 get_idle_time(int cpu) { - cputime64_t idle; + u64 idle; idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; if (cpu_online(cpu) && !nr_iowait_cpu(cpu)) @@ -31,9 +31,9 @@ static cputime64_t get_idle_time(int cpu) return idle; } -static cputime64_t get_iowait_time(int cpu) +static u64 get_iowait_time(int cpu) { - cputime64_t iowait; + u64 iowait; iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; if (cpu_online(cpu) && nr_iowait_cpu(cpu)) @@ -45,32 +45,32 @@ static cputime64_t get_iowait_time(int cpu) static u64 get_idle_time(int cpu) { - u64 idle, idle_time = -1ULL; + u64 idle, idle_usecs = -1ULL; if (cpu_online(cpu)) - idle_time = get_cpu_idle_time_us(cpu, NULL); + idle_usecs = get_cpu_idle_time_us(cpu, NULL); - if (idle_time == -1ULL) + if (idle_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.idle */ idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; else - idle = usecs_to_cputime64(idle_time); + idle = idle_usecs * NSEC_PER_USEC; return idle; } static u64 get_iowait_time(int cpu) { - u64 iowait, iowait_time = -1ULL; + u64 iowait, iowait_usecs = -1ULL; if (cpu_online(cpu)) - iowait_time = get_cpu_iowait_time_us(cpu, NULL); + iowait_usecs = get_cpu_iowait_time_us(cpu, NULL); - if (iowait_time == -1ULL) + if (iowait_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.iowait */ iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; else - iowait = usecs_to_cputime64(iowait_time); + iowait = iowait_usecs * NSEC_PER_USEC; return iowait; } @@ -115,16 +115,16 @@ static int show_stat(struct seq_file *p, void *v) } sum += arch_irq_stat(); - seq_put_decimal_ull(p, "cpu ", cputime64_to_clock_t(user)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice)); + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(user)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(system)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice)); seq_putc(p, '\n'); for_each_online_cpu(i) { @@ -140,16 +140,16 @@ static int show_stat(struct seq_file *p, void *v) guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; seq_printf(p, "cpu%d", i); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(user)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest)); - seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(user)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(system)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest)); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice)); seq_putc(p, '\n'); } seq_put_decimal_ull(p, "intr ", (unsigned long long)sum); diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 33de567c25af..7981c4ffe787 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -5,23 +5,20 @@ #include <linux/seq_file.h> #include <linux/time.h> #include <linux/kernel_stat.h> -#include <linux/cputime.h> static int uptime_proc_show(struct seq_file *m, void *v) { struct timespec uptime; struct timespec idle; - u64 idletime; u64 nsec; u32 rem; int i; - idletime = 0; + nsec = 0; for_each_possible_cpu(i) - idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE]; + nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE]; get_monotonic_boottime(&uptime); - nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC; idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); idle.tv_nsec = rem; seq_printf(m, "%lu.%02lu %lu.%02lu\n", diff --git a/fs/splice.c b/fs/splice.c index 873d83104e79..4ef78aa8ef61 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -204,6 +204,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, buf->len = spd->partial[page_nr].len; buf->private = spd->partial[page_nr].private; buf->ops = spd->ops; + buf->flags = 0; pipe->nrbufs++; page_nr++; diff --git a/fs/timerfd.c b/fs/timerfd.c index c173cc196175..384fa759a563 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -40,6 +40,7 @@ struct timerfd_ctx { short unsigned settime_flags; /* to show in fdinfo */ struct rcu_head rcu; struct list_head clist; + spinlock_t cancel_lock; bool might_cancel; }; @@ -112,7 +113,7 @@ void timerfd_clock_was_set(void) rcu_read_unlock(); } -static void timerfd_remove_cancel(struct timerfd_ctx *ctx) +static void __timerfd_remove_cancel(struct timerfd_ctx *ctx) { if (ctx->might_cancel) { ctx->might_cancel = false; @@ -122,6 +123,13 @@ static void timerfd_remove_cancel(struct timerfd_ctx *ctx) } } +static void timerfd_remove_cancel(struct timerfd_ctx *ctx) +{ + spin_lock(&ctx->cancel_lock); + __timerfd_remove_cancel(ctx); + spin_unlock(&ctx->cancel_lock); +} + static bool timerfd_canceled(struct timerfd_ctx *ctx) { if (!ctx->might_cancel || ctx->moffs != KTIME_MAX) @@ -132,6 +140,7 @@ static bool timerfd_canceled(struct timerfd_ctx *ctx) static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags) { + spin_lock(&ctx->cancel_lock); if ((ctx->clockid == CLOCK_REALTIME || ctx->clockid == CLOCK_REALTIME_ALARM) && (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) { @@ -141,9 +150,10 @@ static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags) list_add_rcu(&ctx->clist, &cancel_list); spin_unlock(&cancel_lock); } - } else if (ctx->might_cancel) { - timerfd_remove_cancel(ctx); + } else { + __timerfd_remove_cancel(ctx); } + spin_unlock(&ctx->cancel_lock); } static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) @@ -400,6 +410,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) return -ENOMEM; init_waitqueue_head(&ctx->wqh); + spin_lock_init(&ctx->cancel_lock); ctx->clockid = clockid; if (isalarm(ctx)) diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h deleted file mode 100644 index 51969436b8b8..000000000000 --- a/include/asm-generic/cputime.h +++ /dev/null @@ -1,15 +0,0 @@ -#ifndef _ASM_GENERIC_CPUTIME_H -#define _ASM_GENERIC_CPUTIME_H - -#include <linux/time.h> -#include <linux/jiffies.h> - -#ifndef CONFIG_VIRT_CPU_ACCOUNTING -# include <asm-generic/cputime_jiffies.h> -#endif - -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -# include <asm-generic/cputime_nsecs.h> -#endif - -#endif diff --git a/include/asm-generic/cputime_jiffies.h b/include/asm-generic/cputime_jiffies.h deleted file mode 100644 index 6bb8cd45f53b..000000000000 --- a/include/asm-generic/cputime_jiffies.h +++ /dev/null @@ -1,75 +0,0 @@ -#ifndef _ASM_GENERIC_CPUTIME_JIFFIES_H -#define _ASM_GENERIC_CPUTIME_JIFFIES_H - -typedef unsigned long __nocast cputime_t; - -#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new) - -#define cputime_one_jiffy jiffies_to_cputime(1) -#define cputime_to_jiffies(__ct) (__force unsigned long)(__ct) -#define jiffies_to_cputime(__hz) (__force cputime_t)(__hz) - -typedef u64 __nocast cputime64_t; - -#define cputime64_to_jiffies64(__ct) (__force u64)(__ct) -#define jiffies64_to_cputime64(__jif) (__force cputime64_t)(__jif) - - -/* - * Convert nanoseconds <-> cputime - */ -#define cputime_to_nsecs(__ct) \ - jiffies_to_nsecs(cputime_to_jiffies(__ct)) -#define nsecs_to_cputime64(__nsec) \ - jiffies64_to_cputime64(nsecs_to_jiffies64(__nsec)) -#define nsecs_to_cputime(__nsec) \ - jiffies_to_cputime(nsecs_to_jiffies(__nsec)) - - -/* - * Convert cputime to microseconds and back. - */ -#define cputime_to_usecs(__ct) \ - jiffies_to_usecs(cputime_to_jiffies(__ct)) -#define usecs_to_cputime(__usec) \ - jiffies_to_cputime(usecs_to_jiffies(__usec)) -#define usecs_to_cputime64(__usec) \ - jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000)) - -/* - * Convert cputime to seconds and back. - */ -#define cputime_to_secs(jif) (cputime_to_jiffies(jif) / HZ) -#define secs_to_cputime(sec) jiffies_to_cputime((sec) * HZ) - -/* - * Convert cputime to timespec and back. - */ -#define timespec_to_cputime(__val) \ - jiffies_to_cputime(timespec_to_jiffies(__val)) -#define cputime_to_timespec(__ct,__val) \ - jiffies_to_timespec(cputime_to_jiffies(__ct),__val) - -/* - * Convert cputime to timeval and back. - */ -#define timeval_to_cputime(__val) \ - jiffies_to_cputime(timeval_to_jiffies(__val)) -#define cputime_to_timeval(__ct,__val) \ - jiffies_to_timeval(cputime_to_jiffies(__ct),__val) - -/* - * Convert cputime to clock and back. - */ -#define cputime_to_clock_t(__ct) \ - jiffies_to_clock_t(cputime_to_jiffies(__ct)) -#define clock_t_to_cputime(__x) \ - jiffies_to_cputime(clock_t_to_jiffies(__x)) - -/* - * Convert cputime64 to clock. - */ -#define cputime64_to_clock_t(__ct) \ - jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct)) - -#endif diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h deleted file mode 100644 index 4e3b18e559b1..000000000000 --- a/include/asm-generic/cputime_nsecs.h +++ /dev/null @@ -1,121 +0,0 @@ -/* - * Definitions for measuring cputime in nsecs resolution. - * - * Based on <arch/ia64/include/asm/cputime.h> - * - * Copyright (C) 2007 FUJITSU LIMITED - * Copyright (C) 2007 Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.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. - * - */ - -#ifndef _ASM_GENERIC_CPUTIME_NSECS_H -#define _ASM_GENERIC_CPUTIME_NSECS_H - -#include <linux/math64.h> - -typedef u64 __nocast cputime_t; -typedef u64 __nocast cputime64_t; - -#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new) - -#define cputime_one_jiffy jiffies_to_cputime(1) - -#define cputime_div(__ct, divisor) div_u64((__force u64)__ct, divisor) -#define cputime_div_rem(__ct, divisor, remainder) \ - div_u64_rem((__force u64)__ct, divisor, remainder); - -/* - * Convert cputime <-> jiffies (HZ) - */ -#define cputime_to_jiffies(__ct) \ - cputime_div(__ct, NSEC_PER_SEC / HZ) -#define jiffies_to_cputime(__jif) \ - (__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ)) -#define cputime64_to_jiffies64(__ct) \ - cputime_div(__ct, NSEC_PER_SEC / HZ) -#define jiffies64_to_cputime64(__jif) \ - (__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ)) - - -/* - * Convert cputime <-> nanoseconds - */ -#define cputime_to_nsecs(__ct) \ - (__force u64)(__ct) -#define nsecs_to_cputime(__nsecs) \ - (__force cputime_t)(__nsecs) -#define nsecs_to_cputime64(__nsecs) \ - (__force cputime64_t)(__nsecs) - - -/* - * Convert cputime <-> microseconds - */ -#define cputime_to_usecs(__ct) \ - cputime_div(__ct, NSEC_PER_USEC) -#define usecs_to_cputime(__usecs) \ - (__force cputime_t)((__usecs) * NSEC_PER_USEC) -#define usecs_to_cputime64(__usecs) \ - (__force cputime64_t)((__usecs) * NSEC_PER_USEC) - -/* - * Convert cputime <-> seconds - */ -#define cputime_to_secs(__ct) \ - cputime_div(__ct, NSEC_PER_SEC) -#define secs_to_cputime(__secs) \ - (__force cputime_t)((__secs) * NSEC_PER_SEC) - -/* - * Convert cputime <-> timespec (nsec) - */ -static inline cputime_t timespec_to_cputime(const struct timespec *val) -{ - u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + val->tv_nsec; - return (__force cputime_t) ret; -} -static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val) -{ - u32 rem; - - val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem); - val->tv_nsec = rem; -} - -/* - * Convert cputime <-> timeval (msec) - */ -static inline cputime_t timeval_to_cputime(const struct timeval *val) -{ - u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + - val->tv_usec * NSEC_PER_USEC; - return (__force cputime_t) ret; -} -static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val) -{ - u32 rem; - - val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem); - val->tv_usec = rem / NSEC_PER_USEC; -} - -/* - * Convert cputime <-> clock (USER_HZ) - */ -#define cputime_to_clock_t(__ct) \ - cputime_div(__ct, (NSEC_PER_SEC / USER_HZ)) -#define clock_t_to_cputime(__x) \ - (__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ)) - -/* - * Convert cputime64 to clock. - */ -#define cputime64_to_clock_t(__ct) \ - cputime_to_clock_t((__force cputime_t)__ct) - -#endif diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h index 5be122e3d326..6c6a2141f271 100644 --- a/include/asm-generic/rwsem.h +++ b/include/asm-generic/rwsem.h @@ -33,7 +33,7 @@ */ static inline void __down_read(struct rw_semaphore *sem) { - if (unlikely(atomic_long_inc_return_acquire((atomic_long_t *)&sem->count) <= 0)) + if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) rwsem_down_read_failed(sem); } @@ -58,7 +58,7 @@ static inline void __down_write(struct rw_semaphore *sem) long tmp; tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, - (atomic_long_t *)&sem->count); + &sem->count); if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) rwsem_down_write_failed(sem); } @@ -68,7 +68,7 @@ static inline int __down_write_killable(struct rw_semaphore *sem) long tmp; tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, - (atomic_long_t *)&sem->count); + &sem->count); if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) if (IS_ERR(rwsem_down_write_failed_killable(sem))) return -EINTR; @@ -91,7 +91,7 @@ static inline void __up_read(struct rw_semaphore *sem) { long tmp; - tmp = atomic_long_dec_return_release((atomic_long_t *)&sem->count); + tmp = atomic_long_dec_return_release(&sem->count); if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)) rwsem_wake(sem); } @@ -102,7 +102,7 @@ static inline void __up_read(struct rw_semaphore *sem) static inline void __up_write(struct rw_semaphore *sem) { if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS, - (atomic_long_t *)&sem->count) < 0)) + &sem->count) < 0)) rwsem_wake(sem); } @@ -120,8 +120,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem) * read-locked region is ok to be re-ordered into the * write side. As such, rely on RELEASE semantics. */ - tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, - (atomic_long_t *)&sem->count); + tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count); if (tmp < 0) rwsem_downgrade_wake(sem); } diff --git a/include/drm/drm_framebuffer.h b/include/drm/drm_framebuffer.h index 1ddfa2928802..a232e7f0c869 100644 --- a/include/drm/drm_framebuffer.h +++ b/include/drm/drm_framebuffer.h @@ -247,7 +247,7 @@ static inline void drm_framebuffer_unreference(struct drm_framebuffer *fb) */ static inline uint32_t drm_framebuffer_read_refcount(struct drm_framebuffer *fb) { - return atomic_read(&fb->base.refcount.refcount); + return kref_read(&fb->base.refcount); } /** diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 652e45be97c8..9a465314572c 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -332,19 +332,6 @@ extern int ttm_bo_validate(struct ttm_buffer_object *bo, */ extern void ttm_bo_unref(struct ttm_buffer_object **bo); - -/** - * ttm_bo_list_ref_sub - * - * @bo: The buffer object. - * @count: The number of references with which to decrease @bo::list_kref; - * @never_free: The refcount should not reach zero with this operation. - * - * Release @count lru list references to this buffer object. - */ -extern void ttm_bo_list_ref_sub(struct ttm_buffer_object *bo, int count, - bool never_free); - /** * ttm_bo_add_to_lru * @@ -367,7 +354,7 @@ extern void ttm_bo_add_to_lru(struct ttm_buffer_object *bo); * and is usually called just immediately after the bo has been reserved to * avoid recursive reservation from lru lists. */ -extern int ttm_bo_del_from_lru(struct ttm_buffer_object *bo); +extern void ttm_bo_del_from_lru(struct ttm_buffer_object *bo); /** * ttm_bo_move_to_lru_tail diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index cdbdb40eb5bd..feecf33a1212 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -878,7 +878,7 @@ static inline int ttm_bo_reserve(struct ttm_buffer_object *bo, { int ret; - WARN_ON(!atomic_read(&bo->kref.refcount)); + WARN_ON(!kref_read(&bo->kref)); ret = __ttm_bo_reserve(bo, interruptible, no_wait, ticket); if (likely(ret == 0)) @@ -903,7 +903,7 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo, { int ret = 0; - WARN_ON(!atomic_read(&bo->kref.refcount)); + WARN_ON(!kref_read(&bo->kref)); if (interruptible) ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock, diff --git a/include/dt-bindings/thermal/lm90.h b/include/dt-bindings/thermal/lm90.h new file mode 100644 index 000000000000..8c2e3095f704 --- /dev/null +++ b/include/dt-bindings/thermal/lm90.h @@ -0,0 +1,12 @@ +/* + * This header provides constants for the LM90 thermal bindings. + */ + +#ifndef _DT_BINDINGS_THERMAL_LM90_H_ +#define _DT_BINDINGS_THERMAL_LM90_H_ + +#define LM90_LOCAL_TEMPERATURE 0 +#define LM90_REMOTE_TEMPERATURE 1 +#define LM90_REMOTE2_TEMPERATURE 2 + +#endif diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 5b36974ed60a..8e577c2cb0ce 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1153,4 +1153,14 @@ int parse_spcr(bool earlycon); static inline int parse_spcr(bool earlycon) { return 0; } #endif +#if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) +int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res); +#else +static inline +int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) +{ + return -EINVAL; +} +#endif + #endif /*_LINUX_ACPI_H*/ diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index b20e3d56253f..2f1c690a3e66 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -593,9 +593,6 @@ struct bcma_sflash { u32 blocksize; u16 numblocks; u32 size; - - struct mtd_info *mtd; - void *priv; }; #endif diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 92bc89ae7e20..c970a25d2a49 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -21,20 +21,19 @@ struct cgroup_bpf { */ struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE]; struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE]; + bool disallow_override[MAX_BPF_ATTACH_TYPE]; }; void cgroup_bpf_put(struct cgroup *cgrp); void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent); -void __cgroup_bpf_update(struct cgroup *cgrp, - struct cgroup *parent, - struct bpf_prog *prog, - enum bpf_attach_type type); +int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, + struct bpf_prog *prog, enum bpf_attach_type type, + bool overridable); /* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */ -void cgroup_bpf_update(struct cgroup *cgrp, - struct bpf_prog *prog, - enum bpf_attach_type type); +int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, bool overridable); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 0d442e34c349..5d3053c34fb3 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -224,4 +224,13 @@ static inline void tick_setup_hrtimer_broadcast(void) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ +#define CLOCKEVENT_OF_DECLARE(name, compat, fn) \ + OF_DECLARE_1_RET(clkevt, name, compat, fn) + +#ifdef CONFIG_CLKEVT_PROBE +extern int clockevent_probe(void); +#els +static inline int clockevent_probe(void) { return 0; } +#endif + #endif /* _LINUX_CLOCKCHIPS_H */ diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index e315d04a2fd9..cfc75848a35d 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -62,6 +62,8 @@ struct module; * @archdata: arch-specific data * @suspend: suspend function for the clocksource, if necessary * @resume: resume function for the clocksource, if necessary + * @mark_unstable: Optional function to inform the clocksource driver that + * the watchdog marked the clocksource unstable * @owner: module reference, must be set by clocksource in modules * * Note: This struct is not used in hotpathes of the timekeeping code @@ -93,6 +95,7 @@ struct clocksource { unsigned long flags; void (*suspend)(struct clocksource *cs); void (*resume)(struct clocksource *cs); + void (*mark_unstable)(struct clocksource *cs); /* private: */ #ifdef CONFIG_CLOCKSOURCE_WATCHDOG diff --git a/include/linux/compat.h b/include/linux/compat.h index 63609398ef9f..9e40be522793 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -731,7 +731,25 @@ asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, static inline bool in_compat_syscall(void) { return is_compat_task(); } #endif -#else +/** + * ns_to_compat_timeval - Compat version of ns_to_timeval + * @nsec: the nanoseconds value to be converted + * + * Returns the compat_timeval representation of the nsec parameter. + */ +static inline struct compat_timeval ns_to_compat_timeval(s64 nsec) +{ + struct timeval tv; + struct compat_timeval ctv; + + tv = ns_to_timeval(nsec); + ctv.tv_sec = tv.tv_sec; + ctv.tv_usec = tv.tv_usec; + + return ctv; +} + +#else /* !CONFIG_COMPAT */ #define is_compat_task() (0) static inline bool in_compat_syscall(void) { return false; } diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b3d2c1a89ac4..96f1e88b767c 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -649,11 +649,15 @@ static inline size_t cpumask_size(void) * used. Please use this_cpu_cpumask_var_t in those cases. The direct use * of this_cpu_ptr() or this_cpu_read() will lead to failures when the * other type of cpumask_var_t implementation is configured. + * + * Please also note that __cpumask_var_read_mostly can be used to declare + * a cpumask_var_t variable itself (not its content) as read mostly. */ #ifdef CONFIG_CPUMASK_OFFSTACK typedef struct cpumask *cpumask_var_t; -#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) +#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) +#define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); @@ -667,6 +671,7 @@ void free_bootmem_cpumask_var(cpumask_var_t mask); typedef struct cpumask cpumask_var_t[1]; #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) +#define __cpumask_var_read_mostly static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { diff --git a/include/linux/cputime.h b/include/linux/cputime.h index f2eb2ee535ca..a691dc4ddc13 100644 --- a/include/linux/cputime.h +++ b/include/linux/cputime.h @@ -1,6 +1,7 @@ #ifndef __LINUX_CPUTIME_H #define __LINUX_CPUTIME_H +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include <asm/cputime.h> #ifndef cputime_to_nsecs @@ -8,9 +9,5 @@ (cputime_to_usecs(__ct) * NSEC_PER_USEC) #endif -#ifndef nsecs_to_cputime -# define nsecs_to_cputime(__nsecs) \ - usecs_to_cputime((__nsecs) / NSEC_PER_USEC) -#endif - +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #endif /* __LINUX_CPUTIME_H */ diff --git a/include/linux/delay.h b/include/linux/delay.h index a6ecb34cf547..2ecb3c46b20a 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -5,6 +5,17 @@ * Copyright (C) 1993 Linus Torvalds * * Delay routines, using a pre-computed "loops_per_jiffy" value. + * + * Please note that ndelay(), udelay() and mdelay() may return early for + * several reasons: + * 1. computed loops_per_jiffy too low (due to the time taken to + * execute the timer interrupt.) + * 2. cache behaviour affecting the time it takes to execute the + * loop function. + * 3. CPU clock rate changes. + * + * Please see this thread: + * http://lists.openwall.net/linux-kernel/2011/01/09/56 */ #include <linux/kernel.h> diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 6cee17c22313..00e60f79a9cc 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -17,6 +17,7 @@ #ifndef _LINUX_DELAYACCT_H #define _LINUX_DELAYACCT_H +#include <uapi/linux/taskstats.h> #include <linux/sched.h> #include <linux/slab.h> diff --git a/include/linux/edac.h b/include/linux/edac.h index 07c52c0af62d..5b6adf964248 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -190,8 +190,8 @@ static inline char *mc_event_error_type(const unsigned int err_type) * part of the memory details to the memory controller. * @MEM_RMBS: Rambus DRAM, used on a few Pentium III/IV controllers. * @MEM_DDR2: DDR2 RAM, as described at JEDEC JESD79-2F. - * Those memories are labed as "PC2-" instead of "PC" to - * differenciate from DDR. + * Those memories are labeled as "PC2-" instead of "PC" to + * differentiate from DDR. * @MEM_FB_DDR2: Fully-Buffered DDR2, as described at JEDEC Std No. 205 * and JESD206. * Those memories are accessed per DIMM slot, and not by diff --git a/include/linux/efi-bgrt.h b/include/linux/efi-bgrt.h index 051b21fedf68..2fd3993c370b 100644 --- a/include/linux/efi-bgrt.h +++ b/include/linux/efi-bgrt.h @@ -1,20 +1,19 @@ #ifndef _LINUX_EFI_BGRT_H #define _LINUX_EFI_BGRT_H -#ifdef CONFIG_ACPI_BGRT - #include <linux/acpi.h> -void efi_bgrt_init(void); +#ifdef CONFIG_ACPI_BGRT + +void efi_bgrt_init(struct acpi_table_header *table); /* The BGRT data itself; only valid if bgrt_image != NULL. */ -extern void *bgrt_image; extern size_t bgrt_image_size; -extern struct acpi_table_bgrt *bgrt_tab; +extern struct acpi_table_bgrt bgrt_tab; #else /* !CONFIG_ACPI_BGRT */ -static inline void efi_bgrt_init(void) {} +static inline void efi_bgrt_init(struct acpi_table_header *table) {} #endif /* !CONFIG_ACPI_BGRT */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 5b1af30ece55..94d34e0be24f 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -509,24 +509,6 @@ typedef struct { u64 query_variable_info; } efi_runtime_services_64_t; -typedef struct { - efi_table_hdr_t hdr; - void *get_time; - void *set_time; - void *get_wakeup_time; - void *set_wakeup_time; - void *set_virtual_address_map; - void *convert_pointer; - void *get_variable; - void *get_next_variable; - void *set_variable; - void *get_next_high_mono_count; - void *reset_system; - void *update_capsule; - void *query_capsule_caps; - void *query_variable_info; -} efi_runtime_services_t; - typedef efi_status_t efi_get_time_t (efi_time_t *tm, efi_time_cap_t *tc); typedef efi_status_t efi_set_time_t (efi_time_t *tm); typedef efi_status_t efi_get_wakeup_time_t (efi_bool_t *enabled, efi_bool_t *pending, @@ -561,6 +543,24 @@ typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size, bool nonblocking); +typedef struct { + efi_table_hdr_t hdr; + efi_get_time_t *get_time; + efi_set_time_t *set_time; + efi_get_wakeup_time_t *get_wakeup_time; + efi_set_wakeup_time_t *set_wakeup_time; + efi_set_virtual_address_map_t *set_virtual_address_map; + void *convert_pointer; + efi_get_variable_t *get_variable; + efi_get_next_variable_t *get_next_variable; + efi_set_variable_t *set_variable; + efi_get_next_high_mono_count_t *get_next_high_mono_count; + efi_reset_system_t *reset_system; + efi_update_capsule_t *update_capsule; + efi_query_capsule_caps_t *query_capsule_caps; + efi_query_variable_info_t *query_variable_info; +} efi_runtime_services_t; + void efi_native_runtime_setup(void); /* @@ -611,6 +611,9 @@ void efi_native_runtime_setup(void); #define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define APPLE_PROPERTIES_PROTOCOL_GUID EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb, 0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0) +#define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) +#define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) + /* * This GUID is used to pass to the kernel proper the struct screen_info * structure that was populated by the stub based on the GOP protocol instance @@ -1065,6 +1068,7 @@ extern int __init efi_setup_pcdp_console(char *); #define EFI_ARCH_1 7 /* First arch-specific bit */ #define EFI_DBG 8 /* Print additional debug info at runtime */ #define EFI_NX_PE_DATA 9 /* Can runtime data regions be mapped non-executable? */ +#define EFI_MEM_ATTR 10 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */ #ifdef CONFIG_EFI /* @@ -1240,17 +1244,17 @@ struct efivar_entry { bool deleting; }; -struct efi_simple_text_output_protocol_32 { +typedef struct { u32 reset; u32 output_string; u32 test_string; -}; +} efi_simple_text_output_protocol_32_t; -struct efi_simple_text_output_protocol_64 { +typedef struct { u64 reset; u64 output_string; u64 test_string; -}; +} efi_simple_text_output_protocol_64_t; struct efi_simple_text_output_protocol { void *reset; @@ -1476,6 +1480,14 @@ efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, bool efi_runtime_disabled(void); extern void efi_call_virt_check_flags(unsigned long flags, const char *call); +enum efi_secureboot_mode { + efi_secureboot_mode_unset, + efi_secureboot_mode_unknown, + efi_secureboot_mode_disabled, + efi_secureboot_mode_enabled, +}; +enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table); + /* * Arch code can implement the following three template macros, avoiding * reptition for the void/non-void return cases of {__,}efi_call_virt(): diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h index 3f9778cbc79d..c332f0a45607 100644 --- a/include/linux/fsl_ifc.h +++ b/include/linux/fsl_ifc.h @@ -733,8 +733,12 @@ struct fsl_ifc_nand { __be32 nand_erattr1; u32 res19[0x10]; __be32 nand_fsr; - u32 res20[0x3]; - __be32 nand_eccstat[6]; + u32 res20; + /* The V1 nand_eccstat is actually 4 words that overlaps the + * V2 nand_eccstat. + */ + __be32 v1_nand_eccstat[2]; + __be32 v2_nand_eccstat[6]; u32 res21[0x1c]; __be32 nanndcr; u32 res22[0x2]; diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index cdab81ba29f8..e52b427223ba 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -88,12 +88,6 @@ enum hrtimer_restart { * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) * @is_rel: Set if the timer was armed relative - * @start_pid: timer statistics field to store the pid of the task which - * started the timer - * @start_site: timer statistics field to store the site where the timer - * was started - * @start_comm: timer statistics field to store the name of the process which - * started the timer * * The hrtimer structure must be initialized by hrtimer_init() */ @@ -104,11 +98,6 @@ struct hrtimer { struct hrtimer_clock_base *base; u8 state; u8 is_rel; -#ifdef CONFIG_TIMER_STATS - int start_pid; - void *start_site; - char start_comm[16]; -#endif }; /** diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 325f649d77ff..3a85d61f7614 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -42,6 +42,27 @@ extern struct fs_struct init_fs; #define INIT_PREV_CPUTIME(x) #endif +#ifdef CONFIG_POSIX_TIMERS +#define INIT_POSIX_TIMERS(s) \ + .posix_timers = LIST_HEAD_INIT(s.posix_timers), +#define INIT_CPU_TIMERS(s) \ + .cpu_timers = { \ + LIST_HEAD_INIT(s.cpu_timers[0]), \ + LIST_HEAD_INIT(s.cpu_timers[1]), \ + LIST_HEAD_INIT(s.cpu_timers[2]), \ + }, +#define INIT_CPUTIMER(s) \ + .cputimer = { \ + .cputime_atomic = INIT_CPUTIME_ATOMIC, \ + .running = false, \ + .checking_timer = false, \ + }, +#else +#define INIT_POSIX_TIMERS(s) +#define INIT_CPU_TIMERS(s) +#define INIT_CPUTIMER(s) +#endif + #define INIT_SIGNALS(sig) { \ .nr_threads = 1, \ .thread_head = LIST_HEAD_INIT(init_task.thread_node), \ @@ -49,14 +70,10 @@ extern struct fs_struct init_fs; .shared_pending = { \ .list = LIST_HEAD_INIT(sig.shared_pending.list), \ .signal = {{0}}}, \ - .posix_timers = LIST_HEAD_INIT(sig.posix_timers), \ - .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ + INIT_POSIX_TIMERS(sig) \ + INIT_CPU_TIMERS(sig) \ .rlim = INIT_RLIMITS, \ - .cputimer = { \ - .cputime_atomic = INIT_CPUTIME_ATOMIC, \ - .running = false, \ - .checking_timer = false, \ - }, \ + INIT_CPUTIMER(sig) \ INIT_PREV_CPUTIME(sig) \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ @@ -247,7 +264,7 @@ extern struct task_group root_task_group; .blocked = {{0}}, \ .alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \ .journal_info = NULL, \ - .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ + INIT_CPU_TIMERS(tsk) \ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ .timer_slack_ns = 50000, /* 50 usec default slack */ \ .pids = { \ @@ -274,13 +291,6 @@ extern struct task_group root_task_group; } -#define INIT_CPU_TIMERS(cpu_timers) \ -{ \ - LIST_HEAD_INIT(cpu_timers[0]), \ - LIST_HEAD_INIT(cpu_timers[1]), \ - LIST_HEAD_INIT(cpu_timers[2]), \ -} - /* Attach to the init_task data structure for proper alignment */ #define __init_task_data __attribute__((__section__(".data..init_task"))) diff --git a/include/linux/irq.h b/include/linux/irq.h index 39e3254e5769..f887351aa80e 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -732,6 +732,10 @@ unsigned int arch_dynirq_lower_bound(unsigned int from); int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, struct module *owner, const struct cpumask *affinity); +int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from, + unsigned int cnt, int node, struct module *owner, + const struct cpumask *affinity); + /* use macros to avoid needing export.h for THIS_MODULE */ #define irq_alloc_descs(irq, from, cnt, node) \ __irq_alloc_descs(irq, from, cnt, node, THIS_MODULE, NULL) @@ -748,6 +752,21 @@ int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, #define irq_alloc_descs_from(from, cnt, node) \ irq_alloc_descs(-1, from, cnt, node) +#define devm_irq_alloc_descs(dev, irq, from, cnt, node) \ + __devm_irq_alloc_descs(dev, irq, from, cnt, node, THIS_MODULE, NULL) + +#define devm_irq_alloc_desc(dev, node) \ + devm_irq_alloc_descs(dev, -1, 0, 1, node) + +#define devm_irq_alloc_desc_at(dev, at, node) \ + devm_irq_alloc_descs(dev, at, at, 1, node) + +#define devm_irq_alloc_desc_from(dev, from, node) \ + devm_irq_alloc_descs(dev, -1, from, 1, node) + +#define devm_irq_alloc_descs_from(dev, from, cnt, node) \ + devm_irq_alloc_descs(dev, -1, from, cnt, node) + void irq_free_descs(unsigned int irq, unsigned int cnt); static inline void irq_free_desc(unsigned int irq) { diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index e808f8ae6f14..725e86b506f3 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -73,7 +73,6 @@ #define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1) #define GICD_TYPER_IRQS(typer) ((((typer) & 0x1f) + 1) * 32) -#define GICD_TYPER_LPIS (1U << 17) #define GICD_IROUTER_SPI_MODE_ONE (0U << 31) #define GICD_IROUTER_SPI_MODE_ANY (1U << 31) @@ -306,7 +305,7 @@ #define GITS_BASER_TYPE_NONE 0 #define GITS_BASER_TYPE_DEVICE 1 #define GITS_BASER_TYPE_VCPU 2 -#define GITS_BASER_TYPE_CPU 3 +#define GITS_BASER_TYPE_RESERVED3 3 #define GITS_BASER_TYPE_COLLECTION 4 #define GITS_BASER_TYPE_RESERVED5 5 #define GITS_BASER_TYPE_RESERVED6 6 @@ -320,8 +319,6 @@ #define GITS_CMD_MAPD 0x08 #define GITS_CMD_MAPC 0x09 #define GITS_CMD_MAPTI 0x0a -/* older GIC documentation used MAPVI for this command */ -#define GITS_CMD_MAPVI GITS_CMD_MAPTI #define GITS_CMD_MAPI 0x0b #define GITS_CMD_MOVI 0x01 #define GITS_CMD_DISCARD 0x0f diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 589d14e970ad..624215cebee5 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -293,6 +293,8 @@ static inline u64 jiffies_to_nsecs(const unsigned long j) return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC; } +extern u64 jiffies64_to_nsecs(u64 j); + extern unsigned long __msecs_to_jiffies(const unsigned int m); #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) /* diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index a0547c571800..b63d6b7b0db0 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -402,6 +402,6 @@ extern bool ____wrong_branch_error(void); #define static_branch_enable(x) static_key_enable(&(x)->key) #define static_branch_disable(x) static_key_disable(&(x)->key) -#endif /* _LINUX_JUMP_LABEL_H */ - #endif /* __ASSEMBLY__ */ + +#endif /* _LINUX_JUMP_LABEL_H */ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 00f776816aa3..66be8b6beceb 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -9,7 +9,6 @@ #include <linux/sched.h> #include <linux/vtime.h> #include <asm/irq.h> -#include <linux/cputime.h> /* * 'kernel_stat.h' contains the definitions needed for doing @@ -78,15 +77,18 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu) return kstat_cpu(cpu).irqs_sum; } -extern void account_user_time(struct task_struct *, cputime_t); -extern void account_system_time(struct task_struct *, int, cputime_t); -extern void account_steal_time(cputime_t); -extern void account_idle_time(cputime_t); +extern void account_user_time(struct task_struct *, u64); +extern void account_guest_time(struct task_struct *, u64); +extern void account_system_time(struct task_struct *, int, u64); +extern void account_system_index_time(struct task_struct *, u64, + enum cpu_usage_stat); +extern void account_steal_time(u64); +extern void account_idle_time(u64); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE static inline void account_process_tick(struct task_struct *tsk, int user) { - vtime_account_user(tsk); + vtime_flush(tsk); } #else extern void account_process_tick(struct task_struct *, int user); diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8f6849084248..16ddfb8b304a 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -278,9 +278,13 @@ struct kprobe_insn_cache { int nr_garbage; }; +#ifdef __ARCH_WANT_KPROBES_INSN_SLOT extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c); extern void __free_insn_slot(struct kprobe_insn_cache *c, kprobe_opcode_t *slot, int dirty); +/* sleep-less address checking routine */ +extern bool __is_insn_slot_addr(struct kprobe_insn_cache *c, + unsigned long addr); #define DEFINE_INSN_CACHE_OPS(__name) \ extern struct kprobe_insn_cache kprobe_##__name##_slots; \ @@ -294,6 +298,18 @@ static inline void free_##__name##_slot(kprobe_opcode_t *slot, int dirty)\ { \ __free_insn_slot(&kprobe_##__name##_slots, slot, dirty); \ } \ + \ +static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ +{ \ + return __is_insn_slot_addr(&kprobe_##__name##_slots, addr); \ +} +#else /* __ARCH_WANT_KPROBES_INSN_SLOT */ +#define DEFINE_INSN_CACHE_OPS(__name) \ +static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ +{ \ + return 0; \ +} +#endif DEFINE_INSN_CACHE_OPS(insn); @@ -330,7 +346,6 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif - #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, @@ -481,6 +496,19 @@ static inline int enable_jprobe(struct jprobe *jp) return enable_kprobe(&jp->kp); } +#ifndef CONFIG_KPROBES +static inline bool is_kprobe_insn_slot(unsigned long addr) +{ + return false; +} +#endif +#ifndef CONFIG_OPTPROBES +static inline bool is_kprobe_optinsn_slot(unsigned long addr) +{ + return false; +} +#endif + #ifdef CONFIG_KPROBES /* * Blacklist ganerating macro. Specify functions which is not probed diff --git a/include/linux/kref.h b/include/linux/kref.h index e15828fd71f1..f4156f88f557 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -15,22 +15,27 @@ #ifndef _KREF_H_ #define _KREF_H_ -#include <linux/bug.h> -#include <linux/atomic.h> -#include <linux/kernel.h> -#include <linux/mutex.h> +#include <linux/spinlock.h> +#include <linux/refcount.h> struct kref { - atomic_t refcount; + refcount_t refcount; }; +#define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } + /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { - atomic_set(&kref->refcount, 1); + refcount_set(&kref->refcount, 1); +} + +static inline unsigned int kref_read(const struct kref *kref) +{ + return refcount_read(&kref->refcount); } /** @@ -39,17 +44,12 @@ static inline void kref_init(struct kref *kref) */ static inline void kref_get(struct kref *kref) { - /* If refcount was 0 before incrementing then we have a race - * condition when this kref is freeing by some other thread right now. - * In this case one should use kref_get_unless_zero() - */ - WARN_ON_ONCE(atomic_inc_return(&kref->refcount) < 2); + refcount_inc(&kref->refcount); } /** - * kref_sub - subtract a number of refcounts for object. + * kref_put - decrement refcount for object. * @kref: object. - * @count: Number of recounts to subtract. * @release: pointer to the function that will clean up the object when the * last reference to the object is released. * This pointer is required, and it is not acceptable to pass kfree @@ -58,57 +58,43 @@ static inline void kref_get(struct kref *kref) * maintainer, and anyone else who happens to notice it. You have * been warned. * - * Subtract @count from the refcount, and if 0, call release(). + * Decrement the refcount, and if 0, call release(). * Return 1 if the object was removed, otherwise return 0. Beware, if this * function returns 0, you still can not count on the kref from remaining in * memory. Only use the return value if you want to see if the kref is now * gone, not present. */ -static inline int kref_sub(struct kref *kref, unsigned int count, - void (*release)(struct kref *kref)) +static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { WARN_ON(release == NULL); - if (atomic_sub_and_test((int) count, &kref->refcount)) { + if (refcount_dec_and_test(&kref->refcount)) { release(kref); return 1; } return 0; } -/** - * kref_put - decrement refcount for object. - * @kref: object. - * @release: pointer to the function that will clean up the object when the - * last reference to the object is released. - * This pointer is required, and it is not acceptable to pass kfree - * in as this function. If the caller does pass kfree to this - * function, you will be publicly mocked mercilessly by the kref - * maintainer, and anyone else who happens to notice it. You have - * been warned. - * - * Decrement the refcount, and if 0, call release(). - * Return 1 if the object was removed, otherwise return 0. Beware, if this - * function returns 0, you still can not count on the kref from remaining in - * memory. Only use the return value if you want to see if the kref is now - * gone, not present. - */ -static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) -{ - return kref_sub(kref, 1, release); -} - static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) { WARN_ON(release == NULL); - if (unlikely(!atomic_add_unless(&kref->refcount, -1, 1))) { - mutex_lock(lock); - if (unlikely(!atomic_dec_and_test(&kref->refcount))) { - mutex_unlock(lock); - return 0; - } + + if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) { + release(kref); + return 1; + } + return 0; +} + +static inline int kref_put_lock(struct kref *kref, + void (*release)(struct kref *kref), + spinlock_t *lock) +{ + WARN_ON(release == NULL); + + if (refcount_dec_and_lock(&kref->refcount, lock)) { release(kref); return 1; } @@ -133,6 +119,6 @@ static inline int kref_put_mutex(struct kref *kref, */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { - return atomic_add_unless(&kref->refcount, 1, 0); + return refcount_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */ diff --git a/include/linux/llist.h b/include/linux/llist.h index fd4ca0b4fe0f..171baa90f6f6 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -3,28 +3,33 @@ /* * Lock-less NULL terminated single linked list * - * If there are multiple producers and multiple consumers, llist_add - * can be used in producers and llist_del_all can be used in - * consumers. They can work simultaneously without lock. But - * llist_del_first can not be used here. Because llist_del_first - * depends on list->first->next does not changed if list->first is not - * changed during its operation, but llist_del_first, llist_add, - * llist_add (or llist_del_all, llist_add, llist_add) sequence in - * another consumer may violate that. - * - * If there are multiple producers and one consumer, llist_add can be - * used in producers and llist_del_all or llist_del_first can be used - * in the consumer. - * - * This can be summarized as follow: + * Cases where locking is not needed: + * If there are multiple producers and multiple consumers, llist_add can be + * used in producers and llist_del_all can be used in consumers simultaneously + * without locking. Also a single consumer can use llist_del_first while + * multiple producers simultaneously use llist_add, without any locking. + * + * Cases where locking is needed: + * If we have multiple consumers with llist_del_first used in one consumer, and + * llist_del_first or llist_del_all used in other consumers, then a lock is + * needed. This is because llist_del_first depends on list->first->next not + * changing, but without lock protection, there's no way to be sure about that + * if a preemption happens in the middle of the delete operation and on being + * preempted back, the list->first is the same as before causing the cmpxchg in + * llist_del_first to succeed. For example, while a llist_del_first operation + * is in progress in one consumer, then a llist_del_first, llist_add, + * llist_add (or llist_del_all, llist_add, llist_add) sequence in another + * consumer may cause violations. + * + * This can be summarized as follows: * * | add | del_first | del_all * add | - | - | - * del_first | | L | L * del_all | | | - * - * Where "-" stands for no lock is needed, while "L" stands for lock - * is needed. + * Where, a particular row's operation can happen concurrently with a column's + * operation, with "-" being no lock needed, while "L" being lock is needed. * * The list entries deleted via llist_del_all can be traversed with * traversing function such as llist_for_each etc. But the list diff --git a/include/linux/math64.h b/include/linux/math64.h index 6e8b5b270ffe..80690c96c734 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -133,6 +133,16 @@ __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) return ret; } +#ifndef mul_u32_u32 +/* + * Many a GCC version messes this up and generates a 64x64 mult :-( + */ +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + return (u64)a * b; +} +#endif + #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__) #ifndef mul_u64_u32_shr @@ -160,9 +170,9 @@ static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) al = a; ah = a >> 32; - ret = ((u64)al * mul) >> shift; + ret = mul_u32_u32(al, mul) >> shift; if (ah) - ret += ((u64)ah * mul) << (32 - shift); + ret += mul_u32_u32(ah, mul) << (32 - shift); return ret; } @@ -186,10 +196,10 @@ static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift) a0.ll = a; b0.ll = b; - rl.ll = (u64)a0.l.low * b0.l.low; - rm.ll = (u64)a0.l.low * b0.l.high; - rn.ll = (u64)a0.l.high * b0.l.low; - rh.ll = (u64)a0.l.high * b0.l.high; + rl.ll = mul_u32_u32(a0.l.low, b0.l.low); + rm.ll = mul_u32_u32(a0.l.low, b0.l.high); + rn.ll = mul_u32_u32(a0.l.high, b0.l.low); + rh.ll = mul_u32_u32(a0.l.high, b0.l.high); /* * Each of these lines computes a 64-bit intermediate result into "c", @@ -229,8 +239,8 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } u, rl, rh; u.ll = a; - rl.ll = (u64)u.l.low * mul; - rh.ll = (u64)u.l.high * mul + rl.l.high; + rl.ll = mul_u32_u32(u.l.low, mul); + rh.ll = mul_u32_u32(u.l.high, mul) + rl.l.high; /* Bits 32-63 of the result will be in rh.l.low. */ rl.l.high = do_div(rh.ll, divisor); diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index a4860bc9b73d..f848ee86a339 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -13,7 +13,7 @@ #include <linux/regmap.h> -enum { +enum axp20x_variants { AXP152_ID = 0, AXP202_ID, AXP209_ID, @@ -532,35 +532,6 @@ struct axp20x_dev { const struct regmap_irq_chip *regmap_irq_chip; }; -#define BATTID_LEN 64 -#define OCV_CURVE_SIZE 32 -#define MAX_THERM_CURVE_SIZE 25 -#define PD_DEF_MIN_TEMP 0 -#define PD_DEF_MAX_TEMP 55 - -struct axp20x_fg_pdata { - char battid[BATTID_LEN + 1]; - int design_cap; - int min_volt; - int max_volt; - int max_temp; - int min_temp; - int cap1; - int cap0; - int rdc1; - int rdc0; - int ocv_curve[OCV_CURVE_SIZE]; - int tcsz; - int thermistor_curve[MAX_THERM_CURVE_SIZE][2]; -}; - -struct axp20x_chrg_pdata { - int max_cc; - int max_cv; - int def_cc; - int def_cv; -}; - struct axp288_extcon_pdata { /* GPIO pin control to switch D+/D- lines b/w PMIC and SOC */ struct gpio_desc *gpio_mux_cntl; diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h index 2b300b44f994..fba8fcb54f8c 100644 --- a/include/linux/mfd/lpc_ich.h +++ b/include/linux/mfd/lpc_ich.h @@ -20,6 +20,8 @@ #ifndef LPC_ICH_H #define LPC_ICH_H +#include <linux/platform_data/intel-spi.h> + /* GPIO resources */ #define ICH_RES_GPIO 0 #define ICH_RES_GPE0 1 @@ -40,6 +42,7 @@ struct lpc_ich_info { char name[32]; unsigned int iTCO_version; unsigned int gpio_version; + enum intel_spi_type spi_type; u8 use_gpio; }; diff --git a/include/linux/msi.h b/include/linux/msi.h index 0db320b7bb15..a83b84ff70e5 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -17,7 +17,13 @@ struct msi_desc; struct pci_dev; struct platform_msi_priv_data; void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); +#ifdef CONFIG_GENERIC_MSI_IRQ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); +#else +static inline void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) +{ +} +#endif typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc, struct msi_msg *msg); @@ -116,11 +122,15 @@ struct msi_desc { struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); void *msi_desc_to_pci_sysdata(struct msi_desc *desc); +void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); #else /* CONFIG_PCI_MSI */ static inline void *msi_desc_to_pci_sysdata(struct msi_desc *desc) { return NULL; } +static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) +{ +} #endif /* CONFIG_PCI_MSI */ struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, @@ -128,7 +138,6 @@ struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, void free_msi_entry(struct msi_desc *entry); void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); -void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag); u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h deleted file mode 100644 index ad3c3488073c..000000000000 --- a/include/linux/mtd/fsmc.h +++ /dev/null @@ -1,156 +0,0 @@ -/* - * incude/mtd/fsmc.h - * - * ST Microelectronics - * Flexible Static Memory Controller (FSMC) - * platform data interface and header file - * - * Copyright © 2010 ST Microelectronics - * Vipin Kumar <vipin.kumar@st.com> - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - */ - -#ifndef __MTD_FSMC_H -#define __MTD_FSMC_H - -#include <linux/io.h> -#include <linux/platform_device.h> -#include <linux/mtd/physmap.h> -#include <linux/types.h> -#include <linux/mtd/partitions.h> -#include <asm/param.h> - -#define FSMC_NAND_BW8 1 -#define FSMC_NAND_BW16 2 - -#define FSMC_MAX_NOR_BANKS 4 -#define FSMC_MAX_NAND_BANKS 4 - -#define FSMC_FLASH_WIDTH8 1 -#define FSMC_FLASH_WIDTH16 2 - -/* fsmc controller registers for NOR flash */ -#define CTRL 0x0 - /* ctrl register definitions */ - #define BANK_ENABLE (1 << 0) - #define MUXED (1 << 1) - #define NOR_DEV (2 << 2) - #define WIDTH_8 (0 << 4) - #define WIDTH_16 (1 << 4) - #define RSTPWRDWN (1 << 6) - #define WPROT (1 << 7) - #define WRT_ENABLE (1 << 12) - #define WAIT_ENB (1 << 13) - -#define CTRL_TIM 0x4 - /* ctrl_tim register definitions */ - -#define FSMC_NOR_BANK_SZ 0x8 -#define FSMC_NOR_REG_SIZE 0x40 - -#define FSMC_NOR_REG(base, bank, reg) (base + \ - FSMC_NOR_BANK_SZ * (bank) + \ - reg) - -/* fsmc controller registers for NAND flash */ -#define PC 0x00 - /* pc register definitions */ - #define FSMC_RESET (1 << 0) - #define FSMC_WAITON (1 << 1) - #define FSMC_ENABLE (1 << 2) - #define FSMC_DEVTYPE_NAND (1 << 3) - #define FSMC_DEVWID_8 (0 << 4) - #define FSMC_DEVWID_16 (1 << 4) - #define FSMC_ECCEN (1 << 6) - #define FSMC_ECCPLEN_512 (0 << 7) - #define FSMC_ECCPLEN_256 (1 << 7) - #define FSMC_TCLR_1 (1) - #define FSMC_TCLR_SHIFT (9) - #define FSMC_TCLR_MASK (0xF) - #define FSMC_TAR_1 (1) - #define FSMC_TAR_SHIFT (13) - #define FSMC_TAR_MASK (0xF) -#define STS 0x04 - /* sts register definitions */ - #define FSMC_CODE_RDY (1 << 15) -#define COMM 0x08 - /* comm register definitions */ - #define FSMC_TSET_0 0 - #define FSMC_TSET_SHIFT 0 - #define FSMC_TSET_MASK 0xFF - #define FSMC_TWAIT_6 6 - #define FSMC_TWAIT_SHIFT 8 - #define FSMC_TWAIT_MASK 0xFF - #define FSMC_THOLD_4 4 - #define FSMC_THOLD_SHIFT 16 - #define FSMC_THOLD_MASK 0xFF - #define FSMC_THIZ_1 1 - #define FSMC_THIZ_SHIFT 24 - #define FSMC_THIZ_MASK 0xFF -#define ATTRIB 0x0C -#define IOATA 0x10 -#define ECC1 0x14 -#define ECC2 0x18 -#define ECC3 0x1C -#define FSMC_NAND_BANK_SZ 0x20 - -#define FSMC_NAND_REG(base, bank, reg) (base + FSMC_NOR_REG_SIZE + \ - (FSMC_NAND_BANK_SZ * (bank)) + \ - reg) - -#define FSMC_BUSY_WAIT_TIMEOUT (1 * HZ) - -struct fsmc_nand_timings { - uint8_t tclr; - uint8_t tar; - uint8_t thiz; - uint8_t thold; - uint8_t twait; - uint8_t tset; -}; - -enum access_mode { - USE_DMA_ACCESS = 1, - USE_WORD_ACCESS, -}; - -/** - * fsmc_nand_platform_data - platform specific NAND controller config - * @nand_timings: timing setup for the physical NAND interface - * @partitions: partition table for the platform, use a default fallback - * if this is NULL - * @nr_partitions: the number of partitions in the previous entry - * @options: different options for the driver - * @width: bus width - * @bank: default bank - * @select_bank: callback to select a certain bank, this is - * platform-specific. If the controller only supports one bank - * this may be set to NULL - */ -struct fsmc_nand_platform_data { - struct fsmc_nand_timings *nand_timings; - struct mtd_partition *partitions; - unsigned int nr_partitions; - unsigned int options; - unsigned int width; - unsigned int bank; - - enum access_mode mode; - - void (*select_bank)(uint32_t bank, uint32_t busw); - - /* priv structures for dma accesses */ - void *read_dma_priv; - void *write_dma_priv; -}; - -extern int __init fsmc_nor_init(struct platform_device *pdev, - unsigned long base, uint32_t bank, uint32_t width); -extern void __init fsmc_init_board_info(struct platform_device *pdev, - struct mtd_partition *partitions, unsigned int nr_partitions, - unsigned int width); - -#endif /* __MTD_FSMC_H */ diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 13f8052b9ff9..eebdc63cf6af 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -24,6 +24,7 @@ #include <linux/uio.h> #include <linux/notifier.h> #include <linux/device.h> +#include <linux/of.h> #include <mtd/mtd-abi.h> @@ -322,6 +323,7 @@ struct mtd_info { int (*_block_isreserved) (struct mtd_info *mtd, loff_t ofs); int (*_block_isbad) (struct mtd_info *mtd, loff_t ofs); int (*_block_markbad) (struct mtd_info *mtd, loff_t ofs); + int (*_max_bad_blocks) (struct mtd_info *mtd, loff_t ofs, size_t len); int (*_suspend) (struct mtd_info *mtd); void (*_resume) (struct mtd_info *mtd); void (*_reboot) (struct mtd_info *mtd); @@ -385,6 +387,8 @@ static inline void mtd_set_of_node(struct mtd_info *mtd, struct device_node *np) { mtd->dev.of_node = np; + if (!mtd->name) + of_property_read_string(np, "label", &mtd->name); } static inline struct device_node *mtd_get_of_node(struct mtd_info *mtd) @@ -397,6 +401,18 @@ static inline int mtd_oobavail(struct mtd_info *mtd, struct mtd_oob_ops *ops) return ops->mode == MTD_OPS_AUTO_OOB ? mtd->oobavail : mtd->oobsize; } +static inline int mtd_max_bad_blocks(struct mtd_info *mtd, + loff_t ofs, size_t len) +{ + if (!mtd->_max_bad_blocks) + return -ENOTSUPP; + + if (mtd->size < (len + ofs) || ofs < 0) + return -EINVAL; + + return mtd->_max_bad_blocks(mtd, ofs, len); +} + int mtd_wunit_to_pairing_info(struct mtd_info *mtd, int wunit, struct mtd_pairing_info *info); int mtd_pairing_info_to_wunit(struct mtd_info *mtd, diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index c5f3a012ae62..9591e0fbe5bd 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -615,7 +615,7 @@ struct nand_buffers { * @tALS_min: ALE setup time * @tAR_min: ALE to RE# delay * @tCEA_max: CE# access time - * @tCEH_min: + * @tCEH_min: CE# high hold time * @tCH_min: CE# hold time * @tCHZ_max: CE# high to output hi-Z * @tCLH_min: CLE hold time @@ -801,6 +801,10 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) * supported, 0 otherwise. * @jedec_params: [INTERN] holds the JEDEC parameter page when JEDEC is * supported, 0 otherwise. + * @max_bb_per_die: [INTERN] the max number of bad blocks each die of a + * this nand device will encounter their life times. + * @blocks_per_die: [INTERN] The number of PEBs in a die + * @data_interface: [INTERN] NAND interface timing information * @read_retries: [INTERN] the number of read retry modes supported * @onfi_set_features: [REPLACEABLE] set the features for ONFI nand * @onfi_get_features: [REPLACEABLE] get the features for ONFI nand @@ -883,6 +887,8 @@ struct nand_chip { struct nand_onfi_params onfi_params; struct nand_jedec_params jedec_params; }; + u16 max_bb_per_die; + u32 blocks_per_die; struct nand_data_interface *data_interface; @@ -958,6 +964,7 @@ static inline void nand_set_controller_data(struct nand_chip *chip, void *priv) #define NAND_MFR_SANDISK 0x45 #define NAND_MFR_INTEL 0x89 #define NAND_MFR_ATO 0x9b +#define NAND_MFR_WINBOND 0xef /* The maximum expected count of bytes in the NAND ID sequence */ #define NAND_MAX_ID_LEN 8 diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 70736e1e6c8f..06df1e06b6e0 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -41,6 +41,7 @@ struct mtd_partition { uint64_t size; /* partition size */ uint64_t offset; /* offset within the master MTD space */ uint32_t mask_flags; /* master MTD flags to mask out for this partition */ + struct device_node *of_node; }; #define MTDPART_OFS_RETAIN (-3) diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index c425c7b4c2a0..f2a718030476 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -43,9 +43,13 @@ #define SPINOR_OP_WRSR 0x01 /* Write status register 1 byte */ #define SPINOR_OP_READ 0x03 /* Read data bytes (low frequency) */ #define SPINOR_OP_READ_FAST 0x0b /* Read data bytes (high frequency) */ -#define SPINOR_OP_READ_1_1_2 0x3b /* Read data bytes (Dual SPI) */ -#define SPINOR_OP_READ_1_1_4 0x6b /* Read data bytes (Quad SPI) */ +#define SPINOR_OP_READ_1_1_2 0x3b /* Read data bytes (Dual Output SPI) */ +#define SPINOR_OP_READ_1_2_2 0xbb /* Read data bytes (Dual I/O SPI) */ +#define SPINOR_OP_READ_1_1_4 0x6b /* Read data bytes (Quad Output SPI) */ +#define SPINOR_OP_READ_1_4_4 0xeb /* Read data bytes (Quad I/O SPI) */ #define SPINOR_OP_PP 0x02 /* Page program (up to 256 bytes) */ +#define SPINOR_OP_PP_1_1_4 0x32 /* Quad page program */ +#define SPINOR_OP_PP_1_4_4 0x38 /* Quad page program */ #define SPINOR_OP_BE_4K 0x20 /* Erase 4KiB block */ #define SPINOR_OP_BE_4K_PMC 0xd7 /* Erase 4KiB block on PMC chips */ #define SPINOR_OP_BE_32K 0x52 /* Erase 32KiB block */ @@ -56,11 +60,17 @@ #define SPINOR_OP_RDFSR 0x70 /* Read flag status register */ /* 4-byte address opcodes - used on Spansion and some Macronix flashes. */ -#define SPINOR_OP_READ4 0x13 /* Read data bytes (low frequency) */ -#define SPINOR_OP_READ4_FAST 0x0c /* Read data bytes (high frequency) */ -#define SPINOR_OP_READ4_1_1_2 0x3c /* Read data bytes (Dual SPI) */ -#define SPINOR_OP_READ4_1_1_4 0x6c /* Read data bytes (Quad SPI) */ +#define SPINOR_OP_READ_4B 0x13 /* Read data bytes (low frequency) */ +#define SPINOR_OP_READ_FAST_4B 0x0c /* Read data bytes (high frequency) */ +#define SPINOR_OP_READ_1_1_2_4B 0x3c /* Read data bytes (Dual Output SPI) */ +#define SPINOR_OP_READ_1_2_2_4B 0xbc /* Read data bytes (Dual I/O SPI) */ +#define SPINOR_OP_READ_1_1_4_4B 0x6c /* Read data bytes (Quad Output SPI) */ +#define SPINOR_OP_READ_1_4_4_4B 0xec /* Read data bytes (Quad I/O SPI) */ #define SPINOR_OP_PP_4B 0x12 /* Page program (up to 256 bytes) */ +#define SPINOR_OP_PP_1_1_4_4B 0x34 /* Quad page program */ +#define SPINOR_OP_PP_1_4_4_4B 0x3e /* Quad page program */ +#define SPINOR_OP_BE_4K_4B 0x21 /* Erase 4KiB block */ +#define SPINOR_OP_BE_32K_4B 0x5c /* Erase 32KiB block */ #define SPINOR_OP_SE_4B 0xdc /* Sector erase (usually 64KiB) */ /* Used for SST flashes only. */ @@ -68,6 +78,15 @@ #define SPINOR_OP_WRDI 0x04 /* Write disable */ #define SPINOR_OP_AAI_WP 0xad /* Auto address increment word program */ +/* Used for S3AN flashes only */ +#define SPINOR_OP_XSE 0x50 /* Sector erase */ +#define SPINOR_OP_XPP 0x82 /* Page program */ +#define SPINOR_OP_XRDSR 0xd7 /* Read status register */ + +#define XSR_PAGESIZE BIT(0) /* Page size in Po2 or Linear */ +#define XSR_RDY BIT(7) /* Ready */ + + /* Used for Macronix and Winbond flashes. */ #define SPINOR_OP_EN4B 0xb7 /* Enter 4-byte mode */ #define SPINOR_OP_EX4B 0xe9 /* Exit 4-byte mode */ @@ -119,6 +138,9 @@ enum spi_nor_ops { enum spi_nor_option_flags { SNOR_F_USE_FSR = BIT(0), SNOR_F_HAS_SR_TB = BIT(1), + SNOR_F_NO_OP_CHIP_ERASE = BIT(2), + SNOR_F_S3AN_ADDR_DEFAULT = BIT(3), + SNOR_F_READY_XSR_RDY = BIT(4), }; /** diff --git a/include/linux/mutex.h b/include/linux/mutex.h index b97870f2debd..1127fe31645d 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -20,6 +20,8 @@ #include <linux/osq_lock.h> #include <linux/debug_locks.h> +struct ww_acquire_ctx; + /* * Simple, straightforward mutexes with strict semantics: * @@ -65,7 +67,7 @@ struct mutex { static inline struct task_struct *__mutex_owner(struct mutex *lock) { - return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x03); + return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x07); } /* @@ -75,6 +77,7 @@ static inline struct task_struct *__mutex_owner(struct mutex *lock) struct mutex_waiter { struct list_head list; struct task_struct *task; + struct ww_acquire_ctx *ww_ctx; #ifdef CONFIG_DEBUG_MUTEXES void *magic; #endif @@ -156,10 +159,12 @@ extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass); extern int __must_check mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass); +extern void mutex_lock_io_nested(struct mutex *lock, unsigned int subclass); #define mutex_lock(lock) mutex_lock_nested(lock, 0) #define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0) #define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0) +#define mutex_lock_io(lock) mutex_lock_io_nested(lock, 0) #define mutex_lock_nest_lock(lock, nest_lock) \ do { \ @@ -171,11 +176,13 @@ do { \ extern void mutex_lock(struct mutex *lock); extern int __must_check mutex_lock_interruptible(struct mutex *lock); extern int __must_check mutex_lock_killable(struct mutex *lock); +extern void mutex_lock_io(struct mutex *lock); # define mutex_lock_nested(lock, subclass) mutex_lock(lock) # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock) # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock) # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) +# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock) #endif /* diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 5b2e6159b744..93664f022ecf 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -4,15 +4,15 @@ #include <linux/atomic.h> #include <linux/rwsem.h> #include <linux/percpu.h> -#include <linux/wait.h> +#include <linux/rcuwait.h> #include <linux/rcu_sync.h> #include <linux/lockdep.h> struct percpu_rw_semaphore { struct rcu_sync rss; unsigned int __percpu *read_count; - struct rw_semaphore rw_sem; - wait_queue_head_t writer; + struct rw_semaphore rw_sem; /* slowpath */ + struct rcuwait writer; /* blocked writer */ int readers_block; }; @@ -22,7 +22,7 @@ static struct percpu_rw_semaphore name = { \ .rss = __RCU_SYNC_INITIALIZER(name.rss, RCU_SCHED_SYNC), \ .read_count = &__percpu_rwsem_rc_##name, \ .rw_sem = __RWSEM_INITIALIZER(name.rw_sem), \ - .writer = __WAIT_QUEUE_HEAD_INITIALIZER(name.writer), \ + .writer = __RCUWAIT_INITIALIZER(name.writer), \ } extern int __percpu_down_read(struct percpu_rw_semaphore *, int); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 78ed8105e64d..000fdb211c7d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -482,6 +482,7 @@ struct perf_addr_filter { * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. + * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). @@ -489,6 +490,7 @@ struct perf_addr_filter { struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; + unsigned int nr_file_filters; }; /** @@ -785,9 +787,9 @@ struct perf_cpu_context { ktime_t hrtimer_interval; unsigned int hrtimer_active; - struct pmu *unique_pmu; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; + struct list_head cgrp_cpuctx_entry; #endif struct list_head sched_cb_entry; diff --git a/include/linux/platform_data/intel-spi.h b/include/linux/platform_data/intel-spi.h new file mode 100644 index 000000000000..942b0c3f8f08 --- /dev/null +++ b/include/linux/platform_data/intel-spi.h @@ -0,0 +1,31 @@ +/* + * Intel PCH/PCU SPI flash driver. + * + * Copyright (C) 2016, Intel Corporation + * Author: Mika Westerberg <mika.westerberg@linux.intel.com> + * + * 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. + */ + +#ifndef INTEL_SPI_PDATA_H +#define INTEL_SPI_PDATA_H + +enum intel_spi_type { + INTEL_SPI_BYT = 1, + INTEL_SPI_LPT, + INTEL_SPI_BXT, +}; + +/** + * struct intel_spi_boardinfo - Board specific data for Intel SPI driver + * @type: Type which this controller is compatible with + * @writeable: The chip is writeable + */ +struct intel_spi_boardinfo { + enum intel_spi_type type; + bool writeable; +}; + +#endif /* INTEL_SPI_PDATA_H */ diff --git a/include/linux/poison.h b/include/linux/poison.h index 51334edec506..a39540326417 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -80,6 +80,7 @@ /********** kernel/mutexes **********/ #define MUTEX_DEBUG_INIT 0x11 #define MUTEX_DEBUG_FREE 0x22 +#define MUTEX_POISON_WW_CTX ((void *) 0x500 + POISON_POINTER_DELTA) /********** lib/flex_array.c **********/ #define FLEX_ARRAY_FREE 0x6c /* for use-after-free poisoning */ diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 62d44c176071..64aa189efe21 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -8,19 +8,9 @@ #include <linux/alarmtimer.h> -static inline unsigned long long cputime_to_expires(cputime_t expires) -{ - return (__force unsigned long long)expires; -} - -static inline cputime_t expires_to_cputime(unsigned long long expires) -{ - return (__force cputime_t)expires; -} - struct cpu_timer_list { struct list_head entry; - unsigned long long expires, incr; + u64 expires, incr; struct task_struct *task; int firing; }; @@ -129,7 +119,7 @@ void run_posix_cpu_timers(struct task_struct *task); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, - cputime_t *newval, cputime_t *oldval); + u64 *newval, u64 *oldval); long clock_nanosleep_restart(struct restart_block *restart_block); diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index bed9557b69e7..b312bcef53da 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -4,8 +4,16 @@ enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ - BQ27500, /* bq27500 */ - BQ27510, /* bq27510, bq27520 */ + BQ2750X, /* bq27500 deprecated alias */ + BQ2751X, /* bq27510, bq27520 deprecated alias */ + BQ27500, /* bq27500/1 */ + BQ27510G1, /* bq27510G1 */ + BQ27510G2, /* bq27510G2 */ + BQ27510G3, /* bq27510G3 */ + BQ27520G1, /* bq27520G1 */ + BQ27520G2, /* bq27520G2 */ + BQ27520G3, /* bq27520G3 */ + BQ27520G4, /* bq27520G4 */ BQ27530, /* bq27530, bq27531 */ BQ27541, /* bq27541, bq27542, bq27546, bq27742 */ BQ27545, /* bq27545 */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 01f71e1d2e94..6ade6a52d9d4 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -1161,5 +1161,17 @@ do { \ ftrace_dump(oops_dump_mode); \ } while (0) +/* + * Place this after a lock-acquisition primitive to guarantee that + * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies + * if the UNLOCK and LOCK are executed by the same CPU or if the + * UNLOCK and LOCK operate on the same lock variable. + */ +#ifdef CONFIG_PPC +#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ +#else /* #ifdef CONFIG_PPC */ +#define smp_mb__after_unlock_lock() do { } while (0) +#endif /* #else #ifdef CONFIG_PPC */ + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index ac81e4063b40..4f9b2fa2173d 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,6 +27,12 @@ #include <linux/cache.h> +struct rcu_dynticks; +static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) +{ + return 0; +} + static inline unsigned long get_state_synchronize_rcu(void) { return 0; diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h new file mode 100644 index 000000000000..a4ede51b3e7c --- /dev/null +++ b/include/linux/rcuwait.h @@ -0,0 +1,63 @@ +#ifndef _LINUX_RCUWAIT_H_ +#define _LINUX_RCUWAIT_H_ + +#include <linux/rcupdate.h> + +/* + * rcuwait provides a way of blocking and waking up a single + * task in an rcu-safe manner; where it is forbidden to use + * after exit_notify(). task_struct is not properly rcu protected, + * unless dealing with rcu-aware lists, ie: find_task_by_*(). + * + * Alternatively we have task_rcu_dereference(), but the return + * semantics have different implications which would break the + * wakeup side. The only time @task is non-nil is when a user is + * blocked (or checking if it needs to) on a condition, and reset + * as soon as we know that the condition has succeeded and are + * awoken. + */ +struct rcuwait { + struct task_struct *task; +}; + +#define __RCUWAIT_INITIALIZER(name) \ + { .task = NULL, } + +static inline void rcuwait_init(struct rcuwait *w) +{ + w->task = NULL; +} + +extern void rcuwait_wake_up(struct rcuwait *w); + +/* + * The caller is responsible for locking around rcuwait_wait_event(), + * such that writes to @task are properly serialized. + */ +#define rcuwait_wait_event(w, condition) \ +({ \ + /* \ + * Complain if we are called after do_exit()/exit_notify(), \ + * as we cannot rely on the rcu critical region for the \ + * wakeup side. \ + */ \ + WARN_ON(current->exit_state); \ + \ + rcu_assign_pointer((w)->task, current); \ + for (;;) { \ + /* \ + * Implicit barrier (A) pairs with (B) in \ + * rcuwait_wake_up(). \ + */ \ + set_current_state(TASK_UNINTERRUPTIBLE); \ + if (condition) \ + break; \ + \ + schedule(); \ + } \ + \ + WRITE_ONCE((w)->task, NULL); \ + __set_current_state(TASK_RUNNING); \ +}) + +#endif /* _LINUX_RCUWAIT_H_ */ diff --git a/include/linux/refcount.h b/include/linux/refcount.h new file mode 100644 index 000000000000..600aadf9cca4 --- /dev/null +++ b/include/linux/refcount.h @@ -0,0 +1,294 @@ +#ifndef _LINUX_REFCOUNT_H +#define _LINUX_REFCOUNT_H + +/* + * Variant of atomic_t specialized for reference counts. + * + * The interface matches the atomic_t interface (to aid in porting) but only + * provides the few functions one should use for reference counting. + * + * It differs in that the counter saturates at UINT_MAX and will not move once + * there. This avoids wrapping the counter and causing 'spurious' + * use-after-free issues. + * + * Memory ordering rules are slightly relaxed wrt regular atomic_t functions + * and provide only what is strictly required for refcounts. + * + * The increments are fully relaxed; these will not provide ordering. The + * rationale is that whatever is used to obtain the object we're increasing the + * reference count on will provide the ordering. For locked data structures, + * its the lock acquire, for RCU/lockless data structures its the dependent + * load. + * + * Do note that inc_not_zero() provides a control dependency which will order + * future stores against the inc, this ensures we'll never modify the object + * if we did not in fact acquire a reference. + * + * The decrements will provide release order, such that all the prior loads and + * stores will be issued before, it also provides a control dependency, which + * will order us against the subsequent free(). + * + * The control dependency is against the load of the cmpxchg (ll/sc) that + * succeeded. This means the stores aren't fully ordered, but this is fine + * because the 1->0 transition indicates no concurrency. + * + * Note that the allocator is responsible for ordering things between free() + * and alloc(). + * + */ + +#include <linux/atomic.h> +#include <linux/bug.h> +#include <linux/mutex.h> +#include <linux/spinlock.h> + +#ifdef CONFIG_DEBUG_REFCOUNT +#define REFCOUNT_WARN(cond, str) WARN_ON(cond) +#define __refcount_check __must_check +#else +#define REFCOUNT_WARN(cond, str) (void)(cond) +#define __refcount_check +#endif + +typedef struct refcount_struct { + atomic_t refs; +} refcount_t; + +#define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } + +static inline void refcount_set(refcount_t *r, unsigned int n) +{ + atomic_set(&r->refs, n); +} + +static inline unsigned int refcount_read(const refcount_t *r) +{ + return atomic_read(&r->refs); +} + +static inline __refcount_check +bool refcount_add_not_zero(unsigned int i, refcount_t *r) +{ + unsigned int old, new, val = atomic_read(&r->refs); + + for (;;) { + if (!val) + return false; + + if (unlikely(val == UINT_MAX)) + return true; + + new = val + i; + if (new < val) + new = UINT_MAX; + old = atomic_cmpxchg_relaxed(&r->refs, val, new); + if (old == val) + break; + + val = old; + } + + REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); + + return true; +} + +static inline void refcount_add(unsigned int i, refcount_t *r) +{ + REFCOUNT_WARN(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); +} + +/* + * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + */ +static inline __refcount_check +bool refcount_inc_not_zero(refcount_t *r) +{ + unsigned int old, new, val = atomic_read(&r->refs); + + for (;;) { + new = val + 1; + + if (!val) + return false; + + if (unlikely(!new)) + return true; + + old = atomic_cmpxchg_relaxed(&r->refs, val, new); + if (old == val) + break; + + val = old; + } + + REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); + + return true; +} + +/* + * Similar to atomic_inc(), will saturate at UINT_MAX and WARN. + * + * Provides no memory ordering, it is assumed the caller already has a + * reference on the object, will WARN when this is not so. + */ +static inline void refcount_inc(refcount_t *r) +{ + REFCOUNT_WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); +} + +/* + * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to + * decrement when saturated at UINT_MAX. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides a control dependency such that free() must come after. + * See the comment on top. + */ +static inline __refcount_check +bool refcount_sub_and_test(unsigned int i, refcount_t *r) +{ + unsigned int old, new, val = atomic_read(&r->refs); + + for (;;) { + if (unlikely(val == UINT_MAX)) + return false; + + new = val - i; + if (new > val) { + REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n"); + return false; + } + + old = atomic_cmpxchg_release(&r->refs, val, new); + if (old == val) + break; + + val = old; + } + + return !new; +} + +static inline __refcount_check +bool refcount_dec_and_test(refcount_t *r) +{ + return refcount_sub_and_test(1, r); +} + +/* + * Similar to atomic_dec(), it will WARN on underflow and fail to decrement + * when saturated at UINT_MAX. + * + * Provides release memory ordering, such that prior loads and stores are done + * before. + */ +static inline +void refcount_dec(refcount_t *r) +{ + REFCOUNT_WARN(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); +} + +/* + * No atomic_t counterpart, it attempts a 1 -> 0 transition and returns the + * success thereof. + * + * Like all decrement operations, it provides release memory order and provides + * a control dependency. + * + * It can be used like a try-delete operator; this explicit case is provided + * and not cmpxchg in generic, because that would allow implementing unsafe + * operations. + */ +static inline __refcount_check +bool refcount_dec_if_one(refcount_t *r) +{ + return atomic_cmpxchg_release(&r->refs, 1, 0) == 1; +} + +/* + * No atomic_t counterpart, it decrements unless the value is 1, in which case + * it will return false. + * + * Was often done like: atomic_add_unless(&var, -1, 1) + */ +static inline __refcount_check +bool refcount_dec_not_one(refcount_t *r) +{ + unsigned int old, new, val = atomic_read(&r->refs); + + for (;;) { + if (unlikely(val == UINT_MAX)) + return true; + + if (val == 1) + return false; + + new = val - 1; + if (new > val) { + REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n"); + return true; + } + + old = atomic_cmpxchg_release(&r->refs, val, new); + if (old == val) + break; + + val = old; + } + + return true; +} + +/* + * Similar to atomic_dec_and_mutex_lock(), it will WARN on underflow and fail + * to decrement when saturated at UINT_MAX. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides a control dependency such that free() must come after. + * See the comment on top. + */ +static inline __refcount_check +bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock) +{ + if (refcount_dec_not_one(r)) + return false; + + mutex_lock(lock); + if (!refcount_dec_and_test(r)) { + mutex_unlock(lock); + return false; + } + + return true; +} + +/* + * Similar to atomic_dec_and_lock(), it will WARN on underflow and fail to + * decrement when saturated at UINT_MAX. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides a control dependency such that free() must come after. + * See the comment on top. + */ +static inline __refcount_check +bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) +{ + if (refcount_dec_not_one(r)) + return false; + + spin_lock(lock); + if (!refcount_dec_and_test(r)) { + spin_unlock(lock); + return false; + } + + return true; +} + +#endif /* _LINUX_REFCOUNT_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index ad3ec9ec61f7..c8e519d0b4a3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -29,7 +29,6 @@ struct sched_param { #include <asm/page.h> #include <asm/ptrace.h> -#include <linux/cputime.h> #include <linux/smp.h> #include <linux/sem.h> @@ -227,7 +226,7 @@ extern void proc_sched_set_task(struct task_struct *p); extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; -/* Convenience macros for the sake of set_task_state */ +/* Convenience macros for the sake of set_current_state */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) #define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) @@ -254,17 +253,6 @@ extern char ___assert_task_state[1 - 2*!!( #ifdef CONFIG_DEBUG_ATOMIC_SLEEP -#define __set_task_state(tsk, state_value) \ - do { \ - (tsk)->task_state_change = _THIS_IP_; \ - (tsk)->state = (state_value); \ - } while (0) -#define set_task_state(tsk, state_value) \ - do { \ - (tsk)->task_state_change = _THIS_IP_; \ - smp_store_mb((tsk)->state, (state_value)); \ - } while (0) - #define __set_current_state(state_value) \ do { \ current->task_state_change = _THIS_IP_; \ @@ -277,20 +265,6 @@ extern char ___assert_task_state[1 - 2*!!( } while (0) #else - -/* - * @tsk had better be current, or you get to keep the pieces. - * - * The only reason is that computing current can be more expensive than - * using a pointer that's already available. - * - * Therefore, see set_current_state(). - */ -#define __set_task_state(tsk, state_value) \ - do { (tsk)->state = (state_value); } while (0) -#define set_task_state(tsk, state_value) \ - smp_store_mb((tsk)->state, (state_value)) - /* * set_current_state() includes a barrier so that the write of current->state * is correctly serialised wrt the caller's subsequent test of whether to @@ -461,12 +435,10 @@ extern signed long schedule_timeout_idle(signed long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); +extern int __must_check io_schedule_prepare(void); +extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); - -static inline void io_schedule(void) -{ - io_schedule_timeout(MAX_SCHEDULE_TIMEOUT); -} +extern void io_schedule(void); void __noreturn do_task_dead(void); @@ -565,15 +537,13 @@ struct pacct_struct { int ac_flag; long ac_exitcode; unsigned long ac_mem; - cputime_t ac_utime, ac_stime; + u64 ac_utime, ac_stime; unsigned long ac_minflt, ac_majflt; }; struct cpu_itimer { - cputime_t expires; - cputime_t incr; - u32 error; - u32 incr_error; + u64 expires; + u64 incr; }; /** @@ -587,8 +557,8 @@ struct cpu_itimer { */ struct prev_cputime { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE - cputime_t utime; - cputime_t stime; + u64 utime; + u64 stime; raw_spinlock_t lock; #endif }; @@ -603,8 +573,8 @@ static inline void prev_cputime_init(struct prev_cputime *prev) /** * struct task_cputime - collected CPU time counts - * @utime: time spent in user mode, in &cputime_t units - * @stime: time spent in kernel mode, in &cputime_t units + * @utime: time spent in user mode, in nanoseconds + * @stime: time spent in kernel mode, in nanoseconds * @sum_exec_runtime: total time spent on the CPU, in nanoseconds * * This structure groups together three kinds of CPU time that are tracked for @@ -612,8 +582,8 @@ static inline void prev_cputime_init(struct prev_cputime *prev) * these counts together and treat all three of them in parallel. */ struct task_cputime { - cputime_t utime; - cputime_t stime; + u64 utime; + u64 stime; unsigned long long sum_exec_runtime; }; @@ -622,13 +592,6 @@ struct task_cputime { #define prof_exp stime #define sched_exp sum_exec_runtime -#define INIT_CPUTIME \ - (struct task_cputime) { \ - .utime = 0, \ - .stime = 0, \ - .sum_exec_runtime = 0, \ - } - /* * This is the atomic variant of task_cputime, which can be used for * storing and updating task_cputime statistics without locking. @@ -734,13 +697,14 @@ struct signal_struct { unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; +#ifdef CONFIG_POSIX_TIMERS + /* POSIX.1b Interval Timers */ int posix_timer_id; struct list_head posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; - struct pid *leader_pid; ktime_t it_real_incr; /* @@ -759,12 +723,16 @@ struct signal_struct { /* Earliest-expiration cache. */ struct task_cputime cputime_expires; + struct list_head cpu_timers[3]; + +#endif + + struct pid *leader_pid; + #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif - struct list_head cpu_timers[3]; - struct pid *tty_old_pgrp; /* boolean value for session group leader */ @@ -782,9 +750,9 @@ struct signal_struct { * in __exit_signal, except for the group leader. */ seqlock_t stats_lock; - cputime_t utime, stime, cutime, cstime; - cputime_t gtime; - cputime_t cgtime; + u64 utime, stime, cutime, cstime; + u64 gtime; + u64 cgtime; struct prev_cputime prev_cputime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; @@ -1025,8 +993,8 @@ enum cpu_idle_type { * * The DEFINE_WAKE_Q macro declares and initializes the list head. * wake_up_q() does NOT reinitialize the list; it's expected to be - * called near the end of a function, where the fact that the queue is - * not used again will be easy to see by inspection. + * called near the end of a function. Otherwise, the list can be + * re-initialized for later re-use by wake_q_init(). * * Note that this can cause spurious wakeups. schedule() callers * must ensure the call is done inside a loop, confirming that the @@ -1046,6 +1014,12 @@ struct wake_q_head { #define DEFINE_WAKE_Q(name) \ struct wake_q_head name = { WAKE_Q_TAIL, &name.first } +static inline void wake_q_init(struct wake_q_head *head) +{ + head->first = WAKE_Q_TAIL; + head->lastp = &head->first; +} + extern void wake_q_add(struct wake_q_head *head, struct task_struct *task); extern void wake_up_q(struct wake_q_head *head); @@ -1663,11 +1637,11 @@ struct task_struct { int __user *set_child_tid; /* CLONE_CHILD_SETTID */ int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */ - cputime_t utime, stime; + u64 utime, stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME - cputime_t utimescaled, stimescaled; + u64 utimescaled, stimescaled; #endif - cputime_t gtime; + u64 gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_t vtime_seqcount; @@ -1691,8 +1665,10 @@ struct task_struct { /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; +#ifdef CONFIG_POSIX_TIMERS struct task_cputime cputime_expires; struct list_head cpu_timers[3]; +#endif /* process credentials */ const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */ @@ -1817,7 +1793,7 @@ struct task_struct { #if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ - cputime_t acct_timexpd; /* stime + utime since last update */ + u64 acct_timexpd; /* stime + utime since last update */ #endif #ifdef CONFIG_CPUSETS nodemask_t mems_allowed; /* Protected by alloc_lock */ @@ -2262,17 +2238,17 @@ struct task_struct *try_get_task_struct(struct task_struct **ptask); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void task_cputime(struct task_struct *t, - cputime_t *utime, cputime_t *stime); -extern cputime_t task_gtime(struct task_struct *t); + u64 *utime, u64 *stime); +extern u64 task_gtime(struct task_struct *t); #else static inline void task_cputime(struct task_struct *t, - cputime_t *utime, cputime_t *stime) + u64 *utime, u64 *stime) { *utime = t->utime; *stime = t->stime; } -static inline cputime_t task_gtime(struct task_struct *t) +static inline u64 task_gtime(struct task_struct *t) { return t->gtime; } @@ -2280,23 +2256,23 @@ static inline cputime_t task_gtime(struct task_struct *t) #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME static inline void task_cputime_scaled(struct task_struct *t, - cputime_t *utimescaled, - cputime_t *stimescaled) + u64 *utimescaled, + u64 *stimescaled) { *utimescaled = t->utimescaled; *stimescaled = t->stimescaled; } #else static inline void task_cputime_scaled(struct task_struct *t, - cputime_t *utimescaled, - cputime_t *stimescaled) + u64 *utimescaled, + u64 *stimescaled) { task_cputime(t, utimescaled, stimescaled); } #endif -extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); -extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); +extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st); +extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st); /* * Per process flags @@ -2515,10 +2491,18 @@ extern u64 sched_clock_cpu(int cpu); extern void sched_clock_init(void); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK +static inline void sched_clock_init_late(void) +{ +} + static inline void sched_clock_tick(void) { } +static inline void clear_sched_clock_stable(void) +{ +} + static inline void sched_clock_idle_sleep_event(void) { } @@ -2537,6 +2521,7 @@ static inline u64 local_clock(void) return sched_clock(); } #else +extern void sched_clock_init_late(void); /* * Architectures can set this to 1 if they have specified * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig, @@ -2544,7 +2529,6 @@ static inline u64 local_clock(void) * is reliable after all: */ extern int sched_clock_stable(void); -extern void set_sched_clock_stable(void); extern void clear_sched_clock_stable(void); extern void sched_clock_tick(void); diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 441145351301..49308e142aae 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -59,6 +59,7 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice; extern unsigned int sysctl_sched_autogroup_enabled; #endif +extern int sysctl_sched_rr_timeslice; extern int sched_rr_timeslice; extern int sched_rr_handler(struct ctl_table *table, int write, diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 47dd0cebd204..59248dcc6ef3 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -180,8 +180,6 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock_nested(lock, subclass) -# define raw_spin_lock_bh_nested(lock, subclass) \ - _raw_spin_lock_bh_nested(lock, subclass) # define raw_spin_lock_nest_lock(lock, nest_lock) \ do { \ @@ -197,7 +195,6 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock(((void)(subclass), (lock))) # define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock) -# define raw_spin_lock_bh_nested(lock, subclass) _raw_spin_lock_bh(lock) #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) @@ -317,11 +314,6 @@ do { \ raw_spin_lock_nested(spinlock_check(lock), subclass); \ } while (0) -#define spin_lock_bh_nested(lock, subclass) \ -do { \ - raw_spin_lock_bh_nested(spinlock_check(lock), subclass);\ -} while (0) - #define spin_lock_nest_lock(lock, nest_lock) \ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 5344268e6e62..42dfab89e740 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -22,8 +22,6 @@ int in_lock_functions(unsigned long addr); void __lockfunc _raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) __acquires(lock); -void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass) - __acquires(lock); void __lockfunc _raw_spin_lock_nest_lock(raw_spinlock_t *lock, struct lockdep_map *map) __acquires(lock); diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h index d3afef9d8dbe..d0d188861ad6 100644 --- a/include/linux/spinlock_api_up.h +++ b/include/linux/spinlock_api_up.h @@ -57,7 +57,6 @@ #define _raw_spin_lock(lock) __LOCK(lock) #define _raw_spin_lock_nested(lock, subclass) __LOCK(lock) -#define _raw_spin_lock_bh_nested(lock, subclass) __LOCK(lock) #define _raw_read_lock(lock) __LOCK(lock) #define _raw_write_lock(lock) __LOCK(lock) #define _raw_spin_lock_bh(lock) __LOCK_BH(lock) diff --git a/include/linux/srcu.h b/include/linux/srcu.h index dc8eb63c6568..a598cf3ac70c 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -33,9 +33,9 @@ #include <linux/rcupdate.h> #include <linux/workqueue.h> -struct srcu_struct_array { - unsigned long c[2]; - unsigned long seq[2]; +struct srcu_array { + unsigned long lock_count[2]; + unsigned long unlock_count[2]; }; struct rcu_batch { @@ -46,7 +46,7 @@ struct rcu_batch { struct srcu_struct { unsigned long completed; - struct srcu_struct_array __percpu *per_cpu_ref; + struct srcu_array __percpu *per_cpu_ref; spinlock_t queue_lock; /* protect ->batch_queue, ->running */ bool running; /* callbacks just queued */ @@ -118,7 +118,7 @@ void process_srcu(struct work_struct *work); * See include/linux/percpu-defs.h for the rules on per-CPU variables. */ #define __DEFINE_SRCU(name, is_static) \ - static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ + static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\ is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 62a60eeacb0a..8a511c0985aa 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -198,7 +198,7 @@ static inline struct cache_head *cache_get(struct cache_head *h) static inline void cache_put(struct cache_head *h, struct cache_detail *cd) { - if (atomic_read(&h->ref.refcount) <= 2 && + if (kref_read(&h->ref) <= 2 && h->expiry_time < cd->nextcheck) cd->nextcheck = h->expiry_time; kref_put(&h->ref, cd->cache_put); diff --git a/include/linux/timer.h b/include/linux/timer.h index 51d601f192d4..5a209b84fd9e 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -20,11 +20,6 @@ struct timer_list { unsigned long data; u32 flags; -#ifdef CONFIG_TIMER_STATS - int start_pid; - void *start_site; - char start_comm[16]; -#endif #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif @@ -197,46 +192,6 @@ extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); */ #define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1) -/* - * Timer-statistics info: - */ -#ifdef CONFIG_TIMER_STATS - -extern int timer_stats_active; - -extern void init_timer_stats(void); - -extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf, - void *timerf, char *comm, u32 flags); - -extern void __timer_stats_timer_set_start_info(struct timer_list *timer, - void *addr); - -static inline void timer_stats_timer_set_start_info(struct timer_list *timer) -{ - if (likely(!timer_stats_active)) - return; - __timer_stats_timer_set_start_info(timer, __builtin_return_address(0)); -} - -static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) -{ - timer->start_site = NULL; -} -#else -static inline void init_timer_stats(void) -{ -} - -static inline void timer_stats_timer_set_start_info(struct timer_list *timer) -{ -} - -static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) -{ -} -#endif - extern void add_timer(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); diff --git a/include/linux/vtime.h b/include/linux/vtime.h index aa9bfea8804a..0681fe25abeb 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -58,27 +58,28 @@ static inline void vtime_task_switch(struct task_struct *prev) extern void vtime_account_system(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); -extern void vtime_account_user(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ static inline void vtime_task_switch(struct task_struct *prev) { } static inline void vtime_account_system(struct task_struct *tsk) { } -static inline void vtime_account_user(struct task_struct *tsk) { } #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void arch_vtime_task_switch(struct task_struct *tsk); +extern void vtime_account_user(struct task_struct *tsk); extern void vtime_user_enter(struct task_struct *tsk); static inline void vtime_user_exit(struct task_struct *tsk) { vtime_account_user(tsk); } + extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); extern void vtime_init_idle(struct task_struct *tsk, int cpu); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ +static inline void vtime_account_user(struct task_struct *tsk) { } static inline void vtime_user_enter(struct task_struct *tsk) { } static inline void vtime_user_exit(struct task_struct *tsk) { } static inline void vtime_guest_enter(struct task_struct *tsk) { } @@ -93,9 +94,11 @@ static inline void vtime_account_irq_exit(struct task_struct *tsk) /* On hard|softirq exit we always account to hard|softirq cputime */ vtime_account_system(tsk); } +extern void vtime_flush(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static inline void vtime_account_irq_enter(struct task_struct *tsk) { } static inline void vtime_account_irq_exit(struct task_struct *tsk) { } +static inline void vtime_flush(struct task_struct *tsk) { } #endif diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 7b0066814fa0..5dd9a7682227 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -51,10 +51,10 @@ struct ww_mutex { }; #ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class) \ - , .ww_class = &ww_class +# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) \ + , .ww_class = class #else -# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class) +# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) #endif #define __WW_CLASS_INITIALIZER(ww_class) \ @@ -63,7 +63,7 @@ struct ww_mutex { , .mutex_name = #ww_class "_mutex" } #define __WW_MUTEX_INITIALIZER(lockname, class) \ - { .base = { \__MUTEX_INITIALIZER(lockname) } \ + { .base = __MUTEX_INITIALIZER(lockname.base) \ __WW_CLASS_MUTEX_INITIALIZER(lockname, class) } #define DEFINE_WW_CLASS(classname) \ @@ -186,11 +186,6 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) #endif } -extern int __must_check __ww_mutex_lock(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx); -extern int __must_check __ww_mutex_lock_interruptible(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx); - /** * ww_mutex_lock - acquire the w/w mutex * @lock: the mutex to be acquired @@ -220,14 +215,7 @@ extern int __must_check __ww_mutex_lock_interruptible(struct ww_mutex *lock, * * A mutex acquired with this function must be released with ww_mutex_unlock. */ -static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) -{ - if (ctx) - return __ww_mutex_lock(lock, ctx); - - mutex_lock(&lock->base); - return 0; -} +extern int /* __must_check */ ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx); /** * ww_mutex_lock_interruptible - acquire the w/w mutex, interruptible @@ -259,14 +247,8 @@ static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ct * * A mutex acquired with this function must be released with ww_mutex_unlock. */ -static inline int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx) -{ - if (ctx) - return __ww_mutex_lock_interruptible(lock, ctx); - else - return mutex_lock_interruptible(&lock->base); -} +extern int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx); /** * ww_mutex_lock_slow - slowpath acquiring of the w/w mutex diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 554671c81f4a..90708f68cc02 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -987,7 +987,7 @@ static inline void hci_conn_drop(struct hci_conn *conn) static inline void hci_dev_put(struct hci_dev *d) { BT_DBG("%s orig refcnt %d", d->name, - atomic_read(&d->dev.kobj.kref.refcount)); + kref_read(&d->dev.kobj.kref)); put_device(&d->dev); } @@ -995,7 +995,7 @@ static inline void hci_dev_put(struct hci_dev *d) static inline struct hci_dev *hci_dev_hold(struct hci_dev *d) { BT_DBG("%s orig refcnt %d", d->name, - atomic_read(&d->dev.kobj.kref.refcount)); + kref_read(&d->dev.kobj.kref)); get_device(&d->dev); return d; diff --git a/include/soc/at91/at91sam9_ddrsdr.h b/include/soc/at91/at91sam9_ddrsdr.h index dc10c52e0e91..393362bdb860 100644 --- a/include/soc/at91/at91sam9_ddrsdr.h +++ b/include/soc/at91/at91sam9_ddrsdr.h @@ -81,6 +81,7 @@ #define AT91_DDRSDRC_LPCB_POWER_DOWN 2 #define AT91_DDRSDRC_LPCB_DEEP_POWER_DOWN 3 #define AT91_DDRSDRC_CLKFR (1 << 2) /* Clock Frozen */ +#define AT91_DDRSDRC_LPDDR2_PWOFF (1 << 3) /* LPDDR Power Off */ #define AT91_DDRSDRC_PASR (7 << 4) /* Partial Array Self Refresh */ #define AT91_DDRSDRC_TCSR (3 << 8) /* Temperature Compensated Self Refresh */ #define AT91_DDRSDRC_DS (3 << 10) /* Drive Strength */ @@ -96,7 +97,9 @@ #define AT91_DDRSDRC_MD_SDR 0 #define AT91_DDRSDRC_MD_LOW_POWER_SDR 1 #define AT91_DDRSDRC_MD_LOW_POWER_DDR 3 +#define AT91_DDRSDRC_MD_LPDDR3 5 #define AT91_DDRSDRC_MD_DDR2 6 /* [SAM9 Only] */ +#define AT91_DDRSDRC_MD_LPDDR2 7 #define AT91_DDRSDRC_DBW (1 << 4) /* Data Bus Width */ #define AT91_DDRSDRC_DBW_32BITS (0 << 4) #define AT91_DDRSDRC_DBW_16BITS (1 << 4) diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 9d4f9b3a2b7b..e3facb356838 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -385,11 +385,11 @@ TRACE_EVENT(rcu_quiescent_state_report, /* * 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, - * or "kick" when kicking a CPU that has been in dyntick-idle mode for - * too long. + * 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. */ TRACE_EVENT(rcu_fqs, diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 1448637616d6..1bca99dbb98f 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -269,17 +269,17 @@ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerval *const value, - cputime_t expires), + unsigned long long expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( - __field( int, which ) - __field( cputime_t, expires ) - __field( long, value_sec ) - __field( long, value_usec ) - __field( long, interval_sec ) - __field( long, interval_usec ) + __field( int, which ) + __field( unsigned long long, expires ) + __field( long, value_sec ) + __field( long, value_usec ) + __field( long, interval_sec ) + __field( long, interval_usec ) ), TP_fast_assign( @@ -292,7 +292,7 @@ TRACE_EVENT(itimer_state, ), TP_printk("which=%d expires=%llu it_value=%ld.%ld it_interval=%ld.%ld", - __entry->which, (unsigned long long)__entry->expires, + __entry->which, __entry->expires, __entry->value_sec, __entry->value_usec, __entry->interval_sec, __entry->interval_usec) ); @@ -305,14 +305,14 @@ TRACE_EVENT(itimer_state, */ TRACE_EVENT(itimer_expire, - TP_PROTO(int which, struct pid *pid, cputime_t now), + TP_PROTO(int which, struct pid *pid, unsigned long long now), TP_ARGS(which, pid, now), TP_STRUCT__entry( - __field( int , which ) - __field( pid_t, pid ) - __field( cputime_t, now ) + __field( int , which ) + __field( pid_t, pid ) + __field( unsigned long long, now ) ), TP_fast_assign( @@ -322,7 +322,7 @@ TRACE_EVENT(itimer_expire, ), TP_printk("which=%d pid=%d now=%llu", __entry->which, - (int) __entry->pid, (unsigned long long)__entry->now) + (int) __entry->pid, __entry->now) ); #ifdef CONFIG_NO_HZ_COMMON diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0eb0e87dbe9f..d2b0ac799d03 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -116,6 +116,12 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command + * to the given target_fd cgroup the descendent cgroup will be able to + * override effective bpf program that was inherited from this cgroup + */ +#define BPF_F_ALLOW_OVERRIDE (1U << 0) + #define BPF_PSEUDO_MAP_FD 1 /* flags for BPF_MAP_UPDATE_ELEM command */ @@ -171,6 +177,7 @@ union bpf_attr { __u32 target_fd; /* container object to attach to */ __u32 attach_bpf_fd; /* eBPF program to attach */ __u32 attach_type; + __u32 attach_flags; }; } __attribute__((aligned(8))); diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 85ddb74fcd1c..b23c1914a182 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -9,9 +9,8 @@ #include <linux/types.h> #include <linux/socket.h> -#ifndef __KERNEL__ -#include <netinet/in.h> -#endif +#include <linux/in.h> +#include <linux/in6.h> #define IPPROTO_L2TP 115 @@ -31,7 +30,7 @@ struct sockaddr_l2tpip { __u32 l2tp_conn_id; /* Connection ID of tunnel */ /* Pad to size of `struct sockaddr'. */ - unsigned char __pad[sizeof(struct sockaddr) - + unsigned char __pad[__SOCK_SIZE__ - sizeof(__kernel_sa_family_t) - sizeof(__be16) - sizeof(struct in_addr) - sizeof(__u32)]; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 46e8a2e369f9..45184a2ef66c 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -362,8 +362,8 @@ enum v4l2_quantization { /* * The default for R'G'B' quantization is always full range, except * for the BT2020 colorspace. For Y'CbCr the quantization is always - * limited range, except for COLORSPACE_JPEG, SRGB, ADOBERGB, - * XV601 or XV709: those are full range. + * limited range, except for COLORSPACE_JPEG, XV601 or XV709: those + * are full range. */ V4L2_QUANTIZATION_DEFAULT = 0, V4L2_QUANTIZATION_FULL_RANGE = 1, @@ -379,8 +379,7 @@ enum v4l2_quantization { (((is_rgb_or_hsv) && (colsp) == V4L2_COLORSPACE_BT2020) ? \ V4L2_QUANTIZATION_LIM_RANGE : \ (((is_rgb_or_hsv) || (ycbcr_enc) == V4L2_YCBCR_ENC_XV601 || \ - (ycbcr_enc) == V4L2_YCBCR_ENC_XV709 || (colsp) == V4L2_COLORSPACE_JPEG) || \ - (colsp) == V4L2_COLORSPACE_ADOBERGB || (colsp) == V4L2_COLORSPACE_SRGB ? \ + (ycbcr_enc) == V4L2_YCBCR_ENC_XV709 || (colsp) == V4L2_COLORSPACE_JPEG) ? \ V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE)) enum v4l2_priority { diff --git a/init/Kconfig b/init/Kconfig index 4dd8bd232a1d..2655abb8f310 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -529,7 +529,6 @@ config SRCU config TASKS_RCU bool default n - depends on !UML select SRCU help This option enables a task-based RCU implementation that uses @@ -781,19 +780,6 @@ config RCU_NOCB_CPU_ALL endchoice -config RCU_EXPEDITE_BOOT - bool - default n - help - This option enables expedited grace periods at boot time, - as if rcu_expedite_gp() had been invoked early in boot. - The corresponding rcu_unexpedite_gp() is invoked from - rcu_end_inkernel_boot(), which is intended to be invoked - at the end of the kernel-only boot sequence, just before - init is exec'ed. - - Accept the default if unsure. - endmenu # "RCU Subsystem" config BUILD_BIN2C diff --git a/init/main.c b/init/main.c index b0c9d6facef9..6ced14a3df12 100644 --- a/init/main.c +++ b/init/main.c @@ -625,7 +625,6 @@ asmlinkage __visible void __init start_kernel(void) numa_policy_init(); if (late_time_init) late_time_init(); - sched_clock_init(); calibrate_delay(); pidmap_init(); anon_vma_init(); @@ -663,7 +662,6 @@ asmlinkage __visible void __init start_kernel(void) sfi_init_late(); if (efi_enabled(EFI_RUNTIME_SERVICES)) { - efi_late_init(); efi_free_boot_services(); } diff --git a/init/version.c b/init/version.c index fe41a63efed6..5606341e9efd 100644 --- a/init/version.c +++ b/init/version.c @@ -23,9 +23,7 @@ int version_string(LINUX_VERSION_CODE); #endif struct uts_namespace init_uts_ns = { - .kref = { - .refcount = ATOMIC_INIT(2), - }, + .kref = KREF_INIT(2), .name = { .sysname = UTS_SYSNAME, .nodename = UTS_NODENAME, diff --git a/kernel/acct.c b/kernel/acct.c index 74963d192c5d..ca9cb55b5855 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -453,8 +453,8 @@ static void fill_ac(acct_t *ac) spin_lock_irq(¤t->sighand->siglock); tty = current->signal->tty; /* Safe as we hold the siglock */ ac->ac_tty = tty ? old_encode_dev(tty_devnum(tty)) : 0; - ac->ac_utime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_utime))); - ac->ac_stime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_stime))); + ac->ac_utime = encode_comp_t(nsec_to_AHZ(pacct->ac_utime)); + ac->ac_stime = encode_comp_t(nsec_to_AHZ(pacct->ac_stime)); ac->ac_flag = pacct->ac_flag; ac->ac_mem = encode_comp_t(pacct->ac_mem); ac->ac_minflt = encode_comp_t(pacct->ac_minflt); @@ -530,7 +530,7 @@ out: void acct_collect(long exitcode, int group_dead) { struct pacct_struct *pacct = ¤t->signal->pacct; - cputime_t utime, stime; + u64 utime, stime; unsigned long vsize = 0; if (group_dead && current->mm) { @@ -559,6 +559,7 @@ void acct_collect(long exitcode, int group_dead) pacct->ac_flag |= ACORE; if (current->flags & PF_SIGNALED) pacct->ac_flag |= AXSIG; + task_cputime(current, &utime, &stime); pacct->ac_utime += utime; pacct->ac_stime += stime; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index a515f7b007c6..da0f53690295 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -52,6 +52,7 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent) e = rcu_dereference_protected(parent->bpf.effective[type], lockdep_is_held(&cgroup_mutex)); rcu_assign_pointer(cgrp->bpf.effective[type], e); + cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type]; } } @@ -82,30 +83,63 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent) * * Must be called with cgroup_mutex held. */ -void __cgroup_bpf_update(struct cgroup *cgrp, - struct cgroup *parent, - struct bpf_prog *prog, - enum bpf_attach_type type) +int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, + struct bpf_prog *prog, enum bpf_attach_type type, + bool new_overridable) { - struct bpf_prog *old_prog, *effective; + struct bpf_prog *old_prog, *effective = NULL; struct cgroup_subsys_state *pos; + bool overridable = true; - old_prog = xchg(cgrp->bpf.prog + type, prog); + if (parent) { + overridable = !parent->bpf.disallow_override[type]; + effective = rcu_dereference_protected(parent->bpf.effective[type], + lockdep_is_held(&cgroup_mutex)); + } + + if (prog && effective && !overridable) + /* if parent has non-overridable prog attached, disallow + * attaching new programs to descendent cgroup + */ + return -EPERM; + + if (prog && effective && overridable != new_overridable) + /* if parent has overridable prog attached, only + * allow overridable programs in descendent cgroup + */ + return -EPERM; - effective = (!prog && parent) ? - rcu_dereference_protected(parent->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)) : - prog; + old_prog = cgrp->bpf.prog[type]; + + if (prog) { + overridable = new_overridable; + effective = prog; + if (old_prog && + cgrp->bpf.disallow_override[type] == new_overridable) + /* disallow attaching non-overridable on top + * of existing overridable in this cgroup + * and vice versa + */ + return -EPERM; + } + + if (!prog && !old_prog) + /* report error when trying to detach and nothing is attached */ + return -ENOENT; + + cgrp->bpf.prog[type] = prog; css_for_each_descendant_pre(pos, &cgrp->self) { struct cgroup *desc = container_of(pos, struct cgroup, self); /* skip the subtree if the descendant has its own program */ - if (desc->bpf.prog[type] && desc != cgrp) + if (desc->bpf.prog[type] && desc != cgrp) { pos = css_rightmost_descendant(pos); - else + } else { rcu_assign_pointer(desc->bpf.effective[type], effective); + desc->bpf.disallow_override[type] = !overridable; + } } if (prog) @@ -115,6 +149,7 @@ void __cgroup_bpf_update(struct cgroup *cgrp, bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); } + return 0; } /** diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 19b6129eab23..bbb016adbaeb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -920,13 +920,14 @@ static int bpf_obj_get(const union bpf_attr *attr) #ifdef CONFIG_CGROUP_BPF -#define BPF_PROG_ATTACH_LAST_FIELD attach_type +#define BPF_PROG_ATTACH_LAST_FIELD attach_flags static int bpf_prog_attach(const union bpf_attr *attr) { + enum bpf_prog_type ptype; struct bpf_prog *prog; struct cgroup *cgrp; - enum bpf_prog_type ptype; + int ret; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -934,6 +935,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; + if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE) + return -EINVAL; + switch (attr->attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: @@ -956,10 +960,13 @@ static int bpf_prog_attach(const union bpf_attr *attr) return PTR_ERR(cgrp); } - cgroup_bpf_update(cgrp, prog, attr->attach_type); + ret = cgroup_bpf_update(cgrp, prog, attr->attach_type, + attr->attach_flags & BPF_F_ALLOW_OVERRIDE); + if (ret) + bpf_prog_put(prog); cgroup_put(cgrp); - return 0; + return ret; } #define BPF_PROG_DETACH_LAST_FIELD attach_type @@ -967,6 +974,7 @@ static int bpf_prog_attach(const union bpf_attr *attr) static int bpf_prog_detach(const union bpf_attr *attr) { struct cgroup *cgrp; + int ret; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -982,7 +990,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) if (IS_ERR(cgrp)) return PTR_ERR(cgrp); - cgroup_bpf_update(cgrp, NULL, attr->attach_type); + ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false); cgroup_put(cgrp); break; @@ -990,7 +998,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) return -EINVAL; } - return 0; + return ret; } #endif /* CONFIG_CGROUP_BPF */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 688dd02af985..53bbca7c4859 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -6498,15 +6498,16 @@ static __init int cgroup_namespaces_init(void) subsys_initcall(cgroup_namespaces_init); #ifdef CONFIG_CGROUP_BPF -void cgroup_bpf_update(struct cgroup *cgrp, - struct bpf_prog *prog, - enum bpf_attach_type type) +int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, bool overridable) { struct cgroup *parent = cgroup_parent(cgrp); + int ret; mutex_lock(&cgroup_mutex); - __cgroup_bpf_update(cgrp, parent, prog, type); + ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable); mutex_unlock(&cgroup_mutex); + return ret; } #endif /* CONFIG_CGROUP_BPF */ diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 435c14a45118..660549656991 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -82,19 +82,19 @@ void __delayacct_blkio_end(void) int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) { - cputime_t utime, stime, stimescaled, utimescaled; + u64 utime, stime, stimescaled, utimescaled; unsigned long long t2, t3; unsigned long flags, t1; s64 tmp; task_cputime(tsk, &utime, &stime); tmp = (s64)d->cpu_run_real_total; - tmp += cputime_to_nsecs(utime + stime); + tmp += utime + stime; d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp; task_cputime_scaled(tsk, &utimescaled, &stimescaled); tmp = (s64)d->cpu_scaled_run_real_total; - tmp += cputime_to_nsecs(utimescaled + stimescaled); + tmp += utimescaled + stimescaled; d->cpu_scaled_run_real_total = (tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp; diff --git a/kernel/events/core.c b/kernel/events/core.c index e235bb991bdd..77a932b54a64 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -355,6 +355,8 @@ enum event_type_t { EVENT_FLEXIBLE = 0x1, EVENT_PINNED = 0x2, EVENT_TIME = 0x4, + /* see ctx_resched() for details */ + EVENT_CPU = 0x8, EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, }; @@ -678,6 +680,8 @@ perf_cgroup_set_timestamp(struct task_struct *task, info->timestamp = ctx->timestamp; } +static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list); + #define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */ #define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */ @@ -690,61 +694,46 @@ perf_cgroup_set_timestamp(struct task_struct *task, static void perf_cgroup_switch(struct task_struct *task, int mode) { struct perf_cpu_context *cpuctx; - struct pmu *pmu; + struct list_head *list; unsigned long flags; /* - * disable interrupts to avoid geting nr_cgroup - * changes via __perf_event_disable(). Also - * avoids preemption. + * Disable interrupts and preemption to avoid this CPU's + * cgrp_cpuctx_entry to change under us. */ local_irq_save(flags); - /* - * we reschedule only in the presence of cgroup - * constrained events. - */ + list = this_cpu_ptr(&cgrp_cpuctx_list); + list_for_each_entry(cpuctx, list, cgrp_cpuctx_entry) { + WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->unique_pmu != pmu) - continue; /* ensure we process each cpuctx once */ - - /* - * perf_cgroup_events says at least one - * context on this CPU has cgroup events. - * - * ctx->nr_cgroups reports the number of cgroup - * events for a context. - */ - if (cpuctx->ctx.nr_cgroups > 0) { - perf_ctx_lock(cpuctx, cpuctx->task_ctx); - perf_pmu_disable(cpuctx->ctx.pmu); + perf_ctx_lock(cpuctx, cpuctx->task_ctx); + perf_pmu_disable(cpuctx->ctx.pmu); - if (mode & PERF_CGROUP_SWOUT) { - cpu_ctx_sched_out(cpuctx, EVENT_ALL); - /* - * must not be done before ctxswout due - * to event_filter_match() in event_sched_out() - */ - cpuctx->cgrp = NULL; - } + if (mode & PERF_CGROUP_SWOUT) { + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + /* + * must not be done before ctxswout due + * to event_filter_match() in event_sched_out() + */ + cpuctx->cgrp = NULL; + } - if (mode & PERF_CGROUP_SWIN) { - WARN_ON_ONCE(cpuctx->cgrp); - /* - * set cgrp before ctxsw in to allow - * event_filter_match() to not have to pass - * task around - * we pass the cpuctx->ctx to perf_cgroup_from_task() - * because cgorup events are only per-cpu - */ - cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx); - cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); - } - perf_pmu_enable(cpuctx->ctx.pmu); - perf_ctx_unlock(cpuctx, cpuctx->task_ctx); + if (mode & PERF_CGROUP_SWIN) { + WARN_ON_ONCE(cpuctx->cgrp); + /* + * set cgrp before ctxsw in to allow + * event_filter_match() to not have to pass + * task around + * we pass the cpuctx->ctx to perf_cgroup_from_task() + * because cgorup events are only per-cpu + */ + cpuctx->cgrp = perf_cgroup_from_task(task, + &cpuctx->ctx); + cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); } + perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } local_irq_restore(flags); @@ -889,6 +878,7 @@ list_update_cgroup_event(struct perf_event *event, struct perf_event_context *ctx, bool add) { struct perf_cpu_context *cpuctx; + struct list_head *cpuctx_entry; if (!is_cgroup_event(event)) return; @@ -902,15 +892,16 @@ list_update_cgroup_event(struct perf_event *event, * this will always be called from the right CPU. */ cpuctx = __get_cpu_context(ctx); - - /* - * cpuctx->cgrp is NULL until a cgroup event is sched in or - * ctx->nr_cgroup == 0 . - */ - if (add && perf_cgroup_from_task(current, ctx) == event->cgrp) - cpuctx->cgrp = event->cgrp; - else if (!add) + cpuctx_entry = &cpuctx->cgrp_cpuctx_entry; + /* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/ + if (add) { + list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list)); + if (perf_cgroup_from_task(current, ctx) == event->cgrp) + cpuctx->cgrp = event->cgrp; + } else { + list_del(cpuctx_entry); cpuctx->cgrp = NULL; + } } #else /* !CONFIG_CGROUP_PERF */ @@ -1453,6 +1444,20 @@ static void update_group_times(struct perf_event *leader) update_event_times(event); } +static enum event_type_t get_event_type(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + enum event_type_t event_type; + + lockdep_assert_held(&ctx->lock); + + event_type = event->attr.pinned ? EVENT_PINNED : EVENT_FLEXIBLE; + if (!ctx->task) + event_type |= EVENT_CPU; + + return event_type; +} + static struct list_head * ctx_group_list(struct perf_event *event, struct perf_event_context *ctx) { @@ -2226,7 +2231,8 @@ ctx_sched_in(struct perf_event_context *ctx, struct task_struct *task); static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) + struct perf_event_context *ctx, + enum event_type_t event_type) { if (!cpuctx->task_ctx) return; @@ -2234,7 +2240,7 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) return; - ctx_sched_out(ctx, cpuctx, EVENT_ALL); + ctx_sched_out(ctx, cpuctx, event_type); } static void perf_event_sched_in(struct perf_cpu_context *cpuctx, @@ -2249,13 +2255,51 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx, ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); } +/* + * We want to maintain the following priority of scheduling: + * - CPU pinned (EVENT_CPU | EVENT_PINNED) + * - task pinned (EVENT_PINNED) + * - CPU flexible (EVENT_CPU | EVENT_FLEXIBLE) + * - task flexible (EVENT_FLEXIBLE). + * + * In order to avoid unscheduling and scheduling back in everything every + * time an event is added, only do it for the groups of equal priority and + * below. + * + * This can be called after a batch operation on task events, in which case + * event_type is a bit mask of the types of events involved. For CPU events, + * event_type is only either EVENT_PINNED or EVENT_FLEXIBLE. + */ static void ctx_resched(struct perf_cpu_context *cpuctx, - struct perf_event_context *task_ctx) + struct perf_event_context *task_ctx, + enum event_type_t event_type) { + enum event_type_t ctx_event_type = event_type & EVENT_ALL; + bool cpu_event = !!(event_type & EVENT_CPU); + + /* + * If pinned groups are involved, flexible groups also need to be + * scheduled out. + */ + if (event_type & EVENT_PINNED) + event_type |= EVENT_FLEXIBLE; + perf_pmu_disable(cpuctx->ctx.pmu); if (task_ctx) - task_ctx_sched_out(cpuctx, task_ctx); - cpu_ctx_sched_out(cpuctx, EVENT_ALL); + task_ctx_sched_out(cpuctx, task_ctx, event_type); + + /* + * Decide which cpu ctx groups to schedule out based on the types + * of events that caused rescheduling: + * - EVENT_CPU: schedule out corresponding groups; + * - EVENT_PINNED task events: schedule out EVENT_FLEXIBLE groups; + * - otherwise, do nothing more. + */ + if (cpu_event) + cpu_ctx_sched_out(cpuctx, ctx_event_type); + else if (ctx_event_type & EVENT_PINNED) + cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); + perf_event_sched_in(cpuctx, task_ctx, current); perf_pmu_enable(cpuctx->ctx.pmu); } @@ -2302,7 +2346,7 @@ static int __perf_install_in_context(void *info) if (reprogram) { ctx_sched_out(ctx, cpuctx, EVENT_TIME); add_event_to_ctx(event, ctx); - ctx_resched(cpuctx, task_ctx); + ctx_resched(cpuctx, task_ctx, get_event_type(event)); } else { add_event_to_ctx(event, ctx); } @@ -2469,7 +2513,7 @@ static void __perf_event_enable(struct perf_event *event, if (ctx->task) WARN_ON_ONCE(task_ctx != ctx); - ctx_resched(cpuctx, task_ctx); + ctx_resched(cpuctx, task_ctx, get_event_type(event)); } /* @@ -2896,7 +2940,7 @@ unlock: if (do_switch) { raw_spin_lock(&ctx->lock); - task_ctx_sched_out(cpuctx, ctx); + task_ctx_sched_out(cpuctx, ctx, EVENT_ALL); raw_spin_unlock(&ctx->lock); } } @@ -2943,7 +2987,7 @@ static void perf_pmu_sched_task(struct task_struct *prev, return; list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) { - pmu = cpuctx->unique_pmu; /* software PMUs will not have sched_task */ + pmu = cpuctx->ctx.pmu; /* software PMUs will not have sched_task */ if (WARN_ON_ONCE(!pmu->sched_task)) continue; @@ -3133,8 +3177,12 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, * We want to keep the following priority order: * cpu pinned (that don't need to move), task pinned, * cpu flexible, task flexible. + * + * However, if task's ctx is not carrying any pinned + * events, no need to flip the cpuctx's events around. */ - cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); + if (!list_empty(&ctx->pinned_groups)) + cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); perf_event_sched_in(cpuctx, ctx, task); perf_pmu_enable(ctx->pmu); perf_ctx_unlock(cpuctx, ctx); @@ -3449,6 +3497,7 @@ static int event_enable_on_exec(struct perf_event *event, static void perf_event_enable_on_exec(int ctxn) { struct perf_event_context *ctx, *clone_ctx = NULL; + enum event_type_t event_type = 0; struct perf_cpu_context *cpuctx; struct perf_event *event; unsigned long flags; @@ -3462,15 +3511,17 @@ static void perf_event_enable_on_exec(int ctxn) cpuctx = __get_cpu_context(ctx); perf_ctx_lock(cpuctx, ctx); ctx_sched_out(ctx, cpuctx, EVENT_TIME); - list_for_each_entry(event, &ctx->event_list, event_entry) + list_for_each_entry(event, &ctx->event_list, event_entry) { enabled |= event_enable_on_exec(event, ctx); + event_type |= get_event_type(event); + } /* * Unclone and reschedule this context if we enabled any event. */ if (enabled) { clone_ctx = unclone_ctx(ctx); - ctx_resched(cpuctx, ctx); + ctx_resched(cpuctx, ctx, event_type); } perf_ctx_unlock(cpuctx, ctx); @@ -8044,6 +8095,9 @@ static void perf_event_addr_filters_apply(struct perf_event *event) if (task == TASK_TOMBSTONE) return; + if (!ifh->nr_file_filters) + return; + mm = get_task_mm(event->ctx->task); if (!mm) goto restart; @@ -8214,6 +8268,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, * attribute. */ if (state == IF_STATE_END) { + ret = -EINVAL; if (kernel && event->attr.exclude_kernel) goto fail; @@ -8221,6 +8276,18 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, if (!filename) goto fail; + /* + * For now, we only support file-based filters + * in per-task events; doing so for CPU-wide + * events requires additional context switching + * trickery, since same object code will be + * mapped at different virtual addresses in + * different processes. + */ + ret = -EOPNOTSUPP; + if (!event->ctx->task) + goto fail_free_name; + /* look up the path and grab its inode */ ret = kern_path(filename, LOOKUP_FOLLOW, &path); if (ret) @@ -8236,6 +8303,8 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, !S_ISREG(filter->inode->i_mode)) /* free_filters_list() will iput() */ goto fail; + + event->addr_filters.nr_file_filters++; } /* ready to consume more filters */ @@ -8275,24 +8344,13 @@ perf_event_set_addr_filter(struct perf_event *event, char *filter_str) if (WARN_ON_ONCE(event->parent)) return -EINVAL; - /* - * For now, we only support filtering in per-task events; doing so - * for CPU-wide events requires additional context switching trickery, - * since same object code will be mapped at different virtual - * addresses in different processes. - */ - if (!event->ctx->task) - return -EOPNOTSUPP; - ret = perf_event_parse_addr_filter(event, filter_str, &filters); if (ret) - return ret; + goto fail_clear_files; ret = event->pmu->addr_filters_validate(&filters); - if (ret) { - free_filters_list(&filters); - return ret; - } + if (ret) + goto fail_free_filters; /* remove existing filters, if any */ perf_addr_filters_splice(event, &filters); @@ -8301,6 +8359,14 @@ perf_event_set_addr_filter(struct perf_event *event, char *filter_str) perf_event_for_each_child(event, perf_event_addr_filters_apply); return ret; + +fail_free_filters: + free_filters_list(&filters); + +fail_clear_files: + event->addr_filters.nr_file_filters = 0; + + return ret; } static int perf_event_set_filter(struct perf_event *event, void __user *arg) @@ -8652,37 +8718,10 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn) return NULL; } -static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct perf_cpu_context *cpuctx; - - cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); - - if (cpuctx->unique_pmu == old_pmu) - cpuctx->unique_pmu = pmu; - } -} - static void free_pmu_context(struct pmu *pmu) { - struct pmu *i; - mutex_lock(&pmus_lock); - /* - * Like a real lame refcount. - */ - list_for_each_entry(i, &pmus, entry) { - if (i->pmu_cpu_context == pmu->pmu_cpu_context) { - update_pmu_context(i, pmu); - goto out; - } - } - free_percpu(pmu->pmu_cpu_context); -out: mutex_unlock(&pmus_lock); } @@ -8886,8 +8925,6 @@ skip_type: cpuctx->ctx.pmu = pmu; __perf_mux_hrtimer_init(cpuctx, cpu); - - cpuctx->unique_pmu = pmu; } got_cpu_context: @@ -9005,6 +9042,14 @@ static struct pmu *perf_init_event(struct perf_event *event) idx = srcu_read_lock(&pmus_srcu); + /* Try parent's PMU first: */ + if (event->parent && event->parent->pmu) { + pmu = event->parent->pmu; + ret = perf_try_init_event(pmu, event); + if (!ret) + goto unlock; + } + rcu_read_lock(); pmu = idr_find(&pmu_idr, event->attr.type); rcu_read_unlock(); @@ -10265,7 +10310,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) * in. */ raw_spin_lock_irq(&child_ctx->lock); - task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx); + task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx, EVENT_ALL); /* * Now that the context is inactive, destroy the task <-> ctx relation @@ -10714,6 +10759,9 @@ static void __init perf_event_init_all_cpus(void) INIT_LIST_HEAD(&per_cpu(pmu_sb_events.list, cpu)); raw_spin_lock_init(&per_cpu(pmu_sb_events.lock, cpu)); +#ifdef CONFIG_CGROUP_PERF + INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu)); +#endif INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu)); } } diff --git a/kernel/exit.c b/kernel/exit.c index 8f14b866f9f6..b67c57faa705 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -55,6 +55,7 @@ #include <linux/shm.h> #include <linux/kcov.h> #include <linux/random.h> +#include <linux/rcuwait.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -86,7 +87,7 @@ static void __exit_signal(struct task_struct *tsk) bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *uninitialized_var(tty); - cputime_t utime, stime; + u64 utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); @@ -282,6 +283,35 @@ retry: return task; } +void rcuwait_wake_up(struct rcuwait *w) +{ + struct task_struct *task; + + rcu_read_lock(); + + /* + * Order condition vs @task, such that everything prior to the load + * of @task is visible. This is the condition as to why the user called + * rcuwait_trywake() in the first place. Pairs with set_current_state() + * barrier (A) in rcuwait_wait_event(). + * + * WAIT WAKE + * [S] tsk = current [S] cond = true + * MB (A) MB (B) + * [L] cond [L] tsk + */ + smp_rmb(); /* (B) */ + + /* + * Avoid using task_rcu_dereference() magic as long as we are careful, + * see comment in rcuwait_wait_event() regarding ->exit_state. + */ + task = rcu_dereference(w->task); + if (task) + wake_up_process(task); + rcu_read_unlock(); +} + struct task_struct *try_get_task_struct(struct task_struct **ptask) { struct task_struct *task; @@ -468,12 +498,12 @@ assign_new_owner: * Turn us into a lazy TLB process if we * aren't already.. */ -static void exit_mm(struct task_struct *tsk) +static void exit_mm(void) { - struct mm_struct *mm = tsk->mm; + struct mm_struct *mm = current->mm; struct core_state *core_state; - mm_release(tsk, mm); + mm_release(current, mm); if (!mm) return; sync_mm_rss(mm); @@ -491,7 +521,7 @@ static void exit_mm(struct task_struct *tsk) up_read(&mm->mmap_sem); - self.task = tsk; + self.task = current; self.next = xchg(&core_state->dumper.next, &self); /* * Implies mb(), the result of xchg() must be visible @@ -501,22 +531,22 @@ static void exit_mm(struct task_struct *tsk) complete(&core_state->startup); for (;;) { - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); if (!self.task) /* see coredump_finish() */ break; freezable_schedule(); } - __set_task_state(tsk, TASK_RUNNING); + __set_current_state(TASK_RUNNING); down_read(&mm->mmap_sem); } atomic_inc(&mm->mm_count); - BUG_ON(mm != tsk->active_mm); + BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ - task_lock(tsk); - tsk->mm = NULL; + task_lock(current); + current->mm = NULL; up_read(&mm->mmap_sem); enter_lazy_tlb(mm, current); - task_unlock(tsk); + task_unlock(current); mm_update_next_owner(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) @@ -823,7 +853,7 @@ void __noreturn do_exit(long code) tsk->exit_code = code; taskstats_exit(tsk, group_dead); - exit_mm(tsk); + exit_mm(); if (group_dead) acct_process(); @@ -1091,7 +1121,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) struct signal_struct *sig = p->signal; struct signal_struct *psig = current->signal; unsigned long maxrss; - cputime_t tgutime, tgstime; + u64 tgutime, tgstime; /* * The resource counters for the group leader are in its diff --git a/kernel/extable.c b/kernel/extable.c index e3beec4a2339..e1359474baa5 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -20,6 +20,7 @@ #include <linux/module.h> #include <linux/mutex.h> #include <linux/init.h> +#include <linux/kprobes.h> #include <asm/sections.h> #include <linux/uaccess.h> @@ -104,6 +105,8 @@ int __kernel_text_address(unsigned long addr) return 1; if (is_ftrace_trampoline(addr)) return 1; + if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) + return 1; /* * There might be init symbols in saved stacktraces. * Give those symbols a chance to be printed in @@ -123,7 +126,11 @@ int kernel_text_address(unsigned long addr) return 1; if (is_module_text_address(addr)) return 1; - return is_ftrace_trampoline(addr); + if (is_ftrace_trampoline(addr)) + return 1; + if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) + return 1; + return 0; } /* diff --git a/kernel/fork.c b/kernel/fork.c index 11c5c8ab827c..ff82e24573b6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -432,11 +432,13 @@ void __init fork_init(void) int i; #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR #ifndef ARCH_MIN_TASKALIGN -#define ARCH_MIN_TASKALIGN L1_CACHE_BYTES +#define ARCH_MIN_TASKALIGN 0 #endif + int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); + /* create a slab on which task_structs can be allocated */ task_struct_cachep = kmem_cache_create("task_struct", - arch_task_struct_size, ARCH_MIN_TASKALIGN, + arch_task_struct_size, align, SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, NULL); #endif @@ -1304,6 +1306,7 @@ void __cleanup_sighand(struct sighand_struct *sighand) } } +#ifdef CONFIG_POSIX_TIMERS /* * Initialize POSIX timer handling for a thread group. */ @@ -1313,7 +1316,7 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); if (cpu_limit != RLIM_INFINITY) { - sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit); + sig->cputime_expires.prof_exp = cpu_limit * NSEC_PER_SEC; sig->cputimer.running = true; } @@ -1322,6 +1325,9 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) INIT_LIST_HEAD(&sig->cpu_timers[1]); INIT_LIST_HEAD(&sig->cpu_timers[2]); } +#else +static inline void posix_cpu_timers_init_group(struct signal_struct *sig) { } +#endif static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { @@ -1346,11 +1352,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); - INIT_LIST_HEAD(&sig->posix_timers); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS + INIT_LIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif @@ -1425,6 +1431,7 @@ static void rt_mutex_init_task(struct task_struct *p) #endif } +#ifdef CONFIG_POSIX_TIMERS /* * Initialize POSIX timer handling for a single task. */ @@ -1437,6 +1444,9 @@ static void posix_cpu_timers_init(struct task_struct *tsk) INIT_LIST_HEAD(&tsk->cpu_timers[1]); INIT_LIST_HEAD(&tsk->cpu_timers[2]); } +#else +static inline void posix_cpu_timers_init(struct task_struct *tsk) { } +#endif static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) diff --git a/kernel/futex.c b/kernel/futex.c index 0842c8ca534b..cdf365036141 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3323,4 +3323,4 @@ static int __init futex_init(void) return 0; } -__initcall(futex_init); +core_initcall(futex_init); diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 74d90a754268..1613bfd48365 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -2,6 +2,7 @@ #include <linux/interrupt.h> #include <linux/device.h> #include <linux/gfp.h> +#include <linux/irq.h> /* * Device resource management aware IRQ request/free implementation. @@ -33,7 +34,7 @@ static int devm_irq_match(struct device *dev, void *res, void *data) * @thread_fn: function to be called in a threaded interrupt context. NULL * for devices which handle everything in @handler * @irqflags: Interrupt type flags - * @devname: An ascii name for the claiming device + * @devname: An ascii name for the claiming device, dev_name(dev) if NULL * @dev_id: A cookie passed back to the handler function * * Except for the extra @dev argument, this function takes the @@ -57,6 +58,9 @@ int devm_request_threaded_irq(struct device *dev, unsigned int irq, if (!dr) return -ENOMEM; + if (!devname) + devname = dev_name(dev); + rc = request_threaded_irq(irq, handler, thread_fn, irqflags, devname, dev_id); if (rc) { @@ -80,7 +84,7 @@ EXPORT_SYMBOL(devm_request_threaded_irq); * @thread_fn: function to be called in a threaded interrupt context. NULL * for devices which handle everything in @handler * @irqflags: Interrupt type flags - * @devname: An ascii name for the claiming device + * @devname: An ascii name for the claiming device, dev_name(dev) if NULL * @dev_id: A cookie passed back to the handler function * * Except for the extra @dev argument, this function takes the @@ -103,6 +107,9 @@ int devm_request_any_context_irq(struct device *dev, unsigned int irq, if (!dr) return -ENOMEM; + if (!devname) + devname = dev_name(dev); + rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id); if (rc < 0) { devres_free(dr); @@ -137,3 +144,57 @@ void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id) free_irq(irq, dev_id); } EXPORT_SYMBOL(devm_free_irq); + +struct irq_desc_devres { + unsigned int from; + unsigned int cnt; +}; + +static void devm_irq_desc_release(struct device *dev, void *res) +{ + struct irq_desc_devres *this = res; + + irq_free_descs(this->from, this->cnt); +} + +/** + * __devm_irq_alloc_descs - Allocate and initialize a range of irq descriptors + * for a managed device + * @dev: Device to allocate the descriptors for + * @irq: Allocate for specific irq number if irq >= 0 + * @from: Start the search from this irq number + * @cnt: Number of consecutive irqs to allocate + * @node: Preferred node on which the irq descriptor should be allocated + * @owner: Owning module (can be NULL) + * @affinity: Optional pointer to an affinity mask array of size @cnt + * which hints where the irq descriptors should be allocated + * and which default affinities to use + * + * Returns the first irq number or error code. + * + * Note: Use the provided wrappers (devm_irq_alloc_desc*) for simplicity. + */ +int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from, + unsigned int cnt, int node, struct module *owner, + const struct cpumask *affinity) +{ + struct irq_desc_devres *dr; + int base; + + dr = devres_alloc(devm_irq_desc_release, sizeof(*dr), GFP_KERNEL); + if (!dr) + return -ENOMEM; + + base = __irq_alloc_descs(irq, from, cnt, node, owner, affinity); + if (base < 0) { + devres_free(dr); + return base; + } + + dr->from = base; + dr->cnt = cnt; + devres_add(dev, dr); + + return base; +} +EXPORT_SYMBOL_GPL(__devm_irq_alloc_descs); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index feaa813b84a9..c53edad7b459 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -487,6 +487,8 @@ int show_interrupts(struct seq_file *p, void *v) } if (desc->irq_data.domain) seq_printf(p, " %*d", prec, (int) desc->irq_data.hwirq); + else + seq_printf(p, " %*s", prec, ""); #ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge"); #endif diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 5707f97a3e6a..061ba7eed4ed 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -175,7 +175,9 @@ out: static inline int bad_action_ret(irqreturn_t action_ret) { - if (likely(action_ret <= (IRQ_HANDLED | IRQ_WAKE_THREAD))) + unsigned int r = action_ret; + + if (likely(r <= (IRQ_HANDLED | IRQ_WAKE_THREAD))) return 0; return 1; } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 43460104f119..ebb4dadca66b 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -149,9 +149,11 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) struct kprobe_insn_page *kip; kprobe_opcode_t *slot = NULL; + /* Since the slot array is not protected by rcu, we need a mutex */ mutex_lock(&c->mutex); retry: - list_for_each_entry(kip, &c->pages, list) { + rcu_read_lock(); + list_for_each_entry_rcu(kip, &c->pages, list) { if (kip->nused < slots_per_page(c)) { int i; for (i = 0; i < slots_per_page(c); i++) { @@ -159,6 +161,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) kip->slot_used[i] = SLOT_USED; kip->nused++; slot = kip->insns + (i * c->insn_size); + rcu_read_unlock(); goto out; } } @@ -167,6 +170,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) WARN_ON(1); } } + rcu_read_unlock(); /* If there are any garbage slots, collect it and try again. */ if (c->nr_garbage && collect_garbage_slots(c) == 0) @@ -193,7 +197,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) kip->nused = 1; kip->ngarbage = 0; kip->cache = c; - list_add(&kip->list, &c->pages); + list_add_rcu(&kip->list, &c->pages); slot = kip->insns; out: mutex_unlock(&c->mutex); @@ -213,7 +217,8 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx) * next time somebody inserts a probe. */ if (!list_is_singular(&kip->list)) { - list_del(&kip->list); + list_del_rcu(&kip->list); + synchronize_rcu(); kip->cache->free(kip->insns); kfree(kip); } @@ -235,8 +240,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c) continue; kip->ngarbage = 0; /* we will collect all garbages */ for (i = 0; i < slots_per_page(c); i++) { - if (kip->slot_used[i] == SLOT_DIRTY && - collect_one_slot(kip, i)) + if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i)) break; } } @@ -248,29 +252,60 @@ void __free_insn_slot(struct kprobe_insn_cache *c, kprobe_opcode_t *slot, int dirty) { struct kprobe_insn_page *kip; + long idx; mutex_lock(&c->mutex); - list_for_each_entry(kip, &c->pages, list) { - long idx = ((long)slot - (long)kip->insns) / - (c->insn_size * sizeof(kprobe_opcode_t)); - if (idx >= 0 && idx < slots_per_page(c)) { - WARN_ON(kip->slot_used[idx] != SLOT_USED); - if (dirty) { - kip->slot_used[idx] = SLOT_DIRTY; - kip->ngarbage++; - if (++c->nr_garbage > slots_per_page(c)) - collect_garbage_slots(c); - } else - collect_one_slot(kip, idx); + rcu_read_lock(); + list_for_each_entry_rcu(kip, &c->pages, list) { + idx = ((long)slot - (long)kip->insns) / + (c->insn_size * sizeof(kprobe_opcode_t)); + if (idx >= 0 && idx < slots_per_page(c)) goto out; - } } - /* Could not free this slot. */ + /* Could not find this slot. */ WARN_ON(1); + kip = NULL; out: + rcu_read_unlock(); + /* Mark and sweep: this may sleep */ + if (kip) { + /* Check double free */ + WARN_ON(kip->slot_used[idx] != SLOT_USED); + if (dirty) { + kip->slot_used[idx] = SLOT_DIRTY; + kip->ngarbage++; + if (++c->nr_garbage > slots_per_page(c)) + collect_garbage_slots(c); + } else { + collect_one_slot(kip, idx); + } + } mutex_unlock(&c->mutex); } +/* + * Check given address is on the page of kprobe instruction slots. + * This will be used for checking whether the address on a stack + * is on a text area or not. + */ +bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr) +{ + struct kprobe_insn_page *kip; + bool ret = false; + + rcu_read_lock(); + list_for_each_entry_rcu(kip, &c->pages, list) { + if (addr >= (unsigned long)kip->insns && + addr < (unsigned long)kip->insns + PAGE_SIZE) { + ret = true; + break; + } + } + rcu_read_unlock(); + + return ret; +} + #ifdef CONFIG_OPTPROBES /* For optimized_kprobe buffer */ struct kprobe_insn_cache kprobe_optinsn_slots = { diff --git a/kernel/kthread.c b/kernel/kthread.c index 2318fba86277..8461a4372e8a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -850,7 +850,6 @@ void __kthread_queue_delayed_work(struct kthread_worker *worker, list_add(&work->node, &worker->delayed_work_list); work->worker = worker; - timer_stats_timer_set_start_info(&dwork->timer); timer->expires = jiffies + delay; add_timer(timer); } diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 6f88e352cd4f..760158d9d98d 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -28,3 +28,4 @@ obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o +obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 7c38f8f3d97b..9812e5dd409e 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2203,7 +2203,7 @@ cache_hit: * Important for check_no_collision(). */ if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) { - if (debug_locks_off_graph_unlock()) + if (!debug_locks_off_graph_unlock()) return 0; print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!"); @@ -4412,13 +4412,13 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) #endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */ /* Note: the following can be executed concurrently, so be careful. */ printk("\n"); - printk("===============================\n"); - printk("[ INFO: suspicious RCU usage. ]\n"); + pr_err("===============================\n"); + pr_err("[ ERR: suspicious RCU usage. ]\n"); print_kernel_ident(); - printk("-------------------------------\n"); - printk("%s:%d %s!\n", file, line, s); - printk("\nother info that might help us debug this:\n\n"); - printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n", + pr_err("-------------------------------\n"); + pr_err("%s:%d %s!\n", file, line, s); + pr_err("\nother info that might help us debug this:\n\n"); + pr_err("\n%srcu_scheduler_active = %d, debug_locks = %d\n", !rcu_lockdep_current_cpu_online() ? "RCU used illegally from offline CPU!\n" : !rcu_is_watching() diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index f8c5af52a131..28350dc8ecbb 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -372,6 +372,78 @@ static struct lock_torture_ops mutex_lock_ops = { .name = "mutex_lock" }; +#include <linux/ww_mutex.h> +static DEFINE_WW_CLASS(torture_ww_class); +static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class); +static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class); +static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class); + +static int torture_ww_mutex_lock(void) +__acquires(torture_ww_mutex_0) +__acquires(torture_ww_mutex_1) +__acquires(torture_ww_mutex_2) +{ + LIST_HEAD(list); + struct reorder_lock { + struct list_head link; + struct ww_mutex *lock; + } locks[3], *ll, *ln; + struct ww_acquire_ctx ctx; + + locks[0].lock = &torture_ww_mutex_0; + list_add(&locks[0].link, &list); + + locks[1].lock = &torture_ww_mutex_1; + list_add(&locks[1].link, &list); + + locks[2].lock = &torture_ww_mutex_2; + list_add(&locks[2].link, &list); + + ww_acquire_init(&ctx, &torture_ww_class); + + list_for_each_entry(ll, &list, link) { + int err; + + err = ww_mutex_lock(ll->lock, &ctx); + if (!err) + continue; + + ln = ll; + list_for_each_entry_continue_reverse(ln, &list, link) + ww_mutex_unlock(ln->lock); + + if (err != -EDEADLK) + return err; + + ww_mutex_lock_slow(ll->lock, &ctx); + list_move(&ll->link, &list); + } + + ww_acquire_fini(&ctx); + return 0; +} + +static void torture_ww_mutex_unlock(void) +__releases(torture_ww_mutex_0) +__releases(torture_ww_mutex_1) +__releases(torture_ww_mutex_2) +{ + ww_mutex_unlock(&torture_ww_mutex_0); + ww_mutex_unlock(&torture_ww_mutex_1); + ww_mutex_unlock(&torture_ww_mutex_2); +} + +static struct lock_torture_ops ww_mutex_lock_ops = { + .writelock = torture_ww_mutex_lock, + .write_delay = torture_mutex_delay, + .task_boost = torture_boost_dummy, + .writeunlock = torture_ww_mutex_unlock, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, + .name = "ww_mutex_lock" +}; + #ifdef CONFIG_RT_MUTEXES static DEFINE_RT_MUTEX(torture_rtmutex); @@ -780,6 +852,10 @@ static void lock_torture_cleanup(void) else lock_torture_print_module_parms(cxt.cur_ops, "End of test: SUCCESS"); + + kfree(cxt.lwsa); + kfree(cxt.lrsa); + end: torture_cleanup_end(); } @@ -793,6 +869,7 @@ static int __init lock_torture_init(void) &spin_lock_ops, &spin_lock_irq_ops, &rw_lock_ops, &rw_lock_irq_ops, &mutex_lock_ops, + &ww_mutex_lock_ops, #ifdef CONFIG_RT_MUTEXES &rtmutex_lock_ops, #endif @@ -924,6 +1001,8 @@ static int __init lock_torture_init(void) GFP_KERNEL); if (reader_tasks == NULL) { VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory"); + kfree(writer_tasks); + writer_tasks = NULL; firsterr = -ENOMEM; goto unwind; } diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h index a459faa48987..4174417d5309 100644 --- a/kernel/locking/mutex-debug.h +++ b/kernel/locking/mutex-debug.h @@ -26,20 +26,3 @@ extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, extern void debug_mutex_unlock(struct mutex *lock); extern void debug_mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key); - -#define spin_lock_mutex(lock, flags) \ - do { \ - struct mutex *l = container_of(lock, struct mutex, wait_lock); \ - \ - DEBUG_LOCKS_WARN_ON(in_interrupt()); \ - local_irq_save(flags); \ - arch_spin_lock(&(lock)->rlock.raw_lock);\ - DEBUG_LOCKS_WARN_ON(l->magic != l); \ - } while (0) - -#define spin_unlock_mutex(lock, flags) \ - do { \ - arch_spin_unlock(&(lock)->rlock.raw_lock); \ - local_irq_restore(flags); \ - preempt_check_resched(); \ - } while (0) diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 9b349619f431..ad2d9e22697b 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -50,16 +50,17 @@ EXPORT_SYMBOL(__mutex_init); /* * @owner: contains: 'struct task_struct *' to the current lock owner, * NULL means not owned. Since task_struct pointers are aligned at - * ARCH_MIN_TASKALIGN (which is at least sizeof(void *)), we have low - * bits to store extra state. + * at least L1_CACHE_BYTES, we have low bits to store extra state. * * Bit0 indicates a non-empty waiter list; unlock must issue a wakeup. * Bit1 indicates unlock needs to hand the lock to the top-waiter + * Bit2 indicates handoff has been done and we're waiting for pickup. */ #define MUTEX_FLAG_WAITERS 0x01 #define MUTEX_FLAG_HANDOFF 0x02 +#define MUTEX_FLAG_PICKUP 0x04 -#define MUTEX_FLAGS 0x03 +#define MUTEX_FLAGS 0x07 static inline struct task_struct *__owner_task(unsigned long owner) { @@ -72,38 +73,29 @@ static inline unsigned long __owner_flags(unsigned long owner) } /* - * Actual trylock that will work on any unlocked state. - * - * When setting the owner field, we must preserve the low flag bits. - * - * Be careful with @handoff, only set that in a wait-loop (where you set - * HANDOFF) to avoid recursive lock attempts. + * Trylock variant that retuns the owning task on failure. */ -static inline bool __mutex_trylock(struct mutex *lock, const bool handoff) +static inline struct task_struct *__mutex_trylock_or_owner(struct mutex *lock) { unsigned long owner, curr = (unsigned long)current; owner = atomic_long_read(&lock->owner); for (;;) { /* must loop, can race against a flag */ unsigned long old, flags = __owner_flags(owner); + unsigned long task = owner & ~MUTEX_FLAGS; - if (__owner_task(owner)) { - if (handoff && unlikely(__owner_task(owner) == current)) { - /* - * Provide ACQUIRE semantics for the lock-handoff. - * - * We cannot easily use load-acquire here, since - * the actual load is a failed cmpxchg, which - * doesn't imply any barriers. - * - * Also, this is a fairly unlikely scenario, and - * this contains the cost. - */ - smp_mb(); /* ACQUIRE */ - return true; - } + if (task) { + if (likely(task != curr)) + break; - return false; + if (likely(!(flags & MUTEX_FLAG_PICKUP))) + break; + + flags &= ~MUTEX_FLAG_PICKUP; + } else { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(flags & MUTEX_FLAG_PICKUP); +#endif } /* @@ -111,15 +103,24 @@ static inline bool __mutex_trylock(struct mutex *lock, const bool handoff) * past the point where we acquire it. This would be possible * if we (accidentally) set the bit on an unlocked mutex. */ - if (handoff) - flags &= ~MUTEX_FLAG_HANDOFF; + flags &= ~MUTEX_FLAG_HANDOFF; old = atomic_long_cmpxchg_acquire(&lock->owner, owner, curr | flags); if (old == owner) - return true; + return NULL; owner = old; } + + return __owner_task(owner); +} + +/* + * Actual trylock that will work on any unlocked state. + */ +static inline bool __mutex_trylock(struct mutex *lock) +{ + return !__mutex_trylock_or_owner(lock); } #ifndef CONFIG_DEBUG_LOCK_ALLOC @@ -171,9 +172,9 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait /* * Give up ownership to a specific task, when @task = NULL, this is equivalent - * to a regular unlock. Clears HANDOFF, preserves WAITERS. Provides RELEASE - * semantics like a regular unlock, the __mutex_trylock() provides matching - * ACQUIRE semantics for the handoff. + * to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves + * WAITERS. Provides RELEASE semantics like a regular unlock, the + * __mutex_trylock() provides a matching ACQUIRE semantics for the handoff. */ static void __mutex_handoff(struct mutex *lock, struct task_struct *task) { @@ -184,10 +185,13 @@ static void __mutex_handoff(struct mutex *lock, struct task_struct *task) #ifdef CONFIG_DEBUG_MUTEXES DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current); + DEBUG_LOCKS_WARN_ON(owner & MUTEX_FLAG_PICKUP); #endif new = (owner & MUTEX_FLAG_WAITERS); new |= (unsigned long)task; + if (task) + new |= MUTEX_FLAG_PICKUP; old = atomic_long_cmpxchg_release(&lock->owner, owner, new); if (old == owner) @@ -237,8 +241,8 @@ void __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); #endif -static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, - struct ww_acquire_ctx *ww_ctx) +static __always_inline void +ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) { #ifdef CONFIG_DEBUG_MUTEXES /* @@ -277,17 +281,50 @@ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, ww_ctx->acquired++; } +static inline bool __sched +__ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b) +{ + return a->stamp - b->stamp <= LONG_MAX && + (a->stamp != b->stamp || a > b); +} + +/* + * Wake up any waiters that may have to back off when the lock is held by the + * given context. + * + * Due to the invariants on the wait list, this can only affect the first + * waiter with a context. + * + * The current task must not be on the wait list. + */ +static void __sched +__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + struct mutex_waiter *cur; + + lockdep_assert_held(&lock->wait_lock); + + list_for_each_entry(cur, &lock->wait_list, list) { + if (!cur->ww_ctx) + continue; + + if (cur->ww_ctx->acquired > 0 && + __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) { + debug_mutex_wake_waiter(lock, cur); + wake_up_process(cur->task); + } + + break; + } +} + /* * After acquiring lock with fastpath or when we lost out in contested * slowpath, set ctx and wake up any waiters so they can recheck. */ static __always_inline void -ww_mutex_set_context_fastpath(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx) +ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - unsigned long flags; - struct mutex_waiter *cur; - ww_mutex_lock_acquired(lock, ctx); lock->ctx = ctx; @@ -311,46 +348,79 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, * Uh oh, we raced in fastpath, wake up everyone in this case, * so they can see the new lock->ctx. */ - spin_lock_mutex(&lock->base.wait_lock, flags); - list_for_each_entry(cur, &lock->base.wait_list, list) { - debug_mutex_wake_waiter(&lock->base, cur); - wake_up_process(cur->task); - } - spin_unlock_mutex(&lock->base.wait_lock, flags); + spin_lock(&lock->base.wait_lock); + __ww_mutex_wakeup_for_backoff(&lock->base, ctx); + spin_unlock(&lock->base.wait_lock); } /* - * After acquiring lock in the slowpath set ctx and wake up any - * waiters so they can recheck. + * After acquiring lock in the slowpath set ctx. + * + * Unlike for the fast path, the caller ensures that waiters are woken up where + * necessary. * * Callers must hold the mutex wait_lock. */ static __always_inline void -ww_mutex_set_context_slowpath(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx) +ww_mutex_set_context_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - struct mutex_waiter *cur; - ww_mutex_lock_acquired(lock, ctx); lock->ctx = ctx; +} + +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER + +static inline +bool ww_mutex_spin_on_owner(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, + struct mutex_waiter *waiter) +{ + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base); /* - * Give any possible sleeping processes the chance to wake up, - * so they can recheck if they have to back off. + * If ww->ctx is set the contents are undefined, only + * by acquiring wait_lock there is a guarantee that + * they are not invalid when reading. + * + * As such, when deadlock detection needs to be + * performed the optimistic spinning cannot be done. + * + * Check this in every inner iteration because we may + * be racing against another thread's ww_mutex_lock. */ - list_for_each_entry(cur, &lock->base.wait_list, list) { - debug_mutex_wake_waiter(&lock->base, cur); - wake_up_process(cur->task); - } + if (ww_ctx->acquired > 0 && READ_ONCE(ww->ctx)) + return false; + + /* + * If we aren't on the wait list yet, cancel the spin + * if there are waiters. We want to avoid stealing the + * lock from a waiter with an earlier stamp, since the + * other thread may already own a lock that we also + * need. + */ + if (!waiter && (atomic_long_read(&lock->owner) & MUTEX_FLAG_WAITERS)) + return false; + + /* + * Similarly, stop spinning if we are no longer the + * first waiter. + */ + if (waiter && !__mutex_waiter_is_first(lock, waiter)) + return false; + + return true; } -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER /* - * Look out! "owner" is an entirely speculative pointer - * access and not reliable. + * Look out! "owner" is an entirely speculative pointer access and not + * reliable. + * + * "noinline" so that this function shows up on perf profiles. */ static noinline -bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner, + struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter) { bool ret = true; @@ -373,6 +443,11 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) break; } + if (ww_ctx && !ww_mutex_spin_on_owner(lock, ww_ctx, waiter)) { + ret = false; + break; + } + cpu_relax(); } rcu_read_unlock(); @@ -431,12 +506,10 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) * with the spinner at the head of the OSQ, if present, until the owner is * changed to itself. */ -static bool mutex_optimistic_spin(struct mutex *lock, - struct ww_acquire_ctx *ww_ctx, - const bool use_ww_ctx, const bool waiter) +static __always_inline bool +mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, + const bool use_ww_ctx, struct mutex_waiter *waiter) { - struct task_struct *task = current; - if (!waiter) { /* * The purpose of the mutex_can_spin_on_owner() function is @@ -460,40 +533,17 @@ static bool mutex_optimistic_spin(struct mutex *lock, for (;;) { struct task_struct *owner; - if (use_ww_ctx && ww_ctx->acquired > 0) { - struct ww_mutex *ww; - - ww = container_of(lock, struct ww_mutex, base); - /* - * If ww->ctx is set the contents are undefined, only - * by acquiring wait_lock there is a guarantee that - * they are not invalid when reading. - * - * As such, when deadlock detection needs to be - * performed the optimistic spinning cannot be done. - */ - if (READ_ONCE(ww->ctx)) - goto fail_unlock; - } + /* Try to acquire the mutex... */ + owner = __mutex_trylock_or_owner(lock); + if (!owner) + break; /* - * If there's an owner, wait for it to either + * There's an owner, wait for it to either * release the lock or go to sleep. */ - owner = __mutex_owner(lock); - if (owner) { - if (waiter && owner == task) { - smp_mb(); /* ACQUIRE */ - break; - } - - if (!mutex_spin_on_owner(lock, owner)) - goto fail_unlock; - } - - /* Try to acquire the mutex if it is unlocked. */ - if (__mutex_trylock(lock, waiter)) - break; + if (!mutex_spin_on_owner(lock, owner, ww_ctx, waiter)) + goto fail_unlock; /* * The cpu_relax() call is a compiler barrier which forces @@ -532,9 +582,9 @@ fail: return false; } #else -static bool mutex_optimistic_spin(struct mutex *lock, - struct ww_acquire_ctx *ww_ctx, - const bool use_ww_ctx, const bool waiter) +static __always_inline bool +mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, + const bool use_ww_ctx, struct mutex_waiter *waiter) { return false; } @@ -594,23 +644,88 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock) EXPORT_SYMBOL(ww_mutex_unlock); static inline int __sched -__ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) +__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter, + struct ww_acquire_ctx *ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); + struct mutex_waiter *cur; + + if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx)) + goto deadlock; + + /* + * If there is a waiter in front of us that has a context, then its + * stamp is earlier than ours and we must back off. + */ + cur = waiter; + list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) { + if (cur->ww_ctx) + goto deadlock; + } + + return 0; - if (!hold_ctx) +deadlock: +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(ctx->contending_lock); + ctx->contending_lock = ww; +#endif + return -EDEADLK; +} + +static inline int __sched +__ww_mutex_add_waiter(struct mutex_waiter *waiter, + struct mutex *lock, + struct ww_acquire_ctx *ww_ctx) +{ + struct mutex_waiter *cur; + struct list_head *pos; + + if (!ww_ctx) { + list_add_tail(&waiter->list, &lock->wait_list); return 0; + } - if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && - (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { + /* + * Add the waiter before the first waiter with a higher stamp. + * Waiters without a context are skipped to avoid starving + * them. + */ + pos = &lock->wait_list; + list_for_each_entry_reverse(cur, &lock->wait_list, list) { + if (!cur->ww_ctx) + continue; + + if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) { + /* Back off immediately if necessary. */ + if (ww_ctx->acquired > 0) { #ifdef CONFIG_DEBUG_MUTEXES - DEBUG_LOCKS_WARN_ON(ctx->contending_lock); - ctx->contending_lock = ww; + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base); + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock); + ww_ctx->contending_lock = ww; #endif - return -EDEADLK; + return -EDEADLK; + } + + break; + } + + pos = &cur->list; + + /* + * Wake up the waiter so that it gets a chance to back + * off. + */ + if (cur->ww_ctx->acquired > 0) { + debug_mutex_wake_waiter(lock, cur); + wake_up_process(cur->task); + } } + list_add_tail(&waiter->list, pos); return 0; } @@ -622,15 +737,15 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, struct lockdep_map *nest_lock, unsigned long ip, struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) { - struct task_struct *task = current; struct mutex_waiter waiter; - unsigned long flags; bool first = false; struct ww_mutex *ww; int ret; - if (use_ww_ctx) { - ww = container_of(lock, struct ww_mutex, base); + might_sleep(); + + ww = container_of(lock, struct ww_mutex, base); + if (use_ww_ctx && ww_ctx) { if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) return -EALREADY; } @@ -638,36 +753,54 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, preempt_disable(); mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); - if (__mutex_trylock(lock, false) || - mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, false)) { + if (__mutex_trylock(lock) || + mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, NULL)) { /* got the lock, yay! */ lock_acquired(&lock->dep_map, ip); - if (use_ww_ctx) + if (use_ww_ctx && ww_ctx) ww_mutex_set_context_fastpath(ww, ww_ctx); preempt_enable(); return 0; } - spin_lock_mutex(&lock->wait_lock, flags); + spin_lock(&lock->wait_lock); /* * After waiting to acquire the wait_lock, try again. */ - if (__mutex_trylock(lock, false)) + if (__mutex_trylock(lock)) { + if (use_ww_ctx && ww_ctx) + __ww_mutex_wakeup_for_backoff(lock, ww_ctx); + goto skip_wait; + } debug_mutex_lock_common(lock, &waiter); - debug_mutex_add_waiter(lock, &waiter, task); + debug_mutex_add_waiter(lock, &waiter, current); + + lock_contended(&lock->dep_map, ip); - /* add waiting tasks to the end of the waitqueue (FIFO): */ - list_add_tail(&waiter.list, &lock->wait_list); - waiter.task = task; + if (!use_ww_ctx) { + /* add waiting tasks to the end of the waitqueue (FIFO): */ + list_add_tail(&waiter.list, &lock->wait_list); + +#ifdef CONFIG_DEBUG_MUTEXES + waiter.ww_ctx = MUTEX_POISON_WW_CTX; +#endif + } else { + /* Add in stamp order, waking up waiters that must back off. */ + ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx); + if (ret) + goto err_early_backoff; + + waiter.ww_ctx = ww_ctx; + } + + waiter.task = current; if (__mutex_waiter_is_first(lock, &waiter)) __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); - lock_contended(&lock->dep_map, ip); - - set_task_state(task, state); + set_current_state(state); for (;;) { /* * Once we hold wait_lock, we're serialized against @@ -675,7 +808,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * before testing the error conditions to make sure we pick up * the handoff. */ - if (__mutex_trylock(lock, first)) + if (__mutex_trylock(lock)) goto acquired; /* @@ -683,42 +816,47 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * wait_lock. This ensures the lock cancellation is ordered * against mutex_unlock() and wake-ups do not go missing. */ - if (unlikely(signal_pending_state(state, task))) { + if (unlikely(signal_pending_state(state, current))) { ret = -EINTR; goto err; } - if (use_ww_ctx && ww_ctx->acquired > 0) { - ret = __ww_mutex_lock_check_stamp(lock, ww_ctx); + if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) { + ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx); if (ret) goto err; } - spin_unlock_mutex(&lock->wait_lock, flags); + spin_unlock(&lock->wait_lock); schedule_preempt_disabled(); - if (!first && __mutex_waiter_is_first(lock, &waiter)) { - first = true; - __mutex_set_flag(lock, MUTEX_FLAG_HANDOFF); + /* + * ww_mutex needs to always recheck its position since its waiter + * list is not FIFO ordered. + */ + if ((use_ww_ctx && ww_ctx) || !first) { + first = __mutex_waiter_is_first(lock, &waiter); + if (first) + __mutex_set_flag(lock, MUTEX_FLAG_HANDOFF); } - set_task_state(task, state); + set_current_state(state); /* * Here we order against unlock; we must either see it change * state back to RUNNING and fall through the next schedule(), * or we must see its unlock and acquire. */ - if ((first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, true)) || - __mutex_trylock(lock, first)) + if (__mutex_trylock(lock) || + (first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, &waiter))) break; - spin_lock_mutex(&lock->wait_lock, flags); + spin_lock(&lock->wait_lock); } - spin_lock_mutex(&lock->wait_lock, flags); + spin_lock(&lock->wait_lock); acquired: - __set_task_state(task, TASK_RUNNING); + __set_current_state(TASK_RUNNING); - mutex_remove_waiter(lock, &waiter, task); + mutex_remove_waiter(lock, &waiter, current); if (likely(list_empty(&lock->wait_list))) __mutex_clear_flag(lock, MUTEX_FLAGS); @@ -728,30 +866,44 @@ skip_wait: /* got the lock - cleanup and rejoice! */ lock_acquired(&lock->dep_map, ip); - if (use_ww_ctx) + if (use_ww_ctx && ww_ctx) ww_mutex_set_context_slowpath(ww, ww_ctx); - spin_unlock_mutex(&lock->wait_lock, flags); + spin_unlock(&lock->wait_lock); preempt_enable(); return 0; err: - __set_task_state(task, TASK_RUNNING); - mutex_remove_waiter(lock, &waiter, task); - spin_unlock_mutex(&lock->wait_lock, flags); + __set_current_state(TASK_RUNNING); + mutex_remove_waiter(lock, &waiter, current); +err_early_backoff: + spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, 1, ip); preempt_enable(); return ret; } +static int __sched +__mutex_lock(struct mutex *lock, long state, unsigned int subclass, + struct lockdep_map *nest_lock, unsigned long ip) +{ + return __mutex_lock_common(lock, state, subclass, nest_lock, ip, NULL, false); +} + +static int __sched +__ww_mutex_lock(struct mutex *lock, long state, unsigned int subclass, + struct lockdep_map *nest_lock, unsigned long ip, + struct ww_acquire_ctx *ww_ctx) +{ + return __mutex_lock_common(lock, state, subclass, nest_lock, ip, ww_ctx, true); +} + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) { - might_sleep(); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, - subclass, NULL, _RET_IP_, NULL, 0); + __mutex_lock(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_nested); @@ -759,30 +911,38 @@ EXPORT_SYMBOL_GPL(mutex_lock_nested); void __sched _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) { - might_sleep(); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, - 0, nest, _RET_IP_, NULL, 0); + __mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_); } EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); int __sched mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass) { - might_sleep(); - return __mutex_lock_common(lock, TASK_KILLABLE, - subclass, NULL, _RET_IP_, NULL, 0); + return __mutex_lock(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); int __sched mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) { - might_sleep(); - return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, - subclass, NULL, _RET_IP_, NULL, 0); + return __mutex_lock(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); +void __sched +mutex_lock_io_nested(struct mutex *lock, unsigned int subclass) +{ + int token; + + might_sleep(); + + token = io_schedule_prepare(); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, + subclass, NULL, _RET_IP_, NULL, 0); + io_schedule_finish(token); +} +EXPORT_SYMBOL_GPL(mutex_lock_io_nested); + static inline int ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { @@ -810,35 +970,37 @@ ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) } int __sched -__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { int ret; might_sleep(); - ret = __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, - 0, &ctx->dep_map, _RET_IP_, ctx, 1); - if (!ret && ctx->acquired > 1) + ret = __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE, + 0, ctx ? &ctx->dep_map : NULL, _RET_IP_, + ctx); + if (!ret && ctx && ctx->acquired > 1) return ww_mutex_deadlock_injection(lock, ctx); return ret; } -EXPORT_SYMBOL_GPL(__ww_mutex_lock); +EXPORT_SYMBOL_GPL(ww_mutex_lock); int __sched -__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { int ret; might_sleep(); - ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, - 0, &ctx->dep_map, _RET_IP_, ctx, 1); + ret = __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE, + 0, ctx ? &ctx->dep_map : NULL, _RET_IP_, + ctx); - if (!ret && ctx->acquired > 1) + if (!ret && ctx && ctx->acquired > 1) return ww_mutex_deadlock_injection(lock, ctx); return ret; } -EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); +EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible); #endif @@ -848,8 +1010,8 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip) { struct task_struct *next = NULL; - unsigned long owner, flags; DEFINE_WAKE_Q(wake_q); + unsigned long owner; mutex_release(&lock->dep_map, 1, ip); @@ -866,6 +1028,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne #ifdef CONFIG_DEBUG_MUTEXES DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current); + DEBUG_LOCKS_WARN_ON(owner & MUTEX_FLAG_PICKUP); #endif if (owner & MUTEX_FLAG_HANDOFF) @@ -883,7 +1046,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne owner = old; } - spin_lock_mutex(&lock->wait_lock, flags); + spin_lock(&lock->wait_lock); debug_mutex_unlock(lock); if (!list_empty(&lock->wait_list)) { /* get the first entry from the wait-list: */ @@ -900,7 +1063,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne if (owner & MUTEX_FLAG_HANDOFF) __mutex_handoff(lock, next); - spin_unlock_mutex(&lock->wait_lock, flags); + spin_unlock(&lock->wait_lock); wake_up_q(&wake_q); } @@ -950,40 +1113,47 @@ int __sched mutex_lock_killable(struct mutex *lock) } EXPORT_SYMBOL(mutex_lock_killable); +void __sched mutex_lock_io(struct mutex *lock) +{ + int token; + + token = io_schedule_prepare(); + mutex_lock(lock); + io_schedule_finish(token); +} +EXPORT_SYMBOL_GPL(mutex_lock_io); + static noinline void __sched __mutex_lock_slowpath(struct mutex *lock) { - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, - NULL, _RET_IP_, NULL, 0); + __mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_); } static noinline int __sched __mutex_lock_killable_slowpath(struct mutex *lock) { - return __mutex_lock_common(lock, TASK_KILLABLE, 0, - NULL, _RET_IP_, NULL, 0); + return __mutex_lock(lock, TASK_KILLABLE, 0, NULL, _RET_IP_); } static noinline int __sched __mutex_lock_interruptible_slowpath(struct mutex *lock) { - return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, - NULL, _RET_IP_, NULL, 0); + return __mutex_lock(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_); } static noinline int __sched __ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - return __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0, - NULL, _RET_IP_, ctx, 1); + return __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE, 0, NULL, + _RET_IP_, ctx); } static noinline int __sched __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - return __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0, - NULL, _RET_IP_, ctx, 1); + return __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE, 0, NULL, + _RET_IP_, ctx); } #endif @@ -1004,7 +1174,7 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, */ int __sched mutex_trylock(struct mutex *lock) { - bool locked = __mutex_trylock(lock, false); + bool locked = __mutex_trylock(lock); if (locked) mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); @@ -1015,32 +1185,34 @@ EXPORT_SYMBOL(mutex_trylock); #ifndef CONFIG_DEBUG_LOCK_ALLOC int __sched -__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { might_sleep(); if (__mutex_trylock_fast(&lock->base)) { - ww_mutex_set_context_fastpath(lock, ctx); + if (ctx) + ww_mutex_set_context_fastpath(lock, ctx); return 0; } return __ww_mutex_lock_slowpath(lock, ctx); } -EXPORT_SYMBOL(__ww_mutex_lock); +EXPORT_SYMBOL(ww_mutex_lock); int __sched -__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { might_sleep(); if (__mutex_trylock_fast(&lock->base)) { - ww_mutex_set_context_fastpath(lock, ctx); + if (ctx) + ww_mutex_set_context_fastpath(lock, ctx); return 0; } return __ww_mutex_lock_interruptible_slowpath(lock, ctx); } -EXPORT_SYMBOL(__ww_mutex_lock_interruptible); +EXPORT_SYMBOL(ww_mutex_lock_interruptible); #endif diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index 4410a4af42a3..6ebc1902f779 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -9,10 +9,6 @@ * !CONFIG_DEBUG_MUTEXES case. Most of them are NOPs: */ -#define spin_lock_mutex(lock, flags) \ - do { spin_lock(lock); (void)(flags); } while (0) -#define spin_unlock_mutex(lock, flags) \ - do { spin_unlock(lock); (void)(flags); } while (0) #define mutex_remove_waiter(lock, waiter, task) \ __list_del((waiter)->list.prev, (waiter)->list.next) diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index ce182599cf2e..883cf1b92d90 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -1,7 +1,6 @@ #include <linux/atomic.h> #include <linux/rwsem.h> #include <linux/percpu.h> -#include <linux/wait.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/rcupdate.h> @@ -18,7 +17,7 @@ int __percpu_init_rwsem(struct percpu_rw_semaphore *sem, /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */ rcu_sync_init(&sem->rss, RCU_SCHED_SYNC); __init_rwsem(&sem->rw_sem, name, rwsem_key); - init_waitqueue_head(&sem->writer); + rcuwait_init(&sem->writer); sem->readers_block = 0; return 0; } @@ -103,7 +102,7 @@ void __percpu_up_read(struct percpu_rw_semaphore *sem) __this_cpu_dec(*sem->read_count); /* Prod writer to recheck readers_active */ - wake_up(&sem->writer); + rcuwait_wake_up(&sem->writer); } EXPORT_SYMBOL_GPL(__percpu_up_read); @@ -160,7 +159,7 @@ void percpu_down_write(struct percpu_rw_semaphore *sem) */ /* Wait for all now active readers to complete. */ - wait_event(sem->writer, readers_active_check(sem)); + rcuwait_wait_event(&sem->writer, readers_active_check(sem)); } EXPORT_SYMBOL_GPL(percpu_down_write); diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index e3b5520005db..e6b2f7ad3e51 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -263,7 +263,7 @@ pv_wait_early(struct pv_node *prev, int loop) if ((loop & PV_PREV_CHECK_MASK) != 0) return false; - return READ_ONCE(prev->state) != vcpu_running; + return READ_ONCE(prev->state) != vcpu_running || vcpu_is_preempted(prev->cpu); } /* diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 2f443ed2320a..d340be3a488f 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1179,7 +1179,7 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, * TASK_INTERRUPTIBLE checks for signals and * timeout. Ignored otherwise. */ - if (unlikely(state == TASK_INTERRUPTIBLE)) { + if (likely(state == TASK_INTERRUPTIBLE)) { /* Signal pending? */ if (signal_pending(current)) ret = -EINTR; diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 1591f6b3539f..5eacab880f67 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -128,7 +128,6 @@ __rwsem_wake_one_writer(struct rw_semaphore *sem) void __sched __down_read(struct rw_semaphore *sem) { struct rwsem_waiter waiter; - struct task_struct *tsk; unsigned long flags; raw_spin_lock_irqsave(&sem->wait_lock, flags); @@ -140,13 +139,12 @@ void __sched __down_read(struct rw_semaphore *sem) goto out; } - tsk = current; - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); /* set up my own style of waitqueue */ - waiter.task = tsk; + waiter.task = current; waiter.type = RWSEM_WAITING_FOR_READ; - get_task_struct(tsk); + get_task_struct(current); list_add_tail(&waiter.list, &sem->wait_list); @@ -158,10 +156,10 @@ void __sched __down_read(struct rw_semaphore *sem) if (!waiter.task) break; schedule(); - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); } - __set_task_state(tsk, TASK_RUNNING); + __set_current_state(TASK_RUNNING); out: ; } @@ -194,15 +192,13 @@ int __down_read_trylock(struct rw_semaphore *sem) int __sched __down_write_common(struct rw_semaphore *sem, int state) { struct rwsem_waiter waiter; - struct task_struct *tsk; unsigned long flags; int ret = 0; raw_spin_lock_irqsave(&sem->wait_lock, flags); /* set up my own style of waitqueue */ - tsk = current; - waiter.task = tsk; + waiter.task = current; waiter.type = RWSEM_WAITING_FOR_WRITE; list_add_tail(&waiter.list, &sem->wait_list); @@ -220,7 +216,7 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state) ret = -EINTR; goto out; } - set_task_state(tsk, state); + set_current_state(state); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); schedule(); raw_spin_lock_irqsave(&sem->wait_lock, flags); diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 631506004f9e..2ad8d8dc3bb1 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -224,10 +224,9 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) { long count, adjustment = -RWSEM_ACTIVE_READ_BIAS; struct rwsem_waiter waiter; - struct task_struct *tsk = current; DEFINE_WAKE_Q(wake_q); - waiter.task = tsk; + waiter.task = current; waiter.type = RWSEM_WAITING_FOR_READ; raw_spin_lock_irq(&sem->wait_lock); @@ -254,13 +253,13 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) /* wait to be given the lock */ while (true) { - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); if (!waiter.task) break; schedule(); } - __set_task_state(tsk, TASK_RUNNING); + __set_current_state(TASK_RUNNING); return sem; } EXPORT_SYMBOL(rwsem_down_read_failed); @@ -503,8 +502,6 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) * wake any read locks that were queued ahead of us. */ if (count > RWSEM_WAITING_BIAS) { - DEFINE_WAKE_Q(wake_q); - __rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q); /* * The wakeup is normally called _after_ the wait_lock @@ -514,6 +511,11 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) * for attempting rwsem_try_write_lock(). */ wake_up_q(&wake_q); + + /* + * Reinitialize wake_q after use. + */ + wake_q_init(&wake_q); } } else diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c index b8120abe594b..9512e37637dc 100644 --- a/kernel/locking/semaphore.c +++ b/kernel/locking/semaphore.c @@ -204,19 +204,18 @@ struct semaphore_waiter { static inline int __sched __down_common(struct semaphore *sem, long state, long timeout) { - struct task_struct *task = current; struct semaphore_waiter waiter; list_add_tail(&waiter.list, &sem->wait_list); - waiter.task = task; + waiter.task = current; waiter.up = false; for (;;) { - if (signal_pending_state(state, task)) + if (signal_pending_state(state, current)) goto interrupted; if (unlikely(timeout <= 0)) goto timed_out; - __set_task_state(task, state); + __set_current_state(state); raw_spin_unlock_irq(&sem->lock); timeout = schedule_timeout(timeout); raw_spin_lock_irq(&sem->lock); diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index db3ccb1dd614..4b082b5cac9e 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -363,14 +363,6 @@ void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) } EXPORT_SYMBOL(_raw_spin_lock_nested); -void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass) -{ - __local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); - spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); - LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); -} -EXPORT_SYMBOL(_raw_spin_lock_bh_nested); - unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock, int subclass) { diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 0374a596cffa..9aa0fccd5d43 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -103,38 +103,14 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock) lock->owner_cpu = -1; } -static void __spin_lock_debug(raw_spinlock_t *lock) -{ - u64 i; - u64 loops = loops_per_jiffy * HZ; - - for (i = 0; i < loops; i++) { - if (arch_spin_trylock(&lock->raw_lock)) - return; - __delay(1); - } - /* lockup suspected: */ - spin_dump(lock, "lockup suspected"); -#ifdef CONFIG_SMP - trigger_all_cpu_backtrace(); -#endif - - /* - * The trylock above was causing a livelock. Give the lower level arch - * specific lock code a chance to acquire the lock. We have already - * printed a warning/backtrace at this point. The non-debug arch - * specific code might actually succeed in acquiring the lock. If it is - * not successful, the end-result is the same - there is no forward - * progress. - */ - arch_spin_lock(&lock->raw_lock); -} - +/* + * We are now relying on the NMI watchdog to detect lockup instead of doing + * the detection here with an unfair lock which can cause problem of its own. + */ void do_raw_spin_lock(raw_spinlock_t *lock) { debug_spin_lock_before(lock); - if (unlikely(!arch_spin_trylock(&lock->raw_lock))) - __spin_lock_debug(lock); + arch_spin_lock(&lock->raw_lock); debug_spin_lock_after(lock); } @@ -172,32 +148,6 @@ static void rwlock_bug(rwlock_t *lock, const char *msg) #define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg) -#if 0 /* __write_lock_debug() can lock up - maybe this can too? */ -static void __read_lock_debug(rwlock_t *lock) -{ - u64 i; - u64 loops = loops_per_jiffy * HZ; - int print_once = 1; - - for (;;) { - for (i = 0; i < loops; i++) { - if (arch_read_trylock(&lock->raw_lock)) - return; - __delay(1); - } - /* lockup suspected: */ - if (print_once) { - print_once = 0; - printk(KERN_EMERG "BUG: read-lock lockup on CPU#%d, " - "%s/%d, %p\n", - raw_smp_processor_id(), current->comm, - current->pid, lock); - dump_stack(); - } - } -} -#endif - void do_raw_read_lock(rwlock_t *lock) { RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); @@ -247,32 +197,6 @@ static inline void debug_write_unlock(rwlock_t *lock) lock->owner_cpu = -1; } -#if 0 /* This can cause lockups */ -static void __write_lock_debug(rwlock_t *lock) -{ - u64 i; - u64 loops = loops_per_jiffy * HZ; - int print_once = 1; - - for (;;) { - for (i = 0; i < loops; i++) { - if (arch_write_trylock(&lock->raw_lock)) - return; - __delay(1); - } - /* lockup suspected: */ - if (print_once) { - print_once = 0; - printk(KERN_EMERG "BUG: write-lock lockup on CPU#%d, " - "%s/%d, %p\n", - raw_smp_processor_id(), current->comm, - current->pid, lock); - dump_stack(); - } - } -} -#endif - void do_raw_write_lock(rwlock_t *lock) { debug_write_lock_before(lock); diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c new file mode 100644 index 000000000000..da6c9a34f62f --- /dev/null +++ b/kernel/locking/test-ww_mutex.c @@ -0,0 +1,646 @@ +/* + * Module-based API test facility for ww_mutexes + * + * 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, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + */ + +#include <linux/kernel.h> + +#include <linux/completion.h> +#include <linux/delay.h> +#include <linux/kthread.h> +#include <linux/module.h> +#include <linux/random.h> +#include <linux/slab.h> +#include <linux/ww_mutex.h> + +static DEFINE_WW_CLASS(ww_class); +struct workqueue_struct *wq; + +struct test_mutex { + struct work_struct work; + struct ww_mutex mutex; + struct completion ready, go, done; + unsigned int flags; +}; + +#define TEST_MTX_SPIN BIT(0) +#define TEST_MTX_TRY BIT(1) +#define TEST_MTX_CTX BIT(2) +#define __TEST_MTX_LAST BIT(3) + +static void test_mutex_work(struct work_struct *work) +{ + struct test_mutex *mtx = container_of(work, typeof(*mtx), work); + + complete(&mtx->ready); + wait_for_completion(&mtx->go); + + if (mtx->flags & TEST_MTX_TRY) { + while (!ww_mutex_trylock(&mtx->mutex)) + cpu_relax(); + } else { + ww_mutex_lock(&mtx->mutex, NULL); + } + complete(&mtx->done); + ww_mutex_unlock(&mtx->mutex); +} + +static int __test_mutex(unsigned int flags) +{ +#define TIMEOUT (HZ / 16) + struct test_mutex mtx; + struct ww_acquire_ctx ctx; + int ret; + + ww_mutex_init(&mtx.mutex, &ww_class); + ww_acquire_init(&ctx, &ww_class); + + INIT_WORK_ONSTACK(&mtx.work, test_mutex_work); + init_completion(&mtx.ready); + init_completion(&mtx.go); + init_completion(&mtx.done); + mtx.flags = flags; + + schedule_work(&mtx.work); + + wait_for_completion(&mtx.ready); + ww_mutex_lock(&mtx.mutex, (flags & TEST_MTX_CTX) ? &ctx : NULL); + complete(&mtx.go); + if (flags & TEST_MTX_SPIN) { + unsigned long timeout = jiffies + TIMEOUT; + + ret = 0; + do { + if (completion_done(&mtx.done)) { + ret = -EINVAL; + break; + } + cpu_relax(); + } while (time_before(jiffies, timeout)); + } else { + ret = wait_for_completion_timeout(&mtx.done, TIMEOUT); + } + ww_mutex_unlock(&mtx.mutex); + ww_acquire_fini(&ctx); + + if (ret) { + pr_err("%s(flags=%x): mutual exclusion failure\n", + __func__, flags); + ret = -EINVAL; + } + + flush_work(&mtx.work); + destroy_work_on_stack(&mtx.work); + return ret; +#undef TIMEOUT +} + +static int test_mutex(void) +{ + int ret; + int i; + + for (i = 0; i < __TEST_MTX_LAST; i++) { + ret = __test_mutex(i); + if (ret) + return ret; + } + + return 0; +} + +static int test_aa(void) +{ + struct ww_mutex mutex; + struct ww_acquire_ctx ctx; + int ret; + + ww_mutex_init(&mutex, &ww_class); + ww_acquire_init(&ctx, &ww_class); + + ww_mutex_lock(&mutex, &ctx); + + if (ww_mutex_trylock(&mutex)) { + pr_err("%s: trylocked itself!\n", __func__); + ww_mutex_unlock(&mutex); + ret = -EINVAL; + goto out; + } + + ret = ww_mutex_lock(&mutex, &ctx); + if (ret != -EALREADY) { + pr_err("%s: missed deadlock for recursing, ret=%d\n", + __func__, ret); + if (!ret) + ww_mutex_unlock(&mutex); + ret = -EINVAL; + goto out; + } + + ret = 0; +out: + ww_mutex_unlock(&mutex); + ww_acquire_fini(&ctx); + return ret; +} + +struct test_abba { + struct work_struct work; + struct ww_mutex a_mutex; + struct ww_mutex b_mutex; + struct completion a_ready; + struct completion b_ready; + bool resolve; + int result; +}; + +static void test_abba_work(struct work_struct *work) +{ + struct test_abba *abba = container_of(work, typeof(*abba), work); + struct ww_acquire_ctx ctx; + int err; + + ww_acquire_init(&ctx, &ww_class); + ww_mutex_lock(&abba->b_mutex, &ctx); + + complete(&abba->b_ready); + wait_for_completion(&abba->a_ready); + + err = ww_mutex_lock(&abba->a_mutex, &ctx); + if (abba->resolve && err == -EDEADLK) { + ww_mutex_unlock(&abba->b_mutex); + ww_mutex_lock_slow(&abba->a_mutex, &ctx); + err = ww_mutex_lock(&abba->b_mutex, &ctx); + } + + if (!err) + ww_mutex_unlock(&abba->a_mutex); + ww_mutex_unlock(&abba->b_mutex); + ww_acquire_fini(&ctx); + + abba->result = err; +} + +static int test_abba(bool resolve) +{ + struct test_abba abba; + struct ww_acquire_ctx ctx; + int err, ret; + + ww_mutex_init(&abba.a_mutex, &ww_class); + ww_mutex_init(&abba.b_mutex, &ww_class); + INIT_WORK_ONSTACK(&abba.work, test_abba_work); + init_completion(&abba.a_ready); + init_completion(&abba.b_ready); + abba.resolve = resolve; + + schedule_work(&abba.work); + + ww_acquire_init(&ctx, &ww_class); + ww_mutex_lock(&abba.a_mutex, &ctx); + + complete(&abba.a_ready); + wait_for_completion(&abba.b_ready); + + err = ww_mutex_lock(&abba.b_mutex, &ctx); + if (resolve && err == -EDEADLK) { + ww_mutex_unlock(&abba.a_mutex); + ww_mutex_lock_slow(&abba.b_mutex, &ctx); + err = ww_mutex_lock(&abba.a_mutex, &ctx); + } + + if (!err) + ww_mutex_unlock(&abba.b_mutex); + ww_mutex_unlock(&abba.a_mutex); + ww_acquire_fini(&ctx); + + flush_work(&abba.work); + destroy_work_on_stack(&abba.work); + + ret = 0; + if (resolve) { + if (err || abba.result) { + pr_err("%s: failed to resolve ABBA deadlock, A err=%d, B err=%d\n", + __func__, err, abba.result); + ret = -EINVAL; + } + } else { + if (err != -EDEADLK && abba.result != -EDEADLK) { + pr_err("%s: missed ABBA deadlock, A err=%d, B err=%d\n", + __func__, err, abba.result); + ret = -EINVAL; + } + } + return ret; +} + +struct test_cycle { + struct work_struct work; + struct ww_mutex a_mutex; + struct ww_mutex *b_mutex; + struct completion *a_signal; + struct completion b_signal; + int result; +}; + +static void test_cycle_work(struct work_struct *work) +{ + struct test_cycle *cycle = container_of(work, typeof(*cycle), work); + struct ww_acquire_ctx ctx; + int err; + + ww_acquire_init(&ctx, &ww_class); + ww_mutex_lock(&cycle->a_mutex, &ctx); + + complete(cycle->a_signal); + wait_for_completion(&cycle->b_signal); + + err = ww_mutex_lock(cycle->b_mutex, &ctx); + if (err == -EDEADLK) { + ww_mutex_unlock(&cycle->a_mutex); + ww_mutex_lock_slow(cycle->b_mutex, &ctx); + err = ww_mutex_lock(&cycle->a_mutex, &ctx); + } + + if (!err) + ww_mutex_unlock(cycle->b_mutex); + ww_mutex_unlock(&cycle->a_mutex); + ww_acquire_fini(&ctx); + + cycle->result = err; +} + +static int __test_cycle(unsigned int nthreads) +{ + struct test_cycle *cycles; + unsigned int n, last = nthreads - 1; + int ret; + + cycles = kmalloc_array(nthreads, sizeof(*cycles), GFP_KERNEL); + if (!cycles) + return -ENOMEM; + + for (n = 0; n < nthreads; n++) { + struct test_cycle *cycle = &cycles[n]; + + ww_mutex_init(&cycle->a_mutex, &ww_class); + if (n == last) + cycle->b_mutex = &cycles[0].a_mutex; + else + cycle->b_mutex = &cycles[n + 1].a_mutex; + + if (n == 0) + cycle->a_signal = &cycles[last].b_signal; + else + cycle->a_signal = &cycles[n - 1].b_signal; + init_completion(&cycle->b_signal); + + INIT_WORK(&cycle->work, test_cycle_work); + cycle->result = 0; + } + + for (n = 0; n < nthreads; n++) + queue_work(wq, &cycles[n].work); + + flush_workqueue(wq); + + ret = 0; + for (n = 0; n < nthreads; n++) { + struct test_cycle *cycle = &cycles[n]; + + if (!cycle->result) + continue; + + pr_err("cylic deadlock not resolved, ret[%d/%d] = %d\n", + n, nthreads, cycle->result); + ret = -EINVAL; + break; + } + + for (n = 0; n < nthreads; n++) + ww_mutex_destroy(&cycles[n].a_mutex); + kfree(cycles); + return ret; +} + +static int test_cycle(unsigned int ncpus) +{ + unsigned int n; + int ret; + + for (n = 2; n <= ncpus + 1; n++) { + ret = __test_cycle(n); + if (ret) + return ret; + } + + return 0; +} + +struct stress { + struct work_struct work; + struct ww_mutex *locks; + int nlocks; + int nloops; +}; + +static int *get_random_order(int count) +{ + int *order; + int n, r, tmp; + + order = kmalloc_array(count, sizeof(*order), GFP_TEMPORARY); + if (!order) + return order; + + for (n = 0; n < count; n++) + order[n] = n; + + for (n = count - 1; n > 1; n--) { + r = get_random_int() % (n + 1); + if (r != n) { + tmp = order[n]; + order[n] = order[r]; + order[r] = tmp; + } + } + + return order; +} + +static void dummy_load(struct stress *stress) +{ + usleep_range(1000, 2000); +} + +static void stress_inorder_work(struct work_struct *work) +{ + struct stress *stress = container_of(work, typeof(*stress), work); + const int nlocks = stress->nlocks; + struct ww_mutex *locks = stress->locks; + struct ww_acquire_ctx ctx; + int *order; + + order = get_random_order(nlocks); + if (!order) + return; + + ww_acquire_init(&ctx, &ww_class); + + do { + int contended = -1; + int n, err; + +retry: + err = 0; + for (n = 0; n < nlocks; n++) { + if (n == contended) + continue; + + err = ww_mutex_lock(&locks[order[n]], &ctx); + if (err < 0) + break; + } + if (!err) + dummy_load(stress); + + if (contended > n) + ww_mutex_unlock(&locks[order[contended]]); + contended = n; + while (n--) + ww_mutex_unlock(&locks[order[n]]); + + if (err == -EDEADLK) { + ww_mutex_lock_slow(&locks[order[contended]], &ctx); + goto retry; + } + + if (err) { + pr_err_once("stress (%s) failed with %d\n", + __func__, err); + break; + } + } while (--stress->nloops); + + ww_acquire_fini(&ctx); + + kfree(order); + kfree(stress); +} + +struct reorder_lock { + struct list_head link; + struct ww_mutex *lock; +}; + +static void stress_reorder_work(struct work_struct *work) +{ + struct stress *stress = container_of(work, typeof(*stress), work); + LIST_HEAD(locks); + struct ww_acquire_ctx ctx; + struct reorder_lock *ll, *ln; + int *order; + int n, err; + + order = get_random_order(stress->nlocks); + if (!order) + return; + + for (n = 0; n < stress->nlocks; n++) { + ll = kmalloc(sizeof(*ll), GFP_KERNEL); + if (!ll) + goto out; + + ll->lock = &stress->locks[order[n]]; + list_add(&ll->link, &locks); + } + kfree(order); + order = NULL; + + ww_acquire_init(&ctx, &ww_class); + + do { + list_for_each_entry(ll, &locks, link) { + err = ww_mutex_lock(ll->lock, &ctx); + if (!err) + continue; + + ln = ll; + list_for_each_entry_continue_reverse(ln, &locks, link) + ww_mutex_unlock(ln->lock); + + if (err != -EDEADLK) { + pr_err_once("stress (%s) failed with %d\n", + __func__, err); + break; + } + + ww_mutex_lock_slow(ll->lock, &ctx); + list_move(&ll->link, &locks); /* restarts iteration */ + } + + dummy_load(stress); + list_for_each_entry(ll, &locks, link) + ww_mutex_unlock(ll->lock); + } while (--stress->nloops); + + ww_acquire_fini(&ctx); + +out: + list_for_each_entry_safe(ll, ln, &locks, link) + kfree(ll); + kfree(order); + kfree(stress); +} + +static void stress_one_work(struct work_struct *work) +{ + struct stress *stress = container_of(work, typeof(*stress), work); + const int nlocks = stress->nlocks; + struct ww_mutex *lock = stress->locks + (get_random_int() % nlocks); + int err; + + do { + err = ww_mutex_lock(lock, NULL); + if (!err) { + dummy_load(stress); + ww_mutex_unlock(lock); + } else { + pr_err_once("stress (%s) failed with %d\n", + __func__, err); + break; + } + } while (--stress->nloops); + + kfree(stress); +} + +#define STRESS_INORDER BIT(0) +#define STRESS_REORDER BIT(1) +#define STRESS_ONE BIT(2) +#define STRESS_ALL (STRESS_INORDER | STRESS_REORDER | STRESS_ONE) + +static int stress(int nlocks, int nthreads, int nloops, unsigned int flags) +{ + struct ww_mutex *locks; + int n; + + locks = kmalloc_array(nlocks, sizeof(*locks), GFP_KERNEL); + if (!locks) + return -ENOMEM; + + for (n = 0; n < nlocks; n++) + ww_mutex_init(&locks[n], &ww_class); + + for (n = 0; nthreads; n++) { + struct stress *stress; + void (*fn)(struct work_struct *work); + + fn = NULL; + switch (n & 3) { + case 0: + if (flags & STRESS_INORDER) + fn = stress_inorder_work; + break; + case 1: + if (flags & STRESS_REORDER) + fn = stress_reorder_work; + break; + case 2: + if (flags & STRESS_ONE) + fn = stress_one_work; + break; + } + + if (!fn) + continue; + + stress = kmalloc(sizeof(*stress), GFP_KERNEL); + if (!stress) + break; + + INIT_WORK(&stress->work, fn); + stress->locks = locks; + stress->nlocks = nlocks; + stress->nloops = nloops; + + queue_work(wq, &stress->work); + nthreads--; + } + + flush_workqueue(wq); + + for (n = 0; n < nlocks; n++) + ww_mutex_destroy(&locks[n]); + kfree(locks); + + return 0; +} + +static int __init test_ww_mutex_init(void) +{ + int ncpus = num_online_cpus(); + int ret; + + wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0); + if (!wq) + return -ENOMEM; + + ret = test_mutex(); + if (ret) + return ret; + + ret = test_aa(); + if (ret) + return ret; + + ret = test_abba(false); + if (ret) + return ret; + + ret = test_abba(true); + if (ret) + return ret; + + ret = test_cycle(ncpus); + if (ret) + return ret; + + ret = stress(16, 2*ncpus, 1<<10, STRESS_INORDER); + if (ret) + return ret; + + ret = stress(16, 2*ncpus, 1<<10, STRESS_REORDER); + if (ret) + return ret; + + ret = stress(4096, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL); + if (ret) + return ret; + + return 0; +} + +static void __exit test_ww_mutex_exit(void) +{ + destroy_workqueue(wq); +} + +module_init(test_ww_mutex_init); +module_exit(test_ww_mutex_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Intel Corporation"); diff --git a/kernel/membarrier.c b/kernel/membarrier.c index 536c727a56e9..9f9284f37f8d 100644 --- a/kernel/membarrier.c +++ b/kernel/membarrier.c @@ -16,6 +16,7 @@ #include <linux/syscalls.h> #include <linux/membarrier.h> +#include <linux/tick.h> /* * Bitmask made from a "or" of all commands within enum membarrier_cmd, @@ -51,6 +52,9 @@ */ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) { + /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */ + if (tick_nohz_full_enabled()) + return -ENOSYS; if (unlikely(flags)) return -EINVAL; switch (cmd) { diff --git a/kernel/pid.c b/kernel/pid.c index f66162f2359b..0291804151b5 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -68,9 +68,7 @@ static inline int mk_pid(struct pid_namespace *pid_ns, * the scheme scales to up to 4 million PIDs, runtime. */ struct pid_namespace init_pid_ns = { - .kref = { - .refcount = ATOMIC_INIT(2), - }, + .kref = KREF_INIT(2), .pidmap = { [ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } }, diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 8b2696420abb..4ba3d34938c0 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1516,7 +1516,7 @@ static void call_console_drivers(int level, { struct console *con; - trace_console(text, len); + trace_console_rcuidle(text, len); if (!console_drivers) return; diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 87c51225ceec..d81345be730e 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -564,10 +564,25 @@ static void srcu_torture_stats(void) pr_alert("%s%s per-CPU(idx=%d):", torture_type, TORTURE_FLAG, idx); for_each_possible_cpu(cpu) { + unsigned long l0, l1; + unsigned long u0, u1; long c0, c1; + struct srcu_array *counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu); - c0 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[!idx]; - c1 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[idx]; + u0 = counts->unlock_count[!idx]; + u1 = counts->unlock_count[idx]; + + /* + * Make sure that a lock is always counted if the corresponding + * unlock is counted. + */ + smp_rmb(); + + l0 = counts->lock_count[!idx]; + l1 = counts->lock_count[idx]; + + c0 = l0 - u0; + c1 = l1 - u1; pr_cont(" %d(%ld,%ld)", cpu, c0, c1); } pr_cont("\n"); diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index 9b9cdd549caa..e773129c8b08 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -106,7 +106,7 @@ static int init_srcu_struct_fields(struct srcu_struct *sp) rcu_batch_init(&sp->batch_check1); rcu_batch_init(&sp->batch_done); INIT_DELAYED_WORK(&sp->work, process_srcu); - sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array); + sp->per_cpu_ref = alloc_percpu(struct srcu_array); return sp->per_cpu_ref ? 0 : -ENOMEM; } @@ -141,114 +141,77 @@ EXPORT_SYMBOL_GPL(init_srcu_struct); #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* - * Returns approximate total of the readers' ->seq[] values for the + * Returns approximate total of the readers' ->lock_count[] values for the * rank of per-CPU counters specified by idx. */ -static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx) +static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx) { int cpu; unsigned long sum = 0; - unsigned long t; for_each_possible_cpu(cpu) { - t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]); - sum += t; + struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu); + + sum += READ_ONCE(cpuc->lock_count[idx]); } return sum; } /* - * Returns approximate number of readers active on the specified rank - * of the per-CPU ->c[] counters. + * Returns approximate total of the readers' ->unlock_count[] values for the + * rank of per-CPU counters specified by idx. */ -static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx) +static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx) { int cpu; unsigned long sum = 0; - unsigned long t; for_each_possible_cpu(cpu) { - t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]); - sum += t; + struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu); + + sum += READ_ONCE(cpuc->unlock_count[idx]); } return sum; } /* * Return true if the number of pre-existing readers is determined to - * be stably zero. An example unstable zero can occur if the call - * to srcu_readers_active_idx() misses an __srcu_read_lock() increment, - * but due to task migration, sees the corresponding __srcu_read_unlock() - * decrement. This can happen because srcu_readers_active_idx() takes - * time to sum the array, and might in fact be interrupted or preempted - * partway through the summation. + * be zero. */ static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx) { - unsigned long seq; + unsigned long unlocks; - seq = srcu_readers_seq_idx(sp, idx); + unlocks = srcu_readers_unlock_idx(sp, idx); /* - * The following smp_mb() A pairs with the smp_mb() B located in - * __srcu_read_lock(). This pairing ensures that if an - * __srcu_read_lock() increments its counter after the summation - * in srcu_readers_active_idx(), then the corresponding SRCU read-side - * critical section will see any changes made prior to the start - * of the current SRCU grace period. + * Make sure that a lock is always counted if the corresponding unlock + * is counted. Needs to be a smp_mb() as the read side may contain a + * read from a variable that is written to before the synchronize_srcu() + * in the write side. In this case smp_mb()s A and B act like the store + * buffering pattern. * - * Also, if the above call to srcu_readers_seq_idx() saw the - * increment of ->seq[], then the call to srcu_readers_active_idx() - * must see the increment of ->c[]. + * This smp_mb() also pairs with smp_mb() C to prevent accesses after the + * synchronize_srcu() from being executed before the grace period ends. */ smp_mb(); /* A */ /* - * Note that srcu_readers_active_idx() can incorrectly return - * zero even though there is a pre-existing reader throughout. - * To see this, suppose that task A is in a very long SRCU - * read-side critical section that started on CPU 0, and that - * no other reader exists, so that the sum of the counters - * is equal to one. Then suppose that task B starts executing - * srcu_readers_active_idx(), summing up to CPU 1, and then that - * task C starts reading on CPU 0, so that its increment is not - * summed, but finishes reading on CPU 2, so that its decrement - * -is- summed. Then when task B completes its sum, it will - * incorrectly get zero, despite the fact that task A has been - * in its SRCU read-side critical section the whole time. - * - * We therefore do a validation step should srcu_readers_active_idx() - * return zero. - */ - if (srcu_readers_active_idx(sp, idx) != 0) - return false; - - /* - * The remainder of this function is the validation step. - * The following smp_mb() D pairs with the smp_mb() C in - * __srcu_read_unlock(). If the __srcu_read_unlock() was seen - * by srcu_readers_active_idx() above, then any destructive - * operation performed after the grace period will happen after - * the corresponding SRCU read-side critical section. + * If the locks are the same as the unlocks, then there must have + * been no readers on this index at some time in between. This does not + * mean that there are no more readers, as one could have read the + * current index but not have incremented the lock counter yet. * - * Note that there can be at most NR_CPUS worth of readers using - * the old index, which is not enough to overflow even a 32-bit - * integer. (Yes, this does mean that systems having more than - * a billion or so CPUs need to be 64-bit systems.) Therefore, - * the sum of the ->seq[] counters cannot possibly overflow. - * Therefore, the only way that the return values of the two - * calls to srcu_readers_seq_idx() can be equal is if there were - * no increments of the corresponding rank of ->seq[] counts - * in the interim. But the missed-increment scenario laid out - * above includes an increment of the ->seq[] counter by - * the corresponding __srcu_read_lock(). Therefore, if this - * scenario occurs, the return values from the two calls to - * srcu_readers_seq_idx() will differ, and thus the validation - * step below suffices. + * Possible bug: There is no guarantee that there haven't been ULONG_MAX + * increments of ->lock_count[] since the unlocks were counted, meaning + * that this could return true even if there are still active readers. + * Since there are no memory barriers around srcu_flip(), the CPU is not + * required to increment ->completed before running + * srcu_readers_unlock_idx(), which means that there could be an + * arbitrarily large number of critical sections that execute after + * srcu_readers_unlock_idx() but use the old value of ->completed. */ - smp_mb(); /* D */ - - return srcu_readers_seq_idx(sp, idx) == seq; + return srcu_readers_lock_idx(sp, idx) == unlocks; } /** @@ -266,8 +229,12 @@ static bool srcu_readers_active(struct srcu_struct *sp) unsigned long sum = 0; for_each_possible_cpu(cpu) { - sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]); - sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]); + struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu); + + sum += READ_ONCE(cpuc->lock_count[0]); + sum += READ_ONCE(cpuc->lock_count[1]); + sum -= READ_ONCE(cpuc->unlock_count[0]); + sum -= READ_ONCE(cpuc->unlock_count[1]); } return sum; } @@ -298,9 +265,8 @@ int __srcu_read_lock(struct srcu_struct *sp) int idx; idx = READ_ONCE(sp->completed) & 0x1; - __this_cpu_inc(sp->per_cpu_ref->c[idx]); + __this_cpu_inc(sp->per_cpu_ref->lock_count[idx]); smp_mb(); /* B */ /* Avoid leaking the critical section. */ - __this_cpu_inc(sp->per_cpu_ref->seq[idx]); return idx; } EXPORT_SYMBOL_GPL(__srcu_read_lock); @@ -314,7 +280,7 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock); void __srcu_read_unlock(struct srcu_struct *sp, int idx) { smp_mb(); /* C */ /* Avoid leaking the critical section. */ - this_cpu_dec(sp->per_cpu_ref->c[idx]); + this_cpu_inc(sp->per_cpu_ref->unlock_count[idx]); } EXPORT_SYMBOL_GPL(__srcu_read_unlock); @@ -349,12 +315,21 @@ static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount) /* * Increment the ->completed counter so that future SRCU readers will - * use the other rank of the ->c[] and ->seq[] arrays. This allows + * use the other rank of the ->(un)lock_count[] arrays. This allows * us to wait for pre-existing readers in a starvation-free manner. */ static void srcu_flip(struct srcu_struct *sp) { - sp->completed++; + WRITE_ONCE(sp->completed, sp->completed + 1); + + /* + * Ensure that if the updater misses an __srcu_read_unlock() + * increment, that task's next __srcu_read_lock() will see the + * above counter update. Note that both this memory barrier + * and the one in srcu_readers_active_idx_check() provide the + * guarantee for __srcu_read_lock(). + */ + smp_mb(); /* D */ /* Pairs with C. */ } /* @@ -392,6 +367,7 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head, head->next = NULL; head->func = func; spin_lock_irqsave(&sp->queue_lock, flags); + smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */ rcu_batch_queue(&sp->batch_queue, head); if (!sp->running) { sp->running = true; @@ -425,6 +401,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount) head->next = NULL; head->func = wakeme_after_rcu; spin_lock_irq(&sp->queue_lock); + smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */ if (!sp->running) { /* steal the processing owner */ sp->running = true; @@ -444,8 +421,11 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount) spin_unlock_irq(&sp->queue_lock); } - if (!done) + if (!done) { wait_for_completion(&rcu.completion); + smp_mb(); /* Caller's later accesses after GP. */ + } + } /** @@ -613,7 +593,8 @@ static void srcu_advance_batches(struct srcu_struct *sp, int trycount) /* * Invoke a limited number of SRCU callbacks that have passed through * their grace period. If there are more to do, SRCU will reschedule - * the workqueue. + * the workqueue. Note that needed memory barriers have been executed + * in this task's context by srcu_readers_active_idx_check(). */ static void srcu_invoke_callbacks(struct srcu_struct *sp) { diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index b23a4d076f3d..fa6a48d3917b 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -41,8 +41,6 @@ /* Forward declarations for tiny_plugin.h. */ struct rcu_ctrlblk; -static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp); -static void rcu_process_callbacks(struct softirq_action *unused); static void __call_rcu(struct rcu_head *head, rcu_callback_t func, struct rcu_ctrlblk *rcp); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index cb4e2056ccf3..d80e0d2f68c6 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -281,6 +281,116 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { #endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ }; +/* + * Record entry into an extended quiescent state. This is only to be + * called when not already in an extended quiescent state. + */ +static void rcu_dynticks_eqs_enter(void) +{ + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + int special; + + /* + * CPUs seeing atomic_inc_return() must see prior RCU read-side + * critical sections, and we also must force ordering with the + * next idle sojourn. + */ + special = atomic_inc_return(&rdtp->dynticks); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && special & 0x1); +} + +/* + * Record exit from an extended quiescent state. This is only to be + * called from an extended quiescent state. + */ +static void rcu_dynticks_eqs_exit(void) +{ + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + int special; + + /* + * CPUs seeing atomic_inc_return() must see prior idle sojourns, + * and we also must force ordering with the next RCU read-side + * critical section. + */ + special = atomic_inc_return(&rdtp->dynticks); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(special & 0x1)); +} + +/* + * Reset the current CPU's ->dynticks counter to indicate that the + * newly onlined CPU is no longer in an extended quiescent state. + * This will either leave the counter unchanged, or increment it + * to the next non-quiescent value. + * + * The non-atomic test/increment sequence works because the upper bits + * of the ->dynticks counter are manipulated only by the corresponding CPU, + * or when the corresponding CPU is offline. + */ +static void rcu_dynticks_eqs_online(void) +{ + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + + if (atomic_read(&rdtp->dynticks) & 0x1) + return; + atomic_add(0x1, &rdtp->dynticks); +} + +/* + * Is the current CPU in an extended quiescent state? + * + * No ordering, as we are sampling CPU-local information. + */ +bool rcu_dynticks_curr_cpu_in_eqs(void) +{ + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + + return !(atomic_read(&rdtp->dynticks) & 0x1); +} + +/* + * Snapshot the ->dynticks counter with full ordering so as to allow + * stable comparison of this counter with past and future snapshots. + */ +int rcu_dynticks_snap(struct rcu_dynticks *rdtp) +{ + int snap = atomic_add_return(0, &rdtp->dynticks); + + return snap; +} + +/* + * Return true if the snapshot returned from rcu_dynticks_snap() + * indicates that RCU is in an extended quiescent state. + */ +static bool rcu_dynticks_in_eqs(int snap) +{ + return !(snap & 0x1); +} + +/* + * Return true if the CPU corresponding to the specified rcu_dynticks + * structure has spent some time in an extended quiescent state since + * rcu_dynticks_snap() returned the specified snapshot. + */ +static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap) +{ + return snap != rcu_dynticks_snap(rdtp); +} + +/* + * 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, &rdtp->dynticks); + + /* It is illegal to call this from idle state. */ + WARN_ON_ONCE(!(special & 0x1)); +} + DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr); EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr); @@ -300,7 +410,6 @@ EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr); static void rcu_momentary_dyntick_idle(void) { struct rcu_data *rdp; - struct rcu_dynticks *rdtp; int resched_mask; struct rcu_state *rsp; @@ -327,10 +436,7 @@ static void rcu_momentary_dyntick_idle(void) * quiescent state, with no need for this CPU to do anything * further. */ - rdtp = this_cpu_ptr(&rcu_dynticks); - smp_mb__before_atomic(); /* Earlier stuff before QS. */ - atomic_add(2, &rdtp->dynticks); /* QS. */ - smp_mb__after_atomic(); /* Later stuff after QS. */ + rcu_dynticks_momentary_idle(); break; } } @@ -611,7 +717,7 @@ static int cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp) { return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] && - rdp->nxttail[RCU_DONE_TAIL] != NULL; + rdp->nxttail[RCU_NEXT_TAIL] != NULL; } /* @@ -673,7 +779,7 @@ static void rcu_eqs_enter_common(long long oldval, bool user) { struct rcu_state *rsp; struct rcu_data *rdp; - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);) trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting); if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && @@ -692,12 +798,7 @@ static void rcu_eqs_enter_common(long long oldval, bool user) do_nocb_deferred_wakeup(rdp); } rcu_prepare_for_idle(); - /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ - smp_mb__before_atomic(); /* See above. */ - atomic_inc(&rdtp->dynticks); - smp_mb__after_atomic(); /* Force ordering with next sojourn. */ - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - atomic_read(&rdtp->dynticks) & 0x1); + rcu_dynticks_eqs_enter(); rcu_dynticks_task_enter(); /* @@ -826,15 +927,10 @@ void rcu_irq_exit_irqson(void) */ static void rcu_eqs_exit_common(long long oldval, int user) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);) rcu_dynticks_task_exit(); - smp_mb__before_atomic(); /* Force ordering w/previous sojourn. */ - atomic_inc(&rdtp->dynticks); - /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ - smp_mb__after_atomic(); /* See above. */ - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - !(atomic_read(&rdtp->dynticks) & 0x1)); + rcu_dynticks_eqs_exit(); rcu_cleanup_after_idle(); trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting); if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && @@ -980,12 +1076,8 @@ void rcu_nmi_enter(void) * to be in the outermost NMI handler that interrupted an RCU-idle * period (observation due to Andy Lutomirski). */ - if (!(atomic_read(&rdtp->dynticks) & 0x1)) { - smp_mb__before_atomic(); /* Force delay from prior write. */ - atomic_inc(&rdtp->dynticks); - /* atomic_inc() before later RCU read-side crit sects */ - smp_mb__after_atomic(); /* See above. */ - WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + if (rcu_dynticks_curr_cpu_in_eqs()) { + rcu_dynticks_eqs_exit(); incby = 1; } rdtp->dynticks_nmi_nesting += incby; @@ -1010,7 +1102,7 @@ void rcu_nmi_exit(void) * to us!) */ WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0); - WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs()); /* * If the nesting level is not 1, the CPU wasn't RCU-idle, so @@ -1023,11 +1115,7 @@ void rcu_nmi_exit(void) /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ rdtp->dynticks_nmi_nesting = 0; - /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ - smp_mb__before_atomic(); /* See above. */ - atomic_inc(&rdtp->dynticks); - smp_mb__after_atomic(); /* Force delay to next write. */ - WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); + rcu_dynticks_eqs_enter(); } /** @@ -1040,7 +1128,7 @@ void rcu_nmi_exit(void) */ bool notrace __rcu_is_watching(void) { - return atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1; + return !rcu_dynticks_curr_cpu_in_eqs(); } /** @@ -1123,9 +1211,9 @@ static int rcu_is_cpu_rrupt_from_idle(void) static int dyntick_save_progress_counter(struct rcu_data *rdp, bool *isidle, unsigned long *maxj) { - rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks); + rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); rcu_sysidle_check_cpu(rdp, isidle, maxj); - if ((rdp->dynticks_snap & 0x1) == 0) { + if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rdp->mynode->gpnum)) @@ -1144,12 +1232,10 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, bool *isidle, unsigned long *maxj) { - unsigned int curr; + unsigned long jtsq; int *rcrmp; - unsigned int snap; - - curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks); - snap = (unsigned int)rdp->dynticks_snap; + unsigned long rjtsc; + struct rcu_node *rnp; /* * If the CPU passed through or entered a dynticks idle phase with @@ -1159,27 +1245,39 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, * read-side critical section that started before the beginning * of the current RCU grace period. */ - if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) { + if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); rdp->dynticks_fqs++; return 1; } + /* Compute and saturate jiffies_till_sched_qs. */ + jtsq = jiffies_till_sched_qs; + rjtsc = rcu_jiffies_till_stall_check(); + if (jtsq > rjtsc / 2) { + WRITE_ONCE(jiffies_till_sched_qs, rjtsc); + jtsq = rjtsc / 2; + } else if (jtsq < 1) { + WRITE_ONCE(jiffies_till_sched_qs, 1); + jtsq = 1; + } + /* - * Check for the CPU being offline, but only if the grace period - * is old enough. We don't need to worry about the CPU changing - * state: If we see it offline even once, it has been through a - * quiescent state. - * - * The reason for insisting that the grace period be at least - * one jiffy old is that CPUs that are not quite online and that - * have just gone offline can still execute RCU read-side critical - * sections. + * Has this CPU encountered a cond_resched_rcu_qs() since the + * beginning of the grace period? For this to be the case, + * the CPU has to have noticed the current grace period. This + * might not be the case for nohz_full CPUs looping in the kernel. */ - if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies)) - return 0; /* Grace period is not old enough. */ - barrier(); - if (cpu_is_offline(rdp->cpu)) { + rnp = rdp->mynode; + if (time_after(jiffies, rdp->rsp->gp_start + jtsq) && + READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(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")); + return 1; + } + + /* 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++; return 1; @@ -1207,9 +1305,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, * warning delay. */ rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu); - if (ULONG_CMP_GE(jiffies, - rdp->rsp->gp_start + jiffies_till_sched_qs) || - ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { + if (time_after(jiffies, rdp->rsp->gp_start + jtsq) || + time_after(jiffies, rdp->rsp->jiffies_resched)) { if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) { WRITE_ONCE(rdp->cond_resched_completed, READ_ONCE(rdp->mynode->completed)); @@ -1220,11 +1317,12 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ } - /* And if it has been a really long time, kick the CPU as well. */ - if (ULONG_CMP_GE(jiffies, - rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) || - ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) - resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ + /* + * If more than halfway to RCU CPU stall-warning time, do + * a resched_cpu() to try to loosen things up a bit. + */ + if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) + resched_cpu(rdp->cpu); return 0; } @@ -1277,7 +1375,10 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) } /* - * Dump stacks of all tasks running on stalled CPUs. + * Dump stacks of all tasks running on stalled CPUs. First try using + * NMIs, but fall back to manual remote stack tracing on architectures + * that don't support NMI-based stack dumps. The NMI-triggered stack + * traces are more accurate because they are printed by the target CPU. */ static void rcu_dump_cpu_stacks(struct rcu_state *rsp) { @@ -1287,11 +1388,10 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp) rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); - if (rnp->qsmask != 0) { - for_each_leaf_node_possible_cpu(rnp, cpu) - if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) + for_each_leaf_node_possible_cpu(rnp, cpu) + if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) + if (!trigger_single_cpu_backtrace(cpu)) dump_cpu_task(cpu); - } raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -1379,6 +1479,9 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) (long)rsp->gpnum, (long)rsp->completed, 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) { @@ -1395,9 +1498,6 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) } } - /* Complain about tasks blocking the grace period. */ - rcu_print_detail_task_stall(rsp); - rcu_check_gp_kthread_starvation(rsp); panic_on_rcu_stall(); @@ -2467,10 +2567,8 @@ 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->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) || - rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum || - rdp->gpwrap) { + if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum || + rnp->completed == rnp->gpnum || rdp->gpwrap) { /* * The grace period in which this quiescent state was @@ -2525,8 +2623,7 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Was there a quiescent state since the beginning of the grace * period? If no, then exit and wait for the next call. */ - if (rdp->cpu_no_qs.b.norm && - rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) + if (rdp->cpu_no_qs.b.norm) return; /* @@ -3480,9 +3577,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) rdp->core_needs_qs && rdp->cpu_no_qs.b.norm && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) { rdp->n_rp_core_needs_qs++; - } else if (rdp->core_needs_qs && - (!rdp->cpu_no_qs.b.norm || - rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) { + } else if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm) { rdp->n_rp_report_qs++; return 1; } @@ -3748,7 +3843,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu); rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); - WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); + WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks))); rdp->cpu = cpu; rdp->rsp = rsp; rcu_boot_init_nocb_percpu_data(rdp); @@ -3765,7 +3860,6 @@ static void rcu_init_percpu_data(int cpu, struct rcu_state *rsp) { unsigned long flags; - unsigned long mask; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); @@ -3778,8 +3872,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) init_callback_list(rdp); /* Re-enable callbacks on this CPU. */ rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; rcu_sysidle_init_percpu_data(rdp->dynticks); - atomic_set(&rdp->dynticks->dynticks, - (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); + rcu_dynticks_eqs_online(); raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ /* @@ -3788,7 +3881,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) * of the next grace period. */ rnp = rdp->mynode; - mask = rdp->grpmask; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ if (!rdp->beenonline) WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1); @@ -3872,7 +3964,7 @@ void rcu_cpu_starting(unsigned int cpu) struct rcu_state *rsp; for_each_rcu_flavor(rsp) { - rdp = this_cpu_ptr(rsp->rda); + rdp = per_cpu_ptr(rsp->rda, cpu); rnp = rdp->mynode; mask = rdp->grpmask; raw_spin_lock_irqsave_rcu_node(rnp, flags); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index fe98dd24adf8..b60f2b6caa14 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -521,7 +521,6 @@ struct rcu_state { struct mutex exp_mutex; /* Serialize expedited GP. */ struct mutex exp_wake_mutex; /* Serialize wakeup. */ unsigned long expedited_sequence; /* Take a ticket. */ - atomic_long_t expedited_normal; /* # fallbacks to normal. */ atomic_t expedited_need_qs; /* # CPUs left to check in. */ struct swait_queue_head expedited_wq; /* Wait for check-ins. */ int ncpus_snap; /* # CPUs seen last time. */ @@ -595,6 +594,8 @@ extern struct rcu_state rcu_bh_state; extern struct rcu_state rcu_preempt_state; #endif /* #ifdef CONFIG_PREEMPT_RCU */ +int rcu_dynticks_snap(struct rcu_dynticks *rdtp); + #ifdef CONFIG_RCU_BOOST DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); @@ -688,18 +689,6 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) #endif /* #ifdef CONFIG_RCU_TRACE */ /* - * Place this after a lock-acquisition primitive to guarantee that - * an UNLOCK+LOCK pair act as a full barrier. This guarantee applies - * if the UNLOCK and LOCK are executed by the same CPU or if the - * UNLOCK and LOCK operate on the same lock variable. - */ -#ifdef CONFIG_PPC -#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ -#else /* #ifdef CONFIG_PPC */ -#define smp_mb__after_unlock_lock() do { } while (0) -#endif /* #else #ifdef CONFIG_PPC */ - -/* * Wrappers for the rcu_node::lock acquire and release. * * Because the rcu_nodes form a tree, the tree traversal locking will observe diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index e59e1849b89a..a7b639ccd46e 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -20,16 +20,26 @@ * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ -/* Wrapper functions for expedited grace periods. */ +/* + * Record the start of an expedited grace period. + */ static void rcu_exp_gp_seq_start(struct rcu_state *rsp) { rcu_seq_start(&rsp->expedited_sequence); } + +/* + * Record the end of an expedited grace period. + */ static void rcu_exp_gp_seq_end(struct rcu_state *rsp) { rcu_seq_end(&rsp->expedited_sequence); smp_mb(); /* Ensure that consecutive grace periods serialize. */ } + +/* + * Take a snapshot of the expedited-grace-period counter. + */ static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp) { unsigned long s; @@ -39,6 +49,12 @@ static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp) trace_rcu_exp_grace_period(rsp->name, s, TPS("snap")); return s; } + +/* + * Given a counter snapshot from rcu_exp_gp_seq_snap(), return true + * if a full expedited grace period has elapsed since that snapshot + * was taken. + */ static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) { return rcu_seq_done(&rsp->expedited_sequence, s); @@ -356,12 +372,11 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, mask_ofl_test = 0; for_each_leaf_node_possible_cpu(rnp, cpu) { struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); rdp->exp_dynticks_snap = - atomic_add_return(0, &rdtp->dynticks); + rcu_dynticks_snap(rdp->dynticks); if (raw_smp_processor_id() == cpu || - !(rdp->exp_dynticks_snap & 0x1) || + rcu_dynticks_in_eqs(rdp->exp_dynticks_snap) || !(rnp->qsmaskinitnext & rdp->grpmask)) mask_ofl_test |= rdp->grpmask; } @@ -380,13 +395,12 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, for_each_leaf_node_possible_cpu(rnp, cpu) { unsigned long mask = leaf_node_cpu_bit(rnp, cpu); struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); if (!(mask_ofl_ipi & mask)) continue; retry_ipi: - if (atomic_add_return(0, &rdtp->dynticks) != - rdp->exp_dynticks_snap) { + if (rcu_dynticks_in_eqs_since(rdp->dynticks, + rdp->exp_dynticks_snap)) { mask_ofl_test |= mask; continue; } @@ -623,6 +637,11 @@ void synchronize_sched_expedited(void) { struct rcu_state *rsp = &rcu_sched_state; + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_sched_expedited() in RCU read-side critical section"); + /* If only one CPU, this is automatically a grace period. */ if (rcu_blocking_is_gp()) return; @@ -692,6 +711,11 @@ void synchronize_rcu_expedited(void) { struct rcu_state *rsp = rcu_state_p; + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu_expedited() in RCU read-side critical section"); + if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) return; _synchronize_rcu_expedited(rsp, sync_rcu_exp_handler); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 56583e764ebf..a240f3308be6 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1643,7 +1643,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)], "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)], ticks_value, ticks_title, - atomic_read(&rdtp->dynticks) & 0xfff, + rcu_dynticks_snap(rdtp) & 0xfff, rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting, rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart, @@ -2366,8 +2366,9 @@ static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp) } /* - * Each pass through this loop sets up one rcu_data structure and - * spawns one rcu_nocb_kthread(). + * Each pass through this loop sets up one rcu_data structure. + * Should the corresponding CPU come online in the future, then + * we will spawn the needed set of rcu_nocb_kthread() kthreads. */ for_each_cpu(cpu, rcu_nocb_mask) { rdp = per_cpu_ptr(rsp->rda, cpu); diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index b1f28972872c..8751a748499a 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -124,7 +124,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu), rdp->core_needs_qs); seq_printf(m, " dt=%d/%llx/%d df=%lu", - atomic_read(&rdp->dynticks->dynticks), + rcu_dynticks_snap(rdp->dynticks), rdp->dynticks->dynticks_nesting, rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); @@ -194,9 +194,8 @@ static int show_rcuexp(struct seq_file *m, void *v) s2 += atomic_long_read(&rdp->exp_workdone2); s3 += atomic_long_read(&rdp->exp_workdone3); } - seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n", + seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu enq=%d sc=%lu\n", rsp->expedited_sequence, s0, s1, s2, s3, - atomic_long_read(&rsp->expedited_normal), atomic_read(&rsp->expedited_need_qs), rsp->expedited_sequence / 2); return 0; diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 4f6db7e6a117..9e03db9ea9c0 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -132,8 +132,7 @@ bool rcu_gp_is_normal(void) } EXPORT_SYMBOL_GPL(rcu_gp_is_normal); -static atomic_t rcu_expedited_nesting = - ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0); +static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1); /* * Should normal grace-period primitives be expedited? Intended for @@ -182,8 +181,7 @@ EXPORT_SYMBOL_GPL(rcu_unexpedite_gp); */ void rcu_end_inkernel_boot(void) { - if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT)) - rcu_unexpedite_gp(); + rcu_unexpedite_gp(); if (rcu_normal_after_boot) WRITE_ONCE(rcu_normal, 1); } diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 5e59b832ae2b..89ab6758667b 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -18,8 +18,8 @@ endif obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o obj-y += wait.o swait.o completion.o idle.o -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o -obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o +obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o +obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o diff --git a/kernel/sched/auto_group.c b/kernel/sched/autogroup.c index da39489d2d80..da39489d2d80 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/autogroup.c diff --git a/kernel/sched/auto_group.h b/kernel/sched/autogroup.h index 890c95f2587a..890c95f2587a 100644 --- a/kernel/sched/auto_group.h +++ b/kernel/sched/autogroup.h diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index e85a725e5c34..ad64efe41722 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -77,41 +77,88 @@ EXPORT_SYMBOL_GPL(sched_clock); __read_mostly int sched_clock_running; +void sched_clock_init(void) +{ + sched_clock_running = 1; +} + #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -static struct static_key __sched_clock_stable = STATIC_KEY_INIT; -static int __sched_clock_stable_early; +/* + * We must start with !__sched_clock_stable because the unstable -> stable + * transition is accurate, while the stable -> unstable transition is not. + * + * Similarly we start with __sched_clock_stable_early, thereby assuming we + * will become stable, such that there's only a single 1 -> 0 transition. + */ +static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable); +static int __sched_clock_stable_early = 1; -int sched_clock_stable(void) +/* + * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset + */ +static __read_mostly u64 raw_offset; +static __read_mostly u64 gtod_offset; + +struct sched_clock_data { + u64 tick_raw; + u64 tick_gtod; + u64 clock; +}; + +static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data); + +static inline struct sched_clock_data *this_scd(void) { - return static_key_false(&__sched_clock_stable); + return this_cpu_ptr(&sched_clock_data); } -static void __set_sched_clock_stable(void) +static inline struct sched_clock_data *cpu_sdc(int cpu) { - if (!sched_clock_stable()) - static_key_slow_inc(&__sched_clock_stable); + return &per_cpu(sched_clock_data, cpu); +} - tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); +int sched_clock_stable(void) +{ + return static_branch_likely(&__sched_clock_stable); } -void set_sched_clock_stable(void) +static void __set_sched_clock_stable(void) { - __sched_clock_stable_early = 1; + struct sched_clock_data *scd = this_scd(); - smp_mb(); /* matches sched_clock_init() */ + /* + * Attempt to make the (initial) unstable->stable transition continuous. + */ + raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw); - if (!sched_clock_running) - return; + printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n", + scd->tick_gtod, gtod_offset, + scd->tick_raw, raw_offset); - __set_sched_clock_stable(); + static_branch_enable(&__sched_clock_stable); + tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); } static void __clear_sched_clock_stable(struct work_struct *work) { - /* XXX worry about clock continuity */ - if (sched_clock_stable()) - static_key_slow_dec(&__sched_clock_stable); + struct sched_clock_data *scd = this_scd(); + + /* + * Attempt to make the stable->unstable transition continuous. + * + * Trouble is, this is typically called from the TSC watchdog + * timer, which is late per definition. This means the tick + * values can already be screwy. + * + * Still do what we can. + */ + gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod); + + printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n", + scd->tick_gtod, gtod_offset, + scd->tick_raw, raw_offset); + static_branch_disable(&__sched_clock_stable); tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE); } @@ -121,47 +168,15 @@ void clear_sched_clock_stable(void) { __sched_clock_stable_early = 0; - smp_mb(); /* matches sched_clock_init() */ - - if (!sched_clock_running) - return; + smp_mb(); /* matches sched_clock_init_late() */ - schedule_work(&sched_clock_work); + if (sched_clock_running == 2) + schedule_work(&sched_clock_work); } -struct sched_clock_data { - u64 tick_raw; - u64 tick_gtod; - u64 clock; -}; - -static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data); - -static inline struct sched_clock_data *this_scd(void) +void sched_clock_init_late(void) { - return this_cpu_ptr(&sched_clock_data); -} - -static inline struct sched_clock_data *cpu_sdc(int cpu) -{ - return &per_cpu(sched_clock_data, cpu); -} - -void sched_clock_init(void) -{ - u64 ktime_now = ktime_to_ns(ktime_get()); - int cpu; - - for_each_possible_cpu(cpu) { - struct sched_clock_data *scd = cpu_sdc(cpu); - - scd->tick_raw = 0; - scd->tick_gtod = ktime_now; - scd->clock = ktime_now; - } - - sched_clock_running = 1; - + sched_clock_running = 2; /* * Ensure that it is impossible to not do a static_key update. * @@ -173,8 +188,6 @@ void sched_clock_init(void) if (__sched_clock_stable_early) __set_sched_clock_stable(); - else - __clear_sched_clock_stable(NULL); } /* @@ -216,7 +229,7 @@ again: * scd->tick_gtod + TICK_NSEC); */ - clock = scd->tick_gtod + delta; + clock = scd->tick_gtod + gtod_offset + delta; min_clock = wrap_max(scd->tick_gtod, old_clock); max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC); @@ -302,7 +315,7 @@ u64 sched_clock_cpu(int cpu) u64 clock; if (sched_clock_stable()) - return sched_clock(); + return sched_clock() + raw_offset; if (unlikely(!sched_clock_running)) return 0ull; @@ -323,23 +336,22 @@ EXPORT_SYMBOL_GPL(sched_clock_cpu); void sched_clock_tick(void) { struct sched_clock_data *scd; - u64 now, now_gtod; - - if (sched_clock_stable()) - return; - - if (unlikely(!sched_clock_running)) - return; WARN_ON_ONCE(!irqs_disabled()); + /* + * Update these values even if sched_clock_stable(), because it can + * become unstable at any point in time at which point we need some + * values to fall back on. + * + * XXX arguably we can skip this if we expose tsc_clocksource_reliable + */ scd = this_scd(); - now_gtod = ktime_to_ns(ktime_get()); - now = sched_clock(); + scd->tick_raw = sched_clock(); + scd->tick_gtod = ktime_get_ns(); - scd->tick_raw = now; - scd->tick_gtod = now_gtod; - sched_clock_local(scd); + if (!sched_clock_stable() && likely(sched_clock_running)) + sched_clock_local(scd); } /* @@ -366,11 +378,6 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ -void sched_clock_init(void) -{ - sched_clock_running = 1; -} - u64 sched_clock_cpu(int cpu) { if (unlikely(!sched_clock_running)) @@ -378,6 +385,7 @@ u64 sched_clock_cpu(int cpu) return sched_clock(); } + #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ /* diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index 8d0f35debf35..f063a25d4449 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -31,7 +31,8 @@ void complete(struct completion *x) unsigned long flags; spin_lock_irqsave(&x->wait.lock, flags); - x->done++; + if (x->done != UINT_MAX) + x->done++; __wake_up_locked(&x->wait, TASK_NORMAL, 1); spin_unlock_irqrestore(&x->wait.lock, flags); } @@ -51,7 +52,7 @@ void complete_all(struct completion *x) unsigned long flags; spin_lock_irqsave(&x->wait.lock, flags); - x->done += UINT_MAX/2; + x->done = UINT_MAX; __wake_up_locked(&x->wait, TASK_NORMAL, 0); spin_unlock_irqrestore(&x->wait.lock, flags); } @@ -79,7 +80,8 @@ do_wait_for_common(struct completion *x, if (!x->done) return timeout; } - x->done--; + if (x->done != UINT_MAX) + x->done--; return timeout ?: 1; } @@ -280,7 +282,7 @@ bool try_wait_for_completion(struct completion *x) spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; - else + else if (x->done != UINT_MAX) x->done--; spin_unlock_irqrestore(&x->wait.lock, flags); return ret; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c56fb57f2991..34e2291a9a6c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1,88 +1,28 @@ /* * kernel/sched/core.c * - * Kernel scheduler and related syscalls + * Core kernel scheduler code and related syscalls * * Copyright (C) 1991-2002 Linus Torvalds - * - * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and - * make semaphores SMP safe - * 1998-11-19 Implemented schedule_timeout() and related stuff - * by Andrea Arcangeli - * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: - * hybrid priority-list and round-robin design with - * an array-switch method of distributing timeslices - * and per-CPU runqueues. Cleanups and useful suggestions - * by Davide Libenzi, preemptible kernel bits by Robert Love. - * 2003-09-03 Interactivity tuning by Con Kolivas. - * 2004-04-02 Scheduler domains code by Nick Piggin - * 2007-04-15 Work begun on replacing all interactivity tuning with a - * fair scheduling design by Con Kolivas. - * 2007-05-05 Load balancing (smp-nice) and other improvements - * by Peter Williams - * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith - * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri - * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins, - * Thomas Gleixner, Mike Kravetz */ - -#include <linux/kasan.h> -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/nmi.h> -#include <linux/init.h> -#include <linux/uaccess.h> -#include <linux/highmem.h> -#include <linux/mmu_context.h> -#include <linux/interrupt.h> -#include <linux/capability.h> -#include <linux/completion.h> -#include <linux/kernel_stat.h> -#include <linux/debug_locks.h> -#include <linux/perf_event.h> -#include <linux/security.h> -#include <linux/notifier.h> -#include <linux/profile.h> -#include <linux/freezer.h> -#include <linux/vmalloc.h> -#include <linux/blkdev.h> -#include <linux/delay.h> -#include <linux/pid_namespace.h> -#include <linux/smp.h> -#include <linux/threads.h> -#include <linux/timer.h> -#include <linux/rcupdate.h> -#include <linux/cpu.h> +#include <linux/sched.h> #include <linux/cpuset.h> -#include <linux/percpu.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/sysctl.h> -#include <linux/syscalls.h> -#include <linux/times.h> -#include <linux/tsacct_kern.h> -#include <linux/kprobes.h> #include <linux/delayacct.h> -#include <linux/unistd.h> -#include <linux/pagemap.h> -#include <linux/hrtimer.h> -#include <linux/tick.h> -#include <linux/ctype.h> -#include <linux/ftrace.h> -#include <linux/slab.h> #include <linux/init_task.h> #include <linux/context_tracking.h> -#include <linux/compiler.h> -#include <linux/frame.h> + +#include <linux/blkdev.h> +#include <linux/kprobes.h> +#include <linux/mmu_context.h> +#include <linux/module.h> +#include <linux/nmi.h> #include <linux/prefetch.h> -#include <linux/mutex.h> +#include <linux/profile.h> +#include <linux/security.h> +#include <linux/syscalls.h> #include <asm/switch_to.h> #include <asm/tlb.h> -#include <asm/irq_regs.h> -#ifdef CONFIG_PARAVIRT -#include <asm/paravirt.h> -#endif #include "sched.h" #include "../workqueue_internal.h" @@ -91,27 +31,8 @@ #define CREATE_TRACE_POINTS #include <trace/events/sched.h> -DEFINE_MUTEX(sched_domains_mutex); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -static void update_rq_clock_task(struct rq *rq, s64 delta); - -void update_rq_clock(struct rq *rq) -{ - s64 delta; - - lockdep_assert_held(&rq->lock); - - if (rq->clock_skip_update & RQCF_ACT_SKIP) - return; - - delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; - if (delta < 0) - return; - rq->clock += delta; - update_rq_clock_task(rq, delta); -} - /* * Debugging: various feature bits */ @@ -140,7 +61,7 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32; const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; /* - * period over which we measure -rt task cpu usage in us. + * period over which we measure -rt task CPU usage in us. * default: 1s */ unsigned int sysctl_sched_rt_period = 1000000; @@ -153,7 +74,7 @@ __read_mostly int scheduler_running; */ int sysctl_sched_rt_runtime = 950000; -/* cpus with isolated domains */ +/* CPUs with isolated domains */ cpumask_var_t cpu_isolated_map; /* @@ -185,7 +106,7 @@ struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) rq = task_rq(p); raw_spin_lock(&rq->lock); if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { - rf->cookie = lockdep_pin_lock(&rq->lock); + rq_pin_lock(rq, rf); return rq; } raw_spin_unlock(&rq->lock); @@ -221,11 +142,11 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) * If we observe the old cpu in task_rq_lock, the acquire of * the old rq->lock will fully serialize against the stores. * - * If we observe the new cpu in task_rq_lock, the acquire will + * If we observe the new CPU in task_rq_lock, the acquire will * pair with the WMB to ensure we must then also see migrating. */ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { - rf->cookie = lockdep_pin_lock(&rq->lock); + rq_pin_lock(rq, rf); return rq; } raw_spin_unlock(&rq->lock); @@ -236,6 +157,84 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) } } +/* + * RQ-clock updating methods: + */ + +static void update_rq_clock_task(struct rq *rq, s64 delta) +{ +/* + * In theory, the compile should just see 0 here, and optimize out the call + * to sched_rt_avg_update. But I don't trust it... + */ +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + s64 steal = 0, irq_delta = 0; +#endif +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; + + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}irq region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}irq + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; + + rq->prev_irq_time += irq_delta; + delta -= irq_delta; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (static_key_false((¶virt_steal_rq_enabled))) { + steal = paravirt_steal_clock(cpu_of(rq)); + steal -= rq->prev_steal_time_rq; + + if (unlikely(steal > delta)) + steal = delta; + + rq->prev_steal_time_rq += steal; + delta -= steal; + } +#endif + + rq->clock_task += delta; + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) + sched_rt_avg_update(rq, irq_delta + steal); +#endif +} + +void update_rq_clock(struct rq *rq) +{ + s64 delta; + + lockdep_assert_held(&rq->lock); + + if (rq->clock_update_flags & RQCF_ACT_SKIP) + return; + +#ifdef CONFIG_SCHED_DEBUG + rq->clock_update_flags |= RQCF_UPDATED; +#endif + delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + if (delta < 0) + return; + rq->clock += delta; + update_rq_clock_task(rq, delta); +} + + #ifdef CONFIG_SCHED_HRTICK /* * Use HR-timers to deliver accurate preemption points. @@ -458,7 +457,7 @@ void wake_up_q(struct wake_q_head *head) task = container_of(node, struct task_struct, wake_q); BUG_ON(!task); - /* task can safely be re-inserted now */ + /* Task can safely be re-inserted now: */ node = node->next; task->wake_q.next = NULL; @@ -516,12 +515,12 @@ void resched_cpu(int cpu) #ifdef CONFIG_SMP #ifdef CONFIG_NO_HZ_COMMON /* - * In the semi idle case, use the nearest busy cpu for migrating timers - * from an idle cpu. This is good for power-savings. + * In the semi idle case, use the nearest busy CPU for migrating timers + * from an idle CPU. This is good for power-savings. * * We don't do similar optimization for completely idle system, as - * selecting an idle cpu will add more delays to the timers than intended - * (as that cpu's timer base may not be uptodate wrt jiffies etc). + * selecting an idle CPU will add more delays to the timers than intended + * (as that CPU's timer base may not be uptodate wrt jiffies etc). */ int get_nohz_timer_target(void) { @@ -550,6 +549,7 @@ unlock: rcu_read_unlock(); return cpu; } + /* * When add_timer_on() enqueues a timer into the timer wheel of an * idle CPU then this timer might expire before the next timer event @@ -784,60 +784,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -static void update_rq_clock_task(struct rq *rq, s64 delta) -{ -/* - * In theory, the compile should just see 0 here, and optimize out the call - * to sched_rt_avg_update. But I don't trust it... - */ -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) - s64 steal = 0, irq_delta = 0; -#endif -#ifdef CONFIG_IRQ_TIME_ACCOUNTING - irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; - - /* - * Since irq_time is only updated on {soft,}irq_exit, we might run into - * this case when a previous update_rq_clock() happened inside a - * {soft,}irq region. - * - * When this happens, we stop ->clock_task and only update the - * prev_irq_time stamp to account for the part that fit, so that a next - * update will consume the rest. This ensures ->clock_task is - * monotonic. - * - * It does however cause some slight miss-attribution of {soft,}irq - * time, a more accurate solution would be to update the irq_time using - * the current rq->clock timestamp, except that would require using - * atomic ops. - */ - if (irq_delta > delta) - irq_delta = delta; - - rq->prev_irq_time += irq_delta; - delta -= irq_delta; -#endif -#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING - if (static_key_false((¶virt_steal_rq_enabled))) { - steal = paravirt_steal_clock(cpu_of(rq)); - steal -= rq->prev_steal_time_rq; - - if (unlikely(steal > delta)) - steal = delta; - - rq->prev_steal_time_rq += steal; - delta -= steal; - } -#endif - - rq->clock_task += delta; - -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) - if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) - sched_rt_avg_update(rq, irq_delta + steal); -#endif -} - void sched_set_stop_task(int cpu, struct task_struct *stop) { struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; @@ -1018,7 +964,7 @@ struct migration_arg { }; /* - * Move (not current) task off this cpu, onto dest cpu. We're doing + * Move (not current) task off this CPU, onto the destination CPU. We're doing * this because either it can't run here any more (set_cpus_allowed() * away from this CPU, or CPU going down), or because we're * attempting to rebalance this task on exec (sched_exec). @@ -1052,8 +998,8 @@ static int migration_cpu_stop(void *data) struct rq *rq = this_rq(); /* - * The original target cpu might have gone down and we might - * be on another cpu but it doesn't matter. + * The original target CPU might have gone down and we might + * be on another CPU but it doesn't matter. */ local_irq_disable(); /* @@ -1171,7 +1117,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, if (p->flags & PF_KTHREAD) { /* * For kernel threads that do indeed end up on online && - * !active we want to ensure they are strict per-cpu threads. + * !active we want to ensure they are strict per-CPU threads. */ WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) && !cpumask_intersects(new_mask, cpu_active_mask) && @@ -1195,9 +1141,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, * OK, since we're going to drop the lock immediately * afterwards anyway. */ - lockdep_unpin_lock(&rq->lock, rf.cookie); + rq_unpin_lock(rq, &rf); rq = move_queued_task(rq, p, dest_cpu); - lockdep_repin_lock(&rq->lock, rf.cookie); + rq_repin_lock(rq, &rf); } out: task_rq_unlock(rq, p, &rf); @@ -1276,7 +1222,7 @@ static void __migrate_swap_task(struct task_struct *p, int cpu) /* * Task isn't running anymore; make it appear like we migrated * it before it went to sleep. This means on wakeup we make the - * previous cpu our target instead of where it really is. + * previous CPU our target instead of where it really is. */ p->wake_cpu = cpu; } @@ -1508,12 +1454,12 @@ EXPORT_SYMBOL_GPL(kick_process); * * - on cpu-up we allow per-cpu kthreads on the online && !active cpu, * see __set_cpus_allowed_ptr(). At this point the newly online - * cpu isn't yet part of the sched domains, and balancing will not + * CPU isn't yet part of the sched domains, and balancing will not * see it. * - * - on cpu-down we clear cpu_active() to mask the sched domains and + * - on CPU-down we clear cpu_active() to mask the sched domains and * avoid the load balancer to place new tasks on the to be removed - * cpu. Existing tasks will remain running there and will be taken + * CPU. Existing tasks will remain running there and will be taken * off. * * This means that fallback selection must not select !active CPUs. @@ -1529,9 +1475,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) int dest_cpu; /* - * If the node that the cpu is on has been offlined, cpu_to_node() - * will return -1. There is no cpu on the node, and we should - * select the cpu on the other node. + * If the node that the CPU is on has been offlined, cpu_to_node() + * will return -1. There is no CPU on the node, and we should + * select the CPU on the other node. */ if (nid != -1) { nodemask = cpumask_of_node(nid); @@ -1563,7 +1509,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) state = possible; break; } - /* fall-through */ + /* Fall-through */ case possible: do_set_cpus_allowed(p, cpu_possible_mask); state = fail; @@ -1607,7 +1553,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) /* * In order not to call set_task_cpu() on a blocking task we need * to rely on ttwu() to place the task on a valid ->cpus_allowed - * cpu. + * CPU. * * Since this is common to all placement strategies, this lives here. * @@ -1681,7 +1627,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl activate_task(rq, p, en_flags); p->on_rq = TASK_ON_RQ_QUEUED; - /* if a worker is waking up, notify workqueue */ + /* If a worker is waking up, notify the workqueue: */ if (p->flags & PF_WQ_WORKER) wq_worker_waking_up(p, cpu_of(rq)); } @@ -1690,7 +1636,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl * Mark the task runnable and perform wakeup-preemption. */ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, - struct pin_cookie cookie) + struct rq_flags *rf) { check_preempt_curr(rq, p, wake_flags); p->state = TASK_RUNNING; @@ -1702,9 +1648,9 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, * Our task @p is fully woken up and running; so its safe to * drop the rq->lock, hereafter rq is only used for statistics. */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, rf); p->sched_class->task_woken(rq, p); - lockdep_repin_lock(&rq->lock, cookie); + rq_repin_lock(rq, rf); } if (rq->idle_stamp) { @@ -1723,7 +1669,7 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, static void ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, - struct pin_cookie cookie) + struct rq_flags *rf) { int en_flags = ENQUEUE_WAKEUP; @@ -1738,7 +1684,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, #endif ttwu_activate(rq, p, en_flags); - ttwu_do_wakeup(rq, p, wake_flags, cookie); + ttwu_do_wakeup(rq, p, wake_flags, rf); } /* @@ -1757,7 +1703,7 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) if (task_on_rq_queued(p)) { /* check_preempt_curr() may use rq clock */ update_rq_clock(rq); - ttwu_do_wakeup(rq, p, wake_flags, rf.cookie); + ttwu_do_wakeup(rq, p, wake_flags, &rf); ret = 1; } __task_rq_unlock(rq, &rf); @@ -1770,15 +1716,15 @@ void sched_ttwu_pending(void) { struct rq *rq = this_rq(); struct llist_node *llist = llist_del_all(&rq->wake_list); - struct pin_cookie cookie; struct task_struct *p; unsigned long flags; + struct rq_flags rf; if (!llist) return; raw_spin_lock_irqsave(&rq->lock, flags); - cookie = lockdep_pin_lock(&rq->lock); + rq_pin_lock(rq, &rf); while (llist) { int wake_flags = 0; @@ -1789,10 +1735,10 @@ void sched_ttwu_pending(void) if (p->sched_remote_wakeup) wake_flags = WF_MIGRATED; - ttwu_do_activate(rq, p, wake_flags, cookie); + ttwu_do_activate(rq, p, wake_flags, &rf); } - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, &rf); raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -1864,7 +1810,7 @@ void wake_up_if_idle(int cpu) raw_spin_lock_irqsave(&rq->lock, flags); if (is_idle_task(rq->curr)) smp_send_reschedule(cpu); - /* Else cpu is not in idle, do nothing here */ + /* Else CPU is not idle, do nothing here: */ raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -1881,20 +1827,20 @@ bool cpus_share_cache(int this_cpu, int that_cpu) static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) { struct rq *rq = cpu_rq(cpu); - struct pin_cookie cookie; + struct rq_flags rf; #if defined(CONFIG_SMP) if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { - sched_clock_cpu(cpu); /* sync clocks x-cpu */ + sched_clock_cpu(cpu); /* Sync clocks across CPUs */ ttwu_queue_remote(p, cpu, wake_flags); return; } #endif raw_spin_lock(&rq->lock); - cookie = lockdep_pin_lock(&rq->lock); - ttwu_do_activate(rq, p, wake_flags, cookie); - lockdep_unpin_lock(&rq->lock, cookie); + rq_pin_lock(rq, &rf); + ttwu_do_activate(rq, p, wake_flags, &rf); + rq_unpin_lock(rq, &rf); raw_spin_unlock(&rq->lock); } @@ -1904,8 +1850,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * MIGRATION * * The basic program-order guarantee on SMP systems is that when a task [t] - * migrates, all its activity on its old cpu [c0] happens-before any subsequent - * execution on its new cpu [c1]. + * migrates, all its activity on its old CPU [c0] happens-before any subsequent + * execution on its new CPU [c1]. * * For migration (of runnable tasks) this is provided by the following means: * @@ -1916,7 +1862,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * * Transitivity guarantees that B happens after A and C after B. * Note: we only require RCpc transitivity. - * Note: the cpu doing B need not be c0 or c1 + * Note: the CPU doing B need not be c0 or c1 * * Example: * @@ -2024,7 +1970,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) trace_sched_waking(p); - success = 1; /* we're going to change ->state */ + /* We're going to change ->state: */ + success = 1; cpu = task_cpu(p); /* @@ -2073,7 +2020,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) smp_rmb(); /* - * If the owning (remote) cpu is still in the middle of schedule() with + * If the owning (remote) CPU is still in the middle of schedule() with * this task as prev, wait until its done referencing the task. * * Pairs with the smp_store_release() in finish_lock_switch(). @@ -2086,11 +2033,24 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; + if (p->in_iowait) { + delayacct_blkio_end(); + atomic_dec(&task_rq(p)->nr_iowait); + } + cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; set_task_cpu(p, cpu); } + +#else /* CONFIG_SMP */ + + if (p->in_iowait) { + delayacct_blkio_end(); + atomic_dec(&task_rq(p)->nr_iowait); + } + #endif /* CONFIG_SMP */ ttwu_queue(p, cpu, wake_flags); @@ -2111,7 +2071,7 @@ out: * ensure that this_rq() is locked, @p is bound to this_rq() and not * the current task. */ -static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie) +static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf) { struct rq *rq = task_rq(p); @@ -2128,11 +2088,11 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie * disabled avoiding further scheduler activity on it and we've * not yet picked a replacement task. */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, rf); raw_spin_unlock(&rq->lock); raw_spin_lock(&p->pi_lock); raw_spin_lock(&rq->lock); - lockdep_repin_lock(&rq->lock, cookie); + rq_repin_lock(rq, rf); } if (!(p->state & TASK_NORMAL)) @@ -2140,10 +2100,15 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie trace_sched_waking(p); - if (!task_on_rq_queued(p)) + if (!task_on_rq_queued(p)) { + if (p->in_iowait) { + delayacct_blkio_end(); + atomic_dec(&rq->nr_iowait); + } ttwu_activate(rq, p, ENQUEUE_WAKEUP); + } - ttwu_do_wakeup(rq, p, 0, cookie); + ttwu_do_wakeup(rq, p, 0, rf); ttwu_stat(p, smp_processor_id(), 0); out: raw_spin_unlock(&p->pi_lock); @@ -2427,7 +2392,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) */ raw_spin_lock_irqsave(&p->pi_lock, flags); /* - * We're setting the cpu for the first time, we don't migrate, + * We're setting the CPU for the first time, we don't migrate, * so use __set_task_cpu(). */ __set_task_cpu(p, cpu); @@ -2570,7 +2535,7 @@ void wake_up_new_task(struct task_struct *p) /* * Fork balancing, do it here and not earlier because: * - cpus_allowed can change in the fork path - * - any previously selected cpu might disappear through hotplug + * - any previously selected CPU might disappear through hotplug * * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, * as we're not fully set-up yet. @@ -2578,6 +2543,7 @@ void wake_up_new_task(struct task_struct *p) __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif rq = __task_rq_lock(p, &rf); + update_rq_clock(rq); post_init_entity_util_avg(&p->se); activate_task(rq, p, 0); @@ -2590,9 +2556,9 @@ void wake_up_new_task(struct task_struct *p) * Nothing relies on rq->lock after this, so its fine to * drop it. */ - lockdep_unpin_lock(&rq->lock, rf.cookie); + rq_unpin_lock(rq, &rf); p->sched_class->task_woken(rq, p); - lockdep_repin_lock(&rq->lock, rf.cookie); + rq_repin_lock(rq, &rf); } #endif task_rq_unlock(rq, p, &rf); @@ -2861,7 +2827,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) */ static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev, - struct task_struct *next, struct pin_cookie cookie) + struct task_struct *next, struct rq_flags *rf) { struct mm_struct *mm, *oldmm; @@ -2887,13 +2853,16 @@ context_switch(struct rq *rq, struct task_struct *prev, prev->active_mm = NULL; rq->prev_mm = oldmm; } + + rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); + /* * Since the runqueue lock will be released by the next * task (which is an invalid locking op but in the case * of the scheduler it's an obvious special-case), so we * do an early lockdep release here: */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, rf); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); /* Here we just switch the register state and the stack. */ @@ -2920,7 +2889,7 @@ unsigned long nr_running(void) } /* - * Check if only the current task is running on the cpu. + * Check if only the current task is running on the CPU. * * Caution: this function does not check that the caller has disabled * preemption, thus the result might have a time-of-check-to-time-of-use @@ -2949,6 +2918,36 @@ unsigned long long nr_context_switches(void) return sum; } +/* + * IO-wait accounting, and how its mostly bollocks (on SMP). + * + * The idea behind IO-wait account is to account the idle time that we could + * have spend running if it were not for IO. That is, if we were to improve the + * storage performance, we'd have a proportional reduction in IO-wait time. + * + * This all works nicely on UP, where, when a task blocks on IO, we account + * idle time as IO-wait, because if the storage were faster, it could've been + * running and we'd not be idle. + * + * This has been extended to SMP, by doing the same for each CPU. This however + * is broken. + * + * Imagine for instance the case where two tasks block on one CPU, only the one + * CPU will have IO-wait accounted, while the other has regular idle. Even + * though, if the storage were faster, both could've ran at the same time, + * utilising both CPUs. + * + * This means, that when looking globally, the current IO-wait accounting on + * SMP is a lower bound, by reason of under accounting. + * + * Worse, since the numbers are provided per CPU, they are sometimes + * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly + * associated with any one particular CPU, it can wake to another CPU than it + * blocked on. This means the per CPU IO-wait number is meaningless. + * + * Task CPU affinities can make all that even more 'interesting'. + */ + unsigned long nr_iowait(void) { unsigned long i, sum = 0; @@ -2959,6 +2958,13 @@ unsigned long nr_iowait(void) return sum; } +/* + * Consumers of these two interfaces, like for example the cpufreq menu + * governor are using nonsensical data. Boosting frequency for a CPU that has + * IO-wait which might not even end up running the task when it does become + * runnable. + */ + unsigned long nr_iowait_cpu(int cpu) { struct rq *this = cpu_rq(cpu); @@ -3042,8 +3048,8 @@ unsigned long long task_sched_runtime(struct task_struct *p) * So we have a optimization chance when the task's delta_exec is 0. * Reading ->on_cpu is racy, but this is ok. * - * If we race with it leaving cpu, we'll take a lock. So we're correct. - * If we race with it entering cpu, unaccounted time is 0. This is + * If we race with it leaving CPU, we'll take a lock. So we're correct. + * If we race with it entering CPU, unaccounted time is 0. This is * indistinguishable from the read occurring a few cycles earlier. * If we see ->on_cpu without ->on_rq, the task is leaving, and has * been accounted, so we're correct here as well. @@ -3257,31 +3263,30 @@ static inline void schedule_debug(struct task_struct *prev) * Pick up the highest-prio task: */ static inline struct task_struct * -pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { - const struct sched_class *class = &fair_sched_class; + const struct sched_class *class; struct task_struct *p; /* * Optimization: we know that if all tasks are in * the fair class we can call that function directly: */ - if (likely(prev->sched_class == class && - rq->nr_running == rq->cfs.h_nr_running)) { - p = fair_sched_class.pick_next_task(rq, prev, cookie); + if (likely(rq->nr_running == rq->cfs.h_nr_running)) { + p = fair_sched_class.pick_next_task(rq, prev, rf); if (unlikely(p == RETRY_TASK)) goto again; - /* assumes fair_sched_class->next == idle_sched_class */ + /* Assumes fair_sched_class->next == idle_sched_class */ if (unlikely(!p)) - p = idle_sched_class.pick_next_task(rq, prev, cookie); + p = idle_sched_class.pick_next_task(rq, prev, rf); return p; } again: for_each_class(class) { - p = class->pick_next_task(rq, prev, cookie); + p = class->pick_next_task(rq, prev, rf); if (p) { if (unlikely(p == RETRY_TASK)) goto again; @@ -3289,7 +3294,8 @@ again: } } - BUG(); /* the idle class will always have a runnable task */ + /* The idle class should always have a runnable task: */ + BUG(); } /* @@ -3335,7 +3341,7 @@ static void __sched notrace __schedule(bool preempt) { struct task_struct *prev, *next; unsigned long *switch_count; - struct pin_cookie cookie; + struct rq_flags rf; struct rq *rq; int cpu; @@ -3358,9 +3364,10 @@ static void __sched notrace __schedule(bool preempt) */ smp_mb__before_spinlock(); raw_spin_lock(&rq->lock); - cookie = lockdep_pin_lock(&rq->lock); + rq_pin_lock(rq, &rf); - rq->clock_skip_update <<= 1; /* promote REQ to ACT */ + /* Promote REQ to ACT */ + rq->clock_update_flags <<= 1; switch_count = &prev->nivcsw; if (!preempt && prev->state) { @@ -3370,6 +3377,11 @@ static void __sched notrace __schedule(bool preempt) deactivate_task(rq, prev, DEQUEUE_SLEEP); prev->on_rq = 0; + if (prev->in_iowait) { + atomic_inc(&rq->nr_iowait); + delayacct_blkio_start(); + } + /* * If a worker went to sleep, notify and ask workqueue * whether it wants to wake up a task to maintain @@ -3380,7 +3392,7 @@ static void __sched notrace __schedule(bool preempt) to_wakeup = wq_worker_sleeping(prev); if (to_wakeup) - try_to_wake_up_local(to_wakeup, cookie); + try_to_wake_up_local(to_wakeup, &rf); } } switch_count = &prev->nvcsw; @@ -3389,10 +3401,9 @@ static void __sched notrace __schedule(bool preempt) if (task_on_rq_queued(prev)) update_rq_clock(rq); - next = pick_next_task(rq, prev, cookie); + next = pick_next_task(rq, prev, &rf); clear_tsk_need_resched(prev); clear_preempt_need_resched(); - rq->clock_skip_update = 0; if (likely(prev != next)) { rq->nr_switches++; @@ -3400,9 +3411,12 @@ static void __sched notrace __schedule(bool preempt) ++*switch_count; trace_sched_switch(preempt, prev, next); - rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */ + + /* Also unlocks the rq: */ + rq = context_switch(rq, prev, next, &rf); } else { - lockdep_unpin_lock(&rq->lock, cookie); + rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); + rq_unpin_lock(rq, &rf); raw_spin_unlock_irq(&rq->lock); } @@ -3426,14 +3440,18 @@ void __noreturn do_task_dead(void) smp_mb(); raw_spin_unlock_wait(¤t->pi_lock); - /* causes final put_task_struct in finish_task_switch(). */ + /* Causes final put_task_struct in finish_task_switch(): */ __set_current_state(TASK_DEAD); - current->flags |= PF_NOFREEZE; /* tell freezer to ignore us */ + + /* Tell freezer to ignore us: */ + current->flags |= PF_NOFREEZE; + __schedule(false); BUG(); - /* Avoid "noreturn function does return". */ + + /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */ for (;;) - cpu_relax(); /* For when BUG is null */ + cpu_relax(); } static inline void sched_submit_work(struct task_struct *tsk) @@ -3651,6 +3669,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) BUG_ON(prio > MAX_PRIO); rq = __task_rq_lock(p, &rf); + update_rq_clock(rq); /* * Idle task boosting is a nono in general. There is one @@ -3725,7 +3744,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio) check_class_changed(rq, p, prev_class, oldprio); out_unlock: - preempt_disable(); /* avoid rq from going away on us */ + /* Avoid rq from going away on us: */ + preempt_disable(); __task_rq_unlock(rq, &rf); balance_callback(rq); @@ -3747,6 +3767,8 @@ void set_user_nice(struct task_struct *p, long nice) * the task might be in the middle of scheduling on another CPU. */ rq = task_rq_lock(p, &rf); + update_rq_clock(rq); + /* * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected @@ -3793,7 +3815,7 @@ EXPORT_SYMBOL(set_user_nice); */ int can_nice(const struct task_struct *p, const int nice) { - /* convert nice value [19,-20] to rlimit style value [1,40] */ + /* Convert nice value [19,-20] to rlimit style value [1,40]: */ int nice_rlim = nice_to_rlimit(nice); return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || @@ -3849,7 +3871,7 @@ int task_prio(const struct task_struct *p) } /** - * idle_cpu - is a given cpu idle currently? + * idle_cpu - is a given CPU idle currently? * @cpu: the processor in question. * * Return: 1 if the CPU is currently idle. 0 otherwise. @@ -3873,10 +3895,10 @@ int idle_cpu(int cpu) } /** - * idle_task - return the idle task for a given cpu. + * idle_task - return the idle task for a given CPU. * @cpu: the processor in question. * - * Return: The idle task for the cpu @cpu. + * Return: The idle task for the CPU @cpu. */ struct task_struct *idle_task(int cpu) { @@ -4042,7 +4064,7 @@ __checkparam_dl(const struct sched_attr *attr) } /* - * check the target process has a UID that matches the current process's + * Check the target process has a UID that matches the current process's: */ static bool check_same_owner(struct task_struct *p) { @@ -4057,8 +4079,7 @@ static bool check_same_owner(struct task_struct *p) return match; } -static bool dl_param_changed(struct task_struct *p, - const struct sched_attr *attr) +static bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) { struct sched_dl_entity *dl_se = &p->dl; @@ -4085,10 +4106,10 @@ static int __sched_setscheduler(struct task_struct *p, int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE; struct rq *rq; - /* may grab non-irq protected spin_locks */ + /* May grab non-irq protected spin_locks: */ BUG_ON(in_interrupt()); recheck: - /* double check policy once rq lock held */ + /* Double check policy once rq lock held: */ if (policy < 0) { reset_on_fork = p->sched_reset_on_fork; policy = oldpolicy = p->policy; @@ -4128,11 +4149,11 @@ recheck: unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); - /* can't set/change the rt policy */ + /* Can't set/change the rt policy: */ if (policy != p->policy && !rlim_rtprio) return -EPERM; - /* can't increase priority */ + /* Can't increase priority: */ if (attr->sched_priority > p->rt_priority && attr->sched_priority > rlim_rtprio) return -EPERM; @@ -4156,11 +4177,11 @@ recheck: return -EPERM; } - /* can't change other user's priorities */ + /* Can't change other user's priorities: */ if (!check_same_owner(p)) return -EPERM; - /* Normal users shall not reset the sched_reset_on_fork flag */ + /* Normal users shall not reset the sched_reset_on_fork flag: */ if (p->sched_reset_on_fork && !reset_on_fork) return -EPERM; } @@ -4172,16 +4193,17 @@ recheck: } /* - * make sure no PI-waiters arrive (or leave) while we are + * Make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: * * To be able to change p->policy safely, the appropriate * runqueue lock must be held. */ rq = task_rq_lock(p, &rf); + update_rq_clock(rq); /* - * Changing the policy of the stop threads its a very bad idea + * Changing the policy of the stop threads its a very bad idea: */ if (p == rq->stop) { task_rq_unlock(rq, p, &rf); @@ -4237,7 +4259,7 @@ change: #endif } - /* recheck policy now with rq lock held */ + /* Re-check policy now with rq lock held: */ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; task_rq_unlock(rq, p, &rf); @@ -4294,15 +4316,15 @@ change: set_curr_task(rq, p); check_class_changed(rq, p, prev_class, oldprio); - preempt_disable(); /* avoid rq from going away on us */ + + /* Avoid rq from going away on us: */ + preempt_disable(); task_rq_unlock(rq, p, &rf); if (pi) rt_mutex_adjust_pi(p); - /* - * Run balance callbacks after we've adjusted the PI chain. - */ + /* Run balance callbacks after we've adjusted the PI chain: */ balance_callback(rq); preempt_enable(); @@ -4395,8 +4417,7 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) /* * Mimics kernel/events/core.c perf_copy_attr(). */ -static int sched_copy_attr(struct sched_attr __user *uattr, - struct sched_attr *attr) +static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr) { u32 size; int ret; @@ -4404,19 +4425,19 @@ static int sched_copy_attr(struct sched_attr __user *uattr, if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0)) return -EFAULT; - /* - * zero the full structure, so that a short copy will be nice. - */ + /* Zero the full structure, so that a short copy will be nice: */ memset(attr, 0, sizeof(*attr)); ret = get_user(size, &uattr->size); if (ret) return ret; - if (size > PAGE_SIZE) /* silly large */ + /* Bail out on silly large: */ + if (size > PAGE_SIZE) goto err_size; - if (!size) /* abi compat */ + /* ABI compatibility quirk: */ + if (!size) size = SCHED_ATTR_SIZE_VER0; if (size < SCHED_ATTR_SIZE_VER0) @@ -4451,7 +4472,7 @@ static int sched_copy_attr(struct sched_attr __user *uattr, return -EFAULT; /* - * XXX: do we want to be lenient like existing syscalls; or do we want + * XXX: Do we want to be lenient like existing syscalls; or do we want * to be strict and return an error on out-of-bounds values? */ attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); @@ -4471,10 +4492,8 @@ err_size: * * Return: 0 on success. An error code otherwise. */ -SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, - struct sched_param __user *, param) +SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param) { - /* negative values for policy are not valid */ if (policy < 0) return -EINVAL; @@ -4784,10 +4803,10 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, } /** - * sys_sched_setaffinity - set the cpu affinity of a process + * sys_sched_setaffinity - set the CPU affinity of a process * @pid: pid of the process * @len: length in bytes of the bitmask pointed to by user_mask_ptr - * @user_mask_ptr: user-space pointer to the new cpu mask + * @user_mask_ptr: user-space pointer to the new CPU mask * * Return: 0 on success. An error code otherwise. */ @@ -4835,10 +4854,10 @@ out_unlock: } /** - * sys_sched_getaffinity - get the cpu affinity of a process + * sys_sched_getaffinity - get the CPU affinity of a process * @pid: pid of the process * @len: length in bytes of the bitmask pointed to by user_mask_ptr - * @user_mask_ptr: user-space pointer to hold the current cpu mask + * @user_mask_ptr: user-space pointer to hold the current CPU mask * * Return: size of CPU mask copied to user_mask_ptr on success. An * error code otherwise. @@ -4966,7 +4985,7 @@ EXPORT_SYMBOL(__cond_resched_softirq); * Typical broken usage is: * * while (!event) - * yield(); + * yield(); * * where one assumes that yield() will let 'the other' process run that will * make event true. If the current task is a SCHED_FIFO task that will never @@ -5057,31 +5076,48 @@ out_irq: } EXPORT_SYMBOL_GPL(yield_to); +int io_schedule_prepare(void) +{ + int old_iowait = current->in_iowait; + + current->in_iowait = 1; + blk_schedule_flush_plug(current); + + return old_iowait; +} + +void io_schedule_finish(int token) +{ + current->in_iowait = token; +} + /* * This task is about to go to sleep on IO. Increment rq->nr_iowait so * that process accounting knows that this is a task in IO wait state. */ long __sched io_schedule_timeout(long timeout) { - int old_iowait = current->in_iowait; - struct rq *rq; + int token; long ret; - current->in_iowait = 1; - blk_schedule_flush_plug(current); - - delayacct_blkio_start(); - rq = raw_rq(); - atomic_inc(&rq->nr_iowait); + token = io_schedule_prepare(); ret = schedule_timeout(timeout); - current->in_iowait = old_iowait; - atomic_dec(&rq->nr_iowait); - delayacct_blkio_end(); + io_schedule_finish(token); return ret; } EXPORT_SYMBOL(io_schedule_timeout); +void io_schedule(void) +{ + int token; + + token = io_schedule_prepare(); + schedule(); + io_schedule_finish(token); +} +EXPORT_SYMBOL(io_schedule); + /** * sys_sched_get_priority_max - return maximum RT priority. * @policy: scheduling class. @@ -5264,7 +5300,7 @@ void init_idle_bootup_task(struct task_struct *idle) /** * init_idle - set up an idle thread for a given CPU * @idle: task in question - * @cpu: cpu the idle task belongs to + * @cpu: CPU the idle task belongs to * * NOTE: this function does not set the idle thread's NEED_RESCHED * flag, to make booting more robust. @@ -5295,7 +5331,7 @@ void init_idle(struct task_struct *idle, int cpu) #endif /* * We're having a chicken and egg problem, even though we are - * holding rq->lock, the cpu isn't yet set to this cpu so the + * holding rq->lock, the CPU isn't yet set to this CPU so the * lockdep check in task_group() will fail. * * Similar case to sched_fork(). / Alternatively we could @@ -5360,7 +5396,7 @@ int task_can_attach(struct task_struct *p, /* * Kthreads which disallow setaffinity shouldn't be moved - * to a new cpuset; we don't want to change their cpu + * to a new cpuset; we don't want to change their CPU * affinity and isolating such threads by their set of * allowed nodes is unnecessary. Thus, cpusets are not * applicable for such threads. This prevents checking for @@ -5409,7 +5445,7 @@ out: #ifdef CONFIG_SMP -static bool sched_smp_initialized __read_mostly; +bool sched_smp_initialized __read_mostly; #ifdef CONFIG_NUMA_BALANCING /* Migrate current task p to target_cpu */ @@ -5461,7 +5497,7 @@ void sched_setnuma(struct task_struct *p, int nid) #ifdef CONFIG_HOTPLUG_CPU /* - * Ensures that the idle task is using init_mm right before its cpu goes + * Ensure that the idle task is using init_mm right before its CPU goes * offline. */ void idle_task_exit(void) @@ -5521,7 +5557,7 @@ static void migrate_tasks(struct rq *dead_rq) { struct rq *rq = dead_rq; struct task_struct *next, *stop = rq->stop; - struct pin_cookie cookie; + struct rq_flags rf, old_rf; int dest_cpu; /* @@ -5545,16 +5581,16 @@ static void migrate_tasks(struct rq *dead_rq) for (;;) { /* * There's this thread running, bail when that's the only - * remaining thread. + * remaining thread: */ if (rq->nr_running == 1) break; /* - * pick_next_task assumes pinned rq->lock. + * pick_next_task() assumes pinned rq->lock: */ - cookie = lockdep_pin_lock(&rq->lock); - next = pick_next_task(rq, &fake_task, cookie); + rq_pin_lock(rq, &rf); + next = pick_next_task(rq, &fake_task, &rf); BUG_ON(!next); next->sched_class->put_prev_task(rq, next); @@ -5567,7 +5603,7 @@ static void migrate_tasks(struct rq *dead_rq) * because !cpu_active at this point, which means load-balance * will not interfere. Also, stop-machine. */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, &rf); raw_spin_unlock(&rq->lock); raw_spin_lock(&next->pi_lock); raw_spin_lock(&rq->lock); @@ -5582,6 +5618,13 @@ static void migrate_tasks(struct rq *dead_rq) continue; } + /* + * __migrate_task() may return with a different + * rq->lock held and a new cookie in 'rf', but we need + * to preserve rf::clock_update_flags for 'dead_rq'. + */ + old_rf = rf; + /* Find suitable destination for @next, with force if needed. */ dest_cpu = select_fallback_rq(dead_rq->cpu, next); @@ -5590,6 +5633,7 @@ static void migrate_tasks(struct rq *dead_rq) raw_spin_unlock(&rq->lock); rq = dead_rq; raw_spin_lock(&rq->lock); + rf = old_rf; } raw_spin_unlock(&next->pi_lock); } @@ -5598,7 +5642,7 @@ static void migrate_tasks(struct rq *dead_rq) } #endif /* CONFIG_HOTPLUG_CPU */ -static void set_rq_online(struct rq *rq) +void set_rq_online(struct rq *rq) { if (!rq->online) { const struct sched_class *class; @@ -5613,7 +5657,7 @@ static void set_rq_online(struct rq *rq) } } -static void set_rq_offline(struct rq *rq) +void set_rq_offline(struct rq *rq) { if (rq->online) { const struct sched_class *class; @@ -5635,1647 +5679,10 @@ static void set_cpu_rq_start_time(unsigned int cpu) rq->age_stamp = sched_clock_cpu(cpu); } -static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ - -#ifdef CONFIG_SCHED_DEBUG - -static __read_mostly int sched_debug_enabled; - -static int __init sched_debug_setup(char *str) -{ - sched_debug_enabled = 1; - - return 0; -} -early_param("sched_debug", sched_debug_setup); - -static inline bool sched_debug(void) -{ - return sched_debug_enabled; -} - -static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, - struct cpumask *groupmask) -{ - struct sched_group *group = sd->groups; - - cpumask_clear(groupmask); - - printk(KERN_DEBUG "%*s domain %d: ", level, "", level); - - if (!(sd->flags & SD_LOAD_BALANCE)) { - printk("does not load-balance\n"); - if (sd->parent) - printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" - " has parent"); - return -1; - } - - printk(KERN_CONT "span %*pbl level %s\n", - cpumask_pr_args(sched_domain_span(sd)), sd->name); - - 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_cpus(group))) { - printk(KERN_ERR "ERROR: domain->groups does not contain" - " CPU%d\n", cpu); - } - - printk(KERN_DEBUG "%*s groups:", level + 1, ""); - do { - if (!group) { - printk("\n"); - printk(KERN_ERR "ERROR: group is NULL\n"); - break; - } - - if (!cpumask_weight(sched_group_cpus(group))) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: empty group\n"); - break; - } - - if (!(sd->flags & SD_OVERLAP) && - cpumask_intersects(groupmask, sched_group_cpus(group))) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: repeated CPUs\n"); - break; - } - - cpumask_or(groupmask, groupmask, sched_group_cpus(group)); - - printk(KERN_CONT " %*pbl", - cpumask_pr_args(sched_group_cpus(group))); - if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { - printk(KERN_CONT " (cpu_capacity = %lu)", - group->sgc->capacity); - } - - group = group->next; - } while (group != sd->groups); - printk(KERN_CONT "\n"); - - if (!cpumask_equal(sched_domain_span(sd), groupmask)) - printk(KERN_ERR "ERROR: groups don't span domain->span\n"); - - if (sd->parent && - !cpumask_subset(groupmask, sched_domain_span(sd->parent))) - printk(KERN_ERR "ERROR: parent span is not a superset " - "of domain->span\n"); - return 0; -} - -static void sched_domain_debug(struct sched_domain *sd, int cpu) -{ - int level = 0; - - if (!sched_debug_enabled) - return; - - if (!sd) { - printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); - return; - } - - printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); - - for (;;) { - if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) - break; - level++; - sd = sd->parent; - if (!sd) - break; - } -} -#else /* !CONFIG_SCHED_DEBUG */ - -# define sched_debug_enabled 0 -# define sched_domain_debug(sd, cpu) do { } while (0) -static inline bool sched_debug(void) -{ - return false; -} -#endif /* CONFIG_SCHED_DEBUG */ - -static int sd_degenerate(struct sched_domain *sd) -{ - if (cpumask_weight(sched_domain_span(sd)) == 1) - return 1; - - /* Following flags need at least 2 groups */ - if (sd->flags & (SD_LOAD_BALANCE | - SD_BALANCE_NEWIDLE | - SD_BALANCE_FORK | - SD_BALANCE_EXEC | - SD_SHARE_CPUCAPACITY | - SD_ASYM_CPUCAPACITY | - SD_SHARE_PKG_RESOURCES | - SD_SHARE_POWERDOMAIN)) { - if (sd->groups != sd->groups->next) - return 0; - } - - /* Following flags don't use groups */ - if (sd->flags & (SD_WAKE_AFFINE)) - return 0; - - return 1; -} - -static int -sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) -{ - unsigned long cflags = sd->flags, pflags = parent->flags; - - if (sd_degenerate(parent)) - return 1; - - if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) - return 0; - - /* Flags needing groups don't count if only 1 group in parent */ - if (parent->groups == parent->groups->next) { - pflags &= ~(SD_LOAD_BALANCE | - SD_BALANCE_NEWIDLE | - SD_BALANCE_FORK | - SD_BALANCE_EXEC | - SD_ASYM_CPUCAPACITY | - SD_SHARE_CPUCAPACITY | - SD_SHARE_PKG_RESOURCES | - SD_PREFER_SIBLING | - SD_SHARE_POWERDOMAIN); - if (nr_node_ids == 1) - pflags &= ~SD_SERIALIZE; - } - if (~cflags & pflags) - return 0; - - return 1; -} - -static void free_rootdomain(struct rcu_head *rcu) -{ - struct root_domain *rd = container_of(rcu, struct root_domain, rcu); - - cpupri_cleanup(&rd->cpupri); - cpudl_cleanup(&rd->cpudl); - free_cpumask_var(rd->dlo_mask); - free_cpumask_var(rd->rto_mask); - free_cpumask_var(rd->online); - free_cpumask_var(rd->span); - kfree(rd); -} - -static void rq_attach_root(struct rq *rq, struct root_domain *rd) -{ - struct root_domain *old_rd = NULL; - unsigned long flags; - - raw_spin_lock_irqsave(&rq->lock, flags); - - if (rq->rd) { - old_rd = rq->rd; - - if (cpumask_test_cpu(rq->cpu, old_rd->online)) - set_rq_offline(rq); - - cpumask_clear_cpu(rq->cpu, old_rd->span); - - /* - * If we dont want to free the old_rd yet then - * set old_rd to NULL to skip the freeing later - * in this function: - */ - if (!atomic_dec_and_test(&old_rd->refcount)) - old_rd = NULL; - } - - atomic_inc(&rd->refcount); - rq->rd = rd; - - cpumask_set_cpu(rq->cpu, rd->span); - if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) - set_rq_online(rq); - - raw_spin_unlock_irqrestore(&rq->lock, flags); - - if (old_rd) - call_rcu_sched(&old_rd->rcu, free_rootdomain); -} - -static int init_rootdomain(struct root_domain *rd) -{ - memset(rd, 0, sizeof(*rd)); - - if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) - goto out; - if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL)) - goto free_span; - if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) - goto free_online; - if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) - goto free_dlo_mask; - - init_dl_bw(&rd->dl_bw); - if (cpudl_init(&rd->cpudl) != 0) - goto free_dlo_mask; - - if (cpupri_init(&rd->cpupri) != 0) - goto free_rto_mask; - return 0; - -free_rto_mask: - free_cpumask_var(rd->rto_mask); -free_dlo_mask: - free_cpumask_var(rd->dlo_mask); -free_online: - free_cpumask_var(rd->online); -free_span: - free_cpumask_var(rd->span); -out: - return -ENOMEM; -} - -/* - * By default the system creates a single root-domain with all cpus as - * members (mimicking the global state we have today). - */ -struct root_domain def_root_domain; - -static void init_defrootdomain(void) -{ - init_rootdomain(&def_root_domain); - - atomic_set(&def_root_domain.refcount, 1); -} - -static struct root_domain *alloc_rootdomain(void) -{ - struct root_domain *rd; - - rd = kmalloc(sizeof(*rd), GFP_KERNEL); - if (!rd) - return NULL; - - if (init_rootdomain(rd) != 0) { - kfree(rd); - return NULL; - } - - return rd; -} - -static void free_sched_groups(struct sched_group *sg, int free_sgc) -{ - struct sched_group *tmp, *first; - - if (!sg) - return; - - first = sg; - do { - tmp = sg->next; - - if (free_sgc && atomic_dec_and_test(&sg->sgc->ref)) - kfree(sg->sgc); - - kfree(sg); - sg = tmp; - } while (sg != first); -} - -static void destroy_sched_domain(struct sched_domain *sd) -{ - /* - * If its an overlapping domain it has private groups, iterate and - * nuke them all. - */ - if (sd->flags & SD_OVERLAP) { - free_sched_groups(sd->groups, 1); - } else if (atomic_dec_and_test(&sd->groups->ref)) { - kfree(sd->groups->sgc); - kfree(sd->groups); - } - if (sd->shared && atomic_dec_and_test(&sd->shared->ref)) - kfree(sd->shared); - kfree(sd); -} - -static void destroy_sched_domains_rcu(struct rcu_head *rcu) -{ - struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); - - while (sd) { - struct sched_domain *parent = sd->parent; - destroy_sched_domain(sd); - sd = parent; - } -} - -static void destroy_sched_domains(struct sched_domain *sd) -{ - if (sd) - call_rcu(&sd->rcu, destroy_sched_domains_rcu); -} - -/* - * Keep a special pointer to the highest sched_domain that has - * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this - * allows us to avoid some pointer chasing select_idle_sibling(). - * - * Also keep a unique ID per domain (we use the first cpu number in - * the cpumask of the domain), this allows us to quickly tell if - * two cpus are in the same cache domain, see cpus_share_cache(). - */ -DEFINE_PER_CPU(struct sched_domain *, sd_llc); -DEFINE_PER_CPU(int, sd_llc_size); -DEFINE_PER_CPU(int, sd_llc_id); -DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); -DEFINE_PER_CPU(struct sched_domain *, sd_numa); -DEFINE_PER_CPU(struct sched_domain *, sd_asym); - -static void update_top_cache_domain(int cpu) -{ - struct sched_domain_shared *sds = NULL; - struct sched_domain *sd; - int id = cpu; - int size = 1; - - sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); - if (sd) { - id = cpumask_first(sched_domain_span(sd)); - size = cpumask_weight(sched_domain_span(sd)); - sds = sd->shared; - } - - rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); - per_cpu(sd_llc_size, cpu) = size; - per_cpu(sd_llc_id, cpu) = id; - rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds); - - sd = lowest_flag_domain(cpu, SD_NUMA); - rcu_assign_pointer(per_cpu(sd_numa, cpu), sd); - - sd = highest_flag_domain(cpu, SD_ASYM_PACKING); - rcu_assign_pointer(per_cpu(sd_asym, cpu), sd); -} - -/* - * Attach the domain 'sd' to 'cpu' as its base domain. Callers must - * hold the hotplug lock. - */ -static void -cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) -{ - struct rq *rq = cpu_rq(cpu); - struct sched_domain *tmp; - - /* Remove the sched domains which do not contribute to scheduling. */ - for (tmp = sd; tmp; ) { - struct sched_domain *parent = tmp->parent; - if (!parent) - break; - - if (sd_parent_degenerate(tmp, parent)) { - tmp->parent = parent->parent; - if (parent->parent) - parent->parent->child = tmp; - /* - * Transfer SD_PREFER_SIBLING down in case of a - * degenerate parent; the spans match for this - * so the property transfers. - */ - if (parent->flags & SD_PREFER_SIBLING) - tmp->flags |= SD_PREFER_SIBLING; - destroy_sched_domain(parent); - } else - tmp = tmp->parent; - } - - if (sd && sd_degenerate(sd)) { - tmp = sd; - sd = sd->parent; - destroy_sched_domain(tmp); - if (sd) - sd->child = NULL; - } - - sched_domain_debug(sd, cpu); - - rq_attach_root(rq, rd); - tmp = rq->sd; - rcu_assign_pointer(rq->sd, sd); - destroy_sched_domains(tmp); - - update_top_cache_domain(cpu); -} - -/* Setup the mask of cpus configured for isolated domains */ -static int __init isolated_cpu_setup(char *str) -{ - int ret; - - alloc_bootmem_cpumask_var(&cpu_isolated_map); - ret = cpulist_parse(str, cpu_isolated_map); - if (ret) { - pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids); - return 0; - } - return 1; -} -__setup("isolcpus=", isolated_cpu_setup); - -struct s_data { - struct sched_domain ** __percpu sd; - struct root_domain *rd; -}; - -enum s_alloc { - sa_rootdomain, - sa_sd, - sa_sd_storage, - sa_none, -}; - -/* - * Build an iteration mask that can exclude certain CPUs from the upwards - * domain traversal. - * - * Asymmetric node setups can result in situations where the domain tree is of - * unequal depth, make sure to skip domains that already cover the entire - * range. - * - * In that case build_sched_domains() will have terminated the iteration early - * and our sibling sd spans will be empty. Domains should always include the - * cpu they're built on, so check that. - * - */ -static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) -{ - const struct cpumask *span = sched_domain_span(sd); - struct sd_data *sdd = sd->private; - struct sched_domain *sibling; - int i; - - for_each_cpu(i, span) { - sibling = *per_cpu_ptr(sdd->sd, i); - if (!cpumask_test_cpu(i, sched_domain_span(sibling))) - continue; - - cpumask_set_cpu(i, sched_group_mask(sg)); - } -} - -/* - * Return the canonical balance cpu for this group, this is the first cpu - * of this group that's also in the iteration mask. - */ -int group_balance_cpu(struct sched_group *sg) -{ - return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg)); -} - -static int -build_overlap_sched_groups(struct sched_domain *sd, int cpu) -{ - struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg; - const struct cpumask *span = sched_domain_span(sd); - struct cpumask *covered = sched_domains_tmpmask; - struct sd_data *sdd = sd->private; - struct sched_domain *sibling; - int i; - - cpumask_clear(covered); - - for_each_cpu(i, span) { - struct cpumask *sg_span; - - if (cpumask_test_cpu(i, covered)) - continue; - - sibling = *per_cpu_ptr(sdd->sd, i); - - /* See the comment near build_group_mask(). */ - if (!cpumask_test_cpu(i, sched_domain_span(sibling))) - continue; - - sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), - GFP_KERNEL, cpu_to_node(cpu)); - - if (!sg) - goto fail; - - sg_span = sched_group_cpus(sg); - if (sibling->child) - cpumask_copy(sg_span, sched_domain_span(sibling->child)); - else - cpumask_set_cpu(i, sg_span); - - cpumask_or(covered, covered, sg_span); - - sg->sgc = *per_cpu_ptr(sdd->sgc, i); - if (atomic_inc_return(&sg->sgc->ref) == 1) - build_group_mask(sd, sg); - - /* - * Initialize sgc->capacity such that even if we mess up the - * domains and no possible iteration will get us here, we won't - * die on a /0 trap. - */ - sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); - sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; - - /* - * Make sure the first group of this domain contains the - * canonical balance cpu. Otherwise the sched_domain iteration - * breaks. See update_sg_lb_stats(). - */ - if ((!groups && cpumask_test_cpu(cpu, sg_span)) || - group_balance_cpu(sg) == cpu) - groups = sg; - - if (!first) - first = sg; - if (last) - last->next = sg; - last = sg; - last->next = first; - } - sd->groups = groups; - - return 0; - -fail: - free_sched_groups(first, 0); - - return -ENOMEM; -} - -static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) -{ - struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); - struct sched_domain *child = sd->child; - - if (child) - cpu = cpumask_first(sched_domain_span(child)); - - if (sg) { - *sg = *per_cpu_ptr(sdd->sg, cpu); - (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); - atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */ - } - - return cpu; -} - -/* - * build_sched_groups will build a circular linked list of the groups - * covered by the given span, and will set each group's ->cpumask correctly, - * and ->cpu_capacity to 0. - * - * Assumes the sched_domain tree is fully constructed - */ -static int -build_sched_groups(struct sched_domain *sd, int cpu) -{ - struct sched_group *first = NULL, *last = NULL; - struct sd_data *sdd = sd->private; - const struct cpumask *span = sched_domain_span(sd); - struct cpumask *covered; - int i; - - get_group(cpu, sdd, &sd->groups); - atomic_inc(&sd->groups->ref); - - if (cpu != cpumask_first(span)) - return 0; - - lockdep_assert_held(&sched_domains_mutex); - covered = sched_domains_tmpmask; - - cpumask_clear(covered); - - for_each_cpu(i, span) { - struct sched_group *sg; - int group, j; - - if (cpumask_test_cpu(i, covered)) - continue; - - group = get_group(i, sdd, &sg); - cpumask_setall(sched_group_mask(sg)); - - for_each_cpu(j, span) { - if (get_group(j, sdd, NULL) != group) - continue; - - cpumask_set_cpu(j, covered); - cpumask_set_cpu(j, sched_group_cpus(sg)); - } - - if (!first) - first = sg; - if (last) - last->next = sg; - last = sg; - } - last->next = first; - - return 0; -} - -/* - * Initialize sched groups cpu_capacity. - * - * cpu_capacity indicates the capacity of sched group, which is used while - * distributing the load between different sched groups in a sched domain. - * Typically cpu_capacity for all the groups in a sched domain will be same - * unless there are asymmetries in the topology. If there are asymmetries, - * group having more cpu_capacity will pickup more load compared to the - * group having less cpu_capacity. - */ -static void init_sched_groups_capacity(int cpu, struct sched_domain *sd) -{ - struct sched_group *sg = sd->groups; - - WARN_ON(!sg); - - do { - int cpu, max_cpu = -1; - - sg->group_weight = cpumask_weight(sched_group_cpus(sg)); - - if (!(sd->flags & SD_ASYM_PACKING)) - goto next; - - for_each_cpu(cpu, sched_group_cpus(sg)) { - if (max_cpu < 0) - max_cpu = cpu; - else if (sched_asym_prefer(cpu, max_cpu)) - max_cpu = cpu; - } - sg->asym_prefer_cpu = max_cpu; - -next: - sg = sg->next; - } while (sg != sd->groups); - - if (cpu != group_balance_cpu(sg)) - return; - - update_group_capacity(sd, cpu); -} - -/* - * Initializers for schedule domains - * Non-inlined to reduce accumulated stack pressure in build_sched_domains() - */ - -static int default_relax_domain_level = -1; -int sched_domain_level_max; - -static int __init setup_relax_domain_level(char *str) -{ - if (kstrtoint(str, 0, &default_relax_domain_level)) - pr_warn("Unable to set relax_domain_level\n"); - - return 1; -} -__setup("relax_domain_level=", setup_relax_domain_level); - -static void set_domain_attribute(struct sched_domain *sd, - struct sched_domain_attr *attr) -{ - int request; - - if (!attr || attr->relax_domain_level < 0) { - if (default_relax_domain_level < 0) - return; - else - request = default_relax_domain_level; - } else - request = attr->relax_domain_level; - if (request < sd->level) { - /* turn off idle balance on this domain */ - sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); - } else { - /* turn on idle balance on this domain */ - sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); - } -} - -static void __sdt_free(const struct cpumask *cpu_map); -static int __sdt_alloc(const struct cpumask *cpu_map); - -static void __free_domain_allocs(struct s_data *d, enum s_alloc what, - const struct cpumask *cpu_map) -{ - switch (what) { - case sa_rootdomain: - if (!atomic_read(&d->rd->refcount)) - free_rootdomain(&d->rd->rcu); /* fall through */ - case sa_sd: - free_percpu(d->sd); /* fall through */ - case sa_sd_storage: - __sdt_free(cpu_map); /* fall through */ - case sa_none: - break; - } -} - -static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, - const struct cpumask *cpu_map) -{ - memset(d, 0, sizeof(*d)); - - if (__sdt_alloc(cpu_map)) - return sa_sd_storage; - d->sd = alloc_percpu(struct sched_domain *); - if (!d->sd) - return sa_sd_storage; - d->rd = alloc_rootdomain(); - if (!d->rd) - return sa_sd; - return sa_rootdomain; -} - -/* - * NULL the sd_data elements we've used to build the sched_domain and - * sched_group structure so that the subsequent __free_domain_allocs() - * will not free the data we're using. - */ -static void claim_allocations(int cpu, struct sched_domain *sd) -{ - struct sd_data *sdd = sd->private; - - WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); - *per_cpu_ptr(sdd->sd, cpu) = NULL; - - if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref)) - *per_cpu_ptr(sdd->sds, cpu) = NULL; - - if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) - *per_cpu_ptr(sdd->sg, cpu) = NULL; - - if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref)) - *per_cpu_ptr(sdd->sgc, cpu) = NULL; -} - -#ifdef CONFIG_NUMA -static int sched_domains_numa_levels; -enum numa_topology_type sched_numa_topology_type; -static int *sched_domains_numa_distance; -int sched_max_numa_distance; -static struct cpumask ***sched_domains_numa_masks; -static int sched_domains_curr_level; -#endif - -/* - * SD_flags allowed in topology descriptions. - * - * These flags are purely descriptive of the topology and do not prescribe - * behaviour. Behaviour is artificial and mapped in the below sd_init() - * function: - * - * SD_SHARE_CPUCAPACITY - describes SMT topologies - * SD_SHARE_PKG_RESOURCES - describes shared caches - * SD_NUMA - describes NUMA topologies - * SD_SHARE_POWERDOMAIN - describes shared power domain - * SD_ASYM_CPUCAPACITY - describes mixed capacity topologies - * - * Odd one out, which beside describing the topology has a quirk also - * prescribes the desired behaviour that goes along with it: - * - * SD_ASYM_PACKING - describes SMT quirks - */ -#define TOPOLOGY_SD_FLAGS \ - (SD_SHARE_CPUCAPACITY | \ - SD_SHARE_PKG_RESOURCES | \ - SD_NUMA | \ - SD_ASYM_PACKING | \ - SD_ASYM_CPUCAPACITY | \ - SD_SHARE_POWERDOMAIN) - -static struct sched_domain * -sd_init(struct sched_domain_topology_level *tl, - const struct cpumask *cpu_map, - struct sched_domain *child, int cpu) -{ - struct sd_data *sdd = &tl->data; - struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); - int sd_id, sd_weight, sd_flags = 0; - -#ifdef CONFIG_NUMA - /* - * Ugly hack to pass state to sd_numa_mask()... - */ - sched_domains_curr_level = tl->numa_level; -#endif - - sd_weight = cpumask_weight(tl->mask(cpu)); - - if (tl->sd_flags) - sd_flags = (*tl->sd_flags)(); - if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, - "wrong sd_flags in topology description\n")) - sd_flags &= ~TOPOLOGY_SD_FLAGS; - - *sd = (struct sched_domain){ - .min_interval = sd_weight, - .max_interval = 2*sd_weight, - .busy_factor = 32, - .imbalance_pct = 125, - - .cache_nice_tries = 0, - .busy_idx = 0, - .idle_idx = 0, - .newidle_idx = 0, - .wake_idx = 0, - .forkexec_idx = 0, - - .flags = 1*SD_LOAD_BALANCE - | 1*SD_BALANCE_NEWIDLE - | 1*SD_BALANCE_EXEC - | 1*SD_BALANCE_FORK - | 0*SD_BALANCE_WAKE - | 1*SD_WAKE_AFFINE - | 0*SD_SHARE_CPUCAPACITY - | 0*SD_SHARE_PKG_RESOURCES - | 0*SD_SERIALIZE - | 0*SD_PREFER_SIBLING - | 0*SD_NUMA - | sd_flags - , - - .last_balance = jiffies, - .balance_interval = sd_weight, - .smt_gain = 0, - .max_newidle_lb_cost = 0, - .next_decay_max_lb_cost = jiffies, - .child = child, -#ifdef CONFIG_SCHED_DEBUG - .name = tl->name, -#endif - }; - - cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); - sd_id = cpumask_first(sched_domain_span(sd)); - - /* - * Convert topological properties into behaviour. - */ - - if (sd->flags & SD_ASYM_CPUCAPACITY) { - struct sched_domain *t = sd; - - for_each_lower_domain(t) - t->flags |= SD_BALANCE_WAKE; - } - - if (sd->flags & SD_SHARE_CPUCAPACITY) { - sd->flags |= SD_PREFER_SIBLING; - sd->imbalance_pct = 110; - sd->smt_gain = 1178; /* ~15% */ - - } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { - sd->imbalance_pct = 117; - sd->cache_nice_tries = 1; - sd->busy_idx = 2; - -#ifdef CONFIG_NUMA - } else if (sd->flags & SD_NUMA) { - sd->cache_nice_tries = 2; - sd->busy_idx = 3; - sd->idle_idx = 2; - - sd->flags |= SD_SERIALIZE; - if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { - sd->flags &= ~(SD_BALANCE_EXEC | - SD_BALANCE_FORK | - SD_WAKE_AFFINE); - } - -#endif - } else { - sd->flags |= SD_PREFER_SIBLING; - sd->cache_nice_tries = 1; - sd->busy_idx = 2; - sd->idle_idx = 1; - } - - /* - * For all levels sharing cache; connect a sched_domain_shared - * instance. - */ - if (sd->flags & SD_SHARE_PKG_RESOURCES) { - sd->shared = *per_cpu_ptr(sdd->sds, sd_id); - atomic_inc(&sd->shared->ref); - atomic_set(&sd->shared->nr_busy_cpus, sd_weight); - } - - sd->private = sdd; - - return sd; -} - -/* - * Topology list, bottom-up. - */ -static struct sched_domain_topology_level default_topology[] = { -#ifdef CONFIG_SCHED_SMT - { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, -#endif -#ifdef CONFIG_SCHED_MC - { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, -#endif - { cpu_cpu_mask, SD_INIT_NAME(DIE) }, - { NULL, }, -}; - -static struct sched_domain_topology_level *sched_domain_topology = - default_topology; - -#define for_each_sd_topology(tl) \ - for (tl = sched_domain_topology; tl->mask; tl++) - -void set_sched_topology(struct sched_domain_topology_level *tl) -{ - if (WARN_ON_ONCE(sched_smp_initialized)) - return; - - sched_domain_topology = tl; -} - -#ifdef CONFIG_NUMA - -static const struct cpumask *sd_numa_mask(int cpu) -{ - return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; -} - -static void sched_numa_warn(const char *str) -{ - static int done = false; - int i,j; - - if (done) - return; - - done = true; - - printk(KERN_WARNING "ERROR: %s\n\n", str); - - for (i = 0; i < nr_node_ids; i++) { - printk(KERN_WARNING " "); - for (j = 0; j < nr_node_ids; j++) - printk(KERN_CONT "%02d ", node_distance(i,j)); - printk(KERN_CONT "\n"); - } - printk(KERN_WARNING "\n"); -} - -bool find_numa_distance(int distance) -{ - int i; - - if (distance == node_distance(0, 0)) - return true; - - for (i = 0; i < sched_domains_numa_levels; i++) { - if (sched_domains_numa_distance[i] == distance) - return true; - } - - return false; -} - -/* - * A system can have three types of NUMA topology: - * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system - * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes - * NUMA_BACKPLANE: nodes can reach other nodes through a backplane - * - * The difference between a glueless mesh topology and a backplane - * topology lies in whether communication between not directly - * connected nodes goes through intermediary nodes (where programs - * could run), or through backplane controllers. This affects - * placement of programs. - * - * The type of topology can be discerned with the following tests: - * - If the maximum distance between any nodes is 1 hop, the system - * is directly connected. - * - If for two nodes A and B, located N > 1 hops away from each other, - * there is an intermediary node C, which is < N hops away from both - * nodes A and B, the system is a glueless mesh. - */ -static void init_numa_topology_type(void) -{ - int a, b, c, n; - - n = sched_max_numa_distance; - - if (sched_domains_numa_levels <= 1) { - sched_numa_topology_type = NUMA_DIRECT; - return; - } - - for_each_online_node(a) { - for_each_online_node(b) { - /* Find two nodes furthest removed from each other. */ - if (node_distance(a, b) < n) - continue; - - /* Is there an intermediary node between a and b? */ - for_each_online_node(c) { - if (node_distance(a, c) < n && - node_distance(b, c) < n) { - sched_numa_topology_type = - NUMA_GLUELESS_MESH; - return; - } - } - - sched_numa_topology_type = NUMA_BACKPLANE; - return; - } - } -} - -static void sched_init_numa(void) -{ - int next_distance, curr_distance = node_distance(0, 0); - struct sched_domain_topology_level *tl; - int level = 0; - int i, j, k; - - sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); - if (!sched_domains_numa_distance) - return; - - /* - * O(nr_nodes^2) deduplicating selection sort -- in order to find the - * unique distances in the node_distance() table. - * - * Assumes node_distance(0,j) includes all distances in - * node_distance(i,j) in order to avoid cubic time. - */ - next_distance = curr_distance; - for (i = 0; i < nr_node_ids; i++) { - for (j = 0; j < nr_node_ids; j++) { - for (k = 0; k < nr_node_ids; k++) { - int distance = node_distance(i, k); - - if (distance > curr_distance && - (distance < next_distance || - next_distance == curr_distance)) - next_distance = distance; - - /* - * While not a strong assumption it would be nice to know - * about cases where if node A is connected to B, B is not - * equally connected to A. - */ - if (sched_debug() && node_distance(k, i) != distance) - sched_numa_warn("Node-distance not symmetric"); - - if (sched_debug() && i && !find_numa_distance(distance)) - sched_numa_warn("Node-0 not representative"); - } - if (next_distance != curr_distance) { - sched_domains_numa_distance[level++] = next_distance; - sched_domains_numa_levels = level; - curr_distance = next_distance; - } else break; - } - - /* - * In case of sched_debug() we verify the above assumption. - */ - if (!sched_debug()) - break; - } - - if (!level) - return; - - /* - * 'level' contains the number of unique distances, excluding the - * identity distance node_distance(i,i). - * - * The sched_domains_numa_distance[] array includes the actual distance - * numbers. - */ - - /* - * Here, we should temporarily reset sched_domains_numa_levels to 0. - * If it fails to allocate memory for array sched_domains_numa_masks[][], - * the array will contain less then 'level' members. This could be - * dangerous when we use it to iterate array sched_domains_numa_masks[][] - * in other functions. - * - * We reset it to 'level' at the end of this function. - */ - sched_domains_numa_levels = 0; - - sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); - if (!sched_domains_numa_masks) - return; - - /* - * Now for each level, construct a mask per node which contains all - * cpus of nodes that are that many hops away from us. - */ - for (i = 0; i < level; i++) { - sched_domains_numa_masks[i] = - kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); - if (!sched_domains_numa_masks[i]) - return; - - for (j = 0; j < nr_node_ids; j++) { - struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); - if (!mask) - return; - - sched_domains_numa_masks[i][j] = mask; - - for_each_node(k) { - if (node_distance(j, k) > sched_domains_numa_distance[i]) - continue; - - cpumask_or(mask, mask, cpumask_of_node(k)); - } - } - } - - /* Compute default topology size */ - for (i = 0; sched_domain_topology[i].mask; i++); - - tl = kzalloc((i + level + 1) * - sizeof(struct sched_domain_topology_level), GFP_KERNEL); - if (!tl) - return; - - /* - * Copy the default topology bits.. - */ - for (i = 0; sched_domain_topology[i].mask; i++) - tl[i] = sched_domain_topology[i]; - - /* - * .. and append 'j' levels of NUMA goodness. - */ - for (j = 0; j < level; i++, j++) { - tl[i] = (struct sched_domain_topology_level){ - .mask = sd_numa_mask, - .sd_flags = cpu_numa_flags, - .flags = SDTL_OVERLAP, - .numa_level = j, - SD_INIT_NAME(NUMA) - }; - } - - sched_domain_topology = tl; - - sched_domains_numa_levels = level; - sched_max_numa_distance = sched_domains_numa_distance[level - 1]; - - init_numa_topology_type(); -} - -static void sched_domains_numa_masks_set(unsigned int cpu) -{ - int node = cpu_to_node(cpu); - int i, j; - - for (i = 0; i < sched_domains_numa_levels; i++) { - for (j = 0; j < nr_node_ids; j++) { - if (node_distance(j, node) <= sched_domains_numa_distance[i]) - cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); - } - } -} - -static void sched_domains_numa_masks_clear(unsigned int cpu) -{ - int i, j; - - for (i = 0; i < sched_domains_numa_levels; i++) { - for (j = 0; j < nr_node_ids; j++) - cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); - } -} - -#else -static inline void sched_init_numa(void) { } -static void sched_domains_numa_masks_set(unsigned int cpu) { } -static void sched_domains_numa_masks_clear(unsigned int cpu) { } -#endif /* CONFIG_NUMA */ - -static int __sdt_alloc(const struct cpumask *cpu_map) -{ - struct sched_domain_topology_level *tl; - int j; - - for_each_sd_topology(tl) { - struct sd_data *sdd = &tl->data; - - sdd->sd = alloc_percpu(struct sched_domain *); - if (!sdd->sd) - return -ENOMEM; - - sdd->sds = alloc_percpu(struct sched_domain_shared *); - if (!sdd->sds) - return -ENOMEM; - - sdd->sg = alloc_percpu(struct sched_group *); - if (!sdd->sg) - return -ENOMEM; - - sdd->sgc = alloc_percpu(struct sched_group_capacity *); - if (!sdd->sgc) - return -ENOMEM; - - for_each_cpu(j, cpu_map) { - struct sched_domain *sd; - struct sched_domain_shared *sds; - struct sched_group *sg; - struct sched_group_capacity *sgc; - - sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), - GFP_KERNEL, cpu_to_node(j)); - if (!sd) - return -ENOMEM; - - *per_cpu_ptr(sdd->sd, j) = sd; - - sds = kzalloc_node(sizeof(struct sched_domain_shared), - GFP_KERNEL, cpu_to_node(j)); - if (!sds) - return -ENOMEM; - - *per_cpu_ptr(sdd->sds, j) = sds; - - sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), - GFP_KERNEL, cpu_to_node(j)); - if (!sg) - return -ENOMEM; - - sg->next = sg; - - *per_cpu_ptr(sdd->sg, j) = sg; - - sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(), - GFP_KERNEL, cpu_to_node(j)); - if (!sgc) - return -ENOMEM; - - *per_cpu_ptr(sdd->sgc, j) = sgc; - } - } - - return 0; -} - -static void __sdt_free(const struct cpumask *cpu_map) -{ - struct sched_domain_topology_level *tl; - int j; - - for_each_sd_topology(tl) { - struct sd_data *sdd = &tl->data; - - for_each_cpu(j, cpu_map) { - struct sched_domain *sd; - - if (sdd->sd) { - sd = *per_cpu_ptr(sdd->sd, j); - if (sd && (sd->flags & SD_OVERLAP)) - free_sched_groups(sd->groups, 0); - kfree(*per_cpu_ptr(sdd->sd, j)); - } - - if (sdd->sds) - kfree(*per_cpu_ptr(sdd->sds, j)); - if (sdd->sg) - kfree(*per_cpu_ptr(sdd->sg, j)); - if (sdd->sgc) - kfree(*per_cpu_ptr(sdd->sgc, j)); - } - free_percpu(sdd->sd); - sdd->sd = NULL; - free_percpu(sdd->sds); - sdd->sds = NULL; - free_percpu(sdd->sg); - sdd->sg = NULL; - free_percpu(sdd->sgc); - sdd->sgc = NULL; - } -} - -struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, - const struct cpumask *cpu_map, struct sched_domain_attr *attr, - struct sched_domain *child, int cpu) -{ - struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu); - - if (child) { - sd->level = child->level + 1; - sched_domain_level_max = max(sched_domain_level_max, sd->level); - child->parent = sd; - - if (!cpumask_subset(sched_domain_span(child), - sched_domain_span(sd))) { - pr_err("BUG: arch topology borken\n"); -#ifdef CONFIG_SCHED_DEBUG - pr_err(" the %s domain not a subset of the %s domain\n", - child->name, sd->name); -#endif - /* Fixup, ensure @sd has at least @child cpus. */ - cpumask_or(sched_domain_span(sd), - sched_domain_span(sd), - sched_domain_span(child)); - } - - } - set_domain_attribute(sd, attr); - - return sd; -} - /* - * Build sched domains for a given set of cpus and attach the sched domains - * to the individual cpus + * used to mark begin/end of suspend/resume: */ -static int build_sched_domains(const struct cpumask *cpu_map, - struct sched_domain_attr *attr) -{ - enum s_alloc alloc_state; - struct sched_domain *sd; - struct s_data d; - struct rq *rq = NULL; - int i, ret = -ENOMEM; - - alloc_state = __visit_domain_allocation_hell(&d, cpu_map); - if (alloc_state != sa_rootdomain) - goto error; - - /* Set up domains for cpus specified by the cpu_map. */ - for_each_cpu(i, cpu_map) { - struct sched_domain_topology_level *tl; - - sd = NULL; - for_each_sd_topology(tl) { - sd = build_sched_domain(tl, cpu_map, attr, sd, i); - if (tl == sched_domain_topology) - *per_cpu_ptr(d.sd, i) = sd; - if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) - sd->flags |= SD_OVERLAP; - if (cpumask_equal(cpu_map, sched_domain_span(sd))) - break; - } - } - - /* Build the groups for the domains */ - for_each_cpu(i, cpu_map) { - for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { - sd->span_weight = cpumask_weight(sched_domain_span(sd)); - if (sd->flags & SD_OVERLAP) { - if (build_overlap_sched_groups(sd, i)) - goto error; - } else { - if (build_sched_groups(sd, i)) - goto error; - } - } - } - - /* Calculate CPU capacity for physical packages and nodes */ - for (i = nr_cpumask_bits-1; i >= 0; i--) { - if (!cpumask_test_cpu(i, cpu_map)) - continue; - - for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { - claim_allocations(i, sd); - init_sched_groups_capacity(i, sd); - } - } - - /* Attach the domains */ - rcu_read_lock(); - for_each_cpu(i, cpu_map) { - rq = cpu_rq(i); - sd = *per_cpu_ptr(d.sd, i); - - /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */ - if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity)) - WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig); - - cpu_attach_domain(sd, d.rd, i); - } - rcu_read_unlock(); - - if (rq && sched_debug_enabled) { - pr_info("span: %*pbl (max cpu_capacity = %lu)\n", - cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity); - } - - ret = 0; -error: - __free_domain_allocs(&d, alloc_state, cpu_map); - return ret; -} - -static cpumask_var_t *doms_cur; /* current sched domains */ -static int ndoms_cur; /* number of sched domains in 'doms_cur' */ -static struct sched_domain_attr *dattr_cur; - /* attribues of custom domains in 'doms_cur' */ - -/* - * Special case: If a kmalloc of a doms_cur partition (array of - * cpumask) fails, then fallback to a single sched domain, - * as determined by the single cpumask fallback_doms. - */ -static cpumask_var_t fallback_doms; - -/* - * arch_update_cpu_topology lets virtualized architectures update the - * cpu core maps. It is supposed to return 1 if the topology changed - * or 0 if it stayed the same. - */ -int __weak arch_update_cpu_topology(void) -{ - return 0; -} - -cpumask_var_t *alloc_sched_domains(unsigned int ndoms) -{ - int i; - cpumask_var_t *doms; - - doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); - if (!doms) - return NULL; - for (i = 0; i < ndoms; i++) { - if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { - free_sched_domains(doms, i); - return NULL; - } - } - return doms; -} - -void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) -{ - unsigned int i; - for (i = 0; i < ndoms; i++) - free_cpumask_var(doms[i]); - kfree(doms); -} - -/* - * Set up scheduler domains and groups. Callers must hold the hotplug lock. - * For now this just excludes isolated cpus, but could be used to - * exclude other special cases in the future. - */ -static int init_sched_domains(const struct cpumask *cpu_map) -{ - int err; - - arch_update_cpu_topology(); - ndoms_cur = 1; - doms_cur = alloc_sched_domains(ndoms_cur); - if (!doms_cur) - doms_cur = &fallback_doms; - cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); - err = build_sched_domains(doms_cur[0], NULL); - register_sched_domain_sysctl(); - - return err; -} - -/* - * Detach sched domains from a group of cpus specified in cpu_map - * These cpus will now be attached to the NULL domain - */ -static void detach_destroy_domains(const struct cpumask *cpu_map) -{ - int i; - - rcu_read_lock(); - for_each_cpu(i, cpu_map) - cpu_attach_domain(NULL, &def_root_domain, i); - rcu_read_unlock(); -} - -/* handle null as "default" */ -static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, - struct sched_domain_attr *new, int idx_new) -{ - struct sched_domain_attr tmp; - - /* fast path */ - if (!new && !cur) - return 1; - - tmp = SD_ATTR_INIT; - return !memcmp(cur ? (cur + idx_cur) : &tmp, - new ? (new + idx_new) : &tmp, - sizeof(struct sched_domain_attr)); -} - -/* - * Partition sched domains as specified by the 'ndoms_new' - * cpumasks in the array doms_new[] of cpumasks. This compares - * doms_new[] to the current sched domain partitioning, doms_cur[]. - * It destroys each deleted domain and builds each new domain. - * - * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. - * The masks don't intersect (don't overlap.) We should setup one - * sched domain for each mask. CPUs not in any of the cpumasks will - * not be load balanced. If the same cpumask appears both in the - * current 'doms_cur' domains and in the new 'doms_new', we can leave - * it as it is. - * - * The passed in 'doms_new' should be allocated using - * alloc_sched_domains. This routine takes ownership of it and will - * free_sched_domains it when done with it. If the caller failed the - * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, - * and partition_sched_domains() will fallback to the single partition - * 'fallback_doms', it also forces the domains to be rebuilt. - * - * If doms_new == NULL it will be replaced with cpu_online_mask. - * ndoms_new == 0 is a special case for destroying existing domains, - * and it will not create the default domain. - * - * Call with hotplug lock held - */ -void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new) -{ - int i, j, n; - int new_topology; - - mutex_lock(&sched_domains_mutex); - - /* always unregister in case we don't destroy any domains */ - unregister_sched_domain_sysctl(); - - /* Let architecture update cpu core mappings. */ - new_topology = arch_update_cpu_topology(); - - n = doms_new ? ndoms_new : 0; - - /* Destroy deleted domains */ - for (i = 0; i < ndoms_cur; i++) { - for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(doms_cur[i], doms_new[j]) - && dattrs_equal(dattr_cur, i, dattr_new, j)) - goto match1; - } - /* no match - a current sched domain not in new doms_new[] */ - detach_destroy_domains(doms_cur[i]); -match1: - ; - } - - n = ndoms_cur; - if (doms_new == NULL) { - n = 0; - doms_new = &fallback_doms; - cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); - WARN_ON_ONCE(dattr_new); - } - - /* Build new domains */ - for (i = 0; i < ndoms_new; i++) { - for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(doms_new[i], doms_cur[j]) - && dattrs_equal(dattr_new, i, dattr_cur, j)) - goto match2; - } - /* no match - add a new doms_new */ - build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); -match2: - ; - } - - /* Remember the new sched domains */ - if (doms_cur != &fallback_doms) - free_sched_domains(doms_cur, ndoms_cur); - kfree(dattr_cur); /* kfree(NULL) is safe */ - doms_cur = doms_new; - dattr_cur = dattr_new; - ndoms_cur = ndoms_new; - - register_sched_domain_sysctl(); - - mutex_unlock(&sched_domains_mutex); -} - -static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ +static int num_cpus_frozen; /* * Update cpusets according to cpu_active mask. If cpusets are @@ -7352,7 +5759,7 @@ int sched_cpu_activate(unsigned int cpu) * Put the rq online, if not already. This happens: * * 1) In the early boot process, because we build the real domains - * after all cpus have been brought up. + * after all CPUs have been brought up. * * 2) At runtime, if cpuset_cpu_active() fails to rebuild the * domains. @@ -7467,7 +5874,7 @@ void __init sched_init_smp(void) /* * There's no userspace yet to cause hotplug operations; hence all the - * cpu masks are stable and all blatant races in the below code cannot + * CPU masks are stable and all blatant races in the below code cannot * happen. */ mutex_lock(&sched_domains_mutex); @@ -7487,6 +5894,7 @@ void __init sched_init_smp(void) init_sched_dl_class(); sched_init_smt(); + sched_clock_init_late(); sched_smp_initialized = true; } @@ -7502,6 +5910,7 @@ early_initcall(migration_init); void __init sched_init_smp(void) { sched_init_granularity(); + sched_clock_init_late(); } #endif /* CONFIG_SMP */ @@ -7545,6 +5954,8 @@ void __init sched_init(void) int i, j; unsigned long alloc_size = 0, ptr; + sched_clock_init(); + for (i = 0; i < WAIT_TABLE_SIZE; i++) init_waitqueue_head(bit_wait_table + i); @@ -7583,10 +5994,8 @@ void __init sched_init(void) } #endif /* CONFIG_CPUMASK_OFFSTACK */ - init_rt_bandwidth(&def_rt_bandwidth, - global_rt_period(), global_rt_runtime()); - init_dl_bandwidth(&def_dl_bandwidth, - global_rt_period(), global_rt_runtime()); + init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime()); + init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime()); #ifdef CONFIG_SMP init_defrootdomain(); @@ -7622,18 +6031,18 @@ void __init sched_init(void) INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; /* - * How much cpu bandwidth does root_task_group get? + * How much CPU bandwidth does root_task_group get? * * In case of task-groups formed thr' the cgroup filesystem, it - * gets 100% of the cpu resources in the system. This overall - * system cpu resource is divided among the tasks of + * gets 100% of the CPU resources in the system. This overall + * system CPU resource is divided among the tasks of * root_task_group and its child task-groups in a fair manner, * based on each entity's (task or task-group's) weight * (se->load.weight). * * In other words, if root_task_group has 10 tasks of weight * 1024) and two child groups A0 and A1 (of weight 1024 each), - * then A0's share of the cpu resource is: + * then A0's share of the CPU resource is: * * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33% * @@ -7742,10 +6151,14 @@ EXPORT_SYMBOL(__might_sleep); void ___might_sleep(const char *file, int line, int preempt_offset) { - static unsigned long prev_jiffy; /* ratelimiting */ + /* Ratelimiting timestamp: */ + static unsigned long prev_jiffy; + unsigned long preempt_disable_ip; - rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ + /* WARN_ON_ONCE() by default, no rate limit required: */ + rcu_sleep_check(); + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && !is_idle_task(current)) || system_state != SYSTEM_RUNNING || oops_in_progress) @@ -7754,7 +6167,7 @@ void ___might_sleep(const char *file, int line, int preempt_offset) return; prev_jiffy = jiffies; - /* Save this before calling printk(), since that will clobber it */ + /* Save this before calling printk(), since that will clobber it: */ preempt_disable_ip = get_preempt_disable_ip(current); printk(KERN_ERR @@ -7833,7 +6246,7 @@ void normalize_rt_tasks(void) */ /** - * curr_task - return the current task for a given cpu. + * curr_task - return the current task for a given CPU. * @cpu: the processor in question. * * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! @@ -7849,13 +6262,13 @@ struct task_struct *curr_task(int cpu) #ifdef CONFIG_IA64 /** - * set_curr_task - set the current task for a given cpu. + * set_curr_task - set the current task for a given CPU. * @cpu: the processor in question. * @p: the task pointer to set. * * Description: This function must only be used when non-maskable interrupts * are serviced on a separate stack. It allows the architecture to switch the - * notion of the current task on a cpu in a non-blocking manner. This function + * notion of the current task on a CPU in a non-blocking manner. This function * must be called with all CPU's synchronized, and interrupts disabled, the * and caller must save the original value of the current task (see * curr_task() above) and restore that value before reenabling interrupts and @@ -7911,7 +6324,8 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) spin_lock_irqsave(&task_group_lock, flags); list_add_rcu(&tg->list, &task_groups); - WARN_ON(!parent); /* root should already exist */ + /* Root should already exist: */ + WARN_ON(!parent); tg->parent = parent; INIT_LIST_HEAD(&tg->children); @@ -7924,13 +6338,13 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) /* rcu callback to free various structures associated with a task group */ static void sched_free_group_rcu(struct rcu_head *rhp) { - /* now it should be safe to free those cfs_rqs */ + /* Now it should be safe to free those cfs_rqs: */ sched_free_group(container_of(rhp, struct task_group, rcu)); } void sched_destroy_group(struct task_group *tg) { - /* wait for possible concurrent references to cfs_rqs complete */ + /* Wait for possible concurrent references to cfs_rqs complete: */ call_rcu(&tg->rcu, sched_free_group_rcu); } @@ -7938,7 +6352,7 @@ void sched_offline_group(struct task_group *tg) { unsigned long flags; - /* end participation in shares distribution */ + /* End participation in shares distribution: */ unregister_fair_sched_group(tg); spin_lock_irqsave(&task_group_lock, flags); @@ -7983,20 +6397,21 @@ void sched_move_task(struct task_struct *tsk) struct rq *rq; rq = task_rq_lock(tsk, &rf); + update_rq_clock(rq); running = task_current(rq, tsk); queued = task_on_rq_queued(tsk); if (queued) dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE); - if (unlikely(running)) + if (running) put_prev_task(rq, tsk); sched_change_group(tsk, TASK_MOVE_GROUP); if (queued) enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE); - if (unlikely(running)) + if (running) set_curr_task(rq, tsk); task_rq_unlock(rq, tsk, &rf); @@ -8366,11 +6781,14 @@ int sched_rr_handler(struct ctl_table *table, int write, mutex_lock(&mutex); ret = proc_dointvec(table, write, buffer, lenp, ppos); - /* make sure that internally we keep jiffies */ - /* also, writing zero resets timeslice to default */ + /* + * Make sure that internally we keep jiffies. + * Also, writing zero resets the timeslice to default: + */ if (!ret && write) { - sched_rr_timeslice = sched_rr_timeslice <= 0 ? - RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice); + sched_rr_timeslice = + sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE : + msecs_to_jiffies(sysctl_sched_rr_timeslice); } mutex_unlock(&mutex); return ret; @@ -8431,6 +6849,7 @@ static void cpu_cgroup_fork(struct task_struct *task) rq = task_rq_lock(task, &rf); + update_rq_clock(rq); sched_change_group(task, TASK_SET_GROUP); task_rq_unlock(rq, task, &rf); @@ -8550,9 +6969,11 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) cfs_b->quota = quota; __refill_cfs_bandwidth_runtime(cfs_b); - /* restart the period timer (if active) to handle new period expiry */ + + /* Restart the period timer (if active) to handle new period expiry: */ if (runtime_enabled) start_cfs_bandwidth(cfs_b); + raw_spin_unlock_irq(&cfs_b->lock); for_each_online_cpu(i) { @@ -8690,8 +7111,8 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data) parent_quota = parent_b->hierarchical_quota; /* - * ensure max(child_quota) <= parent_quota, inherit when no - * limit is set + * Ensure max(child_quota) <= parent_quota, inherit when no + * limit is set: */ if (quota == RUNTIME_INF) quota = parent_quota; @@ -8800,7 +7221,7 @@ static struct cftype cpu_files[] = { .write_u64 = cpu_rt_period_write_uint, }, #endif - { } /* terminate */ + { } /* Terminate */ }; struct cgroup_subsys cpu_cgrp_subsys = { diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 9add206b5608..f95ab29a45d0 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -297,7 +297,7 @@ static int cpuacct_stats_show(struct seq_file *sf, void *v) for (stat = 0; stat < CPUACCT_STAT_NSTATS; stat++) { seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[stat], - (long long)cputime64_to_clock_t(val[stat])); + (long long)nsec_to_clock_t(val[stat])); } return 0; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 7700a9cba335..2ecec3a4f1ee 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -4,6 +4,7 @@ #include <linux/kernel_stat.h> #include <linux/static_key.h> #include <linux/context_tracking.h> +#include <linux/cputime.h> #include "sched.h" #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> @@ -44,6 +45,7 @@ void disable_sched_clock_irqtime(void) void irqtime_account_irq(struct task_struct *curr) { struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime); + u64 *cpustat = kcpustat_this_cpu->cpustat; s64 delta; int cpu; @@ -61,49 +63,34 @@ void irqtime_account_irq(struct task_struct *curr) * in that case, so as not to confuse scheduler with a special task * that do not consume any time, but still wants to run. */ - if (hardirq_count()) - irqtime->hardirq_time += delta; - else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) - irqtime->softirq_time += delta; + if (hardirq_count()) { + cpustat[CPUTIME_IRQ] += delta; + irqtime->tick_delta += delta; + } else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) { + cpustat[CPUTIME_SOFTIRQ] += delta; + irqtime->tick_delta += delta; + } u64_stats_update_end(&irqtime->sync); } EXPORT_SYMBOL_GPL(irqtime_account_irq); -static cputime_t irqtime_account_update(u64 irqtime, int idx, cputime_t maxtime) +static u64 irqtime_tick_accounted(u64 maxtime) { - u64 *cpustat = kcpustat_this_cpu->cpustat; - cputime_t irq_cputime; - - irq_cputime = nsecs_to_cputime64(irqtime) - cpustat[idx]; - irq_cputime = min(irq_cputime, maxtime); - cpustat[idx] += irq_cputime; + struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime); + u64 delta; - return irq_cputime; -} + delta = min(irqtime->tick_delta, maxtime); + irqtime->tick_delta -= delta; -static cputime_t irqtime_account_hi_update(cputime_t maxtime) -{ - return irqtime_account_update(__this_cpu_read(cpu_irqtime.hardirq_time), - CPUTIME_IRQ, maxtime); -} - -static cputime_t irqtime_account_si_update(cputime_t maxtime) -{ - return irqtime_account_update(__this_cpu_read(cpu_irqtime.softirq_time), - CPUTIME_SOFTIRQ, maxtime); + return delta; } #else /* CONFIG_IRQ_TIME_ACCOUNTING */ #define sched_clock_irqtime (0) -static cputime_t irqtime_account_hi_update(cputime_t dummy) -{ - return 0; -} - -static cputime_t irqtime_account_si_update(cputime_t dummy) +static u64 irqtime_tick_accounted(u64 dummy) { return 0; } @@ -129,7 +116,7 @@ static inline void task_group_account_field(struct task_struct *p, int index, * @p: the process that the cpu time gets accounted to * @cputime: the cpu time spent in user space since the last update */ -void account_user_time(struct task_struct *p, cputime_t cputime) +void account_user_time(struct task_struct *p, u64 cputime) { int index; @@ -140,7 +127,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime) index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; /* Add user time to cpustat. */ - task_group_account_field(p, index, (__force u64) cputime); + task_group_account_field(p, index, cputime); /* Account for user time used */ acct_account_cputime(p); @@ -151,7 +138,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime) * @p: the process that the cpu time gets accounted to * @cputime: the cpu time spent in virtual machine since the last update */ -static void account_guest_time(struct task_struct *p, cputime_t cputime) +void account_guest_time(struct task_struct *p, u64 cputime) { u64 *cpustat = kcpustat_this_cpu->cpustat; @@ -162,11 +149,11 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime) /* Add guest time to cpustat. */ if (task_nice(p) > 0) { - cpustat[CPUTIME_NICE] += (__force u64) cputime; - cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; + cpustat[CPUTIME_NICE] += cputime; + cpustat[CPUTIME_GUEST_NICE] += cputime; } else { - cpustat[CPUTIME_USER] += (__force u64) cputime; - cpustat[CPUTIME_GUEST] += (__force u64) cputime; + cpustat[CPUTIME_USER] += cputime; + cpustat[CPUTIME_GUEST] += cputime; } } @@ -176,15 +163,15 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime) * @cputime: the cpu time spent in kernel space since the last update * @index: pointer to cpustat field that has to be updated */ -static inline -void __account_system_time(struct task_struct *p, cputime_t cputime, int index) +void account_system_index_time(struct task_struct *p, + u64 cputime, enum cpu_usage_stat index) { /* Add system time to process. */ p->stime += cputime; account_group_system_time(p, cputime); /* Add system time to cpustat. */ - task_group_account_field(p, index, (__force u64) cputime); + task_group_account_field(p, index, cputime); /* Account for system time used */ acct_account_cputime(p); @@ -196,8 +183,7 @@ void __account_system_time(struct task_struct *p, cputime_t cputime, int index) * @hardirq_offset: the offset to subtract from hardirq_count() * @cputime: the cpu time spent in kernel space since the last update */ -void account_system_time(struct task_struct *p, int hardirq_offset, - cputime_t cputime) +void account_system_time(struct task_struct *p, int hardirq_offset, u64 cputime) { int index; @@ -213,33 +199,33 @@ void account_system_time(struct task_struct *p, int hardirq_offset, else index = CPUTIME_SYSTEM; - __account_system_time(p, cputime, index); + account_system_index_time(p, cputime, index); } /* * Account for involuntary wait time. * @cputime: the cpu time spent in involuntary wait */ -void account_steal_time(cputime_t cputime) +void account_steal_time(u64 cputime) { u64 *cpustat = kcpustat_this_cpu->cpustat; - cpustat[CPUTIME_STEAL] += (__force u64) cputime; + cpustat[CPUTIME_STEAL] += cputime; } /* * Account for idle time. * @cputime: the cpu time spent in idle wait */ -void account_idle_time(cputime_t cputime) +void account_idle_time(u64 cputime) { u64 *cpustat = kcpustat_this_cpu->cpustat; struct rq *rq = this_rq(); if (atomic_read(&rq->nr_iowait) > 0) - cpustat[CPUTIME_IOWAIT] += (__force u64) cputime; + cpustat[CPUTIME_IOWAIT] += cputime; else - cpustat[CPUTIME_IDLE] += (__force u64) cputime; + cpustat[CPUTIME_IDLE] += cputime; } /* @@ -247,21 +233,19 @@ void account_idle_time(cputime_t cputime) * ticks are not redelivered later. Due to that, this function may on * occasion account more time than the calling functions think elapsed. */ -static __always_inline cputime_t steal_account_process_time(cputime_t maxtime) +static __always_inline u64 steal_account_process_time(u64 maxtime) { #ifdef CONFIG_PARAVIRT if (static_key_false(¶virt_steal_enabled)) { - cputime_t steal_cputime; u64 steal; steal = paravirt_steal_clock(smp_processor_id()); steal -= this_rq()->prev_steal_time; + steal = min(steal, maxtime); + account_steal_time(steal); + this_rq()->prev_steal_time += steal; - steal_cputime = min(nsecs_to_cputime(steal), maxtime); - account_steal_time(steal_cputime); - this_rq()->prev_steal_time += cputime_to_nsecs(steal_cputime); - - return steal_cputime; + return steal; } #endif return 0; @@ -270,9 +254,9 @@ static __always_inline cputime_t steal_account_process_time(cputime_t maxtime) /* * Account how much elapsed time was spent in steal, irq, or softirq time. */ -static inline cputime_t account_other_time(cputime_t max) +static inline u64 account_other_time(u64 max) { - cputime_t accounted; + u64 accounted; /* Shall be converted to a lockdep-enabled lightweight check */ WARN_ON_ONCE(!irqs_disabled()); @@ -280,10 +264,7 @@ static inline cputime_t account_other_time(cputime_t max) accounted = steal_account_process_time(max); if (accounted < max) - accounted += irqtime_account_hi_update(max - accounted); - - if (accounted < max) - accounted += irqtime_account_si_update(max - accounted); + accounted += irqtime_tick_accounted(max - accounted); return accounted; } @@ -315,7 +296,7 @@ static u64 read_sum_exec_runtime(struct task_struct *t) void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) { struct signal_struct *sig = tsk->signal; - cputime_t utime, stime; + u64 utime, stime; struct task_struct *t; unsigned int seq, nextseq; unsigned long flags; @@ -379,8 +360,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) static void irqtime_account_process_tick(struct task_struct *p, int user_tick, struct rq *rq, int ticks) { - u64 cputime = (__force u64) cputime_one_jiffy * ticks; - cputime_t other; + u64 other, cputime = TICK_NSEC * ticks; /* * When returning from idle, many ticks can get accounted at @@ -392,6 +372,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, other = account_other_time(ULONG_MAX); if (other >= cputime) return; + cputime -= other; if (this_cpu_ksoftirqd() == p) { @@ -400,7 +381,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, * So, we have to handle it separately here. * Also, p->stime needs to be updated for ksoftirqd. */ - __account_system_time(p, cputime, CPUTIME_SOFTIRQ); + account_system_index_time(p, cputime, CPUTIME_SOFTIRQ); } else if (user_tick) { account_user_time(p, cputime); } else if (p == rq->idle) { @@ -408,7 +389,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, } else if (p->flags & PF_VCPU) { /* System time or guest time */ account_guest_time(p, cputime); } else { - __account_system_time(p, cputime, CPUTIME_SYSTEM); + account_system_index_time(p, cputime, CPUTIME_SYSTEM); } } @@ -437,9 +418,7 @@ void vtime_common_task_switch(struct task_struct *prev) else vtime_account_system(prev); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE - vtime_account_user(prev); -#endif + vtime_flush(prev); arch_vtime_task_switch(prev); } #endif @@ -467,14 +446,14 @@ void vtime_account_irq_enter(struct task_struct *tsk) EXPORT_SYMBOL_GPL(vtime_account_irq_enter); #endif /* __ARCH_HAS_VTIME_ACCOUNT */ -void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) { *ut = p->utime; *st = p->stime; } EXPORT_SYMBOL_GPL(task_cputime_adjusted); -void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) { struct task_cputime cputime; @@ -491,7 +470,7 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime */ void account_process_tick(struct task_struct *p, int user_tick) { - cputime_t cputime, steal; + u64 cputime, steal; struct rq *rq = this_rq(); if (vtime_accounting_cpu_enabled()) @@ -502,7 +481,7 @@ void account_process_tick(struct task_struct *p, int user_tick) return; } - cputime = cputime_one_jiffy; + cputime = TICK_NSEC; steal = steal_account_process_time(ULONG_MAX); if (steal >= cputime) @@ -524,14 +503,14 @@ void account_process_tick(struct task_struct *p, int user_tick) */ void account_idle_ticks(unsigned long ticks) { - cputime_t cputime, steal; + u64 cputime, steal; if (sched_clock_irqtime) { irqtime_account_idle_ticks(ticks); return; } - cputime = jiffies_to_cputime(ticks); + cputime = ticks * TICK_NSEC; steal = steal_account_process_time(ULONG_MAX); if (steal >= cputime) @@ -545,7 +524,7 @@ void account_idle_ticks(unsigned long ticks) * Perform (stime * rtime) / total, but avoid multiplication overflow by * loosing precision when the numbers are big. */ -static cputime_t scale_stime(u64 stime, u64 rtime, u64 total) +static u64 scale_stime(u64 stime, u64 rtime, u64 total) { u64 scaled; @@ -582,7 +561,7 @@ drop_precision: * followed by a 64/32->64 divide. */ scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total); - return (__force cputime_t) scaled; + return scaled; } /* @@ -607,14 +586,14 @@ drop_precision: */ static void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev, - cputime_t *ut, cputime_t *st) + u64 *ut, u64 *st) { - cputime_t rtime, stime, utime; + u64 rtime, stime, utime; unsigned long flags; /* Serialize concurrent callers such that we can honour our guarantees */ raw_spin_lock_irqsave(&prev->lock, flags); - rtime = nsecs_to_cputime(curr->sum_exec_runtime); + rtime = curr->sum_exec_runtime; /* * This is possible under two circumstances: @@ -645,8 +624,7 @@ static void cputime_adjust(struct task_cputime *curr, goto update; } - stime = scale_stime((__force u64)stime, (__force u64)rtime, - (__force u64)(stime + utime)); + stime = scale_stime(stime, rtime, stime + utime); update: /* @@ -679,7 +657,7 @@ out: raw_spin_unlock_irqrestore(&prev->lock, flags); } -void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) { struct task_cputime cputime = { .sum_exec_runtime = p->se.sum_exec_runtime, @@ -690,7 +668,7 @@ void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) } EXPORT_SYMBOL_GPL(task_cputime_adjusted); -void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) { struct task_cputime cputime; @@ -700,20 +678,20 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -static cputime_t vtime_delta(struct task_struct *tsk) +static u64 vtime_delta(struct task_struct *tsk) { unsigned long now = READ_ONCE(jiffies); if (time_before(now, (unsigned long)tsk->vtime_snap)) return 0; - return jiffies_to_cputime(now - tsk->vtime_snap); + return jiffies_to_nsecs(now - tsk->vtime_snap); } -static cputime_t get_vtime_delta(struct task_struct *tsk) +static u64 get_vtime_delta(struct task_struct *tsk) { unsigned long now = READ_ONCE(jiffies); - cputime_t delta, other; + u64 delta, other; /* * Unlike tick based timing, vtime based timing never has lost @@ -722,7 +700,7 @@ static cputime_t get_vtime_delta(struct task_struct *tsk) * elapsed time. Limit account_other_time to prevent rounding * errors from causing elapsed vtime to go negative. */ - delta = jiffies_to_cputime(now - tsk->vtime_snap); + delta = jiffies_to_nsecs(now - tsk->vtime_snap); other = account_other_time(delta); WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); tsk->vtime_snap = now; @@ -732,9 +710,7 @@ static cputime_t get_vtime_delta(struct task_struct *tsk) static void __vtime_account_system(struct task_struct *tsk) { - cputime_t delta_cpu = get_vtime_delta(tsk); - - account_system_time(tsk, irq_count(), delta_cpu); + account_system_time(tsk, irq_count(), get_vtime_delta(tsk)); } void vtime_account_system(struct task_struct *tsk) @@ -749,14 +725,10 @@ void vtime_account_system(struct task_struct *tsk) void vtime_account_user(struct task_struct *tsk) { - cputime_t delta_cpu; - write_seqcount_begin(&tsk->vtime_seqcount); tsk->vtime_snap_whence = VTIME_SYS; - if (vtime_delta(tsk)) { - delta_cpu = get_vtime_delta(tsk); - account_user_time(tsk, delta_cpu); - } + if (vtime_delta(tsk)) + account_user_time(tsk, get_vtime_delta(tsk)); write_seqcount_end(&tsk->vtime_seqcount); } @@ -797,9 +769,7 @@ EXPORT_SYMBOL_GPL(vtime_guest_exit); void vtime_account_idle(struct task_struct *tsk) { - cputime_t delta_cpu = get_vtime_delta(tsk); - - account_idle_time(delta_cpu); + account_idle_time(get_vtime_delta(tsk)); } void arch_vtime_task_switch(struct task_struct *prev) @@ -826,10 +796,10 @@ void vtime_init_idle(struct task_struct *t, int cpu) local_irq_restore(flags); } -cputime_t task_gtime(struct task_struct *t) +u64 task_gtime(struct task_struct *t) { unsigned int seq; - cputime_t gtime; + u64 gtime; if (!vtime_accounting_enabled()) return t->gtime; @@ -851,9 +821,9 @@ cputime_t task_gtime(struct task_struct *t) * add up the pending nohz execution time since the last * cputime snapshot. */ -void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime) +void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { - cputime_t delta; + u64 delta; unsigned int seq; if (!vtime_accounting_enabled()) { diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 70ef2b1901e4..27737f34757d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -663,9 +663,9 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * Nothing relies on rq->lock after this, so its safe to drop * rq->lock. */ - lockdep_unpin_lock(&rq->lock, rf.cookie); + rq_unpin_lock(rq, &rf); push_dl_task(rq); - lockdep_repin_lock(&rq->lock, rf.cookie); + rq_repin_lock(rq, &rf); } #endif @@ -1118,7 +1118,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, } struct task_struct * -pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct sched_dl_entity *dl_se; struct task_struct *p; @@ -1133,9 +1133,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie coo * disabled avoiding further scheduler activity on it and we're * being very careful to re-start the picking loop. */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, rf); pull_dl_task(rq); - lockdep_repin_lock(&rq->lock, cookie); + rq_repin_lock(rq, rf); /* * pull_dl_task() can drop (and re-acquire) rq->lock; this * means a stop task can slip in, in which case we need to @@ -1729,12 +1729,11 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) #ifdef CONFIG_SMP if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded) queue_push_tasks(rq); -#else +#endif if (dl_task(rq->curr)) check_preempt_curr_dl(rq, p, 0); else resched_curr(rq); -#endif } } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index fa178b62ea79..109adc0e9cb9 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -953,6 +953,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) #endif P(policy); P(prio); + if (p->policy == SCHED_DEADLINE) { + P(dl.runtime); + P(dl.deadline); + } #undef PN_SCHEDSTAT #undef PN #undef __PN diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6559d197e08a..274c747a01ce 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2657,6 +2657,18 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) if (tg_weight) shares /= tg_weight; + /* + * MIN_SHARES has to be unscaled here to support per-CPU partitioning + * of a group with small tg->shares value. It is a floor value which is + * assigned as a minimum load.weight to the sched_entity representing + * the group on a CPU. + * + * E.g. on 64-bit for a group with tg->shares of scale_load(15)=15*1024 + * on an 8-core system with 8 tasks each runnable on one CPU shares has + * to be 15*1024*1/8=1920 instead of scale_load(MIN_SHARES)=2*1024. In + * case no task is runnable on a CPU MIN_SHARES=2 should be returned + * instead of 0. + */ if (shares < MIN_SHARES) shares = MIN_SHARES; if (shares > tg->shares) @@ -2689,16 +2701,20 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); -static void update_cfs_shares(struct cfs_rq *cfs_rq) +static void update_cfs_shares(struct sched_entity *se) { + struct cfs_rq *cfs_rq = group_cfs_rq(se); struct task_group *tg; - struct sched_entity *se; long shares; - tg = cfs_rq->tg; - se = tg->se[cpu_of(rq_of(cfs_rq))]; - if (!se || throttled_hierarchy(cfs_rq)) + if (!cfs_rq) + return; + + if (throttled_hierarchy(cfs_rq)) return; + + tg = cfs_rq->tg; + #ifndef CONFIG_SMP if (likely(se->load.weight == tg->shares)) return; @@ -2707,8 +2723,9 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq) reweight_entity(cfs_rq_of(se), se, shares); } + #else /* CONFIG_FAIR_GROUP_SCHED */ -static inline void update_cfs_shares(struct cfs_rq *cfs_rq) +static inline void update_cfs_shares(struct sched_entity *se) { } #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -3424,7 +3441,7 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) return cfs_rq->avg.load_avg; } -static int idle_balance(struct rq *this_rq); +static int idle_balance(struct rq *this_rq, struct rq_flags *rf); #else /* CONFIG_SMP */ @@ -3453,7 +3470,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} static inline void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} -static inline int idle_balance(struct rq *rq) +static inline int idle_balance(struct rq *rq, struct rq_flags *rf) { return 0; } @@ -3582,10 +3599,18 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (renorm && !curr) se->vruntime += cfs_rq->min_vruntime; + /* + * When enqueuing a sched_entity, we must: + * - Update loads to have both entity and cfs_rq synced with now. + * - Add its load to cfs_rq->runnable_avg + * - For group_entity, update its weight to reflect the new share of + * its group cfs_rq + * - Add its new weight to cfs_rq->load.weight + */ update_load_avg(se, UPDATE_TG); enqueue_entity_load_avg(cfs_rq, se); + update_cfs_shares(se); account_entity_enqueue(cfs_rq, se); - update_cfs_shares(cfs_rq); if (flags & ENQUEUE_WAKEUP) place_entity(cfs_rq, se, 0); @@ -3657,6 +3682,15 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * Update run-time statistics of the 'current'. */ update_curr(cfs_rq); + + /* + * When dequeuing a sched_entity, we must: + * - Update loads to have both entity and cfs_rq synced with now. + * - Substract its load from the cfs_rq->runnable_avg. + * - Substract its previous weight from cfs_rq->load.weight. + * - For group entity, update its weight to reflect the new share + * of its group cfs_rq. + */ update_load_avg(se, UPDATE_TG); dequeue_entity_load_avg(cfs_rq, se); @@ -3681,7 +3715,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) /* return excess runtime on last dequeue */ return_cfs_rq_runtime(cfs_rq); - update_cfs_shares(cfs_rq); + update_cfs_shares(se); /* * Now advance min_vruntime if @se was the entity holding it back, @@ -3864,7 +3898,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) * Ensure that runnable average is periodically updated. */ update_load_avg(curr, UPDATE_TG); - update_cfs_shares(cfs_rq); + update_cfs_shares(curr); #ifdef CONFIG_SCHED_HRTICK /* @@ -4761,7 +4795,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) break; update_load_avg(se, UPDATE_TG); - update_cfs_shares(cfs_rq); + update_cfs_shares(se); } if (!se) @@ -4820,7 +4854,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) break; update_load_avg(se, UPDATE_TG); - update_cfs_shares(cfs_rq); + update_cfs_shares(se); } if (!se) @@ -6213,7 +6247,7 @@ preempt: } static struct task_struct * -pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct cfs_rq *cfs_rq = &rq->cfs; struct sched_entity *se; @@ -6320,15 +6354,8 @@ simple: return p; idle: - /* - * This is OK, because current is on_cpu, which avoids it being picked - * for load-balance and preemption/IRQs are still disabled avoiding - * further scheduler activity on it and we're being very careful to - * re-start the picking loop. - */ - lockdep_unpin_lock(&rq->lock, cookie); - new_tasks = idle_balance(rq); - lockdep_repin_lock(&rq->lock, cookie); + new_tasks = idle_balance(rq, rf); + /* * Because idle_balance() releases (and re-acquires) rq->lock, it is * possible for any higher priority task to appear. In that case we @@ -8077,6 +8104,7 @@ redo: more_balance: raw_spin_lock_irqsave(&busiest->lock, flags); + update_rq_clock(busiest); /* * cur_ld_moved - load moved in current iteration @@ -8297,7 +8325,7 @@ update_next_balance(struct sched_domain *sd, unsigned long *next_balance) * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ -static int idle_balance(struct rq *this_rq) +static int idle_balance(struct rq *this_rq, struct rq_flags *rf) { unsigned long next_balance = jiffies + HZ; int this_cpu = this_rq->cpu; @@ -8311,6 +8339,14 @@ static int idle_balance(struct rq *this_rq) */ this_rq->idle_stamp = rq_clock(this_rq); + /* + * This is OK, because current is on_cpu, which avoids it being picked + * for load-balance and preemption/IRQs are still disabled avoiding + * further scheduler activity on it and we're being very careful to + * re-start the picking loop. + */ + rq_unpin_lock(this_rq, rf); + if (this_rq->avg_idle < sysctl_sched_migration_cost || !this_rq->rd->overload) { rcu_read_lock(); @@ -8388,6 +8424,8 @@ out: if (pulled_task) this_rq->idle_stamp = 0; + rq_repin_lock(this_rq, rf); + return pulled_task; } @@ -8443,6 +8481,7 @@ static int active_load_balance_cpu_stop(void *data) }; schedstat_inc(sd->alb_count); + update_rq_clock(busiest_rq); p = detach_one_task(&env); if (p) { @@ -9264,6 +9303,7 @@ void online_fair_sched_group(struct task_group *tg) se = tg->se[i]; raw_spin_lock_irq(&rq->lock); + update_rq_clock(rq); attach_entity_cfs_rq(se); sync_throttle(tg, i); raw_spin_unlock_irq(&rq->lock); @@ -9356,8 +9396,10 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) /* Possible calls to update_curr() need rq clock */ update_rq_clock(rq); - for_each_sched_entity(se) - update_cfs_shares(group_cfs_rq(se)); + for_each_sched_entity(se) { + update_load_avg(se, UPDATE_TG); + update_cfs_shares(se); + } raw_spin_unlock_irqrestore(&rq->lock, flags); } diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index 5405d3feb112..0c00172db63e 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -24,7 +24,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl } static struct task_struct * -pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { put_prev_task(rq, prev); update_idle_core(rq); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 2516b8df6dbb..e8836cfc4cdb 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -9,6 +9,7 @@ #include <linux/irq_work.h> int sched_rr_timeslice = RR_TIMESLICE; +int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); @@ -1523,7 +1524,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) } static struct task_struct * -pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct task_struct *p; struct rt_rq *rt_rq = &rq->rt; @@ -1535,9 +1536,9 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie coo * disabled avoiding further scheduler activity on it and we're * being very careful to re-start the picking loop. */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, rf); pull_rt_task(rq); - lockdep_repin_lock(&rq->lock, cookie); + rq_repin_lock(rq, rf); /* * pull_rt_task() can drop (and re-acquire) rq->lock; this * means a dl or stop task can slip in, in which case we need @@ -2198,10 +2199,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) #ifdef CONFIG_SMP if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded) queue_push_tasks(rq); -#else +#endif /* CONFIG_SMP */ if (p->prio < rq->curr->prio) resched_curr(rq); -#endif /* CONFIG_SMP */ } } @@ -2246,6 +2246,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) } } +#ifdef CONFIG_POSIX_TIMERS static void watchdog(struct rq *rq, struct task_struct *p) { unsigned long soft, hard; @@ -2267,6 +2268,9 @@ static void watchdog(struct rq *rq, struct task_struct *p) p->cputime_expires.sched_exp = p->se.sum_exec_runtime; } } +#else +static inline void watchdog(struct rq *rq, struct task_struct *p) { } +#endif static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) { diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7b34c7826ca5..71b10a9b73cf 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -4,6 +4,7 @@ #include <linux/sched/rt.h> #include <linux/u64_stats_sync.h> #include <linux/sched/deadline.h> +#include <linux/kernel_stat.h> #include <linux/binfmts.h> #include <linux/mutex.h> #include <linux/spinlock.h> @@ -222,7 +223,7 @@ bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw) dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw; } -extern struct mutex sched_domains_mutex; +extern void init_dl_bw(struct dl_bw *dl_b); #ifdef CONFIG_CGROUP_SCHED @@ -583,6 +584,13 @@ struct root_domain { }; extern struct root_domain def_root_domain; +extern struct mutex sched_domains_mutex; +extern cpumask_var_t fallback_doms; +extern cpumask_var_t sched_domains_tmpmask; + +extern void init_defrootdomain(void); +extern int init_sched_domains(const struct cpumask *cpu_map); +extern void rq_attach_root(struct rq *rq, struct root_domain *rd); #endif /* CONFIG_SMP */ @@ -644,7 +652,7 @@ struct rq { unsigned long next_balance; struct mm_struct *prev_mm; - unsigned int clock_skip_update; + unsigned int clock_update_flags; u64 clock; u64 clock_task; @@ -768,28 +776,110 @@ static inline u64 __rq_clock_broken(struct rq *rq) return READ_ONCE(rq->clock); } +/* + * rq::clock_update_flags bits + * + * %RQCF_REQ_SKIP - will request skipping of clock update on the next + * call to __schedule(). This is an optimisation to avoid + * neighbouring rq clock updates. + * + * %RQCF_ACT_SKIP - is set from inside of __schedule() when skipping is + * in effect and calls to update_rq_clock() are being ignored. + * + * %RQCF_UPDATED - is a debug flag that indicates whether a call has been + * made to update_rq_clock() since the last time rq::lock was pinned. + * + * If inside of __schedule(), clock_update_flags will have been + * shifted left (a left shift is a cheap operation for the fast path + * to promote %RQCF_REQ_SKIP to %RQCF_ACT_SKIP), so you must use, + * + * if (rq-clock_update_flags >= RQCF_UPDATED) + * + * to check if %RQCF_UPADTED is set. It'll never be shifted more than + * one position though, because the next rq_unpin_lock() will shift it + * back. + */ +#define RQCF_REQ_SKIP 0x01 +#define RQCF_ACT_SKIP 0x02 +#define RQCF_UPDATED 0x04 + +static inline void assert_clock_updated(struct rq *rq) +{ + /* + * The only reason for not seeing a clock update since the + * last rq_pin_lock() is if we're currently skipping updates. + */ + SCHED_WARN_ON(rq->clock_update_flags < RQCF_ACT_SKIP); +} + static inline u64 rq_clock(struct rq *rq) { lockdep_assert_held(&rq->lock); + assert_clock_updated(rq); + return rq->clock; } static inline u64 rq_clock_task(struct rq *rq) { lockdep_assert_held(&rq->lock); + assert_clock_updated(rq); + return rq->clock_task; } -#define RQCF_REQ_SKIP 0x01 -#define RQCF_ACT_SKIP 0x02 - static inline void rq_clock_skip_update(struct rq *rq, bool skip) { lockdep_assert_held(&rq->lock); if (skip) - rq->clock_skip_update |= RQCF_REQ_SKIP; + rq->clock_update_flags |= RQCF_REQ_SKIP; else - rq->clock_skip_update &= ~RQCF_REQ_SKIP; + rq->clock_update_flags &= ~RQCF_REQ_SKIP; +} + +struct rq_flags { + unsigned long flags; + struct pin_cookie cookie; +#ifdef CONFIG_SCHED_DEBUG + /* + * A copy of (rq::clock_update_flags & RQCF_UPDATED) for the + * current pin context is stashed here in case it needs to be + * restored in rq_repin_lock(). + */ + unsigned int clock_update_flags; +#endif +}; + +static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf) +{ + rf->cookie = lockdep_pin_lock(&rq->lock); + +#ifdef CONFIG_SCHED_DEBUG + rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP); + rf->clock_update_flags = 0; +#endif +} + +static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf) +{ +#ifdef CONFIG_SCHED_DEBUG + if (rq->clock_update_flags > RQCF_ACT_SKIP) + rf->clock_update_flags = RQCF_UPDATED; +#endif + + lockdep_unpin_lock(&rq->lock, rf->cookie); +} + +static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf) +{ + lockdep_repin_lock(&rq->lock, rf->cookie); + +#ifdef CONFIG_SCHED_DEBUG + /* + * Restore the value we stashed in @rf for this pin context. + */ + rq->clock_update_flags |= rf->clock_update_flags; +#endif } #ifdef CONFIG_NUMA @@ -803,6 +893,16 @@ extern int sched_max_numa_distance; extern bool find_numa_distance(int distance); #endif +#ifdef CONFIG_NUMA +extern void sched_init_numa(void); +extern void sched_domains_numa_masks_set(unsigned int cpu); +extern void sched_domains_numa_masks_clear(unsigned int cpu); +#else +static inline void sched_init_numa(void) { } +static inline void sched_domains_numa_masks_set(unsigned int cpu) { } +static inline void sched_domains_numa_masks_clear(unsigned int cpu) { } +#endif + #ifdef CONFIG_NUMA_BALANCING /* The regions in numa_faults array from task_struct */ enum numa_faults_stats { @@ -969,7 +1069,7 @@ static inline void sched_ttwu_pending(void) { } #endif /* CONFIG_SMP */ #include "stats.h" -#include "auto_group.h" +#include "autogroup.h" #ifdef CONFIG_CGROUP_SCHED @@ -1245,7 +1345,7 @@ struct sched_class { */ struct task_struct * (*pick_next_task) (struct rq *rq, struct task_struct *prev, - struct pin_cookie cookie); + struct rq_flags *rf); void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP @@ -1501,11 +1601,6 @@ 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_flags { - unsigned long flags; - struct pin_cookie cookie; -}; - struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) __acquires(rq->lock); struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) @@ -1515,7 +1610,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) __releases(rq->lock) { - lockdep_unpin_lock(&rq->lock, rf->cookie); + rq_unpin_lock(rq, rf); raw_spin_unlock(&rq->lock); } @@ -1524,7 +1619,7 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) __releases(rq->lock) __releases(p->pi_lock) { - lockdep_unpin_lock(&rq->lock, rf->cookie); + rq_unpin_lock(rq, rf); raw_spin_unlock(&rq->lock); raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); } @@ -1674,6 +1769,10 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2) __release(rq2->lock); } +extern void set_rq_online (struct rq *rq); +extern void set_rq_offline(struct rq *rq); +extern bool sched_smp_initialized; + #else /* CONFIG_SMP */ /* @@ -1750,8 +1849,7 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { } #ifdef CONFIG_IRQ_TIME_ACCOUNTING struct irqtime { - u64 hardirq_time; - u64 softirq_time; + u64 tick_delta; u64 irq_start_time; struct u64_stats_sync sync; }; @@ -1761,12 +1859,13 @@ DECLARE_PER_CPU(struct irqtime, cpu_irqtime); static inline u64 irq_time_read(int cpu) { struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu); + u64 *cpustat = kcpustat_cpu(cpu).cpustat; unsigned int seq; u64 total; do { seq = __u64_stats_fetch_begin(&irqtime->sync); - total = irqtime->softirq_time + irqtime->hardirq_time; + total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ]; } while (__u64_stats_fetch_retry(&irqtime->sync, seq)); return total; diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 34659a853505..bf0da0aa0a14 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -172,18 +172,19 @@ sched_info_switch(struct rq *rq, */ /** - * cputimer_running - return true if cputimer is running + * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running * * @tsk: Pointer to target task. */ -static inline bool cputimer_running(struct task_struct *tsk) - +#ifdef CONFIG_POSIX_TIMERS +static inline +struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; /* Check if cputimer isn't running. This is accessed without locking. */ if (!READ_ONCE(cputimer->running)) - return false; + return NULL; /* * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime @@ -200,10 +201,17 @@ static inline bool cputimer_running(struct task_struct *tsk) * clock delta is behind the expiring timer value. */ if (unlikely(!tsk->sighand)) - return false; + return NULL; - return true; + return cputimer; +} +#else +static inline +struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) +{ + return NULL; } +#endif /** * account_group_user_time - Maintain utime for a thread group. @@ -216,11 +224,11 @@ static inline bool cputimer_running(struct task_struct *tsk) * running CPU and update the utime field there. */ static inline void account_group_user_time(struct task_struct *tsk, - cputime_t cputime) + u64 cputime) { - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); - if (!cputimer_running(tsk)) + if (!cputimer) return; atomic64_add(cputime, &cputimer->cputime_atomic.utime); @@ -237,11 +245,11 @@ static inline void account_group_user_time(struct task_struct *tsk, * running CPU and update the stime field there. */ static inline void account_group_system_time(struct task_struct *tsk, - cputime_t cputime) + u64 cputime) { - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); - if (!cputimer_running(tsk)) + if (!cputimer) return; atomic64_add(cputime, &cputimer->cputime_atomic.stime); @@ -260,9 +268,9 @@ static inline void account_group_system_time(struct task_struct *tsk, static inline void account_group_exec_runtime(struct task_struct *tsk, unsigned long long ns) { - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); - if (!cputimer_running(tsk)) + if (!cputimer) return; atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime); diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 604297a08b3a..9f69fb630853 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -24,7 +24,7 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags) } static struct task_struct * -pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct task_struct *stop = rq->stop; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c new file mode 100644 index 000000000000..1b0b4fb12837 --- /dev/null +++ b/kernel/sched/topology.c @@ -0,0 +1,1658 @@ +/* + * Scheduler topology setup/handling methods + */ +#include <linux/sched.h> +#include <linux/mutex.h> + +#include "sched.h" + +DEFINE_MUTEX(sched_domains_mutex); + +/* Protected by sched_domains_mutex: */ +cpumask_var_t sched_domains_tmpmask; + +#ifdef CONFIG_SCHED_DEBUG + +static __read_mostly int sched_debug_enabled; + +static int __init sched_debug_setup(char *str) +{ + sched_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_debug_setup); + +static inline bool sched_debug(void) +{ + return sched_debug_enabled; +} + +static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, + struct cpumask *groupmask) +{ + struct sched_group *group = sd->groups; + + cpumask_clear(groupmask); + + printk(KERN_DEBUG "%*s domain %d: ", level, "", level); + + if (!(sd->flags & SD_LOAD_BALANCE)) { + printk("does not load-balance\n"); + if (sd->parent) + printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" + " has parent"); + return -1; + } + + printk(KERN_CONT "span %*pbl level %s\n", + cpumask_pr_args(sched_domain_span(sd)), sd->name); + + 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_cpus(group))) { + printk(KERN_ERR "ERROR: domain->groups does not contain" + " CPU%d\n", cpu); + } + + printk(KERN_DEBUG "%*s groups:", level + 1, ""); + do { + if (!group) { + printk("\n"); + printk(KERN_ERR "ERROR: group is NULL\n"); + break; + } + + if (!cpumask_weight(sched_group_cpus(group))) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: empty group\n"); + break; + } + + if (!(sd->flags & SD_OVERLAP) && + cpumask_intersects(groupmask, sched_group_cpus(group))) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: repeated CPUs\n"); + break; + } + + cpumask_or(groupmask, groupmask, sched_group_cpus(group)); + + printk(KERN_CONT " %*pbl", + cpumask_pr_args(sched_group_cpus(group))); + if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { + printk(KERN_CONT " (cpu_capacity = %lu)", + group->sgc->capacity); + } + + group = group->next; + } while (group != sd->groups); + printk(KERN_CONT "\n"); + + if (!cpumask_equal(sched_domain_span(sd), groupmask)) + printk(KERN_ERR "ERROR: groups don't span domain->span\n"); + + if (sd->parent && + !cpumask_subset(groupmask, sched_domain_span(sd->parent))) + printk(KERN_ERR "ERROR: parent span is not a superset " + "of domain->span\n"); + return 0; +} + +static void sched_domain_debug(struct sched_domain *sd, int cpu) +{ + int level = 0; + + if (!sched_debug_enabled) + return; + + if (!sd) { + printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); + return; + } + + printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + + for (;;) { + if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) + break; + level++; + sd = sd->parent; + if (!sd) + break; + } +} +#else /* !CONFIG_SCHED_DEBUG */ + +# define sched_debug_enabled 0 +# define sched_domain_debug(sd, cpu) do { } while (0) +static inline bool sched_debug(void) +{ + return false; +} +#endif /* CONFIG_SCHED_DEBUG */ + +static int sd_degenerate(struct sched_domain *sd) +{ + if (cpumask_weight(sched_domain_span(sd)) == 1) + return 1; + + /* Following flags need at least 2 groups */ + if (sd->flags & (SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_SHARE_CPUCAPACITY | + SD_ASYM_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_SHARE_POWERDOMAIN)) { + if (sd->groups != sd->groups->next) + return 0; + } + + /* Following flags don't use groups */ + if (sd->flags & (SD_WAKE_AFFINE)) + return 0; + + return 1; +} + +static int +sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) +{ + unsigned long cflags = sd->flags, pflags = parent->flags; + + if (sd_degenerate(parent)) + return 1; + + if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) + return 0; + + /* Flags needing groups don't count if only 1 group in parent */ + if (parent->groups == parent->groups->next) { + pflags &= ~(SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_ASYM_CPUCAPACITY | + SD_SHARE_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_PREFER_SIBLING | + SD_SHARE_POWERDOMAIN); + if (nr_node_ids == 1) + pflags &= ~SD_SERIALIZE; + } + if (~cflags & pflags) + return 0; + + return 1; +} + +static void free_rootdomain(struct rcu_head *rcu) +{ + struct root_domain *rd = container_of(rcu, struct root_domain, rcu); + + cpupri_cleanup(&rd->cpupri); + cpudl_cleanup(&rd->cpudl); + free_cpumask_var(rd->dlo_mask); + free_cpumask_var(rd->rto_mask); + free_cpumask_var(rd->online); + free_cpumask_var(rd->span); + kfree(rd); +} + +void rq_attach_root(struct rq *rq, struct root_domain *rd) +{ + struct root_domain *old_rd = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + + if (rq->rd) { + old_rd = rq->rd; + + if (cpumask_test_cpu(rq->cpu, old_rd->online)) + set_rq_offline(rq); + + cpumask_clear_cpu(rq->cpu, old_rd->span); + + /* + * If we dont want to free the old_rd yet then + * set old_rd to NULL to skip the freeing later + * in this function: + */ + if (!atomic_dec_and_test(&old_rd->refcount)) + old_rd = NULL; + } + + atomic_inc(&rd->refcount); + rq->rd = rd; + + cpumask_set_cpu(rq->cpu, rd->span); + if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) + set_rq_online(rq); + + raw_spin_unlock_irqrestore(&rq->lock, flags); + + if (old_rd) + call_rcu_sched(&old_rd->rcu, free_rootdomain); +} + +static int init_rootdomain(struct root_domain *rd) +{ + memset(rd, 0, sizeof(*rd)); + + if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) + goto out; + if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL)) + goto free_span; + if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) + goto free_online; + if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + goto free_dlo_mask; + + init_dl_bw(&rd->dl_bw); + if (cpudl_init(&rd->cpudl) != 0) + goto free_rto_mask; + + if (cpupri_init(&rd->cpupri) != 0) + goto free_cpudl; + return 0; + +free_cpudl: + cpudl_cleanup(&rd->cpudl); +free_rto_mask: + free_cpumask_var(rd->rto_mask); +free_dlo_mask: + free_cpumask_var(rd->dlo_mask); +free_online: + free_cpumask_var(rd->online); +free_span: + free_cpumask_var(rd->span); +out: + return -ENOMEM; +} + +/* + * By default the system creates a single root-domain with all CPUs as + * members (mimicking the global state we have today). + */ +struct root_domain def_root_domain; + +void init_defrootdomain(void) +{ + init_rootdomain(&def_root_domain); + + atomic_set(&def_root_domain.refcount, 1); +} + +static struct root_domain *alloc_rootdomain(void) +{ + struct root_domain *rd; + + rd = kmalloc(sizeof(*rd), GFP_KERNEL); + if (!rd) + return NULL; + + if (init_rootdomain(rd) != 0) { + kfree(rd); + return NULL; + } + + return rd; +} + +static void free_sched_groups(struct sched_group *sg, int free_sgc) +{ + struct sched_group *tmp, *first; + + if (!sg) + return; + + first = sg; + do { + tmp = sg->next; + + if (free_sgc && atomic_dec_and_test(&sg->sgc->ref)) + kfree(sg->sgc); + + kfree(sg); + sg = tmp; + } while (sg != first); +} + +static void destroy_sched_domain(struct sched_domain *sd) +{ + /* + * If its an overlapping domain it has private groups, iterate and + * nuke them all. + */ + if (sd->flags & SD_OVERLAP) { + free_sched_groups(sd->groups, 1); + } else if (atomic_dec_and_test(&sd->groups->ref)) { + kfree(sd->groups->sgc); + kfree(sd->groups); + } + if (sd->shared && atomic_dec_and_test(&sd->shared->ref)) + kfree(sd->shared); + kfree(sd); +} + +static void destroy_sched_domains_rcu(struct rcu_head *rcu) +{ + struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); + + while (sd) { + struct sched_domain *parent = sd->parent; + destroy_sched_domain(sd); + sd = parent; + } +} + +static void destroy_sched_domains(struct sched_domain *sd) +{ + if (sd) + call_rcu(&sd->rcu, destroy_sched_domains_rcu); +} + +/* + * Keep a special pointer to the highest sched_domain that has + * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this + * allows us to avoid some pointer chasing select_idle_sibling(). + * + * Also keep a unique ID per domain (we use the first CPU number in + * the cpumask of the domain), this allows us to quickly tell if + * two CPUs are in the same cache domain, see cpus_share_cache(). + */ +DEFINE_PER_CPU(struct sched_domain *, sd_llc); +DEFINE_PER_CPU(int, sd_llc_size); +DEFINE_PER_CPU(int, sd_llc_id); +DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); +DEFINE_PER_CPU(struct sched_domain *, sd_numa); +DEFINE_PER_CPU(struct sched_domain *, sd_asym); + +static void update_top_cache_domain(int cpu) +{ + struct sched_domain_shared *sds = NULL; + struct sched_domain *sd; + int id = cpu; + int size = 1; + + sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); + if (sd) { + id = cpumask_first(sched_domain_span(sd)); + size = cpumask_weight(sched_domain_span(sd)); + sds = sd->shared; + } + + rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); + per_cpu(sd_llc_size, cpu) = size; + per_cpu(sd_llc_id, cpu) = id; + rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds); + + sd = lowest_flag_domain(cpu, SD_NUMA); + rcu_assign_pointer(per_cpu(sd_numa, cpu), sd); + + sd = highest_flag_domain(cpu, SD_ASYM_PACKING); + rcu_assign_pointer(per_cpu(sd_asym, cpu), sd); +} + +/* + * Attach the domain 'sd' to 'cpu' as its base domain. Callers must + * hold the hotplug lock. + */ +static void +cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_domain *tmp; + + /* Remove the sched domains which do not contribute to scheduling. */ + for (tmp = sd; tmp; ) { + struct sched_domain *parent = tmp->parent; + if (!parent) + break; + + if (sd_parent_degenerate(tmp, parent)) { + tmp->parent = parent->parent; + if (parent->parent) + parent->parent->child = tmp; + /* + * Transfer SD_PREFER_SIBLING down in case of a + * degenerate parent; the spans match for this + * so the property transfers. + */ + if (parent->flags & SD_PREFER_SIBLING) + tmp->flags |= SD_PREFER_SIBLING; + destroy_sched_domain(parent); + } else + tmp = tmp->parent; + } + + if (sd && sd_degenerate(sd)) { + tmp = sd; + sd = sd->parent; + destroy_sched_domain(tmp); + if (sd) + sd->child = NULL; + } + + sched_domain_debug(sd, cpu); + + rq_attach_root(rq, rd); + tmp = rq->sd; + rcu_assign_pointer(rq->sd, sd); + destroy_sched_domains(tmp); + + update_top_cache_domain(cpu); +} + +/* Setup the mask of CPUs configured for isolated domains */ +static int __init isolated_cpu_setup(char *str) +{ + int ret; + + alloc_bootmem_cpumask_var(&cpu_isolated_map); + ret = cpulist_parse(str, cpu_isolated_map); + if (ret) { + pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids); + return 0; + } + return 1; +} +__setup("isolcpus=", isolated_cpu_setup); + +struct s_data { + struct sched_domain ** __percpu sd; + struct root_domain *rd; +}; + +enum s_alloc { + sa_rootdomain, + sa_sd, + sa_sd_storage, + sa_none, +}; + +/* + * Build an iteration mask that can exclude certain CPUs from the upwards + * domain traversal. + * + * Asymmetric node setups can result in situations where the domain tree is of + * unequal depth, make sure to skip domains that already cover the entire + * range. + * + * In that case build_sched_domains() will have terminated the iteration early + * and our sibling sd spans will be empty. Domains should always include the + * CPU they're built on, so check that. + */ +static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) +{ + const struct cpumask *span = sched_domain_span(sd); + struct sd_data *sdd = sd->private; + struct sched_domain *sibling; + int i; + + for_each_cpu(i, span) { + sibling = *per_cpu_ptr(sdd->sd, i); + if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + continue; + + cpumask_set_cpu(i, sched_group_mask(sg)); + } +} + +/* + * Return the canonical balance CPU for this group, this is the first CPU + * of this group that's also in the iteration mask. + */ +int group_balance_cpu(struct sched_group *sg) +{ + return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg)); +} + +static int +build_overlap_sched_groups(struct sched_domain *sd, int cpu) +{ + struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered = sched_domains_tmpmask; + struct sd_data *sdd = sd->private; + struct sched_domain *sibling; + int i; + + cpumask_clear(covered); + + for_each_cpu(i, span) { + struct cpumask *sg_span; + + if (cpumask_test_cpu(i, covered)) + continue; + + sibling = *per_cpu_ptr(sdd->sd, i); + + /* See the comment near build_group_mask(). */ + if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + continue; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(cpu)); + + if (!sg) + goto fail; + + sg_span = sched_group_cpus(sg); + if (sibling->child) + cpumask_copy(sg_span, sched_domain_span(sibling->child)); + else + cpumask_set_cpu(i, sg_span); + + cpumask_or(covered, covered, sg_span); + + sg->sgc = *per_cpu_ptr(sdd->sgc, i); + if (atomic_inc_return(&sg->sgc->ref) == 1) + build_group_mask(sd, sg); + + /* + * Initialize sgc->capacity such that even if we mess up the + * domains and no possible iteration will get us here, we won't + * die on a /0 trap. + */ + sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); + sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; + + /* + * Make sure the first group of this domain contains the + * canonical balance CPU. Otherwise the sched_domain iteration + * breaks. See update_sg_lb_stats(). + */ + if ((!groups && cpumask_test_cpu(cpu, sg_span)) || + group_balance_cpu(sg) == cpu) + groups = sg; + + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + last->next = first; + } + sd->groups = groups; + + return 0; + +fail: + free_sched_groups(first, 0); + + return -ENOMEM; +} + +static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) +{ + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); + struct sched_domain *child = sd->child; + + if (child) + cpu = cpumask_first(sched_domain_span(child)); + + if (sg) { + *sg = *per_cpu_ptr(sdd->sg, cpu); + (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); + + /* For claim_allocations: */ + atomic_set(&(*sg)->sgc->ref, 1); + } + + return cpu; +} + +/* + * build_sched_groups will build a circular linked list of the groups + * covered by the given span, and will set each group's ->cpumask correctly, + * and ->cpu_capacity to 0. + * + * Assumes the sched_domain tree is fully constructed + */ +static int +build_sched_groups(struct sched_domain *sd, int cpu) +{ + struct sched_group *first = NULL, *last = NULL; + struct sd_data *sdd = sd->private; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered; + int i; + + get_group(cpu, sdd, &sd->groups); + atomic_inc(&sd->groups->ref); + + if (cpu != cpumask_first(span)) + return 0; + + lockdep_assert_held(&sched_domains_mutex); + covered = sched_domains_tmpmask; + + cpumask_clear(covered); + + for_each_cpu(i, span) { + struct sched_group *sg; + int group, j; + + if (cpumask_test_cpu(i, covered)) + continue; + + group = get_group(i, sdd, &sg); + cpumask_setall(sched_group_mask(sg)); + + for_each_cpu(j, span) { + if (get_group(j, sdd, NULL) != group) + continue; + + cpumask_set_cpu(j, covered); + cpumask_set_cpu(j, sched_group_cpus(sg)); + } + + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + } + last->next = first; + + return 0; +} + +/* + * Initialize sched groups cpu_capacity. + * + * cpu_capacity indicates the capacity of sched group, which is used while + * distributing the load between different sched groups in a sched domain. + * Typically cpu_capacity for all the groups in a sched domain will be same + * unless there are asymmetries in the topology. If there are asymmetries, + * group having more cpu_capacity will pickup more load compared to the + * group having less cpu_capacity. + */ +static void init_sched_groups_capacity(int cpu, struct sched_domain *sd) +{ + struct sched_group *sg = sd->groups; + + WARN_ON(!sg); + + do { + int cpu, max_cpu = -1; + + sg->group_weight = cpumask_weight(sched_group_cpus(sg)); + + if (!(sd->flags & SD_ASYM_PACKING)) + goto next; + + for_each_cpu(cpu, sched_group_cpus(sg)) { + if (max_cpu < 0) + max_cpu = cpu; + else if (sched_asym_prefer(cpu, max_cpu)) + max_cpu = cpu; + } + sg->asym_prefer_cpu = max_cpu; + +next: + sg = sg->next; + } while (sg != sd->groups); + + if (cpu != group_balance_cpu(sg)) + return; + + update_group_capacity(sd, cpu); +} + +/* + * Initializers for schedule domains + * Non-inlined to reduce accumulated stack pressure in build_sched_domains() + */ + +static int default_relax_domain_level = -1; +int sched_domain_level_max; + +static int __init setup_relax_domain_level(char *str) +{ + if (kstrtoint(str, 0, &default_relax_domain_level)) + pr_warn("Unable to set relax_domain_level\n"); + + return 1; +} +__setup("relax_domain_level=", setup_relax_domain_level); + +static void set_domain_attribute(struct sched_domain *sd, + struct sched_domain_attr *attr) +{ + int request; + + if (!attr || attr->relax_domain_level < 0) { + if (default_relax_domain_level < 0) + return; + else + request = default_relax_domain_level; + } else + request = attr->relax_domain_level; + if (request < sd->level) { + /* Turn off idle balance on this domain: */ + sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } else { + /* Turn on idle balance on this domain: */ + sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } +} + +static void __sdt_free(const struct cpumask *cpu_map); +static int __sdt_alloc(const struct cpumask *cpu_map); + +static void __free_domain_allocs(struct s_data *d, enum s_alloc what, + const struct cpumask *cpu_map) +{ + switch (what) { + case sa_rootdomain: + if (!atomic_read(&d->rd->refcount)) + free_rootdomain(&d->rd->rcu); + /* Fall through */ + case sa_sd: + free_percpu(d->sd); + /* Fall through */ + case sa_sd_storage: + __sdt_free(cpu_map); + /* Fall through */ + case sa_none: + break; + } +} + +static enum s_alloc +__visit_domain_allocation_hell(struct s_data *d, const struct cpumask *cpu_map) +{ + memset(d, 0, sizeof(*d)); + + if (__sdt_alloc(cpu_map)) + return sa_sd_storage; + d->sd = alloc_percpu(struct sched_domain *); + if (!d->sd) + return sa_sd_storage; + d->rd = alloc_rootdomain(); + if (!d->rd) + return sa_sd; + return sa_rootdomain; +} + +/* + * NULL the sd_data elements we've used to build the sched_domain and + * sched_group structure so that the subsequent __free_domain_allocs() + * will not free the data we're using. + */ +static void claim_allocations(int cpu, struct sched_domain *sd) +{ + struct sd_data *sdd = sd->private; + + WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); + *per_cpu_ptr(sdd->sd, cpu) = NULL; + + if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref)) + *per_cpu_ptr(sdd->sds, cpu) = NULL; + + if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) + *per_cpu_ptr(sdd->sg, cpu) = NULL; + + if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref)) + *per_cpu_ptr(sdd->sgc, cpu) = NULL; +} + +#ifdef CONFIG_NUMA +static int sched_domains_numa_levels; +enum numa_topology_type sched_numa_topology_type; +static int *sched_domains_numa_distance; +int sched_max_numa_distance; +static struct cpumask ***sched_domains_numa_masks; +static int sched_domains_curr_level; +#endif + +/* + * SD_flags allowed in topology descriptions. + * + * These flags are purely descriptive of the topology and do not prescribe + * behaviour. Behaviour is artificial and mapped in the below sd_init() + * function: + * + * SD_SHARE_CPUCAPACITY - describes SMT topologies + * SD_SHARE_PKG_RESOURCES - describes shared caches + * SD_NUMA - describes NUMA topologies + * SD_SHARE_POWERDOMAIN - describes shared power domain + * SD_ASYM_CPUCAPACITY - describes mixed capacity topologies + * + * Odd one out, which beside describing the topology has a quirk also + * prescribes the desired behaviour that goes along with it: + * + * SD_ASYM_PACKING - describes SMT quirks + */ +#define TOPOLOGY_SD_FLAGS \ + (SD_SHARE_CPUCAPACITY | \ + SD_SHARE_PKG_RESOURCES | \ + SD_NUMA | \ + SD_ASYM_PACKING | \ + SD_ASYM_CPUCAPACITY | \ + SD_SHARE_POWERDOMAIN) + +static struct sched_domain * +sd_init(struct sched_domain_topology_level *tl, + const struct cpumask *cpu_map, + struct sched_domain *child, int cpu) +{ + struct sd_data *sdd = &tl->data; + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); + int sd_id, sd_weight, sd_flags = 0; + +#ifdef CONFIG_NUMA + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; +#endif + + sd_weight = cpumask_weight(tl->mask(cpu)); + + if (tl->sd_flags) + sd_flags = (*tl->sd_flags)(); + if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, + "wrong sd_flags in topology description\n")) + sd_flags &= ~TOPOLOGY_SD_FLAGS; + + *sd = (struct sched_domain){ + .min_interval = sd_weight, + .max_interval = 2*sd_weight, + .busy_factor = 32, + .imbalance_pct = 125, + + .cache_nice_tries = 0, + .busy_idx = 0, + .idle_idx = 0, + .newidle_idx = 0, + .wake_idx = 0, + .forkexec_idx = 0, + + .flags = 1*SD_LOAD_BALANCE + | 1*SD_BALANCE_NEWIDLE + | 1*SD_BALANCE_EXEC + | 1*SD_BALANCE_FORK + | 0*SD_BALANCE_WAKE + | 1*SD_WAKE_AFFINE + | 0*SD_SHARE_CPUCAPACITY + | 0*SD_SHARE_PKG_RESOURCES + | 0*SD_SERIALIZE + | 0*SD_PREFER_SIBLING + | 0*SD_NUMA + | sd_flags + , + + .last_balance = jiffies, + .balance_interval = sd_weight, + .smt_gain = 0, + .max_newidle_lb_cost = 0, + .next_decay_max_lb_cost = jiffies, + .child = child, +#ifdef CONFIG_SCHED_DEBUG + .name = tl->name, +#endif + }; + + cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); + sd_id = cpumask_first(sched_domain_span(sd)); + + /* + * Convert topological properties into behaviour. + */ + + if (sd->flags & SD_ASYM_CPUCAPACITY) { + struct sched_domain *t = sd; + + for_each_lower_domain(t) + t->flags |= SD_BALANCE_WAKE; + } + + if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->flags |= SD_PREFER_SIBLING; + sd->imbalance_pct = 110; + sd->smt_gain = 1178; /* ~15% */ + + } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->imbalance_pct = 117; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + +#ifdef CONFIG_NUMA + } else if (sd->flags & SD_NUMA) { + sd->cache_nice_tries = 2; + sd->busy_idx = 3; + sd->idle_idx = 2; + + sd->flags |= SD_SERIALIZE; + if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + sd->flags &= ~(SD_BALANCE_EXEC | + SD_BALANCE_FORK | + SD_WAKE_AFFINE); + } + +#endif + } else { + sd->flags |= SD_PREFER_SIBLING; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + sd->idle_idx = 1; + } + + /* + * For all levels sharing cache; connect a sched_domain_shared + * instance. + */ + if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->shared = *per_cpu_ptr(sdd->sds, sd_id); + atomic_inc(&sd->shared->ref); + atomic_set(&sd->shared->nr_busy_cpus, sd_weight); + } + + sd->private = sdd; + + return sd; +} + +/* + * Topology list, bottom-up. + */ +static struct sched_domain_topology_level default_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + +static struct sched_domain_topology_level *sched_domain_topology = + default_topology; + +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->mask; tl++) + +void set_sched_topology(struct sched_domain_topology_level *tl) +{ + if (WARN_ON_ONCE(sched_smp_initialized)) + return; + + sched_domain_topology = tl; +} + +#ifdef CONFIG_NUMA + +static const struct cpumask *sd_numa_mask(int cpu) +{ + return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; +} + +static void sched_numa_warn(const char *str) +{ + static int done = false; + int i,j; + + if (done) + return; + + done = true; + + printk(KERN_WARNING "ERROR: %s\n\n", str); + + for (i = 0; i < nr_node_ids; i++) { + printk(KERN_WARNING " "); + for (j = 0; j < nr_node_ids; j++) + printk(KERN_CONT "%02d ", node_distance(i,j)); + printk(KERN_CONT "\n"); + } + printk(KERN_WARNING "\n"); +} + +bool find_numa_distance(int distance) +{ + int i; + + if (distance == node_distance(0, 0)) + return true; + + for (i = 0; i < sched_domains_numa_levels; i++) { + if (sched_domains_numa_distance[i] == distance) + return true; + } + + return false; +} + +/* + * A system can have three types of NUMA topology: + * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system + * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes + * NUMA_BACKPLANE: nodes can reach other nodes through a backplane + * + * The difference between a glueless mesh topology and a backplane + * topology lies in whether communication between not directly + * connected nodes goes through intermediary nodes (where programs + * could run), or through backplane controllers. This affects + * placement of programs. + * + * The type of topology can be discerned with the following tests: + * - If the maximum distance between any nodes is 1 hop, the system + * is directly connected. + * - If for two nodes A and B, located N > 1 hops away from each other, + * there is an intermediary node C, which is < N hops away from both + * nodes A and B, the system is a glueless mesh. + */ +static void init_numa_topology_type(void) +{ + int a, b, c, n; + + n = sched_max_numa_distance; + + if (sched_domains_numa_levels <= 1) { + sched_numa_topology_type = NUMA_DIRECT; + return; + } + + for_each_online_node(a) { + for_each_online_node(b) { + /* Find two nodes furthest removed from each other. */ + if (node_distance(a, b) < n) + continue; + + /* Is there an intermediary node between a and b? */ + for_each_online_node(c) { + if (node_distance(a, c) < n && + node_distance(b, c) < n) { + sched_numa_topology_type = + NUMA_GLUELESS_MESH; + return; + } + } + + sched_numa_topology_type = NUMA_BACKPLANE; + return; + } + } +} + +void sched_init_numa(void) +{ + int next_distance, curr_distance = node_distance(0, 0); + struct sched_domain_topology_level *tl; + int level = 0; + int i, j, k; + + sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + if (!sched_domains_numa_distance) + return; + + /* + * O(nr_nodes^2) deduplicating selection sort -- in order to find the + * unique distances in the node_distance() table. + * + * Assumes node_distance(0,j) includes all distances in + * node_distance(i,j) in order to avoid cubic time. + */ + next_distance = curr_distance; + for (i = 0; i < nr_node_ids; i++) { + for (j = 0; j < nr_node_ids; j++) { + for (k = 0; k < nr_node_ids; k++) { + int distance = node_distance(i, k); + + if (distance > curr_distance && + (distance < next_distance || + next_distance == curr_distance)) + next_distance = distance; + + /* + * While not a strong assumption it would be nice to know + * about cases where if node A is connected to B, B is not + * equally connected to A. + */ + if (sched_debug() && node_distance(k, i) != distance) + sched_numa_warn("Node-distance not symmetric"); + + if (sched_debug() && i && !find_numa_distance(distance)) + sched_numa_warn("Node-0 not representative"); + } + if (next_distance != curr_distance) { + sched_domains_numa_distance[level++] = next_distance; + sched_domains_numa_levels = level; + curr_distance = next_distance; + } else break; + } + + /* + * In case of sched_debug() we verify the above assumption. + */ + if (!sched_debug()) + break; + } + + if (!level) + return; + + /* + * 'level' contains the number of unique distances, excluding the + * identity distance node_distance(i,i). + * + * The sched_domains_numa_distance[] array includes the actual distance + * numbers. + */ + + /* + * Here, we should temporarily reset sched_domains_numa_levels to 0. + * If it fails to allocate memory for array sched_domains_numa_masks[][], + * the array will contain less then 'level' members. This could be + * dangerous when we use it to iterate array sched_domains_numa_masks[][] + * in other functions. + * + * We reset it to 'level' at the end of this function. + */ + sched_domains_numa_levels = 0; + + sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + if (!sched_domains_numa_masks) + return; + + /* + * Now for each level, construct a mask per node which contains all + * CPUs of nodes that are that many hops away from us. + */ + for (i = 0; i < level; i++) { + sched_domains_numa_masks[i] = + kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); + if (!sched_domains_numa_masks[i]) + return; + + for (j = 0; j < nr_node_ids; j++) { + struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!mask) + return; + + sched_domains_numa_masks[i][j] = mask; + + for_each_node(k) { + if (node_distance(j, k) > sched_domains_numa_distance[i]) + continue; + + cpumask_or(mask, mask, cpumask_of_node(k)); + } + } + } + + /* Compute default topology size */ + for (i = 0; sched_domain_topology[i].mask; i++); + + tl = kzalloc((i + level + 1) * + sizeof(struct sched_domain_topology_level), GFP_KERNEL); + if (!tl) + return; + + /* + * Copy the default topology bits.. + */ + for (i = 0; sched_domain_topology[i].mask; i++) + tl[i] = sched_domain_topology[i]; + + /* + * .. and append 'j' levels of NUMA goodness. + */ + for (j = 0; j < level; i++, j++) { + tl[i] = (struct sched_domain_topology_level){ + .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, + .flags = SDTL_OVERLAP, + .numa_level = j, + SD_INIT_NAME(NUMA) + }; + } + + sched_domain_topology = tl; + + sched_domains_numa_levels = level; + sched_max_numa_distance = sched_domains_numa_distance[level - 1]; + + init_numa_topology_type(); +} + +void sched_domains_numa_masks_set(unsigned int cpu) +{ + int node = cpu_to_node(cpu); + int i, j; + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) { + if (node_distance(j, node) <= sched_domains_numa_distance[i]) + cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); + } + } +} + +void sched_domains_numa_masks_clear(unsigned int cpu) +{ + int i, j; + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) + cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); + } +} + +#endif /* CONFIG_NUMA */ + +static int __sdt_alloc(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + sdd->sd = alloc_percpu(struct sched_domain *); + if (!sdd->sd) + return -ENOMEM; + + sdd->sds = alloc_percpu(struct sched_domain_shared *); + if (!sdd->sds) + return -ENOMEM; + + sdd->sg = alloc_percpu(struct sched_group *); + if (!sdd->sg) + return -ENOMEM; + + sdd->sgc = alloc_percpu(struct sched_group_capacity *); + if (!sdd->sgc) + return -ENOMEM; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + struct sched_domain_shared *sds; + struct sched_group *sg; + struct sched_group_capacity *sgc; + + sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sd) + return -ENOMEM; + + *per_cpu_ptr(sdd->sd, j) = sd; + + sds = kzalloc_node(sizeof(struct sched_domain_shared), + GFP_KERNEL, cpu_to_node(j)); + if (!sds) + return -ENOMEM; + + *per_cpu_ptr(sdd->sds, j) = sds; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sg) + return -ENOMEM; + + sg->next = sg; + + *per_cpu_ptr(sdd->sg, j) = sg; + + sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sgc) + return -ENOMEM; + + *per_cpu_ptr(sdd->sgc, j) = sgc; + } + } + + return 0; +} + +static void __sdt_free(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + + if (sdd->sd) { + sd = *per_cpu_ptr(sdd->sd, j); + if (sd && (sd->flags & SD_OVERLAP)) + free_sched_groups(sd->groups, 0); + kfree(*per_cpu_ptr(sdd->sd, j)); + } + + if (sdd->sds) + kfree(*per_cpu_ptr(sdd->sds, j)); + if (sdd->sg) + kfree(*per_cpu_ptr(sdd->sg, j)); + if (sdd->sgc) + kfree(*per_cpu_ptr(sdd->sgc, j)); + } + free_percpu(sdd->sd); + sdd->sd = NULL; + free_percpu(sdd->sds); + sdd->sds = NULL; + free_percpu(sdd->sg); + sdd->sg = NULL; + free_percpu(sdd->sgc); + sdd->sgc = NULL; + } +} + +struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *child, int cpu) +{ + struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu); + + if (child) { + sd->level = child->level + 1; + sched_domain_level_max = max(sched_domain_level_max, sd->level); + child->parent = sd; + + if (!cpumask_subset(sched_domain_span(child), + sched_domain_span(sd))) { + pr_err("BUG: arch topology borken\n"); +#ifdef CONFIG_SCHED_DEBUG + pr_err(" the %s domain not a subset of the %s domain\n", + child->name, sd->name); +#endif + /* Fixup, ensure @sd has at least @child cpus. */ + cpumask_or(sched_domain_span(sd), + sched_domain_span(sd), + sched_domain_span(child)); + } + + } + set_domain_attribute(sd, attr); + + return sd; +} + +/* + * Build sched domains for a given set of CPUs and attach the sched domains + * to the individual CPUs + */ +static int +build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr) +{ + enum s_alloc alloc_state; + struct sched_domain *sd; + struct s_data d; + struct rq *rq = NULL; + int i, ret = -ENOMEM; + + alloc_state = __visit_domain_allocation_hell(&d, cpu_map); + if (alloc_state != sa_rootdomain) + goto error; + + /* Set up domains for CPUs specified by the cpu_map: */ + for_each_cpu(i, cpu_map) { + struct sched_domain_topology_level *tl; + + sd = NULL; + for_each_sd_topology(tl) { + sd = build_sched_domain(tl, cpu_map, attr, sd, i); + if (tl == sched_domain_topology) + *per_cpu_ptr(d.sd, i) = sd; + if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) + sd->flags |= SD_OVERLAP; + if (cpumask_equal(cpu_map, sched_domain_span(sd))) + break; + } + } + + /* Build the groups for the domains */ + for_each_cpu(i, cpu_map) { + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + sd->span_weight = cpumask_weight(sched_domain_span(sd)); + if (sd->flags & SD_OVERLAP) { + if (build_overlap_sched_groups(sd, i)) + goto error; + } else { + if (build_sched_groups(sd, i)) + goto error; + } + } + } + + /* Calculate CPU capacity for physical packages and nodes */ + for (i = nr_cpumask_bits-1; i >= 0; i--) { + if (!cpumask_test_cpu(i, cpu_map)) + continue; + + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + claim_allocations(i, sd); + init_sched_groups_capacity(i, sd); + } + } + + /* Attach the domains */ + rcu_read_lock(); + for_each_cpu(i, cpu_map) { + rq = cpu_rq(i); + sd = *per_cpu_ptr(d.sd, i); + + /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */ + if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity)) + WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig); + + cpu_attach_domain(sd, d.rd, i); + } + rcu_read_unlock(); + + if (rq && sched_debug_enabled) { + pr_info("span: %*pbl (max cpu_capacity = %lu)\n", + cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity); + } + + ret = 0; +error: + __free_domain_allocs(&d, alloc_state, cpu_map); + return ret; +} + +/* Current sched domains: */ +static cpumask_var_t *doms_cur; + +/* Number of sched domains in 'doms_cur': */ +static int ndoms_cur; + +/* Attribues of custom domains in 'doms_cur' */ +static struct sched_domain_attr *dattr_cur; + +/* + * Special case: If a kmalloc() of a doms_cur partition (array of + * cpumask) fails, then fallback to a single sched domain, + * as determined by the single cpumask fallback_doms. + */ +cpumask_var_t fallback_doms; + +/* + * arch_update_cpu_topology lets virtualized architectures update the + * CPU core maps. It is supposed to return 1 if the topology changed + * or 0 if it stayed the same. + */ +int __weak arch_update_cpu_topology(void) +{ + return 0; +} + +cpumask_var_t *alloc_sched_domains(unsigned int ndoms) +{ + int i; + cpumask_var_t *doms; + + doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); + if (!doms) + return NULL; + for (i = 0; i < ndoms; i++) { + if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { + free_sched_domains(doms, i); + return NULL; + } + } + return doms; +} + +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) +{ + unsigned int i; + for (i = 0; i < ndoms; i++) + free_cpumask_var(doms[i]); + kfree(doms); +} + +/* + * Set up scheduler domains and groups. Callers must hold the hotplug lock. + * For now this just excludes isolated CPUs, but could be used to + * exclude other special cases in the future. + */ +int init_sched_domains(const struct cpumask *cpu_map) +{ + int err; + + arch_update_cpu_topology(); + ndoms_cur = 1; + doms_cur = alloc_sched_domains(ndoms_cur); + if (!doms_cur) + doms_cur = &fallback_doms; + cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); + err = build_sched_domains(doms_cur[0], NULL); + register_sched_domain_sysctl(); + + return err; +} + +/* + * Detach sched domains from a group of CPUs specified in cpu_map + * These CPUs will now be attached to the NULL domain + */ +static void detach_destroy_domains(const struct cpumask *cpu_map) +{ + int i; + + rcu_read_lock(); + for_each_cpu(i, cpu_map) + cpu_attach_domain(NULL, &def_root_domain, i); + rcu_read_unlock(); +} + +/* handle null as "default" */ +static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, + struct sched_domain_attr *new, int idx_new) +{ + struct sched_domain_attr tmp; + + /* Fast path: */ + if (!new && !cur) + return 1; + + tmp = SD_ATTR_INIT; + return !memcmp(cur ? (cur + idx_cur) : &tmp, + new ? (new + idx_new) : &tmp, + sizeof(struct sched_domain_attr)); +} + +/* + * Partition sched domains as specified by the 'ndoms_new' + * cpumasks in the array doms_new[] of cpumasks. This compares + * doms_new[] to the current sched domain partitioning, doms_cur[]. + * It destroys each deleted domain and builds each new domain. + * + * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. + * The masks don't intersect (don't overlap.) We should setup one + * sched domain for each mask. CPUs not in any of the cpumasks will + * not be load balanced. If the same cpumask appears both in the + * current 'doms_cur' domains and in the new 'doms_new', we can leave + * it as it is. + * + * The passed in 'doms_new' should be allocated using + * alloc_sched_domains. This routine takes ownership of it and will + * free_sched_domains it when done with it. If the caller failed the + * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, + * and partition_sched_domains() will fallback to the single partition + * 'fallback_doms', it also forces the domains to be rebuilt. + * + * If doms_new == NULL it will be replaced with cpu_online_mask. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. + * + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + int i, j, n; + int new_topology; + + mutex_lock(&sched_domains_mutex); + + /* Always unregister in case we don't destroy any domains: */ + unregister_sched_domain_sysctl(); + + /* Let the architecture update CPU core mappings: */ + new_topology = arch_update_cpu_topology(); + + n = doms_new ? ndoms_new : 0; + + /* Destroy deleted domains: */ + for (i = 0; i < ndoms_cur; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(doms_cur[i], doms_new[j]) + && dattrs_equal(dattr_cur, i, dattr_new, j)) + goto match1; + } + /* No match - a current sched domain not in new doms_new[] */ + detach_destroy_domains(doms_cur[i]); +match1: + ; + } + + n = ndoms_cur; + if (doms_new == NULL) { + n = 0; + doms_new = &fallback_doms; + cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); + WARN_ON_ONCE(dattr_new); + } + + /* Build new domains: */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(doms_new[i], doms_cur[j]) + && dattrs_equal(dattr_new, i, dattr_cur, j)) + goto match2; + } + /* No match - add a new doms_new */ + build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); +match2: + ; + } + + /* Remember the new sched domains: */ + if (doms_cur != &fallback_doms) + free_sched_domains(doms_cur, ndoms_cur); + + kfree(dattr_cur); + doms_cur = doms_new; + dattr_cur = dattr_new; + ndoms_cur = ndoms_new; + + register_sched_domain_sysctl(); + + mutex_unlock(&sched_domains_mutex); +} + diff --git a/kernel/signal.c b/kernel/signal.c index 3603d93a1968..13f9def8b24a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1581,7 +1581,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig) unsigned long flags; struct sighand_struct *psig; bool autoreap = false; - cputime_t utime, stime; + u64 utime, stime; BUG_ON(sig == -1); @@ -1620,8 +1620,8 @@ bool do_notify_parent(struct task_struct *tsk, int sig) rcu_read_unlock(); task_cputime(tsk, &utime, &stime); - info.si_utime = cputime_to_clock_t(utime + tsk->signal->utime); - info.si_stime = cputime_to_clock_t(stime + tsk->signal->stime); + info.si_utime = nsec_to_clock_t(utime + tsk->signal->utime); + info.si_stime = nsec_to_clock_t(stime + tsk->signal->stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) @@ -1685,7 +1685,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, unsigned long flags; struct task_struct *parent; struct sighand_struct *sighand; - cputime_t utime, stime; + u64 utime, stime; if (for_ptracer) { parent = tsk->parent; @@ -1705,8 +1705,8 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, rcu_read_unlock(); task_cputime(tsk, &utime, &stime); - info.si_utime = cputime_to_clock_t(utime); - info.si_stime = cputime_to_clock_t(stime); + info.si_utime = nsec_to_clock_t(utime); + info.si_stime = nsec_to_clock_t(stime); info.si_code = why; switch (why) { diff --git a/kernel/sys.c b/kernel/sys.c index 842914ef7de4..7d4a9a6df956 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -881,15 +881,15 @@ SYSCALL_DEFINE0(getegid) void do_sys_times(struct tms *tms) { - cputime_t tgutime, tgstime, cutime, cstime; + u64 tgutime, tgstime, cutime, cstime; thread_group_cputime_adjusted(current, &tgutime, &tgstime); cutime = current->signal->cutime; cstime = current->signal->cstime; - tms->tms_utime = cputime_to_clock_t(tgutime); - tms->tms_stime = cputime_to_clock_t(tgstime); - tms->tms_cutime = cputime_to_clock_t(cutime); - tms->tms_cstime = cputime_to_clock_t(cstime); + tms->tms_utime = nsec_to_clock_t(tgutime); + tms->tms_stime = nsec_to_clock_t(tgstime); + tms->tms_cutime = nsec_to_clock_t(cutime); + tms->tms_cstime = nsec_to_clock_t(cstime); } SYSCALL_DEFINE1(times, struct tms __user *, tbuf) @@ -1544,7 +1544,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; - cputime_t tgutime, tgstime, utime, stime; + u64 tgutime, tgstime, utime, stime; unsigned long maxrss = 0; memset((char *)r, 0, sizeof (*r)); @@ -1600,8 +1600,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) unlock_task_sighand(p, &flags); out: - cputime_to_timeval(utime, &r->ru_utime); - cputime_to_timeval(stime, &r->ru_stime); + r->ru_utime = ns_to_timeval(utime); + r->ru_stime = ns_to_timeval(stime); if (who != RUSAGE_CHILDREN) { struct mm_struct *mm = get_task_mm(p); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 1aea594a54db..bb260ceb3718 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -416,7 +416,7 @@ static struct ctl_table kern_table[] = { }, { .procname = "sched_rr_timeslice_ms", - .data = &sched_rr_timeslice, + .data = &sysctl_sched_rr_timeslice, .maxlen = sizeof(int), .mode = 0644, .proc_handler = sched_rr_handler, diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 976840d29a71..938dbf33ef49 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -15,6 +15,5 @@ ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y) endif obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o -obj-$(CONFIG_TIMER_STATS) += timer_stats.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o obj-$(CONFIG_TEST_UDELAY) += test_udelay.o diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 665985b0a89a..93621ae718d3 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -141,6 +141,10 @@ static void __clocksource_unstable(struct clocksource *cs) { cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); cs->flags |= CLOCK_SOURCE_UNSTABLE; + + if (cs->mark_unstable) + cs->mark_unstable(cs); + if (finished_booting) schedule_work(&watchdog_work); } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index c6ecedd3b839..8e11d8d9f419 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -94,17 +94,15 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = }; static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { + /* Make sure we catch unsupported clockids */ + [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES, + [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; -static inline int hrtimer_clockid_to_base(clockid_t clock_id) -{ - return hrtimer_clock_to_base_table[clock_id]; -} - /* * Functions and macros which are different for UP/SMP systems are kept in a * single place @@ -766,34 +764,6 @@ void hrtimers_resume(void) clock_was_set_delayed(); } -static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) -{ -#ifdef CONFIG_TIMER_STATS - if (timer->start_site) - return; - timer->start_site = __builtin_return_address(0); - memcpy(timer->start_comm, current->comm, TASK_COMM_LEN); - timer->start_pid = current->pid; -#endif -} - -static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer) -{ -#ifdef CONFIG_TIMER_STATS - timer->start_site = NULL; -#endif -} - -static inline void timer_stats_account_hrtimer(struct hrtimer *timer) -{ -#ifdef CONFIG_TIMER_STATS - if (likely(!timer_stats_active)) - return; - timer_stats_update_stats(timer, timer->start_pid, timer->start_site, - timer->function, timer->start_comm, 0); -#endif -} - /* * Counterpart to lock_hrtimer_base above: */ @@ -932,7 +902,6 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool rest * rare case and less expensive than a smp call. */ debug_deactivate(timer); - timer_stats_hrtimer_clear_start_info(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); if (!restart) @@ -990,8 +959,6 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, /* Switch the timer base, if necessary: */ new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); - timer_stats_hrtimer_set_start_info(timer); - leftmost = enqueue_hrtimer(timer, new_base); if (!leftmost) goto unlock; @@ -1112,6 +1079,18 @@ u64 hrtimer_get_next_event(void) } #endif +static inline int hrtimer_clockid_to_base(clockid_t clock_id) +{ + if (likely(clock_id < MAX_CLOCKS)) { + int base = hrtimer_clock_to_base_table[clock_id]; + + if (likely(base != HRTIMER_MAX_CLOCK_BASES)) + return base; + } + WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); + return HRTIMER_BASE_MONOTONIC; +} + static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { @@ -1128,12 +1107,6 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, base = hrtimer_clockid_to_base(clock_id); timer->base = &cpu_base->clock_base[base]; timerqueue_init(&timer->node); - -#ifdef CONFIG_TIMER_STATS - timer->start_site = NULL; - timer->start_pid = -1; - memset(timer->start_comm, 0, TASK_COMM_LEN); -#endif } /** @@ -1217,7 +1190,6 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, raw_write_seqcount_barrier(&cpu_base->seq); __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); - timer_stats_account_hrtimer(timer); fn = timer->function; /* diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 8c89143f9ebf..a95f13c31464 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -45,16 +45,16 @@ static struct timeval itimer_get_remtime(struct hrtimer *timer) static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, struct itimerval *const value) { - cputime_t cval, cinterval; + u64 val, interval; struct cpu_itimer *it = &tsk->signal->it[clock_id]; spin_lock_irq(&tsk->sighand->siglock); - cval = it->expires; - cinterval = it->incr; - if (cval) { + val = it->expires; + interval = it->incr; + if (val) { struct task_cputime cputime; - cputime_t t; + u64 t; thread_group_cputimer(tsk, &cputime); if (clock_id == CPUCLOCK_PROF) @@ -63,17 +63,17 @@ static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, /* CPUCLOCK_VIRT */ t = cputime.utime; - if (cval < t) + if (val < t) /* about to fire */ - cval = cputime_one_jiffy; + val = TICK_NSEC; else - cval = cval - t; + val -= t; } spin_unlock_irq(&tsk->sighand->siglock); - cputime_to_timeval(cval, &value->it_value); - cputime_to_timeval(cinterval, &value->it_interval); + value->it_value = ns_to_timeval(val); + value->it_interval = ns_to_timeval(interval); } int do_getitimer(int which, struct itimerval *value) @@ -129,55 +129,35 @@ enum hrtimer_restart it_real_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } -static inline u32 cputime_sub_ns(cputime_t ct, s64 real_ns) -{ - struct timespec ts; - s64 cpu_ns; - - cputime_to_timespec(ct, &ts); - cpu_ns = timespec_to_ns(&ts); - - return (cpu_ns <= real_ns) ? 0 : cpu_ns - real_ns; -} - static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, const struct itimerval *const value, struct itimerval *const ovalue) { - cputime_t cval, nval, cinterval, ninterval; - s64 ns_ninterval, ns_nval; - u32 error, incr_error; + u64 oval, nval, ointerval, ninterval; struct cpu_itimer *it = &tsk->signal->it[clock_id]; - nval = timeval_to_cputime(&value->it_value); - ns_nval = timeval_to_ns(&value->it_value); - ninterval = timeval_to_cputime(&value->it_interval); - ns_ninterval = timeval_to_ns(&value->it_interval); - - error = cputime_sub_ns(nval, ns_nval); - incr_error = cputime_sub_ns(ninterval, ns_ninterval); + nval = timeval_to_ns(&value->it_value); + ninterval = timeval_to_ns(&value->it_interval); spin_lock_irq(&tsk->sighand->siglock); - cval = it->expires; - cinterval = it->incr; - if (cval || nval) { + oval = it->expires; + ointerval = it->incr; + if (oval || nval) { if (nval > 0) - nval += cputime_one_jiffy; - set_process_cpu_timer(tsk, clock_id, &nval, &cval); + nval += TICK_NSEC; + set_process_cpu_timer(tsk, clock_id, &nval, &oval); } it->expires = nval; it->incr = ninterval; - it->error = error; - it->incr_error = incr_error; trace_itimer_state(clock_id == CPUCLOCK_VIRT ? ITIMER_VIRTUAL : ITIMER_PROF, value, nval); spin_unlock_irq(&tsk->sighand->siglock); if (ovalue) { - cputime_to_timeval(cval, &ovalue->it_value); - cputime_to_timeval(cinterval, &ovalue->it_interval); + ovalue->it_value = ns_to_timeval(oval); + ovalue->it_interval = ns_to_timeval(ointerval); } } diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a4a0e478e44d..7906b3f0c41a 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -27,19 +27,8 @@ #include "timekeeping.h" -/* The Jiffies based clocksource is the lowest common - * denominator clock source which should function on - * all systems. It has the same coarse resolution as - * the timer interrupt frequency HZ and it suffers - * inaccuracies caused by missed or lost timer - * interrupts and the inability for the timer - * interrupt hardware to accuratly tick at the - * requested HZ value. It is also not recommended - * for "tick-less" systems. - */ -#define NSEC_PER_JIFFY ((NSEC_PER_SEC+HZ/2)/HZ) -/* Since jiffies uses a simple NSEC_PER_JIFFY multiplier +/* Since jiffies uses a simple TICK_NSEC multiplier * conversion, the .shift value could be zero. However * this would make NTP adjustments impossible as they are * in units of 1/2^.shift. Thus we use JIFFIES_SHIFT to @@ -47,8 +36,8 @@ * amount, and give ntp adjustments in units of 1/2^8 * * The value 8 is somewhat carefully chosen, as anything - * larger can result in overflows. NSEC_PER_JIFFY grows as - * HZ shrinks, so values greater than 8 overflow 32bits when + * larger can result in overflows. TICK_NSEC grows as HZ + * shrinks, so values greater than 8 overflow 32bits when * HZ=100. */ #if HZ < 34 @@ -64,12 +53,23 @@ static u64 jiffies_read(struct clocksource *cs) return (u64) jiffies; } +/* + * The Jiffies based clocksource is the lowest common + * denominator clock source which should function on + * all systems. It has the same coarse resolution as + * the timer interrupt frequency HZ and it suffers + * inaccuracies caused by missed or lost timer + * interrupts and the inability for the timer + * interrupt hardware to accuratly tick at the + * requested HZ value. It is also not recommended + * for "tick-less" systems. + */ static struct clocksource clocksource_jiffies = { .name = "jiffies", .rating = 1, /* lowest valid rating*/ .read = jiffies_read, .mask = CLOCKSOURCE_MASK(32), - .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ + .mult = TICK_NSEC << JIFFIES_SHIFT, /* details above */ .shift = JIFFIES_SHIFT, .max_cycles = 10, }; @@ -125,7 +125,7 @@ int register_refined_jiffies(long cycles_per_second) shift_hz += cycles_per_tick/2; do_div(shift_hz, cycles_per_tick); /* Calculate nsec_per_tick using shift_hz */ - nsec_per_tick = (u64)NSEC_PER_SEC << 8; + nsec_per_tick = (u64)TICK_NSEC << 8; nsec_per_tick += (u32)shift_hz/2; do_div(nsec_per_tick, (u32)shift_hz); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index e9e8c10f0d9a..b4377a5e4269 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -20,10 +20,10 @@ */ void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new) { - cputime_t cputime = secs_to_cputime(rlim_new); + u64 nsecs = rlim_new * NSEC_PER_SEC; spin_lock_irq(&task->sighand->siglock); - set_process_cpu_timer(task, CPUCLOCK_PROF, &cputime, NULL); + set_process_cpu_timer(task, CPUCLOCK_PROF, &nsecs, NULL); spin_unlock_irq(&task->sighand->siglock); } @@ -50,39 +50,14 @@ static int check_clock(const clockid_t which_clock) return error; } -static inline unsigned long long -timespec_to_sample(const clockid_t which_clock, const struct timespec *tp) -{ - unsigned long long ret; - - ret = 0; /* high half always zero when .cpu used */ - if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - ret = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; - } else { - ret = cputime_to_expires(timespec_to_cputime(tp)); - } - return ret; -} - -static void sample_to_timespec(const clockid_t which_clock, - unsigned long long expires, - struct timespec *tp) -{ - if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) - *tp = ns_to_timespec(expires); - else - cputime_to_timespec((__force cputime_t)expires, tp); -} - /* * Update expiry time from increment, and increase overrun count, * given the current clock sample. */ -static void bump_cpu_timer(struct k_itimer *timer, - unsigned long long now) +static void bump_cpu_timer(struct k_itimer *timer, u64 now) { int i; - unsigned long long delta, incr; + u64 delta, incr; if (timer->it.cpu.incr == 0) return; @@ -122,21 +97,21 @@ static inline int task_cputime_zero(const struct task_cputime *cputime) return 0; } -static inline unsigned long long prof_ticks(struct task_struct *p) +static inline u64 prof_ticks(struct task_struct *p) { - cputime_t utime, stime; + u64 utime, stime; task_cputime(p, &utime, &stime); - return cputime_to_expires(utime + stime); + return utime + stime; } -static inline unsigned long long virt_ticks(struct task_struct *p) +static inline u64 virt_ticks(struct task_struct *p) { - cputime_t utime, stime; + u64 utime, stime; task_cputime(p, &utime, &stime); - return cputime_to_expires(utime); + return utime; } static int @@ -176,8 +151,8 @@ posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp) /* * Sample a per-thread clock for the given task. */ -static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, - unsigned long long *sample) +static int cpu_clock_sample(const clockid_t which_clock, + struct task_struct *p, u64 *sample) { switch (CPUCLOCK_WHICH(which_clock)) { default: @@ -260,7 +235,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) */ static int cpu_clock_sample_group(const clockid_t which_clock, struct task_struct *p, - unsigned long long *sample) + u64 *sample) { struct task_cputime cputime; @@ -269,11 +244,11 @@ static int cpu_clock_sample_group(const clockid_t which_clock, return -EINVAL; case CPUCLOCK_PROF: thread_group_cputime(p, &cputime); - *sample = cputime_to_expires(cputime.utime + cputime.stime); + *sample = cputime.utime + cputime.stime; break; case CPUCLOCK_VIRT: thread_group_cputime(p, &cputime); - *sample = cputime_to_expires(cputime.utime); + *sample = cputime.utime; break; case CPUCLOCK_SCHED: thread_group_cputime(p, &cputime); @@ -288,7 +263,7 @@ static int posix_cpu_clock_get_task(struct task_struct *tsk, struct timespec *tp) { int err = -EINVAL; - unsigned long long rtn; + u64 rtn; if (CPUCLOCK_PERTHREAD(which_clock)) { if (same_thread_group(tsk, current)) @@ -299,7 +274,7 @@ static int posix_cpu_clock_get_task(struct task_struct *tsk, } if (!err) - sample_to_timespec(which_clock, rtn, tp); + *tp = ns_to_timespec(rtn); return err; } @@ -453,7 +428,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk) cleanup_timers(tsk->signal->cpu_timers); } -static inline int expires_gt(cputime_t expires, cputime_t new_exp) +static inline int expires_gt(u64 expires, u64 new_exp) { return expires == 0 || expires > new_exp; } @@ -488,7 +463,7 @@ static void arm_timer(struct k_itimer *timer) list_add(&nt->entry, listpos); if (listpos == head) { - unsigned long long exp = nt->expires; + u64 exp = nt->expires; /* * We are the new earliest-expiring POSIX 1.b timer, hence @@ -499,16 +474,15 @@ static void arm_timer(struct k_itimer *timer) switch (CPUCLOCK_WHICH(timer->it_clock)) { case CPUCLOCK_PROF: - if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp))) - cputime_expires->prof_exp = expires_to_cputime(exp); + if (expires_gt(cputime_expires->prof_exp, exp)) + cputime_expires->prof_exp = exp; break; case CPUCLOCK_VIRT: - if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp))) - cputime_expires->virt_exp = expires_to_cputime(exp); + if (expires_gt(cputime_expires->virt_exp, exp)) + cputime_expires->virt_exp = exp; break; case CPUCLOCK_SCHED: - if (cputime_expires->sched_exp == 0 || - cputime_expires->sched_exp > exp) + if (expires_gt(cputime_expires->sched_exp, exp)) cputime_expires->sched_exp = exp; break; } @@ -559,8 +533,7 @@ static void cpu_timer_fire(struct k_itimer *timer) * traversal. */ static int cpu_timer_sample_group(const clockid_t which_clock, - struct task_struct *p, - unsigned long long *sample) + struct task_struct *p, u64 *sample) { struct task_cputime cputime; @@ -569,10 +542,10 @@ static int cpu_timer_sample_group(const clockid_t which_clock, default: return -EINVAL; case CPUCLOCK_PROF: - *sample = cputime_to_expires(cputime.utime + cputime.stime); + *sample = cputime.utime + cputime.stime; break; case CPUCLOCK_VIRT: - *sample = cputime_to_expires(cputime.utime); + *sample = cputime.utime; break; case CPUCLOCK_SCHED: *sample = cputime.sum_exec_runtime; @@ -593,12 +566,12 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, unsigned long flags; struct sighand_struct *sighand; struct task_struct *p = timer->it.cpu.task; - unsigned long long old_expires, new_expires, old_incr, val; + u64 old_expires, new_expires, old_incr, val; int ret; WARN_ON_ONCE(p == NULL); - new_expires = timespec_to_sample(timer->it_clock, &new->it_value); + new_expires = timespec_to_ns(&new->it_value); /* * Protect against sighand release/switch in exit/exec and p->cpu_timers @@ -659,9 +632,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, bump_cpu_timer(timer, val); if (val < timer->it.cpu.expires) { old_expires = timer->it.cpu.expires - val; - sample_to_timespec(timer->it_clock, - old_expires, - &old->it_value); + old->it_value = ns_to_timespec(old_expires); } else { old->it_value.tv_nsec = 1; old->it_value.tv_sec = 0; @@ -699,8 +670,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, * Install the new reload setting, and * set up the signal and overrun bookkeeping. */ - timer->it.cpu.incr = timespec_to_sample(timer->it_clock, - &new->it_interval); + timer->it.cpu.incr = timespec_to_ns(&new->it_interval); /* * This acts as a modification timestamp for the timer, @@ -723,17 +693,15 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, ret = 0; out: - if (old) { - sample_to_timespec(timer->it_clock, - old_incr, &old->it_interval); - } + if (old) + old->it_interval = ns_to_timespec(old_incr); return ret; } static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) { - unsigned long long now; + u64 now; struct task_struct *p = timer->it.cpu.task; WARN_ON_ONCE(p == NULL); @@ -741,8 +709,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) /* * Easy part: convert the reload time. */ - sample_to_timespec(timer->it_clock, - timer->it.cpu.incr, &itp->it_interval); + itp->it_interval = ns_to_timespec(timer->it.cpu.incr); if (timer->it.cpu.expires == 0) { /* Timer not armed at all. */ itp->it_value.tv_sec = itp->it_value.tv_nsec = 0; @@ -771,8 +738,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) * Call the timer disarmed, nothing else to do. */ timer->it.cpu.expires = 0; - sample_to_timespec(timer->it_clock, timer->it.cpu.expires, - &itp->it_value); + itp->it_value = ns_to_timespec(timer->it.cpu.expires); return; } else { cpu_timer_sample_group(timer->it_clock, p, &now); @@ -781,9 +747,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) } if (now < timer->it.cpu.expires) { - sample_to_timespec(timer->it_clock, - timer->it.cpu.expires - now, - &itp->it_value); + itp->it_value = ns_to_timespec(timer->it.cpu.expires - now); } else { /* * The timer should have expired already, but the firing @@ -827,7 +791,7 @@ static void check_thread_timers(struct task_struct *tsk, struct list_head *timers = tsk->cpu_timers; struct signal_struct *const sig = tsk->signal; struct task_cputime *tsk_expires = &tsk->cputime_expires; - unsigned long long expires; + u64 expires; unsigned long soft; /* @@ -838,10 +802,10 @@ static void check_thread_timers(struct task_struct *tsk, return; expires = check_timers_list(timers, firing, prof_ticks(tsk)); - tsk_expires->prof_exp = expires_to_cputime(expires); + tsk_expires->prof_exp = expires; expires = check_timers_list(++timers, firing, virt_ticks(tsk)); - tsk_expires->virt_exp = expires_to_cputime(expires); + tsk_expires->virt_exp = expires; tsk_expires->sched_exp = check_timers_list(++timers, firing, tsk->se.sum_exec_runtime); @@ -890,26 +854,17 @@ static inline void stop_process_timers(struct signal_struct *sig) tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER); } -static u32 onecputick; - static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, - unsigned long long *expires, - unsigned long long cur_time, int signo) + u64 *expires, u64 cur_time, int signo) { if (!it->expires) return; if (cur_time >= it->expires) { - if (it->incr) { + if (it->incr) it->expires += it->incr; - it->error += it->incr_error; - if (it->error >= onecputick) { - it->expires -= cputime_one_jiffy; - it->error -= onecputick; - } - } else { + else it->expires = 0; - } trace_itimer_expire(signo == SIGPROF ? ITIMER_PROF : ITIMER_VIRTUAL, @@ -917,9 +872,8 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, __group_send_sig_info(signo, SEND_SIG_PRIV, tsk); } - if (it->expires && (!*expires || it->expires < *expires)) { + if (it->expires && (!*expires || it->expires < *expires)) *expires = it->expires; - } } /* @@ -931,8 +885,8 @@ static void check_process_timers(struct task_struct *tsk, struct list_head *firing) { struct signal_struct *const sig = tsk->signal; - unsigned long long utime, ptime, virt_expires, prof_expires; - unsigned long long sum_sched_runtime, sched_expires; + u64 utime, ptime, virt_expires, prof_expires; + u64 sum_sched_runtime, sched_expires; struct list_head *timers = sig->cpu_timers; struct task_cputime cputime; unsigned long soft; @@ -954,8 +908,8 @@ static void check_process_timers(struct task_struct *tsk, * Collect the current process totals. */ thread_group_cputimer(tsk, &cputime); - utime = cputime_to_expires(cputime.utime); - ptime = utime + cputime_to_expires(cputime.stime); + utime = cputime.utime; + ptime = utime + cputime.stime; sum_sched_runtime = cputime.sum_exec_runtime; prof_expires = check_timers_list(timers, firing, ptime); @@ -971,10 +925,10 @@ static void check_process_timers(struct task_struct *tsk, SIGVTALRM); soft = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); if (soft != RLIM_INFINITY) { - unsigned long psecs = cputime_to_secs(ptime); + unsigned long psecs = div_u64(ptime, NSEC_PER_SEC); unsigned long hard = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_max); - cputime_t x; + u64 x; if (psecs >= hard) { /* * At the hard limit, we just die. @@ -993,14 +947,13 @@ static void check_process_timers(struct task_struct *tsk, sig->rlim[RLIMIT_CPU].rlim_cur = soft; } } - x = secs_to_cputime(soft); - if (!prof_expires || x < prof_expires) { + x = soft * NSEC_PER_SEC; + if (!prof_expires || x < prof_expires) prof_expires = x; - } } - sig->cputime_expires.prof_exp = expires_to_cputime(prof_expires); - sig->cputime_expires.virt_exp = expires_to_cputime(virt_expires); + sig->cputime_expires.prof_exp = prof_expires; + sig->cputime_expires.virt_exp = virt_expires; sig->cputime_expires.sched_exp = sched_expires; if (task_cputime_zero(&sig->cputime_expires)) stop_process_timers(sig); @@ -1017,7 +970,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) struct sighand_struct *sighand; unsigned long flags; struct task_struct *p = timer->it.cpu.task; - unsigned long long now; + u64 now; WARN_ON_ONCE(p == NULL); @@ -1214,9 +1167,9 @@ void run_posix_cpu_timers(struct task_struct *tsk) * The tsk->sighand->siglock must be held by the caller. */ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, - cputime_t *newval, cputime_t *oldval) + u64 *newval, u64 *oldval) { - unsigned long long now; + u64 now; WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED); cpu_timer_sample_group(clock_idx, tsk, &now); @@ -1230,7 +1183,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, if (*oldval) { if (*oldval <= now) { /* Just about to fire. */ - *oldval = cputime_one_jiffy; + *oldval = TICK_NSEC; } else { *oldval -= now; } @@ -1310,7 +1263,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, /* * We were interrupted by a signal. */ - sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp); + *rqtp = ns_to_timespec(timer.it.cpu.expires); error = posix_cpu_timer_set(&timer, 0, &zero_it, it); if (!error) { /* @@ -1476,15 +1429,10 @@ static __init int init_posix_cpu_timers(void) .clock_get = thread_cpu_clock_get, .timer_create = thread_cpu_timer_create, }; - struct timespec ts; posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process); posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread); - cputime_to_timespec(cputime_one_jiffy, &ts); - onecputick = ts.tv_nsec; - WARN_ON(ts.tv_sec != 0); - return 0; } __initcall(init_posix_cpu_timers); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 3109204c87cc..987e496bb51a 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -29,12 +29,13 @@ */ static struct tick_device tick_broadcast_device; -static cpumask_var_t tick_broadcast_mask; -static cpumask_var_t tick_broadcast_on; -static cpumask_var_t tmpmask; -static DEFINE_RAW_SPINLOCK(tick_broadcast_lock); +static cpumask_var_t tick_broadcast_mask __cpumask_var_read_mostly; +static cpumask_var_t tick_broadcast_on __cpumask_var_read_mostly; +static cpumask_var_t tmpmask __cpumask_var_read_mostly; static int tick_broadcast_forced; +static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); + #ifdef CONFIG_TICK_ONESHOT static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); @@ -347,17 +348,16 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) * * Called when the system enters a state where affected tick devices * might stop. Note: TICK_BROADCAST_FORCE cannot be undone. - * - * Called with interrupts disabled, so clockevents_lock is not - * required here because the local clock event device cannot go away - * under us. */ void tick_broadcast_control(enum tick_broadcast_mode mode) { struct clock_event_device *bc, *dev; struct tick_device *td; int cpu, bc_stopped; + unsigned long flags; + /* Protects also the local clockevent device. */ + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; @@ -365,12 +365,11 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) * Is the device not affected by the powerstate ? */ if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP)) - return; + goto out; if (!tick_device_is_functional(dev)) - return; + goto out; - raw_spin_lock(&tick_broadcast_lock); cpu = smp_processor_id(); bc = tick_broadcast_device.evtdev; bc_stopped = cpumask_empty(tick_broadcast_mask); @@ -420,7 +419,8 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) tick_broadcast_setup_oneshot(bc); } } - raw_spin_unlock(&tick_broadcast_lock); +out: + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } EXPORT_SYMBOL_GPL(tick_broadcast_control); @@ -517,9 +517,9 @@ void tick_resume_broadcast(void) #ifdef CONFIG_TICK_ONESHOT -static cpumask_var_t tick_broadcast_oneshot_mask; -static cpumask_var_t tick_broadcast_pending_mask; -static cpumask_var_t tick_broadcast_force_mask; +static cpumask_var_t tick_broadcast_oneshot_mask __cpumask_var_read_mostly; +static cpumask_var_t tick_broadcast_pending_mask __cpumask_var_read_mostly; +static cpumask_var_t tick_broadcast_force_mask __cpumask_var_read_mostly; /* * Exposed for debugging: see timer_list.c diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index fc6f740d0277..2c115fdab397 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -725,11 +725,6 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, */ if (delta == 0) { tick_nohz_restart(ts, now); - /* - * Make sure next tick stop doesn't get fooled by past - * clock deadline - */ - ts->next_tick = 0; goto out; } } @@ -772,7 +767,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, tick = expires; /* Skip reprogram of event if its not changed */ - if (ts->tick_stopped && (expires == ts->next_tick)) + if (ts->tick_stopped && (expires == dev->next_event)) goto out; /* @@ -792,8 +787,6 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, trace_tick_stop(1, TICK_DEP_MASK_NONE); } - ts->next_tick = tick; - /* * If the expiration time == KTIME_MAX, then we simply stop * the tick timer. @@ -809,10 +802,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, else tick_program_event(tick, 1); out: - /* - * Update the estimated sleep length until the next timer - * (not only the tick). - */ + /* Update the estimated sleep length */ ts->sleep_length = ktime_sub(dev->next_event, now); return tick; } diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 075444e3d48e..bf38226e5c17 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -27,7 +27,6 @@ enum tick_nohz_mode { * timer is modified for nohz sleeps. This is necessary * to resume the tick timer operation in the timeline * when the CPU returns from nohz sleep. - * @next_tick: Next tick to be fired when in dynticks mode. * @tick_stopped: Indicator that the idle tick has been stopped * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_calls: Total number of idle calls @@ -45,7 +44,6 @@ struct tick_sched { unsigned long check_clocks; enum tick_nohz_mode nohz_mode; ktime_t last_tick; - ktime_t next_tick; int inidle; int tick_stopped; unsigned long idle_jiffies; diff --git a/kernel/time/time.c b/kernel/time/time.c index a3a9a8a029dc..25bdd2504571 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -702,6 +702,16 @@ u64 nsec_to_clock_t(u64 x) #endif } +u64 jiffies64_to_nsecs(u64 j) +{ +#if !(NSEC_PER_SEC % HZ) + return (NSEC_PER_SEC / HZ) * j; +# else + return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN); +#endif +} +EXPORT_SYMBOL(jiffies64_to_nsecs); + /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc index c48688904f9f..f83bbb81600b 100644 --- a/kernel/time/timeconst.bc +++ b/kernel/time/timeconst.bc @@ -98,6 +98,12 @@ define timeconst(hz) { print "#define HZ_TO_USEC_DEN\t\t", hz/cd, "\n" print "#define USEC_TO_HZ_NUM\t\t", hz/cd, "\n" print "#define USEC_TO_HZ_DEN\t\t", 1000000/cd, "\n" + + cd=gcd(hz,1000000000) + print "#define HZ_TO_NSEC_NUM\t\t", 1000000000/cd, "\n" + print "#define HZ_TO_NSEC_DEN\t\t", hz/cd, "\n" + print "#define NSEC_TO_HZ_NUM\t\t", hz/cd, "\n" + print "#define NSEC_TO_HZ_DEN\t\t", 1000000000/cd, "\n" print "\n" print "#endif /* KERNEL_TIMECONST_H */\n" diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index db087d7e106d..95b258dd75db 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1275,27 +1275,8 @@ error: /* even if we error out, we forwarded the time, so call update */ } EXPORT_SYMBOL(timekeeping_inject_offset); - -/** - * timekeeping_get_tai_offset - Returns current TAI offset from UTC - * - */ -s32 timekeeping_get_tai_offset(void) -{ - struct timekeeper *tk = &tk_core.timekeeper; - unsigned int seq; - s32 ret; - - do { - seq = read_seqcount_begin(&tk_core.seq); - ret = tk->tai_offset; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - return ret; -} - /** - * __timekeeping_set_tai_offset - Lock free worker function + * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic * */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) @@ -1305,24 +1286,6 @@ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) } /** - * timekeeping_set_tai_offset - Sets the current TAI offset from UTC - * - */ -void timekeeping_set_tai_offset(s32 tai_offset) -{ - struct timekeeper *tk = &tk_core.timekeeper; - unsigned long flags; - - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); - __timekeeping_set_tai_offset(tk, tai_offset); - timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); - clock_was_set(); -} - -/** * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 704f595ce83f..d0914676d4c5 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -11,8 +11,6 @@ extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, extern int timekeeping_valid_for_hres(void); extern u64 timekeeping_max_deferment(void); extern int timekeeping_inject_offset(struct timespec *ts); -extern s32 timekeeping_get_tai_offset(void); -extern void timekeeping_set_tai_offset(s32 tai_offset); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index ca9fb800336b..38bc4d2208e8 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -75,7 +75,7 @@ void tk_debug_account_sleep_time(struct timespec64 *t) int bin = min(fls(t->tv_sec), NUM_BINS-1); sleep_time_bin[bin]++; - pr_info("Suspended for %lld.%03lu seconds\n", (s64)t->tv_sec, - t->tv_nsec / NSEC_PER_MSEC); + printk_deferred(KERN_INFO "Suspended for %lld.%03lu seconds\n", + (s64)t->tv_sec, t->tv_nsec / NSEC_PER_MSEC); } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index ec33a6933eae..82a6bfa0c307 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -571,38 +571,6 @@ internal_add_timer(struct timer_base *base, struct timer_list *timer) trigger_dyntick_cpu(base, timer); } -#ifdef CONFIG_TIMER_STATS -void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr) -{ - if (timer->start_site) - return; - - timer->start_site = addr; - memcpy(timer->start_comm, current->comm, TASK_COMM_LEN); - timer->start_pid = current->pid; -} - -static void timer_stats_account_timer(struct timer_list *timer) -{ - void *site; - - /* - * start_site can be concurrently reset by - * timer_stats_timer_clear_start_info() - */ - site = READ_ONCE(timer->start_site); - if (likely(!site)) - return; - - timer_stats_update_stats(timer, timer->start_pid, site, - timer->function, timer->start_comm, - timer->flags); -} - -#else -static void timer_stats_account_timer(struct timer_list *timer) {} -#endif - #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static struct debug_obj_descr timer_debug_descr; @@ -789,11 +757,6 @@ static void do_init_timer(struct timer_list *timer, unsigned int flags, { timer->entry.pprev = NULL; timer->flags = flags | raw_smp_processor_id(); -#ifdef CONFIG_TIMER_STATS - timer->start_site = NULL; - timer->start_pid = -1; - memset(timer->start_comm, 0, TASK_COMM_LEN); -#endif lockdep_init_map(&timer->lockdep_map, name, key, 0); } @@ -1001,8 +964,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) base = lock_timer_base(timer, &flags); } - timer_stats_timer_set_start_info(timer); - ret = detach_if_pending(timer, base, false); if (!ret && pending_only) goto out_unlock; @@ -1130,7 +1091,6 @@ void add_timer_on(struct timer_list *timer, int cpu) struct timer_base *new_base, *base; unsigned long flags; - timer_stats_timer_set_start_info(timer); BUG_ON(timer_pending(timer) || !timer->function); new_base = get_timer_cpu_base(timer->flags, cpu); @@ -1176,7 +1136,6 @@ int del_timer(struct timer_list *timer) debug_assert_init(timer); - timer_stats_timer_clear_start_info(timer); if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, true); @@ -1204,10 +1163,9 @@ int try_to_del_timer_sync(struct timer_list *timer) base = lock_timer_base(timer, &flags); - if (base->running_timer != timer) { - timer_stats_timer_clear_start_info(timer); + if (base->running_timer != timer) ret = detach_if_pending(timer, base, true); - } + spin_unlock_irqrestore(&base->lock, flags); return ret; @@ -1331,7 +1289,6 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) unsigned long data; timer = hlist_entry(head->first, struct timer_list, entry); - timer_stats_account_timer(timer); base->running_timer = timer; detach_timer(timer, true); @@ -1868,7 +1825,6 @@ static void __init init_timer_cpus(void) void __init init_timers(void) { init_timer_cpus(); - init_timer_stats(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index afe6cd1944fc..ff8d5c13d04b 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -62,21 +62,11 @@ static void print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, int idx, u64 now) { -#ifdef CONFIG_TIMER_STATS - char tmp[TASK_COMM_LEN + 1]; -#endif SEQ_printf(m, " #%d: ", idx); print_name_offset(m, taddr); SEQ_printf(m, ", "); print_name_offset(m, timer->function); SEQ_printf(m, ", S:%02x", timer->state); -#ifdef CONFIG_TIMER_STATS - SEQ_printf(m, ", "); - print_name_offset(m, timer->start_site); - memcpy(tmp, timer->start_comm, TASK_COMM_LEN); - tmp[TASK_COMM_LEN] = 0; - SEQ_printf(m, ", %s/%d", tmp, timer->start_pid); -#endif SEQ_printf(m, "\n"); SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n", (unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)), @@ -127,7 +117,7 @@ print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now) SEQ_printf(m, " .base: %pK\n", base); SEQ_printf(m, " .index: %d\n", base->index); - SEQ_printf(m, " .resolution: %u nsecs\n", (unsigned) hrtimer_resolution); + SEQ_printf(m, " .resolution: %u nsecs\n", hrtimer_resolution); SEQ_printf(m, " .get_time: "); print_name_offset(m, base->get_time); diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c deleted file mode 100644 index afddded947df..000000000000 --- a/kernel/time/timer_stats.c +++ /dev/null @@ -1,425 +0,0 @@ -/* - * kernel/time/timer_stats.c - * - * Collect timer usage statistics. - * - * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar - * Copyright(C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> - * - * timer_stats is based on timer_top, a similar functionality which was part of - * Con Kolivas dyntick patch set. It was developed by Daniel Petrini at the - * Instituto Nokia de Tecnologia - INdT - Manaus. timer_top's design was based - * on dynamic allocation of the statistics entries and linear search based - * lookup combined with a global lock, rather than the static array, hash - * and per-CPU locking which is used by timer_stats. It was written for the - * pre hrtimer kernel code and therefore did not take hrtimers into account. - * Nevertheless it provided the base for the timer_stats implementation and - * was a helpful source of inspiration. Kudos to Daniel and the Nokia folks - * for this effort. - * - * timer_top.c is - * Copyright (C) 2005 Instituto Nokia de Tecnologia - INdT - Manaus - * Written by Daniel Petrini <d.pensator@gmail.com> - * timer_top.c was released under the GNU General Public License version 2 - * - * We export the addresses and counting of timer functions being called, - * the pid and cmdline from the owner process if applicable. - * - * Start/stop data collection: - * # echo [1|0] >/proc/timer_stats - * - * Display the information collected so far: - * # cat /proc/timer_stats - * - * 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. - */ - -#include <linux/proc_fs.h> -#include <linux/module.h> -#include <linux/spinlock.h> -#include <linux/sched.h> -#include <linux/seq_file.h> -#include <linux/kallsyms.h> - -#include <linux/uaccess.h> - -/* - * This is our basic unit of interest: a timer expiry event identified - * by the timer, its start/expire functions and the PID of the task that - * started the timer. We count the number of times an event happens: - */ -struct entry { - /* - * Hash list: - */ - struct entry *next; - - /* - * Hash keys: - */ - void *timer; - void *start_func; - void *expire_func; - pid_t pid; - - /* - * Number of timeout events: - */ - unsigned long count; - u32 flags; - - /* - * We save the command-line string to preserve - * this information past task exit: - */ - char comm[TASK_COMM_LEN + 1]; - -} ____cacheline_aligned_in_smp; - -/* - * Spinlock protecting the tables - not taken during lookup: - */ -static DEFINE_RAW_SPINLOCK(table_lock); - -/* - * Per-CPU lookup locks for fast hash lookup: - */ -static DEFINE_PER_CPU(raw_spinlock_t, tstats_lookup_lock); - -/* - * Mutex to serialize state changes with show-stats activities: - */ -static DEFINE_MUTEX(show_mutex); - -/* - * Collection status, active/inactive: - */ -int __read_mostly timer_stats_active; - -/* - * Beginning/end timestamps of measurement: - */ -static ktime_t time_start, time_stop; - -/* - * tstat entry structs only get allocated while collection is - * active and never freed during that time - this simplifies - * things quite a bit. - * - * They get freed when a new collection period is started. - */ -#define MAX_ENTRIES_BITS 10 -#define MAX_ENTRIES (1UL << MAX_ENTRIES_BITS) - -static unsigned long nr_entries; -static struct entry entries[MAX_ENTRIES]; - -static atomic_t overflow_count; - -/* - * The entries are in a hash-table, for fast lookup: - */ -#define TSTAT_HASH_BITS (MAX_ENTRIES_BITS - 1) -#define TSTAT_HASH_SIZE (1UL << TSTAT_HASH_BITS) -#define TSTAT_HASH_MASK (TSTAT_HASH_SIZE - 1) - -#define __tstat_hashfn(entry) \ - (((unsigned long)(entry)->timer ^ \ - (unsigned long)(entry)->start_func ^ \ - (unsigned long)(entry)->expire_func ^ \ - (unsigned long)(entry)->pid ) & TSTAT_HASH_MASK) - -#define tstat_hashentry(entry) (tstat_hash_table + __tstat_hashfn(entry)) - -static struct entry *tstat_hash_table[TSTAT_HASH_SIZE] __read_mostly; - -static void reset_entries(void) -{ - nr_entries = 0; - memset(entries, 0, sizeof(entries)); - memset(tstat_hash_table, 0, sizeof(tstat_hash_table)); - atomic_set(&overflow_count, 0); -} - -static struct entry *alloc_entry(void) -{ - if (nr_entries >= MAX_ENTRIES) - return NULL; - - return entries + nr_entries++; -} - -static int match_entries(struct entry *entry1, struct entry *entry2) -{ - return entry1->timer == entry2->timer && - entry1->start_func == entry2->start_func && - entry1->expire_func == entry2->expire_func && - entry1->pid == entry2->pid; -} - -/* - * Look up whether an entry matching this item is present - * in the hash already. Must be called with irqs off and the - * lookup lock held: - */ -static struct entry *tstat_lookup(struct entry *entry, char *comm) -{ - struct entry **head, *curr, *prev; - - head = tstat_hashentry(entry); - curr = *head; - - /* - * The fastpath is when the entry is already hashed, - * we do this with the lookup lock held, but with the - * table lock not held: - */ - while (curr) { - if (match_entries(curr, entry)) - return curr; - - curr = curr->next; - } - /* - * Slowpath: allocate, set up and link a new hash entry: - */ - prev = NULL; - curr = *head; - - raw_spin_lock(&table_lock); - /* - * Make sure we have not raced with another CPU: - */ - while (curr) { - if (match_entries(curr, entry)) - goto out_unlock; - - prev = curr; - curr = curr->next; - } - - curr = alloc_entry(); - if (curr) { - *curr = *entry; - curr->count = 0; - curr->next = NULL; - memcpy(curr->comm, comm, TASK_COMM_LEN); - - smp_mb(); /* Ensure that curr is initialized before insert */ - - if (prev) - prev->next = curr; - else - *head = curr; - } - out_unlock: - raw_spin_unlock(&table_lock); - - return curr; -} - -/** - * timer_stats_update_stats - Update the statistics for a timer. - * @timer: pointer to either a timer_list or a hrtimer - * @pid: the pid of the task which set up the timer - * @startf: pointer to the function which did the timer setup - * @timerf: pointer to the timer callback function of the timer - * @comm: name of the process which set up the timer - * @tflags: The flags field of the timer - * - * When the timer is already registered, then the event counter is - * incremented. Otherwise the timer is registered in a free slot. - */ -void timer_stats_update_stats(void *timer, pid_t pid, void *startf, - void *timerf, char *comm, u32 tflags) -{ - /* - * It doesn't matter which lock we take: - */ - raw_spinlock_t *lock; - struct entry *entry, input; - unsigned long flags; - - if (likely(!timer_stats_active)) - return; - - lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id()); - - input.timer = timer; - input.start_func = startf; - input.expire_func = timerf; - input.pid = pid; - input.flags = tflags; - - raw_spin_lock_irqsave(lock, flags); - if (!timer_stats_active) - goto out_unlock; - - entry = tstat_lookup(&input, comm); - if (likely(entry)) - entry->count++; - else - atomic_inc(&overflow_count); - - out_unlock: - raw_spin_unlock_irqrestore(lock, flags); -} - -static void print_name_offset(struct seq_file *m, unsigned long addr) -{ - char symname[KSYM_NAME_LEN]; - - if (lookup_symbol_name(addr, symname) < 0) - seq_printf(m, "<%p>", (void *)addr); - else - seq_printf(m, "%s", symname); -} - -static int tstats_show(struct seq_file *m, void *v) -{ - struct timespec64 period; - struct entry *entry; - unsigned long ms; - long events = 0; - ktime_t time; - int i; - - mutex_lock(&show_mutex); - /* - * If still active then calculate up to now: - */ - if (timer_stats_active) - time_stop = ktime_get(); - - time = ktime_sub(time_stop, time_start); - - period = ktime_to_timespec64(time); - ms = period.tv_nsec / 1000000; - - seq_puts(m, "Timer Stats Version: v0.3\n"); - seq_printf(m, "Sample period: %ld.%03ld s\n", (long)period.tv_sec, ms); - if (atomic_read(&overflow_count)) - seq_printf(m, "Overflow: %d entries\n", atomic_read(&overflow_count)); - seq_printf(m, "Collection: %s\n", timer_stats_active ? "active" : "inactive"); - - for (i = 0; i < nr_entries; i++) { - entry = entries + i; - if (entry->flags & TIMER_DEFERRABLE) { - seq_printf(m, "%4luD, %5d %-16s ", - entry->count, entry->pid, entry->comm); - } else { - seq_printf(m, " %4lu, %5d %-16s ", - entry->count, entry->pid, entry->comm); - } - - print_name_offset(m, (unsigned long)entry->start_func); - seq_puts(m, " ("); - print_name_offset(m, (unsigned long)entry->expire_func); - seq_puts(m, ")\n"); - - events += entry->count; - } - - ms += period.tv_sec * 1000; - if (!ms) - ms = 1; - - if (events && period.tv_sec) - seq_printf(m, "%ld total events, %ld.%03ld events/sec\n", - events, events * 1000 / ms, - (events * 1000000 / ms) % 1000); - else - seq_printf(m, "%ld total events\n", events); - - mutex_unlock(&show_mutex); - - return 0; -} - -/* - * After a state change, make sure all concurrent lookup/update - * activities have stopped: - */ -static void sync_access(void) -{ - unsigned long flags; - int cpu; - - for_each_online_cpu(cpu) { - raw_spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu); - - raw_spin_lock_irqsave(lock, flags); - /* nothing */ - raw_spin_unlock_irqrestore(lock, flags); - } -} - -static ssize_t tstats_write(struct file *file, const char __user *buf, - size_t count, loff_t *offs) -{ - char ctl[2]; - - if (count != 2 || *offs) - return -EINVAL; - - if (copy_from_user(ctl, buf, count)) - return -EFAULT; - - mutex_lock(&show_mutex); - switch (ctl[0]) { - case '0': - if (timer_stats_active) { - timer_stats_active = 0; - time_stop = ktime_get(); - sync_access(); - } - break; - case '1': - if (!timer_stats_active) { - reset_entries(); - time_start = ktime_get(); - smp_mb(); - timer_stats_active = 1; - } - break; - default: - count = -EINVAL; - } - mutex_unlock(&show_mutex); - - return count; -} - -static int tstats_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, tstats_show, NULL); -} - -static const struct file_operations tstats_fops = { - .open = tstats_open, - .read = seq_read, - .write = tstats_write, - .llseek = seq_lseek, - .release = single_release, -}; - -void __init init_timer_stats(void) -{ - int cpu; - - for_each_possible_cpu(cpu) - raw_spin_lock_init(&per_cpu(tstats_lookup_lock, cpu)); -} - -static int __init init_tstats_procfs(void) -{ - struct proc_dir_entry *pe; - - pe = proc_create("timer_stats", 0644, NULL, &tstats_fops); - if (!pe) - return -ENOMEM; - return 0; -} -__initcall(init_tstats_procfs); diff --git a/kernel/tsacct.c b/kernel/tsacct.c index f8e26ab963ed..5c21f0535056 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -31,7 +31,7 @@ void bacct_add_tsk(struct user_namespace *user_ns, struct taskstats *stats, struct task_struct *tsk) { const struct cred *tcred; - cputime_t utime, stime, utimescaled, stimescaled; + u64 utime, stime, utimescaled, stimescaled; u64 delta; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); @@ -67,12 +67,12 @@ void bacct_add_tsk(struct user_namespace *user_ns, rcu_read_unlock(); task_cputime(tsk, &utime, &stime); - stats->ac_utime = cputime_to_usecs(utime); - stats->ac_stime = cputime_to_usecs(stime); + stats->ac_utime = div_u64(utime, NSEC_PER_USEC); + stats->ac_stime = div_u64(stime, NSEC_PER_USEC); task_cputime_scaled(tsk, &utimescaled, &stimescaled); - stats->ac_utimescaled = cputime_to_usecs(utimescaled); - stats->ac_stimescaled = cputime_to_usecs(stimescaled); + stats->ac_utimescaled = div_u64(utimescaled, NSEC_PER_USEC); + stats->ac_stimescaled = div_u64(stimescaled, NSEC_PER_USEC); stats->ac_minflt = tsk->min_flt; stats->ac_majflt = tsk->maj_flt; @@ -123,18 +123,15 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) #undef MB static void __acct_update_integrals(struct task_struct *tsk, - cputime_t utime, cputime_t stime) + u64 utime, u64 stime) { - cputime_t time, dtime; - u64 delta; + u64 time, delta; if (!likely(tsk->mm)) return; time = stime + utime; - dtime = time - tsk->acct_timexpd; - /* Avoid division: cputime_t is often in nanoseconds already. */ - delta = cputime_to_nsecs(dtime); + delta = time - tsk->acct_timexpd; if (delta < TICK_NSEC) return; @@ -155,7 +152,7 @@ static void __acct_update_integrals(struct task_struct *tsk, */ void acct_update_integrals(struct task_struct *tsk) { - cputime_t utime, stime; + u64 utime, stime; unsigned long flags; local_irq_save(flags); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1d9fb6543a66..072cbc9b175d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1523,8 +1523,6 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, return; } - timer_stats_timer_set_start_info(&dwork->timer); - dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index eb9e9a7870fa..acedbe626d47 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -716,6 +716,19 @@ source "lib/Kconfig.kmemcheck" source "lib/Kconfig.kasan" +config DEBUG_REFCOUNT + bool "Verbose refcount checks" + help + Say Y here if you want reference counters (refcount_t and kref) to + generate WARNs on dubious usage. Without this refcount_t will still + be a saturating counter and avoid Use-After-Free by turning it into + a resource leak Denial-Of-Service. + + Use of this option will increase kernel text size but will alert the + admin of potential abuse. + + If in doubt, say "N". + endmenu # "Memory Debugging" config ARCH_HAS_KCOV @@ -980,20 +993,6 @@ config DEBUG_TIMEKEEPING If unsure, say N. -config TIMER_STATS - bool "Collect kernel timers statistics" - depends on DEBUG_KERNEL && PROC_FS - help - If you say Y here, additional code will be inserted into the - timer routines to collect statistics about kernel timers being - reprogrammed. The statistics can be read from /proc/timer_stats. - The statistics collection is started by writing 1 to /proc/timer_stats, - writing 0 stops it. This feature is useful to collect information - about timer usage patterns in kernel and userspace. This feature - is lightweight if enabled in the kernel config but not activated - (it defaults to deactivated on bootup and will only be activated - if some application like powertop activates it explicitly). - config DEBUG_PREEMPT bool "Debug preemptible kernel" depends on DEBUG_KERNEL && PREEMPT && TRACE_IRQFLAGS_SUPPORT @@ -1180,6 +1179,18 @@ config LOCK_TORTURE_TEST Say M if you want these torture tests to build as a module. Say N if you are unsure. +config WW_MUTEX_SELFTEST + tristate "Wait/wound mutex selftests" + help + This option provides a kernel module that runs tests on the + on the struct ww_mutex locking API. + + It is recommended to enable DEBUG_WW_MUTEX_SLOWPATH in conjunction + with this test harness. + + Say M if you want these self tests to build as a module. + Say N if you are unsure. + endmenu # lock debugging config TRACE_IRQFLAGS @@ -1450,6 +1461,7 @@ config RCU_CPU_STALL_TIMEOUT config RCU_TRACE bool "Enable tracing for RCU" depends on DEBUG_KERNEL + default y if TREE_RCU select TRACE_CLOCK help This option provides tracing in RCU which presents stats diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 04c1ef717fe0..8c28cbd7e104 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -52,9 +52,18 @@ static int debug_objects_fixups __read_mostly; static int debug_objects_warnings __read_mostly; static int debug_objects_enabled __read_mostly = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT; - +static int debug_objects_pool_size __read_mostly + = ODEBUG_POOL_SIZE; +static int debug_objects_pool_min_level __read_mostly + = ODEBUG_POOL_MIN_LEVEL; static struct debug_obj_descr *descr_test __read_mostly; +/* + * Track numbers of kmem_cache_alloc()/free() calls done. + */ +static int debug_objects_allocated; +static int debug_objects_freed; + static void free_obj_work(struct work_struct *work); static DECLARE_WORK(debug_obj_work, free_obj_work); @@ -88,13 +97,13 @@ static void fill_pool(void) struct debug_obj *new; unsigned long flags; - if (likely(obj_pool_free >= ODEBUG_POOL_MIN_LEVEL)) + if (likely(obj_pool_free >= debug_objects_pool_min_level)) return; if (unlikely(!obj_cache)) return; - while (obj_pool_free < ODEBUG_POOL_MIN_LEVEL) { + while (obj_pool_free < debug_objects_pool_min_level) { new = kmem_cache_zalloc(obj_cache, gfp); if (!new) @@ -102,6 +111,7 @@ static void fill_pool(void) raw_spin_lock_irqsave(&pool_lock, flags); hlist_add_head(&new->node, &obj_pool); + debug_objects_allocated++; obj_pool_free++; raw_spin_unlock_irqrestore(&pool_lock, flags); } @@ -162,24 +172,39 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr) /* * workqueue function to free objects. + * + * To reduce contention on the global pool_lock, the actual freeing of + * debug objects will be delayed if the pool_lock is busy. We also free + * the objects in a batch of 4 for each lock/unlock cycle. */ +#define ODEBUG_FREE_BATCH 4 + static void free_obj_work(struct work_struct *work) { - struct debug_obj *obj; + struct debug_obj *objs[ODEBUG_FREE_BATCH]; unsigned long flags; + int i; - raw_spin_lock_irqsave(&pool_lock, flags); - while (obj_pool_free > ODEBUG_POOL_SIZE) { - obj = hlist_entry(obj_pool.first, typeof(*obj), node); - hlist_del(&obj->node); - obj_pool_free--; + if (!raw_spin_trylock_irqsave(&pool_lock, flags)) + return; + while (obj_pool_free >= debug_objects_pool_size + ODEBUG_FREE_BATCH) { + for (i = 0; i < ODEBUG_FREE_BATCH; i++) { + objs[i] = hlist_entry(obj_pool.first, + typeof(*objs[0]), node); + hlist_del(&objs[i]->node); + } + + obj_pool_free -= ODEBUG_FREE_BATCH; + debug_objects_freed += ODEBUG_FREE_BATCH; /* * We release pool_lock across kmem_cache_free() to * avoid contention on pool_lock. */ raw_spin_unlock_irqrestore(&pool_lock, flags); - kmem_cache_free(obj_cache, obj); - raw_spin_lock_irqsave(&pool_lock, flags); + for (i = 0; i < ODEBUG_FREE_BATCH; i++) + kmem_cache_free(obj_cache, objs[i]); + if (!raw_spin_trylock_irqsave(&pool_lock, flags)) + return; } raw_spin_unlock_irqrestore(&pool_lock, flags); } @@ -198,7 +223,7 @@ static void free_object(struct debug_obj *obj) * schedule work when the pool is filled and the cache is * initialized: */ - if (obj_pool_free > ODEBUG_POOL_SIZE && obj_cache) + if (obj_pool_free > debug_objects_pool_size && obj_cache) sched = 1; hlist_add_head(&obj->node, &obj_pool); obj_pool_free++; @@ -758,6 +783,8 @@ static int debug_stats_show(struct seq_file *m, void *v) seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free); seq_printf(m, "pool_used :%d\n", obj_pool_used); seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used); + seq_printf(m, "objs_allocated:%d\n", debug_objects_allocated); + seq_printf(m, "objs_freed :%d\n", debug_objects_freed); return 0; } @@ -1116,4 +1143,11 @@ void __init debug_objects_mem_init(void) pr_warn("out of memory.\n"); } else debug_objects_selftest(); + + /* + * Increase the thresholds for allocating and freeing objects + * according to the number of possible CPUs available in the system. + */ + debug_objects_pool_size += num_possible_cpus() * 32; + debug_objects_pool_min_level += num_possible_cpus() * 4; } diff --git a/lib/timerqueue.c b/lib/timerqueue.c index adc6ee0a5126..4a720ed4fdaf 100644 --- a/lib/timerqueue.c +++ b/lib/timerqueue.c @@ -80,8 +80,7 @@ bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node) if (head->next == node) { struct rb_node *rbn = rb_next(&node->node); - head->next = rbn ? - rb_entry(rbn, struct timerqueue_node, node) : NULL; + head->next = rb_entry_safe(rbn, struct timerqueue_node, node); } rb_erase(&node->node, &head->head); RB_CLEAR_NODE(&node->node); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 1904a93f47d5..d491529332f4 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -920,7 +920,7 @@ static void chan_close_cb(struct l2cap_chan *chan) BT_DBG("dev %p removing %speer %p", dev, last ? "last " : "1 ", peer); BT_DBG("chan %p orig refcnt %d", chan, - atomic_read(&chan->kref.refcount)); + kref_read(&chan->kref)); l2cap_chan_put(chan); break; diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 5f123c3320a7..f0095fd79818 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -810,7 +810,7 @@ static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked) /* AMP Manager functions */ struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr) { - BT_DBG("mgr %p orig refcnt %d", mgr, atomic_read(&mgr->kref.refcount)); + BT_DBG("mgr %p orig refcnt %d", mgr, kref_read(&mgr->kref)); kref_get(&mgr->kref); @@ -833,7 +833,7 @@ static void amp_mgr_destroy(struct kref *kref) int amp_mgr_put(struct amp_mgr *mgr) { - BT_DBG("mgr %p orig refcnt %d", mgr, atomic_read(&mgr->kref.refcount)); + BT_DBG("mgr %p orig refcnt %d", mgr, kref_read(&mgr->kref)); return kref_put(&mgr->kref, &_mgr_destroy); } diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index e32f34189007..02a4ccc04e1e 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -24,7 +24,7 @@ void amp_ctrl_get(struct amp_ctrl *ctrl) { BT_DBG("ctrl %p orig refcnt %d", ctrl, - atomic_read(&ctrl->kref.refcount)); + kref_read(&ctrl->kref)); kref_get(&ctrl->kref); } @@ -42,7 +42,7 @@ static void amp_ctrl_destroy(struct kref *kref) int amp_ctrl_put(struct amp_ctrl *ctrl) { BT_DBG("ctrl %p orig refcnt %d", ctrl, - atomic_read(&ctrl->kref.refcount)); + kref_read(&ctrl->kref)); return kref_put(&ctrl->kref, &_ctrl_destroy); } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index ce0b5dd01953..fc7f321a3823 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -481,14 +481,14 @@ static void l2cap_chan_destroy(struct kref *kref) void l2cap_chan_hold(struct l2cap_chan *c) { - BT_DBG("chan %p orig refcnt %d", c, atomic_read(&c->kref.refcount)); + BT_DBG("chan %p orig refcnt %d", c, kref_read(&c->kref)); kref_get(&c->kref); } void l2cap_chan_put(struct l2cap_chan *c) { - BT_DBG("chan %p orig refcnt %d", c, atomic_read(&c->kref.refcount)); + BT_DBG("chan %p orig refcnt %d", c, kref_read(&c->kref)); kref_put(&c->kref, l2cap_chan_destroy); } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 770c52701efa..bad3d4ae43f6 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -3425,7 +3425,7 @@ static void ceph_msg_release(struct kref *kref) struct ceph_msg *ceph_msg_get(struct ceph_msg *msg) { dout("%s %p (was %d)\n", __func__, msg, - atomic_read(&msg->kref.refcount)); + kref_read(&msg->kref)); kref_get(&msg->kref); return msg; } @@ -3434,7 +3434,7 @@ EXPORT_SYMBOL(ceph_msg_get); void ceph_msg_put(struct ceph_msg *msg) { dout("%s %p (was %d)\n", __func__, msg, - atomic_read(&msg->kref.refcount)); + kref_read(&msg->kref)); kref_put(&msg->kref, ceph_msg_release); } EXPORT_SYMBOL(ceph_msg_put); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 842f049abb86..f3378ba1a828 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -438,7 +438,7 @@ static void ceph_osdc_release_request(struct kref *kref) void ceph_osdc_get_request(struct ceph_osd_request *req) { dout("%s %p (was %d)\n", __func__, req, - atomic_read(&req->r_kref.refcount)); + kref_read(&req->r_kref)); kref_get(&req->r_kref); } EXPORT_SYMBOL(ceph_osdc_get_request); @@ -447,7 +447,7 @@ void ceph_osdc_put_request(struct ceph_osd_request *req) { if (req) { dout("%s %p (was %d)\n", __func__, req, - atomic_read(&req->r_kref.refcount)); + kref_read(&req->r_kref)); kref_put(&req->r_kref, ceph_osdc_release_request); } } @@ -487,11 +487,11 @@ static void request_reinit(struct ceph_osd_request *req) struct ceph_msg *reply_msg = req->r_reply; dout("%s req %p\n", __func__, req); - WARN_ON(atomic_read(&req->r_kref.refcount) != 1); + WARN_ON(kref_read(&req->r_kref) != 1); request_release_checks(req); - WARN_ON(atomic_read(&request_msg->kref.refcount) != 1); - WARN_ON(atomic_read(&reply_msg->kref.refcount) != 1); + WARN_ON(kref_read(&request_msg->kref) != 1); + WARN_ON(kref_read(&reply_msg->kref) != 1); target_destroy(&req->r_t); request_init(req); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 7bb12e07ffef..e7c12caa20c8 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2923,7 +2923,8 @@ static void neigh_proc_update(struct ctl_table *ctl, int write) return; set_bit(index, p->data_state); - call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p); + if (index == NEIGH_VAR_DELAY_PROBE_TIME) + call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p); if (!dev) /* NULL dev means this is default value */ neigh_copy_dflt_parms(net, p, index); } diff --git a/net/dccp/input.c b/net/dccp/input.c index ba347184bda9..8fedc2d49770 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -606,7 +606,8 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) < 0) return 1; - goto discard; + consume_skb(skb); + return 0; } if (dh->dccph_type == DCCP_PKT_RESET) goto discard; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 89a8cac4726a..51b27ae09fbd 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1263,7 +1263,7 @@ void __init arp_init(void) /* * ax25 -> ASCII conversion */ -static char *ax2asc2(ax25_address *a, char *buf) +static void ax2asc2(ax25_address *a, char *buf) { char c, *s; int n; @@ -1285,10 +1285,10 @@ static char *ax2asc2(ax25_address *a, char *buf) *s++ = n + '0'; *s++ = '\0'; - if (*buf == '\0' || *buf == '-') - return "*"; - - return buf; + if (*buf == '\0' || *buf == '-') { + buf[0] = '*'; + buf[1] = '\0'; + } } #endif /* CONFIG_AX25 */ @@ -1322,7 +1322,7 @@ static void arp_format_neigh_entry(struct seq_file *seq, } #endif sprintf(tbuf, "%pI4", n->primary_key); - seq_printf(seq, "%-16s 0x%-10x0x%-10x%s * %s\n", + seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s * %s\n", tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name); read_unlock(&n->lock); } diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index f6c50af24a64..3d063eb37848 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -117,7 +117,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, (fwmark > 0 && skb->mark == fwmark)) && (full || tp->snd_cwnd != tcp_probe.lastcwnd)) { - spin_lock(&tcp_probe.lock); + spin_lock_bh(&tcp_probe.lock); /* If log fills, just silently drop */ if (tcp_probe_avail() > 1) { struct tcp_log *p = tcp_probe.log + tcp_probe.head; @@ -157,7 +157,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1); } tcp_probe.lastcwnd = tp->snd_cwnd; - spin_unlock(&tcp_probe.lock); + spin_unlock_bh(&tcp_probe.lock); wake_up(&tcp_probe.wait); } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index a3eaafd87100..eec27f87efac 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -167,18 +167,22 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, if (np->sndflow) fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; - addr_type = ipv6_addr_type(&usin->sin6_addr); - - if (addr_type == IPV6_ADDR_ANY) { + if (ipv6_addr_any(&usin->sin6_addr)) { /* * connect to self */ - usin->sin6_addr.s6_addr[15] = 0x01; + if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), + &usin->sin6_addr); + else + usin->sin6_addr = in6addr_loopback; } + addr_type = ipv6_addr_type(&usin->sin6_addr); + daddr = &usin->sin6_addr; - if (addr_type == IPV6_ADDR_MAPPED) { + if (addr_type & IPV6_ADDR_MAPPED) { struct sockaddr_in sin; if (__ipv6_only_sock(sk)) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index b6a94ff0bbd0..7cebee58e55b 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1021,6 +1021,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, } } #endif + if (ipv6_addr_v4mapped(&fl6->saddr) && + !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) { + err = -EAFNOSUPPORT; + goto out_err_release; + } return 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index eaad72c3d746..4c60c6f71cd3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -148,8 +148,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, * connect() to INADDR_ANY means loopback (BSD'ism). */ - if (ipv6_addr_any(&usin->sin6_addr)) - usin->sin6_addr.s6_addr[15] = 0x1; + if (ipv6_addr_any(&usin->sin6_addr)) { + if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), + &usin->sin6_addr); + else + usin->sin6_addr = in6addr_loopback; + } addr_type = ipv6_addr_type(&usin->sin6_addr); @@ -188,7 +193,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, * TCP over IPv4 */ - if (addr_type == IPV6_ADDR_MAPPED) { + if (addr_type & IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8990856f5101..221825a9407a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1033,6 +1033,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; daddr = &sin6->sin6_addr; + if (ipv6_addr_any(daddr) && + ipv6_addr_v4mapped(&np->saddr)) + ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), + daddr); break; case AF_INET: goto do_udp_sendmsg; diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c index acbe61c7e683..160dc89335e2 100644 --- a/net/irda/irqueue.c +++ b/net/irda/irqueue.c @@ -383,9 +383,6 @@ EXPORT_SYMBOL(hashbin_new); * for deallocating this structure if it's complex. If not the user can * just supply kfree, which should take care of the job. */ -#ifdef CONFIG_LOCKDEP -static int hashbin_lock_depth = 0; -#endif int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func) { irda_queue_t* queue; @@ -396,22 +393,27 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func) IRDA_ASSERT(hashbin->magic == HB_MAGIC, return -1;); /* Synchronize */ - if ( hashbin->hb_type & HB_LOCK ) { - spin_lock_irqsave_nested(&hashbin->hb_spinlock, flags, - hashbin_lock_depth++); - } + if (hashbin->hb_type & HB_LOCK) + spin_lock_irqsave(&hashbin->hb_spinlock, flags); /* * Free the entries in the hashbin, TODO: use hashbin_clear when * it has been shown to work */ for (i = 0; i < HASHBIN_SIZE; i ++ ) { - queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]); - while (queue ) { - if (free_func) - (*free_func)(queue); - queue = dequeue_first( - (irda_queue_t**) &hashbin->hb_queue[i]); + while (1) { + queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]); + + if (!queue) + break; + + if (free_func) { + if (hashbin->hb_type & HB_LOCK) + spin_unlock_irqrestore(&hashbin->hb_spinlock, flags); + free_func(queue); + if (hashbin->hb_type & HB_LOCK) + spin_lock_irqsave(&hashbin->hb_spinlock, flags); + } } } @@ -420,12 +422,8 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func) hashbin->magic = ~HB_MAGIC; /* Release lock */ - if ( hashbin->hb_type & HB_LOCK) { + if (hashbin->hb_type & HB_LOCK) spin_unlock_irqrestore(&hashbin->hb_spinlock, flags); -#ifdef CONFIG_LOCKDEP - hashbin_lock_depth--; -#endif - } /* * Free the hashbin structure diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 64f0e8531af0..a646f3481240 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1044,8 +1044,10 @@ wait_for_memory: } else { /* Message not complete, save state */ partial_message: - kcm->seq_skb = head; - kcm_tx_msg(head)->last_skb = skb; + if (head) { + kcm->seq_skb = head; + kcm_tx_msg(head)->last_skb = skb; + } } KCM_STATS_ADD(kcm->stats.tx_bytes, copied); diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 3e821daf9dd4..8bc5a1bd2d45 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -821,7 +821,10 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) * another trick required to cope with how the PROCOM state * machine works. -acme */ + skb_orphan(skb); + sock_hold(sk); skb->sk = sk; + skb->destructor = sock_efree; } if (!sock_owned_by_user(sk)) llc_conn_rcv(sk, skb); diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index d0e1e804ebd7..5404d0d195cc 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -290,7 +290,10 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, ev->type = LLC_SAP_EV_TYPE_PDU; ev->reason = 0; + skb_orphan(skb); + sock_hold(sk); skb->sk = sk; + skb->destructor = sock_efree; llc_sap_state_process(sap, skb); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d56ee46b11fc..70f5b6a4683c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1497,6 +1497,8 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po) f->arr[f->num_members] = sk; smp_wmb(); f->num_members++; + if (f->num_members == 1) + dev_add_pack(&f->prot_hook); spin_unlock(&f->lock); } @@ -1513,6 +1515,8 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po) BUG_ON(i >= f->num_members); f->arr[i] = f->arr[f->num_members - 1]; f->num_members--; + if (f->num_members == 0) + __dev_remove_pack(&f->prot_hook); spin_unlock(&f->lock); } @@ -1619,6 +1623,7 @@ static void fanout_release_data(struct packet_fanout *f) static int fanout_add(struct sock *sk, u16 id, u16 type_flags) { + struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f, *match; u8 type = type_flags & 0xff; @@ -1641,23 +1646,28 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) return -EINVAL; } + mutex_lock(&fanout_mutex); + + err = -EINVAL; if (!po->running) - return -EINVAL; + goto out; + err = -EALREADY; if (po->fanout) - return -EALREADY; + goto out; if (type == PACKET_FANOUT_ROLLOVER || (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) { - po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL); - if (!po->rollover) - return -ENOMEM; - atomic_long_set(&po->rollover->num, 0); - atomic_long_set(&po->rollover->num_huge, 0); - atomic_long_set(&po->rollover->num_failed, 0); + err = -ENOMEM; + rollover = kzalloc(sizeof(*rollover), GFP_KERNEL); + if (!rollover) + goto out; + atomic_long_set(&rollover->num, 0); + atomic_long_set(&rollover->num_huge, 0); + atomic_long_set(&rollover->num_failed, 0); + po->rollover = rollover; } - mutex_lock(&fanout_mutex); match = NULL; list_for_each_entry(f, &fanout_list, list) { if (f->id == id && @@ -1687,7 +1697,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; match->prot_hook.id_match = match_fanout_group; - dev_add_pack(&match->prot_hook); list_add(&match->list, &fanout_list); } err = -EINVAL; @@ -1704,36 +1713,40 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) } } out: - mutex_unlock(&fanout_mutex); - if (err) { - kfree(po->rollover); + if (err && rollover) { + kfree(rollover); po->rollover = NULL; } + mutex_unlock(&fanout_mutex); return err; } -static void fanout_release(struct sock *sk) +/* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes + * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout. + * It is the responsibility of the caller to call fanout_release_data() and + * free the returned packet_fanout (after synchronize_net()) + */ +static struct packet_fanout *fanout_release(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f; + mutex_lock(&fanout_mutex); f = po->fanout; - if (!f) - return; + if (f) { + po->fanout = NULL; - mutex_lock(&fanout_mutex); - po->fanout = NULL; + if (atomic_dec_and_test(&f->sk_ref)) + list_del(&f->list); + else + f = NULL; - if (atomic_dec_and_test(&f->sk_ref)) { - list_del(&f->list); - dev_remove_pack(&f->prot_hook); - fanout_release_data(f); - kfree(f); + if (po->rollover) + kfree_rcu(po->rollover, rcu); } mutex_unlock(&fanout_mutex); - if (po->rollover) - kfree_rcu(po->rollover, rcu); + return f; } static bool packet_extra_vlan_len_allowed(const struct net_device *dev, @@ -2907,6 +2920,7 @@ static int packet_release(struct socket *sock) { struct sock *sk = sock->sk; struct packet_sock *po; + struct packet_fanout *f; struct net *net; union tpacket_req_u req_u; @@ -2946,9 +2960,14 @@ static int packet_release(struct socket *sock) packet_set_ring(sk, &req_u, 1, 1); } - fanout_release(sk); + f = fanout_release(sk); synchronize_net(); + + if (f) { + fanout_release_data(f); + kfree(f); + } /* * Now the socket is dead. No more input will appear. */ @@ -3900,7 +3919,6 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); - fanout_release(sk); po->ifindex = -1; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 8147e8d56eb2..f39e3e11f9aa 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1358,7 +1358,7 @@ static int c_show(struct seq_file *m, void *p) ifdebug(CACHE) seq_printf(m, "# expiry=%ld refcnt=%d flags=%lx\n", convert_to_wallclock(cp->expiry_time), - atomic_read(&cp->ref.refcount), cp->flags); + kref_read(&cp->ref), cp->flags); cache_get(cp); if (cache_check(cd, cp, NULL)) /* cache_check does a cache_put on failure */ diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 9c9db55a0c1e..7bfe1fb42add 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -490,7 +490,7 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool) svc_xprt_get(xprt); dprintk("svc: transport %p dequeued, inuse=%d\n", - xprt, atomic_read(&xprt->xpt_ref.refcount)); + xprt, kref_read(&xprt->xpt_ref)); } spin_unlock_bh(&pool->sp_lock); out: @@ -822,7 +822,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) /* XPT_DATA|XPT_DEFERRED case: */ dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", rqstp, rqstp->rq_pool->sp_id, xprt, - atomic_read(&xprt->xpt_ref.refcount)); + kref_read(&xprt->xpt_ref)); rqstp->rq_deferred = svc_deferred_dequeue(xprt); if (rqstp->rq_deferred) len = svc_deferred_recv(rqstp); @@ -980,7 +980,7 @@ static void svc_age_temp_xprts(unsigned long closure) * through, close it. */ if (!test_and_set_bit(XPT_OLD, &xprt->xpt_flags)) continue; - if (atomic_read(&xprt->xpt_ref.refcount) > 1 || + if (kref_read(&xprt->xpt_ref) > 1 || test_bit(XPT_BUSY, &xprt->xpt_flags)) continue; list_del_init(le); diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index e112da8005b5..bb8db3cb8032 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -126,13 +126,18 @@ EXPORT_SYMBOL_GPL(svc_auth_unregister); static struct hlist_head auth_domain_table[DN_HASHMAX]; static DEFINE_SPINLOCK(auth_domain_lock); +static void auth_domain_release(struct kref *kref) +{ + struct auth_domain *dom = container_of(kref, struct auth_domain, ref); + + hlist_del(&dom->hash); + dom->flavour->domain_release(dom); + spin_unlock(&auth_domain_lock); +} + void auth_domain_put(struct auth_domain *dom) { - if (atomic_dec_and_lock(&dom->ref.refcount, &auth_domain_lock)) { - hlist_del(&dom->hash); - dom->flavour->domain_release(dom); - spin_unlock(&auth_domain_lock); - } + kref_put_lock(&dom->ref, auth_domain_release, &auth_domain_lock); } EXPORT_SYMBOL_GPL(auth_domain_put); diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index ca2799af05a6..39652d390a9c 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -1201,9 +1201,9 @@ static void __svc_rdma_free(struct work_struct *work) ib_drain_qp(rdma->sc_qp); /* We should only be called from kref_put */ - if (atomic_read(&xprt->xpt_ref.refcount) != 0) + if (kref_read(&xprt->xpt_ref) != 0) pr_err("svcrdma: sc_xprt still in use? (%d)\n", - atomic_read(&xprt->xpt_ref.refcount)); + kref_read(&xprt->xpt_ref)); /* * Destroy queued, but not processed read completions. Note diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 396e204888b3..b86ee54da2d1 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -277,6 +277,11 @@ int load_bpf_file(char *path) Elf_Data *data, *data_prog, *symbols = NULL; char *shname, *shname_prog; + /* reset global variables */ + kern_version = 0; + memset(license, 0, sizeof(license)); + memset(processed_sec, 0, sizeof(processed_sec)); + if (elf_version(EV_CURRENT) == EV_NONE) return 1; @@ -328,6 +333,8 @@ int load_bpf_file(char *path) /* load programs that need map fixup (relocations) */ for (i = 1; i < ehdr.e_shnum; i++) { + if (processed_sec[i]) + continue; if (get_sec(elf, i, &ehdr, &shname, &shdr, &data)) continue; diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c index 504058631ffc..4bfcaf93fcf3 100644 --- a/samples/bpf/test_cgrp2_attach.c +++ b/samples/bpf/test_cgrp2_attach.c @@ -104,7 +104,7 @@ static int attach_filter(int cg_fd, int type, int verdict) return EXIT_FAILURE; } - ret = bpf_prog_attach(prog_fd, cg_fd, type); + ret = bpf_prog_attach(prog_fd, cg_fd, type, 0); if (ret < 0) { printf("Failed to attach prog to cgroup: '%s'\n", strerror(errno)); diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c index 6e69be37f87f..3049b1f26267 100644 --- a/samples/bpf/test_cgrp2_attach2.c +++ b/samples/bpf/test_cgrp2_attach2.c @@ -79,11 +79,12 @@ int main(int argc, char **argv) if (join_cgroup(FOO)) goto err; - if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS)) { + if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 1)) { log_err("Attaching prog to /foo"); goto err; } + printf("Attached DROP prog. This ping in cgroup /foo should fail...\n"); assert(system(PING_CMD) != 0); /* Create cgroup /foo/bar, get fd, and join it */ @@ -94,24 +95,27 @@ int main(int argc, char **argv) if (join_cgroup(BAR)) goto err; + printf("Attached DROP prog. This ping in cgroup /foo/bar should fail...\n"); assert(system(PING_CMD) != 0); - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS)) { + if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) { log_err("Attaching prog to /foo/bar"); goto err; } + printf("Attached PASS prog. This ping in cgroup /foo/bar should pass...\n"); assert(system(PING_CMD) == 0); - if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) { log_err("Detaching program from /foo/bar"); goto err; } + printf("Detached PASS from /foo/bar while DROP is attached to /foo.\n" + "This ping in cgroup /foo/bar should fail...\n"); assert(system(PING_CMD) != 0); - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS)) { + if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) { log_err("Attaching prog to /foo/bar"); goto err; } @@ -121,8 +125,60 @@ int main(int argc, char **argv) goto err; } + printf("Attached PASS from /foo/bar and detached DROP from /foo.\n" + "This ping in cgroup /foo/bar should pass...\n"); assert(system(PING_CMD) == 0); + if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) { + log_err("Attaching prog to /foo/bar"); + goto err; + } + + if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) { + errno = 0; + log_err("Unexpected success attaching prog to /foo/bar"); + goto err; + } + + if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) { + log_err("Detaching program from /foo/bar"); + goto err; + } + + if (!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) { + errno = 0; + log_err("Unexpected success in double detach from /foo"); + goto err; + } + + if (bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) { + log_err("Attaching non-overridable prog to /foo"); + goto err; + } + + if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) { + errno = 0; + log_err("Unexpected success attaching non-overridable prog to /foo/bar"); + goto err; + } + + if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) { + errno = 0; + log_err("Unexpected success attaching overridable prog to /foo/bar"); + goto err; + } + + if (!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 1)) { + errno = 0; + log_err("Unexpected success attaching overridable prog to /foo"); + goto err; + } + + if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) { + log_err("Attaching different non-overridable prog to /foo"); + goto err; + } + goto out; err: @@ -132,5 +188,9 @@ out: close(foo); close(bar); cleanup_cgroup_environment(); + if (!rc) + printf("PASS\n"); + else + printf("FAIL\n"); return rc; } diff --git a/samples/bpf/test_cgrp2_sock.c b/samples/bpf/test_cgrp2_sock.c index 0791b949cbe4..c3cfb23e23b5 100644 --- a/samples/bpf/test_cgrp2_sock.c +++ b/samples/bpf/test_cgrp2_sock.c @@ -75,7 +75,7 @@ int main(int argc, char **argv) return EXIT_FAILURE; } - ret = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_INET_SOCK_CREATE); + ret = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_INET_SOCK_CREATE, 0); if (ret < 0) { printf("Failed to attach prog to cgroup: '%s'\n", strerror(errno)); diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c index 455ef0d06e93..db036077b644 100644 --- a/samples/bpf/test_cgrp2_sock2.c +++ b/samples/bpf/test_cgrp2_sock2.c @@ -55,7 +55,7 @@ int main(int argc, char **argv) } ret = bpf_prog_attach(prog_fd[filter_id], cg_fd, - BPF_CGROUP_INET_SOCK_CREATE); + BPF_CGROUP_INET_SOCK_CREATE, 0); if (ret < 0) { printf("Failed to attach prog to cgroup: '%s'\n", strerror(errno)); diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c index fd12d7154d42..7e4cf74553ff 100644 --- a/samples/bpf/tracex5_kern.c +++ b/samples/bpf/tracex5_kern.c @@ -8,6 +8,7 @@ #include <linux/version.h> #include <uapi/linux/bpf.h> #include <uapi/linux/seccomp.h> +#include <uapi/linux/unistd.h> #include "bpf_helpers.h" #define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F diff --git a/security/apparmor/include/apparmor.h b/security/apparmor/include/apparmor.h index 5d721e990876..f067be814626 100644 --- a/security/apparmor/include/apparmor.h +++ b/security/apparmor/include/apparmor.h @@ -78,12 +78,6 @@ static inline void *kvzalloc(size_t size) return __aa_kvmalloc(size, __GFP_ZERO); } -/* returns 0 if kref not incremented */ -static inline int kref_get_not0(struct kref *kref) -{ - return atomic_inc_not_zero(&kref->refcount); -} - /** * aa_strneq - compare null terminated @str to a non null terminated substring * @str: a null terminated string diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index 52275f040a5f..46467aaa557b 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -287,7 +287,7 @@ static inline struct aa_profile *aa_get_profile(struct aa_profile *p) */ static inline struct aa_profile *aa_get_profile_not0(struct aa_profile *p) { - if (p && kref_get_not0(&p->count)) + if (p && kref_get_unless_zero(&p->count)) return p; return NULL; @@ -307,7 +307,7 @@ static inline struct aa_profile *aa_get_profile_rcu(struct aa_profile __rcu **p) rcu_read_lock(); do { c = rcu_dereference(*p); - } while (c && !kref_get_not0(&c->count)); + } while (c && !kref_get_unless_zero(&c->count)); rcu_read_unlock(); return c; diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index a2b3eb313a25..af05f8e0903e 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -84,6 +84,15 @@ struct kvm_regs { #define KVM_VGIC_V2_DIST_SIZE 0x1000 #define KVM_VGIC_V2_CPU_SIZE 0x2000 +/* Supported VGICv3 address types */ +#define KVM_VGIC_V3_ADDR_TYPE_DIST 2 +#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 +#define KVM_VGIC_ITS_ADDR_TYPE 4 + +#define KVM_VGIC_V3_DIST_SIZE SZ_64K +#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) +#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K) + #define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */ #define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */ diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index c93cf35ce379..3603b6f51b11 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -573,6 +573,10 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_SPRG9 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba) #define KVM_REG_PPC_DBSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb) +/* POWER9 registers */ +#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc) +#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ @@ -596,6 +600,7 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67) #define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68) #define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69) +#define KVM_REG_PPC_TM_XER (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a) /* PPC64 eXternal Interrupt Controller Specification */ #define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index cddd5d06e1cb..293149a1c6a1 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -105,6 +105,7 @@ #define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ #define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ +#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ @@ -188,10 +189,14 @@ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ #define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ @@ -220,11 +225,13 @@ #define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ #define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ #define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ #define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ #define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ #define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ @@ -278,8 +285,11 @@ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ +#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ +#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ @@ -310,4 +320,6 @@ #define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ #define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ +#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ + #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 37fee272618f..14458658e988 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -65,6 +65,8 @@ #define EXIT_REASON_TPR_BELOW_THRESHOLD 43 #define EXIT_REASON_APIC_ACCESS 44 #define EXIT_REASON_EOI_INDUCED 45 +#define EXIT_REASON_GDTR_IDTR 46 +#define EXIT_REASON_LDTR_TR 47 #define EXIT_REASON_EPT_VIOLATION 48 #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_INVEPT 50 @@ -113,6 +115,8 @@ { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ + { EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \ + { EXIT_REASON_LDTR_TR, "LDTR_TR" }, \ { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ { EXIT_REASON_INVEPT, "INVEPT" }, \ @@ -129,6 +133,7 @@ { EXIT_REASON_XRSTORS, "XRSTORS" } #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 +#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 #endif /* _UAPIVMX_H */ diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index 99c0ccd2f176..e279a71c650d 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -19,6 +19,16 @@ else Q=@ endif +ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4 +ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),) + quiet=silent_ +endif +else # make-3.8x +ifneq ($(filter s% -s%,$(MAKEFLAGS)),) + quiet=silent_ +endif +endif + build-dir := $(srctree)/tools/build # Define $(fixdep) for dep-cmd function diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h new file mode 100644 index 000000000000..48af2f10a42d --- /dev/null +++ b/tools/include/linux/compiler-gcc.h @@ -0,0 +1,14 @@ +#ifndef _TOOLS_LINUX_COMPILER_H_ +#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead." +#endif + +/* + * Common definitions for all gcc versions go here. + */ +#define GCC_VERSION (__GNUC__ * 10000 \ + + __GNUC_MINOR__ * 100 \ + + __GNUC_PATCHLEVEL__) + +#if GCC_VERSION >= 70000 && !defined(__CHECKER__) +# define __fallthrough __attribute__ ((fallthrough)) +#endif diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index e33fc1df3935..6326ede9aece 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -1,6 +1,10 @@ #ifndef _TOOLS_LINUX_COMPILER_H_ #define _TOOLS_LINUX_COMPILER_H_ +#ifdef __GNUC__ +#include <linux/compiler-gcc.h> +#endif + /* Optimization barrier */ /* The "volatile" is due to gcc bugs */ #define barrier() __asm__ __volatile__("": : :"memory") @@ -126,4 +130,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #define WRITE_ONCE(x, val) \ ({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; }) + +#ifndef __fallthrough +# define __fallthrough +#endif + #endif /* _TOOLS_LINUX_COMPILER_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0eb0e87dbe9f..d2b0ac799d03 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -116,6 +116,12 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command + * to the given target_fd cgroup the descendent cgroup will be able to + * override effective bpf program that was inherited from this cgroup + */ +#define BPF_F_ALLOW_OVERRIDE (1U << 0) + #define BPF_PSEUDO_MAP_FD 1 /* flags for BPF_MAP_UPDATE_ELEM command */ @@ -171,6 +177,7 @@ union bpf_attr { __u32 target_fd; /* container object to attach to */ __u32 attach_bpf_fd; /* eBPF program to attach */ __u32 attach_type; + __u32 attach_flags; }; } __attribute__((aligned(8))); diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile index adba83b325d5..eb6e0b36bfc1 100644 --- a/tools/lib/api/Makefile +++ b/tools/lib/api/Makefile @@ -17,7 +17,13 @@ MAKEFLAGS += --no-print-directory LIBFILE = $(OUTPUT)libapi.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC + +ifeq ($(CC), clang) + CFLAGS += -O3 +else + CFLAGS += -O6 +endif # Treat warnings as errors unless directed not to ifneq ($(WERROR),0) diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index f99f49e4a31e..4b6bfc43cccf 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -38,6 +38,10 @@ #define HUGETLBFS_MAGIC 0x958458f6 #endif +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + static const char * const sysfs__fs_known_mountpoints[] = { "/sys", 0, @@ -75,6 +79,11 @@ static const char * const hugetlbfs__known_mountpoints[] = { 0, }; +static const char * const bpf_fs__known_mountpoints[] = { + "/sys/fs/bpf", + 0, +}; + struct fs { const char *name; const char * const *mounts; @@ -89,6 +98,7 @@ enum { FS__DEBUGFS = 2, FS__TRACEFS = 3, FS__HUGETLBFS = 4, + FS__BPF_FS = 5, }; #ifndef TRACEFS_MAGIC @@ -121,6 +131,11 @@ static struct fs fs__entries[] = { .mounts = hugetlbfs__known_mountpoints, .magic = HUGETLBFS_MAGIC, }, + [FS__BPF_FS] = { + .name = "bpf", + .mounts = bpf_fs__known_mountpoints, + .magic = BPF_FS_MAGIC, + }, }; static bool fs__read_mounts(struct fs *fs) @@ -280,6 +295,7 @@ FS(procfs, FS__PROCFS); FS(debugfs, FS__DEBUGFS); FS(tracefs, FS__TRACEFS); FS(hugetlbfs, FS__HUGETLBFS); +FS(bpf_fs, FS__BPF_FS); int filename__read_int(const char *filename, int *value) { diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h index a63269f5d20c..6b332dc74498 100644 --- a/tools/lib/api/fs/fs.h +++ b/tools/lib/api/fs/fs.h @@ -22,6 +22,7 @@ FS(procfs) FS(debugfs) FS(tracefs) FS(hugetlbfs) +FS(bpf_fs) #undef FS diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c index 251b7c342a87..3e606b9c443e 100644 --- a/tools/lib/api/fs/tracing_path.c +++ b/tools/lib/api/fs/tracing_path.c @@ -86,9 +86,13 @@ void put_tracing_file(char *file) free(file); } -static int strerror_open(int err, char *buf, size_t size, const char *filename) +int tracing_path__strerror_open_tp(int err, char *buf, size_t size, + const char *sys, const char *name) { char sbuf[128]; + char filename[PATH_MAX]; + + snprintf(filename, PATH_MAX, "%s/%s", sys, name ?: "*"); switch (err) { case ENOENT: @@ -99,10 +103,19 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename) * - jirka */ if (debugfs__configured() || tracefs__configured()) { - snprintf(buf, size, - "Error:\tFile %s/%s not found.\n" - "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n", - tracing_events_path, filename); + /* sdt markers */ + if (!strncmp(filename, "sdt_", 4)) { + snprintf(buf, size, + "Error:\tFile %s/%s not found.\n" + "Hint:\tSDT event cannot be directly recorded on.\n" + "\tPlease first use 'perf probe %s:%s' before recording it.\n", + tracing_events_path, filename, sys, name); + } else { + snprintf(buf, size, + "Error:\tFile %s/%s not found.\n" + "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n", + tracing_events_path, filename); + } break; } snprintf(buf, size, "%s", @@ -125,12 +138,3 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename) return 0; } - -int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name) -{ - char path[PATH_MAX]; - - snprintf(path, PATH_MAX, "%s/%s", sys, name ?: "*"); - - return strerror_open(err, buf, size, path); -} diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 3ddb58a36d3c..ae752fa4eaa7 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -168,7 +168,8 @@ int bpf_obj_get(const char *pathname) return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr)); } -int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type) +int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, + unsigned int flags) { union bpf_attr attr; @@ -176,6 +177,7 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type) attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; + attr.attach_flags = flags; return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index a2f9853dd882..44fb7c5f8ae6 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -22,6 +22,7 @@ #define __BPF_BPF_H #include <linux/bpf.h> +#include <stddef.h> int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags); @@ -41,7 +42,8 @@ int bpf_map_delete_elem(int fd, void *key); int bpf_map_get_next_key(int fd, void *key, void *next_key); int bpf_obj_pin(int fd, const char *pathname); int bpf_obj_get(const char *pathname); -int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type); +int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, + unsigned int flags); int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 84e6b35da4bd..ac6eb863b2a4 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4,6 +4,7 @@ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> * Copyright (C) 2015 Huawei Inc. + * Copyright (C) 2017 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public @@ -22,15 +23,21 @@ #include <stdlib.h> #include <stdio.h> #include <stdarg.h> +#include <libgen.h> #include <inttypes.h> #include <string.h> #include <unistd.h> #include <fcntl.h> #include <errno.h> #include <asm/unistd.h> +#include <linux/err.h> #include <linux/kernel.h> #include <linux/bpf.h> #include <linux/list.h> +#include <linux/limits.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/vfs.h> #include <libelf.h> #include <gelf.h> @@ -41,6 +48,10 @@ #define EM_BPF 247 #endif +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + #define __printf(a, b) __attribute__((format(printf, a, b))) __printf(1, 2) @@ -779,7 +790,7 @@ static int bpf_program__collect_reloc(struct bpf_program *prog, size_t nr_maps, GElf_Shdr *shdr, Elf_Data *data, Elf_Data *symbols, - int maps_shndx) + int maps_shndx, struct bpf_map *maps) { int i, nrels; @@ -829,7 +840,15 @@ bpf_program__collect_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__RELOC; } - map_idx = sym.st_value / sizeof(struct bpf_map_def); + /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */ + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + if (maps[map_idx].offset == sym.st_value) { + pr_debug("relocation: find map %zd (%s) for insn %u\n", + map_idx, maps[map_idx].name, insn_idx); + break; + } + } + if (map_idx >= nr_maps) { pr_warning("bpf relocation: map_idx %d large than %d\n", (int)map_idx, (int)nr_maps - 1); @@ -953,7 +972,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) err = bpf_program__collect_reloc(prog, nr_maps, shdr, data, obj->efile.symbols, - obj->efile.maps_shndx); + obj->efile.maps_shndx, + obj->maps); if (err) return err; } @@ -1227,6 +1247,191 @@ out: return err; } +static int check_path(const char *path) +{ + struct statfs st_fs; + char *dname, *dir; + int err = 0; + + if (path == NULL) + return -EINVAL; + + dname = strdup(path); + if (dname == NULL) + return -ENOMEM; + + dir = dirname(dname); + if (statfs(dir, &st_fs)) { + pr_warning("failed to statfs %s: %s\n", dir, strerror(errno)); + err = -errno; + } + free(dname); + + if (!err && st_fs.f_type != BPF_FS_MAGIC) { + pr_warning("specified path %s is not on BPF FS\n", path); + err = -EINVAL; + } + + return err; +} + +int bpf_program__pin_instance(struct bpf_program *prog, const char *path, + int instance) +{ + int err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warning("invalid program pointer\n"); + return -EINVAL; + } + + if (instance < 0 || instance >= prog->instances.nr) { + pr_warning("invalid prog instance %d of prog %s (max %d)\n", + instance, prog->section_name, prog->instances.nr); + return -EINVAL; + } + + if (bpf_obj_pin(prog->instances.fds[instance], path)) { + pr_warning("failed to pin program: %s\n", strerror(errno)); + return -errno; + } + pr_debug("pinned program '%s'\n", path); + + return 0; +} + +static int make_dir(const char *path) +{ + int err = 0; + + if (mkdir(path, 0700) && errno != EEXIST) + err = -errno; + + if (err) + pr_warning("failed to mkdir %s: %s\n", path, strerror(-err)); + return err; +} + +int bpf_program__pin(struct bpf_program *prog, const char *path) +{ + int i, err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warning("invalid program pointer\n"); + return -EINVAL; + } + + if (prog->instances.nr <= 0) { + pr_warning("no instances of prog %s to pin\n", + prog->section_name); + return -EINVAL; + } + + err = make_dir(path); + if (err) + return err; + + for (i = 0; i < prog->instances.nr; i++) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%d", path, i); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_program__pin_instance(prog, buf, i); + if (err) + return err; + } + + return 0; +} + +int bpf_map__pin(struct bpf_map *map, const char *path) +{ + int err; + + err = check_path(path); + if (err) + return err; + + if (map == NULL) { + pr_warning("invalid map pointer\n"); + return -EINVAL; + } + + if (bpf_obj_pin(map->fd, path)) { + pr_warning("failed to pin map: %s\n", strerror(errno)); + return -errno; + } + + pr_debug("pinned map '%s'\n", path); + return 0; +} + +int bpf_object__pin(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + struct bpf_map *map; + int err; + + if (!obj) + return -ENOENT; + + if (!obj->loaded) { + pr_warning("object not yet loaded; load it first\n"); + return -ENOENT; + } + + err = make_dir(path); + if (err) + return err; + + bpf_map__for_each(map, obj) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + bpf_map__name(map)); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_map__pin(map, buf); + if (err) + return err; + } + + bpf_object__for_each_program(prog, obj) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + prog->section_name); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_program__pin(prog, buf); + if (err) + return err; + } + + return 0; +} + void bpf_object__close(struct bpf_object *obj) { size_t i; @@ -1419,37 +1624,33 @@ static void bpf_program__set_type(struct bpf_program *prog, prog->type = type; } -int bpf_program__set_tracepoint(struct bpf_program *prog) -{ - if (!prog) - return -EINVAL; - bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT); - return 0; -} - -int bpf_program__set_kprobe(struct bpf_program *prog) -{ - if (!prog) - return -EINVAL; - bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE); - return 0; -} - static bool bpf_program__is_type(struct bpf_program *prog, enum bpf_prog_type type) { return prog ? (prog->type == type) : false; } -bool bpf_program__is_tracepoint(struct bpf_program *prog) -{ - return bpf_program__is_type(prog, BPF_PROG_TYPE_TRACEPOINT); -} - -bool bpf_program__is_kprobe(struct bpf_program *prog) -{ - return bpf_program__is_type(prog, BPF_PROG_TYPE_KPROBE); -} +#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ +int bpf_program__set_##NAME(struct bpf_program *prog) \ +{ \ + if (!prog) \ + return -EINVAL; \ + bpf_program__set_type(prog, TYPE); \ + return 0; \ +} \ + \ +bool bpf_program__is_##NAME(struct bpf_program *prog) \ +{ \ + return bpf_program__is_type(prog, TYPE); \ +} \ + +BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER); +BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); +BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS); +BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT); +BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); +BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); +BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); int bpf_map__fd(struct bpf_map *map) { @@ -1537,3 +1738,10 @@ bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) } return ERR_PTR(-ENOENT); } + +long libbpf_get_error(const void *ptr) +{ + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + return 0; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index a5a8b86a06fe..b30394f9947a 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -22,8 +22,8 @@ #define __BPF_LIBBPF_H #include <stdio.h> +#include <stdint.h> #include <stdbool.h> -#include <linux/err.h> #include <sys/types.h> // for size_t enum libbpf_errno { @@ -65,6 +65,7 @@ struct bpf_object *bpf_object__open(const char *path); struct bpf_object *bpf_object__open_buffer(void *obj_buf, size_t obj_buf_sz, const char *name); +int bpf_object__pin(struct bpf_object *object, const char *path); void bpf_object__close(struct bpf_object *object); /* Load/unload object into/from kernel */ @@ -106,6 +107,9 @@ void *bpf_program__priv(struct bpf_program *prog); const char *bpf_program__title(struct bpf_program *prog, bool needs_copy); int bpf_program__fd(struct bpf_program *prog); +int bpf_program__pin_instance(struct bpf_program *prog, const char *path, + int instance); +int bpf_program__pin(struct bpf_program *prog, const char *path); struct bpf_insn; @@ -174,11 +178,21 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n); /* * Adjust type of bpf program. Default is kprobe. */ +int bpf_program__set_socket_filter(struct bpf_program *prog); int bpf_program__set_tracepoint(struct bpf_program *prog); int bpf_program__set_kprobe(struct bpf_program *prog); +int bpf_program__set_sched_cls(struct bpf_program *prog); +int bpf_program__set_sched_act(struct bpf_program *prog); +int bpf_program__set_xdp(struct bpf_program *prog); +int bpf_program__set_perf_event(struct bpf_program *prog); +bool bpf_program__is_socket_filter(struct bpf_program *prog); bool bpf_program__is_tracepoint(struct bpf_program *prog); bool bpf_program__is_kprobe(struct bpf_program *prog); +bool bpf_program__is_sched_cls(struct bpf_program *prog); +bool bpf_program__is_sched_act(struct bpf_program *prog); +bool bpf_program__is_xdp(struct bpf_program *prog); +bool bpf_program__is_perf_event(struct bpf_program *prog); /* * We don't need __attribute__((packed)) now since it is @@ -223,5 +237,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv); void *bpf_map__priv(struct bpf_map *map); +int bpf_map__pin(struct bpf_map *map, const char *path); + +long libbpf_get_error(const void *ptr); #endif diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index 3f8cc44a0dbd..3d1c3b5b5150 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -19,7 +19,13 @@ MAKEFLAGS += --no-print-directory LIBFILE = $(OUTPUT)libsubcmd.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC + +ifeq ($(CC), clang) + CFLAGS += -O3 +else + CFLAGS += -O6 +endif # Treat warnings as errors unless directed not to ifneq ($(WERROR),0) diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c index 8aad81151d50..6bc24025d054 100644 --- a/tools/lib/subcmd/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -270,6 +270,8 @@ static int get_value(struct parse_opt_ctx_t *p, } if (get_arg(p, opt, flags, &arg)) return -1; + if (arg[0] == '-') + return opterror(opt, "expects an unsigned numerical value", flags); *(unsigned int *)opt->value = strtol(arg, (char **)&s, 10); if (*s) return opterror(opt, "expects a numerical value", flags); @@ -302,6 +304,8 @@ static int get_value(struct parse_opt_ctx_t *p, } if (get_arg(p, opt, flags, &arg)) return -1; + if (arg[0] == '-') + return opterror(opt, "expects an unsigned numerical value", flags); *(u64 *)opt->value = strtoull(arg, (char **)&s, 10); if (*s) return opterror(opt, "expects a numerical value", flags); diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h index 11c3be3bcce7..f054ca1b899d 100644 --- a/tools/lib/subcmd/parse-options.h +++ b/tools/lib/subcmd/parse-options.h @@ -1,6 +1,7 @@ #ifndef __SUBCMD_PARSE_OPTIONS_H #define __SUBCMD_PARSE_OPTIONS_H +#include <linux/kernel.h> #include <stdbool.h> #include <stdint.h> @@ -132,32 +133,32 @@ struct option { #define OPT_UINTEGER(s, l, v, h) { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) } #define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) } #define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) } -#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) } +#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) } #define OPT_STRING_OPTARG(s, l, v, a, h, d) \ { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \ - .value = check_vtype(v, const char **), (a), .help = (h), \ + .value = check_vtype(v, const char **), .argh =(a), .help = (h), \ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) } #define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \ { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \ - .value = check_vtype(v, const char **), (a), .help = (h), \ + .value = check_vtype(v, const char **), .argh = (a), .help = (h), \ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \ .set = check_vtype(os, bool *)} -#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY} +#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h), .flags = PARSE_OPT_NOEMPTY} #define OPT_DATE(s, l, v, h) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb } #define OPT_CALLBACK(s, l, v, a, h, f) \ - { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) } + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f) } #define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \ - { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG } + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG } #define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \ - { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT } + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT } #define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\ - .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\ + .value = (v), .arg = (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\ .flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG} #define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \ - .value = (v), (a), .help = (h), .callback = (f), \ + .value = (v), .argh = (a), .help = (h), .callback = (f), \ .flags = PARSE_OPT_OPTARG, .data = (d) } /* parse_options() will filter out the processed options and leave the diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 2616c66e10c1..47076b15eebe 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -257,10 +257,16 @@ define do_install_plugins endef define do_generate_dynamic_list_file - (echo '{'; \ - $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u; \ - echo '};'; \ - ) > $2 + symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \ + xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\ + if [ "$$symbol_type" = "U W w" ];then \ + (echo '{'; \ + $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ + echo '};'; \ + ) > $2; \ + else \ + (echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\ + fi endef install_lib: all_cmd install_plugins diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c index 65984f1c2974..c94e3641b046 100644 --- a/tools/lib/traceevent/kbuffer-parse.c +++ b/tools/lib/traceevent/kbuffer-parse.c @@ -315,6 +315,7 @@ static unsigned int old_update_pointers(struct kbuffer *kbuf) extend += delta; delta = extend; ptr += 4; + length = 0; break; case OLD_RINGBUF_TYPE_TIME_STAMP: diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c index a00ec190821a..42dbf73758f3 100644 --- a/tools/lib/traceevent/plugin_function.c +++ b/tools/lib/traceevent/plugin_function.c @@ -130,7 +130,7 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record, unsigned long long pfunction; const char *func; const char *parent; - int index; + int index = 0; if (pevent_get_field_val(s, event, "ip", record, &function, 1)) return trace_seq_putc(s, '!'); diff --git a/tools/perf/Build b/tools/perf/Build index b12d5d1666e3..9b79f8d7db50 100644 --- a/tools/perf/Build +++ b/tools/perf/Build @@ -3,10 +3,12 @@ perf-y += builtin-annotate.o perf-y += builtin-config.o perf-y += builtin-diff.o perf-y += builtin-evlist.o +perf-y += builtin-ftrace.o perf-y += builtin-help.o perf-y += builtin-sched.o perf-y += builtin-buildid-list.o perf-y += builtin-buildid-cache.o +perf-y += builtin-kallsyms.o perf-y += builtin-list.o perf-y += builtin-record.o perf-y += builtin-report.o @@ -39,8 +41,7 @@ CFLAGS_builtin-help.o += $(paths) CFLAGS_builtin-timechart.o += $(paths) CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" \ -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" \ - -DPREFIX="BUILD_STR($(prefix_SQ))" \ - -include $(OUTPUT)PERF-VERSION-FILE + -DPREFIX="BUILD_STR($(prefix_SQ))" CFLAGS_builtin-trace.o += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))" CFLAGS_builtin-report.o += -DTIPDIR="BUILD_STR($(tipdir_SQ))" CFLAGS_builtin-report.o += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)" diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 3f06730c7f47..2da07e51e119 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -248,7 +248,7 @@ output fields set for caheline offsets output: Code address, Code symbol, Shared Object, Source line dso - coalesced by shared object -By default the coalescing is setup with 'pid,tid,iaddr'. +By default the coalescing is setup with 'pid,iaddr'. STDIO OUTPUT ------------ diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 9365b75fd04f..5b4fff3adc4b 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -498,6 +498,18 @@ record.*:: But if this option is 'no-cache', it will not update the build-id cache. 'skip' skips post-processing and does not update the cache. +diff.*:: + diff.order:: + This option sets the number of columns to sort the result. + The default is 0, which means sorting by baseline. + Setting it to 1 will sort the result by delta (or other + compute method selected). + + diff.compute:: + This options sets the method for computing the diff result. + Possible values are 'delta', 'delta-abs', 'ratio' and + 'wdiff'. Default is 'delta'. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index 3e9490b9c533..66dbe3dee74b 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -86,8 +86,9 @@ OPTIONS -c:: --compute:: - Differential computation selection - delta,ratio,wdiff (default is delta). - See COMPARISON METHODS section for more info. + Differential computation selection - delta, ratio, wdiff, delta-abs + (default is delta-abs). Default can be changed using diff.compute + config option. See COMPARISON METHODS section for more info. -p:: --period:: @@ -99,7 +100,11 @@ OPTIONS -o:: --order:: - Specify compute sorting column number. + Specify compute sorting column number. 0 means sorting by baseline + overhead and 1 (default) means sorting by computed value of column 1 + (data from the first file other base baseline). Values more than 1 + can be used only if enough data files are provided. + The default value can be set using the diff.order config option. --percentage:: Determine how to display the overhead percentage of filtered entries. @@ -181,6 +186,10 @@ with: relative to how entries are filtered. Use --percentage=absolute to prevent such fluctuation. +delta-abs +~~~~~~~~~ +Same as 'delta` method, but sort the result with the absolute values. + ratio ~~~~~ If specified the 'Ratio' column is displayed with value 'r' computed as: diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt new file mode 100644 index 000000000000..2d96de6132a9 --- /dev/null +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -0,0 +1,36 @@ +perf-ftrace(1) +============= + +NAME +---- +perf-ftrace - simple wrapper for kernel's ftrace functionality + + +SYNOPSIS +-------- +[verse] +'perf ftrace' <command> + +DESCRIPTION +----------- +The 'perf ftrace' command is a simple wrapper of kernel's ftrace +functionality. It only supports single thread tracing currently and +just reads trace_pipe in text and then write it to stdout. + +The following options apply to perf ftrace. + +OPTIONS +------- + +-t:: +--tracer=:: + Tracer to use: function_graph or function. + +-v:: +--verbose=:: + Verbosity level. + + +SEE ALSO +-------- +linkperf:perf-record[1], linkperf:perf-trace[1] diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt new file mode 100644 index 000000000000..954ea9e21236 --- /dev/null +++ b/tools/perf/Documentation/perf-kallsyms.txt @@ -0,0 +1,24 @@ +perf-kallsyms(1) +============== + +NAME +---- +perf-kallsyms - Searches running kernel for symbols + +SYNOPSIS +-------- +[verse] +'perf kallsyms <options> symbol_name[,symbol_name...]' + +DESCRIPTION +----------- +This command searches the running kernel kallsyms file for the given symbol(s) +and prints information about it, including the DSO, the kallsyms begin/end +addresses and the addresses in the ELF kallsyms symbol table (for symbols in +modules). + +OPTIONS +------- +-v:: +--verbose=:: + Increase verbosity level, showing details about symbol table loading, etc. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 5054d9147f0f..27256bc68eda 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -421,9 +421,19 @@ Configure all used events to run in user space. --timestamp-filename Append timestamp to output file name. ---switch-output:: +--switch-output[=mode]:: Generate multiple perf.data files, timestamp prefixed, switching to a new one -when receiving a SIGUSR2. +based on 'mode' value: + "signal" - when receiving a SIGUSR2 (default value) or + <size> - when reaching the size threshold, size is expected to + be a number with appended unit character - B/K/M/G + <time> - when reaching the time threshold, size is expected to + be a number with appended unit character - s/m/h/d + + Note: the precision of the size threshold hugely depends + on your configuration - the number and size of your ring + buffers (-m). It is generally more precise for higher sizes + (like >5M), for lower values expect different sizes. A possible use case is to, given an external event, slice the perf.data file that gets then processed, possibly via a perf script, to decide if that diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index 76173969ab80..d33deddb0146 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -143,6 +143,8 @@ OPTIONS for 'perf sched timehist' stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. +--state:: + Show task state when it switched out. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 5dc5c6a09ac4..4ed5f239ba7d 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -36,7 +36,7 @@ There are several variants of perf script: 'perf script report <script> [args]' to run and display the results of <script>. <script> is the name displayed in the output of 'perf - trace --list' i.e. the actual script name minus any language + script --list' i.e. the actual script name minus any language extension. The perf.data output from a previous run of 'perf script record <script>' is used and should be present for this command to succeed. [args] refers to the (mainly optional) args expected by @@ -76,7 +76,7 @@ OPTIONS Any command you can specify in a shell. -D:: ---dump-raw-script=:: +--dump-raw-trace=:: Display verbose dump of the trace data. -L:: diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 781b019751a4..afd728672b6f 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -35,7 +35,10 @@ OPTIONS -e:: --expr:: - List of syscalls to show, currently only syscall names. +--event:: + List of syscalls and other perf events (tracepoints, HW cache events, + etc) to show. + See 'perf list' for a complete list of events. Prefixing with ! shows all syscalls but the ones specified. You may need to escape it. @@ -135,9 +138,6 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --kernel-syscall-graph:: Show the kernel callchains on the syscall exit path. ---event:: - Trace other events, see 'perf list' for a complete list. - --max-stack:: Set the stack depth limit when parsing the callchain, anything beyond the specified depth will be ignored. Note that at this point diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index a511e5f31e36..8672f835ae4e 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -61,6 +61,7 @@ tools/include/asm-generic/bitops.h tools/include/linux/atomic.h tools/include/linux/bitops.h tools/include/linux/compiler.h +tools/include/linux/compiler-gcc.h tools/include/linux/coresight-pmu.h tools/include/linux/filter.h tools/include/linux/hash.h diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 76c84f0eec52..2b941efadb04 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -144,8 +144,12 @@ ifndef DEBUG endif ifeq ($(DEBUG),0) +ifeq ($(CC), clang) + CFLAGS += -O3 +else CFLAGS += -O6 endif +endif ifdef PARSER_DEBUG PARSER_DEBUG_BISON := -t @@ -291,8 +295,10 @@ else endif endif ifneq ($(feature-dwarf), 1) - msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); - NO_DWARF := 1 + ifndef NO_DWARF + msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); + NO_DWARF := 1 + endif else ifneq ($(feature-dwarf_getlocations), 1) msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157); diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 8bb16aa9d661..4da19b6ba94a 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -661,6 +661,7 @@ ifndef NO_PERF_READ_VDSOX32 endif ifndef NO_JVMTI $(call QUIET_INSTALL, $(LIBJVMTI)) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \ $(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)'; endif $(call QUIET_INSTALL, libexec) \ diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 18b13518d8d8..eebe1ec9d2ee 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -2,3 +2,4 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 endif PERF_HAVE_JITDUMP := 1 +PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h index 26759363f921..36e375f5a211 100644 --- a/tools/perf/arch/arm64/include/dwarf-regs-table.h +++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h @@ -2,12 +2,12 @@ /* This is included in perf/util/dwarf-regs.c */ static const char * const aarch64_regstr_tbl[] = { - "%r0", "%r1", "%r2", "%r3", "%r4", - "%r5", "%r6", "%r7", "%r8", "%r9", - "%r10", "%r11", "%r12", "%r13", "%r14", - "%r15", "%r16", "%r17", "%r18", "%r19", - "%r20", "%r21", "%r22", "%r23", "%r24", - "%r25", "%r26", "%r27", "%r28", "%r29", + "%x0", "%x1", "%x2", "%x3", "%x4", + "%x5", "%x6", "%x7", "%x8", "%x9", + "%x10", "%x11", "%x12", "%x13", "%x14", + "%x15", "%x16", "%x17", "%x18", "%x19", + "%x20", "%x21", "%x22", "%x23", "%x24", + "%x25", "%x26", "%x27", "%x28", "%x29", "%lr", "%sp", }; #endif diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c index d49efeb8172e..068b6189157b 100644 --- a/tools/perf/arch/arm64/util/dwarf-regs.c +++ b/tools/perf/arch/arm64/util/dwarf-regs.c @@ -10,17 +10,20 @@ #include <stddef.h> #include <dwarf-regs.h> +#include <linux/ptrace.h> /* for struct user_pt_regs */ +#include "util.h" struct pt_regs_dwarfnum { const char *name; unsigned int dwarfnum; }; -#define STR(s) #s #define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num} #define GPR_DWARFNUM_NAME(num) \ {.name = STR(%x##num), .dwarfnum = num} #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0} +#define DWARFNUM2OFFSET(index) \ + (index * sizeof((struct user_pt_regs *)0)->regs[0]) /* * Reference: @@ -78,3 +81,13 @@ const char *get_arch_regstr(unsigned int n) return roff->name; return NULL; } + +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_dwarfnum *roff; + + for (roff = regdwarfnum_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return DWARFNUM2OFFSET(roff->dwarfnum); + return -EINVAL; +} diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index bfbb6b5f609c..da04b8c5568a 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -130,8 +130,6 @@ int bench_futex_hash(int argc, const char **argv, } ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nsecs = futexbench_sanitize_numeric(nsecs); - nfutexes = futexbench_sanitize_numeric(nfutexes); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; @@ -139,8 +137,6 @@ int bench_futex_hash(int argc, const char **argv, if (!nthreads) /* default to the number of CPUs */ nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6d9d6c40a916..91877777ec6e 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -152,7 +152,6 @@ int bench_futex_lock_pi(int argc, const char **argv, goto err; ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nsecs = futexbench_sanitize_numeric(nsecs); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; @@ -160,8 +159,6 @@ int bench_futex_lock_pi(int argc, const char **argv, if (!nthreads) nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index fd4ee95b689a..2b9705a8734c 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -128,8 +128,6 @@ int bench_futex_requeue(int argc, const char **argv, if (!nthreads) nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index beaa6c142477..2c8fa67ad537 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -217,12 +217,8 @@ int bench_futex_wake_parallel(int argc, const char **argv, sigaction(SIGINT, &act, NULL); ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nwaking_threads = futexbench_sanitize_numeric(nwaking_threads); - if (!nblocked_threads) nblocked_threads = ncpus; - else - nblocked_threads = futexbench_sanitize_numeric(nblocked_threads); /* some sanity checks */ if (nwaking_threads > nblocked_threads || !nwaking_threads) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index 46efcb98b5a4..e246b1b8388a 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -129,7 +129,6 @@ int bench_futex_wake(int argc, const char **argv, } ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nwakes = futexbench_sanitize_numeric(nwakes); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; @@ -137,8 +136,6 @@ int bench_futex_wake(int argc, const char **argv, if (!nthreads) nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h index ba7c735c0c62..b2e06d1190d0 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -7,7 +7,6 @@ #ifndef _FUTEX_H #define _FUTEX_H -#include <stdlib.h> #include <unistd.h> #include <sys/syscall.h> #include <sys/types.h> @@ -100,7 +99,4 @@ static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr, } #endif -/* User input sanitation */ -#define futexbench_sanitize_numeric(__n) abs((__n)) - #endif /* _FUTEX_H */ diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 8efe904e486b..3083fc36282b 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -43,6 +43,7 @@ /* * Debug printf: */ +#undef dprintf #define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0) struct thread_data { @@ -1573,13 +1574,13 @@ static int __bench_numa(const char *name) "GB/sec,", "total-speed", "GB/sec total speed"); if (g->p.show_details >= 2) { - char tname[32]; + char tname[14 + 2 * 10 + 1]; struct thread_data *td; for (p = 0; p < g->p.nr_proc; p++) { for (t = 0; t < g->p.nr_threads; t++) { - memset(tname, 0, 32); + memset(tname, 0, sizeof(tname)); td = g->threads + p*g->p.nr_threads + t; - snprintf(tname, 32, "process%d:thread%d", p, t); + snprintf(tname, sizeof(tname), "process%d:thread%d", p, t); print_res(tname, td->speed_gbs, "GB/sec", "thread-speed", "GB/sec/thread speed"); print_res(tname, td->system_time_ns / NSEC_PER_SEC, diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index f8ca7a4ebabc..e2b21723bbf8 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -58,7 +58,7 @@ struct c2c_hist_entry { struct hist_entry he; }; -static char const *coalesce_default = "pid,tid,iaddr"; +static char const *coalesce_default = "pid,iaddr"; struct perf_c2c { struct perf_tool tool; @@ -2476,6 +2476,7 @@ static int build_cl_output(char *cl_sort, bool no_source) "mean_rmt," "mean_lcl," "mean_load," + "tot_recs," "cpucnt,", add_sym ? "symbol," : "", add_dso ? "dso," : "", diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 933aeec46f4a..70a289347591 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -17,6 +17,7 @@ #include "util/symbol.h" #include "util/util.h" #include "util/data.h" +#include "util/config.h" #include <stdlib.h> #include <math.h> @@ -30,6 +31,7 @@ enum { PERF_HPP_DIFF__RATIO, PERF_HPP_DIFF__WEIGHTED_DIFF, PERF_HPP_DIFF__FORMULA, + PERF_HPP_DIFF__DELTA_ABS, PERF_HPP_DIFF__MAX_INDEX }; @@ -64,7 +66,7 @@ static bool force; static bool show_period; static bool show_formula; static bool show_baseline_only; -static unsigned int sort_compute; +static unsigned int sort_compute = 1; static s64 compute_wdiff_w1; static s64 compute_wdiff_w2; @@ -73,19 +75,22 @@ enum { COMPUTE_DELTA, COMPUTE_RATIO, COMPUTE_WEIGHTED_DIFF, + COMPUTE_DELTA_ABS, COMPUTE_MAX, }; const char *compute_names[COMPUTE_MAX] = { [COMPUTE_DELTA] = "delta", + [COMPUTE_DELTA_ABS] = "delta-abs", [COMPUTE_RATIO] = "ratio", [COMPUTE_WEIGHTED_DIFF] = "wdiff", }; -static int compute; +static int compute = COMPUTE_DELTA_ABS; static int compute_2_hpp[COMPUTE_MAX] = { [COMPUTE_DELTA] = PERF_HPP_DIFF__DELTA, + [COMPUTE_DELTA_ABS] = PERF_HPP_DIFF__DELTA_ABS, [COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO, [COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF, }; @@ -111,6 +116,10 @@ static struct header_column { .name = "Delta", .width = 7, }, + [PERF_HPP_DIFF__DELTA_ABS] = { + .name = "Delta Abs", + .width = 7, + }, [PERF_HPP_DIFF__RATIO] = { .name = "Ratio", .width = 14, @@ -298,6 +307,7 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair, { switch (compute) { case COMPUTE_DELTA: + case COMPUTE_DELTA_ABS: return formula_delta(he, pair, buf, size); case COMPUTE_RATIO: return formula_ratio(he, pair, buf, size); @@ -461,6 +471,7 @@ static void hists__precompute(struct hists *hists) switch (compute) { case COMPUTE_DELTA: + case COMPUTE_DELTA_ABS: compute_delta(he, pair); break; case COMPUTE_RATIO: @@ -498,6 +509,13 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, return cmp_doubles(l, r); } + case COMPUTE_DELTA_ABS: + { + double l = fabs(left->diff.period_ratio_delta); + double r = fabs(right->diff.period_ratio_delta); + + return cmp_doubles(l, r); + } case COMPUTE_RATIO: { double l = left->diff.period_ratio; @@ -564,7 +582,7 @@ hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right, if (!p_left || !p_right) return p_left ? -1 : 1; - if (c != COMPUTE_DELTA) { + if (c != COMPUTE_DELTA && c != COMPUTE_DELTA_ABS) { /* * The delta can be computed without the baseline, but * others are not. Put those entries which have no @@ -607,6 +625,15 @@ hist_entry__cmp_delta(struct perf_hpp_fmt *fmt, } static int64_t +hist_entry__cmp_delta_abs(struct perf_hpp_fmt *fmt, + struct hist_entry *left, struct hist_entry *right) +{ + struct data__file *d = fmt_to_data_file(fmt); + + return hist_entry__cmp_compute(right, left, COMPUTE_DELTA_ABS, d->idx); +} + +static int64_t hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt, struct hist_entry *left, struct hist_entry *right) { @@ -633,6 +660,14 @@ hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused, } static int64_t +hist_entry__cmp_delta_abs_idx(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA_ABS, + sort_compute); +} + +static int64_t hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused, struct hist_entry *left, struct hist_entry *right) { @@ -775,7 +810,7 @@ static const struct option options[] = { OPT_BOOLEAN('b', "baseline-only", &show_baseline_only, "Show only items with match in baseline"), OPT_CALLBACK('c', "compute", &compute, - "delta,ratio,wdiff:w1,w2 (default delta)", + "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)", "Entries differential computation selection", setup_compute), OPT_BOOLEAN('p', "period", &show_period, @@ -945,6 +980,7 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair, switch (idx) { case PERF_HPP_DIFF__DELTA: + case PERF_HPP_DIFF__DELTA_ABS: if (pair->diff.computed) diff = pair->diff.period_ratio_delta; else @@ -1118,6 +1154,10 @@ static void data__hpp_register(struct data__file *d, int idx) fmt->color = hpp__color_wdiff; fmt->sort = hist_entry__cmp_wdiff; break; + case PERF_HPP_DIFF__DELTA_ABS: + fmt->color = hpp__color_delta; + fmt->sort = hist_entry__cmp_delta_abs; + break; default: fmt->sort = hist_entry__cmp_nop; break; @@ -1195,6 +1235,9 @@ static int ui_init(void) case COMPUTE_WEIGHTED_DIFF: fmt->sort = hist_entry__cmp_wdiff_idx; break; + case COMPUTE_DELTA_ABS: + fmt->sort = hist_entry__cmp_delta_abs_idx; + break; default: BUG_ON(1); } @@ -1249,6 +1292,31 @@ static int data_init(int argc, const char **argv) return 0; } +static int diff__config(const char *var, const char *value, + void *cb __maybe_unused) +{ + if (!strcmp(var, "diff.order")) { + sort_compute = perf_config_int(var, value); + return 0; + } + if (!strcmp(var, "diff.compute")) { + if (!strcmp(value, "delta")) { + compute = COMPUTE_DELTA; + } else if (!strcmp(value, "delta-abs")) { + compute = COMPUTE_DELTA_ABS; + } else if (!strcmp(value, "ratio")) { + compute = COMPUTE_RATIO; + } else if (!strcmp(value, "wdiff")) { + compute = COMPUTE_WEIGHTED_DIFF; + } else { + pr_err("Invalid compute method: %s\n", value); + return -1; + } + } + + return 0; +} + int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) { int ret = hists__init(); @@ -1256,6 +1324,8 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) if (ret < 0) return ret; + perf_config(diff__config, NULL); + argc = parse_options(argc, argv, options, diff_usage, 0); if (symbol__init(NULL) < 0) diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c new file mode 100644 index 000000000000..c3e643666c72 --- /dev/null +++ b/tools/perf/builtin-ftrace.c @@ -0,0 +1,265 @@ +/* + * builtin-ftrace.c + * + * Copyright (c) 2013 LG Electronics, Namhyung Kim <namhyung@kernel.org> + * + * Released under the GPL v2. + */ + +#include "builtin.h" +#include "perf.h" + +#include <unistd.h> +#include <signal.h> + +#include "debug.h" +#include <subcmd/parse-options.h> +#include "evlist.h" +#include "target.h" +#include "thread_map.h" +#include "util/config.h" + + +#define DEFAULT_TRACER "function_graph" + +struct perf_ftrace { + struct perf_evlist *evlist; + struct target target; + const char *tracer; +}; + +static bool done; + +static void sig_handler(int sig __maybe_unused) +{ + done = true; +} + +/* + * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since + * we asked by setting its exec_error to the function below, + * ftrace__workload_exec_failed_signal. + * + * XXX We need to handle this more appropriately, emitting an error, etc. + */ +static void ftrace__workload_exec_failed_signal(int signo __maybe_unused, + siginfo_t *info __maybe_unused, + void *ucontext __maybe_unused) +{ + /* workload_exec_errno = info->si_value.sival_int; */ + done = true; +} + +static int write_tracing_file(const char *name, const char *val) +{ + char *file; + int fd, ret = -1; + ssize_t size = strlen(val); + + file = get_tracing_file(name); + if (!file) { + pr_debug("cannot get tracing file: %s\n", name); + return -1; + } + + fd = open(file, O_WRONLY); + if (fd < 0) { + pr_debug("cannot open tracing file: %s\n", name); + goto out; + } + + if (write(fd, val, size) == size) + ret = 0; + else + pr_debug("write '%s' to tracing/%s failed\n", val, name); + + close(fd); +out: + put_tracing_file(file); + return ret; +} + +static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused) +{ + if (write_tracing_file("tracing_on", "0") < 0) + return -1; + + if (write_tracing_file("current_tracer", "nop") < 0) + return -1; + + if (write_tracing_file("set_ftrace_pid", " ") < 0) + return -1; + + return 0; +} + +static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) +{ + char *trace_file; + int trace_fd; + char *trace_pid; + char buf[4096]; + struct pollfd pollfd = { + .events = POLLIN, + }; + + if (geteuid() != 0) { + pr_err("ftrace only works for root!\n"); + return -1; + } + + if (argc < 1) + return -1; + + signal(SIGINT, sig_handler); + signal(SIGUSR1, sig_handler); + signal(SIGCHLD, sig_handler); + + reset_tracing_files(ftrace); + + /* reset ftrace buffer */ + if (write_tracing_file("trace", "0") < 0) + goto out; + + if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target, + argv, false, ftrace__workload_exec_failed_signal) < 0) + goto out; + + if (write_tracing_file("current_tracer", ftrace->tracer) < 0) { + pr_err("failed to set current_tracer to %s\n", ftrace->tracer); + goto out; + } + + if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) { + pr_err("failed to allocate pid string\n"); + goto out; + } + + if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) { + pr_err("failed to set pid: %s\n", trace_pid); + goto out_free_pid; + } + + trace_file = get_tracing_file("trace_pipe"); + if (!trace_file) { + pr_err("failed to open trace_pipe\n"); + goto out_free_pid; + } + + trace_fd = open(trace_file, O_RDONLY); + + put_tracing_file(trace_file); + + if (trace_fd < 0) { + pr_err("failed to open trace_pipe\n"); + goto out_free_pid; + } + + fcntl(trace_fd, F_SETFL, O_NONBLOCK); + pollfd.fd = trace_fd; + + if (write_tracing_file("tracing_on", "1") < 0) { + pr_err("can't enable tracing\n"); + goto out_close_fd; + } + + perf_evlist__start_workload(ftrace->evlist); + + while (!done) { + if (poll(&pollfd, 1, -1) < 0) + break; + + if (pollfd.revents & POLLIN) { + int n = read(trace_fd, buf, sizeof(buf)); + if (n < 0) + break; + if (fwrite(buf, n, 1, stdout) != 1) + break; + } + } + + write_tracing_file("tracing_on", "0"); + + /* read remaining buffer contents */ + while (true) { + int n = read(trace_fd, buf, sizeof(buf)); + if (n <= 0) + break; + if (fwrite(buf, n, 1, stdout) != 1) + break; + } + +out_close_fd: + close(trace_fd); +out_free_pid: + free(trace_pid); +out: + reset_tracing_files(ftrace); + + return done ? 0 : -1; +} + +static int perf_ftrace_config(const char *var, const char *value, void *cb) +{ + struct perf_ftrace *ftrace = cb; + + if (prefixcmp(var, "ftrace.")) + return 0; + + if (strcmp(var, "ftrace.tracer")) + return -1; + + if (!strcmp(value, "function_graph") || + !strcmp(value, "function")) { + ftrace->tracer = value; + return 0; + } + + pr_err("Please select \"function_graph\" (default) or \"function\"\n"); + return -1; +} + +int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused) +{ + int ret; + struct perf_ftrace ftrace = { + .tracer = DEFAULT_TRACER, + .target = { .uid = UINT_MAX, }, + }; + const char * const ftrace_usage[] = { + "perf ftrace [<options>] <command>", + "perf ftrace [<options>] -- <command> [<options>]", + NULL + }; + const struct option ftrace_options[] = { + OPT_STRING('t', "tracer", &ftrace.tracer, "tracer", + "tracer to use: function_graph(default) or function"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose"), + OPT_END() + }; + + ret = perf_config(perf_ftrace_config, &ftrace); + if (ret < 0) + return -1; + + argc = parse_options(argc, argv, ftrace_options, ftrace_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (!argc) + usage_with_options(ftrace_usage, ftrace_options); + + ftrace.evlist = perf_evlist__new(); + if (ftrace.evlist == NULL) + return -ENOMEM; + + ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target); + if (ret < 0) + goto out_delete_evlist; + + ret = __cmd_ftrace(&ftrace, argc, argv); + +out_delete_evlist: + perf_evlist__delete(ftrace.evlist); + + return ret; +} diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 3bdb2c78a21b..aed0d844e8c2 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -434,7 +434,7 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) const char * const builtin_help_subcommands[] = { "buildid-cache", "buildid-list", "diff", "evlist", "help", "list", "record", "report", "bench", "stat", "timechart", "top", "annotate", - "script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data", + "script", "sched", "kallsyms", "kmem", "lock", "kvm", "test", "inject", "mem", "data", #ifdef HAVE_LIBELF_SUPPORT "probe", #endif @@ -447,11 +447,13 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; const char *alias; - int rc = 0; + int rc; load_command_list("perf-", &main_cmds, &other_cmds); - perf_config(perf_help_config, &help_format); + rc = perf_config(perf_help_config, &help_format); + if (rc) + return rc; argc = parse_options_subcommand(argc, argv, builtin_help_options, builtin_help_subcommands, builtin_help_usage, 0); diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c new file mode 100644 index 000000000000..224bfc454b4a --- /dev/null +++ b/tools/perf/builtin-kallsyms.c @@ -0,0 +1,67 @@ +/* + * builtin-kallsyms.c + * + * Builtin command: Look for a symbol in the running kernel and its modules + * + * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Released under the GPL v2. (and only v2, not any later version) + */ +#include "builtin.h" +#include <linux/compiler.h> +#include <subcmd/parse-options.h> +#include "debug.h" +#include "machine.h" +#include "symbol.h" + +static int __cmd_kallsyms(int argc, const char **argv) +{ + int i; + struct machine *machine = machine__new_kallsyms(); + + if (machine == NULL) { + pr_err("Couldn't read /proc/kallsyms\n"); + return -1; + } + + for (i = 0; i < argc; ++i) { + struct map *map; + struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map); + + if (symbol == NULL) { + printf("%s: not found\n", argv[i]); + continue; + } + + printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n", + symbol->name, map->dso->short_name, map->dso->long_name, + map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end), + symbol->start, symbol->end); + } + + machine__delete(machine); + return 0; +} + +int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused) +{ + const struct option options[] = { + OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), + OPT_END() + }; + const char * const kallsyms_usage[] = { + "perf kallsyms [<options>] symbol_name", + NULL + }; + + argc = parse_options(argc, argv, options, kallsyms_usage, 0); + if (argc < 1) + usage_with_options(kallsyms_usage, options); + + symbol_conf.sort_by_name = true; + symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); + if (symbol__init(NULL) < 0) + return -1; + + return __cmd_kallsyms(argc, argv); +} diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 915869e00d86..6da8d083e4e5 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1065,7 +1065,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines) data = rb_entry(next, struct page_stat, node); sym = machine__find_kernel_function(machine, data->callsite, &map); - if (sym && sym->name) + if (sym) caller = sym->name; else scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite); @@ -1107,7 +1107,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines data = rb_entry(next, struct page_stat, node); sym = machine__find_kernel_function(machine, data->callsite, &map); - if (sym && sym->name) + if (sym) caller = sym->name; else scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite); @@ -1920,10 +1920,12 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; struct perf_session *session; - int ret = -1; const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n"; + int ret = perf_config(kmem_config, NULL); + + if (ret) + return ret; - perf_config(kmem_config, NULL); argc = parse_options_subcommand(argc, argv, kmem_options, kmem_subcommands, kmem_usage, 0); @@ -1948,6 +1950,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) if (session == NULL) return -1; + ret = -1; + if (kmem_slab) { if (!perf_evlist__find_tracepoint_by_name(session->evlist, "kmem:kmalloc")) { diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index ba9322ff858b..3b9d98b5feef 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -14,6 +14,7 @@ #include "util/parse-events.h" #include "util/cache.h" #include "util/pmu.h" +#include "util/debug.h" #include <subcmd/parse-options.h> static bool desc_flag = true; @@ -29,6 +30,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) "Print extra event descriptions. --no-desc to not print."), OPT_BOOLEAN('v', "long-desc", &long_desc_flag, "Print longer event descriptions."), + OPT_INCR(0, "debug", &verbose, + "Enable debugging output"), OPT_END() }; const char * const list_usage[] = { diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index f87996b0cb29..1fcebc31a508 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -552,6 +552,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"), + OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", + "Look for files with symbols relative to this directory"), OPT_END() }; int ret; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 4ec10e9427d9..6cd6776052e7 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -46,6 +46,15 @@ #include <asm/bug.h> #include <linux/time64.h> +struct switch_output { + bool enabled; + bool signal; + unsigned long size; + unsigned long time; + const char *str; + bool set; +}; + struct record { struct perf_tool tool; struct record_opts opts; @@ -62,10 +71,33 @@ struct record { bool no_buildid_cache_set; bool buildid_all; bool timestamp_filename; - bool switch_output; + struct switch_output switch_output; unsigned long long samples; }; +static volatile int auxtrace_record__snapshot_started; +static DEFINE_TRIGGER(auxtrace_snapshot_trigger); +static DEFINE_TRIGGER(switch_output_trigger); + +static bool switch_output_signal(struct record *rec) +{ + return rec->switch_output.signal && + trigger_is_ready(&switch_output_trigger); +} + +static bool switch_output_size(struct record *rec) +{ + return rec->switch_output.size && + trigger_is_ready(&switch_output_trigger) && + (rec->bytes_written >= rec->switch_output.size); +} + +static bool switch_output_time(struct record *rec) +{ + return rec->switch_output.time && + trigger_is_ready(&switch_output_trigger); +} + static int record__write(struct record *rec, void *bf, size_t size) { if (perf_data_file__write(rec->session->file, bf, size) < 0) { @@ -74,6 +106,10 @@ static int record__write(struct record *rec, void *bf, size_t size) } rec->bytes_written += size; + + if (switch_output_size(rec)) + trigger_hit(&switch_output_trigger); + return 0; } @@ -193,10 +229,6 @@ static volatile int done; static volatile int signr = -1; static volatile int child_finished; -static volatile int auxtrace_record__snapshot_started; -static DEFINE_TRIGGER(auxtrace_snapshot_trigger); -static DEFINE_TRIGGER(switch_output_trigger); - static void sig_handler(int sig) { if (sig == SIGCHLD) @@ -386,7 +418,7 @@ static int record__mmap(struct record *rec) static int record__open(struct record *rec) { - char msg[512]; + char msg[BUFSIZ]; struct perf_evsel *pos; struct perf_evlist *evlist = rec->evlist; struct perf_session *session = rec->session; @@ -623,22 +655,23 @@ record__finish_output(struct record *rec) static int record__synthesize_workload(struct record *rec, bool tail) { - struct { - struct thread_map map; - struct thread_map_data map_data; - } thread_map; + int err; + struct thread_map *thread_map; if (rec->opts.tail_synthesize != tail) return 0; - thread_map.map.nr = 1; - thread_map.map.map[0].pid = rec->evlist->workload.pid; - thread_map.map.map[0].comm = NULL; - return perf_event__synthesize_thread_map(&rec->tool, &thread_map.map, + thread_map = thread_map__new_by_tid(rec->evlist->workload.pid); + if (thread_map == NULL) + return -1; + + err = perf_event__synthesize_thread_map(&rec->tool, thread_map, process_synthesized_event, &rec->session->machines.host, rec->opts.sample_address, rec->opts.proc_map_timeout); + thread_map__put(thread_map); + return err; } static int record__synthesize(struct record *rec, bool tail); @@ -712,6 +745,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, } static void snapshot_sig_handler(int sig); +static void alarm_sig_handler(int sig); int __weak perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused, @@ -842,11 +876,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) signal(SIGTERM, sig_handler); signal(SIGSEGV, sigsegv_handler); - if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) { + if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) { signal(SIGUSR2, snapshot_sig_handler); if (rec->opts.auxtrace_snapshot_mode) trigger_on(&auxtrace_snapshot_trigger); - if (rec->switch_output) + if (rec->switch_output.enabled) trigger_on(&switch_output_trigger); } else { signal(SIGUSR2, SIG_IGN); @@ -1043,6 +1077,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) err = fd; goto out_child; } + + /* re-arm the alarm */ + if (rec->switch_output.time) + alarm(rec->switch_output.time); } if (hits == rec->samples) { @@ -1352,6 +1390,78 @@ out_free: return ret; } +static void switch_output_size_warn(struct record *rec) +{ + u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages); + struct switch_output *s = &rec->switch_output; + + wakeup_size /= 2; + + if (s->size < wakeup_size) { + char buf[100]; + + unit_number__scnprintf(buf, sizeof(buf), wakeup_size); + pr_warning("WARNING: switch-output data size lower than " + "wakeup kernel buffer size (%s) " + "expect bigger perf.data sizes\n", buf); + } +} + +static int switch_output_setup(struct record *rec) +{ + struct switch_output *s = &rec->switch_output; + static struct parse_tag tags_size[] = { + { .tag = 'B', .mult = 1 }, + { .tag = 'K', .mult = 1 << 10 }, + { .tag = 'M', .mult = 1 << 20 }, + { .tag = 'G', .mult = 1 << 30 }, + { .tag = 0 }, + }; + static struct parse_tag tags_time[] = { + { .tag = 's', .mult = 1 }, + { .tag = 'm', .mult = 60 }, + { .tag = 'h', .mult = 60*60 }, + { .tag = 'd', .mult = 60*60*24 }, + { .tag = 0 }, + }; + unsigned long val; + + if (!s->set) + return 0; + + if (!strcmp(s->str, "signal")) { + s->signal = true; + pr_debug("switch-output with SIGUSR2 signal\n"); + goto enabled; + } + + val = parse_tag_value(s->str, tags_size); + if (val != (unsigned long) -1) { + s->size = val; + pr_debug("switch-output with %s size threshold\n", s->str); + goto enabled; + } + + val = parse_tag_value(s->str, tags_time); + if (val != (unsigned long) -1) { + s->time = val; + pr_debug("switch-output with %s time threshold (%lu seconds)\n", + s->str, s->time); + goto enabled; + } + + return -1; + +enabled: + rec->timestamp_filename = true; + s->enabled = true; + + if (s->size && !rec->opts.no_buffering) + switch_output_size_warn(rec); + + return 0; +} + static const char * const __record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -1519,8 +1629,10 @@ static struct option __record_options[] = { "Record build-id of all DSOs regardless of hits"), OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename, "append timestamp to output filename"), - OPT_BOOLEAN(0, "switch-output", &record.switch_output, - "Switch output when receive SIGUSR2"), + OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str, + &record.switch_output.set, "signal,size,time", + "Switch output when receive SIGUSR2 or cross size,time threshold", + "signal"), OPT_BOOLEAN(0, "dry-run", &dry_run, "Parse options then exit"), OPT_END() @@ -1559,7 +1671,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (rec->evlist == NULL) return -ENOMEM; - perf_config(perf_record_config, rec); + err = perf_config(perf_record_config, rec); + if (err) + return err; argc = parse_options(argc, argv, record_options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); @@ -1578,8 +1692,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) return -EINVAL; } - if (rec->switch_output) - rec->timestamp_filename = true; + if (switch_output_setup(rec)) { + parse_options_usage(record_usage, record_options, "switch-output", 0); + return -EINVAL; + } + + if (rec->switch_output.time) { + signal(SIGALRM, alarm_sig_handler); + alarm(rec->switch_output.time); + } if (!rec->itr) { rec->itr = auxtrace_record__init(rec->evlist, &err); @@ -1629,7 +1750,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (rec->no_buildid_cache || rec->no_buildid) { disable_buildid_cache(); - } else if (rec->switch_output) { + } else if (rec->switch_output.enabled) { /* * In 'perf record --switch-output', disable buildid * generation by default to reduce data file switching @@ -1721,6 +1842,8 @@ out: static void snapshot_sig_handler(int sig __maybe_unused) { + struct record *rec = &record; + if (trigger_is_ready(&auxtrace_snapshot_trigger)) { trigger_hit(&auxtrace_snapshot_trigger); auxtrace_record__snapshot_started = 1; @@ -1728,6 +1851,14 @@ static void snapshot_sig_handler(int sig __maybe_unused) trigger_error(&auxtrace_snapshot_trigger); } - if (trigger_is_ready(&switch_output_trigger)) + if (switch_output_signal(rec)) + trigger_hit(&switch_output_trigger); +} + +static void alarm_sig_handler(int sig __maybe_unused) +{ + struct record *rec = &record; + + if (switch_output_time(rec)) trigger_hit(&switch_output_trigger); } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 06cc759a4597..dbd7fa028861 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -847,7 +847,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) if (ret < 0) return ret; - perf_config(report__config, &report); + ret = perf_config(report__config, &report); + if (ret) + return ret; argc = parse_options(argc, argv, options, report_usage, 0); if (argc) { diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 5b134b0d1ff3..270eb2d8ca6b 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -77,6 +77,22 @@ struct sched_atom { #define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" +/* task state bitmask, copied from include/linux/sched.h */ +#define TASK_RUNNING 0 +#define TASK_INTERRUPTIBLE 1 +#define TASK_UNINTERRUPTIBLE 2 +#define __TASK_STOPPED 4 +#define __TASK_TRACED 8 +/* in tsk->exit_state */ +#define EXIT_DEAD 16 +#define EXIT_ZOMBIE 32 +#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) +/* in tsk->state again */ +#define TASK_DEAD 64 +#define TASK_WAKEKILL 128 +#define TASK_WAKING 256 +#define TASK_PARKED 512 + enum thread_state { THREAD_SLEEPING = 0, THREAD_WAIT_CPU, @@ -206,6 +222,7 @@ struct perf_sched { bool show_cpu_visual; bool show_wakeups; bool show_migrations; + bool show_state; u64 skipped_samples; const char *time_str; struct perf_time_interval ptime; @@ -216,13 +233,20 @@ struct perf_sched { struct thread_runtime { u64 last_time; /* time of previous sched in/out event */ u64 dt_run; /* run time */ - u64 dt_wait; /* time between CPU access (off cpu) */ + u64 dt_sleep; /* time between CPU access by sleep (off cpu) */ + u64 dt_iowait; /* time between CPU access by iowait (off cpu) */ + u64 dt_preempt; /* time between CPU access by preempt (off cpu) */ u64 dt_delay; /* time between wakeup and sched-in */ u64 ready_to_run; /* time of wakeup */ struct stats run_stats; u64 total_run_time; + u64 total_sleep_time; + u64 total_iowait_time; + u64 total_preempt_time; + u64 total_delay_time; + int last_state; u64 migrations; }; @@ -1821,6 +1845,9 @@ static void timehist_header(struct perf_sched *sched) printf(" %-*s %9s %9s %9s", comm_width, "task name", "wait time", "sch delay", "run time"); + if (sched->show_state) + printf(" %s", "state"); + printf("\n"); /* @@ -1831,9 +1858,14 @@ static void timehist_header(struct perf_sched *sched) if (sched->show_cpu_visual) printf(" %*s ", ncpus, ""); - printf(" %-*s %9s %9s %9s\n", comm_width, + printf(" %-*s %9s %9s %9s", comm_width, "[tid/pid]", "(msec)", "(msec)", "(msec)"); + if (sched->show_state) + printf(" %5s", ""); + + printf("\n"); + /* * separator */ @@ -1846,18 +1878,34 @@ static void timehist_header(struct perf_sched *sched) graph_dotted_line, graph_dotted_line, graph_dotted_line, graph_dotted_line); + if (sched->show_state) + printf(" %.5s", graph_dotted_line); + printf("\n"); } +static char task_state_char(struct thread *thread, int state) +{ + static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; + unsigned bit = state ? ffs(state) : 0; + + /* 'I' for idle */ + if (thread->tid == 0) + return 'I'; + + return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; +} + static void timehist_print_sample(struct perf_sched *sched, struct perf_sample *sample, struct addr_location *al, struct thread *thread, - u64 t) + u64 t, int state) { struct thread_runtime *tr = thread__priv(thread); u32 max_cpus = sched->max_cpu + 1; char tstr[64]; + u64 wait_time; timestamp__scnprintf_usec(t, tstr, sizeof(tstr)); printf("%15s [%04d] ", tstr, sample->cpu); @@ -1880,10 +1928,15 @@ static void timehist_print_sample(struct perf_sched *sched, printf(" %-*s ", comm_width, timehist_get_commstr(thread)); - print_sched_time(tr->dt_wait, 6); + wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt; + print_sched_time(wait_time, 6); + print_sched_time(tr->dt_delay, 6); print_sched_time(tr->dt_run, 6); + if (sched->show_state) + printf(" %5c ", task_state_char(thread, state)); + if (sched->show_wakeups) printf(" %-*s", comm_width, ""); @@ -1930,8 +1983,11 @@ static void timehist_update_runtime_stats(struct thread_runtime *r, u64 t, u64 tprev) { r->dt_delay = 0; - r->dt_wait = 0; + r->dt_sleep = 0; + r->dt_iowait = 0; + r->dt_preempt = 0; r->dt_run = 0; + if (tprev) { r->dt_run = t - tprev; if (r->ready_to_run) { @@ -1943,12 +1999,25 @@ static void timehist_update_runtime_stats(struct thread_runtime *r, if (r->last_time > tprev) pr_debug("time travel: last sched out time for task > previous sched_switch event\n"); - else if (r->last_time) - r->dt_wait = tprev - r->last_time; + else if (r->last_time) { + u64 dt_wait = tprev - r->last_time; + + if (r->last_state == TASK_RUNNING) + r->dt_preempt = dt_wait; + else if (r->last_state == TASK_UNINTERRUPTIBLE) + r->dt_iowait = dt_wait; + else + r->dt_sleep = dt_wait; + } } update_stats(&r->run_stats, r->dt_run); - r->total_run_time += r->dt_run; + + r->total_run_time += r->dt_run; + r->total_delay_time += r->dt_delay; + r->total_sleep_time += r->dt_sleep; + r->total_iowait_time += r->dt_iowait; + r->total_preempt_time += r->dt_preempt; } static bool is_idle_sample(struct perf_sample *sample, @@ -1998,7 +2067,7 @@ static void save_task_callchain(struct perf_sched *sched, break; sym = node->sym; - if (sym && sym->name) { + if (sym) { if (!strcmp(sym->name, "schedule") || !strcmp(sym->name, "__schedule") || !strcmp(sym->name, "preempt_schedule")) @@ -2373,6 +2442,8 @@ static int timehist_sched_change_event(struct perf_tool *tool, struct thread_runtime *tr = NULL; u64 tprev, t = sample->time; int rc = 0; + int state = perf_evsel__intval(evsel, sample, "prev_state"); + if (machine__resolve(machine, &al, sample) < 0) { pr_err("problem processing %d event. skipping it\n", @@ -2447,8 +2518,10 @@ static int timehist_sched_change_event(struct perf_tool *tool, * time. we only care total run time and run stat. */ last_tr->dt_run = 0; - last_tr->dt_wait = 0; last_tr->dt_delay = 0; + last_tr->dt_sleep = 0; + last_tr->dt_iowait = 0; + last_tr->dt_preempt = 0; if (itr->cursor.nr) callchain_append(&itr->callchain, &itr->cursor, t - tprev); @@ -2458,7 +2531,7 @@ static int timehist_sched_change_event(struct perf_tool *tool, } if (!sched->summary_only) - timehist_print_sample(sched, sample, &al, thread, t); + timehist_print_sample(sched, sample, &al, thread, t, state); out: if (sched->hist_time.start == 0 && t >= ptime->start) @@ -2470,6 +2543,9 @@ out: /* time of this sched_switch event becomes last time task seen */ tr->last_time = sample->time; + /* last state is used to determine where to account wait time */ + tr->last_state = state; + /* sched out event for task so reset ready to run time */ tr->ready_to_run = 0; } @@ -2526,7 +2602,26 @@ static void print_thread_runtime(struct thread *t, printf("\n"); } +static void print_thread_waittime(struct thread *t, + struct thread_runtime *r) +{ + printf("%*s %5d %9" PRIu64 " ", + comm_width, timehist_get_commstr(t), t->ppid, + (u64) r->run_stats.n); + + print_sched_time(r->total_run_time, 8); + print_sched_time(r->total_sleep_time, 6); + printf(" "); + print_sched_time(r->total_iowait_time, 6); + printf(" "); + print_sched_time(r->total_preempt_time, 6); + printf(" "); + print_sched_time(r->total_delay_time, 6); + printf("\n"); +} + struct total_run_stats { + struct perf_sched *sched; u64 sched_count; u64 task_count; u64 total_run_time; @@ -2545,7 +2640,11 @@ static int __show_thread_runtime(struct thread *t, void *priv) stats->task_count++; stats->sched_count += r->run_stats.n; stats->total_run_time += r->total_run_time; - print_thread_runtime(t, r); + + if (stats->sched->show_state) + print_thread_waittime(t, r); + else + print_thread_runtime(t, r); } return 0; @@ -2633,18 +2732,24 @@ static void timehist_print_summary(struct perf_sched *sched, u64 hist_time = sched->hist_time.end - sched->hist_time.start; memset(&totals, 0, sizeof(totals)); + totals.sched = sched; if (sched->idle_hist) { printf("\nIdle-time summary\n"); printf("%*s parent sched-out ", comm_width, "comm"); printf(" idle-time min-idle avg-idle max-idle stddev migrations\n"); + } else if (sched->show_state) { + printf("\nWait-time summary\n"); + printf("%*s parent sched-in ", comm_width, "comm"); + printf(" run-time sleep iowait preempt delay\n"); } else { printf("\nRuntime summary\n"); printf("%*s parent sched-in ", comm_width, "comm"); printf(" run-time min-run avg-run max-run stddev migrations\n"); } printf("%*s (count) ", comm_width, ""); - printf(" (msec) (msec) (msec) (msec) %%\n"); + printf(" (msec) (msec) (msec) (msec) %s\n", + sched->show_state ? "(msec)" : "%"); printf("%.117s\n", graph_dotted_line); machine__for_each_thread(m, show_thread_runtime, &totals); @@ -3240,6 +3345,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"), OPT_STRING(0, "time", &sched.time_str, "str", "Time span for analysis (start,stop)"), + OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"), OPT_PARENT(sched_options) }; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 2f3ff69fc4e7..c0783b4f7b6c 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2180,7 +2180,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Show the mmap events"), OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events, "Show context switch events (if recorded)"), - OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"), + OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), OPT_BOOLEAN(0, "ns", &nanosecs, "Use 9 decimal places when displaying time"), OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", @@ -2212,6 +2212,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) PARSE_OPT_STOP_AT_NON_OPTION); file.path = input_name; + file.force = symbol_conf.force; if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) { rec_script_path = get_script_path(argv[1], RECORD_SUFFIX); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index a02f2e965628..f28719178b51 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -533,7 +533,7 @@ static int store_counter_ids(struct perf_evsel *counter) static int __run_perf_stat(int argc, const char **argv) { int interval = stat_config.interval; - char msg[512]; + char msg[BUFSIZ]; unsigned long long t0, t1; struct perf_evsel *counter; struct timespec ts; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 3df4178ba378..5a7fd7af3a6d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -643,7 +643,7 @@ repeat: case -1: if (errno == EINTR) continue; - /* Fall trhu */ + __fallthrough; default: c = getc(stdin); tcsetattr(0, TCSAFLUSH, &save); @@ -859,7 +859,7 @@ static void perf_top__mmap_read(struct perf_top *top) static int perf_top__start_counters(struct perf_top *top) { - char msg[512]; + char msg[BUFSIZ]; struct perf_evsel *counter; struct perf_evlist *evlist = top->evlist; struct record_opts *opts = &top->record_opts; @@ -1216,7 +1216,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (top.evlist == NULL) return -ENOMEM; - perf_config(perf_top_config, &top); + status = perf_config(perf_top_config, &top); + if (status) + return status; argc = parse_options(argc, argv, options, top_usage, 0); if (argc) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 206bf72b77fc..40ef9b293d1b 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -40,6 +40,7 @@ #include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */ #include <stdlib.h> +#include <string.h> #include <linux/err.h> #include <linux/filter.h> #include <linux/audit.h> @@ -2699,6 +2700,91 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler) evsel->handler = handler; } +/* + * XXX: Hackish, just splitting the combined -e+--event (syscalls + * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use + * existing facilities unchanged (trace->ev_qualifier + parse_options()). + * + * It'd be better to introduce a parse_options() variant that would return a + * list with the terms it didn't match to an event... + */ +static int trace__parse_events_option(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct trace *trace = (struct trace *)opt->value; + const char *s = str; + char *sep = NULL, *lists[2] = { NULL, NULL, }; + int len = strlen(str), err = -1, list; + char *strace_groups_dir = system_path(STRACE_GROUPS_DIR); + char group_name[PATH_MAX]; + + if (strace_groups_dir == NULL) + return -1; + + if (*s == '!') { + ++s; + trace->not_ev_qualifier = true; + } + + while (1) { + if ((sep = strchr(s, ',')) != NULL) + *sep = '\0'; + + list = 0; + if (syscalltbl__id(trace->sctbl, s) >= 0) { + list = 1; + } else { + path__join(group_name, sizeof(group_name), strace_groups_dir, s); + if (access(group_name, R_OK) == 0) + list = 1; + } + + if (lists[list]) { + sprintf(lists[list] + strlen(lists[list]), ",%s", s); + } else { + lists[list] = malloc(len); + if (lists[list] == NULL) + goto out; + strcpy(lists[list], s); + } + + if (!sep) + break; + + *sep = ','; + s = sep + 1; + } + + if (lists[1] != NULL) { + struct strlist_config slist_config = { + .dirname = strace_groups_dir, + }; + + trace->ev_qualifier = strlist__new(lists[1], &slist_config); + if (trace->ev_qualifier == NULL) { + fputs("Not enough memory to parse event qualifier", trace->output); + goto out; + } + + if (trace__validate_ev_qualifier(trace)) + goto out; + } + + err = 0; + + if (lists[0]) { + struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event", + "event selector. use 'perf list' to list available events", + parse_events_option); + err = parse_events_option(&o, lists[0], 0); + } +out: + if (sep) + *sep = ','; + + return err; +} + int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) { const char *trace_usage[] = { @@ -2730,15 +2816,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) .max_stack = UINT_MAX, }; const char *output_name = NULL; - const char *ev_qualifier_str = NULL; const struct option trace_options[] = { - OPT_CALLBACK(0, "event", &trace.evlist, "event", - "event selector. use 'perf list' to list available events", - parse_events_option), + OPT_CALLBACK('e', "event", &trace, "event", + "event/syscall selector. use 'perf list' to list available events", + trace__parse_events_option), OPT_BOOLEAN(0, "comm", &trace.show_comm, "show the thread COMM next to its id"), OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"), - OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"), + OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace", + trace__parse_events_option), OPT_STRING('o', "output", &output_name, "file", "output file name"), OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"), OPT_STRING('p', "pid", &trace.opts.target.pid, "pid", @@ -2863,7 +2949,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } - if (!trace.trace_syscalls && ev_qualifier_str) { + if (!trace.trace_syscalls && trace.ev_qualifier) { pr_err("The -e option can't be used with --no-syscalls.\n"); goto out; } @@ -2878,28 +2964,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) trace.open_id = syscalltbl__id(trace.sctbl, "open"); - if (ev_qualifier_str != NULL) { - const char *s = ev_qualifier_str; - struct strlist_config slist_config = { - .dirname = system_path(STRACE_GROUPS_DIR), - }; - - trace.not_ev_qualifier = *s == '!'; - if (trace.not_ev_qualifier) - ++s; - trace.ev_qualifier = strlist__new(s, &slist_config); - if (trace.ev_qualifier == NULL) { - fputs("Not enough memory to parse event qualifier", - trace.output); - err = -ENOMEM; - goto out_close; - } - - err = trace__validate_ev_qualifier(&trace); - if (err) - goto out_close; - } - err = target__validate(&trace.opts.target); if (err) { target__strerror(&trace.opts.target, err, bf, sizeof(bf)); diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 0bcf68e98ccc..036e1e35b1a8 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -23,6 +23,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix); int cmd_evlist(int argc, const char **argv, const char *prefix); int cmd_help(int argc, const char **argv, const char *prefix); int cmd_sched(int argc, const char **argv, const char *prefix); +int cmd_kallsyms(int argc, const char **argv, const char *prefix); int cmd_list(int argc, const char **argv, const char *prefix); int cmd_record(int argc, const char **argv, const char *prefix); int cmd_report(int argc, const char **argv, const char *prefix); @@ -40,6 +41,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix); int cmd_inject(int argc, const char **argv, const char *prefix); int cmd_mem(int argc, const char **argv, const char *prefix); int cmd_data(int argc, const char **argv, const char *prefix); +int cmd_ftrace(int argc, const char **argv, const char *prefix); int find_scripts(char **scripts_array, char **scripts_path_array); #endif diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index ab5cbaa170d0..ac3efd396a72 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -11,7 +11,9 @@ perf-data mainporcelain common perf-diff mainporcelain common perf-config mainporcelain common perf-evlist mainporcelain common +perf-ftrace mainporcelain common perf-inject mainporcelain common +perf-kallsyms mainporcelain common perf-kmem mainporcelain common perf-kvm mainporcelain common perf-list mainporcelain common diff --git a/tools/perf/perf.c b/tools/perf/perf.c index aa23b3347d6b..6d5479e03e0d 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -29,7 +29,6 @@ const char perf_usage_string[] = const char perf_more_info_string[] = "See 'perf help COMMAND' for more information on a specific command."; -int use_browser = -1; static int use_pager = -1; const char *input_name; @@ -47,6 +46,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, + { "kallsyms", cmd_kallsyms, 0 }, { "list", cmd_list, 0 }, { "record", cmd_record, 0 }, { "report", cmd_report, 0 }, @@ -71,6 +71,7 @@ static struct cmd_struct commands[] = { { "inject", cmd_inject, 0 }, { "mem", cmd_mem, 0 }, { "data", cmd_data, 0 }, + { "ftrace", cmd_ftrace, 0 }, }; struct pager_config { @@ -89,11 +90,12 @@ static int pager_command_config(const char *var, const char *value, void *data) /* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */ int check_pager_config(const char *cmd) { + int err; struct pager_config c; c.cmd = cmd; c.val = -1; - perf_config(pager_command_config, &c); - return c.val; + err = perf_config(pager_command_config, &c); + return err ?: c.val; } static int browser_command_config(const char *var, const char *value, void *data) @@ -112,11 +114,12 @@ static int browser_command_config(const char *var, const char *value, void *data */ static int check_browser_config(const char *cmd) { + int err; struct pager_config c; c.cmd = cmd; c.val = -1; - perf_config(browser_command_config, &c); - return c.val; + err = perf_config(browser_command_config, &c); + return err ?: c.val; } static void commit_pager_choice(void) @@ -329,8 +332,6 @@ static int handle_alias(int *argcp, const char ***argv) return ret; } -const char perf_version_string[] = PERF_VERSION; - #define RUN_SETUP (1<<0) #define USE_PAGER (1<<1) @@ -510,6 +511,7 @@ static void cache_line_size(int *cacheline_sizep) int main(int argc, const char **argv) { + int err; const char *cmd; char sbuf[STRERR_BUFSIZE]; int value; @@ -535,7 +537,9 @@ int main(int argc, const char **argv) srandom(time(NULL)); perf_config__init(); - perf_config(perf_default_config, NULL); + err = perf_config(perf_default_config, NULL); + if (err) + return err; set_buildid_dir(NULL); /* get debugfs/tracefs mount point from /proc/mounts */ diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json new file mode 100644 index 000000000000..076459c51d4e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json @@ -0,0 +1,317 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "filter_opc=0x187,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "filter_opc=0x18f,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x180,filter_tid=0x3e", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x181", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json new file mode 100644 index 000000000000..d17dc235f734 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json @@ -0,0 +1,83 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json new file mode 100644 index 000000000000..b44d43088bbb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json @@ -0,0 +1,84 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json new file mode 100644 index 000000000000..076459c51d4e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json @@ -0,0 +1,317 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "filter_opc=0x187,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "filter_opc=0x18f,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x180,filter_tid=0x3e", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x181", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json new file mode 100644 index 000000000000..39387f7909b2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json @@ -0,0 +1,28 @@ +[ + { + "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json new file mode 100644 index 000000000000..d17dc235f734 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json @@ -0,0 +1,83 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json new file mode 100644 index 000000000000..b44d43088bbb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json @@ -0,0 +1,84 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json new file mode 100644 index 000000000000..076459c51d4e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json @@ -0,0 +1,317 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "filter_opc=0x187,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "filter_opc=0x18f,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x180,filter_tid=0x3e", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x181", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json new file mode 100644 index 000000000000..39387f7909b2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json @@ -0,0 +1,28 @@ +[ + { + "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json new file mode 100644 index 000000000000..d17dc235f734 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json @@ -0,0 +1,83 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json new file mode 100644 index 000000000000..b44d43088bbb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json @@ -0,0 +1,84 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json new file mode 100644 index 000000000000..2efdc6772e0b --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json @@ -0,0 +1,322 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode.rfo_prefetch", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode.code", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode.data_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe non-snoop reads. Derived from unc_c_tor_inserts.miss_opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_READ", + "Filter": "filter_opc=0x1e4", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.miss_opcode.pcie_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1e6", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ", + "Filter": "filter_opc=0x195", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_READ", + "Filter": "filter_opc=0x1e4", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x1e5", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_WRITE", + "Filter": "filter_opc=0x1e6", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory. Derived from unc_c_tor_occupancy.miss_local", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL", + "PerPkg": "1", + "UMask": "0x2A", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory. Derived from unc_c_tor_occupancy.miss_remote", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE", + "PerPkg": "1", + "UMask": "0x8A", + "Unit": "CBO" + }, + { + "BriefDescription": "Read requests to home agent. Derived from unc_h_requests.reads", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "Write requests to home agent. Derived from unc_h_requests.writes", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json new file mode 100644 index 000000000000..d7e2fda1d695 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json @@ -0,0 +1,46 @@ +[ + { + "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events. Derived from unc_q_clockticks", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json new file mode 100644 index 000000000000..ac4ad4d6357b --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json @@ -0,0 +1,75 @@ +[ + { + "BriefDescription": "Memory page activates for reads and writes. Derived from unc_m_act_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT.RD", + "PerPkg": "1", + "UMask": "0x1", + "Umask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events. Derived from unc_m_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json new file mode 100644 index 000000000000..dc2586db0dfc --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json @@ -0,0 +1,249 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c6", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when thermal conditions are the upper limit on frequency. This is related to the THERMAL_THROTTLE CYCLES_ABOVE_TEMP event, which always counts cycles when we are above the thermal temperature. This event (STRONGEST_UPPER_LIMIT) is sampled at the output of the algorithm that determines the actual frequency, while THERMAL_THROTTLE looks at the input. Derived from unc_p_freq_max_limit_thermal_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system. Derived from unc_p_freq_trans_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", + "Filter": "filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", + "Filter": "filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", + "Filter": "filter_band2=3000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", + "Filter": "filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band2=4000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json new file mode 100644 index 000000000000..2f23cf0129e7 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json @@ -0,0 +1,209 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ", + "Filter": "filter_opc=0x195", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_READ", + "Filter": "filter_opc=0x1e4", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x1e5", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_WRITE", + "Filter": "filter_opc=0x1e6", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth. Derived from unc_c_tor_occupancy.miss_all", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL", + "Filter": "filter_opc=0x182", + "MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json new file mode 100644 index 000000000000..63351876eb57 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json @@ -0,0 +1,46 @@ +[ + { + "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events. Derived from unc_q_clockticks", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json new file mode 100644 index 000000000000..e2cf6daa7b37 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json @@ -0,0 +1,79 @@ +[ + { + "BriefDescription": "Memory page activates. Derived from unc_m_act_count", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events. Derived from unc_m_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Occupancy counter for memory read queue. Derived from unc_m_rpq_occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_M_RPQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json new file mode 100644 index 000000000000..bbe36d547386 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json @@ -0,0 +1,248 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transistioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events . Derived from unc_p_power_state_occupancy.cores_c6", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency. Derived from unc_p_freq_max_limit_thermal_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles", + "Counter": "0,1,2,3", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", + "Filter": "filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", + "Filter": "filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", + "Filter": "filter_band2=3000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", + "Filter": "filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band2=4000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json new file mode 100644 index 000000000000..e3bcd86c4f56 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json @@ -0,0 +1,42 @@ +[ + { + "BriefDescription": "ddr bandwidth read (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x03", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x01", + "Unit": "imc" + }, + { + "BriefDescription": "ddr bandwidth write (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x03", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x02", + "Unit": "imc" + }, + { + "BriefDescription": "mcdram bandwidth read (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x01", + "EventName": "UNC_E_RPQ_INSERTS", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x01", + "Unit": "edc_eclk" + }, + { + "BriefDescription": "mcdram bandwidth write (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x02", + "EventName": "UNC_E_WPQ_INSERTS", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x01", + "Unit": "edc_eclk" + } +] diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 41611d7f9873..eed09346a72a 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -135,7 +135,6 @@ static struct field { const char *field; const char *kernel; } fields[] = { - { "EventCode", "event=" }, { "UMask", "umask=" }, { "CounterMask", "cmask=" }, { "Invert", "inv=" }, @@ -189,6 +188,27 @@ static struct msrmap *lookup_msr(char *map, jsmntok_t *val) return NULL; } +static struct map { + const char *json; + const char *perf; +} unit_to_pmu[] = { + { "CBO", "uncore_cbox" }, + { "QPI LL", "uncore_qpi" }, + { "SBO", "uncore_sbox" }, + {} +}; + +static const char *field_to_perf(struct map *table, char *map, jsmntok_t *val) +{ + int i; + + for (i = 0; table[i].json; i++) { + if (json_streq(map, val, table[i].json)) + return table[i].perf; + } + return NULL; +} + #define EXPECT(e, t, m) do { if (!(e)) { \ jsmntok_t *loc = (t); \ if (!(t)->start && (t) > tokens) \ @@ -270,7 +290,8 @@ static void print_events_table_prefix(FILE *fp, const char *tblname) } static int print_events_table_entry(void *data, char *name, char *event, - char *desc, char *long_desc) + char *desc, char *long_desc, + char *pmu, char *unit, char *perpkg) { struct perf_entry_data *pd = data; FILE *outfp = pd->outfp; @@ -288,7 +309,12 @@ static int print_events_table_entry(void *data, char *name, char *event, fprintf(outfp, "\t.topic = \"%s\",\n", topic); if (long_desc && long_desc[0]) fprintf(outfp, "\t.long_desc = \"%s\",\n", long_desc); - + if (pmu) + fprintf(outfp, "\t.pmu = \"%s\",\n", pmu); + if (unit) + fprintf(outfp, "\t.unit = \"%s\",\n", unit); + if (perpkg) + fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg); fprintf(outfp, "},\n"); return 0; @@ -335,7 +361,8 @@ static char *real_event(const char *name, char *event) /* Call func with each event in the json file */ int json_events(const char *fn, int (*func)(void *data, char *name, char *event, char *desc, - char *long_desc), + char *long_desc, + char *pmu, char *unit, char *perpkg), void *data) { int err = -EIO; @@ -343,6 +370,7 @@ int json_events(const char *fn, jsmntok_t *tokens, *tok; int i, j, len; char *map; + char buf[128]; if (!fn) return -ENOENT; @@ -356,6 +384,11 @@ int json_events(const char *fn, char *event = NULL, *desc = NULL, *name = NULL; char *long_desc = NULL; char *extra_desc = NULL; + char *pmu = NULL; + char *filter = NULL; + char *perpkg = NULL; + char *unit = NULL; + unsigned long long eventcode = 0; struct msrmap *msr = NULL; jsmntok_t *msrval = NULL; jsmntok_t *precise = NULL; @@ -376,6 +409,16 @@ int json_events(const char *fn, nz = !json_streq(map, val, "0"); if (match_field(map, field, nz, &event, val)) { /* ok */ + } else if (json_streq(map, field, "EventCode")) { + char *code = NULL; + addfield(map, &code, "", "", val); + eventcode |= strtoul(code, NULL, 0); + free(code); + } else if (json_streq(map, field, "ExtSel")) { + char *code = NULL; + addfield(map, &code, "", "", val); + eventcode |= strtoul(code, NULL, 0) << 21; + free(code); } else if (json_streq(map, field, "EventName")) { addfield(map, &name, "", "", val); } else if (json_streq(map, field, "BriefDescription")) { @@ -399,6 +442,28 @@ int json_events(const char *fn, addfield(map, &extra_desc, ". ", " Supports address when precise", NULL); + } else if (json_streq(map, field, "Unit")) { + const char *ppmu; + char *s; + + ppmu = field_to_perf(unit_to_pmu, map, val); + if (ppmu) { + pmu = strdup(ppmu); + } else { + if (!pmu) + pmu = strdup("uncore_"); + addfield(map, &pmu, "", "", val); + for (s = pmu; *s; s++) + *s = tolower(*s); + } + addfield(map, &desc, ". ", "Unit: ", NULL); + addfield(map, &desc, "", pmu, NULL); + } else if (json_streq(map, field, "Filter")) { + addfield(map, &filter, "", "", val); + } else if (json_streq(map, field, "ScaleUnit")) { + addfield(map, &unit, "", "", val); + } else if (json_streq(map, field, "PerPkg")) { + addfield(map, &perpkg, "", "", val); } /* ignore unknown fields */ } @@ -410,20 +475,29 @@ int json_events(const char *fn, addfield(map, &extra_desc, " ", "(Precise event)", NULL); } + snprintf(buf, sizeof buf, "event=%#llx", eventcode); + addfield(map, &event, ",", buf, NULL); if (desc && extra_desc) addfield(map, &desc, " ", extra_desc, NULL); if (long_desc && extra_desc) addfield(map, &long_desc, " ", extra_desc, NULL); + if (filter) + addfield(map, &event, ",", filter, NULL); if (msr != NULL) addfield(map, &event, ",", msr->pname, msrval); fixname(name); - err = func(data, name, real_event(name, event), desc, long_desc); + err = func(data, name, real_event(name, event), desc, long_desc, + pmu, unit, perpkg); free(event); free(desc); free(name); free(long_desc); free(extra_desc); + free(pmu); + free(filter); + free(perpkg); + free(unit); if (err) break; tok += j; diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h index b0eb2744b498..71e13de31092 100644 --- a/tools/perf/pmu-events/jevents.h +++ b/tools/perf/pmu-events/jevents.h @@ -3,7 +3,9 @@ int json_events(const char *fn, int (*func)(void *data, char *name, char *event, char *desc, - char *long_desc), + char *long_desc, + char *pmu, + char *unit, char *perpkg), void *data); char *get_cpu_str(void); diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 2eaef595d8a0..c669a3cdb9f0 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -10,6 +10,9 @@ struct pmu_event { const char *desc; const char *topic; const char *long_desc; + const char *pmu; + const char *unit; + const char *perpkg; }; /* diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 6676c2dd6dcb..1cb3d9b540e9 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -44,6 +44,7 @@ perf-y += is_printable_array.o perf-y += bitmap.o perf-y += perf-hooks.o perf-y += clang.o +perf-y += unit_number__scnprintf.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 92343f43e44a..1a04fe77487d 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -5,11 +5,13 @@ #include <util/evlist.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <api/fs/fs.h> #include <bpf/bpf.h> #include "tests.h" #include "llvm.h" #include "debug.h" #define NR_ITERS 111 +#define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test" #ifdef HAVE_LIBBPF_SUPPORT @@ -54,6 +56,7 @@ static struct { const char *msg_load_fail; int (*target_func)(void); int expect_result; + bool pin; } bpf_testcase_table[] = { { LLVM_TESTCASE_BASE, @@ -63,6 +66,17 @@ static struct { "load bpf object failed", &epoll_wait_loop, (NR_ITERS + 1) / 2, + false, + }, + { + LLVM_TESTCASE_BASE, + "BPF pinning", + "[bpf_pinning]", + "fix kbuild first", + "check your vmlinux setting?", + &epoll_wait_loop, + (NR_ITERS + 1) / 2, + true, }, #ifdef HAVE_BPF_PROLOGUE { @@ -73,6 +87,7 @@ static struct { "check your vmlinux setting?", &llseek_loop, (NR_ITERS + 1) / 4, + false, }, #endif { @@ -83,6 +98,7 @@ static struct { "libbpf error when dealing with relocation", NULL, 0, + false, }, }; @@ -226,10 +242,34 @@ static int __test__bpf(int idx) goto out; } - if (obj) + if (obj) { ret = do_test(obj, bpf_testcase_table[idx].target_func, bpf_testcase_table[idx].expect_result); + if (ret != TEST_OK) + goto out; + if (bpf_testcase_table[idx].pin) { + int err; + + if (!bpf_fs__mount()) { + pr_debug("BPF filesystem not mounted\n"); + ret = TEST_FAIL; + goto out; + } + err = mkdir(PERF_TEST_BPF_PATH, 0777); + if (err && errno != EEXIST) { + pr_debug("Failed to make perf_test dir: %s\n", + strerror(errno)); + ret = TEST_FAIL; + goto out; + } + if (bpf_object__pin(obj, PERF_TEST_BPF_PATH)) + ret = TEST_FAIL; + if (rm_rf(PERF_TEST_BPF_PATH)) + ret = TEST_FAIL; + } + } + out: bpf__clear(); return ret; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index a77dcc0d24e3..37e326bfd2dc 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -247,6 +247,10 @@ static struct test generic_tests[] = { } }, { + .desc = "unit_number__scnprintf", + .func = test__unit_number__scnprint, + }, + { .func = NULL, }, }; diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 02a33ebcd992..d357dab72e68 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -13,7 +13,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) struct bpf_object *obj; obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL); - if (IS_ERR(obj)) + if (libbpf_get_error(obj)) return TEST_FAIL; bpf_object__close(obj); return TEST_OK; diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 20c2e641c422..aa9276bfe3e9 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1779,15 +1779,14 @@ static int test_pmu_events(void) } while (!ret && (ent = readdir(dir))) { -#define MAX_NAME 100 struct evlist_test e; - char name[MAX_NAME]; + char name[2 * NAME_MAX + 1 + 12 + 3]; /* Names containing . are special and cannot be used directly */ if (strchr(ent->d_name, '.')) continue; - snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name); + snprintf(name, sizeof(name), "cpu/event=%s/u", ent->d_name); e.name = name; e.check = test__checkevent_pmu_events; @@ -1795,11 +1794,10 @@ static int test_pmu_events(void) ret = test_event(&e); if (ret) break; - snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name); + snprintf(name, sizeof(name), "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name); e.name = name; e.check = test__checkevent_pmu_events_mix; ret = test_event(&e); -#undef MAX_NAME } closedir(dir); diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 81c6eeaca0f5..65dcf48a92fb 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -50,7 +50,8 @@ static int process_events(union perf_event **events, size_t count) } struct test_attr_event { - struct attr_event attr; + struct perf_event_header header; + struct perf_event_attr attr; u64 id; }; @@ -71,20 +72,16 @@ int test__parse_no_sample_id_all(int subtest __maybe_unused) int err; struct test_attr_event event1 = { - .attr = { - .header = { - .type = PERF_RECORD_HEADER_ATTR, - .size = sizeof(struct test_attr_event), - }, + .header = { + .type = PERF_RECORD_HEADER_ATTR, + .size = sizeof(struct test_attr_event), }, .id = 1, }; struct test_attr_event event2 = { - .attr = { - .header = { - .type = PERF_RECORD_HEADER_ATTR, - .size = sizeof(struct test_attr_event), - }, + .header = { + .type = PERF_RECORD_HEADER_ATTR, + .size = sizeof(struct test_attr_event), }, .id = 2, }; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 8f2e1de6d0ea..541da7a68f91 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -66,7 +66,7 @@ int test__PERF_RECORD(int subtest __maybe_unused) if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */ evlist = perf_evlist__new_default(); - if (evlist == NULL || argv == NULL) { + if (evlist == NULL) { pr_debug("Not enough memory to create evlist\n"); goto out; } diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index a512f0c8ff5b..1fa9b9d83aa5 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -96,6 +96,7 @@ int test__perf_hooks(int subtest); int test__clang(int subtest); const char *test__clang_subtest_get_desc(int subtest); int test__clang_subtest_get_nr(void); +int test__unit_number__scnprint(int subtest); #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c new file mode 100644 index 000000000000..623c2aa53c4a --- /dev/null +++ b/tools/perf/tests/unit_number__scnprintf.c @@ -0,0 +1,37 @@ +#include <linux/compiler.h> +#include <linux/types.h> +#include "tests.h" +#include "util.h" +#include "debug.h" + +int test__unit_number__scnprint(int subtest __maybe_unused) +{ + struct { + u64 n; + const char *str; + } test[] = { + { 1, "1B" }, + { 10*1024, "10K" }, + { 20*1024*1024, "20M" }, + { 30*1024*1024*1024ULL, "30G" }, + { 0, "0B" }, + { 0, NULL }, + }; + unsigned i = 0; + + while (test[i].str) { + char buf[100]; + + unit_number__scnprintf(buf, sizeof(buf), test[i].n); + + pr_debug("n %" PRIu64 ", str '%s', buf '%s'\n", + test[i].n, test[i].str, buf); + + if (strcmp(test[i].str, buf)) + return TEST_FAIL; + + i++; + } + + return TEST_OK; +} diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 641b40234a9d..fc4fb669ceee 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -501,8 +501,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he, return n; } -static void hist_entry__set_folding(struct hist_entry *he, - struct hist_browser *hb, bool unfold) +static void __hist_entry__set_folding(struct hist_entry *he, + struct hist_browser *hb, bool unfold) { hist_entry__init_have_children(he); he->unfolded = unfold ? he->has_children : false; @@ -520,12 +520,34 @@ static void hist_entry__set_folding(struct hist_entry *he, he->nr_rows = 0; } +static void hist_entry__set_folding(struct hist_entry *he, + struct hist_browser *browser, bool unfold) +{ + double percent; + + percent = hist_entry__get_percent_limit(he); + if (he->filtered || percent < browser->min_pcnt) + return; + + __hist_entry__set_folding(he, browser, unfold); + + if (!he->depth || unfold) + browser->nr_hierarchy_entries++; + if (he->leaf) + browser->nr_callchain_rows += he->nr_rows; + else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { + browser->nr_hierarchy_entries++; + he->has_no_entry = true; + he->nr_rows = 1; + } else + he->has_no_entry = false; +} + static void __hist_browser__set_folding(struct hist_browser *browser, bool unfold) { struct rb_node *nd; struct hist_entry *he; - double percent; nd = rb_first(&browser->hists->entries); while (nd) { @@ -535,21 +557,6 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold) nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD); hist_entry__set_folding(he, browser, unfold); - - percent = hist_entry__get_percent_limit(he); - if (he->filtered || percent < browser->min_pcnt) - continue; - - if (!he->depth || unfold) - browser->nr_hierarchy_entries++; - if (he->leaf) - browser->nr_callchain_rows += he->nr_rows; - else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { - browser->nr_hierarchy_entries++; - he->has_no_entry = true; - he->nr_rows = 1; - } else - he->has_no_entry = false; } } @@ -564,6 +571,15 @@ static void hist_browser__set_folding(struct hist_browser *browser, bool unfold) ui_browser__reset_index(&browser->b); } +static void hist_browser__set_folding_selected(struct hist_browser *browser, bool unfold) +{ + if (!browser->he_selection) + return; + + hist_entry__set_folding(browser->he_selection, browser, unfold); + browser->b.nr_entries = hist_browser__nr_entries(browser); +} + static void ui_browser__warn_lost_events(struct ui_browser *browser) { ui_browser__warning(browser, 4, @@ -637,10 +653,18 @@ int hist_browser__run(struct hist_browser *browser, const char *help) /* Collapse the whole world. */ hist_browser__set_folding(browser, false); break; + case 'c': + /* Collapse the selected entry. */ + hist_browser__set_folding_selected(browser, false); + break; case 'E': /* Expand the whole world. */ hist_browser__set_folding(browser, true); break; + case 'e': + /* Expand the selected entry. */ + hist_browser__set_folding_selected(browser, true); + break; case 'H': browser->show_headers = !browser->show_headers; hist_browser__update_rows(browser); diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index 1f6b0994f4f4..50d13e58210f 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -7,6 +7,7 @@ pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; void *perf_gtk_handle; +int use_browser = -1; #ifdef HAVE_GTK2_SUPPORT static int setup_gtk_browser(void) diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 3840e3a87057..5da376bc1afc 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -162,6 +162,7 @@ CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_parse-events.o += -Wno-redundant-decls +CFLAGS_header.o += -include $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE $(call rule_mkdir) diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 36c861103291..bc6bc7062eb4 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -670,13 +670,13 @@ int bpf__probe(struct bpf_object *obj) err = convert_perf_probe_events(pev, 1); if (err < 0) { - pr_debug("bpf_probe: failed to convert perf probe events"); + pr_debug("bpf_probe: failed to convert perf probe events\n"); goto out; } err = apply_perf_probe_events(pev, 1); if (err < 0) { - pr_debug("bpf_probe: failed to apply perf probe events"); + pr_debug("bpf_probe: failed to apply perf probe events\n"); goto out; } diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 8b610dd9e2f6..aba953421a03 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -48,6 +48,8 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_FOLDED; return 0; } + + pr_err("Invalid callchain mode: %s\n", value); return -1; } @@ -63,6 +65,8 @@ static int parse_callchain_order(const char *value) callchain_param.order_set = true; return 0; } + + pr_err("Invalid callchain order: %s\n", value); return -1; } @@ -80,6 +84,8 @@ static int parse_callchain_sort_key(const char *value) callchain_param.branch_callstack = 1; return 0; } + + pr_err("Invalid callchain sort key: %s\n", value); return -1; } @@ -97,6 +103,8 @@ static int parse_callchain_value(const char *value) callchain_param.value = CCVAL_COUNT; return 0; } + + pr_err("Invalid callchain config key: %s\n", value); return -1; } @@ -210,13 +218,17 @@ int perf_callchain_config(const char *var, const char *value) return parse_callchain_sort_key(value); if (!strcmp(var, "threshold")) { callchain_param.min_percent = strtod(value, &endptr); - if (value == endptr) + if (value == endptr) { + pr_err("Invalid callchain threshold: %s\n", value); return -1; + } } if (!strcmp(var, "print-limit")) { callchain_param.print_limit = strtod(value, &endptr); - if (value == endptr) + if (value == endptr) { + pr_err("Invalid callchain print limit: %s\n", value); return -1; + } } return 0; diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 3d906dbbef74..0c7d5a4975cd 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -386,8 +386,10 @@ static int perf_buildid_config(const char *var, const char *value) if (!strcmp(var, "buildid.dir")) { const char *dir = perf_config_dirname(var, value); - if (!dir) + if (!dir) { + pr_err("Invalid buildid directory!\n"); return -1; + } strncpy(buildid_dir, dir, MAXPATHLEN-1); buildid_dir[MAXPATHLEN-1] = '\0'; } @@ -405,10 +407,9 @@ static int perf_default_core_config(const char *var __maybe_unused, static int perf_ui_config(const char *var, const char *value) { /* Add other config variables here. */ - if (!strcmp(var, "ui.show-headers")) { + if (!strcmp(var, "ui.show-headers")) symbol_conf.show_hist_headers = perf_config_bool(var, value); - return 0; - } + return 0; } @@ -646,8 +647,13 @@ static int perf_config_set__init(struct perf_config_set *set) goto out; } - if (stat(user_config, &st) < 0) + if (stat(user_config, &st) < 0) { + if (errno == ENOENT) + ret = 0; goto out_free; + } + + ret = 0; if (st.st_uid && (st.st_uid != geteuid())) { warning("File %s not owned by current user or root, " @@ -655,11 +661,8 @@ static int perf_config_set__init(struct perf_config_set *set) goto out_free; } - if (!st.st_size) - goto out_free; - - ret = perf_config_from_file(collect_config, user_config, set); - + if (st.st_size) + ret = perf_config_from_file(collect_config, user_config, set); out_free: free(user_config); } diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 7123f4de32cc..4e6cbc99f08e 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -1473,7 +1473,7 @@ int bt_convert__perf2ctf(const char *input, const char *path, }, }; struct ctf_writer *cw = &c.writer; - int err = -1; + int err; if (opts->all) { c.tool.comm = process_comm_event; @@ -1481,12 +1481,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, c.tool.fork = process_fork_event; } - perf_config(convert__config, &c); + err = perf_config(convert__config, &c); + if (err) + return err; /* CTF writer */ if (ctf_writer__init(cw, path)) return -1; + err = -1; /* perf.data session */ session = perf_session__new(&file, 0, &c.tool); if (!session) diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index d2c6cdd9d42b..28d41e709128 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -9,6 +9,13 @@ #include "debug.h" #include "vdso.h" +static const char * const debuglink_paths[] = { + "%.0s%s", + "%s/%s", + "%s/.debug/%s", + "/usr/lib/debug%s/%s" +}; + char dso__symtab_origin(const struct dso *dso) { static const char origin[] = { @@ -44,24 +51,43 @@ int dso__read_binary_type_filename(const struct dso *dso, size_t len; switch (type) { - case DSO_BINARY_TYPE__DEBUGLINK: { - char *debuglink; + case DSO_BINARY_TYPE__DEBUGLINK: + { + const char *last_slash; + char dso_dir[PATH_MAX]; + char symfile[PATH_MAX]; + unsigned int i; len = __symbol__join_symfs(filename, size, dso->long_name); - debuglink = filename + len; - while (debuglink != filename && *debuglink != '/') - debuglink--; - if (*debuglink == '/') - debuglink++; + last_slash = filename + len; + while (last_slash != filename && *last_slash != '/') + last_slash--; - ret = -1; - if (!is_regular_file(filename)) + strncpy(dso_dir, filename, last_slash - filename); + dso_dir[last_slash-filename] = '\0'; + + if (!is_regular_file(filename)) { + ret = -1; + break; + } + + ret = filename__read_debuglink(filename, symfile, PATH_MAX); + if (ret) break; - ret = filename__read_debuglink(filename, debuglink, - size - (debuglink - filename)); + /* Check predefined locations where debug file might reside */ + ret = -1; + for (i = 0; i < ARRAY_SIZE(debuglink_paths); i++) { + snprintf(filename, size, + debuglink_paths[i], dso_dir, symfile); + if (is_regular_file(filename)) { + ret = 0; + break; + } } + break; + } case DSO_BINARY_TYPE__BUILD_ID_CACHE: if (dso__build_id_filename(dso, filename, size) == NULL) ret = -1; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 8ab0d7da956b..4ea7ce72ed9c 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,5 +1,5 @@ #include <linux/types.h> -#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ +#include <linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include <api/fs/fs.h> #include "event.h" #include "debug.h" diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d92e02006fb8..b601f2814a30 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1184,7 +1184,7 @@ unsigned long perf_event_mlock_kb_in_pages(void) return pages; } -static size_t perf_evlist__mmap_size(unsigned long pages) +size_t perf_evlist__mmap_size(unsigned long pages) { if (pages == UINT_MAX) pages = perf_event_mlock_kb_in_pages(); @@ -1224,12 +1224,16 @@ static long parse_pages_arg(const char *str, unsigned long min, if (pages == 0 && min == 0) { /* leave number of pages at 0 */ } else if (!is_power_of_2(pages)) { + char buf[100]; + /* round pages up to next power of 2 */ pages = roundup_pow_of_two(pages); if (!pages) return -EINVAL; - pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n", - pages * page_size, pages); + + unit_number__scnprintf(buf, sizeof(buf), pages * page_size); + pr_info("rounding mmap pages size to %s (%lu pages)\n", + buf, pages); } if (pages > max) @@ -1797,7 +1801,7 @@ int perf_evlist__start_workload(struct perf_evlist *evlist) */ ret = write(evlist->workload.cork_fd, &bf, 1); if (ret < 0) - perror("enable to write to pipe"); + perror("unable to write to pipe"); close(evlist->workload.cork_fd); return ret; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 4fd034f22d2f..389b9ccdf8c7 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -218,6 +218,8 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, bool overwrite); void perf_evlist__munmap(struct perf_evlist *evlist); +size_t perf_evlist__mmap_size(unsigned long pages); + void perf_evlist__disable(struct perf_evlist *evlist); void perf_evlist__enable(struct perf_evlist *evlist); void perf_evlist__toggle_enable(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 04e536ae4d88..ac59710b79e0 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1448,8 +1448,8 @@ static bool ignore_missing_thread(struct perf_evsel *evsel, return true; } -static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads) +int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, + struct thread_map *threads) { int cpu, thread, nthreads; unsigned long flags = PERF_FLAG_FD_CLOEXEC; @@ -1459,6 +1459,30 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, if (perf_missing_features.write_backward && evsel->attr.write_backward) return -EINVAL; + if (cpus == NULL) { + static struct cpu_map *empty_cpu_map; + + if (empty_cpu_map == NULL) { + empty_cpu_map = cpu_map__dummy_new(); + if (empty_cpu_map == NULL) + return -ENOMEM; + } + + cpus = empty_cpu_map; + } + + if (threads == NULL) { + static struct thread_map *empty_thread_map; + + if (empty_thread_map == NULL) { + empty_thread_map = thread_map__new_by_tid(-1); + if (empty_thread_map == NULL) + return -ENOMEM; + } + + threads = empty_thread_map; + } + if (evsel->system_wide) nthreads = 1; else @@ -1655,46 +1679,16 @@ void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads) perf_evsel__free_fd(evsel); } -static struct { - struct cpu_map map; - int cpus[1]; -} empty_cpu_map = { - .map.nr = 1, - .cpus = { -1, }, -}; - -static struct { - struct thread_map map; - int threads[1]; -} empty_thread_map = { - .map.nr = 1, - .threads = { -1, }, -}; - -int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads) -{ - if (cpus == NULL) { - /* Work around old compiler warnings about strict aliasing */ - cpus = &empty_cpu_map.map; - } - - if (threads == NULL) - threads = &empty_thread_map.map; - - return __perf_evsel__open(evsel, cpus, threads); -} - int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus) { - return __perf_evsel__open(evsel, cpus, &empty_thread_map.map); + return perf_evsel__open(evsel, cpus, NULL); } int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads) { - return __perf_evsel__open(evsel, &empty_cpu_map.map, threads); + return perf_evsel__open(evsel, NULL, threads); } static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, @@ -2469,7 +2463,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, " -1: Allow use of (almost) all events by all users\n" ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n" ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" - ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN", + ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n" + "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n" + " kernel.perf_event_paranoid = -1\n" , target->system_wide ? "system-wide " : "", perf_event_paranoid()); case ENOENT: diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 6b2925542c0a..4ef5184819a0 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -168,7 +168,6 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (symbol_conf.bt_stop_list && node->sym && - node->sym->name && strlist__has_entry(symbol_conf.bt_stop_list, node->sym->name)) { break; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d89c9c7ef4e5..3d12c16e5103 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -41,6 +41,8 @@ static const u64 __perf_magic2_sw = 0x50455246494c4532ULL; #define PERF_MAGIC __perf_magic2 +const char perf_version_string[] = PERF_VERSION; + struct perf_file_attr { struct perf_event_attr attr; struct perf_file_section ids; @@ -2801,8 +2803,10 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, } event = pevent_find_event(pevent, evsel->attr.config); - if (event == NULL) + if (event == NULL) { + pr_debug("cannot find event format for %d\n", (int)evsel->attr.config); return -1; + } if (!evsel->name) { snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name); @@ -3201,6 +3205,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, case PERF_EVENT_UPDATE__SCALE: ev_scale = (struct event_update_event_scale *) ev->data; evsel->scale = ev_scale->scale; + break; case PERF_EVENT_UPDATE__CPUS: ev_cpus = (struct event_update_event_cpus *) ev->data; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 7d1b7d33e644..32c6a939e4cc 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -2446,8 +2446,10 @@ int parse_filter_percentage(const struct option *opt __maybe_unused, symbol_conf.filter_relative = true; else if (!strcmp(arg, "absolute")) symbol_conf.filter_relative = false; - else + else { + pr_debug("Invalud percentage: %s\n", arg); return -1; + } return 0; } diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 9b742ea8bfe8..7aca5d6d7e1f 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -23,4 +23,8 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -Wno-override-init +CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder + +ifneq ($(CC), clang) + CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init +endif diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index e4e7dc781d21..7cf7f7aca4d2 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -22,6 +22,7 @@ #include <errno.h> #include <stdint.h> #include <inttypes.h> +#include <linux/compiler.h> #include "../cache.h" #include "../util.h" @@ -1746,6 +1747,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; + __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: intel_pt_log("ERROR: Unexpected packet\n"); @@ -1799,6 +1801,8 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; intel_pt_clear_tx_flags(decoder); + __fallthrough; + case INTEL_PT_TNT: decoder->have_tma = false; intel_pt_log("ERROR: Unexpected packet\n"); @@ -1839,6 +1843,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; + __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index 4f7b32020487..7528ae4f7e28 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -17,6 +17,7 @@ #include <string.h> #include <endian.h> #include <byteswap.h> +#include <linux/compiler.h> #include "intel-pt-pkt-decoder.h" @@ -498,6 +499,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, case INTEL_PT_FUP: if (!(packet->count)) return snprintf(buf, buf_len, "%s no ip", name); + __fallthrough; case INTEL_PT_CYC: case INTEL_PT_VMCS: case INTEL_PT_MTC: diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 85d5eeb66c75..da20cd5612e9 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -2159,7 +2159,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event, addr_filters__init(&pt->filts); - perf_config(intel_pt_perf_config, pt); + err = perf_config(intel_pt_perf_config, pt); + if (err) + goto err_free; err = auxtrace_queues__init(&pt->queues); if (err) diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index b23ff44cf214..824356488ce6 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -48,8 +48,10 @@ int perf_llvm_config(const char *var, const char *value) llvm_param.kbuild_opts = strdup(value); else if (!strcmp(var, "dump-obj")) llvm_param.dump_obj = !!perf_config_bool(var, value); - else + else { + pr_debug("Invalid LLVM config option: %s\n", value); return -1; + } llvm_param.user_set_param = true; return 0; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 9b33bef54581..71c9720d4973 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -87,6 +87,25 @@ out_delete: return NULL; } +struct machine *machine__new_kallsyms(void) +{ + struct machine *machine = machine__new_host(); + /* + * FIXME: + * 1) MAP__FUNCTION will go away when we stop loading separate maps for + * functions and data objects. + * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely + * ask for not using the kcore parsing code, once this one is fixed + * to create a map per module. + */ + if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) { + machine__delete(machine); + machine = NULL; + } + + return machine; +} + static void dsos__purge(struct dsos *dsos) { struct dso *pos, *n; @@ -763,7 +782,7 @@ static u64 machine__get_running_kernel_start(struct machine *machine, int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { - enum map_type type; + int type; u64 start = machine__get_running_kernel_start(machine, NULL); /* In case of renewal the kernel map, destroy previous one */ @@ -794,7 +813,7 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) void machine__destroy_kernel_maps(struct machine *machine) { - enum map_type type; + int type; for (type = 0; type < MAP__NR_TYPES; ++type) { struct kmap *kmap; @@ -1546,7 +1565,7 @@ int machine__process_event(struct machine *machine, union perf_event *event, static bool symbol__match_regex(struct symbol *sym, regex_t *regex) { - if (sym->name && !regexec(regex, sym->name, 0, NULL, 0)) + if (!regexec(regex, sym->name, 0, NULL, 0)) return 1; return 0; } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 354de6e56109..a28305029711 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -129,6 +129,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size); void machines__set_comm_exec(struct machines *machines, bool comm_exec); struct machine *machine__new_host(void); +struct machine *machine__new_kallsyms(void); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); void machine__delete_threads(struct machine *machine); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 4f9a71c63026..0a943e7b1ea7 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -387,10 +387,10 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp) { const char *dsoname = "[unknown]"; - if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (map && map->dso) { if (symbol_conf.show_kernel_path && map->dso->long_name) dsoname = map->dso->long_name; - else if (map->dso->name) + else dsoname = map->dso->name; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 3c876b8ba4de..281e44af31e2 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -211,6 +211,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) closedir(evt_dir); closedir(sys_dir); path = zalloc(sizeof(*path)); + if (!path) + return NULL; path->system = malloc(MAX_EVENT_LENGTH); if (!path->system) { free(path); @@ -252,8 +254,7 @@ struct tracepoint_path *tracepoint_name_to_path(const char *name) if (path->system == NULL || path->name == NULL) { zfree(&path->system); zfree(&path->name); - free(path); - path = NULL; + zfree(&path); } return path; @@ -310,10 +311,11 @@ __add_event(struct list_head *list, int *idx, event_attr_init(attr); - evsel = perf_evsel__new_idx(attr, (*idx)++); + evsel = perf_evsel__new_idx(attr, *idx); if (!evsel) return NULL; + (*idx)++; evsel->cpus = cpu_map__get(cpus); evsel->own_cpus = cpu_map__get(cpus); @@ -1477,10 +1479,9 @@ static void perf_pmu__parse_cleanup(void) for (i = 0; i < perf_pmu_events_list_num; i++) { p = perf_pmu_events_list + i; - free(p->symbol); + zfree(&p->symbol); } - free(perf_pmu_events_list); - perf_pmu_events_list = NULL; + zfree(&perf_pmu_events_list); perf_pmu_events_list_num = 0; } } @@ -1504,35 +1505,41 @@ static void perf_pmu__parse_init(void) struct perf_pmu_alias *alias; int len = 0; - pmu = perf_pmu__find("cpu"); - if ((pmu == NULL) || list_empty(&pmu->aliases)) { + pmu = NULL; + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + list_for_each_entry(alias, &pmu->aliases, list) { + if (strchr(alias->name, '-')) + len++; + len++; + } + } + + if (len == 0) { perf_pmu_events_list_num = -1; return; } - list_for_each_entry(alias, &pmu->aliases, list) { - if (strchr(alias->name, '-')) - len++; - len++; - } perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len); if (!perf_pmu_events_list) return; perf_pmu_events_list_num = len; len = 0; - list_for_each_entry(alias, &pmu->aliases, list) { - struct perf_pmu_event_symbol *p = perf_pmu_events_list + len; - char *tmp = strchr(alias->name, '-'); - - if (tmp != NULL) { - SET_SYMBOL(strndup(alias->name, tmp - alias->name), - PMU_EVENT_SYMBOL_PREFIX); - p++; - SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX); - len += 2; - } else { - SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL); - len++; + pmu = NULL; + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + list_for_each_entry(alias, &pmu->aliases, list) { + struct perf_pmu_event_symbol *p = perf_pmu_events_list + len; + char *tmp = strchr(alias->name, '-'); + + if (tmp != NULL) { + SET_SYMBOL(strndup(alias->name, tmp - alias->name), + PMU_EVENT_SYMBOL_PREFIX); + p++; + SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX); + len += 2; + } else { + SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL); + len++; + } } } qsort(perf_pmu_events_list, len, @@ -1563,7 +1570,7 @@ perf_pmu__parse_check(const char *name) r = bsearch(&p, perf_pmu_events_list, (size_t) perf_pmu_events_list_num, sizeof(struct perf_pmu_event_symbol), comp_pmu); - free(p.symbol); + zfree(&p.symbol); return r ? r->type : PMU_EVENT_SYMBOL_ERR; } @@ -1710,8 +1717,8 @@ static void parse_events_print_error(struct parse_events_error *err, fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str); if (err->help) fprintf(stderr, "\n%s\n", err->help); - free(err->str); - free(err->help); + zfree(&err->str); + zfree(&err->help); } fprintf(stderr, "Run 'perf list' for a list of valid events\n"); @@ -2013,17 +2020,14 @@ static bool is_event_supported(u8 type, unsigned config) .config = config, .disabled = 1, }; - struct { - struct thread_map map; - int threads[1]; - } tmap = { - .map.nr = 1, - .threads = { 0 }, - }; + struct thread_map *tmap = thread_map__new_by_tid(0); + + if (tmap == NULL) + return false; evsel = perf_evsel__new(&attr); if (evsel) { - open_return = perf_evsel__open(evsel, NULL, &tmap.map); + open_return = perf_evsel__open(evsel, NULL, tmap); ret = open_return >= 0; if (open_return == -EACCES) { @@ -2035,7 +2039,7 @@ static bool is_event_supported(u8 type, unsigned config) * */ evsel->attr.exclude_kernel = 1; - ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0; + ret = perf_evsel__open(evsel, NULL, tmap) >= 0; } perf_evsel__delete(evsel); } @@ -2406,7 +2410,7 @@ void parse_events_terms__purge(struct list_head *terms) list_for_each_entry_safe(term, h, terms, list) { if (term->array.nr_ranges) - free(term->array.ranges); + zfree(&term->array.ranges); list_del_init(&term->list); free(term); } @@ -2422,7 +2426,7 @@ void parse_events_terms__delete(struct list_head *terms) void parse_events__clear_array(struct parse_events_array *a) { - free(a->ranges); + zfree(&a->ranges); } void parse_events_evlist_error(struct parse_events_evlist *data, diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 879115f93edc..a14b47ab3879 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -12,9 +12,13 @@ #include <linux/list.h> #include <linux/types.h> #include "util.h" +#include "pmu.h" +#include "debug.h" #include "parse-events.h" #include "parse-events-bison.h" +void parse_events_error(YYLTYPE *loc, void *data, void *scanner, char const *msg); + #define ABORT_ON(val) \ do { \ if (val) \ @@ -236,15 +240,34 @@ PE_KERNEL_PMU_EVENT sep_dc struct list_head *head; struct parse_events_term *term; struct list_head *list; + struct perf_pmu *pmu = NULL; + int ok = 0; - ALLOC_LIST(head); - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, 1, &@1, NULL)); - list_add_tail(&term->list, head); - + /* Add it for all PMUs that support the alias */ ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(data, list, "cpu", head)); - parse_events_terms__delete(head); + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + struct perf_pmu_alias *alias; + + list_for_each_entry(alias, &pmu->aliases, list) { + if (!strcasecmp(alias->name, $1)) { + ALLOC_LIST(head); + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, 1, &@1, NULL)); + list_add_tail(&term->list, head); + + if (!parse_events_add_pmu(data, list, + pmu->name, head)) { + pr_debug("%s -> %s/%s/\n", $1, + pmu->name, alias->str); + ok++; + } + + parse_events_terms__delete(head); + } + } + } + if (!ok) + YYABORT; $$ = list; } | diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index dc6ccaa4e927..49bfee0e3d9e 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -94,32 +94,10 @@ static int pmu_format(const char *name, struct list_head *format) return 0; } -static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name) +static int convert_scale(const char *scale, char **end, double *sval) { - struct stat st; - ssize_t sret; - char scale[128]; - int fd, ret = -1; - char path[PATH_MAX]; char *lc; - - snprintf(path, PATH_MAX, "%s/%s.scale", dir, name); - - fd = open(path, O_RDONLY); - if (fd == -1) - return -1; - - if (fstat(fd, &st) < 0) - goto error; - - sret = read(fd, scale, sizeof(scale)-1); - if (sret < 0) - goto error; - - if (scale[sret - 1] == '\n') - scale[sret - 1] = '\0'; - else - scale[sret] = '\0'; + int ret = 0; /* * save current locale @@ -134,7 +112,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * lc = strdup(lc); if (!lc) { ret = -ENOMEM; - goto error; + goto out; } /* @@ -144,14 +122,42 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * */ setlocale(LC_NUMERIC, "C"); - alias->scale = strtod(scale, NULL); + *sval = strtod(scale, end); +out: /* restore locale */ setlocale(LC_NUMERIC, lc); - free(lc); + return ret; +} + +static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name) +{ + struct stat st; + ssize_t sret; + char scale[128]; + int fd, ret = -1; + char path[PATH_MAX]; + + snprintf(path, PATH_MAX, "%s/%s.scale", dir, name); + + fd = open(path, O_RDONLY); + if (fd == -1) + return -1; + + if (fstat(fd, &st) < 0) + goto error; + + sret = read(fd, scale, sizeof(scale)-1); + if (sret < 0) + goto error; - ret = 0; + if (scale[sret - 1] == '\n') + scale[sret - 1] = '\0'; + else + scale[sret] = '\0'; + + ret = convert_scale(scale, NULL, &alias->scale); error: close(fd); return ret; @@ -223,11 +229,13 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, } static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, - char *desc, char *val, char *long_desc, - char *topic) + char *desc, char *val, + char *long_desc, char *topic, + char *unit, char *perpkg) { struct perf_pmu_alias *alias; int ret; + int num; alias = malloc(sizeof(*alias)); if (!alias) @@ -261,6 +269,13 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, alias->long_desc = long_desc ? strdup(long_desc) : desc ? strdup(desc) : NULL; alias->topic = topic ? strdup(topic) : NULL; + if (unit) { + if (convert_scale(unit, &unit, &alias->scale) < 0) + return -1; + snprintf(alias->unit, sizeof(alias->unit), "%s", unit); + } + alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1; + alias->str = strdup(val); list_add_tail(&alias->list, list); @@ -278,7 +293,8 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI buf[ret] = 0; - return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL); + return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL, + NULL); } static inline bool pmu_alias_info_file(char *name) @@ -498,7 +514,7 @@ char * __weak get_cpuid_str(void) * to the current running CPU. Then, add all PMU events from that table * as aliases. */ -static void pmu_add_cpu_aliases(struct list_head *head) +static void pmu_add_cpu_aliases(struct list_head *head, const char *name) { int i; struct pmu_events_map *map; @@ -534,14 +550,21 @@ static void pmu_add_cpu_aliases(struct list_head *head) */ i = 0; while (1) { + const char *pname; + pe = &map->table[i++]; if (!pe->name) break; + pname = pe->pmu ? pe->pmu : "cpu"; + if (strncmp(pname, name, strlen(pname))) + continue; + /* need type casts to override 'const' */ __perf_pmu__new_alias(head, NULL, (char *)pe->name, (char *)pe->desc, (char *)pe->event, - (char *)pe->long_desc, (char *)pe->topic); + (char *)pe->long_desc, (char *)pe->topic, + (char *)pe->unit, (char *)pe->perpkg); } out: @@ -569,15 +592,16 @@ static struct perf_pmu *pmu_lookup(const char *name) if (pmu_format(name, &format)) return NULL; - if (pmu_aliases(name, &aliases)) + /* + * Check the type first to avoid unnecessary work. + */ + if (pmu_type(name, &type)) return NULL; - if (!strcmp(name, "cpu")) - pmu_add_cpu_aliases(&aliases); - - if (pmu_type(name, &type)) + if (pmu_aliases(name, &aliases)) return NULL; + pmu_add_cpu_aliases(&aliases, name); pmu = zalloc(sizeof(*pmu)); if (!pmu) return NULL; @@ -921,12 +945,12 @@ static int check_info_data(struct perf_pmu_alias *alias, * define unit, scale and snapshot, fail * if there's more than one. */ - if ((info->unit && alias->unit) || + if ((info->unit && alias->unit[0]) || (info->scale && alias->scale) || (info->snapshot && alias->snapshot)) return -EINVAL; - if (alias->unit) + if (alias->unit[0]) info->unit = alias->unit; if (alias->scale) @@ -1065,6 +1089,8 @@ struct sevent { char *name; char *desc; char *topic; + char *str; + char *pmu; }; static int cmp_sevent(const void *a, const void *b) @@ -1161,6 +1187,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, aliases[j].desc = long_desc ? alias->long_desc : alias->desc; aliases[j].topic = alias->topic; + aliases[j].str = alias->str; + aliases[j].pmu = pmu->name; j++; } if (pmu->selectable && @@ -1175,6 +1203,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, len = j; qsort(aliases, len, sizeof(struct sevent), cmp_sevent); for (j = 0; j < len; j++) { + /* Skip duplicates */ + if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name)) + continue; if (name_only) { printf("%s ", aliases[j].name); continue; @@ -1192,6 +1223,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, printf("%*s", 8, "["); wordwrap(aliases[j].desc, 8, columns, 0); printf("]\n"); + if (verbose) + printf("%*s%s/%s/\n", 8, "", aliases[j].pmu, aliases[j].str); } else printf(" %-50s [Kernel PMU event]\n", aliases[j].name); printed++; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 25712034c815..00852ddc7741 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -43,6 +43,7 @@ struct perf_pmu_alias { char *desc; char *long_desc; char *topic; + char *str; struct list_head terms; /* HEAD struct parse_events_term -> list */ struct list_head list; /* ELEM */ char unit[UNIT_MAX_LEN+1]; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 6a6f44dd594b..35f5b7b7715c 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2061,7 +2061,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp, bool is_kprobe) { struct symbol *sym = NULL; - struct map *map; + struct map *map = NULL; u64 addr = tp->address; int ret = -ENOENT; @@ -3023,20 +3023,17 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev, tev->nargs = pev->nargs; tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); - if (!tev->args) { - err = -ENOMEM; + if (!tev->args) goto errout; - } + for (i = 0; i < tev->nargs; i++) copy_to_probe_trace_arg(&tev->args[i], &pev->args[i]); return 1; errout: - if (*tevs) { - clear_probe_trace_events(*tevs, 1); - *tevs = NULL; - } + clear_probe_trace_events(*tevs, 1); + *tevs = NULL; return err; } diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build index 6516e220c247..82d28c67e0f3 100644 --- a/tools/perf/util/scripting-engines/Build +++ b/tools/perf/util/scripting-engines/Build @@ -1,6 +1,6 @@ libperf-$(CONFIG_LIBPERL) += trace-event-perl.o libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o -CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default +CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index e55a132f69b7..c1555fd0035a 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -309,10 +309,10 @@ static SV *perl_process_callchain(struct perf_sample *sample, if (node->map) { struct map *map = node->map; const char *dsoname = "[unknown]"; - if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (map && map->dso) { if (symbol_conf.show_kernel_path && map->dso->long_name) dsoname = map->dso->long_name; - else if (map->dso->name) + else dsoname = map->dso->name; } if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) { @@ -350,8 +350,10 @@ static void perl_process_tracepoint(struct perf_sample *sample, if (evsel->attr.type != PERF_TYPE_TRACEPOINT) return; - if (!event) - die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + if (!event) { + pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + return; + } pid = raw_field_value(event, "common_pid", data); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index f268201048a0..4cdbc8f5f14d 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1191,7 +1191,7 @@ static int u64 sample_type = evsel->attr.sample_type; u64 read_format = evsel->attr.read_format; - /* Standard sample delievery. */ + /* Standard sample delivery. */ if (!(sample_type & PERF_SAMPLE_READ)) return tool->sample(tool, event, sample, evsel, machine); @@ -1901,7 +1901,7 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr) { char *bracket; - enum map_type i; + int i; struct ref_reloc_sym *ref; ref = zalloc(sizeof(struct ref_reloc_sym)); diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c index bcae659b6546..efb53772e0ec 100644 --- a/tools/perf/util/strfilter.c +++ b/tools/perf/util/strfilter.c @@ -269,6 +269,7 @@ static int strfilter_node__sprint(struct strfilter_node *node, char *buf) len = strfilter_node__sprint_pt(node->l, buf); if (len < 0) return len; + __fallthrough; case '!': if (buf) { *(buf + len++) = *node->p; diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index d8dfaf64b32e..bddca519dd58 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -21,6 +21,8 @@ s64 perf_atoll(const char *str) case 'b': case 'B': if (*p) goto out_err; + + __fallthrough; case '\0': return length; default: diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index dc93940de351..70e389bc4af7 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1460,9 +1460,11 @@ int dso__load(struct dso *dso, struct map *map) * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ if (!dso->has_build_id && - is_regular_file(dso->long_name) && - filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) + is_regular_file(dso->long_name)) { + __symbol__join_symfs(name, PATH_MAX, dso->long_name); + if (filename__read_build_id(name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); + } /* * Iterate over candidate debug images. diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index 7c6b33e8e2d2..63694e174e5c 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -21,7 +21,7 @@ size_t __symbol__fprintf_symname_offs(const struct symbol *sym, unsigned long offset; size_t length; - if (sym && sym->name) { + if (sym) { length = fprintf(fp, "%s", sym->name); if (al && print_offsets) { if (al->addr < sym->end) diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index f9eab200fd75..7c3fcc538a70 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -93,7 +93,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) { DIR *proc; int max_threads = 32, items, i; - char path[256]; + char path[NAME_MAX + 1 + 6]; struct dirent *dirent, **namelist = NULL; struct thread_map *threads = thread_map__alloc(max_threads); diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index d995743cb673..e7d60d05596d 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -42,7 +42,7 @@ #include "evsel.h" #include "debug.h" -#define VERSION "0.5" +#define VERSION "0.6" static int output_fd; @@ -170,6 +170,12 @@ static bool name_in_tp_list(char *sys, struct tracepoint_path *tps) return false; } +#define for_each_event(dir, dent, tps) \ + while ((dent = readdir(dir))) \ + if (dent->d_type == DT_DIR && \ + (strcmp(dent->d_name, ".")) && \ + (strcmp(dent->d_name, ".."))) \ + static int copy_event_system(const char *sys, struct tracepoint_path *tps) { struct dirent *dent; @@ -186,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) return -errno; } - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - !name_in_tp_list(dent->d_name, tps)) + for_each_event(dir, dent, tps) { + if (!name_in_tp_list(dent->d_name, tps)) continue; + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; @@ -210,12 +214,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) } rewinddir(dir); - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - !name_in_tp_list(dent->d_name, tps)) + for_each_event(dir, dent, tps) { + if (!name_in_tp_list(dent->d_name, tps)) continue; + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; @@ -290,13 +292,11 @@ static int record_event_files(struct tracepoint_path *tps) goto out; } - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - strcmp(dent->d_name, "ftrace") == 0 || + for_each_event(dir, dent, tps) { + if (strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; + count++; } @@ -307,13 +307,11 @@ static int record_event_files(struct tracepoint_path *tps) } rewinddir(dir); - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - strcmp(dent->d_name, "ftrace") == 0 || + for_each_event(dir, dent, tps) { + if (strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; + if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) { err = -ENOMEM; goto out; @@ -379,6 +377,34 @@ out: return err; } +static int record_saved_cmdline(void) +{ + unsigned int size; + char *path; + struct stat st; + int ret, err = 0; + + path = get_tracing_file("saved_cmdlines"); + if (!path) { + pr_debug("can't get tracing/saved_cmdline"); + return -ENOMEM; + } + + ret = stat(path, &st); + if (ret < 0) { + /* not found */ + size = 0; + if (write(output_fd, &size, 8) != 8) + err = -EIO; + goto out; + } + err = record_file(path, 8); + +out: + put_tracing_file(path); + return err; +} + static void put_tracepoints_path(struct tracepoint_path *tps) { @@ -539,6 +565,9 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, if (err) goto out; err = record_ftrace_printk(); + if (err) + goto out; + err = record_saved_cmdline(); out: /* diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 33b52eaa39db..de0078e21408 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -160,6 +160,23 @@ void parse_ftrace_printk(struct pevent *pevent, } } +void parse_saved_cmdline(struct pevent *pevent, + char *file, unsigned int size __maybe_unused) +{ + char *comm; + char *line; + char *next = NULL; + int pid; + + line = strtok_r(file, "\n", &next); + while (line) { + sscanf(line, "%d %ms", &pid, &comm); + pevent_register_comm(pevent, comm, pid); + free(comm); + line = strtok_r(NULL, "\n", &next); + } +} + int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size) { return pevent_parse_event(pevent, buf, size, "ftrace"); diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index b67a0ccf5ab9..27420159bf69 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -260,39 +260,53 @@ static int read_header_files(struct pevent *pevent) static int read_ftrace_file(struct pevent *pevent, unsigned long long size) { + int ret; char *buf; buf = malloc(size); - if (buf == NULL) + if (buf == NULL) { + pr_debug("memory allocation failure\n"); return -1; + } - if (do_read(buf, size) < 0) { - free(buf); - return -1; + ret = do_read(buf, size); + if (ret < 0) { + pr_debug("error reading ftrace file.\n"); + goto out; } - parse_ftrace_file(pevent, buf, size); + ret = parse_ftrace_file(pevent, buf, size); + if (ret < 0) + pr_debug("error parsing ftrace file.\n"); +out: free(buf); - return 0; + return ret; } static int read_event_file(struct pevent *pevent, char *sys, unsigned long long size) { + int ret; char *buf; buf = malloc(size); - if (buf == NULL) + if (buf == NULL) { + pr_debug("memory allocation failure\n"); return -1; + } - if (do_read(buf, size) < 0) { + ret = do_read(buf, size); + if (ret < 0) { free(buf); - return -1; + goto out; } - parse_event_file(pevent, buf, size, sys); + ret = parse_event_file(pevent, buf, size, sys); + if (ret < 0) + pr_debug("error parsing event file.\n"); +out: free(buf); - return 0; + return ret; } static int read_ftrace_files(struct pevent *pevent) @@ -341,6 +355,36 @@ static int read_event_files(struct pevent *pevent) return 0; } +static int read_saved_cmdline(struct pevent *pevent) +{ + unsigned long long size; + char *buf; + int ret; + + /* it can have 0 size */ + size = read8(pevent); + if (!size) + return 0; + + buf = malloc(size + 1); + if (buf == NULL) { + pr_debug("memory allocation failure\n"); + return -1; + } + + ret = do_read(buf, size); + if (ret < 0) { + pr_debug("error reading saved cmdlines\n"); + goto out; + } + + parse_saved_cmdline(pevent, buf, size); + ret = 0; +out: + free(buf); + return ret; +} + ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) { char buf[BUFSIZ]; @@ -379,10 +423,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) return -1; if (show_version) printf("version = %s\n", version); - free(version); - if (do_read(buf, 1) < 0) + if (do_read(buf, 1) < 0) { + free(version); return -1; + } file_bigendian = buf[0]; host_bigendian = bigendian(); @@ -423,6 +468,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) err = read_ftrace_printk(pevent); if (err) goto out; + if (atof(version) >= 0.6) { + err = read_saved_cmdline(pevent); + if (err) + goto out; + } size = trace_data_size; repipe = false; @@ -438,5 +488,6 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) out: if (pevent) trace_event__cleanup(tevent); + free(version); return size; } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index b0af9c81bb0d..1fbc044f9eb0 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -42,6 +42,7 @@ raw_field_value(struct event_format *event, const char *name, void *data); void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size); void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size); +void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size); ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe); diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 6fec84dff3f7..bfb9b7987692 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -35,6 +35,7 @@ #include "util.h" #include "debug.h" #include "asm/bug.h" +#include "dso.h" extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, @@ -297,15 +298,58 @@ static int read_unwind_spec_debug_frame(struct dso *dso, int fd; u64 ofs = dso->data.debug_frame_offset; + /* debug_frame can reside in: + * - dso + * - debug pointed by symsrc_filename + * - gnu_debuglink, which doesn't necessary + * has to be pointed by symsrc_filename + */ if (ofs == 0) { fd = dso__data_get_fd(dso, machine); - if (fd < 0) - return -EINVAL; + if (fd >= 0) { + ofs = elf_section_offset(fd, ".debug_frame"); + dso__data_put_fd(dso); + } + + if (ofs <= 0) { + fd = open(dso->symsrc_filename, O_RDONLY); + if (fd >= 0) { + ofs = elf_section_offset(fd, ".debug_frame"); + close(fd); + } + } + + if (ofs <= 0) { + char *debuglink = malloc(PATH_MAX); + int ret = 0; + + ret = dso__read_binary_type_filename( + dso, DSO_BINARY_TYPE__DEBUGLINK, + machine->root_dir, debuglink, PATH_MAX); + if (!ret) { + fd = open(debuglink, O_RDONLY); + if (fd >= 0) { + ofs = elf_section_offset(fd, + ".debug_frame"); + close(fd); + } + } + if (ofs > 0) { + if (dso->symsrc_filename != NULL) { + pr_warning( + "%s: overwrite symsrc(%s,%s)\n", + __func__, + dso->symsrc_filename, + debuglink); + free(dso->symsrc_filename); + } + dso->symsrc_filename = debuglink; + } else { + free(debuglink); + } + } - /* Check the .debug_frame section for unwinding info */ - ofs = elf_section_offset(fd, ".debug_frame"); dso->data.debug_frame_offset = ofs; - dso__data_put_fd(dso); } *offset = ofs; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 9ddd98827d12..d8b45cea54d0 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -85,7 +85,7 @@ int mkdir_p(char *path, mode_t mode) return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0; } -int rm_rf(char *path) +int rm_rf(const char *path) { DIR *dir; int ret = 0; @@ -789,3 +789,16 @@ int is_printable_array(char *p, unsigned int len) } return 1; } + +int unit_number__scnprintf(char *buf, size_t size, u64 n) +{ + char unit[4] = "BKMG"; + int i = 0; + + while (((n / 1024) > 1) && (i < 3)) { + n /= 1024; + i++; + } + + return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]); +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 1d639e38aa82..c74708da8571 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -209,7 +209,7 @@ static inline int sane_case(int x, int high) } int mkdir_p(char *path, mode_t mode); -int rm_rf(char *path); +int rm_rf(const char *path); struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *)); bool lsdir_no_dot_filter(const char *name, struct dirent *d); int copyfile(const char *from, const char *to); @@ -363,4 +363,5 @@ int is_printable_array(char *p, unsigned int len); int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); +int unit_number__scnprintf(char *buf, size_t size, u64 n); #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 8abbef164b4e..621578aa12d6 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -32,7 +32,6 @@ EXTRA_WARNINGS += -Wold-style-definition EXTRA_WARNINGS += -Wpacked EXTRA_WARNINGS += -Wredundant-decls EXTRA_WARNINGS += -Wshadow -EXTRA_WARNINGS += -Wstrict-aliasing=3 EXTRA_WARNINGS += -Wstrict-prototypes EXTRA_WARNINGS += -Wswitch-default EXTRA_WARNINGS += -Wswitch-enum @@ -40,12 +39,26 @@ EXTRA_WARNINGS += -Wundef EXTRA_WARNINGS += -Wwrite-strings EXTRA_WARNINGS += -Wformat +ifneq ($(CC), clang) +EXTRA_WARNINGS += -Wstrict-aliasing=3 +endif + ifneq ($(findstring $(MAKEFLAGS), w),w) PRINT_DIR = --no-print-directory else NO_SUBDIR = : endif +ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4 +ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),) + silent=1 +endif +else # make-3.8x +ifneq ($(filter s% -s%,$(MAKEFLAGS)),) + silent=1 +endif +endif + # # Define a callable command for descending to a new directory # @@ -58,7 +71,7 @@ descend = \ QUIET_SUBDIR0 = +$(MAKE) $(COMMAND_O) -C # space to separate -C and subdir QUIET_SUBDIR1 = -ifneq ($(findstring $(MAKEFLAGS),s),s) +ifneq ($(silent),1) ifneq ($(V),1) QUIET_CC = @echo ' CC '$@; QUIET_CC_FPIC = @echo ' CC FPIC '$@; diff --git a/tools/testing/selftests/locking/ww_mutex.sh b/tools/testing/selftests/locking/ww_mutex.sh new file mode 100644 index 000000000000..6905da965f3b --- /dev/null +++ b/tools/testing/selftests/locking/ww_mutex.sh @@ -0,0 +1,10 @@ +#!/bin/sh +# Runs API tests for struct ww_mutex (Wait/Wound mutexes) + +if /sbin/modprobe -q test-ww_mutex; then + /sbin/modprobe -q -r test-ww_mutex + echo "locking/ww_mutex: ok" +else + echo "locking/ww_mutex: [FAIL]" + exit 1 +fi diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST index b9611c523723..41bae5824339 100644 --- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST @@ -4,3 +4,4 @@ LOCK03 LOCK04 LOCK05 LOCK06 +LOCK07 diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK07 b/tools/testing/selftests/rcutorture/configs/lock/LOCK07 new file mode 100644 index 000000000000..1d1da1477fc3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK07 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot new file mode 100644 index 000000000000..97dadd1a9e45 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot @@ -0,0 +1 @@ +locktorture.torture_type=ww_mutex_lock diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon index f824b4c9d9d9..d2d2a86139db 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon @@ -1,5 +1,2 @@ CONFIG_RCU_TORTURE_TEST=y CONFIG_PRINTK_TIME=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 index 0a63e073a00c..6db705e55487 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 @@ -7,6 +7,7 @@ CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n CONFIG_RCU_TRACE=n +#CHECK#CONFIG_RCU_STALL_COMMON=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_PREEMPT_COUNT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 index f1892e0371c9..a59f7686e219 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 @@ -8,7 +8,8 @@ CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=n CONFIG_RCU_TRACE=y CONFIG_PROVE_LOCKING=y +CONFIG_PROVE_RCU_REPEATEDLY=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_DEBUG_LOCK_ALLOC=y -CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_PREEMPT_COUNT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index f572b873c620..359cb258f639 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -16,3 +16,6 @@ CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 index ef6a22c44dea..c1ab5926568b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 @@ -20,3 +20,7 @@ CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 index 7a17c503b382..3b93ee544e70 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 @@ -17,3 +17,6 @@ CONFIG_RCU_BOOST=y CONFIG_RCU_KTHREAD_PRIO=2 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 17cbe098b115..5af758e783c7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -19,3 +19,7 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y +CONFIG_RCU_EQS_DEBUG=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index 1257d3227b1e..d4cdc0d74e16 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -19,3 +19,6 @@ CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index d3e456b74cbe..4cb02bd28f08 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -20,3 +20,6 @@ CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index 3956b4131f72..b12a3ea1867e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -19,3 +19,6 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 index bb9b0c1a23c2..099cc63c6a3b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 @@ -17,8 +17,8 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_LOCKING=y -#CHECK#CONFIG_PROVE_RCU=y +CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_EQS_DEBUG=y diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index 4e2b1893d40d..364801b1a230 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -14,6 +14,7 @@ CONFIG_NO_HZ_FULL_SYSIDLE -- Do one. CONFIG_PREEMPT -- Do half. (First three and #8.) CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not. CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING. +CONFIG_PROVE_RCU_REPEATEDLY -- Do one. CONFIG_RCU_BOOST -- one of PREEMPT_RCU. CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing. CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others. @@ -25,7 +26,12 @@ CONFIG_RCU_NOCB_CPU_NONE -- Do one. CONFIG_RCU_NOCB_CPU_ZERO -- Do one. CONFIG_RCU_TRACE -- Do half. CONFIG_SMP -- Need one !SMP for PREEMPT_RCU. -!RCU_EXPERT -- Do a few, but these have to be vanilla configurations. +CONFIG_RCU_EXPERT=n -- Do a few, but these have to be vanilla configurations. +CONFIG_RCU_EQS_DEBUG -- Do at least one for CONFIG_NO_HZ_FULL and not. +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP -- Do for all but a couple TREE scenarios. +CONFIG_RCU_TORTURE_TEST_SLOW_INIT -- Do for all but a couple TREE scenarios. +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT -- Do for all but a couple TREE scenarios. + RCU-bh: Do one with PREEMPT and one with !PREEMPT. RCU-sched: Do one with PREEMPT but not BOOST. @@ -72,7 +78,30 @@ CONFIG_RCU_TORTURE_TEST_RUNNABLE Always used in KVM testing. +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY +CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY + + Inspection suffices, ignore. + CONFIG_PREEMPT_RCU CONFIG_TREE_RCU +CONFIG_TINY_RCU + + These are controlled by CONFIG_PREEMPT and/or CONFIG_SMP. + +CONFIG_SPARSE_RCU_POINTER + + Makes sense only for sparse runs, not for kernel builds. + +CONFIG_SRCU +CONFIG_TASKS_RCU + + Selected by CONFIG_RCU_TORTURE_TEST, so cannot disable. + +CONFIG_RCU_TRACE + + Implied by CONFIG_RCU_TRACE for Tree RCU. + - These are controlled by CONFIG_PREEMPT. +boot parameters ignored: TBD diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore new file mode 100644 index 000000000000..712a3d41a325 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore @@ -0,0 +1 @@ +srcu.c diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile new file mode 100644 index 000000000000..16b01559fa55 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile @@ -0,0 +1,16 @@ +all: srcu.c store_buffering + +LINUX_SOURCE = ../../../../../.. + +modified_srcu_input = $(LINUX_SOURCE)/include/linux/srcu.h \ + $(LINUX_SOURCE)/kernel/rcu/srcu.c + +modified_srcu_output = include/linux/srcu.h srcu.c + +include/linux/srcu.h: srcu.c + +srcu.c: modify_srcu.awk Makefile $(modified_srcu_input) + awk -f modify_srcu.awk $(modified_srcu_input) $(modified_srcu_output) + +store_buffering: + @cd tests/store_buffering; make diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore new file mode 100644 index 000000000000..1d016e66980a --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore @@ -0,0 +1 @@ +srcu.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h new file mode 100644 index 000000000000..f2860dd1b407 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h @@ -0,0 +1 @@ +#include <LINUX_SOURCE/linux/kconfig.h> diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h new file mode 100644 index 000000000000..4a3d538fef12 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h @@ -0,0 +1,155 @@ +/* + * This header has been modifies to remove definitions of types that + * are defined in standard userspace headers or are problematic for some + * other reason. + */ + +#ifndef _LINUX_TYPES_H +#define _LINUX_TYPES_H + +#define __EXPORTED_HEADERS__ +#include <uapi/linux/types.h> + +#ifndef __ASSEMBLY__ + +#define DECLARE_BITMAP(name, bits) \ + unsigned long name[BITS_TO_LONGS(bits)] + +typedef __u32 __kernel_dev_t; + +/* bsd */ +typedef unsigned char u_char; +typedef unsigned short u_short; +typedef unsigned int u_int; +typedef unsigned long u_long; + +/* sysv */ +typedef unsigned char unchar; +typedef unsigned short ushort; +typedef unsigned int uint; +typedef unsigned long ulong; + +#ifndef __BIT_TYPES_DEFINED__ +#define __BIT_TYPES_DEFINED__ + +typedef __u8 u_int8_t; +typedef __s8 int8_t; +typedef __u16 u_int16_t; +typedef __s16 int16_t; +typedef __u32 u_int32_t; +typedef __s32 int32_t; + +#endif /* !(__BIT_TYPES_DEFINED__) */ + +typedef __u8 uint8_t; +typedef __u16 uint16_t; +typedef __u32 uint32_t; + +/* this is a special 64bit data type that is 8-byte aligned */ +#define aligned_u64 __u64 __attribute__((aligned(8))) +#define aligned_be64 __be64 __attribute__((aligned(8))) +#define aligned_le64 __le64 __attribute__((aligned(8))) + +/** + * The type used for indexing onto a disc or disc partition. + * + * Linux always considers sectors to be 512 bytes long independently + * of the devices real block size. + * + * blkcnt_t is the type of the inode's block count. + */ +#ifdef CONFIG_LBDAF +typedef u64 sector_t; +#else +typedef unsigned long sector_t; +#endif + +/* + * The type of an index into the pagecache. + */ +#define pgoff_t unsigned long + +/* + * A dma_addr_t can hold any valid DMA address, i.e., any address returned + * by the DMA API. + * + * If the DMA API only uses 32-bit addresses, dma_addr_t need only be 32 + * bits wide. Bus addresses, e.g., PCI BARs, may be wider than 32 bits, + * but drivers do memory-mapped I/O to ioremapped kernel virtual addresses, + * so they don't care about the size of the actual bus addresses. + */ +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT +typedef u64 dma_addr_t; +#else +typedef u32 dma_addr_t; +#endif + +#ifdef CONFIG_PHYS_ADDR_T_64BIT +typedef u64 phys_addr_t; +#else +typedef u32 phys_addr_t; +#endif + +typedef phys_addr_t resource_size_t; + +/* + * This type is the placeholder for a hardware interrupt number. It has to be + * big enough to enclose whatever representation is used by a given platform. + */ +typedef unsigned long irq_hw_number_t; + +typedef struct { + int counter; +} atomic_t; + +#ifdef CONFIG_64BIT +typedef struct { + long counter; +} atomic64_t; +#endif + +struct list_head { + struct list_head *next, *prev; +}; + +struct hlist_head { + struct hlist_node *first; +}; + +struct hlist_node { + struct hlist_node *next, **pprev; +}; + +/** + * struct callback_head - callback structure for use with RCU and task_work + * @next: next update requests in a list + * @func: actual update function to call after the grace period. + * + * The struct is aligned to size of pointer. On most architectures it happens + * naturally due ABI requirements, but some architectures (like CRIS) have + * weird ABI and we need to ask it explicitly. + * + * The alignment is required to guarantee that bits 0 and 1 of @next will be + * clear under normal conditions -- as long as we use call_rcu(), + * call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback. + * + * This guarantee is important for few reasons: + * - future call_rcu_lazy() will make use of lower bits in the pointer; + * - the structure shares storage spacer in struct page with @compound_head, + * which encode PageTail() in bit 0. The guarantee is needed to avoid + * false-positive PageTail(). + */ +struct callback_head { + struct callback_head *next; + void (*func)(struct callback_head *head); +} __attribute__((aligned(sizeof(void *)))); +#define rcu_head callback_head + +typedef void (*rcu_callback_t)(struct rcu_head *head); +typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); + +/* clocksource cycle base type */ +typedef u64 cycle_t; + +#endif /* __ASSEMBLY__ */ +#endif /* _LINUX_TYPES_H */ diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk new file mode 100755 index 000000000000..8ff89043d0a9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk @@ -0,0 +1,375 @@ +#!/bin/awk -f + +# Modify SRCU for formal verification. The first argument should be srcu.h and +# the second should be srcu.c. Outputs modified srcu.h and srcu.c into the +# current directory. + +BEGIN { + if (ARGC != 5) { + print "Usange: input.h input.c output.h output.c" > "/dev/stderr"; + exit 1; + } + h_output = ARGV[3]; + c_output = ARGV[4]; + ARGC = 3; + + # Tokenize using FS and not RS as FS supports regular expressions. Each + # record is one line of source, except that backslashed lines are + # combined. Comments are treated as field separators, as are quotes. + quote_regexp="\"([^\\\\\"]|\\\\.)*\""; + comment_regexp="\\/\\*([^*]|\\*+[^*/])*\\*\\/|\\/\\/.*(\n|$)"; + FS="([ \\\\\t\n\v\f;,.=(){}+*/<>&|^-]|\\[|\\]|" comment_regexp "|" quote_regexp ")+"; + + inside_srcu_struct = 0; + inside_srcu_init_def = 0; + srcu_init_param_name = ""; + in_macro = 0; + brace_nesting = 0; + paren_nesting = 0; + + # Allow the manipulation of the last field separator after has been + # seen. + last_fs = ""; + # Whether the last field separator was intended to be output. + last_fs_print = 0; + + # rcu_batches stores the initialization for each instance of struct + # rcu_batch + + in_comment = 0; + + outputfile = ""; +} + +{ + prev_outputfile = outputfile; + if (FILENAME ~ /\.h$/) { + outputfile = h_output; + if (FNR != NR) { + print "Incorrect file order" > "/dev/stderr"; + exit 1; + } + } + else + outputfile = c_output; + + if (prev_outputfile && outputfile != prev_outputfile) { + new_outputfile = outputfile; + outputfile = prev_outputfile; + update_fieldsep("", 0); + outputfile = new_outputfile; + } +} + +# Combine the next line into $0. +function combine_line() { + ret = getline next_line; + if (ret == 0) { + # Don't allow two consecutive getlines at the end of the file + if (eof_found) { + print "Error: expected more input." > "/dev/stderr"; + exit 1; + } else { + eof_found = 1; + } + } else if (ret == -1) { + print "Error reading next line of file" FILENAME > "/dev/stderr"; + exit 1; + } + $0 = $0 "\n" next_line; +} + +# Combine backslashed lines and multiline comments. +function combine_backslashes() { + while (/\\$|\/\*([^*]|\*+[^*\/])*\**$/) { + combine_line(); + } +} + +function read_line() { + combine_line(); + combine_backslashes(); +} + +# Print out field separators and update variables that depend on them. Only +# print if p is true. Call with sep="" and p=0 to print out the last field +# separator. +function update_fieldsep(sep, p) { + # Count braces + sep_tmp = sep; + gsub(quote_regexp "|" comment_regexp, "", sep_tmp); + while (1) + { + if (sub("[^{}()]*\\{", "", sep_tmp)) { + brace_nesting++; + continue; + } + if (sub("[^{}()]*\\}", "", sep_tmp)) { + brace_nesting--; + if (brace_nesting < 0) { + print "Unbalanced braces!" > "/dev/stderr"; + exit 1; + } + continue; + } + if (sub("[^{}()]*\\(", "", sep_tmp)) { + paren_nesting++; + continue; + } + if (sub("[^{}()]*\\)", "", sep_tmp)) { + paren_nesting--; + if (paren_nesting < 0) { + print "Unbalanced parenthesis!" > "/dev/stderr"; + exit 1; + } + continue; + } + + break; + } + + if (last_fs_print) + printf("%s", last_fs) > outputfile; + last_fs = sep; + last_fs_print = p; +} + +# Shifts the fields down by n positions. Calls next if there are no more. If p +# is true then print out field separators. +function shift_fields(n, p) { + do { + if (match($0, FS) > 0) { + update_fieldsep(substr($0, RSTART, RLENGTH), p); + if (RSTART + RLENGTH <= length()) + $0 = substr($0, RSTART + RLENGTH); + else + $0 = ""; + } else { + update_fieldsep("", 0); + print "" > outputfile; + next; + } + } while (--n > 0); +} + +# Shifts and prints the first n fields. +function print_fields(n) { + do { + update_fieldsep("", 0); + printf("%s", $1) > outputfile; + shift_fields(1, 1); + } while (--n > 0); +} + +{ + combine_backslashes(); +} + +# Print leading FS +{ + if (match($0, "^(" FS ")+") > 0) { + update_fieldsep(substr($0, RSTART, RLENGTH), 1); + if (RSTART + RLENGTH <= length()) + $0 = substr($0, RSTART + RLENGTH); + else + $0 = ""; + } +} + +# Parse the line. +{ + while (NF > 0) { + if ($1 == "struct" && NF < 3) { + read_line(); + continue; + } + + if (FILENAME ~ /\.h$/ && !inside_srcu_struct && + brace_nesting == 0 && paren_nesting == 0 && + $1 == "struct" && $2 == "srcu_struct" && + $0 ~ "^struct(" FS ")+srcu_struct(" FS ")+\\{") { + inside_srcu_struct = 1; + print_fields(2); + continue; + } + if (inside_srcu_struct && brace_nesting == 0 && + paren_nesting == 0) { + inside_srcu_struct = 0; + update_fieldsep("", 0); + for (name in rcu_batches) + print "extern struct rcu_batch " name ";" > outputfile; + } + + if (inside_srcu_struct && $1 == "struct" && $2 == "rcu_batch") { + # Move rcu_batches outside of the struct. + rcu_batches[$3] = ""; + shift_fields(3, 1); + sub(/;[[:space:]]*$/, "", last_fs); + continue; + } + + if (FILENAME ~ /\.h$/ && !inside_srcu_init_def && + $1 == "#define" && $2 == "__SRCU_STRUCT_INIT") { + inside_srcu_init_def = 1; + srcu_init_param_name = $3; + in_macro = 1; + print_fields(3); + continue; + } + if (inside_srcu_init_def && brace_nesting == 0 && + paren_nesting == 0) { + inside_srcu_init_def = 0; + in_macro = 0; + continue; + } + + if (inside_srcu_init_def && brace_nesting == 1 && + paren_nesting == 0 && last_fs ~ /\.[[:space:]]*$/ && + $1 ~ /^[[:alnum:]_]+$/) { + name = $1; + if (name in rcu_batches) { + # Remove the dot. + sub(/\.[[:space:]]*$/, "", last_fs); + + old_record = $0; + do + shift_fields(1, 0); + while (last_fs !~ /,/ || paren_nesting > 0); + end_loc = length(old_record) - length($0); + end_loc += index(last_fs, ",") - length(last_fs); + + last_fs = substr(last_fs, index(last_fs, ",") + 1); + last_fs_print = 1; + + match(old_record, "^"name"("FS")+="); + start_loc = RSTART + RLENGTH; + + len = end_loc - start_loc; + initializer = substr(old_record, start_loc, len); + gsub(srcu_init_param_name "\\.", "", initializer); + rcu_batches[name] = initializer; + continue; + } + } + + # Don't include a nonexistent file + if (!in_macro && $1 == "#include" && /^#include[[:space:]]+"rcu\.h"/) { + update_fieldsep("", 0); + next; + } + + # Ignore most preprocessor stuff. + if (!in_macro && $1 ~ /#/) { + break; + } + + if (brace_nesting > 0 && $1 ~ "^[[:alnum:]_]+$" && NF < 2) { + read_line(); + continue; + } + if (brace_nesting > 0 && + $0 ~ "^[[:alnum:]_]+[[:space:]]*(\\.|->)[[:space:]]*[[:alnum:]_]+" && + $2 in rcu_batches) { + # Make uses of rcu_batches global. Somewhat unreliable. + shift_fields(1, 0); + print_fields(1); + continue; + } + + if ($1 == "static" && NF < 3) { + read_line(); + continue; + } + if ($1 == "static" && ($2 == "bool" && $3 == "try_check_zero" || + $2 == "void" && $3 == "srcu_flip")) { + shift_fields(1, 1); + print_fields(2); + continue; + } + + # Distinguish between read-side and write-side memory barriers. + if ($1 == "smp_mb" && NF < 2) { + read_line(); + continue; + } + if (match($0, /^smp_mb[[:space:]();\/*]*[[:alnum:]]/)) { + barrier_letter = substr($0, RLENGTH, 1); + if (barrier_letter ~ /A|D/) + new_barrier_name = "sync_smp_mb"; + else if (barrier_letter ~ /B|C/) + new_barrier_name = "rs_smp_mb"; + else { + print "Unrecognized memory barrier." > "/dev/null"; + exit 1; + } + + shift_fields(1, 1); + printf("%s", new_barrier_name) > outputfile; + continue; + } + + # Skip definition of rcu_synchronize, since it is already + # defined in misc.h. Only present in old versions of srcu. + if (brace_nesting == 0 && paren_nesting == 0 && + $1 == "struct" && $2 == "rcu_synchronize" && + $0 ~ "^struct(" FS ")+rcu_synchronize(" FS ")+\\{") { + shift_fields(2, 0); + while (brace_nesting) { + if (NF < 2) + read_line(); + shift_fields(1, 0); + } + } + + # Skip definition of wakeme_after_rcu for the same reason + if (brace_nesting == 0 && $1 == "static" && $2 == "void" && + $3 == "wakeme_after_rcu") { + while (NF < 5) + read_line(); + shift_fields(3, 0); + do { + while (NF < 3) + read_line(); + shift_fields(1, 0); + } while (paren_nesting || brace_nesting); + } + + if ($1 ~ /^(unsigned|long)$/ && NF < 3) { + read_line(); + continue; + } + + # Give srcu_batches_completed the correct type for old SRCU. + if (brace_nesting == 0 && $1 == "long" && + $2 == "srcu_batches_completed") { + update_fieldsep("", 0); + printf("unsigned ") > outputfile; + print_fields(2); + continue; + } + if (brace_nesting == 0 && $1 == "unsigned" && $2 == "long" && + $3 == "srcu_batches_completed") { + print_fields(3); + continue; + } + + # Just print out the input code by default. + print_fields(1); + } + update_fieldsep("", 0); + print > outputfile; + next; +} + +END { + update_fieldsep("", 0); + + if (brace_nesting != 0) { + print "Unbalanced braces!" > "/dev/stderr"; + exit 1; + } + + # Define the rcu_batches + for (name in rcu_batches) + print "struct rcu_batch " name " = " rcu_batches[name] ";" > c_output; +} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h new file mode 100644 index 000000000000..a64955447995 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h @@ -0,0 +1,16 @@ +#ifndef ASSUME_H +#define ASSUME_H + +/* Provide an assumption macro that can be disabled for gcc. */ +#ifdef RUN +#define assume(x) \ + do { \ + /* Evaluate x to suppress warnings. */ \ + (void) (x); \ + } while (0) + +#else +#define assume(x) __CPROVER_assume(x) +#endif + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h new file mode 100644 index 000000000000..6687acc08e6d --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h @@ -0,0 +1,41 @@ +#ifndef BARRIERS_H +#define BARRIERS_H + +#define barrier() __asm__ __volatile__("" : : : "memory") + +#ifdef RUN +#define smp_mb() __sync_synchronize() +#define smp_mb__after_unlock_lock() __sync_synchronize() +#else +/* + * Copied from CBMC's implementation of __sync_synchronize(), which + * seems to be disabled by default. + */ +#define smp_mb() __CPROVER_fence("WWfence", "RRfence", "RWfence", "WRfence", \ + "WWcumul", "RRcumul", "RWcumul", "WRcumul") +#define smp_mb__after_unlock_lock() __CPROVER_fence("WWfence", "RRfence", "RWfence", "WRfence", \ + "WWcumul", "RRcumul", "RWcumul", "WRcumul") +#endif + +/* + * Allow memory barriers to be disabled in either the read or write side + * of SRCU individually. + */ + +#ifndef NO_SYNC_SMP_MB +#define sync_smp_mb() smp_mb() +#else +#define sync_smp_mb() do {} while (0) +#endif + +#ifndef NO_READ_SIDE_SMP_MB +#define rs_smp_mb() smp_mb() +#else +#define rs_smp_mb() do {} while (0) +#endif + +#define ACCESS_ONCE(x) (*(volatile typeof(x) *) &(x)) +#define READ_ONCE(x) ACCESS_ONCE(x) +#define WRITE_ONCE(x, val) (ACCESS_ONCE(x) = (val)) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h new file mode 100644 index 000000000000..2a80e91f78e7 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h @@ -0,0 +1,13 @@ +#ifndef BUG_ON_H +#define BUG_ON_H + +#include <assert.h> + +#define BUG() assert(0) +#define BUG_ON(x) assert(!(x)) + +/* Does it make sense to treat warnings as errors? */ +#define WARN() BUG() +#define WARN_ON(x) (BUG_ON(x), false) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c new file mode 100644 index 000000000000..29eb5d2697ed --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c @@ -0,0 +1,13 @@ +#include <config.h> + +/* Include all source files. */ + +#include "include_srcu.c" + +#include "preempt.c" +#include "misc.c" + +/* Used by test.c files */ +#include <pthread.h> +#include <stdlib.h> +#include <linux/srcu.h> diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h new file mode 100644 index 000000000000..a60038aeea7a --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h @@ -0,0 +1,27 @@ +/* "Cheater" definitions based on restricted Kconfig choices. */ + +#undef CONFIG_TINY_RCU +#undef __CHECKER__ +#undef CONFIG_DEBUG_LOCK_ALLOC +#undef CONFIG_DEBUG_OBJECTS_RCU_HEAD +#undef CONFIG_HOTPLUG_CPU +#undef CONFIG_MODULES +#undef CONFIG_NO_HZ_FULL_SYSIDLE +#undef CONFIG_PREEMPT_COUNT +#undef CONFIG_PREEMPT_RCU +#undef CONFIG_PROVE_RCU +#undef CONFIG_RCU_NOCB_CPU +#undef CONFIG_RCU_NOCB_CPU_ALL +#undef CONFIG_RCU_STALL_COMMON +#undef CONFIG_RCU_TRACE +#undef CONFIG_RCU_USER_QS +#undef CONFIG_TASKS_RCU +#define CONFIG_TREE_RCU + +#define CONFIG_GENERIC_ATOMIC64 + +#if NR_CPUS > 1 +#define CONFIG_SMP +#else +#undef CONFIG_SMP +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c new file mode 100644 index 000000000000..5ec582a53018 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c @@ -0,0 +1,31 @@ +#include <config.h> + +#include <assert.h> +#include <errno.h> +#include <inttypes.h> +#include <pthread.h> +#include <stddef.h> +#include <string.h> +#include <sys/types.h> + +#include "int_typedefs.h" + +#include "barriers.h" +#include "bug_on.h" +#include "locks.h" +#include "misc.h" +#include "preempt.h" +#include "percpu.h" +#include "workqueues.h" + +#ifdef USE_SIMPLE_SYNC_SRCU +#define synchronize_srcu(sp) synchronize_srcu_original(sp) +#endif + +#include <srcu.c> + +#ifdef USE_SIMPLE_SYNC_SRCU +#undef synchronize_srcu + +#include "simple_sync_srcu.c" +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h new file mode 100644 index 000000000000..3aad63917858 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h @@ -0,0 +1,33 @@ +#ifndef INT_TYPEDEFS_H +#define INT_TYPEDEFS_H + +#include <inttypes.h> + +typedef int8_t s8; +typedef uint8_t u8; +typedef int16_t s16; +typedef uint16_t u16; +typedef int32_t s32; +typedef uint32_t u32; +typedef int64_t s64; +typedef uint64_t u64; + +typedef int8_t __s8; +typedef uint8_t __u8; +typedef int16_t __s16; +typedef uint16_t __u16; +typedef int32_t __s32; +typedef uint32_t __u32; +typedef int64_t __s64; +typedef uint64_t __u64; + +#define S8_C(x) INT8_C(x) +#define U8_C(x) UINT8_C(x) +#define S16_C(x) INT16_C(x) +#define U16_C(x) UINT16_C(x) +#define S32_C(x) INT32_C(x) +#define U32_C(x) UINT32_C(x) +#define S64_C(x) INT64_C(x) +#define U64_C(x) UINT64_C(x) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h new file mode 100644 index 000000000000..356004665576 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h @@ -0,0 +1,220 @@ +#ifndef LOCKS_H +#define LOCKS_H + +#include <limits.h> +#include <pthread.h> +#include <stdbool.h> + +#include "assume.h" +#include "bug_on.h" +#include "preempt.h" + +int nondet_int(void); + +#define __acquire(x) +#define __acquires(x) +#define __release(x) +#define __releases(x) + +/* Only use one lock mechanism. Select which one. */ +#ifdef PTHREAD_LOCK +struct lock_impl { + pthread_mutex_t mutex; +}; + +static inline void lock_impl_lock(struct lock_impl *lock) +{ + BUG_ON(pthread_mutex_lock(&lock->mutex)); +} + +static inline void lock_impl_unlock(struct lock_impl *lock) +{ + BUG_ON(pthread_mutex_unlock(&lock->mutex)); +} + +static inline bool lock_impl_trylock(struct lock_impl *lock) +{ + int err = pthread_mutex_trylock(&lock->mutex); + + if (!err) + return true; + else if (err == EBUSY) + return false; + BUG(); +} + +static inline void lock_impl_init(struct lock_impl *lock) +{ + pthread_mutex_init(&lock->mutex, NULL); +} + +#define LOCK_IMPL_INITIALIZER {.mutex = PTHREAD_MUTEX_INITIALIZER} + +#else /* !defined(PTHREAD_LOCK) */ +/* Spinlock that assumes that it always gets the lock immediately. */ + +struct lock_impl { + bool locked; +}; + +static inline bool lock_impl_trylock(struct lock_impl *lock) +{ +#ifdef RUN + /* TODO: Should this be a test and set? */ + return __sync_bool_compare_and_swap(&lock->locked, false, true); +#else + __CPROVER_atomic_begin(); + bool old_locked = lock->locked; + lock->locked = true; + __CPROVER_atomic_end(); + + /* Minimal barrier to prevent accesses leaking out of lock. */ + __CPROVER_fence("RRfence", "RWfence"); + + return !old_locked; +#endif +} + +static inline void lock_impl_lock(struct lock_impl *lock) +{ + /* + * CBMC doesn't support busy waiting, so just assume that the + * lock is available. + */ + assume(lock_impl_trylock(lock)); + + /* + * If the lock was already held by this thread then the assumption + * is unsatisfiable (deadlock). + */ +} + +static inline void lock_impl_unlock(struct lock_impl *lock) +{ +#ifdef RUN + BUG_ON(!__sync_bool_compare_and_swap(&lock->locked, true, false)); +#else + /* Minimal barrier to prevent accesses leaking out of lock. */ + __CPROVER_fence("RWfence", "WWfence"); + + __CPROVER_atomic_begin(); + bool old_locked = lock->locked; + lock->locked = false; + __CPROVER_atomic_end(); + + BUG_ON(!old_locked); +#endif +} + +static inline void lock_impl_init(struct lock_impl *lock) +{ + lock->locked = false; +} + +#define LOCK_IMPL_INITIALIZER {.locked = false} + +#endif /* !defined(PTHREAD_LOCK) */ + +/* + * Implement spinlocks using the lock mechanism. Wrap the lock to prevent mixing + * locks of different types. + */ +typedef struct { + struct lock_impl internal_lock; +} spinlock_t; + +#define SPIN_LOCK_UNLOCKED {.internal_lock = LOCK_IMPL_INITIALIZER} +#define __SPIN_LOCK_UNLOCKED(x) SPIN_LOCK_UNLOCKED +#define DEFINE_SPINLOCK(x) spinlock_t x = SPIN_LOCK_UNLOCKED + +static inline void spin_lock_init(spinlock_t *lock) +{ + lock_impl_init(&lock->internal_lock); +} + +static inline void spin_lock(spinlock_t *lock) +{ + /* + * Spin locks also need to be removed in order to eliminate all + * memory barriers. They are only used by the write side anyway. + */ +#ifndef NO_SYNC_SMP_MB + preempt_disable(); + lock_impl_lock(&lock->internal_lock); +#endif +} + +static inline void spin_unlock(spinlock_t *lock) +{ +#ifndef NO_SYNC_SMP_MB + lock_impl_unlock(&lock->internal_lock); + preempt_enable(); +#endif +} + +/* Don't bother with interrupts */ +#define spin_lock_irq(lock) spin_lock(lock) +#define spin_unlock_irq(lock) spin_unlock(lock) +#define spin_lock_irqsave(lock, flags) spin_lock(lock) +#define spin_unlock_irqrestore(lock, flags) spin_unlock(lock) + +/* + * This is supposed to return an int, but I think that a bool should work as + * well. + */ +static inline bool spin_trylock(spinlock_t *lock) +{ +#ifndef NO_SYNC_SMP_MB + preempt_disable(); + return lock_impl_trylock(&lock->internal_lock); +#else + return true; +#endif +} + +struct completion { + /* Hopefuly this won't overflow. */ + unsigned int count; +}; + +#define COMPLETION_INITIALIZER(x) {.count = 0} +#define DECLARE_COMPLETION(x) struct completion x = COMPLETION_INITIALIZER(x) +#define DECLARE_COMPLETION_ONSTACK(x) DECLARE_COMPLETION(x) + +static inline void init_completion(struct completion *c) +{ + c->count = 0; +} + +static inline void wait_for_completion(struct completion *c) +{ + unsigned int prev_count = __sync_fetch_and_sub(&c->count, 1); + + assume(prev_count); +} + +static inline void complete(struct completion *c) +{ + unsigned int prev_count = __sync_fetch_and_add(&c->count, 1); + + BUG_ON(prev_count == UINT_MAX); +} + +/* This function probably isn't very useful for CBMC. */ +static inline bool try_wait_for_completion(struct completion *c) +{ + BUG(); +} + +static inline bool completion_done(struct completion *c) +{ + return c->count; +} + +/* TODO: Implement complete_all */ +static inline void complete_all(struct completion *c) +{ + BUG(); +} + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c new file mode 100644 index 000000000000..ca892e3b2351 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c @@ -0,0 +1,11 @@ +#include <config.h> + +#include "misc.h" +#include "bug_on.h" + +struct rcu_head; + +void wakeme_after_rcu(struct rcu_head *head) +{ + BUG(); +} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h new file mode 100644 index 000000000000..aca50030f954 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h @@ -0,0 +1,58 @@ +#ifndef MISC_H +#define MISC_H + +#include "assume.h" +#include "int_typedefs.h" +#include "locks.h" + +#include <linux/types.h> + +/* Probably won't need to deal with bottom halves. */ +static inline void local_bh_disable(void) {} +static inline void local_bh_enable(void) {} + +#define MODULE_ALIAS(X) +#define module_param(...) +#define EXPORT_SYMBOL_GPL(x) + +#define container_of(ptr, type, member) ({ \ + const typeof(((type *)0)->member) *__mptr = (ptr); \ + (type *)((char *)__mptr - offsetof(type, member)); \ +}) + +#ifndef USE_SIMPLE_SYNC_SRCU +/* Abuse udelay to make sure that busy loops terminate. */ +#define udelay(x) assume(0) + +#else + +/* The simple custom synchronize_srcu is ok with try_check_zero failing. */ +#define udelay(x) do { } while (0) +#endif + +#define trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ + do { } while (0) + +#define notrace + +/* Avoid including rcupdate.h */ +struct rcu_synchronize { + struct rcu_head head; + struct completion completion; +}; + +void wakeme_after_rcu(struct rcu_head *head); + +#define rcu_lock_acquire(a) do { } while (0) +#define rcu_lock_release(a) do { } while (0) +#define rcu_lockdep_assert(c, s) do { } while (0) +#define RCU_LOCKDEP_WARN(c, s) do { } while (0) + +/* Let CBMC non-deterministically choose switch between normal and expedited. */ +bool rcu_gp_is_normal(void); +bool rcu_gp_is_expedited(void); + +/* Do the same for old versions of rcu. */ +#define rcu_expedited (rcu_gp_is_expedited()) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h new file mode 100644 index 000000000000..3de5a49de49b --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h @@ -0,0 +1,92 @@ +#ifndef PERCPU_H +#define PERCPU_H + +#include <stddef.h> +#include "bug_on.h" +#include "preempt.h" + +#define __percpu + +/* Maximum size of any percpu data. */ +#define PERCPU_OFFSET (4 * sizeof(long)) + +/* Ignore alignment, as CBMC doesn't care about false sharing. */ +#define alloc_percpu(type) __alloc_percpu(sizeof(type), 1) + +static inline void *__alloc_percpu(size_t size, size_t align) +{ + BUG(); + return NULL; +} + +static inline void free_percpu(void *ptr) +{ + BUG(); +} + +#define per_cpu_ptr(ptr, cpu) \ + ((typeof(ptr)) ((char *) (ptr) + PERCPU_OFFSET * cpu)) + +#define __this_cpu_inc(pcp) __this_cpu_add(pcp, 1) +#define __this_cpu_dec(pcp) __this_cpu_sub(pcp, 1) +#define __this_cpu_sub(pcp, n) __this_cpu_add(pcp, -(typeof(pcp)) (n)) + +#define this_cpu_inc(pcp) this_cpu_add(pcp, 1) +#define this_cpu_dec(pcp) this_cpu_sub(pcp, 1) +#define this_cpu_sub(pcp, n) this_cpu_add(pcp, -(typeof(pcp)) (n)) + +/* Make CBMC use atomics to work around bug. */ +#ifdef RUN +#define THIS_CPU_ADD_HELPER(ptr, x) (*(ptr) += (x)) +#else +/* + * Split the atomic into a read and a write so that it has the least + * possible ordering. + */ +#define THIS_CPU_ADD_HELPER(ptr, x) \ + do { \ + typeof(ptr) this_cpu_add_helper_ptr = (ptr); \ + typeof(ptr) this_cpu_add_helper_x = (x); \ + typeof(*ptr) this_cpu_add_helper_temp; \ + __CPROVER_atomic_begin(); \ + this_cpu_add_helper_temp = *(this_cpu_add_helper_ptr); \ + __CPROVER_atomic_end(); \ + this_cpu_add_helper_temp += this_cpu_add_helper_x; \ + __CPROVER_atomic_begin(); \ + *(this_cpu_add_helper_ptr) = this_cpu_add_helper_temp; \ + __CPROVER_atomic_end(); \ + } while (0) +#endif + +/* + * For some reason CBMC needs an atomic operation even though this is percpu + * data. + */ +#define __this_cpu_add(pcp, n) \ + do { \ + BUG_ON(preemptible()); \ + THIS_CPU_ADD_HELPER(per_cpu_ptr(&(pcp), thread_cpu_id), \ + (typeof(pcp)) (n)); \ + } while (0) + +#define this_cpu_add(pcp, n) \ + do { \ + int this_cpu_add_impl_cpu = get_cpu(); \ + THIS_CPU_ADD_HELPER(per_cpu_ptr(&(pcp), this_cpu_add_impl_cpu), \ + (typeof(pcp)) (n)); \ + put_cpu(); \ + } while (0) + +/* + * This will cause a compiler warning because of the cast from char[][] to + * type*. This will cause a compile time error if type is too big. + */ +#define DEFINE_PER_CPU(type, name) \ + char name[NR_CPUS][PERCPU_OFFSET]; \ + typedef char percpu_too_big_##name \ + [sizeof(type) > PERCPU_OFFSET ? -1 : 1] + +#define for_each_possible_cpu(cpu) \ + for ((cpu) = 0; (cpu) < NR_CPUS; ++(cpu)) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c new file mode 100644 index 000000000000..4f1b068e9b7a --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c @@ -0,0 +1,78 @@ +#include <config.h> + +#include "preempt.h" + +#include "assume.h" +#include "locks.h" + +/* Support NR_CPUS of at most 64 */ +#define CPU_PREEMPTION_LOCKS_INIT0 LOCK_IMPL_INITIALIZER +#define CPU_PREEMPTION_LOCKS_INIT1 \ + CPU_PREEMPTION_LOCKS_INIT0, CPU_PREEMPTION_LOCKS_INIT0 +#define CPU_PREEMPTION_LOCKS_INIT2 \ + CPU_PREEMPTION_LOCKS_INIT1, CPU_PREEMPTION_LOCKS_INIT1 +#define CPU_PREEMPTION_LOCKS_INIT3 \ + CPU_PREEMPTION_LOCKS_INIT2, CPU_PREEMPTION_LOCKS_INIT2 +#define CPU_PREEMPTION_LOCKS_INIT4 \ + CPU_PREEMPTION_LOCKS_INIT3, CPU_PREEMPTION_LOCKS_INIT3 +#define CPU_PREEMPTION_LOCKS_INIT5 \ + CPU_PREEMPTION_LOCKS_INIT4, CPU_PREEMPTION_LOCKS_INIT4 + +/* + * Simulate disabling preemption by locking a particular cpu. NR_CPUS + * should be the actual number of cpus, not just the maximum. + */ +struct lock_impl cpu_preemption_locks[NR_CPUS] = { + CPU_PREEMPTION_LOCKS_INIT0 +#if (NR_CPUS - 1) & 1 + , CPU_PREEMPTION_LOCKS_INIT0 +#endif +#if (NR_CPUS - 1) & 2 + , CPU_PREEMPTION_LOCKS_INIT1 +#endif +#if (NR_CPUS - 1) & 4 + , CPU_PREEMPTION_LOCKS_INIT2 +#endif +#if (NR_CPUS - 1) & 8 + , CPU_PREEMPTION_LOCKS_INIT3 +#endif +#if (NR_CPUS - 1) & 16 + , CPU_PREEMPTION_LOCKS_INIT4 +#endif +#if (NR_CPUS - 1) & 32 + , CPU_PREEMPTION_LOCKS_INIT5 +#endif +}; + +#undef CPU_PREEMPTION_LOCKS_INIT0 +#undef CPU_PREEMPTION_LOCKS_INIT1 +#undef CPU_PREEMPTION_LOCKS_INIT2 +#undef CPU_PREEMPTION_LOCKS_INIT3 +#undef CPU_PREEMPTION_LOCKS_INIT4 +#undef CPU_PREEMPTION_LOCKS_INIT5 + +__thread int thread_cpu_id; +__thread int preempt_disable_count; + +void preempt_disable(void) +{ + BUG_ON(preempt_disable_count < 0 || preempt_disable_count == INT_MAX); + + if (preempt_disable_count++) + return; + + thread_cpu_id = nondet_int(); + assume(thread_cpu_id >= 0); + assume(thread_cpu_id < NR_CPUS); + lock_impl_lock(&cpu_preemption_locks[thread_cpu_id]); +} + +void preempt_enable(void) +{ + BUG_ON(preempt_disable_count < 1); + + if (--preempt_disable_count) + return; + + lock_impl_unlock(&cpu_preemption_locks[thread_cpu_id]); +} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h new file mode 100644 index 000000000000..2f95ee0e4dd5 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h @@ -0,0 +1,58 @@ +#ifndef PREEMPT_H +#define PREEMPT_H + +#include <stdbool.h> + +#include "bug_on.h" + +/* This flag contains garbage if preempt_disable_count is 0. */ +extern __thread int thread_cpu_id; + +/* Support recursive preemption disabling. */ +extern __thread int preempt_disable_count; + +void preempt_disable(void); +void preempt_enable(void); + +static inline void preempt_disable_notrace(void) +{ + preempt_disable(); +} + +static inline void preempt_enable_no_resched(void) +{ + preempt_enable(); +} + +static inline void preempt_enable_notrace(void) +{ + preempt_enable(); +} + +static inline int preempt_count(void) +{ + return preempt_disable_count; +} + +static inline bool preemptible(void) +{ + return !preempt_count(); +} + +static inline int get_cpu(void) +{ + preempt_disable(); + return thread_cpu_id; +} + +static inline void put_cpu(void) +{ + preempt_enable(); +} + +static inline void might_sleep(void) +{ + BUG_ON(preempt_disable_count); +} + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c new file mode 100644 index 000000000000..ac9cbc62b411 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c @@ -0,0 +1,50 @@ +#include <config.h> + +#include <assert.h> +#include <errno.h> +#include <inttypes.h> +#include <pthread.h> +#include <stddef.h> +#include <string.h> +#include <sys/types.h> + +#include "int_typedefs.h" + +#include "barriers.h" +#include "bug_on.h" +#include "locks.h" +#include "misc.h" +#include "preempt.h" +#include "percpu.h" +#include "workqueues.h" + +#include <linux/srcu.h> + +/* Functions needed from modify_srcu.c */ +bool try_check_zero(struct srcu_struct *sp, int idx, int trycount); +void srcu_flip(struct srcu_struct *sp); + +/* Simpler implementation of synchronize_srcu that ignores batching. */ +void synchronize_srcu(struct srcu_struct *sp) +{ + int idx; + /* + * This code assumes that try_check_zero will succeed anyway, + * so there is no point in multiple tries. + */ + const int trycount = 1; + + might_sleep(); + + /* Ignore the lock, as multiple writers aren't working yet anyway. */ + + idx = 1 ^ (sp->completed & 1); + + /* For comments see srcu_advance_batches. */ + + assume(try_check_zero(sp, idx, trycount)); + + srcu_flip(sp); + + assume(try_check_zero(sp, idx^1, trycount)); +} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h new file mode 100644 index 000000000000..e58c8dfd3e90 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h @@ -0,0 +1,102 @@ +#ifndef WORKQUEUES_H +#define WORKQUEUES_H + +#include <stdbool.h> + +#include "barriers.h" +#include "bug_on.h" +#include "int_typedefs.h" + +#include <linux/types.h> + +/* Stub workqueue implementation. */ + +struct work_struct; +typedef void (*work_func_t)(struct work_struct *work); +void delayed_work_timer_fn(unsigned long __data); + +struct work_struct { +/* atomic_long_t data; */ + unsigned long data; + + struct list_head entry; + work_func_t func; +#ifdef CONFIG_LOCKDEP + struct lockdep_map lockdep_map; +#endif +}; + +struct timer_list { + struct hlist_node entry; + unsigned long expires; + void (*function)(unsigned long); + unsigned long data; + u32 flags; + int slack; +}; + +struct delayed_work { + struct work_struct work; + struct timer_list timer; + + /* target workqueue and CPU ->timer uses to queue ->work */ + struct workqueue_struct *wq; + int cpu; +}; + + +static inline bool schedule_work(struct work_struct *work) +{ + BUG(); + return true; +} + +static inline bool schedule_work_on(int cpu, struct work_struct *work) +{ + BUG(); + return true; +} + +static inline bool queue_work(struct workqueue_struct *wq, + struct work_struct *work) +{ + BUG(); + return true; +} + +static inline bool queue_delayed_work(struct workqueue_struct *wq, + struct delayed_work *dwork, + unsigned long delay) +{ + BUG(); + return true; +} + +#define INIT_WORK(w, f) \ + do { \ + (w)->data = 0; \ + (w)->func = (f); \ + } while (0) + +#define INIT_DELAYED_WORK(w, f) INIT_WORK(&(w)->work, (f)) + +#define __WORK_INITIALIZER(n, f) { \ + .data = 0, \ + .entry = { &(n).entry, &(n).entry }, \ + .func = f \ + } + +/* Don't bother initializing timer. */ +#define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ + .work = __WORK_INITIALIZER((n).work, (f)), \ + } + +#define DECLARE_WORK(n, f) \ + struct workqueue_struct n = __WORK_INITIALIZER + +#define DECLARE_DELAYED_WORK(n, f) \ + struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) + +#define system_power_efficient_wq ((struct workqueue_struct *) NULL) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore new file mode 100644 index 000000000000..f47cb2045f13 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore @@ -0,0 +1 @@ +*.out diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile new file mode 100644 index 000000000000..3a3aee149225 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile @@ -0,0 +1,11 @@ +CBMC_FLAGS = -I../.. -I../../src -I../../include -I../../empty_includes -32 -pointer-check -mm pso + +all: + for i in ./*.pass; do \ + echo $$i ; \ + CBMC_FLAGS="$(CBMC_FLAGS)" sh ../test_script.sh --should-pass $$i > $$i.out 2>&1 ; \ + done + for i in ./*.fail; do \ + echo $$i ; \ + CBMC_FLAGS="$(CBMC_FLAGS)" sh ../test_script.sh --should-fail $$i > $$i.out 2>&1 ; \ + done diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail new file mode 100644 index 000000000000..40c8075919d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail @@ -0,0 +1 @@ +test_cbmc_options="-DASSERT_END" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail new file mode 100644 index 000000000000..ada5baf0b60d --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail @@ -0,0 +1 @@ +test_cbmc_options="-DFORCE_FAILURE" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail new file mode 100644 index 000000000000..8fe00c8db466 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail @@ -0,0 +1 @@ +test_cbmc_options="-DFORCE_FAILURE_2" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail new file mode 100644 index 000000000000..612ed6772844 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail @@ -0,0 +1 @@ +test_cbmc_options="-DFORCE_FAILURE_3" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c new file mode 100644 index 000000000000..470b1105a112 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c @@ -0,0 +1,72 @@ +#include <src/combined_source.c> + +int x; +int y; + +int __unbuffered_tpr_x; +int __unbuffered_tpr_y; + +DEFINE_SRCU(ss); + +void rcu_reader(void) +{ + int idx; + +#ifndef FORCE_FAILURE_3 + idx = srcu_read_lock(&ss); +#endif + might_sleep(); + + __unbuffered_tpr_y = READ_ONCE(y); +#ifdef FORCE_FAILURE + srcu_read_unlock(&ss, idx); + idx = srcu_read_lock(&ss); +#endif + WRITE_ONCE(x, 1); + +#ifndef FORCE_FAILURE_3 + srcu_read_unlock(&ss, idx); +#endif + might_sleep(); +} + +void *thread_update(void *arg) +{ + WRITE_ONCE(y, 1); +#ifndef FORCE_FAILURE_2 + synchronize_srcu(&ss); +#endif + might_sleep(); + __unbuffered_tpr_x = READ_ONCE(x); + + return NULL; +} + +void *thread_process_reader(void *arg) +{ + rcu_reader(); + + return NULL; +} + +int main(int argc, char *argv[]) +{ + pthread_t tu; + pthread_t tpr; + + if (pthread_create(&tu, NULL, thread_update, NULL)) + abort(); + if (pthread_create(&tpr, NULL, thread_process_reader, NULL)) + abort(); + if (pthread_join(tu, NULL)) + abort(); + if (pthread_join(tpr, NULL)) + abort(); + assert(__unbuffered_tpr_y != 0 || __unbuffered_tpr_x != 0); + +#ifdef ASSERT_END + assert(0); +#endif + + return 0; +} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh new file mode 100755 index 000000000000..d1545972a0fa --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh @@ -0,0 +1,102 @@ +#!/bin/sh + +# This script expects a mode (either --should-pass or --should-fail) followed by +# an input file. The script uses the following environment variables. The test C +# source file is expected to be named test.c in the directory containing the +# input file. +# +# CBMC: The command to run CBMC. Default: cbmc +# CBMC_FLAGS: Additional flags to pass to CBMC +# NR_CPUS: Number of cpus to run tests with. Default specified by the test +# SYNC_SRCU_MODE: Choose implementation of synchronize_srcu. Defaults to simple. +# kernel: Version included in the linux kernel source. +# simple: Use try_check_zero directly. +# +# The input file is a script that is sourced by this file. It can define any of +# the following variables to configure the test. +# +# test_cbmc_options: Extra options to pass to CBMC. +# min_cpus_fail: Minimum number of CPUs (NR_CPUS) for verification to fail. +# The test is expected to pass if it is run with fewer. (Only +# useful for .fail files) +# default_cpus: Quantity of CPUs to use for the test, if not specified on the +# command line. Default: Larger of 2 and MIN_CPUS_FAIL. + +set -e + +if test "$#" -ne 2; then + echo "Expected one option followed by an input file" 1>&2 + exit 99 +fi + +if test "x$1" = "x--should-pass"; then + should_pass="yes" +elif test "x$1" = "x--should-fail"; then + should_pass="no" +else + echo "Unrecognized argument '$1'" 1>&2 + + # Exit code 99 indicates a hard error. + exit 99 +fi + +CBMC=${CBMC:-cbmc} + +SYNC_SRCU_MODE=${SYNC_SRCU_MODE:-simple} + +case ${SYNC_SRCU_MODE} in +kernel) sync_srcu_mode_flags="" ;; +simple) sync_srcu_mode_flags="-DUSE_SIMPLE_SYNC_SRCU" ;; + +*) + echo "Unrecognized argument '${SYNC_SRCU_MODE}'" 1>&2 + exit 99 + ;; +esac + +min_cpus_fail=1 + +c_file=`dirname "$2"`/test.c + +# Source the input file. +. $2 + +if test ${min_cpus_fail} -gt 2; then + default_default_cpus=${min_cpus_fail} +else + default_default_cpus=2 +fi +default_cpus=${default_cpus:-${default_default_cpus}} +cpus=${NR_CPUS:-${default_cpus}} + +# Check if there are two few cpus to make the test fail. +if test $cpus -lt ${min_cpus_fail:-0}; then + should_pass="yes" +fi + +cbmc_opts="-DNR_CPUS=${cpus} ${sync_srcu_mode_flags} ${test_cbmc_options} ${CBMC_FLAGS}" + +echo "Running CBMC: ${CBMC} ${cbmc_opts} ${c_file}" +if ${CBMC} ${cbmc_opts} "${c_file}"; then + # Verification successful. Make sure that it was supposed to verify. + test "x${should_pass}" = xyes +else + cbmc_exit_status=$? + + # An exit status of 10 indicates a failed verification. + # (see cbmc_parse_optionst::do_bmc in the CBMC source code) + if test ${cbmc_exit_status} -eq 10 && test "x${should_pass}" = xno; then + : + else + echo "CBMC returned ${cbmc_exit_status} exit status" 1>&2 + + # Parse errors have exit status 6. Any other type of error + # should be considered a hard error. + if test ${cbmc_exit_status} -ne 6 && \ + test ${cbmc_exit_status} -ne 10; then + exit 99 + else + exit 1 + fi + fi +fi diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index fefd95043fd7..83d8b1c6cb0e 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -10,7 +10,7 @@ TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_sysc TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer -TARGETS_C_64BIT_ONLY := fsgsbase +TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY) diff --git a/tools/testing/selftests/x86/sysret_rip.c b/tools/testing/selftests/x86/sysret_rip.c new file mode 100644 index 000000000000..d85ec5b3671c --- /dev/null +++ b/tools/testing/selftests/x86/sysret_rip.c @@ -0,0 +1,195 @@ +/* + * sigreturn.c - tests that x86 avoids Intel SYSRET pitfalls + * Copyright (c) 2014-2016 Andrew Lutomirski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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 _GNU_SOURCE + +#include <stdlib.h> +#include <unistd.h> +#include <stdio.h> +#include <string.h> +#include <inttypes.h> +#include <sys/signal.h> +#include <sys/ucontext.h> +#include <sys/syscall.h> +#include <err.h> +#include <stddef.h> +#include <stdbool.h> +#include <setjmp.h> +#include <sys/user.h> +#include <sys/mman.h> +#include <assert.h> + + +asm ( + ".pushsection \".text\", \"ax\"\n\t" + ".balign 4096\n\t" + "test_page: .globl test_page\n\t" + ".fill 4094,1,0xcc\n\t" + "test_syscall_insn:\n\t" + "syscall\n\t" + ".ifne . - test_page - 4096\n\t" + ".error \"test page is not one page long\"\n\t" + ".endif\n\t" + ".popsection" + ); + +extern const char test_page[]; +static void const *current_test_page_addr = test_page; + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +/* State used by our signal handlers. */ +static gregset_t initial_regs; + +static volatile unsigned long rip; + +static void sigsegv_for_sigreturn_test(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + if (rip != ctx->uc_mcontext.gregs[REG_RIP]) { + printf("[FAIL]\tRequested RIP=0x%lx but got RIP=0x%lx\n", + rip, (unsigned long)ctx->uc_mcontext.gregs[REG_RIP]); + fflush(stdout); + _exit(1); + } + + memcpy(&ctx->uc_mcontext.gregs, &initial_regs, sizeof(gregset_t)); + + printf("[OK]\tGot SIGSEGV at RIP=0x%lx\n", rip); +} + +static void sigusr1(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t)); + + /* Set IP and CX to match so that SYSRET can happen. */ + ctx->uc_mcontext.gregs[REG_RIP] = rip; + ctx->uc_mcontext.gregs[REG_RCX] = rip; + + /* R11 and EFLAGS should already match. */ + assert(ctx->uc_mcontext.gregs[REG_EFL] == + ctx->uc_mcontext.gregs[REG_R11]); + + sethandler(SIGSEGV, sigsegv_for_sigreturn_test, SA_RESETHAND); + + return; +} + +static void test_sigreturn_to(unsigned long ip) +{ + rip = ip; + printf("[RUN]\tsigreturn to 0x%lx\n", ip); + raise(SIGUSR1); +} + +static jmp_buf jmpbuf; + +static void sigsegv_for_fallthrough(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + if (rip != ctx->uc_mcontext.gregs[REG_RIP]) { + printf("[FAIL]\tExpected SIGSEGV at 0x%lx but got RIP=0x%lx\n", + rip, (unsigned long)ctx->uc_mcontext.gregs[REG_RIP]); + fflush(stdout); + _exit(1); + } + + siglongjmp(jmpbuf, 1); +} + +static void test_syscall_fallthrough_to(unsigned long ip) +{ + void *new_address = (void *)(ip - 4096); + void *ret; + + printf("[RUN]\tTrying a SYSCALL that falls through to 0x%lx\n", ip); + + ret = mremap((void *)current_test_page_addr, 4096, 4096, + MREMAP_MAYMOVE | MREMAP_FIXED, new_address); + if (ret == MAP_FAILED) { + if (ip <= (1UL << 47) - PAGE_SIZE) { + err(1, "mremap to %p", new_address); + } else { + printf("[OK]\tmremap to %p failed\n", new_address); + return; + } + } + + if (ret != new_address) + errx(1, "mremap malfunctioned: asked for %p but got %p\n", + new_address, ret); + + current_test_page_addr = new_address; + rip = ip; + + if (sigsetjmp(jmpbuf, 1) == 0) { + asm volatile ("call *%[syscall_insn]" :: "a" (SYS_getpid), + [syscall_insn] "rm" (ip - 2)); + errx(1, "[FAIL]\tSyscall trampoline returned"); + } + + printf("[OK]\tWe survived\n"); +} + +int main() +{ + /* + * When the kernel returns from a slow-path syscall, it will + * detect whether SYSRET is appropriate. If it incorrectly + * thinks that SYSRET is appropriate when RIP is noncanonical, + * it'll crash on Intel CPUs. + */ + sethandler(SIGUSR1, sigusr1, 0); + for (int i = 47; i < 64; i++) + test_sigreturn_to(1UL<<i); + + clearhandler(SIGUSR1); + + sethandler(SIGSEGV, sigsegv_for_fallthrough, 0); + + /* One extra test to check that we didn't screw up the mremap logic. */ + test_syscall_fallthrough_to((1UL << 47) - 2*PAGE_SIZE); + + /* These are the interesting cases. */ + for (int i = 47; i < 64; i++) { + test_syscall_fallthrough_to((1UL<<i) - PAGE_SIZE); + test_syscall_fallthrough_to(1UL<<i); + } + + return 0; +} |
